From f41c7cab8727d99a2376450d233f128f23060b98 Mon Sep 17 00:00:00 2001
From: Kalle Valo <quic_kvalo@quicinc.com>
Date: Fri, 3 May 2024 13:34:36 +0300
Subject: [PATCH 001/950] wifi: ath11k: ath11k_mac_op_ipv6_changed(): use
 list_for_each_entry()

Simplify the loop by using list_for_each_entry(). No functional changes.

Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-03125-QCAHSPSWPL_V1_V2_SILICONZ_LITE-3.6510.37

Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Link: https://msgid.link/20240411165516.4070649-3-kvalo@kernel.org
---
 drivers/net/wireless/ath/ath11k/mac.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c
index 4f62e38ba48b3..a71195344288a 100644
--- a/drivers/net/wireless/ath/ath11k/mac.c
+++ b/drivers/net/wireless/ath/ath11k/mac.c
@@ -9104,7 +9104,6 @@ static void ath11k_mac_op_ipv6_changed(struct ieee80211_hw *hw,
 	struct ath11k_vif *arvif = ath11k_vif_to_arvif(vif);
 	struct inet6_ifaddr *ifa6;
 	struct ifacaddr6 *ifaca6;
-	struct list_head *p;
 	u32 count, scope;
 
 	ath11k_dbg(ar->ab, ATH11K_DBG_MAC, "op ipv6 changed\n");
@@ -9120,11 +9119,10 @@ static void ath11k_mac_op_ipv6_changed(struct ieee80211_hw *hw,
 	memcpy(offload->mac_addr, vif->addr, ETH_ALEN);
 
 	/* get unicast address */
-	list_for_each(p, &idev->addr_list) {
+	list_for_each_entry(ifa6, &idev->addr_list, if_list) {
 		if (count >= ATH11K_IPV6_MAX_COUNT)
 			goto generate;
 
-		ifa6 = list_entry(p, struct inet6_ifaddr, if_list);
 		if (ifa6->flags & IFA_F_DADFAILED)
 			continue;
 		scope = ipv6_addr_src_scope(&ifa6->addr);
-- 
GitLab


From ecd509b6f263e4f0d86876320c36260dc28bb53b Mon Sep 17 00:00:00 2001
From: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Date: Fri, 3 May 2024 13:34:36 +0300
Subject: [PATCH 002/950] wifi: ath12k: Refactor the hardware recovery
 procedure

Currently, in multi-wiphy models, the recovery handler access mac80211
HW from the radio/link structure. This will be incorrect for single wiphy
model, as they will hold multiple link/radio structures. To fix this,
access mac80211 HW based on the number of hardware in the SoC/chip. This
approach makes the recovery handler compatible with both multi wiphy and
single wiphy models.

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

Signed-off-by: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240425090307.3233434-2-quic_periyasa@quicinc.com
---
 drivers/net/wireless/ath/ath12k/core.c | 119 +++++++++++++------------
 drivers/net/wireless/ath/ath12k/mac.c  |  23 +++--
 2 files changed, 80 insertions(+), 62 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/core.c b/drivers/net/wireless/ath/ath12k/core.c
index 6663f4e1792de..ae14614c3568a 100644
--- a/drivers/net/wireless/ath/ath12k/core.c
+++ b/drivers/net/wireless/ath/ath12k/core.c
@@ -994,9 +994,8 @@ void ath12k_core_halt(struct ath12k *ar)
 static void ath12k_core_pre_reconfigure_recovery(struct ath12k_base *ab)
 {
 	struct ath12k *ar;
-	struct ath12k_pdev *pdev;
 	struct ath12k_hw *ah;
-	int i;
+	int i, j;
 
 	spin_lock_bh(&ab->base_lock);
 	ab->stats.fw_crash_counter++;
@@ -1006,35 +1005,34 @@ static void ath12k_core_pre_reconfigure_recovery(struct ath12k_base *ab)
 		set_bit(ATH12K_FLAG_CRASH_FLUSH, &ab->dev_flags);
 
 	for (i = 0; i < ab->num_hw; i++) {
-		if (!ab->ah[i])
+		ah = ab->ah[i];
+		if (!ah)
 			continue;
 
-		ah = ab->ah[i];
 		ieee80211_stop_queues(ah->hw);
-	}
 
-	for (i = 0; i < ab->num_radios; i++) {
-		pdev = &ab->pdevs[i];
-		ar = pdev->ar;
-		if (!ar || ar->state == ATH12K_STATE_OFF)
-			continue;
+		for (j = 0; j < ah->num_radio; j++) {
+			ar = &ah->radio[j];
+			if (ar->state == ATH12K_STATE_OFF)
+				continue;
 
-		ath12k_mac_drain_tx(ar);
-		complete(&ar->scan.started);
-		complete(&ar->scan.completed);
-		complete(&ar->scan.on_channel);
-		complete(&ar->peer_assoc_done);
-		complete(&ar->peer_delete_done);
-		complete(&ar->install_key_done);
-		complete(&ar->vdev_setup_done);
-		complete(&ar->vdev_delete_done);
-		complete(&ar->bss_survey_done);
-
-		wake_up(&ar->dp.tx_empty_waitq);
-		idr_for_each(&ar->txmgmt_idr,
-			     ath12k_mac_tx_mgmt_pending_free, ar);
-		idr_destroy(&ar->txmgmt_idr);
-		wake_up(&ar->txmgmt_empty_waitq);
+			ath12k_mac_drain_tx(ar);
+			complete(&ar->scan.started);
+			complete(&ar->scan.completed);
+			complete(&ar->scan.on_channel);
+			complete(&ar->peer_assoc_done);
+			complete(&ar->peer_delete_done);
+			complete(&ar->install_key_done);
+			complete(&ar->vdev_setup_done);
+			complete(&ar->vdev_delete_done);
+			complete(&ar->bss_survey_done);
+
+			wake_up(&ar->dp.tx_empty_waitq);
+			idr_for_each(&ar->txmgmt_idr,
+				     ath12k_mac_tx_mgmt_pending_free, ar);
+			idr_destroy(&ar->txmgmt_idr);
+			wake_up(&ar->txmgmt_empty_waitq);
+		}
 	}
 
 	wake_up(&ab->wmi_ab.tx_credits_wq);
@@ -1043,41 +1041,52 @@ static void ath12k_core_pre_reconfigure_recovery(struct ath12k_base *ab)
 
 static void ath12k_core_post_reconfigure_recovery(struct ath12k_base *ab)
 {
+	struct ath12k_hw *ah;
 	struct ath12k *ar;
-	struct ath12k_pdev *pdev;
-	int i;
+	int i, j;
+	u8 restart_count;
 
-	for (i = 0; i < ab->num_radios; i++) {
-		pdev = &ab->pdevs[i];
-		ar = pdev->ar;
-		if (!ar || ar->state == ATH12K_STATE_OFF)
+	for (i = 0; i < ab->num_hw; i++) {
+		ah = ab->ah[i];
+		if (!ah)
 			continue;
 
-		mutex_lock(&ar->conf_mutex);
-
-		switch (ar->state) {
-		case ATH12K_STATE_ON:
-			ar->state = ATH12K_STATE_RESTARTING;
-			ath12k_core_halt(ar);
-			ieee80211_restart_hw(ath12k_ar_to_hw(ar));
-			break;
-		case ATH12K_STATE_OFF:
-			ath12k_warn(ab,
-				    "cannot restart radio %d that hasn't been started\n",
-				    i);
-			break;
-		case ATH12K_STATE_RESTARTING:
-			break;
-		case ATH12K_STATE_RESTARTED:
-			ar->state = ATH12K_STATE_WEDGED;
-			fallthrough;
-		case ATH12K_STATE_WEDGED:
-			ath12k_warn(ab,
-				    "device is wedged, will not restart radio %d\n", i);
-			break;
+		for (j = 0, restart_count = 0; j < ah->num_radio; j++) {
+			ar = &ah->radio[j];
+			if (ar->state == ATH12K_STATE_OFF)
+				continue;
+
+			mutex_lock(&ar->conf_mutex);
+
+			switch (ar->state) {
+			case ATH12K_STATE_ON:
+				ar->state = ATH12K_STATE_RESTARTING;
+				ath12k_core_halt(ar);
+				restart_count++;
+				break;
+			case ATH12K_STATE_OFF:
+				ath12k_warn(ab,
+					    "cannot restart radio %d that hasn't been started\n",
+					    j);
+				break;
+			case ATH12K_STATE_RESTARTING:
+				break;
+			case ATH12K_STATE_RESTARTED:
+				ar->state = ATH12K_STATE_WEDGED;
+				fallthrough;
+			case ATH12K_STATE_WEDGED:
+				ath12k_warn(ab,
+					    "device is wedged, will not restart radio %d\n", j);
+				break;
+			}
+			mutex_unlock(&ar->conf_mutex);
 		}
-		mutex_unlock(&ar->conf_mutex);
+
+		/* Restart after all the link/radio got restart */
+		if (restart_count == ah->num_radio)
+			ieee80211_restart_hw(ah->hw);
 	}
+
 	complete(&ab->driver_recovery);
 }
 
diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index 805cb084484a4..6d19b6003aea2 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -7920,26 +7920,33 @@ ath12k_mac_op_reconfig_complete(struct ieee80211_hw *hw,
 	struct ath12k *ar;
 	struct ath12k_base *ab;
 	struct ath12k_vif *arvif;
-	int recovery_count;
+	int recovery_count, i;
 
 	if (reconfig_type != IEEE80211_RECONFIG_TYPE_RESTART)
 		return;
 
-	ar = ath12k_ah_to_ar(ah, 0);
-	ab = ar->ab;
+	for_each_ar(ah, ar, i) {
+		mutex_lock(&ar->conf_mutex);
 
-	mutex_lock(&ar->conf_mutex);
+		if (ar->state != ATH12K_STATE_RESTARTED) {
+			mutex_unlock(&ar->conf_mutex);
+			continue;
+		}
+
+		ab = ar->ab;
 
-	if (ar->state == ATH12K_STATE_RESTARTED) {
 		ath12k_warn(ar->ab, "pdev %d successfully recovered\n",
 			    ar->pdev->pdev_id);
+
 		ar->state = ATH12K_STATE_ON;
 		ieee80211_wake_queues(hw);
 
 		if (ab->is_reset) {
 			recovery_count = atomic_inc_return(&ab->recovery_count);
+
 			ath12k_dbg(ab, ATH12K_DBG_BOOT, "recovery count %d\n",
 				   recovery_count);
+
 			/* When there are multiple radios in an SOC,
 			 * the recovery has to be done for each radio
 			 */
@@ -7958,6 +7965,7 @@ ath12k_mac_op_reconfig_complete(struct ieee80211_hw *hw,
 				   arvif->key_cipher,
 				   arvif->is_up,
 				   arvif->vdev_type);
+
 			/* After trigger disconnect, then upper layer will
 			 * trigger connect again, then the PN number of
 			 * upper layer will be reset to keep up with AP
@@ -7967,13 +7975,14 @@ ath12k_mac_op_reconfig_complete(struct ieee80211_hw *hw,
 			    arvif->vdev_type == WMI_VDEV_TYPE_STA &&
 			    arvif->vdev_subtype == WMI_VDEV_SUBTYPE_NONE) {
 				ieee80211_hw_restart_disconnect(arvif->vif);
+
 				ath12k_dbg(ab, ATH12K_DBG_BOOT,
 					   "restart disconnect\n");
 			}
 		}
-	}
 
-	mutex_unlock(&ar->conf_mutex);
+		mutex_unlock(&ar->conf_mutex);
+	}
 }
 
 static void
-- 
GitLab


From 9b4e5caaf5905edb7c184e8d14a9fab09f2f865b Mon Sep 17 00:00:00 2001
From: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Date: Fri, 3 May 2024 13:34:37 +0300
Subject: [PATCH 003/950] wifi: ath12k: Refactor the hardware state

Currently, in multi wiphy models, the mac80211 hardware state is maintained
within the radio/link structure. However, in single wiphy models, the
mac80211 hardware state is needed at the hardware abstraction layer
(ath12k_hw). Therefore, move the hardware state from the radio/link
structure to the hardware abstraction layer (ath12k_hw). Additionally,
update the naming convention of the state enums to enhance clarity and
consistency.

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

Signed-off-by: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240425090307.3233434-3-quic_periyasa@quicinc.com
---
 drivers/net/wireless/ath/ath12k/core.c | 59 +++++++++++--------------
 drivers/net/wireless/ath/ath12k/core.h | 22 ++++++----
 drivers/net/wireless/ath/ath12k/mac.c  | 61 ++++++++++++++------------
 drivers/net/wireless/ath/ath12k/reg.c  | 19 ++++----
 4 files changed, 83 insertions(+), 78 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/core.c b/drivers/net/wireless/ath/ath12k/core.c
index ae14614c3568a..a685cfd6fd92f 100644
--- a/drivers/net/wireless/ath/ath12k/core.c
+++ b/drivers/net/wireless/ath/ath12k/core.c
@@ -1006,15 +1006,13 @@ static void ath12k_core_pre_reconfigure_recovery(struct ath12k_base *ab)
 
 	for (i = 0; i < ab->num_hw; i++) {
 		ah = ab->ah[i];
-		if (!ah)
+		if (!ah || ah->state == ATH12K_HW_STATE_OFF)
 			continue;
 
 		ieee80211_stop_queues(ah->hw);
 
 		for (j = 0; j < ah->num_radio; j++) {
 			ar = &ah->radio[j];
-			if (ar->state == ATH12K_STATE_OFF)
-				continue;
 
 			ath12k_mac_drain_tx(ar);
 			complete(&ar->scan.started);
@@ -1044,47 +1042,42 @@ static void ath12k_core_post_reconfigure_recovery(struct ath12k_base *ab)
 	struct ath12k_hw *ah;
 	struct ath12k *ar;
 	int i, j;
-	u8 restart_count;
 
 	for (i = 0; i < ab->num_hw; i++) {
 		ah = ab->ah[i];
-		if (!ah)
+		if (!ah || ah->state == ATH12K_HW_STATE_OFF)
 			continue;
 
-		for (j = 0, restart_count = 0; j < ah->num_radio; j++) {
-			ar = &ah->radio[j];
-			if (ar->state == ATH12K_STATE_OFF)
-				continue;
+		switch (ah->state) {
+		case ATH12K_HW_STATE_ON:
+			ah->state = ATH12K_HW_STATE_RESTARTING;
 
-			mutex_lock(&ar->conf_mutex);
+			for (j = 0; j < ah->num_radio; j++) {
+				ar = &ah->radio[j];
 
-			switch (ar->state) {
-			case ATH12K_STATE_ON:
-				ar->state = ATH12K_STATE_RESTARTING;
+				mutex_lock(&ar->conf_mutex);
 				ath12k_core_halt(ar);
-				restart_count++;
-				break;
-			case ATH12K_STATE_OFF:
-				ath12k_warn(ab,
-					    "cannot restart radio %d that hasn't been started\n",
-					    j);
-				break;
-			case ATH12K_STATE_RESTARTING:
-				break;
-			case ATH12K_STATE_RESTARTED:
-				ar->state = ATH12K_STATE_WEDGED;
-				fallthrough;
-			case ATH12K_STATE_WEDGED:
-				ath12k_warn(ab,
-					    "device is wedged, will not restart radio %d\n", j);
-				break;
+				mutex_unlock(&ar->conf_mutex);
 			}
-			mutex_unlock(&ar->conf_mutex);
-		}
 
-		/* Restart after all the link/radio got restart */
-		if (restart_count == ah->num_radio)
+			/* Restart after all the link/radio halt */
 			ieee80211_restart_hw(ah->hw);
+			break;
+		case ATH12K_HW_STATE_OFF:
+			ath12k_warn(ab,
+				    "cannot restart hw %d that hasn't been started\n",
+				    i);
+			break;
+		case ATH12K_HW_STATE_RESTARTING:
+			break;
+		case ATH12K_HW_STATE_RESTARTED:
+			ah->state = ATH12K_HW_STATE_WEDGED;
+			fallthrough;
+		case ATH12K_HW_STATE_WEDGED:
+			ath12k_warn(ab,
+				    "device is wedged, will not restart hw %d\n", i);
+			break;
+		}
 	}
 
 	complete(&ab->driver_recovery);
diff --git a/drivers/net/wireless/ath/ath12k/core.h b/drivers/net/wireless/ath/ath12k/core.h
index 47dde44012100..c4eb8b25398c0 100644
--- a/drivers/net/wireless/ath/ath12k/core.h
+++ b/drivers/net/wireless/ath/ath12k/core.h
@@ -457,12 +457,12 @@ struct ath12k_sta {
 #define ATH12K_NUM_CHANS 100
 #define ATH12K_MAX_5G_CHAN 173
 
-enum ath12k_state {
-	ATH12K_STATE_OFF,
-	ATH12K_STATE_ON,
-	ATH12K_STATE_RESTARTING,
-	ATH12K_STATE_RESTARTED,
-	ATH12K_STATE_WEDGED,
+enum ath12k_hw_state {
+	ATH12K_HW_STATE_OFF,
+	ATH12K_HW_STATE_ON,
+	ATH12K_HW_STATE_RESTARTING,
+	ATH12K_HW_STATE_RESTARTED,
+	ATH12K_HW_STATE_WEDGED,
 	/* Add other states as required */
 };
 
@@ -511,7 +511,6 @@ struct ath12k {
 	u32 ht_cap_info;
 	u32 vht_cap_info;
 	struct ath12k_he ar_he;
-	enum ath12k_state state;
 	bool supports_6ghz;
 	struct {
 		struct completion started;
@@ -636,10 +635,12 @@ struct ath12k {
 
 struct ath12k_hw {
 	struct ieee80211_hw *hw;
+	struct ath12k_base *ab;
+	enum ath12k_hw_state state;
 	bool regd_updated;
 	bool use_6ghz_regd;
-
 	u8 num_radio;
+
 	struct ath12k radio[] __aligned(sizeof(void *));
 };
 
@@ -1037,6 +1038,11 @@ static inline struct ath12k *ath12k_ah_to_ar(struct ath12k_hw *ah, u8 hw_link_id
 	return &ah->radio[hw_link_id];
 }
 
+static inline struct ath12k_hw *ath12k_ar_to_ah(struct ath12k *ar)
+{
+	return ar->ah;
+}
+
 static inline struct ieee80211_hw *ath12k_ar_to_hw(struct ath12k *ar)
 {
 	return ar->ah->hw;
diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index 6d19b6003aea2..0cb2e0435cc06 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -5269,6 +5269,7 @@ static void ath12k_mac_setup_sband_iftype_data(struct ath12k *ar,
 
 static int __ath12k_set_antenna(struct ath12k *ar, u32 tx_ant, u32 rx_ant)
 {
+	struct ath12k_hw *ah = ath12k_ar_to_ah(ar);
 	int ret;
 
 	lockdep_assert_held(&ar->conf_mutex);
@@ -5289,8 +5290,8 @@ static int __ath12k_set_antenna(struct ath12k *ar, u32 tx_ant, u32 rx_ant)
 	ar->cfg_tx_chainmask = tx_ant;
 	ar->cfg_rx_chainmask = rx_ant;
 
-	if (ar->state != ATH12K_STATE_ON &&
-	    ar->state != ATH12K_STATE_RESTARTED)
+	if (ah->state != ATH12K_HW_STATE_ON &&
+	    ah->state != ATH12K_HW_STATE_RESTARTED)
 		return 0;
 
 	ret = ath12k_wmi_pdev_set_param(ar, WMI_PDEV_PARAM_TX_CHAIN_MASK,
@@ -5620,22 +5621,6 @@ static int ath12k_mac_start(struct ath12k *ar)
 
 	mutex_lock(&ar->conf_mutex);
 
-	switch (ar->state) {
-	case ATH12K_STATE_OFF:
-		ar->state = ATH12K_STATE_ON;
-		break;
-	case ATH12K_STATE_RESTARTING:
-		ar->state = ATH12K_STATE_RESTARTED;
-		ath12k_mac_wait_reconfigure(ab);
-		break;
-	case ATH12K_STATE_RESTARTED:
-	case ATH12K_STATE_WEDGED:
-	case ATH12K_STATE_ON:
-		WARN_ON(1);
-		ret = -EINVAL;
-		goto err;
-	}
-
 	ret = ath12k_wmi_pdev_set_param(ar, WMI_PDEV_PARAM_PMF_QOS,
 					1, pdev->pdev_id);
 
@@ -5726,7 +5711,6 @@ static int ath12k_mac_start(struct ath12k *ar)
 
 	return 0;
 err:
-	ar->state = ATH12K_STATE_OFF;
 	mutex_unlock(&ar->conf_mutex);
 
 	return ret;
@@ -5749,9 +5733,28 @@ static int ath12k_mac_op_start(struct ieee80211_hw *hw)
 
 	ath12k_drain_tx(ah);
 
+	switch (ah->state) {
+	case ATH12K_HW_STATE_OFF:
+		ah->state = ATH12K_HW_STATE_ON;
+		break;
+	case ATH12K_HW_STATE_RESTARTING:
+		ah->state = ATH12K_HW_STATE_RESTARTED;
+		ath12k_mac_wait_reconfigure(ah->ab);
+		break;
+	case ATH12K_HW_STATE_RESTARTED:
+	case ATH12K_HW_STATE_WEDGED:
+	case ATH12K_HW_STATE_ON:
+		ah->state = ATH12K_HW_STATE_OFF;
+
+		WARN_ON(1);
+		return -EINVAL;
+	}
+
 	for_each_ar(ah, ar, i) {
 		ret = ath12k_mac_start(ar);
 		if (ret) {
+			ah->state = ATH12K_HW_STATE_OFF;
+
 			ath12k_err(ar->ab, "fail to start mac operations in pdev idx %d ret %d\n",
 				   ar->pdev_idx, ret);
 			goto fail_start;
@@ -5759,11 +5762,13 @@ static int ath12k_mac_op_start(struct ieee80211_hw *hw)
 	}
 
 	return 0;
+
 fail_start:
 	for (; i > 0; i--) {
 		ar = ath12k_ah_to_ar(ah, i - 1);
 		ath12k_mac_stop(ar);
 	}
+
 	return ret;
 }
 
@@ -5836,7 +5841,6 @@ static void ath12k_mac_stop(struct ath12k *ar)
 			   ret);
 
 	clear_bit(ATH12K_CAC_RUNNING, &ar->dev_flags);
-	ar->state = ATH12K_STATE_OFF;
 	mutex_unlock(&ar->conf_mutex);
 
 	cancel_delayed_work_sync(&ar->scan.timeout);
@@ -5865,6 +5869,8 @@ static void ath12k_mac_op_stop(struct ieee80211_hw *hw)
 
 	ath12k_drain_tx(ah);
 
+	ah->state = ATH12K_HW_STATE_OFF;
+
 	for_each_ar(ah, ar, i)
 		ath12k_mac_stop(ar);
 }
@@ -7925,22 +7931,20 @@ ath12k_mac_op_reconfig_complete(struct ieee80211_hw *hw,
 	if (reconfig_type != IEEE80211_RECONFIG_TYPE_RESTART)
 		return;
 
+	if (ah->state != ATH12K_HW_STATE_RESTARTED)
+		return;
+
+	ah->state = ATH12K_HW_STATE_ON;
+	ieee80211_wake_queues(hw);
+
 	for_each_ar(ah, ar, i) {
 		mutex_lock(&ar->conf_mutex);
 
-		if (ar->state != ATH12K_STATE_RESTARTED) {
-			mutex_unlock(&ar->conf_mutex);
-			continue;
-		}
-
 		ab = ar->ab;
 
 		ath12k_warn(ar->ab, "pdev %d successfully recovered\n",
 			    ar->pdev->pdev_id);
 
-		ar->state = ATH12K_STATE_ON;
-		ieee80211_wake_queues(hw);
-
 		if (ab->is_reset) {
 			recovery_count = atomic_inc_return(&ab->recovery_count);
 
@@ -8926,6 +8930,7 @@ static struct ath12k_hw *ath12k_mac_hw_allocate(struct ath12k_base *ab,
 
 	ah = ath12k_hw_to_ah(hw);
 	ah->hw = hw;
+	ah->ab = ab;
 	ah->num_radio = num_pdev_map;
 
 	for (i = 0; i < num_pdev_map; i++) {
diff --git a/drivers/net/wireless/ath/ath12k/reg.c b/drivers/net/wireless/ath/ath12k/reg.c
index fbf38044938c6..439d61f284d89 100644
--- a/drivers/net/wireless/ath/ath12k/reg.c
+++ b/drivers/net/wireless/ath/ath12k/reg.c
@@ -206,9 +206,9 @@ static void ath12k_copy_regd(struct ieee80211_regdomain *regd_orig,
 
 int ath12k_regd_update(struct ath12k *ar, bool init)
 {
-	struct ieee80211_hw *hw = ath12k_ar_to_hw(ar);
+	struct ath12k_hw *ah = ath12k_ar_to_ah(ar);
+	struct ieee80211_hw *hw = ah->hw;
 	struct ieee80211_regdomain *regd, *regd_copy = NULL;
-	struct ath12k_hw *ah = ar->ah;
 	int ret, regd_len, pdev_id;
 	struct ath12k_base *ab;
 	int i;
@@ -286,19 +286,20 @@ int ath12k_regd_update(struct ath12k *ar, bool init)
 	if (ret)
 		goto err;
 
+	if (ah->state != ATH12K_HW_STATE_ON)
+		goto skip;
+
 	ah->regd_updated = true;
 	/* Apply the new regd to all the radios, this is expected to be received only once
 	 * since we check for ah->regd_updated and allow here only once.
 	 */
 	for_each_ar(ah, ar, i) {
-		if (ar->state == ATH12K_STATE_ON) {
-			ab = ar->ab;
-			ret = ath12k_reg_update_chan_list(ar);
-			if (ret)
-				goto err;
-		}
+		ab = ar->ab;
+		ret = ath12k_reg_update_chan_list(ar);
+		if (ret)
+			goto err;
 	}
-
+skip:
 	return 0;
 err:
 	ath12k_warn(ab, "failed to perform regd update : %d\n", ret);
-- 
GitLab


From acaa84009fade2ae80922861aa9464e89c9d3ef0 Mon Sep 17 00:00:00 2001
From: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Date: Fri, 3 May 2024 13:34:37 +0300
Subject: [PATCH 004/950] wifi: ath12k: Add lock to protect the hardware state

Currently, hardware state is not protected across the reconfigure
operations. However, in single wiphy models, multiple radio/links is
exposed as a MAC hardware (ieee80211_hw) through the driver hardware
abstraction (ath12k_hw) layer. In such scenario, we need to protect
hardware state across the multiple radio/link at the driver hardware
abstraction (ath12k_hw) layer. Therefore, introduce a new mutex in
the ath12k_hw layer.

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

Signed-off-by: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240425090307.3233434-4-quic_periyasa@quicinc.com
---
 drivers/net/wireless/ath/ath12k/core.c |  4 ++++
 drivers/net/wireless/ath/ath12k/core.h |  6 ++++++
 drivers/net/wireless/ath/ath12k/mac.c  | 16 ++++++++++++++++
 3 files changed, 26 insertions(+)

diff --git a/drivers/net/wireless/ath/ath12k/core.c b/drivers/net/wireless/ath/ath12k/core.c
index a685cfd6fd92f..e9aabdb9341c3 100644
--- a/drivers/net/wireless/ath/ath12k/core.c
+++ b/drivers/net/wireless/ath/ath12k/core.c
@@ -1048,6 +1048,8 @@ static void ath12k_core_post_reconfigure_recovery(struct ath12k_base *ab)
 		if (!ah || ah->state == ATH12K_HW_STATE_OFF)
 			continue;
 
+		mutex_lock(&ah->hw_mutex);
+
 		switch (ah->state) {
 		case ATH12K_HW_STATE_ON:
 			ah->state = ATH12K_HW_STATE_RESTARTING;
@@ -1078,6 +1080,8 @@ static void ath12k_core_post_reconfigure_recovery(struct ath12k_base *ab)
 				    "device is wedged, will not restart hw %d\n", i);
 			break;
 		}
+
+		mutex_unlock(&ah->hw_mutex);
 	}
 
 	complete(&ab->driver_recovery);
diff --git a/drivers/net/wireless/ath/ath12k/core.h b/drivers/net/wireless/ath/ath12k/core.h
index c4eb8b25398c0..d833361948b73 100644
--- a/drivers/net/wireless/ath/ath12k/core.h
+++ b/drivers/net/wireless/ath/ath12k/core.h
@@ -636,11 +636,17 @@ struct ath12k {
 struct ath12k_hw {
 	struct ieee80211_hw *hw;
 	struct ath12k_base *ab;
+
+	/* Protect the write operation of the hardware state ath12k_hw::state
+	 * between hardware start<=>reconfigure<=>stop transitions.
+	 */
+	struct mutex hw_mutex;
 	enum ath12k_hw_state state;
 	bool regd_updated;
 	bool use_6ghz_regd;
 	u8 num_radio;
 
+	/* Keep last */
 	struct ath12k radio[] __aligned(sizeof(void *));
 };
 
diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index 0cb2e0435cc06..4f07ac8c0287c 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -5615,10 +5615,13 @@ static void ath12k_mac_wait_reconfigure(struct ath12k_base *ab)
 
 static int ath12k_mac_start(struct ath12k *ar)
 {
+	struct ath12k_hw *ah = ar->ah;
 	struct ath12k_base *ab = ar->ab;
 	struct ath12k_pdev *pdev = ar->pdev;
 	int ret;
 
+	lockdep_assert_held(&ah->hw_mutex);
+
 	mutex_lock(&ar->conf_mutex);
 
 	ret = ath12k_wmi_pdev_set_param(ar, WMI_PDEV_PARAM_PMF_QOS,
@@ -5733,6 +5736,8 @@ static int ath12k_mac_op_start(struct ieee80211_hw *hw)
 
 	ath12k_drain_tx(ah);
 
+	guard(mutex)(&ah->hw_mutex);
+
 	switch (ah->state) {
 	case ATH12K_HW_STATE_OFF:
 		ah->state = ATH12K_HW_STATE_ON;
@@ -5831,9 +5836,12 @@ int ath12k_mac_rfkill_enable_radio(struct ath12k *ar, bool enable)
 
 static void ath12k_mac_stop(struct ath12k *ar)
 {
+	struct ath12k_hw *ah = ar->ah;
 	struct htt_ppdu_stats_info *ppdu_stats, *tmp;
 	int ret;
 
+	lockdep_assert_held(&ah->hw_mutex);
+
 	mutex_lock(&ar->conf_mutex);
 	ret = ath12k_mac_config_mon_status_default(ar, false);
 	if (ret && (ret != -EOPNOTSUPP))
@@ -5869,10 +5877,14 @@ static void ath12k_mac_op_stop(struct ieee80211_hw *hw)
 
 	ath12k_drain_tx(ah);
 
+	mutex_lock(&ah->hw_mutex);
+
 	ah->state = ATH12K_HW_STATE_OFF;
 
 	for_each_ar(ah, ar, i)
 		ath12k_mac_stop(ar);
+
+	mutex_unlock(&ah->hw_mutex);
 }
 
 static u8
@@ -7931,6 +7943,8 @@ ath12k_mac_op_reconfig_complete(struct ieee80211_hw *hw,
 	if (reconfig_type != IEEE80211_RECONFIG_TYPE_RESTART)
 		return;
 
+	guard(mutex)(&ah->hw_mutex);
+
 	if (ah->state != ATH12K_HW_STATE_RESTARTED)
 		return;
 
@@ -8933,6 +8947,8 @@ static struct ath12k_hw *ath12k_mac_hw_allocate(struct ath12k_base *ab,
 	ah->ab = ab;
 	ah->num_radio = num_pdev_map;
 
+	mutex_init(&ah->hw_mutex);
+
 	for (i = 0; i < num_pdev_map; i++) {
 		ab = pdev_map[i].ab;
 		pdev_idx = pdev_map[i].pdev_idx;
-- 
GitLab


From 8b9ea752a9d67b0b668b38e7efa34fffba8b5331 Mon Sep 17 00:00:00 2001
From: Jeff Johnson <quic_jjohnson@quicinc.com>
Date: Fri, 3 May 2024 13:34:37 +0300
Subject: [PATCH 005/950] wifi: ath11k: refactor CE remap & unmap

Currently the logic that handles hw_params->ce_remap is inline code,
both for doing the remap and the unmap. An upcoming change needs to do
the unmap in a second place, so refactor the unmap logic into a
separate function. And although it is only called from one place,
refactor the remap logic as well to have functional symmetry.

No functional changes, compile tested only.

Signed-off-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240430-ce-unmap-v1-1-e468328f95d9@quicinc.com
---
 drivers/net/wireless/ath/ath11k/ahb.c | 52 +++++++++++++++++----------
 1 file changed, 34 insertions(+), 18 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/ahb.c b/drivers/net/wireless/ath/ath11k/ahb.c
index ca0f17ddebbaa..88dfef71c2b59 100644
--- a/drivers/net/wireless/ath/ath11k/ahb.c
+++ b/drivers/net/wireless/ath/ath11k/ahb.c
@@ -954,6 +954,36 @@ static int ath11k_ahb_setup_msa_resources(struct ath11k_base *ab)
 	return 0;
 }
 
+static int ath11k_ahb_ce_remap(struct ath11k_base *ab)
+{
+	const struct ce_remap *ce_remap = ab->hw_params.ce_remap;
+	struct platform_device *pdev = ab->pdev;
+
+	if (!ce_remap) {
+		/* no separate CE register space */
+		ab->mem_ce = ab->mem;
+		return 0;
+	}
+
+	/* ce register space is moved out of wcss unlike ipq8074 or ipq6018
+	 * and the space is not contiguous, hence remapping the CE registers
+	 * to a new space for accessing them.
+	 */
+	ab->mem_ce = ioremap(ce_remap->base, ce_remap->size);
+	if (!ab->mem_ce) {
+		dev_err(&pdev->dev, "ce ioremap error\n");
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void ath11k_ahb_ce_unmap(struct ath11k_base *ab)
+{
+	if (ab->hw_params.ce_remap)
+		iounmap(ab->mem_ce);
+}
+
 static int ath11k_ahb_fw_resources_init(struct ath11k_base *ab)
 {
 	struct ath11k_ahb *ab_ahb = ath11k_ahb_priv(ab);
@@ -1146,21 +1176,9 @@ static int ath11k_ahb_probe(struct platform_device *pdev)
 	if (ret)
 		goto err_core_free;
 
-	ab->mem_ce = ab->mem;
-
-	if (ab->hw_params.ce_remap) {
-		const struct ce_remap *ce_remap = ab->hw_params.ce_remap;
-		/* ce register space is moved out of wcss unlike ipq8074 or ipq6018
-		 * and the space is not contiguous, hence remapping the CE registers
-		 * to a new space for accessing them.
-		 */
-		ab->mem_ce = ioremap(ce_remap->base, ce_remap->size);
-		if (!ab->mem_ce) {
-			dev_err(&pdev->dev, "ce ioremap error\n");
-			ret = -ENOMEM;
-			goto err_core_free;
-		}
-	}
+	ret = ath11k_ahb_ce_remap(ab);
+	if (ret)
+		goto err_core_free;
 
 	ret = ath11k_ahb_fw_resources_init(ab);
 	if (ret)
@@ -1248,9 +1266,7 @@ static void ath11k_ahb_free_resources(struct ath11k_base *ab)
 	ath11k_ahb_release_smp2p_handle(ab);
 	ath11k_ahb_fw_resource_deinit(ab);
 	ath11k_ce_free_pipes(ab);
-
-	if (ab->hw_params.ce_remap)
-		iounmap(ab->mem_ce);
+	ath11k_ahb_ce_unmap(ab);
 
 	ath11k_core_free(ab);
 	platform_set_drvdata(pdev, NULL);
-- 
GitLab


From c57d00a4d3d80a6af376bf37527c93654afadc02 Mon Sep 17 00:00:00 2001
From: Jeff Johnson <quic_jjohnson@quicinc.com>
Date: Fri, 3 May 2024 13:34:38 +0300
Subject: [PATCH 006/950] wifi: ath11k: unmap the CE in ath11k_ahb_probe()
 error path

Currently, in ath11k_ahb_probe(), if a failure occurs after
ath11k_ahb_ce_remap() is called, and if hw_params->ce_remap is
enabled, the CE register memory is not unmapped. So add a call to
ath11k_ahb_ce_unmap() in the error path.

This issue was identified by smatch/smatch_scripts/kchecker:

drivers/net/wireless/ath/ath11k/ahb.c:1218 ath11k_ahb_probe() warn: 'ab->mem_ce' from ioremap() not released on lines: 1218.

Since this is a rare error path with no simple way to test, and since
the change is trivial to review, compile tested only.

Signed-off-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240430-ce-unmap-v1-2-e468328f95d9@quicinc.com
---
 drivers/net/wireless/ath/ath11k/ahb.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath11k/ahb.c b/drivers/net/wireless/ath/ath11k/ahb.c
index 88dfef71c2b59..e3ff4786c714d 100644
--- a/drivers/net/wireless/ath/ath11k/ahb.c
+++ b/drivers/net/wireless/ath/ath11k/ahb.c
@@ -1182,7 +1182,7 @@ static int ath11k_ahb_probe(struct platform_device *pdev)
 
 	ret = ath11k_ahb_fw_resources_init(ab);
 	if (ret)
-		goto err_core_free;
+		goto err_ce_unmap;
 
 	ret = ath11k_ahb_setup_smp2p_handle(ab);
 	if (ret)
@@ -1234,6 +1234,9 @@ err_release_smp2p_handle:
 err_fw_deinit:
 	ath11k_ahb_fw_resource_deinit(ab);
 
+err_ce_unmap:
+	ath11k_ahb_ce_unmap(ab);
+
 err_core_free:
 	ath11k_core_free(ab);
 	platform_set_drvdata(pdev, NULL);
-- 
GitLab


From 5f6c3a418b401187c36536dae235beaf322dc7fc Mon Sep 17 00:00:00 2001
From: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Date: Fri, 3 May 2024 13:34:38 +0300
Subject: [PATCH 007/950] wifi: ath12k: Replace "chip" with "device" in hal Rx
 return buffer manager

Prefer the term "device" over "chip". Therefore, modify the relevant terms
in hal Rx return buffer manager to use "device" instead.

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

Signed-off-by: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240430165811.1377182-2-quic_periyasa@quicinc.com
---
 drivers/net/wireless/ath/ath12k/dp_rx.c |  4 ++--
 drivers/net/wireless/ath/ath12k/hal.h   | 18 +++++++++---------
 2 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/dp_rx.c b/drivers/net/wireless/ath/ath12k/dp_rx.c
index 75df622f25d85..fc4b953249552 100644
--- a/drivers/net/wireless/ath/ath12k/dp_rx.c
+++ b/drivers/net/wireless/ath/ath12k/dp_rx.c
@@ -3071,7 +3071,7 @@ static int ath12k_dp_rx_h_defrag_reo_reinject(struct ath12k *ar,
 
 	ath12k_hal_rx_buf_addr_info_set(&reo_ent_ring->buf_addr_info, link_paddr,
 					cookie,
-					HAL_RX_BUF_RBM_WBM_CHIP0_IDLE_DESC_LIST);
+					HAL_RX_BUF_RBM_WBM_DEV0_IDLE_DESC_LIST);
 
 	mpdu_info = u32_encode_bits(1, RX_MPDU_DESC_INFO0_MSDU_COUNT) |
 		    u32_encode_bits(0, RX_MPDU_DESC_INFO0_FRAG_FLAG) |
@@ -3451,7 +3451,7 @@ int ath12k_dp_rx_process_err(struct ath12k_base *ab, struct napi_struct *napi,
 			       (paddr - link_desc_banks[desc_bank].paddr);
 		ath12k_hal_rx_msdu_link_info_get(link_desc_va, &num_msdus, msdu_cookies,
 						 &rbm);
-		if (rbm != HAL_RX_BUF_RBM_WBM_CHIP0_IDLE_DESC_LIST &&
+		if (rbm != HAL_RX_BUF_RBM_WBM_DEV0_IDLE_DESC_LIST &&
 		    rbm != HAL_RX_BUF_RBM_SW3_BM &&
 		    rbm != ab->hw_params->hal_params->rx_buf_rbm) {
 			ab->soc_stats.invalid_rbm++;
diff --git a/drivers/net/wireless/ath/ath12k/hal.h b/drivers/net/wireless/ath/ath12k/hal.h
index dbb9205bfa10d..f364b2938ef85 100644
--- a/drivers/net/wireless/ath/ath12k/hal.h
+++ b/drivers/net/wireless/ath/ath12k/hal.h
@@ -770,12 +770,12 @@ struct hal_srng_config {
  * enum hal_rx_buf_return_buf_manager - manager for returned rx buffers
  *
  * @HAL_RX_BUF_RBM_WBM_IDLE_BUF_LIST: Buffer returned to WBM idle buffer list
- * @HAL_RX_BUF_RBM_WBM_CHIP0_IDLE_DESC_LIST: Descriptor returned to WBM idle
- *	descriptor list, where the chip 0 WBM is chosen in case of a multi-chip config
- * @HAL_RX_BUF_RBM_WBM_CHIP1_IDLE_DESC_LIST: Descriptor returned to WBM idle
- *	descriptor list, where the chip 1 WBM is chosen in case of a multi-chip config
- * @HAL_RX_BUF_RBM_WBM_CHIP2_IDLE_DESC_LIST: Descriptor returned to WBM idle
- *	descriptor list, where the chip 2 WBM is chosen in case of a multi-chip config
+ * @HAL_RX_BUF_RBM_WBM_DEV0_IDLE_DESC_LIST: Descriptor returned to WBM idle
+ *	descriptor list, where the device 0 WBM is chosen in case of a multi-device config
+ * @HAL_RX_BUF_RBM_WBM_DEV1_IDLE_DESC_LIST: Descriptor returned to WBM idle
+ *	descriptor list, where the device 1 WBM is chosen in case of a multi-device config
+ * @HAL_RX_BUF_RBM_WBM_DEV2_IDLE_DESC_LIST: Descriptor returned to WBM idle
+ *	descriptor list, where the device 2 WBM is chosen in case of a multi-device config
  * @HAL_RX_BUF_RBM_FW_BM: Buffer returned to FW
  * @HAL_RX_BUF_RBM_SW0_BM: For ring 0 -- returned to host
  * @HAL_RX_BUF_RBM_SW1_BM: For ring 1 -- returned to host
@@ -788,9 +788,9 @@ struct hal_srng_config {
 
 enum hal_rx_buf_return_buf_manager {
 	HAL_RX_BUF_RBM_WBM_IDLE_BUF_LIST,
-	HAL_RX_BUF_RBM_WBM_CHIP0_IDLE_DESC_LIST,
-	HAL_RX_BUF_RBM_WBM_CHIP1_IDLE_DESC_LIST,
-	HAL_RX_BUF_RBM_WBM_CHIP2_IDLE_DESC_LIST,
+	HAL_RX_BUF_RBM_WBM_DEV0_IDLE_DESC_LIST,
+	HAL_RX_BUF_RBM_WBM_DEV1_IDLE_DESC_LIST,
+	HAL_RX_BUF_RBM_WBM_DEV2_IDLE_DESC_LIST,
 	HAL_RX_BUF_RBM_FW_BM,
 	HAL_RX_BUF_RBM_SW0_BM,
 	HAL_RX_BUF_RBM_SW1_BM,
-- 
GitLab


From acc6afb31c3f999076d998f2d1678c0899f0bfb1 Mon Sep 17 00:00:00 2001
From: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Date: Fri, 3 May 2024 13:34:38 +0300
Subject: [PATCH 008/950] wifi: ath12k: Refactor idle ring descriptor setup

Currently, the WBM idle ring descriptor setup uses implicit value
HAL_RX_BUF_RBM_WBM_DEV0_IDLE_DESC_LIST for the return buffer manager
parameter. To support inter-device MLO (Multi-link operation), this
parameter needs to be configure dynamically based on the device identifier
within the MLO group. Therefore, introduce a new argument to the helper
function ath12k_hal_set_link_desc_addr().

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

Signed-off-by: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240430165811.1377182-3-quic_periyasa@quicinc.com
---
 drivers/net/wireless/ath/ath12k/dp.c    | 9 ++++++---
 drivers/net/wireless/ath/ath12k/dp.h    | 1 +
 drivers/net/wireless/ath/ath12k/dp_rx.c | 5 +++--
 drivers/net/wireless/ath/ath12k/hal.c   | 5 +++--
 drivers/net/wireless/ath/ath12k/hal.h   | 3 ++-
 5 files changed, 15 insertions(+), 8 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/dp.c b/drivers/net/wireless/ath/ath12k/dp.c
index 7843c76a82c17..f41b3f9dac3d5 100644
--- a/drivers/net/wireless/ath/ath12k/dp.c
+++ b/drivers/net/wireless/ath/ath12k/dp.c
@@ -616,6 +616,7 @@ static int ath12k_dp_scatter_idle_link_desc_setup(struct ath12k_base *ab,
 	int i;
 	int ret = 0;
 	u32 end_offset, cookie;
+	enum hal_rx_buf_return_buf_manager rbm = dp->idle_link_rbm;
 
 	n_entries_per_buf = HAL_WBM_IDLE_SCATTER_BUF_SIZE /
 		ath12k_hal_srng_get_entrysize(ab, HAL_WBM_IDLE_LINK);
@@ -646,7 +647,8 @@ static int ath12k_dp_scatter_idle_link_desc_setup(struct ath12k_base *ab,
 		paddr = link_desc_banks[i].paddr;
 		while (n_entries) {
 			cookie = DP_LINK_DESC_COOKIE_SET(n_entries, i);
-			ath12k_hal_set_link_desc_addr(scatter_buf, cookie, paddr);
+			ath12k_hal_set_link_desc_addr(scatter_buf, cookie,
+						      paddr, rbm);
 			n_entries--;
 			paddr += HAL_LINK_DESC_SIZE;
 			if (rem_entries) {
@@ -790,6 +792,7 @@ int ath12k_dp_link_desc_setup(struct ath12k_base *ab,
 	u32 paddr;
 	int i, ret;
 	u32 cookie;
+	enum hal_rx_buf_return_buf_manager rbm = ab->dp.idle_link_rbm;
 
 	tot_mem_sz = n_link_desc * HAL_LINK_DESC_SIZE;
 	tot_mem_sz += HAL_LINK_DESC_ALIGN;
@@ -850,8 +853,7 @@ int ath12k_dp_link_desc_setup(struct ath12k_base *ab,
 		while (n_entries &&
 		       (desc = ath12k_hal_srng_src_get_next_entry(ab, srng))) {
 			cookie = DP_LINK_DESC_COOKIE_SET(n_entries, i);
-			ath12k_hal_set_link_desc_addr(desc,
-						      cookie, paddr);
+			ath12k_hal_set_link_desc_addr(desc, cookie, paddr, rbm);
 			n_entries--;
 			paddr += HAL_LINK_DESC_SIZE;
 		}
@@ -1603,6 +1605,7 @@ int ath12k_dp_alloc(struct ath12k_base *ab)
 	spin_lock_init(&dp->reo_cmd_lock);
 
 	dp->reo_cmd_cache_flush_count = 0;
+	dp->idle_link_rbm = HAL_RX_BUF_RBM_WBM_DEV0_IDLE_DESC_LIST;
 
 	ret = ath12k_wbm_idle_ring_setup(ab, &n_link_desc);
 	if (ret) {
diff --git a/drivers/net/wireless/ath/ath12k/dp.h b/drivers/net/wireless/ath/ath12k/dp.h
index 5cf0d21ef184b..e9880b34a7abe 100644
--- a/drivers/net/wireless/ath/ath12k/dp.h
+++ b/drivers/net/wireless/ath/ath12k/dp.h
@@ -325,6 +325,7 @@ struct ath12k_dp {
 	u8 htt_tgt_ver_major;
 	u8 htt_tgt_ver_minor;
 	struct dp_link_desc_bank link_desc_banks[DP_LINK_DESC_BANKS_MAX];
+	enum hal_rx_buf_return_buf_manager idle_link_rbm;
 	struct dp_srng wbm_idle_ring;
 	struct dp_srng wbm_desc_rel_ring;
 	struct dp_srng tcl_cmd_ring;
diff --git a/drivers/net/wireless/ath/ath12k/dp_rx.c b/drivers/net/wireless/ath/ath12k/dp_rx.c
index fc4b953249552..18030c9e735d4 100644
--- a/drivers/net/wireless/ath/ath12k/dp_rx.c
+++ b/drivers/net/wireless/ath/ath12k/dp_rx.c
@@ -2994,6 +2994,7 @@ static int ath12k_dp_rx_h_defrag_reo_reinject(struct ath12k *ar,
 	u32 cookie, hal_rx_desc_sz, dest_ring_info0;
 	int ret;
 	struct ath12k_rx_desc_info *desc_info;
+	enum hal_rx_buf_return_buf_manager idle_link_rbm = dp->idle_link_rbm;
 	u8 dst_ind;
 
 	hal_rx_desc_sz = ab->hal.hal_desc_sz;
@@ -3071,7 +3072,7 @@ static int ath12k_dp_rx_h_defrag_reo_reinject(struct ath12k *ar,
 
 	ath12k_hal_rx_buf_addr_info_set(&reo_ent_ring->buf_addr_info, link_paddr,
 					cookie,
-					HAL_RX_BUF_RBM_WBM_DEV0_IDLE_DESC_LIST);
+					idle_link_rbm);
 
 	mpdu_info = u32_encode_bits(1, RX_MPDU_DESC_INFO0_MSDU_COUNT) |
 		    u32_encode_bits(0, RX_MPDU_DESC_INFO0_FRAG_FLAG) |
@@ -3451,7 +3452,7 @@ int ath12k_dp_rx_process_err(struct ath12k_base *ab, struct napi_struct *napi,
 			       (paddr - link_desc_banks[desc_bank].paddr);
 		ath12k_hal_rx_msdu_link_info_get(link_desc_va, &num_msdus, msdu_cookies,
 						 &rbm);
-		if (rbm != HAL_RX_BUF_RBM_WBM_DEV0_IDLE_DESC_LIST &&
+		if (rbm != dp->idle_link_rbm &&
 		    rbm != HAL_RX_BUF_RBM_SW3_BM &&
 		    rbm != ab->hw_params->hal_params->rx_buf_rbm) {
 			ab->soc_stats.invalid_rbm++;
diff --git a/drivers/net/wireless/ath/ath12k/hal.c b/drivers/net/wireless/ath/ath12k/hal.c
index 78310da8cfe8e..ca04bfae8bdcc 100644
--- a/drivers/net/wireless/ath/ath12k/hal.c
+++ b/drivers/net/wireless/ath/ath12k/hal.c
@@ -1969,14 +1969,15 @@ u32 ath12k_hal_ce_dst_status_get_length(struct hal_ce_srng_dst_status_desc *desc
 }
 
 void ath12k_hal_set_link_desc_addr(struct hal_wbm_link_desc *desc, u32 cookie,
-				   dma_addr_t paddr)
+				   dma_addr_t paddr,
+				   enum hal_rx_buf_return_buf_manager rbm)
 {
 	desc->buf_addr_info.info0 = le32_encode_bits((paddr & HAL_ADDR_LSB_REG_MASK),
 						     BUFFER_ADDR_INFO0_ADDR);
 	desc->buf_addr_info.info1 =
 			le32_encode_bits(((u64)paddr >> HAL_ADDR_MSB_REG_SHIFT),
 					 BUFFER_ADDR_INFO1_ADDR) |
-			le32_encode_bits(1, BUFFER_ADDR_INFO1_RET_BUF_MGR) |
+			le32_encode_bits(rbm, BUFFER_ADDR_INFO1_RET_BUF_MGR) |
 			le32_encode_bits(cookie, BUFFER_ADDR_INFO1_SW_COOKIE);
 }
 
diff --git a/drivers/net/wireless/ath/ath12k/hal.h b/drivers/net/wireless/ath/ath12k/hal.h
index f364b2938ef85..8a78bb9a10bc1 100644
--- a/drivers/net/wireless/ath/ath12k/hal.h
+++ b/drivers/net/wireless/ath/ath12k/hal.h
@@ -1113,7 +1113,8 @@ dma_addr_t ath12k_hal_srng_get_tp_addr(struct ath12k_base *ab,
 dma_addr_t ath12k_hal_srng_get_hp_addr(struct ath12k_base *ab,
 				       struct hal_srng *srng);
 void ath12k_hal_set_link_desc_addr(struct hal_wbm_link_desc *desc, u32 cookie,
-				   dma_addr_t paddr);
+				   dma_addr_t paddr,
+				   enum hal_rx_buf_return_buf_manager rbm);
 u32 ath12k_hal_ce_get_desc_size(enum hal_ce_desc type);
 void ath12k_hal_ce_src_set_desc(struct hal_ce_srng_src_desc *desc, dma_addr_t paddr,
 				u32 len, u32 id, u8 byte_swap_data);
-- 
GitLab


From b2d54ca73a5a177490f3f1ee2d23ff6ab6045b25 Mon Sep 17 00:00:00 2001
From: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Date: Fri, 3 May 2024 13:34:38 +0300
Subject: [PATCH 009/950] wifi: ath12k: Introduce device index

Introduce a device index parameter in the ath12k_base structure. This
value is used as unique identifier for devices involved in Inter-device
MLO. It is also used to configure the MLO parameter within the QMI host
capability send request. While currently set to zero, future logic will
be added for inter device support to populate this parameter with
non-zero values.

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

Signed-off-by: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240430165811.1377182-4-quic_periyasa@quicinc.com
---
 drivers/net/wireless/ath/ath12k/core.c | 10 ++++++++++
 drivers/net/wireless/ath/ath12k/core.h |  1 +
 drivers/net/wireless/ath/ath12k/qmi.c  |  4 ++--
 3 files changed, 13 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/core.c b/drivers/net/wireless/ath/ath12k/core.c
index e9aabdb9341c3..9482d5db71e77 100644
--- a/drivers/net/wireless/ath/ath12k/core.c
+++ b/drivers/net/wireless/ath/ath12k/core.c
@@ -1268,6 +1268,16 @@ struct ath12k_base *ath12k_core_alloc(struct device *dev, size_t priv_size,
 	ab->qmi.num_radios = U8_MAX;
 	ab->mlo_capable_flags = ATH12K_INTRA_DEVICE_MLO_SUPPORT;
 
+	/* Device index used to identify the devices in a group.
+	 *
+	 * In Intra-device MLO, only one device present in a group,
+	 * so it is always zero.
+	 *
+	 * In Inter-device MLO, Multiple device present in a group,
+	 * expect non-zero value.
+	 */
+	ab->device_id = 0;
+
 	return ab;
 
 err_free_wq:
diff --git a/drivers/net/wireless/ath/ath12k/core.h b/drivers/net/wireless/ath/ath12k/core.h
index d833361948b73..3cfc65b365797 100644
--- a/drivers/net/wireless/ath/ath12k/core.h
+++ b/drivers/net/wireless/ath/ath12k/core.h
@@ -754,6 +754,7 @@ struct ath12k_base {
 	struct ath12k_qmi qmi;
 	struct ath12k_wmi_base wmi_ab;
 	struct completion fw_ready;
+	u8 device_id;
 	int num_radios;
 	/* HW channel counters frequency value in hertz common to all MACs */
 	u32 cc_freq_hz;
diff --git a/drivers/net/wireless/ath/ath12k/qmi.c b/drivers/net/wireless/ath/ath12k/qmi.c
index 5484112859a66..3bb730326a024 100644
--- a/drivers/net/wireless/ath/ath12k/qmi.c
+++ b/drivers/net/wireless/ath/ath12k/qmi.c
@@ -2041,7 +2041,7 @@ static void ath12k_host_cap_parse_mlo(struct ath12k_base *ab,
 	req->mlo_capable_valid = 1;
 	req->mlo_capable = 1;
 	req->mlo_chip_id_valid = 1;
-	req->mlo_chip_id = 0;
+	req->mlo_chip_id = ab->device_id;
 	req->mlo_group_id_valid = 1;
 	req->mlo_group_id = 0;
 	req->max_mlo_peer_valid = 1;
@@ -2053,7 +2053,7 @@ static void ath12k_host_cap_parse_mlo(struct ath12k_base *ab,
 	req->mlo_num_chips = 1;
 
 	info = &req->mlo_chip_info[0];
-	info->chip_id = 0;
+	info->chip_id = ab->device_id;
 	info->num_local_links = ab->qmi.num_radios;
 
 	for (i = 0; i < info->num_local_links; i++) {
-- 
GitLab


From 53bf4a14f8c55e84d200f8328fde39ab6bdf1bf5 Mon Sep 17 00:00:00 2001
From: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Date: Fri, 3 May 2024 13:34:39 +0300
Subject: [PATCH 010/950] wifi: ath12k: add multi device support for WBM idle
 ring buffer setup

Currently, inter device MLO is not supported. Therefore, the WBM idle ring
buffers choose the implicit return buffer manager (DEV0_IDLE_DESC_LIST).
However, this implicit return buffer manager design is not meeting the
requirements to support inter device MLO. In inter device MLO, multiple
devices participate. The device specific WBM idle ring buffers transmit
to multiple device REO rings. To distinguish between device specific WBM
idle buffers, the setup configuration need to choose a different return
buffer manager based on the unique identifier (device index).

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

Signed-off-by: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240430165811.1377182-5-quic_periyasa@quicinc.com
---
 drivers/net/wireless/ath/ath12k/dp.c | 20 +++++++++++++++++++-
 1 file changed, 19 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath12k/dp.c b/drivers/net/wireless/ath/ath12k/dp.c
index f41b3f9dac3d5..72ea9baaf8d70 100644
--- a/drivers/net/wireless/ath/ath12k/dp.c
+++ b/drivers/net/wireless/ath/ath12k/dp.c
@@ -1589,6 +1589,24 @@ static int ath12k_dp_reoq_lut_setup(struct ath12k_base *ab)
 	return 0;
 }
 
+static enum hal_rx_buf_return_buf_manager
+ath12k_dp_get_idle_link_rbm(struct ath12k_base *ab)
+{
+	switch (ab->device_id) {
+	case 0:
+		return HAL_RX_BUF_RBM_WBM_DEV0_IDLE_DESC_LIST;
+	case 1:
+		return HAL_RX_BUF_RBM_WBM_DEV1_IDLE_DESC_LIST;
+	case 2:
+		return HAL_RX_BUF_RBM_WBM_DEV2_IDLE_DESC_LIST;
+	default:
+		ath12k_warn(ab, "invalid %d device id, so choose default rbm\n",
+			    ab->device_id);
+		WARN_ON(1);
+		return HAL_RX_BUF_RBM_WBM_DEV0_IDLE_DESC_LIST;
+	}
+}
+
 int ath12k_dp_alloc(struct ath12k_base *ab)
 {
 	struct ath12k_dp *dp = &ab->dp;
@@ -1605,7 +1623,7 @@ int ath12k_dp_alloc(struct ath12k_base *ab)
 	spin_lock_init(&dp->reo_cmd_lock);
 
 	dp->reo_cmd_cache_flush_count = 0;
-	dp->idle_link_rbm = HAL_RX_BUF_RBM_WBM_DEV0_IDLE_DESC_LIST;
+	dp->idle_link_rbm = ath12k_dp_get_idle_link_rbm(ab);
 
 	ret = ath12k_wbm_idle_ring_setup(ab, &n_link_desc);
 	if (ret) {
-- 
GitLab


From 5453bbd6fef4ca2fea3b4b338fc715d7135afc6f Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Fri, 3 May 2024 13:34:39 +0300
Subject: [PATCH 011/950] wifi: ath12k: Don't drop tx_status in failure case

When a station idles for a long time, hostapd will try to send
a QoS Null frame to the station as "poll". NL80211_CMD_PROBE_CLIENT
is used for this purpose.
And the skb will be added to ack_status_frame - waiting for a
completion via ieee80211_report_ack_skb().

But when the peer was already removed before the tx_complete arrives,
the peer will be missing. And when using dev_kfree_skb_any (instead
of going through mac80211), the entry will stay inside
ack_status_frames thus not clean up related information in its
internal data structures. This IDR will therefore run full after
8K request were generated for such clients.
At this point, the access point will then just stall and not allow
any new clients because idr_alloc() for ack_status_frame will fail.

ieee80211_free_txskb() on the other hand will (when required) call
ieee80211_report_ack_skb() and make sure that (when required) remove
the entry from the ack_status_frame and clean up related
information in its internal data structures.

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

Fixes: d889913205cf ("wifi: ath12k: driver for Qualcomm Wi-Fi 7 devices")
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Sarika Sharma <quic_sarishar@quicinc.com>
Signed-off-by: Karthikeyan Kathirvel <quic_kathirve@quicinc.com>
Link: https://lore.kernel.org/r/20230802-ath11k-ack_status_leak-v2-1-c0af729d6229@narfation.org
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240430074313.885807-2-quic_kathirve@quicinc.com
---
 drivers/net/wireless/ath/ath12k/dp_tx.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/dp_tx.c b/drivers/net/wireless/ath/ath12k/dp_tx.c
index 9b6d7d72f57c4..81a85d5946f5a 100644
--- a/drivers/net/wireless/ath/ath12k/dp_tx.c
+++ b/drivers/net/wireless/ath/ath12k/dp_tx.c
@@ -352,15 +352,15 @@ static void ath12k_dp_tx_free_txbuf(struct ath12k_base *ab,
 	u8 pdev_id = ath12k_hw_mac_id_to_pdev_id(ab->hw_params, mac_id);
 
 	skb_cb = ATH12K_SKB_CB(msdu);
+	ar = ab->pdevs[pdev_id].ar;
 
 	dma_unmap_single(ab->dev, skb_cb->paddr, msdu->len, DMA_TO_DEVICE);
 	if (skb_cb->paddr_ext_desc)
 		dma_unmap_single(ab->dev, skb_cb->paddr_ext_desc,
 				 sizeof(struct hal_tx_msdu_ext_desc), DMA_TO_DEVICE);
 
-	dev_kfree_skb_any(msdu);
+	ieee80211_free_txskb(ar->ah->hw, msdu);
 
-	ar = ab->pdevs[pdev_id].ar;
 	if (atomic_dec_and_test(&ar->dp.num_tx_pending))
 		wake_up(&ar->dp.tx_empty_waitq);
 }
@@ -448,6 +448,7 @@ static void ath12k_dp_tx_complete_msdu(struct ath12k *ar,
 				       struct hal_tx_status *ts)
 {
 	struct ath12k_base *ab = ar->ab;
+	struct ath12k_hw *ah = ar->ah;
 	struct ieee80211_tx_info *info;
 	struct ath12k_skb_cb *skb_cb;
 
@@ -466,12 +467,12 @@ static void ath12k_dp_tx_complete_msdu(struct ath12k *ar,
 	rcu_read_lock();
 
 	if (!rcu_dereference(ab->pdevs_active[ar->pdev_idx])) {
-		dev_kfree_skb_any(msdu);
+		ieee80211_free_txskb(ah->hw, msdu);
 		goto exit;
 	}
 
 	if (!skb_cb->vif) {
-		dev_kfree_skb_any(msdu);
+		ieee80211_free_txskb(ah->hw, msdu);
 		goto exit;
 	}
 
-- 
GitLab


From 50971dc6694c0845fcddfe337ea39c5b723d5a92 Mon Sep 17 00:00:00 2001
From: Karthikeyan Kathirvel <quic_kathirve@quicinc.com>
Date: Fri, 3 May 2024 13:34:39 +0300
Subject: [PATCH 012/950] wifi: ath12k: drop failed transmitted frames from
 metric calculation.

In mesh node traffic, internal firmware-transmitted failures are
reported as transmitted failures in mesh metric calculation, leading
to the breakage of the mesh link.

Fix the issue by dropping the internal firmware-transmitted failures
before updating the TX completion status to mac80211, in order to
prevent false failure averaging in mesh metric calculation.

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

Fixes: d889913205cf ("wifi: ath12k: driver for Qualcomm Wi-Fi 7 devices")
Signed-off-by: Karthikeyan Kathirvel <quic_kathirve@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240430074313.885807-3-quic_kathirve@quicinc.com
---
 drivers/net/wireless/ath/ath12k/dp_tx.c    | 38 ++++++++++++++++------
 drivers/net/wireless/ath/ath12k/hal_desc.h | 22 ++++++++++++-
 2 files changed, 49 insertions(+), 11 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/dp_tx.c b/drivers/net/wireless/ath/ath12k/dp_tx.c
index 81a85d5946f5a..a7c7a868c14ce 100644
--- a/drivers/net/wireless/ath/ath12k/dp_tx.c
+++ b/drivers/net/wireless/ath/ath12k/dp_tx.c
@@ -482,18 +482,36 @@ static void ath12k_dp_tx_complete_msdu(struct ath12k *ar,
 	/* skip tx rate update from ieee80211_status*/
 	info->status.rates[0].idx = -1;
 
-	if (ts->status == HAL_WBM_TQM_REL_REASON_FRAME_ACKED &&
-	    !(info->flags & IEEE80211_TX_CTL_NO_ACK)) {
-		info->flags |= IEEE80211_TX_STAT_ACK;
-		info->status.ack_signal = ATH12K_DEFAULT_NOISE_FLOOR +
-					  ts->ack_rssi;
-		info->status.flags = IEEE80211_TX_STATUS_ACK_SIGNAL_VALID;
+	switch (ts->status) {
+	case HAL_WBM_TQM_REL_REASON_FRAME_ACKED:
+		if (!(info->flags & IEEE80211_TX_CTL_NO_ACK)) {
+			info->flags |= IEEE80211_TX_STAT_ACK;
+			info->status.ack_signal = ATH12K_DEFAULT_NOISE_FLOOR +
+						  ts->ack_rssi;
+			info->status.flags = IEEE80211_TX_STATUS_ACK_SIGNAL_VALID;
+		}
+		break;
+	case HAL_WBM_TQM_REL_REASON_CMD_REMOVE_TX:
+		if (info->flags & IEEE80211_TX_CTL_NO_ACK) {
+			info->flags |= IEEE80211_TX_STAT_NOACK_TRANSMITTED;
+			break;
+		}
+		fallthrough;
+	case HAL_WBM_TQM_REL_REASON_CMD_REMOVE_MPDU:
+	case HAL_WBM_TQM_REL_REASON_DROP_THRESHOLD:
+	case HAL_WBM_TQM_REL_REASON_CMD_REMOVE_AGED_FRAMES:
+		/* The failure status is due to internal firmware tx failure
+		 * hence drop the frame; do not update the status of frame to
+		 * the upper layer
+		 */
+		ieee80211_free_txskb(ah->hw, msdu);
+		goto exit;
+	default:
+		ath12k_dbg(ab, ATH12K_DBG_DP_TX, "tx frame is not acked status %d\n",
+			   ts->status);
+		break;
 	}
 
-	if (ts->status == HAL_WBM_TQM_REL_REASON_CMD_REMOVE_TX &&
-	    (info->flags & IEEE80211_TX_CTL_NO_ACK))
-		info->flags |= IEEE80211_TX_STAT_NOACK_TRANSMITTED;
-
 	/* NOTE: Tx rate status reporting. Tx completion status does not have
 	 * necessary information (for example nss) to build the tx rate.
 	 * Might end up reporting it out-of-band from HTT stats.
diff --git a/drivers/net/wireless/ath/ath12k/hal_desc.h b/drivers/net/wireless/ath/ath12k/hal_desc.h
index 63340256d3f64..814c02f876d64 100644
--- a/drivers/net/wireless/ath/ath12k/hal_desc.h
+++ b/drivers/net/wireless/ath/ath12k/hal_desc.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2022, 2024 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 #include "core.h"
 
@@ -2048,6 +2048,19 @@ struct hal_wbm_release_ring {
  *	fw with fw_reason2.
  * @HAL_WBM_TQM_REL_REASON_CMD_REMOVE_RESEAON3: Remove command initiated by
  *	fw with fw_reason3.
+ * @HAL_WBM_TQM_REL_REASON_CMD_DISABLE_QUEUE: Remove command initiated by
+ *	fw with disable queue.
+ * @HAL_WBM_TQM_REL_REASON_CMD_TILL_NONMATCHING: Remove command initiated by
+ *	fw to remove all mpdu until 1st non-match.
+ * @HAL_WBM_TQM_REL_REASON_DROP_THRESHOLD: Dropped due to drop threshold
+ *	criteria
+ * @HAL_WBM_TQM_REL_REASON_DROP_LINK_DESC_UNAVAIL: Dropped due to link desc
+ *	not available
+ * @HAL_WBM_TQM_REL_REASON_DROP_OR_INVALID_MSDU: Dropped due drop bit set or
+ *	null flow
+ * @HAL_WBM_TQM_REL_REASON_MULTICAST_DROP: Dropped due mcast drop set for VDEV
+ * @HAL_WBM_TQM_REL_REASON_VDEV_MISMATCH_DROP: Dropped due to being set with
+ *	'TCL_drop_reason'
  */
 enum hal_wbm_tqm_rel_reason {
 	HAL_WBM_TQM_REL_REASON_FRAME_ACKED,
@@ -2058,6 +2071,13 @@ enum hal_wbm_tqm_rel_reason {
 	HAL_WBM_TQM_REL_REASON_CMD_REMOVE_RESEAON1,
 	HAL_WBM_TQM_REL_REASON_CMD_REMOVE_RESEAON2,
 	HAL_WBM_TQM_REL_REASON_CMD_REMOVE_RESEAON3,
+	HAL_WBM_TQM_REL_REASON_CMD_DISABLE_QUEUE,
+	HAL_WBM_TQM_REL_REASON_CMD_TILL_NONMATCHING,
+	HAL_WBM_TQM_REL_REASON_DROP_THRESHOLD,
+	HAL_WBM_TQM_REL_REASON_DROP_LINK_DESC_UNAVAIL,
+	HAL_WBM_TQM_REL_REASON_DROP_OR_INVALID_MSDU,
+	HAL_WBM_TQM_REL_REASON_MULTICAST_DROP,
+	HAL_WBM_TQM_REL_REASON_VDEV_MISMATCH_DROP,
 };
 
 struct hal_wbm_buffer_ring {
-- 
GitLab


From 4c2b796be3a12a11ab611917fafdabc9d3862a1d Mon Sep 17 00:00:00 2001
From: Venkateswara Naralasetty <quic_vnaralas@quicinc.com>
Date: Fri, 3 May 2024 16:24:16 +0300
Subject: [PATCH 013/950] wifi: ath11k: skip status ring entry processing

If STATUS_BUFFER_DONE is not set for a monitor status ring entry,
we don't process the status ring until STATUS_BUFFER_DONE set
for that status ring entry.

During LMAC reset it may happen that hardware will not write
STATUS_BUFFER_DONE tlv in status buffer, in that case we end up
waiting for STATUS_BUFFER_DONE leading to backpressure on monitor
status ring.

To fix the issue, when HP (Head Pointer) + 1 entry is peeked and if DMA is not
done and if HP + 2 entry's DMA done is set, replenish HP + 1 entry and start
processing in next interrupt. If HP + 2 entry's DMA done is not set, poll onto
HP + 1 entry DMA done to be set.

Also, during monitor attach HP points to the end of the ring and TP (Tail
Pointer) points to the start of the ring.  Using ath11k_hal_srng_src_peek() may
result in processing invalid buffer for the very first interrupt. Since, HW
starts writing buffer from TP.

To avoid this issue call ath11k_hal_srng_src_next_peek() instead of
calling ath11k_hal_srng_src_peek().

Tested-on: IPQ5018 hw1.0 AHB WLAN.HK.2.6.0.1-00861-QCAHKSWPL_SILICONZ-1

Signed-off-by: Venkateswara Naralasetty <quic_vnaralas@quicinc.com>
Co-developed-by: Tamizh Chelvam Raja <quic_tamizhr@quicinc.com>
Signed-off-by: Tamizh Chelvam Raja <quic_tamizhr@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240429073624.736147-1-quic_tamizhr@quicinc.com
---
 drivers/net/wireless/ath/ath11k/dp_rx.c | 82 ++++++++++++++++++++++---
 drivers/net/wireless/ath/ath11k/hal.c   | 16 ++++-
 drivers/net/wireless/ath/ath11k/hal.h   |  2 +
 3 files changed, 90 insertions(+), 10 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/dp_rx.c b/drivers/net/wireless/ath/ath11k/dp_rx.c
index afd481f5858f0..8a860a17d7e48 100644
--- a/drivers/net/wireless/ath/ath11k/dp_rx.c
+++ b/drivers/net/wireless/ath/ath11k/dp_rx.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <linux/ieee80211.h>
@@ -2990,11 +2990,52 @@ ath11k_dp_rx_mon_update_status_buf_state(struct ath11k_mon_data *pmon,
 	}
 }
 
+static enum dp_mon_status_buf_state
+ath11k_dp_rx_mon_buf_done(struct ath11k_base *ab, struct hal_srng *srng,
+			  struct dp_rxdma_ring *rx_ring)
+{
+	struct ath11k_skb_rxcb *rxcb;
+	struct hal_tlv_hdr *tlv;
+	struct sk_buff *skb;
+	void *status_desc;
+	dma_addr_t paddr;
+	u32 cookie;
+	int buf_id;
+	u8 rbm;
+
+	status_desc = ath11k_hal_srng_src_next_peek(ab, srng);
+	if (!status_desc)
+		return DP_MON_STATUS_NO_DMA;
+
+	ath11k_hal_rx_buf_addr_info_get(status_desc, &paddr, &cookie, &rbm);
+
+	buf_id = FIELD_GET(DP_RXDMA_BUF_COOKIE_BUF_ID, cookie);
+
+	spin_lock_bh(&rx_ring->idr_lock);
+	skb = idr_find(&rx_ring->bufs_idr, buf_id);
+	spin_unlock_bh(&rx_ring->idr_lock);
+
+	if (!skb)
+		return DP_MON_STATUS_NO_DMA;
+
+	rxcb = ATH11K_SKB_RXCB(skb);
+	dma_sync_single_for_cpu(ab->dev, rxcb->paddr,
+				skb->len + skb_tailroom(skb),
+				DMA_FROM_DEVICE);
+
+	tlv = (struct hal_tlv_hdr *)skb->data;
+	if (FIELD_GET(HAL_TLV_HDR_TAG, tlv->tl) != HAL_RX_STATUS_BUFFER_DONE)
+		return DP_MON_STATUS_NO_DMA;
+
+	return DP_MON_STATUS_REPLINISH;
+}
+
 static int ath11k_dp_rx_reap_mon_status_ring(struct ath11k_base *ab, int mac_id,
 					     int *budget, struct sk_buff_head *skb_list)
 {
 	struct ath11k *ar;
 	const struct ath11k_hw_hal_params *hal_params;
+	enum dp_mon_status_buf_state reap_status;
 	struct ath11k_pdev_dp *dp;
 	struct dp_rxdma_ring *rx_ring;
 	struct ath11k_mon_data *pmon;
@@ -3057,15 +3098,38 @@ static int ath11k_dp_rx_reap_mon_status_ring(struct ath11k_base *ab, int mac_id,
 				ath11k_warn(ab, "mon status DONE not set %lx, buf_id %d\n",
 					    FIELD_GET(HAL_TLV_HDR_TAG,
 						      tlv->tl), buf_id);
-				/* If done status is missing, hold onto status
-				 * ring until status is done for this status
-				 * ring buffer.
-				 * Keep HP in mon_status_ring unchanged,
-				 * and break from here.
-				 * Check status for same buffer for next time
+				/* RxDMA status done bit might not be set even
+				 * though tp is moved by HW.
 				 */
-				pmon->buf_state = DP_MON_STATUS_NO_DMA;
-				break;
+
+				/* If done status is missing:
+				 * 1. As per MAC team's suggestion,
+				 *    when HP + 1 entry is peeked and if DMA
+				 *    is not done and if HP + 2 entry's DMA done
+				 *    is set. skip HP + 1 entry and
+				 *    start processing in next interrupt.
+				 * 2. If HP + 2 entry's DMA done is not set,
+				 *    poll onto HP + 1 entry DMA done to be set.
+				 *    Check status for same buffer for next time
+				 *    dp_rx_mon_status_srng_process
+				 */
+
+				reap_status = ath11k_dp_rx_mon_buf_done(ab, srng,
+									rx_ring);
+				if (reap_status == DP_MON_STATUS_NO_DMA)
+					continue;
+
+				spin_lock_bh(&rx_ring->idr_lock);
+				idr_remove(&rx_ring->bufs_idr, buf_id);
+				spin_unlock_bh(&rx_ring->idr_lock);
+
+				dma_unmap_single(ab->dev, rxcb->paddr,
+						 skb->len + skb_tailroom(skb),
+						 DMA_FROM_DEVICE);
+
+				dev_kfree_skb_any(skb);
+				pmon->buf_state = DP_MON_STATUS_REPLINISH;
+				goto move_next;
 			}
 
 			spin_lock_bh(&rx_ring->idr_lock);
diff --git a/drivers/net/wireless/ath/ath11k/hal.c b/drivers/net/wireless/ath/ath11k/hal.c
index f3d04568c221b..f02599bd1c36b 100644
--- a/drivers/net/wireless/ath/ath11k/hal.c
+++ b/drivers/net/wireless/ath/ath11k/hal.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 #include <linux/dma-mapping.h>
 #include "hal_tx.h"
@@ -796,6 +796,20 @@ u32 *ath11k_hal_srng_src_get_next_reaped(struct ath11k_base *ab,
 	return desc;
 }
 
+u32 *ath11k_hal_srng_src_next_peek(struct ath11k_base *ab, struct hal_srng *srng)
+{
+	u32 next_hp;
+
+	lockdep_assert_held(&srng->lock);
+
+	next_hp = (srng->u.src_ring.hp + srng->entry_size) % srng->ring_size;
+
+	if (next_hp != srng->u.src_ring.cached_tp)
+		return srng->ring_base_vaddr + next_hp;
+
+	return NULL;
+}
+
 u32 *ath11k_hal_srng_src_peek(struct ath11k_base *ab, struct hal_srng *srng)
 {
 	lockdep_assert_held(&srng->lock);
diff --git a/drivers/net/wireless/ath/ath11k/hal.h b/drivers/net/wireless/ath/ath11k/hal.h
index e453c137385e5..dc8bbe0730170 100644
--- a/drivers/net/wireless/ath/ath11k/hal.h
+++ b/drivers/net/wireless/ath/ath11k/hal.h
@@ -947,6 +947,8 @@ u32 *ath11k_hal_srng_dst_peek(struct ath11k_base *ab, struct hal_srng *srng);
 int ath11k_hal_srng_dst_num_free(struct ath11k_base *ab, struct hal_srng *srng,
 				 bool sync_hw_ptr);
 u32 *ath11k_hal_srng_src_peek(struct ath11k_base *ab, struct hal_srng *srng);
+u32 *ath11k_hal_srng_src_next_peek(struct ath11k_base *ab,
+				   struct hal_srng *srng);
 u32 *ath11k_hal_srng_src_get_next_reaped(struct ath11k_base *ab,
 					 struct hal_srng *srng);
 u32 *ath11k_hal_srng_src_reap_next(struct ath11k_base *ab,
-- 
GitLab


From 10d2b4f4aa0b9a1ac55d2313d2c682add25e31c6 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Fri, 3 May 2024 03:32:56 -0700
Subject: [PATCH 014/950] wifi: wil6210: Do not use embedded netdev in
 wil6210_priv

Embedding net_device into structures prohibits the usage of flexible
arrays in the net_device structure. For more details, see the discussion
at [1].

Un-embed the net_device from struct wil6210_priv by converting it
into a pointer. Then use the leverage alloc_netdev_dummy() to allocate
the net_device object at wil_if_add(). The free of the device
occurs at wil_if_remove().

Link: https://lore.kernel.org/all/20240229225910.79e224cf@kernel.org/ [1]
Signed-off-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240503103304.339489-1-leitao@debian.org
---
 drivers/net/wireless/ath/wil6210/netdev.c  | 21 +++++++++++++++------
 drivers/net/wireless/ath/wil6210/wil6210.h |  2 +-
 2 files changed, 16 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wireless/ath/wil6210/netdev.c b/drivers/net/wireless/ath/wil6210/netdev.c
index ee7d7e9c27184..d5d364683c0e9 100644
--- a/drivers/net/wireless/ath/wil6210/netdev.c
+++ b/drivers/net/wireless/ath/wil6210/netdev.c
@@ -453,16 +453,21 @@ int wil_if_add(struct wil6210_priv *wil)
 		return rc;
 	}
 
-	init_dummy_netdev(&wil->napi_ndev);
+	wil->napi_ndev = alloc_netdev_dummy(0);
+	if (!wil->napi_ndev) {
+		wil_err(wil, "failed to allocate dummy netdev");
+		rc = -ENOMEM;
+		goto out_wiphy;
+	}
 	if (wil->use_enhanced_dma_hw) {
-		netif_napi_add(&wil->napi_ndev, &wil->napi_rx,
+		netif_napi_add(wil->napi_ndev, &wil->napi_rx,
 			       wil6210_netdev_poll_rx_edma);
-		netif_napi_add_tx(&wil->napi_ndev,
+		netif_napi_add_tx(wil->napi_ndev,
 				  &wil->napi_tx, wil6210_netdev_poll_tx_edma);
 	} else {
-		netif_napi_add(&wil->napi_ndev, &wil->napi_rx,
+		netif_napi_add(wil->napi_ndev, &wil->napi_rx,
 			       wil6210_netdev_poll_rx);
-		netif_napi_add_tx(&wil->napi_ndev,
+		netif_napi_add_tx(wil->napi_ndev,
 				  &wil->napi_tx, wil6210_netdev_poll_tx);
 	}
 
@@ -474,10 +479,12 @@ int wil_if_add(struct wil6210_priv *wil)
 	wiphy_unlock(wiphy);
 	rtnl_unlock();
 	if (rc < 0)
-		goto out_wiphy;
+		goto free_dummy;
 
 	return 0;
 
+free_dummy:
+	free_netdev(wil->napi_ndev);
 out_wiphy:
 	wiphy_unregister(wiphy);
 	return rc;
@@ -554,5 +561,7 @@ void wil_if_remove(struct wil6210_priv *wil)
 	netif_napi_del(&wil->napi_tx);
 	netif_napi_del(&wil->napi_rx);
 
+	free_netdev(wil->napi_ndev);
+
 	wiphy_unregister(wiphy);
 }
diff --git a/drivers/net/wireless/ath/wil6210/wil6210.h b/drivers/net/wireless/ath/wil6210/wil6210.h
index 22a6eb3e12b7e..9bd1286d2857b 100644
--- a/drivers/net/wireless/ath/wil6210/wil6210.h
+++ b/drivers/net/wireless/ath/wil6210/wil6210.h
@@ -983,7 +983,7 @@ struct wil6210_priv {
 	spinlock_t eap_lock; /* guarding access to eap rekey fields */
 	struct napi_struct napi_rx;
 	struct napi_struct napi_tx;
-	struct net_device napi_ndev; /* dummy net_device serving all VIFs */
+	struct net_device *napi_ndev; /* dummy net_device serving all VIFs */
 
 	/* DMA related */
 	struct wil_ring ring_rx;
-- 
GitLab


From 9f74e7b306dcd7a163822ecb3b1587e9bd3f9c62 Mon Sep 17 00:00:00 2001
From: Tamizh Chelvam Raja <quic_tamizhr@quicinc.com>
Date: Tue, 30 Apr 2024 14:44:12 +0530
Subject: [PATCH 015/950] wifi: ath12k: fix calling correct function for rx
 monitor mode

Currently in ath12k_dp_tx_htt_monitor_mode_ring_config()
ath12k_dp_tx_htt_tx_monitor_mode_ring_config() function wrongly called twice.
Fix that by calling ath12k_dp_tx_htt_rx_monitor_mode_ring_config().

Currently monitor mode is disabled in driver so the change is compile
tested and boot sequence verified.

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

Signed-off-by: Tamizh Chelvam Raja <quic_tamizhr@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240430091414.2486196-2-quic_tamizhr@quicinc.com
---
 drivers/net/wireless/ath/ath12k/dp_tx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath12k/dp_tx.c b/drivers/net/wireless/ath/ath12k/dp_tx.c
index a7c7a868c14ce..7adfdefc3bdcc 100644
--- a/drivers/net/wireless/ath/ath12k/dp_tx.c
+++ b/drivers/net/wireless/ath/ath12k/dp_tx.c
@@ -1069,7 +1069,7 @@ int ath12k_dp_tx_htt_monitor_mode_ring_config(struct ath12k *ar, bool reset)
 		return ret;
 	}
 
-	ret = ath12k_dp_tx_htt_tx_monitor_mode_ring_config(ar, reset);
+	ret = ath12k_dp_tx_htt_rx_monitor_mode_ring_config(ar, reset);
 	if (ret) {
 		ath12k_err(ab, "failed to setup rx monitor filter %d\n", ret);
 		return ret;
-- 
GitLab


From ed07ff6745092f36cd996658bd64d74e4331d331 Mon Sep 17 00:00:00 2001
From: Tamizh Chelvam Raja <quic_tamizhr@quicinc.com>
Date: Tue, 30 Apr 2024 14:44:13 +0530
Subject: [PATCH 016/950] wifi: ath12k: Remove unsupported tx monitor handling

Currently tx monitor is not supported in driver. So remove
the tx monitor ring configuration, allocation and handling.

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

Signed-off-by: Tamizh Chelvam Raja <quic_tamizhr@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240430091414.2486196-3-quic_tamizhr@quicinc.com
---
 drivers/net/wireless/ath/ath12k/dp_mon.c | 40 +---------------
 drivers/net/wireless/ath/ath12k/dp_rx.c  | 59 +-----------------------
 drivers/net/wireless/ath/ath12k/dp_tx.c  | 42 -----------------
 drivers/net/wireless/ath/ath12k/dp_tx.h  |  3 +-
 4 files changed, 3 insertions(+), 141 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/dp_mon.c b/drivers/net/wireless/ath/ath12k/dp_mon.c
index 6b0b724775407..5c6749bc4039d 100644
--- a/drivers/net/wireless/ath/ath12k/dp_mon.c
+++ b/drivers/net/wireless/ath/ath12k/dp_mon.c
@@ -1903,43 +1903,6 @@ ath12k_dp_mon_tx_parse_status_tlv(struct ath12k_base *ab,
 		break;
 	}
 
-	case HAL_MON_BUF_ADDR: {
-		struct dp_rxdma_mon_ring *buf_ring = &ab->dp.tx_mon_buf_ring;
-		struct dp_mon_packet_info *packet_info =
-			(struct dp_mon_packet_info *)tlv_data;
-		int buf_id = u32_get_bits(packet_info->cookie,
-					  DP_RXDMA_BUF_COOKIE_BUF_ID);
-		struct sk_buff *msdu;
-		struct dp_mon_mpdu *mon_mpdu = tx_ppdu_info->tx_mon_mpdu;
-		struct ath12k_skb_rxcb *rxcb;
-
-		spin_lock_bh(&buf_ring->idr_lock);
-		msdu = idr_remove(&buf_ring->bufs_idr, buf_id);
-		spin_unlock_bh(&buf_ring->idr_lock);
-
-		if (unlikely(!msdu)) {
-			ath12k_warn(ab, "monitor destination with invalid buf_id %d\n",
-				    buf_id);
-			return DP_MON_TX_STATUS_PPDU_NOT_DONE;
-		}
-
-		rxcb = ATH12K_SKB_RXCB(msdu);
-		dma_unmap_single(ab->dev, rxcb->paddr,
-				 msdu->len + skb_tailroom(msdu),
-				 DMA_FROM_DEVICE);
-
-		if (!mon_mpdu->head)
-			mon_mpdu->head = msdu;
-		else if (mon_mpdu->tail)
-			mon_mpdu->tail->next = msdu;
-
-		mon_mpdu->tail = msdu;
-
-		ath12k_dp_mon_buf_replenish(ab, buf_ring, 1);
-		status = DP_MON_TX_BUFFER_ADDR;
-		break;
-	}
-
 	case HAL_TX_MPDU_END:
 		list_add_tail(&tx_ppdu_info->tx_mon_mpdu->list,
 			      &tx_ppdu_info->dp_tx_mon_mpdu_list);
@@ -2088,8 +2051,7 @@ int ath12k_dp_mon_srng_process(struct ath12k *ar, int mac_id, int *budget,
 		mon_dst_ring = &pdev_dp->rxdma_mon_dst_ring[srng_id];
 		buf_ring = &dp->rxdma_mon_buf_ring;
 	} else {
-		mon_dst_ring = &pdev_dp->tx_mon_dst_ring[srng_id];
-		buf_ring = &dp->tx_mon_buf_ring;
+		return 0;
 	}
 
 	srng = &ab->hal.srng_list[mon_dst_ring->ring_id];
diff --git a/drivers/net/wireless/ath/ath12k/dp_rx.c b/drivers/net/wireless/ath/ath12k/dp_rx.c
index 18030c9e735d4..952a377b54911 100644
--- a/drivers/net/wireless/ath/ath12k/dp_rx.c
+++ b/drivers/net/wireless/ath/ath12k/dp_rx.c
@@ -422,8 +422,6 @@ static int ath12k_dp_rxdma_buf_free(struct ath12k_base *ab)
 
 	ath12k_dp_rxdma_mon_buf_ring_free(ab, &dp->rxdma_mon_buf_ring);
 
-	ath12k_dp_rxdma_mon_buf_ring_free(ab, &dp->tx_mon_buf_ring);
-
 	return 0;
 }
 
@@ -476,15 +474,6 @@ static int ath12k_dp_rxdma_buf_setup(struct ath12k_base *ab)
 				    "failed to setup HAL_RXDMA_MONITOR_BUF\n");
 			return ret;
 		}
-
-		ret = ath12k_dp_rxdma_mon_ring_buf_setup(ab,
-							 &dp->tx_mon_buf_ring,
-							 HAL_TX_MONITOR_BUF);
-		if (ret) {
-			ath12k_warn(ab,
-				    "failed to setup HAL_TX_MONITOR_BUF\n");
-			return ret;
-		}
 	}
 
 	return 0;
@@ -496,10 +485,8 @@ static void ath12k_dp_rx_pdev_srng_free(struct ath12k *ar)
 	struct ath12k_base *ab = ar->ab;
 	int i;
 
-	for (i = 0; i < ab->hw_params->num_rxmda_per_pdev; i++) {
+	for (i = 0; i < ab->hw_params->num_rxmda_per_pdev; i++)
 		ath12k_dp_srng_cleanup(ab, &dp->rxdma_mon_dst_ring[i]);
-		ath12k_dp_srng_cleanup(ab, &dp->tx_mon_dst_ring[i]);
-	}
 }
 
 void ath12k_dp_rx_pdev_reo_cleanup(struct ath12k_base *ab)
@@ -554,17 +541,6 @@ static int ath12k_dp_rx_pdev_srng_alloc(struct ath12k *ar)
 				    "failed to setup HAL_RXDMA_MONITOR_DST\n");
 			return ret;
 		}
-
-		ret = ath12k_dp_srng_setup(ar->ab,
-					   &dp->tx_mon_dst_ring[i],
-					   HAL_TX_MONITOR_DST,
-					   0, mac_id + i,
-					   DP_TX_MONITOR_DEST_RING_SIZE);
-		if (ret) {
-			ath12k_warn(ar->ab,
-				    "failed to setup HAL_TX_MONITOR_DST\n");
-			return ret;
-		}
 	}
 
 	return 0;
@@ -3971,7 +3947,6 @@ void ath12k_dp_rx_free(struct ath12k_base *ab)
 		ath12k_dp_srng_cleanup(ab, &dp->rxdma_err_dst_ring[i]);
 
 	ath12k_dp_srng_cleanup(ab, &dp->rxdma_mon_buf_ring.refill_buf_ring);
-	ath12k_dp_srng_cleanup(ab, &dp->tx_mon_buf_ring.refill_buf_ring);
 
 	ath12k_dp_rxdma_buf_free(ab);
 }
@@ -4114,15 +4089,6 @@ int ath12k_dp_rx_htt_setup(struct ath12k_base *ab)
 				    ret);
 			return ret;
 		}
-
-		ring_id = dp->tx_mon_buf_ring.refill_buf_ring.ring_id;
-		ret = ath12k_dp_tx_htt_srng_setup(ab, ring_id,
-						  0, HAL_TX_MONITOR_BUF);
-		if (ret) {
-			ath12k_warn(ab, "failed to configure rxdma_mon_buf_ring %d\n",
-				    ret);
-			return ret;
-		}
 	}
 
 	ret = ab->hw_params->hw_ops->rxdma_ring_sel_config(ab);
@@ -4142,9 +4108,6 @@ int ath12k_dp_rx_alloc(struct ath12k_base *ab)
 	idr_init(&dp->rxdma_mon_buf_ring.bufs_idr);
 	spin_lock_init(&dp->rxdma_mon_buf_ring.idr_lock);
 
-	idr_init(&dp->tx_mon_buf_ring.bufs_idr);
-	spin_lock_init(&dp->tx_mon_buf_ring.idr_lock);
-
 	ret = ath12k_dp_srng_setup(ab,
 				   &dp->rx_refill_buf_ring.refill_buf_ring,
 				   HAL_RXDMA_BUF, 0, 0,
@@ -4187,15 +4150,6 @@ int ath12k_dp_rx_alloc(struct ath12k_base *ab)
 			ath12k_warn(ab, "failed to setup HAL_RXDMA_MONITOR_BUF\n");
 			return ret;
 		}
-
-		ret = ath12k_dp_srng_setup(ab,
-					   &dp->tx_mon_buf_ring.refill_buf_ring,
-					   HAL_TX_MONITOR_BUF, 0, 0,
-					   DP_TX_MONITOR_BUF_RING_SIZE);
-		if (ret) {
-			ath12k_warn(ab, "failed to setup DP_TX_MONITOR_BUF_RING_SIZE\n");
-			return ret;
-		}
 	}
 
 	ret = ath12k_dp_rxdma_buf_setup(ab);
@@ -4235,17 +4189,6 @@ int ath12k_dp_rx_pdev_alloc(struct ath12k_base *ab, int mac_id)
 				    i, ret);
 			return ret;
 		}
-
-		ring_id = dp->tx_mon_dst_ring[i].ring_id;
-		ret = ath12k_dp_tx_htt_srng_setup(ab, ring_id,
-						  mac_id + i,
-						  HAL_TX_MONITOR_DST);
-		if (ret) {
-			ath12k_warn(ab,
-				    "failed to configure tx_mon_dst_ring %d %d\n",
-				    i, ret);
-			return ret;
-		}
 	}
 out:
 	return 0;
diff --git a/drivers/net/wireless/ath/ath12k/dp_tx.c b/drivers/net/wireless/ath/ath12k/dp_tx.c
index 7adfdefc3bdcc..a22fa43c87ec5 100644
--- a/drivers/net/wireless/ath/ath12k/dp_tx.c
+++ b/drivers/net/wireless/ath/ath12k/dp_tx.c
@@ -688,14 +688,6 @@ ath12k_dp_tx_get_ring_id_type(struct ath12k_base *ab,
 		*htt_ring_id = HTT_RXDMA_MONITOR_DESC_RING;
 		*htt_ring_type = HTT_SW_TO_HW_RING;
 		break;
-	case HAL_TX_MONITOR_BUF:
-		*htt_ring_id = HTT_TX_MON_HOST2MON_BUF_RING;
-		*htt_ring_type = HTT_SW_TO_HW_RING;
-		break;
-	case HAL_TX_MONITOR_DST:
-		*htt_ring_id = HTT_TX_MON_MON2HOST_DEST_RING;
-		*htt_ring_type = HTT_HW_TO_SW_RING;
-		break;
 	default:
 		ath12k_warn(ab, "Unsupported ring type in DP :%d\n", ring_type);
 		ret = -EINVAL;
@@ -1063,12 +1055,6 @@ int ath12k_dp_tx_htt_monitor_mode_ring_config(struct ath12k *ar, bool reset)
 	struct ath12k_base *ab = ar->ab;
 	int ret;
 
-	ret = ath12k_dp_tx_htt_tx_monitor_mode_ring_config(ar, reset);
-	if (ret) {
-		ath12k_err(ab, "failed to setup tx monitor filter %d\n", ret);
-		return ret;
-	}
-
 	ret = ath12k_dp_tx_htt_rx_monitor_mode_ring_config(ar, reset);
 	if (ret) {
 		ath12k_err(ab, "failed to setup rx monitor filter %d\n", ret);
@@ -1228,31 +1214,3 @@ err_free:
 	dev_kfree_skb_any(skb);
 	return ret;
 }
-
-int ath12k_dp_tx_htt_tx_monitor_mode_ring_config(struct ath12k *ar, bool reset)
-{
-	struct ath12k_base *ab = ar->ab;
-	struct ath12k_dp *dp = &ab->dp;
-	struct htt_tx_ring_tlv_filter tlv_filter = {0};
-	int ret, ring_id;
-
-	ring_id = dp->tx_mon_buf_ring.refill_buf_ring.ring_id;
-
-	/* TODO: Need to set upstream/downstream tlv filters
-	 * here
-	 */
-
-	if (ab->hw_params->rxdma1_enable) {
-		ret = ath12k_dp_tx_htt_tx_filter_setup(ar->ab, ring_id, 0,
-						       HAL_TX_MONITOR_BUF,
-						       DP_RXDMA_REFILL_RING_SIZE,
-						       &tlv_filter);
-		if (ret) {
-			ath12k_err(ab,
-				   "failed to setup filter for monitor buf %d\n", ret);
-			return ret;
-		}
-	}
-
-	return 0;
-}
diff --git a/drivers/net/wireless/ath/ath12k/dp_tx.h b/drivers/net/wireless/ath/ath12k/dp_tx.h
index 436d77e5e9ee8..7faa81faf6a72 100644
--- a/drivers/net/wireless/ath/ath12k/dp_tx.h
+++ b/drivers/net/wireless/ath/ath12k/dp_tx.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2022, 2024 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH12K_DP_TX_H
@@ -36,6 +36,5 @@ int ath12k_dp_tx_htt_tx_filter_setup(struct ath12k_base *ab, u32 ring_id,
 				     int mac_id, enum hal_ring_type ring_type,
 				     int tx_buf_size,
 				     struct htt_tx_ring_tlv_filter *htt_tlv_filter);
-int ath12k_dp_tx_htt_tx_monitor_mode_ring_config(struct ath12k *ar, bool reset);
 int ath12k_dp_tx_htt_monitor_mode_ring_config(struct ath12k *ar, bool reset);
 #endif
-- 
GitLab


From 582e94ebe230afa35baef06833006b24b601ab11 Mon Sep 17 00:00:00 2001
From: Tamizh Chelvam Raja <quic_tamizhr@quicinc.com>
Date: Tue, 30 Apr 2024 14:44:14 +0530
Subject: [PATCH 017/950] wifi: ath12k: Remove unused tcl_*_ring configuration

Currently memory allocation for multiple hardware rings done
in host as these memory will be used by firmware/hardware.
But in case of tcl_cmd_ring and tcl_status_ring neither firmware
nor hardware uses host allocated memory and it uses memory
allocated by firmware itself. So avoid tcl_cmd_ring and
tcl_status_ring setup in host.

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

Signed-off-by: Tamizh Chelvam Raja <quic_tamizhr@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240430091414.2486196-4-quic_tamizhr@quicinc.com
---
 drivers/net/wireless/ath/ath12k/dp.c | 16 ----------------
 drivers/net/wireless/ath/ath12k/dp.h |  2 --
 2 files changed, 18 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/dp.c b/drivers/net/wireless/ath/ath12k/dp.c
index 72ea9baaf8d70..ca41f44313948 100644
--- a/drivers/net/wireless/ath/ath12k/dp.c
+++ b/drivers/net/wireless/ath/ath12k/dp.c
@@ -457,8 +457,6 @@ static void ath12k_dp_srng_common_cleanup(struct ath12k_base *ab)
 		ath12k_dp_srng_cleanup(ab, &dp->tx_ring[i].tcl_comp_ring);
 		ath12k_dp_srng_cleanup(ab, &dp->tx_ring[i].tcl_data_ring);
 	}
-	ath12k_dp_srng_cleanup(ab, &dp->tcl_status_ring);
-	ath12k_dp_srng_cleanup(ab, &dp->tcl_cmd_ring);
 	ath12k_dp_srng_cleanup(ab, &dp->wbm_desc_rel_ring);
 }
 
@@ -479,20 +477,6 @@ static int ath12k_dp_srng_common_setup(struct ath12k_base *ab)
 		goto err;
 	}
 
-	ret = ath12k_dp_srng_setup(ab, &dp->tcl_cmd_ring, HAL_TCL_CMD, 0, 0,
-				   DP_TCL_CMD_RING_SIZE);
-	if (ret) {
-		ath12k_warn(ab, "failed to set up tcl_cmd ring :%d\n", ret);
-		goto err;
-	}
-
-	ret = ath12k_dp_srng_setup(ab, &dp->tcl_status_ring, HAL_TCL_STATUS,
-				   0, 0, DP_TCL_STATUS_RING_SIZE);
-	if (ret) {
-		ath12k_warn(ab, "failed to set up tcl_status ring :%d\n", ret);
-		goto err;
-	}
-
 	for (i = 0; i < ab->hw_params->max_tx_ring; i++) {
 		map = ab->hw_params->hal_ops->tcl_to_wbm_rbm_map;
 		tx_comp_ring_num = map[i].wbm_ring_num;
diff --git a/drivers/net/wireless/ath/ath12k/dp.h b/drivers/net/wireless/ath/ath12k/dp.h
index e9880b34a7abe..43589c3dd4bc1 100644
--- a/drivers/net/wireless/ath/ath12k/dp.h
+++ b/drivers/net/wireless/ath/ath12k/dp.h
@@ -328,8 +328,6 @@ struct ath12k_dp {
 	enum hal_rx_buf_return_buf_manager idle_link_rbm;
 	struct dp_srng wbm_idle_ring;
 	struct dp_srng wbm_desc_rel_ring;
-	struct dp_srng tcl_cmd_ring;
-	struct dp_srng tcl_status_ring;
 	struct dp_srng reo_reinject_ring;
 	struct dp_srng rx_rel_ring;
 	struct dp_srng reo_except_ring;
-- 
GitLab


From 782615f280ce8ad4e3effb42d70304f4dd2d487f Mon Sep 17 00:00:00 2001
From: Kang Yang <quic_kangyang@quicinc.com>
Date: Mon, 29 Apr 2024 16:15:21 +0800
Subject: [PATCH 018/950] wifi: ath12k: remove unused variable monitor_flags

monitor_flags is defined in struct ath12k. Although it is changed in
some places, but it is not actually used.

So remove related code.

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Signed-off-by: Kang Yang <quic_kangyang@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240429081525.983-2-quic_kangyang@quicinc.com
---
 drivers/net/wireless/ath/ath12k/core.h |  5 -----
 drivers/net/wireless/ath/ath12k/mac.c  | 10 +---------
 2 files changed, 1 insertion(+), 14 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/core.h b/drivers/net/wireless/ath/ath12k/core.h
index 3cfc65b365797..bb6c1b562baf6 100644
--- a/drivers/net/wireless/ath/ath12k/core.h
+++ b/drivers/net/wireless/ath/ath12k/core.h
@@ -212,10 +212,6 @@ enum ath12k_dev_flags {
 	ATH12K_FLAG_EXT_IRQ_ENABLED,
 };
 
-enum ath12k_monitor_flags {
-	ATH12K_FLAG_MONITOR_ENABLED,
-};
-
 struct ath12k_tx_conf {
 	bool changed;
 	u16 ac;
@@ -532,7 +528,6 @@ struct ath12k {
 
 	unsigned long dev_flags;
 	unsigned int filter_flags;
-	unsigned long monitor_flags;
 	u32 min_tx_power;
 	u32 max_tx_power;
 	u32 txpower_limit_2g;
diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index 4f07ac8c0287c..a2b5aa86ec0b8 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -6510,7 +6510,6 @@ err_vdev_del:
 
 	/* Recalc txpower for remaining vdev */
 	ath12k_mac_txpower_recalc(ar);
-	clear_bit(ATH12K_FLAG_MONITOR_ENABLED, &ar->monitor_flags);
 
 	/* TODO: recal traffic pause state based on the available vdevs */
 	arvif->is_created = false;
@@ -6581,15 +6580,9 @@ static void ath12k_mac_configure_filter(struct ath12k *ar,
 	reset_flag = !(ar->filter_flags & FIF_BCN_PRBRESP_PROMISC);
 
 	ret = ath12k_dp_tx_htt_monitor_mode_ring_config(ar, reset_flag);
-	if (!ret) {
-		if (!reset_flag)
-			set_bit(ATH12K_FLAG_MONITOR_ENABLED, &ar->monitor_flags);
-		else
-			clear_bit(ATH12K_FLAG_MONITOR_ENABLED, &ar->monitor_flags);
-	} else {
+	if (ret)
 		ath12k_warn(ar->ab,
 			    "fail to set monitor filter: %d\n", ret);
-	}
 
 	ath12k_dbg(ar->ab, ATH12K_DBG_MAC,
 		   "total_flags:0x%x, reset_flag:%d\n",
@@ -8869,7 +8862,6 @@ static void ath12k_mac_setup(struct ath12k *ar)
 
 	INIT_WORK(&ar->wmi_mgmt_tx_work, ath12k_mgmt_over_wmi_tx_work);
 	skb_queue_head_init(&ar->wmi_mgmt_tx_queue);
-	clear_bit(ATH12K_FLAG_MONITOR_ENABLED, &ar->monitor_flags);
 }
 
 int ath12k_mac_register(struct ath12k_base *ab)
-- 
GitLab


From 3b0989e925f38df733a03ff5a320d6841006b3f9 Mon Sep 17 00:00:00 2001
From: Kang Yang <quic_kangyang@quicinc.com>
Date: Mon, 29 Apr 2024 16:15:22 +0800
Subject: [PATCH 019/950] wifi: ath12k: avoid duplicated vdev stop

ath12k_mac_op_unassign_vif_chanctx() will do vdev stop in
ath12k_mac_monitor_stop(). This ath12k_mac_vdev_stop() will do vdev stop
again, then might trigger firmware crash.

So add judgement to avoid duplicated vdev stop.

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Fixes: c9e4e41e71ff ("wifi: ath12k: move peer delete after vdev stop of station for WCN7850")
Signed-off-by: Kang Yang <quic_kangyang@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240429081525.983-3-quic_kangyang@quicinc.com
---
 drivers/net/wireless/ath/ath12k/mac.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index a2b5aa86ec0b8..cdea47faef742 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -7397,7 +7397,8 @@ ath12k_mac_op_unassign_vif_chanctx(struct ieee80211_hw *hw,
 		arvif->is_started = false;
 	}
 
-	if (arvif->vdev_type != WMI_VDEV_TYPE_STA) {
+	if (arvif->vdev_type != WMI_VDEV_TYPE_STA &&
+	    arvif->vdev_type != WMI_VDEV_TYPE_MONITOR) {
 		ath12k_bss_disassoc(ar, arvif);
 		ret = ath12k_mac_vdev_stop(arvif);
 		if (ret)
-- 
GitLab


From f40aaca07bf7b52e82ca8e5ddb29190466b5dcbd Mon Sep 17 00:00:00 2001
From: Kang Yang <quic_kangyang@quicinc.com>
Date: Mon, 29 Apr 2024 16:15:23 +0800
Subject: [PATCH 020/950] wifi: ath12k: avoid duplicated vdev down

ath12k_mac_op_unassign_vif_chanctx() will do vdev down in function
ath12k_mac_monitor_stop(). So no need to do vdev down again.

remove the duplicated one.

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Signed-off-by: Kang Yang <quic_kangyang@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240429081525.983-4-quic_kangyang@quicinc.com
---
 drivers/net/wireless/ath/ath12k/mac.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index cdea47faef742..1fc727b614d66 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -7407,10 +7407,6 @@ ath12k_mac_op_unassign_vif_chanctx(struct ieee80211_hw *hw,
 	}
 	arvif->is_started = false;
 
-	if (ab->hw_params->vdev_start_delay &&
-	    arvif->vdev_type == WMI_VDEV_TYPE_MONITOR)
-		ath12k_wmi_vdev_down(ar, arvif->vdev_id);
-
 	if (arvif->vdev_type != WMI_VDEV_TYPE_MONITOR &&
 	    ar->num_started_vdevs == 1 && ar->monitor_vdev_created)
 		ath12k_mac_monitor_stop(ar);
-- 
GitLab


From efd920f48d1f9c41368579d1a278e88c082cc233 Mon Sep 17 00:00:00 2001
From: Kang Yang <quic_kangyang@quicinc.com>
Date: Mon, 29 Apr 2024 16:15:25 +0800
Subject: [PATCH 021/950] wifi: ath12k: remove invalid peer create logic

In ath12k_mac_op_assign_vif_chanctx(), there is a logic to
create peer using ar->mac_addr for a STA vdev. This is invalid
because a STA vdev should have a peer created using AP's
MAC address. Besides, if we run into that logic, it means a peer
has already been created earlier, we should not create it again.
So remove it.

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Signed-off-by: Kang Yang <quic_kangyang@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240429081525.983-6-quic_kangyang@quicinc.com
---
 drivers/net/wireless/ath/ath12k/mac.c | 16 ----------------
 1 file changed, 16 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index 1fc727b614d66..96dc5c2e096fb 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -7270,7 +7270,6 @@ ath12k_mac_op_assign_vif_chanctx(struct ieee80211_hw *hw,
 	struct ath12k_base *ab;
 	struct ath12k_vif *arvif = ath12k_vif_to_arvif(vif);
 	int ret;
-	struct ath12k_wmi_peer_create_arg param;
 
 	/* For multi radio wiphy, the vdev was not created during add_interface
 	 * create now since we have a channel ctx now to assign to a specific ar/fw
@@ -7306,21 +7305,6 @@ ath12k_mac_op_assign_vif_chanctx(struct ieee80211_hw *hw,
 		goto out;
 	}
 
-	if (ab->hw_params->vdev_start_delay &&
-	    arvif->vdev_type != WMI_VDEV_TYPE_AP &&
-	    arvif->vdev_type != WMI_VDEV_TYPE_MONITOR) {
-		param.vdev_id = arvif->vdev_id;
-		param.peer_type = WMI_PEER_TYPE_DEFAULT;
-		param.peer_addr = ar->mac_addr;
-
-		ret = ath12k_peer_create(ar, arvif, NULL, &param);
-		if (ret) {
-			ath12k_warn(ab, "failed to create peer after vdev start delay: %d",
-				    ret);
-			goto out;
-		}
-	}
-
 	if (arvif->vdev_type == WMI_VDEV_TYPE_MONITOR) {
 		ret = ath12k_mac_monitor_start(ar);
 		if (ret)
-- 
GitLab


From 4c9aa94a39e6ef1a1381b1e6d841105fee5b7c96 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Wed, 24 Apr 2024 11:23:49 -0700
Subject: [PATCH 022/950] wifi: rtw89: Un-embed dummy device

Embedding net_device into structures prohibits the usage of flexible
arrays in the net_device structure. For more details, see the discussion
at [1].

Un-embed the net_device from the private struct by converting it
into a pointer. Then use the leverage the new alloc_netdev_dummy()
helper to allocate and initialize dummy devices.

[1] https://lore.kernel.org/all/20240229225910.79e224cf@kernel.org/

Tested with RTL8852BE, RTL8852C and RTL8922AE.

Signed-off-by: Breno Leitao <leitao@debian.org>
Acked-by: Ping-Ke Shih <pkshih@realtek.com>
Tested-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://msgid.link/20240424182351.3936556-1-leitao@debian.org
---
 drivers/net/wireless/realtek/rtw89/core.c | 11 ++++++++---
 drivers/net/wireless/realtek/rtw89/core.h |  4 ++--
 drivers/net/wireless/realtek/rtw89/pci.c  |  6 +++++-
 3 files changed, 15 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c
index ddc390d24ec1a..53997fa51ba0d 100644
--- a/drivers/net/wireless/realtek/rtw89/core.c
+++ b/drivers/net/wireless/realtek/rtw89/core.c
@@ -2492,11 +2492,15 @@ void rtw89_core_napi_stop(struct rtw89_dev *rtwdev)
 }
 EXPORT_SYMBOL(rtw89_core_napi_stop);
 
-void rtw89_core_napi_init(struct rtw89_dev *rtwdev)
+int rtw89_core_napi_init(struct rtw89_dev *rtwdev)
 {
-	init_dummy_netdev(&rtwdev->netdev);
-	netif_napi_add(&rtwdev->netdev, &rtwdev->napi,
+	rtwdev->netdev = alloc_netdev_dummy(0);
+	if (!rtwdev->netdev)
+		return -ENOMEM;
+
+	netif_napi_add(rtwdev->netdev, &rtwdev->napi,
 		       rtwdev->hci.ops->napi_poll);
+	return 0;
 }
 EXPORT_SYMBOL(rtw89_core_napi_init);
 
@@ -2504,6 +2508,7 @@ void rtw89_core_napi_deinit(struct rtw89_dev *rtwdev)
 {
 	rtw89_core_napi_stop(rtwdev);
 	netif_napi_del(&rtwdev->napi);
+	free_netdev(rtwdev->netdev);
 }
 EXPORT_SYMBOL(rtw89_core_napi_deinit);
 
diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index 112bdd95fc6ea..0648458110cef 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -5469,7 +5469,7 @@ struct rtw89_dev {
 	struct rtw89_wow_param wow;
 
 	/* napi structure */
-	struct net_device netdev;
+	struct net_device *netdev;
 	struct napi_struct napi;
 	int napi_budget_countdown;
 
@@ -6441,7 +6441,7 @@ void rtw89_core_query_rxdesc_v2(struct rtw89_dev *rtwdev,
 				u8 *data, u32 data_offset);
 void rtw89_core_napi_start(struct rtw89_dev *rtwdev);
 void rtw89_core_napi_stop(struct rtw89_dev *rtwdev);
-void rtw89_core_napi_init(struct rtw89_dev *rtwdev);
+int rtw89_core_napi_init(struct rtw89_dev *rtwdev);
 void rtw89_core_napi_deinit(struct rtw89_dev *rtwdev);
 int rtw89_core_sta_add(struct rtw89_dev *rtwdev,
 		       struct ieee80211_vif *vif,
diff --git a/drivers/net/wireless/realtek/rtw89/pci.c b/drivers/net/wireless/realtek/rtw89/pci.c
index 7b00476a5dee3..f93385cc20cd3 100644
--- a/drivers/net/wireless/realtek/rtw89/pci.c
+++ b/drivers/net/wireless/realtek/rtw89/pci.c
@@ -4293,7 +4293,11 @@ int rtw89_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	rtw89_pci_link_cfg(rtwdev);
 	rtw89_pci_l1ss_cfg(rtwdev);
 
-	rtw89_core_napi_init(rtwdev);
+	ret = rtw89_core_napi_init(rtwdev);
+	if (ret) {
+		rtw89_err(rtwdev, "failed to init napi\n");
+		goto err_clear_resource;
+	}
 
 	ret = rtw89_pci_request_irq(rtwdev, pdev);
 	if (ret) {
-- 
GitLab


From d0bcb10e7b94861c714ab1e62c98bf8abaa37527 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Thu, 25 Apr 2024 01:29:09 -0700
Subject: [PATCH 023/950] wifi: rtw88: Un-embed dummy device

Embedding net_device into structures prohibits the usage of flexible
arrays in the net_device structure. For more details, see the discussion
at [1].

Un-embed the net_device from the private struct by converting it
into a pointer. Then use the leverage the new alloc_netdev_dummy()
helper to allocate and initialize dummy devices.

[1] https://lore.kernel.org/all/20240229225910.79e224cf@kernel.org/

Tested with RTL8723DE and RTL8822CE.

Signed-off-by: Breno Leitao <leitao@debian.org>
Acked-by: Ping-Ke Shih <pkshih@realtek.com>
Tested-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://msgid.link/20240425082910.2824393-1-leitao@debian.org
---
 drivers/net/wireless/realtek/rtw88/pci.c | 17 +++++++++++++----
 drivers/net/wireless/realtek/rtw88/pci.h |  2 +-
 2 files changed, 14 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw88/pci.c b/drivers/net/wireless/realtek/rtw88/pci.c
index 7a093f3d5f742..095dcbadbeda8 100644
--- a/drivers/net/wireless/realtek/rtw88/pci.c
+++ b/drivers/net/wireless/realtek/rtw88/pci.c
@@ -1682,12 +1682,16 @@ static int rtw_pci_napi_poll(struct napi_struct *napi, int budget)
 	return work_done;
 }
 
-static void rtw_pci_napi_init(struct rtw_dev *rtwdev)
+static int rtw_pci_napi_init(struct rtw_dev *rtwdev)
 {
 	struct rtw_pci *rtwpci = (struct rtw_pci *)rtwdev->priv;
 
-	init_dummy_netdev(&rtwpci->netdev);
-	netif_napi_add(&rtwpci->netdev, &rtwpci->napi, rtw_pci_napi_poll);
+	rtwpci->netdev = alloc_netdev_dummy(0);
+	if (!rtwpci->netdev)
+		return -ENOMEM;
+
+	netif_napi_add(rtwpci->netdev, &rtwpci->napi, rtw_pci_napi_poll);
+	return 0;
 }
 
 static void rtw_pci_napi_deinit(struct rtw_dev *rtwdev)
@@ -1696,6 +1700,7 @@ static void rtw_pci_napi_deinit(struct rtw_dev *rtwdev)
 
 	rtw_pci_napi_stop(rtwdev);
 	netif_napi_del(&rtwpci->napi);
+	free_netdev(rtwpci->netdev);
 }
 
 int rtw_pci_probe(struct pci_dev *pdev,
@@ -1745,7 +1750,11 @@ int rtw_pci_probe(struct pci_dev *pdev,
 		goto err_pci_declaim;
 	}
 
-	rtw_pci_napi_init(rtwdev);
+	ret = rtw_pci_napi_init(rtwdev);
+	if (ret) {
+		rtw_err(rtwdev, "failed to setup NAPI\n");
+		goto err_pci_declaim;
+	}
 
 	ret = rtw_chip_info_setup(rtwdev);
 	if (ret) {
diff --git a/drivers/net/wireless/realtek/rtw88/pci.h b/drivers/net/wireless/realtek/rtw88/pci.h
index 0c37efd8c66fa..13988db1cb4c4 100644
--- a/drivers/net/wireless/realtek/rtw88/pci.h
+++ b/drivers/net/wireless/realtek/rtw88/pci.h
@@ -215,7 +215,7 @@ struct rtw_pci {
 	bool running;
 
 	/* napi structure */
-	struct net_device netdev;
+	struct net_device *netdev;
 	struct napi_struct napi;
 
 	u16 rx_tag;
-- 
GitLab


From a892f6ffbec7a1a25c639534bee62200418242f9 Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Fri, 3 May 2024 13:53:28 +0300
Subject: [PATCH 024/950] wifi: rtw88: usb: Simplify rtw_usb_write_data

The skb created in this function always has the same headroom,
the chip's TX descriptor size. (pkt_info->offset is set by
rtw_usb_write_data_rsvd_page() to chip->tx_pkt_desc_sz.) Use
chip->tx_pkt_desc_sz directly.

Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Tested-by: Larry Finger <Larry.Finger@lwfinger.net>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://msgid.link/2479507e-3946-492f-857e-83e54969aad2@gmail.com
---
 drivers/net/wireless/realtek/rtw88/usb.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw88/usb.c b/drivers/net/wireless/realtek/rtw88/usb.c
index a0188511099a1..90afeefe002f3 100644
--- a/drivers/net/wireless/realtek/rtw88/usb.c
+++ b/drivers/net/wireless/realtek/rtw88/usb.c
@@ -433,23 +433,21 @@ static int rtw_usb_write_data(struct rtw_dev *rtwdev,
 {
 	const struct rtw_chip_info *chip = rtwdev->chip;
 	struct sk_buff *skb;
-	unsigned int desclen, headsize, size;
+	unsigned int size;
 	u8 qsel;
 	int ret = 0;
 
 	size = pkt_info->tx_pkt_size;
 	qsel = pkt_info->qsel;
-	desclen = chip->tx_pkt_desc_sz;
-	headsize = pkt_info->offset ? pkt_info->offset : desclen;
 
-	skb = dev_alloc_skb(headsize + size);
+	skb = dev_alloc_skb(chip->tx_pkt_desc_sz + size);
 	if (unlikely(!skb))
 		return -ENOMEM;
 
-	skb_reserve(skb, headsize);
+	skb_reserve(skb, chip->tx_pkt_desc_sz);
 	skb_put_data(skb, buf, size);
-	skb_push(skb, headsize);
-	memset(skb->data, 0, headsize);
+	skb_push(skb, chip->tx_pkt_desc_sz);
+	memset(skb->data, 0, chip->tx_pkt_desc_sz);
 	rtw_tx_fill_tx_desc(pkt_info, skb);
 	rtw_tx_fill_txdesc_checksum(rtwdev, pkt_info, skb->data);
 
-- 
GitLab


From 28818b4d871bc93cc4f5c7c7d7c526a6a096c09c Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Mon, 29 Apr 2024 20:57:52 +0300
Subject: [PATCH 025/950] wifi: rtw88: usb: Fix disconnection after beacon loss

When there is beacon loss, for example due to unrelated Bluetooth
devices transmitting music nearby, the wifi connection dies soon
after the first beacon loss message:

Apr 28 20:47:14 ideapad2 wpa_supplicant[1161]: wlp3s0f3u4:
 CTRL-EVENT-BEACON-LOSS
Apr 28 20:47:15 ideapad2 wpa_supplicant[1161]: wlp3s0f3u4:
 CTRL-EVENT-DISCONNECTED bssid=... reason=4 locally_generated=1

Apr 28 20:47:24 ideapad2 wpa_supplicant[1161]: wlp3s0f3u4:
 CTRL-EVENT-BEACON-LOSS
Apr 28 20:47:25 ideapad2 wpa_supplicant[1161]: wlp3s0f3u4:
 CTRL-EVENT-DISCONNECTED bssid=... reason=4 locally_generated=1

Apr 28 20:47:34 ideapad2 wpa_supplicant[1161]: wlp3s0f3u4:
 CTRL-EVENT-BEACON-LOSS
Apr 28 20:47:35 ideapad2 wpa_supplicant[1161]: wlp3s0f3u4:
 CTRL-EVENT-DISCONNECTED bssid=... reason=4 locally_generated=1

When the beacon loss happens, mac80211 makes rtw88 transmit a QOS
NULL frame and asks to confirm the ACK status. Even though rtw88
confirms to mac80211 that the QOS NULL was transmitted successfully,
the connection still dies. This is because rtw88 is handing the QOS
NULL back to mac80211 with skb->data pointing to the headroom (the
TX descriptor) instead of ieee80211_hdr.

Fix the disconnection by moving skb->data to the correct position
before ieee80211_tx_status_irqsafe().

The problem was observed with RTL8811AU (TP-Link Archer T2U Nano)
and the potential future rtw88_8821au driver. Also tested with
RTL8811CU (Tenda U9).

Cc: stable@vger.kernel.org
Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://msgid.link/ecbf0601-810d-4609-b8fc-8b0e38d2948d@gmail.com
---
 drivers/net/wireless/realtek/rtw88/usb.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/wireless/realtek/rtw88/usb.c b/drivers/net/wireless/realtek/rtw88/usb.c
index 90afeefe002f3..d204d138afe29 100644
--- a/drivers/net/wireless/realtek/rtw88/usb.c
+++ b/drivers/net/wireless/realtek/rtw88/usb.c
@@ -273,6 +273,8 @@ static void rtw_usb_write_port_tx_complete(struct urb *urb)
 		info = IEEE80211_SKB_CB(skb);
 		tx_data = rtw_usb_get_tx_data(skb);
 
+		skb_pull(skb, rtwdev->chip->tx_pkt_desc_sz);
+
 		/* enqueue to wait for tx report */
 		if (info->flags & IEEE80211_TX_CTL_REQ_TX_STATUS) {
 			rtw_tx_report_enqueue(rtwdev, skb, tx_data->sn);
-- 
GitLab


From bb0b0a6b96e6de854cb1e349e17bd0e8bf421a59 Mon Sep 17 00:00:00 2001
From: Jeff Johnson <quic_jjohnson@quicinc.com>
Date: Sat, 4 May 2024 11:52:08 -0700
Subject: [PATCH 026/950] wifi: ath12k: initialize 'ret' in
 ath12k_qmi_load_file_target_mem()

smatch flagged the following issue:

drivers/net/wireless/ath/ath12k/qmi.c:2619 ath12k_qmi_load_file_target_mem() error: uninitialized symbol 'ret'.

The reality is that 'ret' is initialized in every path through
ath12k_qmi_load_file_target_mem() except one, the case where the input
'len' is 0, and hence the "while (remaining)" loop is never entered.
But to make sure this case is also handled, add an initializer to the
declaration of 'ret'.

No functional changes, compile tested only.

Signed-off-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240504-qmi_load_file_target_mem-v1-1-069fc44c45eb@quicinc.com
---
 drivers/net/wireless/ath/ath12k/qmi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath12k/qmi.c b/drivers/net/wireless/ath/ath12k/qmi.c
index 3bb730326a024..f273cb93dedb8 100644
--- a/drivers/net/wireless/ath/ath12k/qmi.c
+++ b/drivers/net/wireless/ath/ath12k/qmi.c
@@ -2538,7 +2538,7 @@ static int ath12k_qmi_load_file_target_mem(struct ath12k_base *ab,
 	struct qmi_wlanfw_bdf_download_resp_msg_v01 resp = {};
 	struct qmi_txn txn;
 	const u8 *temp = data;
-	int ret;
+	int ret = 0;
 	u32 remaining = len;
 
 	req = kzalloc(sizeof(*req), GFP_KERNEL);
-- 
GitLab


From 199f149e97dc7be80e5eed4b232529c1d1aa8055 Mon Sep 17 00:00:00 2001
From: Jeff Johnson <quic_jjohnson@quicinc.com>
Date: Sat, 4 May 2024 11:52:09 -0700
Subject: [PATCH 027/950] wifi: ath11k: initialize 'ret' in
 ath11k_qmi_load_file_target_mem()

smatch flagged the following issue:

drivers/net/wireless/ath/ath11k/qmi.c:2401 ath11k_qmi_load_file_target_mem() error: uninitialized symbol 'ret'.

The reality is that 'ret' is initialized in every path through
ath11k_qmi_load_file_target_mem() except one, the case where the input
'len' is 0, and hence the "while (remaining)" loop is never entered.
But to make sure this case is also handled, add an initializer to the
declaration of 'ret'.

No functional changes, compile tested only.

Signed-off-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240504-qmi_load_file_target_mem-v1-2-069fc44c45eb@quicinc.com
---
 drivers/net/wireless/ath/ath11k/qmi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath11k/qmi.c b/drivers/net/wireless/ath/ath11k/qmi.c
index d4a243b64f6c3..aa160e6fe24f1 100644
--- a/drivers/net/wireless/ath/ath11k/qmi.c
+++ b/drivers/net/wireless/ath/ath11k/qmi.c
@@ -2293,7 +2293,7 @@ static int ath11k_qmi_load_file_target_mem(struct ath11k_base *ab,
 	struct qmi_txn txn;
 	const u8 *temp = data;
 	void __iomem *bdf_addr = NULL;
-	int ret;
+	int ret = 0;
 	u32 remaining = len;
 
 	req = kzalloc(sizeof(*req), GFP_KERNEL);
-- 
GitLab


From 2db7a82fd150193849d04592e205b3d178207840 Mon Sep 17 00:00:00 2001
From: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Date: Mon, 6 May 2024 23:00:17 +0530
Subject: [PATCH 028/950] wifi: ath12k: avoid double SW2HW_MACID conversion

Currently, ath12k_wmi_pdev_dma_ring_cfg() fails due to an invalid pdev_id
parameter passed to the WMI_PDEV_DMA_RING_CFG_REQ_CMDID WMI command. This
invalid pdev_id is caused by a double conversion of the MAC ID. Since the
the caller of ath12k_wmi_pdev_dma_ring_cfg() already performs the MAC ID
conversion, it is unnecessary to do it again within the function. To fix
this, remove the software (SW) to hardware (HW) MAC ID conversion from
ath12k_wmi_pdev_dma_ring_cfg() to avoid this redundant conversion.

Found in code review.

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

Signed-off-by: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240506173017.597715-1-quic_periyasa@quicinc.com
---
 drivers/net/wireless/ath/ath12k/wmi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index 7a52d2082b792..9e9f58b5cbfb0 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -3808,7 +3808,7 @@ int ath12k_wmi_pdev_dma_ring_cfg(struct ath12k *ar,
 	cmd->tlv_header = ath12k_wmi_tlv_cmd_hdr(WMI_TAG_DMA_RING_CFG_REQ,
 						 sizeof(*cmd));
 
-	cmd->pdev_id = cpu_to_le32(DP_SW2HW_MACID(arg->pdev_id));
+	cmd->pdev_id = cpu_to_le32(arg->pdev_id);
 	cmd->module_id = cpu_to_le32(arg->module_id);
 	cmd->base_paddr_lo = cpu_to_le32(arg->base_paddr_lo);
 	cmd->base_paddr_hi = cpu_to_le32(arg->base_paddr_hi);
-- 
GitLab


From a6efa4ea06138d04b50ed5a7954a307a91a33478 Mon Sep 17 00:00:00 2001
From: Jeff Johnson <quic_jjohnson@quicinc.com>
Date: Sat, 4 May 2024 14:36:35 -0700
Subject: [PATCH 029/950] wifi: ath11k: fix misspelling of "dma" in
 num_rxmda_per_pdev

The ath11k_hw_params member num_rxmda_per_pdev contains a misspelling
of "dma" so fix it.

No functional changes, compile tested only.

Signed-off-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240504-ath11k-num_rxmda_per_pdev-v1-1-7f97bced8495@quicinc.com
---
 drivers/net/wireless/ath/ath11k/core.c    | 20 ++++++++++----------
 drivers/net/wireless/ath/ath11k/debugfs.c |  6 +++---
 drivers/net/wireless/ath/ath11k/dp.c      | 12 ++++++------
 drivers/net/wireless/ath/ath11k/dp_rx.c   | 22 +++++++++++-----------
 drivers/net/wireless/ath/ath11k/dp_tx.c   |  6 +++---
 drivers/net/wireless/ath/ath11k/hw.h      |  4 ++--
 drivers/net/wireless/ath/ath11k/mac.c     |  2 +-
 drivers/net/wireless/ath/ath11k/reg.c     |  4 ++--
 drivers/net/wireless/ath/ath11k/wmi.c     |  2 +-
 9 files changed, 39 insertions(+), 39 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/core.c b/drivers/net/wireless/ath/ath11k/core.c
index 3cc817a3b4a40..d4ef556852c2c 100644
--- a/drivers/net/wireless/ath/ath11k/core.c
+++ b/drivers/net/wireless/ath/ath11k/core.c
@@ -62,7 +62,7 @@ static const struct ath11k_hw_params ath11k_hw_params[] = {
 		.ce_ie_addr = &ath11k_ce_ie_addr_ipq8074,
 		.single_pdev_only = false,
 		.rxdma1_enable = true,
-		.num_rxmda_per_pdev = 1,
+		.num_rxdma_per_pdev = 1,
 		.rx_mac_buf_ring = false,
 		.vdev_start_delay = false,
 		.htt_peer_map_v2 = true,
@@ -148,7 +148,7 @@ static const struct ath11k_hw_params ath11k_hw_params[] = {
 		.ce_ie_addr = &ath11k_ce_ie_addr_ipq8074,
 		.single_pdev_only = false,
 		.rxdma1_enable = true,
-		.num_rxmda_per_pdev = 1,
+		.num_rxdma_per_pdev = 1,
 		.rx_mac_buf_ring = false,
 		.vdev_start_delay = false,
 		.htt_peer_map_v2 = true,
@@ -232,7 +232,7 @@ static const struct ath11k_hw_params ath11k_hw_params[] = {
 		.ce_ie_addr = &ath11k_ce_ie_addr_ipq8074,
 		.single_pdev_only = true,
 		.rxdma1_enable = false,
-		.num_rxmda_per_pdev = 2,
+		.num_rxdma_per_pdev = 2,
 		.rx_mac_buf_ring = true,
 		.vdev_start_delay = true,
 		.htt_peer_map_v2 = false,
@@ -320,7 +320,7 @@ static const struct ath11k_hw_params ath11k_hw_params[] = {
 		.svc_to_ce_map_len = 18,
 		.ce_ie_addr = &ath11k_ce_ie_addr_ipq8074,
 		.rxdma1_enable = true,
-		.num_rxmda_per_pdev = 1,
+		.num_rxdma_per_pdev = 1,
 		.rx_mac_buf_ring = false,
 		.vdev_start_delay = false,
 		.htt_peer_map_v2 = true,
@@ -404,7 +404,7 @@ static const struct ath11k_hw_params ath11k_hw_params[] = {
 		.ce_ie_addr = &ath11k_ce_ie_addr_ipq8074,
 		.single_pdev_only = true,
 		.rxdma1_enable = false,
-		.num_rxmda_per_pdev = 2,
+		.num_rxdma_per_pdev = 2,
 		.rx_mac_buf_ring = true,
 		.vdev_start_delay = true,
 		.htt_peer_map_v2 = false,
@@ -492,7 +492,7 @@ static const struct ath11k_hw_params ath11k_hw_params[] = {
 		.svc_to_ce_map_len = 14,
 		.single_pdev_only = true,
 		.rxdma1_enable = false,
-		.num_rxmda_per_pdev = 2,
+		.num_rxdma_per_pdev = 2,
 		.rx_mac_buf_ring = true,
 		.vdev_start_delay = true,
 		.htt_peer_map_v2 = false,
@@ -580,7 +580,7 @@ static const struct ath11k_hw_params ath11k_hw_params[] = {
 		.ce_ie_addr = &ath11k_ce_ie_addr_ipq8074,
 		.single_pdev_only = true,
 		.rxdma1_enable = false,
-		.num_rxmda_per_pdev = 1,
+		.num_rxdma_per_pdev = 1,
 		.rx_mac_buf_ring = true,
 		.vdev_start_delay = true,
 		.htt_peer_map_v2 = false,
@@ -673,7 +673,7 @@ static const struct ath11k_hw_params ath11k_hw_params[] = {
 		.ce_ie_addr = &ath11k_ce_ie_addr_ipq5018,
 		.ce_remap = &ath11k_ce_remap_ipq5018,
 		.rxdma1_enable = true,
-		.num_rxmda_per_pdev = RXDMA_PER_PDEV_5018,
+		.num_rxdma_per_pdev = RXDMA_PER_PDEV_5018,
 		.rx_mac_buf_ring = false,
 		.vdev_start_delay = false,
 		.htt_peer_map_v2 = true,
@@ -744,7 +744,7 @@ static const struct ath11k_hw_params ath11k_hw_params[] = {
 		.ce_ie_addr = &ath11k_ce_ie_addr_ipq8074,
 		.single_pdev_only = true,
 		.rxdma1_enable = false,
-		.num_rxmda_per_pdev = 2,
+		.num_rxdma_per_pdev = 2,
 		.rx_mac_buf_ring = true,
 		.vdev_start_delay = true,
 		.htt_peer_map_v2 = false,
@@ -1801,7 +1801,7 @@ static int ath11k_core_start(struct ath11k_base *ab)
 	}
 
 	/* put hardware to DBS mode */
-	if (ab->hw_params.single_pdev_only && ab->hw_params.num_rxmda_per_pdev > 1) {
+	if (ab->hw_params.single_pdev_only && ab->hw_params.num_rxdma_per_pdev > 1) {
 		ret = ath11k_wmi_set_hw_mode(ab, WMI_HOST_HW_MODE_DBS);
 		if (ret) {
 			ath11k_err(ab, "failed to send dbs mode: %d\n", ret);
diff --git a/drivers/net/wireless/ath/ath11k/debugfs.c b/drivers/net/wireless/ath/ath11k/debugfs.c
index 414a5ce279f78..57281a135dd7f 100644
--- a/drivers/net/wireless/ath/ath11k/debugfs.c
+++ b/drivers/net/wireless/ath/ath11k/debugfs.c
@@ -668,7 +668,7 @@ static ssize_t ath11k_write_extd_rx_stats(struct file *file,
 
 	ar->debug.rx_filter = tlv_filter.rx_filter;
 
-	for (i = 0; i < ab->hw_params.num_rxmda_per_pdev; i++) {
+	for (i = 0; i < ab->hw_params.num_rxdma_per_pdev; i++) {
 		ring_id = ar->dp.rx_mon_status_refill_ring[i].refill_buf_ring.ring_id;
 		ret = ath11k_dp_tx_htt_rx_filter_setup(ar->ab, ring_id, ar->dp.mac_id,
 						       HAL_RXDMA_MONITOR_STATUS,
@@ -1112,7 +1112,7 @@ static ssize_t ath11k_write_pktlog_filter(struct file *file,
 	}
 
 	/* Clear rx filter set for monitor mode and rx status */
-	for (i = 0; i < ab->hw_params.num_rxmda_per_pdev; i++) {
+	for (i = 0; i < ab->hw_params.num_rxdma_per_pdev; i++) {
 		ring_id = ar->dp.rx_mon_status_refill_ring[i].refill_buf_ring.ring_id;
 		ret = ath11k_dp_tx_htt_rx_filter_setup(ar->ab, ring_id, ar->dp.mac_id,
 						       HAL_RXDMA_MONITOR_STATUS,
@@ -1171,7 +1171,7 @@ static ssize_t ath11k_write_pktlog_filter(struct file *file,
 					       HTT_RX_FP_DATA_FILTER_FLASG3;
 	}
 
-	for (i = 0; i < ab->hw_params.num_rxmda_per_pdev; i++) {
+	for (i = 0; i < ab->hw_params.num_rxdma_per_pdev; i++) {
 		ring_id = ar->dp.rx_mon_status_refill_ring[i].refill_buf_ring.ring_id;
 		ret = ath11k_dp_tx_htt_rx_filter_setup(ab, ring_id,
 						       ar->dp.mac_id + i,
diff --git a/drivers/net/wireless/ath/ath11k/dp.c b/drivers/net/wireless/ath/ath11k/dp.c
index 1a62407e5a9f2..fbf666d0ecf1d 100644
--- a/drivers/net/wireless/ath/ath11k/dp.c
+++ b/drivers/net/wireless/ath/ath11k/dp.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <crypto/hash.h>
@@ -830,8 +830,8 @@ int ath11k_dp_service_srng(struct ath11k_base *ab,
 
 	if (ab->hw_params.ring_mask->rx_mon_status[grp_id]) {
 		for (i = 0; i < ab->num_radios; i++) {
-			for (j = 0; j < ab->hw_params.num_rxmda_per_pdev; j++) {
-				int id = i * ab->hw_params.num_rxmda_per_pdev + j;
+			for (j = 0; j < ab->hw_params.num_rxdma_per_pdev; j++) {
+				int id = i * ab->hw_params.num_rxdma_per_pdev + j;
 
 				if (ab->hw_params.ring_mask->rx_mon_status[grp_id] &
 					BIT(id)) {
@@ -853,8 +853,8 @@ int ath11k_dp_service_srng(struct ath11k_base *ab,
 		ath11k_dp_process_reo_status(ab);
 
 	for (i = 0; i < ab->num_radios; i++) {
-		for (j = 0; j < ab->hw_params.num_rxmda_per_pdev; j++) {
-			int id = i * ab->hw_params.num_rxmda_per_pdev + j;
+		for (j = 0; j < ab->hw_params.num_rxdma_per_pdev; j++) {
+			int id = i * ab->hw_params.num_rxdma_per_pdev + j;
 
 			if (ab->hw_params.ring_mask->rxdma2host[grp_id] & BIT(id)) {
 				work_done = ath11k_dp_process_rxdma_err(ab, id, budget);
@@ -913,7 +913,7 @@ void ath11k_dp_pdev_pre_alloc(struct ath11k_base *ab)
 		spin_lock_init(&dp->rx_refill_buf_ring.idr_lock);
 		atomic_set(&dp->num_tx_pending, 0);
 		init_waitqueue_head(&dp->tx_empty_waitq);
-		for (j = 0; j < ab->hw_params.num_rxmda_per_pdev; j++) {
+		for (j = 0; j < ab->hw_params.num_rxdma_per_pdev; j++) {
 			idr_init(&dp->rx_mon_status_refill_ring[j].bufs_idr);
 			spin_lock_init(&dp->rx_mon_status_refill_ring[j].idr_lock);
 		}
diff --git a/drivers/net/wireless/ath/ath11k/dp_rx.c b/drivers/net/wireless/ath/ath11k/dp_rx.c
index 8a860a17d7e48..198fb359a688c 100644
--- a/drivers/net/wireless/ath/ath11k/dp_rx.c
+++ b/drivers/net/wireless/ath/ath11k/dp_rx.c
@@ -311,7 +311,7 @@ static void ath11k_dp_service_mon_ring(struct timer_list *t)
 	struct ath11k_base *ab = from_timer(ab, t, mon_reap_timer);
 	int i;
 
-	for (i = 0; i < ab->hw_params.num_rxmda_per_pdev; i++)
+	for (i = 0; i < ab->hw_params.num_rxdma_per_pdev; i++)
 		ath11k_dp_rx_process_mon_rings(ab, i, NULL, DP_MON_SERVICE_BUDGET);
 
 	mod_timer(&ab->mon_reap_timer, jiffies +
@@ -324,7 +324,7 @@ static int ath11k_dp_purge_mon_ring(struct ath11k_base *ab)
 	unsigned long timeout = jiffies + msecs_to_jiffies(DP_MON_PURGE_TIMEOUT_MS);
 
 	do {
-		for (i = 0; i < ab->hw_params.num_rxmda_per_pdev; i++)
+		for (i = 0; i < ab->hw_params.num_rxdma_per_pdev; i++)
 			reaped += ath11k_dp_rx_process_mon_rings(ab, i,
 								 NULL,
 								 DP_MON_SERVICE_BUDGET);
@@ -468,7 +468,7 @@ static int ath11k_dp_rxdma_pdev_buf_free(struct ath11k *ar)
 	rx_ring = &dp->rxdma_mon_buf_ring;
 	ath11k_dp_rxdma_buf_ring_free(ar, rx_ring);
 
-	for (i = 0; i < ab->hw_params.num_rxmda_per_pdev; i++) {
+	for (i = 0; i < ab->hw_params.num_rxdma_per_pdev; i++) {
 		rx_ring = &dp->rx_mon_status_refill_ring[i];
 		ath11k_dp_rxdma_buf_ring_free(ar, rx_ring);
 	}
@@ -506,7 +506,7 @@ static int ath11k_dp_rxdma_pdev_buf_setup(struct ath11k *ar)
 		ath11k_dp_rxdma_ring_buf_setup(ar, rx_ring, HAL_RXDMA_MONITOR_BUF);
 	}
 
-	for (i = 0; i < ab->hw_params.num_rxmda_per_pdev; i++) {
+	for (i = 0; i < ab->hw_params.num_rxdma_per_pdev; i++) {
 		rx_ring = &dp->rx_mon_status_refill_ring[i];
 		ath11k_dp_rxdma_ring_buf_setup(ar, rx_ring, HAL_RXDMA_MONITOR_STATUS);
 	}
@@ -522,7 +522,7 @@ static void ath11k_dp_rx_pdev_srng_free(struct ath11k *ar)
 
 	ath11k_dp_srng_cleanup(ab, &dp->rx_refill_buf_ring.refill_buf_ring);
 
-	for (i = 0; i < ab->hw_params.num_rxmda_per_pdev; i++) {
+	for (i = 0; i < ab->hw_params.num_rxdma_per_pdev; i++) {
 		if (ab->hw_params.rx_mac_buf_ring)
 			ath11k_dp_srng_cleanup(ab, &dp->rx_mac_buf_ring[i]);
 
@@ -585,7 +585,7 @@ static int ath11k_dp_rx_pdev_srng_alloc(struct ath11k *ar)
 	}
 
 	if (ar->ab->hw_params.rx_mac_buf_ring) {
-		for (i = 0; i < ab->hw_params.num_rxmda_per_pdev; i++) {
+		for (i = 0; i < ab->hw_params.num_rxdma_per_pdev; i++) {
 			ret = ath11k_dp_srng_setup(ar->ab,
 						   &dp->rx_mac_buf_ring[i],
 						   HAL_RXDMA_BUF, 1,
@@ -598,7 +598,7 @@ static int ath11k_dp_rx_pdev_srng_alloc(struct ath11k *ar)
 		}
 	}
 
-	for (i = 0; i < ab->hw_params.num_rxmda_per_pdev; i++) {
+	for (i = 0; i < ab->hw_params.num_rxdma_per_pdev; i++) {
 		ret = ath11k_dp_srng_setup(ar->ab, &dp->rxdma_err_dst_ring[i],
 					   HAL_RXDMA_DST, 0, dp->mac_id + i,
 					   DP_RXDMA_ERR_DST_RING_SIZE);
@@ -608,7 +608,7 @@ static int ath11k_dp_rx_pdev_srng_alloc(struct ath11k *ar)
 		}
 	}
 
-	for (i = 0; i < ab->hw_params.num_rxmda_per_pdev; i++) {
+	for (i = 0; i < ab->hw_params.num_rxdma_per_pdev; i++) {
 		srng = &dp->rx_mon_status_refill_ring[i].refill_buf_ring;
 		ret = ath11k_dp_srng_setup(ar->ab,
 					   srng,
@@ -4455,7 +4455,7 @@ int ath11k_dp_rx_pdev_alloc(struct ath11k_base *ab, int mac_id)
 	}
 
 	if (ab->hw_params.rx_mac_buf_ring) {
-		for (i = 0; i < ab->hw_params.num_rxmda_per_pdev; i++) {
+		for (i = 0; i < ab->hw_params.num_rxdma_per_pdev; i++) {
 			ring_id = dp->rx_mac_buf_ring[i].ring_id;
 			ret = ath11k_dp_tx_htt_srng_setup(ab, ring_id,
 							  mac_id + i, HAL_RXDMA_BUF);
@@ -4467,7 +4467,7 @@ int ath11k_dp_rx_pdev_alloc(struct ath11k_base *ab, int mac_id)
 		}
 	}
 
-	for (i = 0; i < ab->hw_params.num_rxmda_per_pdev; i++) {
+	for (i = 0; i < ab->hw_params.num_rxdma_per_pdev; i++) {
 		ring_id = dp->rxdma_err_dst_ring[i].ring_id;
 		ret = ath11k_dp_tx_htt_srng_setup(ab, ring_id,
 						  mac_id + i, HAL_RXDMA_DST);
@@ -4507,7 +4507,7 @@ int ath11k_dp_rx_pdev_alloc(struct ath11k_base *ab, int mac_id)
 	}
 
 config_refill_ring:
-	for (i = 0; i < ab->hw_params.num_rxmda_per_pdev; i++) {
+	for (i = 0; i < ab->hw_params.num_rxdma_per_pdev; i++) {
 		ring_id = dp->rx_mon_status_refill_ring[i].refill_buf_ring.ring_id;
 		ret = ath11k_dp_tx_htt_srng_setup(ab, ring_id, mac_id + i,
 						  HAL_RXDMA_MONITOR_STATUS);
diff --git a/drivers/net/wireless/ath/ath11k/dp_tx.c b/drivers/net/wireless/ath/ath11k/dp_tx.c
index 272b1c35f98df..21819b7417010 100644
--- a/drivers/net/wireless/ath/ath11k/dp_tx.c
+++ b/drivers/net/wireless/ath/ath11k/dp_tx.c
@@ -1035,7 +1035,7 @@ int ath11k_dp_tx_htt_h2t_ppdu_stats_req(struct ath11k *ar, u32 mask)
 	int ret;
 	int i;
 
-	for (i = 0; i < ab->hw_params.num_rxmda_per_pdev; i++) {
+	for (i = 0; i < ab->hw_params.num_rxdma_per_pdev; i++) {
 		skb = ath11k_htc_alloc_skb(ab, len);
 		if (!skb)
 			return -ENOMEM;
@@ -1218,7 +1218,7 @@ int ath11k_dp_tx_htt_monitor_mode_ring_config(struct ath11k *ar, bool reset)
 						       &tlv_filter);
 	} else if (!reset) {
 		/* set in monitor mode only */
-		for (i = 0; i < ab->hw_params.num_rxmda_per_pdev; i++) {
+		for (i = 0; i < ab->hw_params.num_rxdma_per_pdev; i++) {
 			ring_id = dp->rx_mac_buf_ring[i].ring_id;
 			ret = ath11k_dp_tx_htt_rx_filter_setup(ar->ab, ring_id,
 							       dp->mac_id + i,
@@ -1231,7 +1231,7 @@ int ath11k_dp_tx_htt_monitor_mode_ring_config(struct ath11k *ar, bool reset)
 	if (ret)
 		return ret;
 
-	for (i = 0; i < ab->hw_params.num_rxmda_per_pdev; i++) {
+	for (i = 0; i < ab->hw_params.num_rxdma_per_pdev; i++) {
 		ring_id = dp->rx_mon_status_refill_ring[i].refill_buf_ring.ring_id;
 		if (!reset) {
 			tlv_filter.rx_filter =
diff --git a/drivers/net/wireless/ath/ath11k/hw.h b/drivers/net/wireless/ath/ath11k/hw.h
index 14ef4eb48f807..300322535766e 100644
--- a/drivers/net/wireless/ath/ath11k/hw.h
+++ b/drivers/net/wireless/ath/ath11k/hw.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH11K_HW_H
@@ -167,7 +167,7 @@ struct ath11k_hw_params {
 	bool single_pdev_only;
 
 	bool rxdma1_enable;
-	int num_rxmda_per_pdev;
+	int num_rxdma_per_pdev;
 	bool rx_mac_buf_ring;
 	bool vdev_start_delay;
 	bool htt_peer_map_v2;
diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c
index a71195344288a..17b06c0cd0628 100644
--- a/drivers/net/wireless/ath/ath11k/mac.c
+++ b/drivers/net/wireless/ath/ath11k/mac.c
@@ -6108,7 +6108,7 @@ static int ath11k_mac_config_mon_status_default(struct ath11k *ar, bool enable)
 			tlv_filter.rx_filter = ath11k_debugfs_rx_filter(ar);
 	}
 
-	for (i = 0; i < ab->hw_params.num_rxmda_per_pdev; i++) {
+	for (i = 0; i < ab->hw_params.num_rxdma_per_pdev; i++) {
 		ring_id = ar->dp.rx_mon_status_refill_ring[i].refill_buf_ring.ring_id;
 		ret = ath11k_dp_tx_htt_rx_filter_setup(ar->ab, ring_id,
 						       ar->dp.mac_id + i,
diff --git a/drivers/net/wireless/ath/ath11k/reg.c b/drivers/net/wireless/ath/ath11k/reg.c
index 737fcd450d4bd..4c3aefbbabbe7 100644
--- a/drivers/net/wireless/ath/ath11k/reg.c
+++ b/drivers/net/wireless/ath/ath11k/reg.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 #include <linux/rtnetlink.h>
 
@@ -878,7 +878,7 @@ int ath11k_reg_handle_chan_list(struct ath11k_base *ab,
 		ath11k_reg_reset_info(reg_info);
 
 		if (ab->hw_params.single_pdev_only &&
-		    pdev_idx < ab->hw_params.num_rxmda_per_pdev)
+		    pdev_idx < ab->hw_params.num_rxdma_per_pdev)
 			return 0;
 		goto fallback;
 	}
diff --git a/drivers/net/wireless/ath/ath11k/wmi.c b/drivers/net/wireless/ath/ath11k/wmi.c
index 6ff01c45f1659..38f175dd15578 100644
--- a/drivers/net/wireless/ath/ath11k/wmi.c
+++ b/drivers/net/wireless/ath/ath11k/wmi.c
@@ -9082,7 +9082,7 @@ int ath11k_wmi_attach(struct ath11k_base *ab)
 	ab->wmi_ab.preferred_hw_mode = WMI_HOST_HW_MODE_MAX;
 
 	/* It's overwritten when service_ext_ready is handled */
-	if (ab->hw_params.single_pdev_only && ab->hw_params.num_rxmda_per_pdev > 1)
+	if (ab->hw_params.single_pdev_only && ab->hw_params.num_rxdma_per_pdev > 1)
 		ab->wmi_ab.preferred_hw_mode = WMI_HOST_HW_MODE_SINGLE;
 
 	/* TODO: Init remaining wmi soc resources required */
-- 
GitLab


From ff5fa958d2fd45de7282a8bd3968426c947591d5 Mon Sep 17 00:00:00 2001
From: Jeff Johnson <quic_jjohnson@quicinc.com>
Date: Sat, 4 May 2024 14:45:17 -0700
Subject: [PATCH 030/950] wifi: ath12k: fix misspelling of "dma" in
 num_rxmda_per_pdev

The ath12k_hw_params member num_rxmda_per_pdev contains a misspelling
of "dma" so fix it.

No functional changes, compile tested only.

Signed-off-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240504-ath12k_dp_rxdma_ring_sel_config_wcn7850-ret-v1-1-44d2843a2857@quicinc.com
---
 drivers/net/wireless/ath/ath12k/dp.c    | 10 +++++-----
 drivers/net/wireless/ath/ath12k/dp_rx.c | 14 +++++++-------
 drivers/net/wireless/ath/ath12k/dp_tx.c |  2 +-
 drivers/net/wireless/ath/ath12k/hw.c    |  6 +++---
 drivers/net/wireless/ath/ath12k/hw.h    |  2 +-
 drivers/net/wireless/ath/ath12k/wmi.c   |  2 +-
 6 files changed, 18 insertions(+), 18 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/dp.c b/drivers/net/wireless/ath/ath12k/dp.c
index ca41f44313948..412ab08e6cca2 100644
--- a/drivers/net/wireless/ath/ath12k/dp.c
+++ b/drivers/net/wireless/ath/ath12k/dp.c
@@ -907,8 +907,8 @@ int ath12k_dp_service_srng(struct ath12k_base *ab,
 		monitor_mode = ATH12K_DP_RX_MONITOR_MODE;
 		ring_mask = ab->hw_params->ring_mask->rx_mon_dest[grp_id];
 		for (i = 0; i < ab->num_radios; i++) {
-			for (j = 0; j < ab->hw_params->num_rxmda_per_pdev; j++) {
-				int id = i * ab->hw_params->num_rxmda_per_pdev + j;
+			for (j = 0; j < ab->hw_params->num_rxdma_per_pdev; j++) {
+				int id = i * ab->hw_params->num_rxdma_per_pdev + j;
 
 				if (ring_mask & BIT(id)) {
 					work_done =
@@ -928,8 +928,8 @@ int ath12k_dp_service_srng(struct ath12k_base *ab,
 		monitor_mode = ATH12K_DP_TX_MONITOR_MODE;
 		ring_mask = ab->hw_params->ring_mask->tx_mon_dest[grp_id];
 		for (i = 0; i < ab->num_radios; i++) {
-			for (j = 0; j < ab->hw_params->num_rxmda_per_pdev; j++) {
-				int id = i * ab->hw_params->num_rxmda_per_pdev + j;
+			for (j = 0; j < ab->hw_params->num_rxdma_per_pdev; j++) {
+				int id = i * ab->hw_params->num_rxdma_per_pdev + j;
 
 				if (ring_mask & BIT(id)) {
 					work_done =
@@ -1017,7 +1017,7 @@ static void ath12k_dp_service_mon_ring(struct timer_list *t)
 	struct ath12k_base *ab = from_timer(ab, t, mon_reap_timer);
 	int i;
 
-	for (i = 0; i < ab->hw_params->num_rxmda_per_pdev; i++)
+	for (i = 0; i < ab->hw_params->num_rxdma_per_pdev; i++)
 		ath12k_dp_mon_process_ring(ab, i, NULL, DP_MON_SERVICE_BUDGET,
 					   ATH12K_DP_RX_MONITOR_MODE);
 
diff --git a/drivers/net/wireless/ath/ath12k/dp_rx.c b/drivers/net/wireless/ath/ath12k/dp_rx.c
index 952a377b54911..e3ff14cd283f7 100644
--- a/drivers/net/wireless/ath/ath12k/dp_rx.c
+++ b/drivers/net/wireless/ath/ath12k/dp_rx.c
@@ -485,7 +485,7 @@ static void ath12k_dp_rx_pdev_srng_free(struct ath12k *ar)
 	struct ath12k_base *ab = ar->ab;
 	int i;
 
-	for (i = 0; i < ab->hw_params->num_rxmda_per_pdev; i++)
+	for (i = 0; i < ab->hw_params->num_rxdma_per_pdev; i++)
 		ath12k_dp_srng_cleanup(ab, &dp->rxdma_mon_dst_ring[i]);
 }
 
@@ -530,7 +530,7 @@ static int ath12k_dp_rx_pdev_srng_alloc(struct ath12k *ar)
 	int ret;
 	u32 mac_id = dp->mac_id;
 
-	for (i = 0; i < ab->hw_params->num_rxmda_per_pdev; i++) {
+	for (i = 0; i < ab->hw_params->num_rxdma_per_pdev; i++) {
 		ret = ath12k_dp_srng_setup(ar->ab,
 					   &dp->rxdma_mon_dst_ring[i],
 					   HAL_RXDMA_MONITOR_DST,
@@ -3938,7 +3938,7 @@ void ath12k_dp_rx_free(struct ath12k_base *ab)
 
 	ath12k_dp_srng_cleanup(ab, &dp->rx_refill_buf_ring.refill_buf_ring);
 
-	for (i = 0; i < ab->hw_params->num_rxmda_per_pdev; i++) {
+	for (i = 0; i < ab->hw_params->num_rxdma_per_pdev; i++) {
 		if (ab->hw_params->rx_mac_buf_ring)
 			ath12k_dp_srng_cleanup(ab, &dp->rx_mac_buf_ring[i]);
 	}
@@ -4030,7 +4030,7 @@ int ath12k_dp_rxdma_ring_sel_config_wcn7850(struct ath12k_base *ab)
 	 * and modify the rx_desc struct
 	 */
 
-	for (i = 0; i < ab->hw_params->num_rxmda_per_pdev; i++) {
+	for (i = 0; i < ab->hw_params->num_rxdma_per_pdev; i++) {
 		ring_id = dp->rx_mac_buf_ring[i].ring_id;
 		ret = ath12k_dp_tx_htt_rx_filter_setup(ab, ring_id, i,
 						       HAL_RXDMA_BUF,
@@ -4057,7 +4057,7 @@ int ath12k_dp_rx_htt_setup(struct ath12k_base *ab)
 	}
 
 	if (ab->hw_params->rx_mac_buf_ring) {
-		for (i = 0; i < ab->hw_params->num_rxmda_per_pdev; i++) {
+		for (i = 0; i < ab->hw_params->num_rxdma_per_pdev; i++) {
 			ring_id = dp->rx_mac_buf_ring[i].ring_id;
 			ret = ath12k_dp_tx_htt_srng_setup(ab, ring_id,
 							  i, HAL_RXDMA_BUF);
@@ -4118,7 +4118,7 @@ int ath12k_dp_rx_alloc(struct ath12k_base *ab)
 	}
 
 	if (ab->hw_params->rx_mac_buf_ring) {
-		for (i = 0; i < ab->hw_params->num_rxmda_per_pdev; i++) {
+		for (i = 0; i < ab->hw_params->num_rxdma_per_pdev; i++) {
 			ret = ath12k_dp_srng_setup(ab,
 						   &dp->rx_mac_buf_ring[i],
 						   HAL_RXDMA_BUF, 1,
@@ -4178,7 +4178,7 @@ int ath12k_dp_rx_pdev_alloc(struct ath12k_base *ab, int mac_id)
 		return ret;
 	}
 
-	for (i = 0; i < ab->hw_params->num_rxmda_per_pdev; i++) {
+	for (i = 0; i < ab->hw_params->num_rxdma_per_pdev; i++) {
 		ring_id = dp->rxdma_mon_dst_ring[i].ring_id;
 		ret = ath12k_dp_tx_htt_srng_setup(ab, ring_id,
 						  mac_id + i,
diff --git a/drivers/net/wireless/ath/ath12k/dp_tx.c b/drivers/net/wireless/ath/ath12k/dp_tx.c
index a22fa43c87ec5..32496015cf9a1 100644
--- a/drivers/net/wireless/ath/ath12k/dp_tx.c
+++ b/drivers/net/wireless/ath/ath12k/dp_tx.c
@@ -865,7 +865,7 @@ int ath12k_dp_tx_htt_h2t_ppdu_stats_req(struct ath12k *ar, u32 mask)
 	int ret;
 	int i;
 
-	for (i = 0; i < ab->hw_params->num_rxmda_per_pdev; i++) {
+	for (i = 0; i < ab->hw_params->num_rxdma_per_pdev; i++) {
 		skb = ath12k_htc_alloc_skb(ab, len);
 		if (!skb)
 			return -ENOMEM;
diff --git a/drivers/net/wireless/ath/ath12k/hw.c b/drivers/net/wireless/ath/ath12k/hw.c
index f4c8270158215..06f4432164886 100644
--- a/drivers/net/wireless/ath/ath12k/hw.c
+++ b/drivers/net/wireless/ath/ath12k/hw.c
@@ -884,7 +884,7 @@ static const struct ath12k_hw_params ath12k_hw_params[] = {
 		.hal_params = &ath12k_hw_hal_params_qcn9274,
 
 		.rxdma1_enable = false,
-		.num_rxmda_per_pdev = 1,
+		.num_rxdma_per_pdev = 1,
 		.num_rxdma_dst_ring = 0,
 		.rx_mac_buf_ring = false,
 		.vdev_start_delay = false,
@@ -956,7 +956,7 @@ static const struct ath12k_hw_params ath12k_hw_params[] = {
 		.hal_params = &ath12k_hw_hal_params_wcn7850,
 
 		.rxdma1_enable = false,
-		.num_rxmda_per_pdev = 2,
+		.num_rxdma_per_pdev = 2,
 		.num_rxdma_dst_ring = 1,
 		.rx_mac_buf_ring = true,
 		.vdev_start_delay = true,
@@ -1029,7 +1029,7 @@ static const struct ath12k_hw_params ath12k_hw_params[] = {
 		.hal_params = &ath12k_hw_hal_params_qcn9274,
 
 		.rxdma1_enable = false,
-		.num_rxmda_per_pdev = 1,
+		.num_rxdma_per_pdev = 1,
 		.num_rxdma_dst_ring = 0,
 		.rx_mac_buf_ring = false,
 		.vdev_start_delay = false,
diff --git a/drivers/net/wireless/ath/ath12k/hw.h b/drivers/net/wireless/ath/ath12k/hw.h
index 3f450ee93f34b..2a5a9d638d934 100644
--- a/drivers/net/wireless/ath/ath12k/hw.h
+++ b/drivers/net/wireless/ath/ath12k/hw.h
@@ -174,7 +174,7 @@ struct ath12k_hw_params {
 	const struct ath12k_hw_hal_params *hal_params;
 
 	bool rxdma1_enable:1;
-	int num_rxmda_per_pdev;
+	int num_rxdma_per_pdev;
 	int num_rxdma_dst_ring;
 	bool rx_mac_buf_ring:1;
 	bool vdev_start_delay:1;
diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index 9e9f58b5cbfb0..3004c7463be99 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -5693,7 +5693,7 @@ static int ath12k_reg_chan_list_event(struct ath12k_base *ab, struct sk_buff *sk
 		 * event. Otherwise, it goes to fallback.
 		 */
 		if (ab->hw_params->single_pdev_only &&
-		    pdev_idx < ab->hw_params->num_rxmda_per_pdev)
+		    pdev_idx < ab->hw_params->num_rxdma_per_pdev)
 			goto mem_free;
 		else
 			goto fallback;
-- 
GitLab


From 3b9344740843d965e9e37fba30620b3b1c0afa4f Mon Sep 17 00:00:00 2001
From: Jeff Johnson <quic_jjohnson@quicinc.com>
Date: Tue, 7 May 2024 13:45:03 +0300
Subject: [PATCH 031/950] wifi: ath12k: initialize 'ret' in
 ath12k_dp_rxdma_ring_sel_config_wcn7850()

smatch flagged the following issue:

drivers/net/wireless/ath/ath12k/dp_rx.c:4065 ath12k_dp_rxdma_ring_sel_config_wcn7850() error: uninitialized symbol 'ret'.

In ath12k_dp_rxdma_ring_sel_config_wcn7850() if it were ever the case
that ab->hw_params->num_rxdma_per_pdev was 0 then 'ret' would be
uninitialized when it is returned. This should never be the case, but
to be safe and to quiet smatch, add an initializer to the declaration
of 'ret'.

No functional changes, compile tested only.

Signed-off-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240504-ath12k_dp_rxdma_ring_sel_config_wcn7850-ret-v1-2-44d2843a2857@quicinc.com
---
 drivers/net/wireless/ath/ath12k/dp_rx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath12k/dp_rx.c b/drivers/net/wireless/ath/ath12k/dp_rx.c
index e3ff14cd283f7..37205e894afee 100644
--- a/drivers/net/wireless/ath/ath12k/dp_rx.c
+++ b/drivers/net/wireless/ath/ath12k/dp_rx.c
@@ -4004,7 +4004,7 @@ int ath12k_dp_rxdma_ring_sel_config_wcn7850(struct ath12k_base *ab)
 	struct ath12k_dp *dp = &ab->dp;
 	struct htt_rx_ring_tlv_filter tlv_filter = {0};
 	u32 ring_id;
-	int ret;
+	int ret = 0;
 	u32 hal_rx_desc_sz = ab->hal.hal_desc_sz;
 	int i;
 
-- 
GitLab


From 71b6e321e30271beb08772871c4f76777f49e402 Mon Sep 17 00:00:00 2001
From: Marc Gonzalez <mgonzalez@freebox.fr>
Date: Mon, 29 Apr 2024 16:04:51 +0200
Subject: [PATCH 032/950] dt-bindings: net: wireless: ath10k: add
 qcom,no-msa-ready-indicator prop

The ath10k driver waits for an "MSA_READY" indicator
to complete initialization. If the indicator is not
received, then the device remains unusable.

cf. ath10k_qmi_driver_event_work()

Several msm8998-based devices are affected by this issue.
Oddly, it seems safe to NOT wait for the indicator, and
proceed immediately when QMI_EVENT_SERVER_ARRIVE.

Jeff Johnson wrote:

  The feedback I received was "it might be ok to change all ath10k qmi
  to skip waiting for msa_ready", and it was pointed out that ath11k
  (and ath12k) do not wait for it.

  However with so many deployed devices, "might be ok" isn't a strong
  argument for changing the default behavior.

Kalle Valo first suggested setting a bit in firmware-5.bin to trigger
work-around in the driver. However, firmware-5.bin is parsed too late.
So we are stuck with a DT property.

Signed-off-by: Marc Gonzalez <mgonzalez@freebox.fr>
Reviewed-by: Bjorn Andersson <quic_bjorande@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Acked-by: Rob Herring (Arm) <robh@kernel.org>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/54ac2295-36b4-49fc-9583-a10db8d9d5d6@freebox.fr
---
 .../devicetree/bindings/net/wireless/qcom,ath10k.yaml        | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/Documentation/devicetree/bindings/net/wireless/qcom,ath10k.yaml b/Documentation/devicetree/bindings/net/wireless/qcom,ath10k.yaml
index 5c4498b762c89..070c4c9b86437 100644
--- a/Documentation/devicetree/bindings/net/wireless/qcom,ath10k.yaml
+++ b/Documentation/devicetree/bindings/net/wireless/qcom,ath10k.yaml
@@ -128,6 +128,11 @@ properties:
       Whether to skip executing an SCM call that reassigns the memory
       region ownership.
 
+  qcom,no-msa-ready-indicator:
+    type: boolean
+    description:
+      Don't wait for MSA_READY indicator to complete init.
+
   qcom,smem-states:
     $ref: /schemas/types.yaml#/definitions/phandle-array
     description: State bits used by the AP to signal the WLAN Q6.
-- 
GitLab


From 6d67d18014a8130defbca1972d7f0e0a8f8f259e Mon Sep 17 00:00:00 2001
From: Marc Gonzalez <mgonzalez@freebox.fr>
Date: Mon, 29 Apr 2024 16:06:29 +0200
Subject: [PATCH 033/950] wifi: ath10k: do not always wait for MSA_READY
 indicator

The ath10k driver waits for an "MSA_READY" indicator
to complete initialization. If the indicator is not
received, then the device remains unusable.

Several msm8998-based devices are affected by this issue.
Oddly, it seems safe to NOT wait for the indicator, and
proceed immediately when QMI_EVENT_SERVER_ARRIVE.

fw_version 0x100204b2
fw_build_timestamp 2019-09-04 03:01
fw_build_id QC_IMAGE_VERSION_STRING=WLAN.HL.1.0-01202-QCAHLSWMTPLZ-1.221523.2

Jeff Johnson wrote:

  The feedback I received was "it might be ok to change all ath10k qmi
  to skip waiting for msa_ready", and it was pointed out that ath11k
  (and ath12k) do not wait for it.

  However with so many deployed devices, "might be ok" isn't a strong
  argument for changing the default behavior.

Signed-off-by: Marc Gonzalez <mgonzalez@freebox.fr>
Reviewed-by: Bjorn Andersson <quic_bjorande@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/23540303-5816-45d5-a1af-5f09d645a73b@freebox.fr
---
 drivers/net/wireless/ath/ath10k/qmi.c | 11 +++++++++++
 drivers/net/wireless/ath/ath10k/qmi.h |  1 +
 2 files changed, 12 insertions(+)

diff --git a/drivers/net/wireless/ath/ath10k/qmi.c b/drivers/net/wireless/ath/ath10k/qmi.c
index 38e939f572a9e..f1f33af0170a0 100644
--- a/drivers/net/wireless/ath/ath10k/qmi.c
+++ b/drivers/net/wireless/ath/ath10k/qmi.c
@@ -1040,6 +1040,10 @@ static void ath10k_qmi_driver_event_work(struct work_struct *work)
 		switch (event->type) {
 		case ATH10K_QMI_EVENT_SERVER_ARRIVE:
 			ath10k_qmi_event_server_arrive(qmi);
+			if (qmi->no_msa_ready_indicator) {
+				ath10k_info(ar, "qmi not waiting for msa_ready indicator");
+				ath10k_qmi_event_msa_ready(qmi);
+			}
 			break;
 		case ATH10K_QMI_EVENT_SERVER_EXIT:
 			ath10k_qmi_event_server_exit(qmi);
@@ -1048,6 +1052,10 @@ static void ath10k_qmi_driver_event_work(struct work_struct *work)
 			ath10k_qmi_event_fw_ready_ind(qmi);
 			break;
 		case ATH10K_QMI_EVENT_MSA_READY_IND:
+			if (qmi->no_msa_ready_indicator) {
+				ath10k_warn(ar, "qmi unexpected msa_ready indicator");
+				break;
+			}
 			ath10k_qmi_event_msa_ready(qmi);
 			break;
 		default:
@@ -1077,6 +1085,9 @@ int ath10k_qmi_init(struct ath10k *ar, u32 msa_size)
 	if (of_property_read_bool(dev->of_node, "qcom,msa-fixed-perm"))
 		qmi->msa_fixed_perm = true;
 
+	if (of_property_read_bool(dev->of_node, "qcom,no-msa-ready-indicator"))
+		qmi->no_msa_ready_indicator = true;
+
 	ret = qmi_handle_init(&qmi->qmi_hdl,
 			      WLFW_BDF_DOWNLOAD_REQ_MSG_V01_MAX_MSG_LEN,
 			      &ath10k_qmi_ops, qmi_msg_handler);
diff --git a/drivers/net/wireless/ath/ath10k/qmi.h b/drivers/net/wireless/ath/ath10k/qmi.h
index 89464239fe96a..0816eb4e4a18a 100644
--- a/drivers/net/wireless/ath/ath10k/qmi.h
+++ b/drivers/net/wireless/ath/ath10k/qmi.h
@@ -107,6 +107,7 @@ struct ath10k_qmi {
 	char fw_build_timestamp[MAX_TIMESTAMP_LEN + 1];
 	struct ath10k_qmi_cal_data cal_data[MAX_NUM_CAL_V01];
 	bool msa_fixed_perm;
+	bool no_msa_ready_indicator;
 	enum ath10k_qmi_state state;
 };
 
-- 
GitLab


From 4f9206e8c2c15a3770e3eb0b9755a05d559fecea Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Wed, 8 May 2024 02:54:09 -0700
Subject: [PATCH 034/950] wifi: ath12k: allocate dummy net_device dynamically

Embedding net_device into structures prohibits the usage of flexible
arrays in the net_device structure. For more details, see the discussion
at [1].

Un-embed the net_device from struct ath12k_ext_irq_grp by converting it
into a pointer. Then use the leverage alloc_netdev_dummy() to allocate
the net_device object at ath12k_pci_ext_irq_config().

The free of the device occurs at ath12k_pci_free_ext_irq().

Link: https://lore.kernel.org/all/20240229225910.79e224cf@kernel.org/ [1]
Signed-off-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240508095410.1923198-1-leitao@debian.org
---
 drivers/net/wireless/ath/ath12k/core.h |  2 +-
 drivers/net/wireless/ath/ath12k/pci.c  | 27 +++++++++++++++++++++-----
 2 files changed, 23 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/core.h b/drivers/net/wireless/ath/ath12k/core.h
index bb6c1b562baf6..c6b7524ce3a05 100644
--- a/drivers/net/wireless/ath/ath12k/core.h
+++ b/drivers/net/wireless/ath/ath12k/core.h
@@ -146,7 +146,7 @@ struct ath12k_ext_irq_grp {
 	u32 grp_id;
 	u64 timestamp;
 	struct napi_struct napi;
-	struct net_device napi_ndev;
+	struct net_device *napi_ndev;
 };
 
 struct ath12k_smbios_bdf {
diff --git a/drivers/net/wireless/ath/ath12k/pci.c b/drivers/net/wireless/ath/ath12k/pci.c
index 16af046c33d9e..ac75e8e3916bd 100644
--- a/drivers/net/wireless/ath/ath12k/pci.c
+++ b/drivers/net/wireless/ath/ath12k/pci.c
@@ -350,6 +350,7 @@ static void ath12k_pci_free_ext_irq(struct ath12k_base *ab)
 			free_irq(ab->irq_num[irq_grp->irqs[j]], irq_grp);
 
 		netif_napi_del(&irq_grp->napi);
+		free_netdev(irq_grp->napi_ndev);
 	}
 }
 
@@ -560,8 +561,9 @@ static irqreturn_t ath12k_pci_ext_interrupt_handler(int irq, void *arg)
 static int ath12k_pci_ext_irq_config(struct ath12k_base *ab)
 {
 	struct ath12k_pci *ab_pci = ath12k_pci_priv(ab);
-	int i, j, ret, num_vectors = 0;
+	int i, j, n, ret, num_vectors = 0;
 	u32 user_base_data = 0, base_vector = 0, base_idx;
+	struct ath12k_ext_irq_grp *irq_grp;
 
 	base_idx = ATH12K_PCI_IRQ_CE0_OFFSET + CE_COUNT_MAX;
 	ret = ath12k_pci_get_user_msi_assignment(ab, "DP",
@@ -572,13 +574,18 @@ static int ath12k_pci_ext_irq_config(struct ath12k_base *ab)
 		return ret;
 
 	for (i = 0; i < ATH12K_EXT_IRQ_GRP_NUM_MAX; i++) {
-		struct ath12k_ext_irq_grp *irq_grp = &ab->ext_irq_grp[i];
+		irq_grp = &ab->ext_irq_grp[i];
 		u32 num_irq = 0;
 
 		irq_grp->ab = ab;
 		irq_grp->grp_id = i;
-		init_dummy_netdev(&irq_grp->napi_ndev);
-		netif_napi_add(&irq_grp->napi_ndev, &irq_grp->napi,
+		irq_grp->napi_ndev = alloc_netdev_dummy(0);
+		if (!irq_grp->napi_ndev) {
+			ret = -ENOMEM;
+			goto fail_allocate;
+		}
+
+		netif_napi_add(irq_grp->napi_ndev, &irq_grp->napi,
 			       ath12k_pci_ext_grp_napi_poll);
 
 		if (ab->hw_params->ring_mask->tx[i] ||
@@ -611,13 +618,23 @@ static int ath12k_pci_ext_irq_config(struct ath12k_base *ab)
 			if (ret) {
 				ath12k_err(ab, "failed request irq %d: %d\n",
 					   vector, ret);
-				return ret;
+				goto fail_request;
 			}
 		}
 		ath12k_pci_ext_grp_disable(irq_grp);
 	}
 
 	return 0;
+
+fail_request:
+	/* i ->napi_ndev was properly allocated. Free it also */
+	i += 1;
+fail_allocate:
+	for (n = 0; n < i; n++) {
+		irq_grp = &ab->ext_irq_grp[n];
+		free_netdev(irq_grp->napi_ndev);
+	}
+	return ret;
 }
 
 static int ath12k_pci_set_irq_affinity_hint(struct ath12k_pci *ab_pci,
-- 
GitLab


From aed9a1a4f7106ff99a882ad06318cebfa71016a2 Mon Sep 17 00:00:00 2001
From: Mohamed Ahmed <mohamedahmedegypt2001@gmail.com>
Date: Thu, 9 May 2024 23:43:52 +0300
Subject: [PATCH 035/950] drm/nouveau: use tile_mode and pte_kind for VM_BIND
 bo allocations

Allow PTE kind and tile mode on BO create with VM_BIND, and add a
GETPARAM to indicate this change. This is needed to support modifiers in
NVK and ensure correctness when dealing with the nouveau GL driver.

The userspace modifiers implementation this is for can be found here:
https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24795

Fixes: b88baab82871 ("drm/nouveau: implement new VM_BIND uAPI")
Signed-off-by: Mohamed Ahmed <mohamedahmedegypt2001@gmail.com>
Reviewed-by: Faith Ekstrand <faith.ekstrand@collabora.com>
Signed-off-by: Danilo Krummrich <dakr@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240509204352.7597-1-mohamedahmedegypt2001@gmail.com
---
 drivers/gpu/drm/nouveau/nouveau_abi16.c |  3 ++
 drivers/gpu/drm/nouveau/nouveau_bo.c    | 44 +++++++++++--------------
 include/uapi/drm/nouveau_drm.h          |  7 ++++
 3 files changed, 29 insertions(+), 25 deletions(-)

diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.c b/drivers/gpu/drm/nouveau/nouveau_abi16.c
index 80f74ee0fc786..47e53e17b4e58 100644
--- a/drivers/gpu/drm/nouveau/nouveau_abi16.c
+++ b/drivers/gpu/drm/nouveau/nouveau_abi16.c
@@ -272,6 +272,9 @@ nouveau_abi16_ioctl_getparam(ABI16_IOCTL_ARGS)
 		getparam->value = (u64)ttm_resource_manager_usage(vram_mgr);
 		break;
 	}
+	case NOUVEAU_GETPARAM_HAS_VMA_TILEMODE:
+		getparam->value = 1;
+		break;
 	default:
 		NV_PRINTK(dbg, cli, "unknown parameter %lld\n", getparam->param);
 		return -EINVAL;
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index db8cbf6151129..186add400ea5f 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -241,28 +241,28 @@ nouveau_bo_alloc(struct nouveau_cli *cli, u64 *size, int *align, u32 domain,
 	}
 
 	nvbo->contig = !(tile_flags & NOUVEAU_GEM_TILE_NONCONTIG);
-	if (!nouveau_cli_uvmm(cli) || internal) {
-		/* for BO noVM allocs, don't assign kinds */
-		if (cli->device.info.family >= NV_DEVICE_INFO_V0_FERMI) {
-			nvbo->kind = (tile_flags & 0x0000ff00) >> 8;
-			if (!nvif_mmu_kind_valid(mmu, nvbo->kind)) {
-				kfree(nvbo);
-				return ERR_PTR(-EINVAL);
-			}
 
-			nvbo->comp = mmu->kind[nvbo->kind] != nvbo->kind;
-		} else if (cli->device.info.family >= NV_DEVICE_INFO_V0_TESLA) {
-			nvbo->kind = (tile_flags & 0x00007f00) >> 8;
-			nvbo->comp = (tile_flags & 0x00030000) >> 16;
-			if (!nvif_mmu_kind_valid(mmu, nvbo->kind)) {
-				kfree(nvbo);
-				return ERR_PTR(-EINVAL);
-			}
-		} else {
-			nvbo->zeta = (tile_flags & 0x00000007);
+	if (cli->device.info.family >= NV_DEVICE_INFO_V0_FERMI) {
+		nvbo->kind = (tile_flags & 0x0000ff00) >> 8;
+		if (!nvif_mmu_kind_valid(mmu, nvbo->kind)) {
+			kfree(nvbo);
+			return ERR_PTR(-EINVAL);
+		}
+
+		nvbo->comp = mmu->kind[nvbo->kind] != nvbo->kind;
+	} else if (cli->device.info.family >= NV_DEVICE_INFO_V0_TESLA) {
+		nvbo->kind = (tile_flags & 0x00007f00) >> 8;
+		nvbo->comp = (tile_flags & 0x00030000) >> 16;
+		if (!nvif_mmu_kind_valid(mmu, nvbo->kind)) {
+			kfree(nvbo);
+			return ERR_PTR(-EINVAL);
 		}
-		nvbo->mode = tile_mode;
+	} else {
+		nvbo->zeta = (tile_flags & 0x00000007);
+	}
+	nvbo->mode = tile_mode;
 
+	if (!nouveau_cli_uvmm(cli) || internal) {
 		/* Determine the desirable target GPU page size for the buffer. */
 		for (i = 0; i < vmm->page_nr; i++) {
 			/* Because we cannot currently allow VMM maps to fail
@@ -304,12 +304,6 @@ nouveau_bo_alloc(struct nouveau_cli *cli, u64 *size, int *align, u32 domain,
 		}
 		nvbo->page = vmm->page[pi].shift;
 	} else {
-		/* reject other tile flags when in VM mode. */
-		if (tile_mode)
-			return ERR_PTR(-EINVAL);
-		if (tile_flags & ~NOUVEAU_GEM_TILE_NONCONTIG)
-			return ERR_PTR(-EINVAL);
-
 		/* Determine the desirable target GPU page size for the buffer. */
 		for (i = 0; i < vmm->page_nr; i++) {
 			/* Because we cannot currently allow VMM maps to fail
diff --git a/include/uapi/drm/nouveau_drm.h b/include/uapi/drm/nouveau_drm.h
index cd84227f1b42f..5402f77ee8594 100644
--- a/include/uapi/drm/nouveau_drm.h
+++ b/include/uapi/drm/nouveau_drm.h
@@ -68,6 +68,13 @@ extern "C" {
  */
 #define NOUVEAU_GETPARAM_VRAM_USED 19
 
+/*
+ * NOUVEAU_GETPARAM_HAS_VMA_TILEMODE
+ *
+ * Query whether tile mode and PTE kind are accepted with VM allocs or not.
+ */
+#define NOUVEAU_GETPARAM_HAS_VMA_TILEMODE 20
+
 struct drm_nouveau_getparam {
 	__u64 param;
 	__u64 value;
-- 
GitLab


From cea4066588308fa932b6b03486c608efff1d761c Mon Sep 17 00:00:00 2001
From: Zong-Zhe Yang <kevin_yang@realtek.com>
Date: Thu, 9 May 2024 17:06:43 +0800
Subject: [PATCH 036/950] wifi: rtw89: ser: avoid multiple deinit on same CAM

We did deinit CAM in STA iteration in VIF loop. But, the STA iteration
missed to restrict the target VIF. So, if there are multiple VIFs, we
would deinit a CAM multiple times. Now, fix it.

Signed-off-by: Zong-Zhe Yang <kevin_yang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://msgid.link/20240509090646.35304-2-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/ser.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/ser.c b/drivers/net/wireless/realtek/rtw89/ser.c
index 99896d85d2f81..5fc2faa9ba5a7 100644
--- a/drivers/net/wireless/realtek/rtw89/ser.c
+++ b/drivers/net/wireless/realtek/rtw89/ser.c
@@ -308,9 +308,13 @@ static void ser_reset_vif(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
 
 static void ser_sta_deinit_cam_iter(void *data, struct ieee80211_sta *sta)
 {
-	struct rtw89_vif *rtwvif = (struct rtw89_vif *)data;
-	struct rtw89_dev *rtwdev = rtwvif->rtwdev;
+	struct rtw89_vif *target_rtwvif = (struct rtw89_vif *)data;
 	struct rtw89_sta *rtwsta = (struct rtw89_sta *)sta->drv_priv;
+	struct rtw89_vif *rtwvif = rtwsta->rtwvif;
+	struct rtw89_dev *rtwdev = rtwvif->rtwdev;
+
+	if (rtwvif != target_rtwvif)
+		return;
 
 	if (rtwvif->net_type == RTW89_NET_TYPE_AP_MODE || sta->tdls)
 		rtw89_cam_deinit_addr_cam(rtwdev, &rtwsta->addr_cam);
-- 
GitLab


From 0448c65af9219ee296f844748d60448f7418180f Mon Sep 17 00:00:00 2001
From: Zong-Zhe Yang <kevin_yang@realtek.com>
Date: Thu, 9 May 2024 17:06:44 +0800
Subject: [PATCH 037/950] wifi: rtw89: cam: tweak relation between sec CAM and
 addr CAM

In original code architecture, sec CAM is a component of addr CAM.
Hence, sec CAM could not be shared. After MLO, each link has its own
addr CAM. However, one MLD PTK takes only one sec CAM but it needs to
work on multiple links' addr CAMs. So, we now manage sec CAMs in global
pool, and each of them is not bound to a single addr CAM now.

before:

+-----------------+         +--------------------+
| rtw89_{vif/sta} |   ...   | ieee80211_key_conf |
+-----------------+         +--------------------+
        ^                              |
        V                              | hw_key_idx
        |                              |
        |                              V
        |                             +--
   +----------+   addr_cam::key_idx   |  \        +---------+
   | addr_cam |<>---------------------|   |-------| sec_cam |
   +----------+                       |  /        +---------+
                                      +--

after:

+----------------------+         +--------------------+
| rtw89_{vif/sta}_link |   ...   | ieee80211_key_conf |
+----------------------+         +--------------------+
        ^                                   |
        V                                   | hw_key_idx
        |                                   |
        |                                   V
        |                                  --+                  +---------+
        |              +---------+        /  |  sec_cam_idx     | global  |
        |              | sec_cam |-------|   |----------------<>| sec_cam |
        |              +---------+        \  |                  | pool    |
        |                   ^              --+                  +---------+
        |                   |
        |               (*) |
   +----------+             |
   | addr_cam |-------------+
   +----------+

Signed-off-by: Zong-Zhe Yang <kevin_yang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://msgid.link/20240509090646.35304-3-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/cam.c   | 79 ++++++++++++++--------
 drivers/net/wireless/realtek/rtw89/core.c  | 20 ++----
 drivers/net/wireless/realtek/rtw89/core.h  |  2 +-
 drivers/net/wireless/realtek/rtw89/debug.c | 16 +++--
 4 files changed, 67 insertions(+), 50 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/cam.c b/drivers/net/wireless/realtek/rtw89/cam.c
index 1864f543a6c67..35291efbbae9f 100644
--- a/drivers/net/wireless/realtek/rtw89/cam.c
+++ b/drivers/net/wireless/realtek/rtw89/cam.c
@@ -211,6 +211,46 @@ static int rtw89_cam_get_addr_cam_key_idx(struct rtw89_addr_cam_entry *addr_cam,
 	return 0;
 }
 
+static int rtw89_cam_detach_sec_cam(struct rtw89_dev *rtwdev,
+				    struct ieee80211_vif *vif,
+				    struct ieee80211_sta *sta,
+				    const struct rtw89_sec_cam_entry *sec_cam,
+				    bool inform_fw)
+{
+	struct rtw89_sta *rtwsta = sta_to_rtwsta_safe(sta);
+	struct rtw89_vif *rtwvif;
+	struct rtw89_addr_cam_entry *addr_cam;
+	unsigned int i;
+	int ret = 0;
+
+	if (!vif) {
+		rtw89_err(rtwdev, "No iface for deleting sec cam\n");
+		return -EINVAL;
+	}
+
+	rtwvif = (struct rtw89_vif *)vif->drv_priv;
+	addr_cam = rtw89_get_addr_cam_of(rtwvif, rtwsta);
+
+	for_each_set_bit(i, addr_cam->sec_cam_map, RTW89_SEC_CAM_IN_ADDR_CAM) {
+		if (addr_cam->sec_ent[i] != sec_cam->sec_cam_idx)
+			continue;
+
+		clear_bit(i, addr_cam->sec_cam_map);
+	}
+
+	if (inform_fw) {
+		ret = rtw89_chip_h2c_dctl_sec_cam(rtwdev, rtwvif, rtwsta);
+		if (ret)
+			rtw89_err(rtwdev,
+				  "failed to update dctl cam del key: %d\n", ret);
+		ret = rtw89_fw_h2c_cam(rtwdev, rtwvif, rtwsta, NULL);
+		if (ret)
+			rtw89_err(rtwdev, "failed to update cam del key: %d\n", ret);
+	}
+
+	return ret;
+}
+
 static int rtw89_cam_attach_sec_cam(struct rtw89_dev *rtwdev,
 				    struct ieee80211_vif *vif,
 				    struct ieee80211_sta *sta,
@@ -242,10 +282,8 @@ static int rtw89_cam_attach_sec_cam(struct rtw89_dev *rtwdev,
 		return ret;
 	}
 
-	key->hw_key_idx = key_idx;
 	addr_cam->sec_ent_keyid[key_idx] = key->keyidx;
 	addr_cam->sec_ent[key_idx] = sec_cam->sec_cam_idx;
-	addr_cam->sec_entries[key_idx] = sec_cam;
 	set_bit(key_idx, addr_cam->sec_cam_map);
 	ret = rtw89_chip_h2c_dctl_sec_cam(rtwdev, rtwvif, rtwsta);
 	if (ret) {
@@ -258,7 +296,6 @@ static int rtw89_cam_attach_sec_cam(struct rtw89_dev *rtwdev,
 		rtw89_err(rtwdev, "failed to update addr cam sec entry: %d\n",
 			  ret);
 		clear_bit(key_idx, addr_cam->sec_cam_map);
-		addr_cam->sec_entries[key_idx] = NULL;
 		return ret;
 	}
 
@@ -295,6 +332,9 @@ static int rtw89_cam_sec_key_install(struct rtw89_dev *rtwdev,
 		goto err_release_cam;
 	}
 
+	key->hw_key_idx = sec_cam_idx;
+	cam_info->sec_entries[sec_cam_idx] = sec_cam;
+
 	sec_cam->sec_cam_idx = sec_cam_idx;
 	sec_cam->type = hw_key_type;
 	sec_cam->len = RTW89_SEC_CAM_LEN;
@@ -316,6 +356,7 @@ static int rtw89_cam_sec_key_install(struct rtw89_dev *rtwdev,
 	return 0;
 
 err_release_cam:
+	cam_info->sec_entries[sec_cam_idx] = NULL;
 	kfree(sec_cam);
 	clear_bit(sec_cam_idx, cam_info->sec_cam_map);
 	if (ext_key)
@@ -386,42 +427,22 @@ int rtw89_cam_sec_key_del(struct rtw89_dev *rtwdev,
 			  struct ieee80211_key_conf *key,
 			  bool inform_fw)
 {
-	struct rtw89_sta *rtwsta = sta_to_rtwsta_safe(sta);
 	struct rtw89_cam_info *cam_info = &rtwdev->cam_info;
-	struct rtw89_vif *rtwvif;
-	struct rtw89_addr_cam_entry *addr_cam;
-	struct rtw89_sec_cam_entry *sec_cam;
-	u8 key_idx = key->hw_key_idx;
+	const struct rtw89_sec_cam_entry *sec_cam;
 	u8 sec_cam_idx;
-	int ret = 0;
-
-	if (!vif) {
-		rtw89_err(rtwdev, "No iface for deleting sec cam\n");
-		return -EINVAL;
-	}
+	int ret;
 
-	rtwvif = (struct rtw89_vif *)vif->drv_priv;
-	addr_cam = rtw89_get_addr_cam_of(rtwvif, rtwsta);
-	sec_cam = addr_cam->sec_entries[key_idx];
+	sec_cam_idx = key->hw_key_idx;
+	sec_cam = cam_info->sec_entries[sec_cam_idx];
 	if (!sec_cam)
 		return -EINVAL;
 
-	/* detach sec cam from addr cam */
-	clear_bit(key_idx, addr_cam->sec_cam_map);
-	addr_cam->sec_entries[key_idx] = NULL;
-	if (inform_fw) {
-		ret = rtw89_chip_h2c_dctl_sec_cam(rtwdev, rtwvif, rtwsta);
-		if (ret)
-			rtw89_err(rtwdev, "failed to update dctl cam del key: %d\n", ret);
-		ret = rtw89_fw_h2c_cam(rtwdev, rtwvif, rtwsta, NULL);
-		if (ret)
-			rtw89_err(rtwdev, "failed to update cam del key: %d\n", ret);
-	}
+	ret = rtw89_cam_detach_sec_cam(rtwdev, vif, sta, sec_cam, inform_fw);
 
 	/* clear valid bit in addr cam will disable sec cam,
 	 * so we don't need to send H2C command again
 	 */
-	sec_cam_idx = sec_cam->sec_cam_idx;
+	cam_info->sec_entries[sec_cam_idx] = NULL;
 	clear_bit(sec_cam_idx, cam_info->sec_cam_map);
 	if (sec_cam->ext_key)
 		clear_bit(sec_cam_idx + 1, cam_info->sec_cam_map);
diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c
index 53997fa51ba0d..1382bd24ba3ba 100644
--- a/drivers/net/wireless/realtek/rtw89/core.c
+++ b/drivers/net/wireless/realtek/rtw89/core.c
@@ -499,31 +499,21 @@ static void
 rtw89_core_tx_update_sec_key(struct rtw89_dev *rtwdev,
 			     struct rtw89_core_tx_request *tx_req)
 {
+	struct rtw89_cam_info *cam_info = &rtwdev->cam_info;
 	const struct rtw89_chip_info *chip = rtwdev->chip;
-	struct ieee80211_vif *vif = tx_req->vif;
-	struct ieee80211_sta *sta = tx_req->sta;
+	const struct rtw89_sec_cam_entry *sec_cam;
 	struct ieee80211_tx_info *info;
 	struct ieee80211_key_conf *key;
-	struct rtw89_vif *rtwvif;
-	struct rtw89_sta *rtwsta = sta_to_rtwsta_safe(sta);
-	struct rtw89_addr_cam_entry *addr_cam;
-	struct rtw89_sec_cam_entry *sec_cam;
 	struct rtw89_tx_desc_info *desc_info = &tx_req->desc_info;
 	struct sk_buff *skb = tx_req->skb;
 	u8 sec_type = RTW89_SEC_KEY_TYPE_NONE;
+	u8 sec_cam_idx;
 	u64 pn64;
 
-	if (!vif) {
-		rtw89_warn(rtwdev, "cannot set sec key without vif\n");
-		return;
-	}
-
-	rtwvif = (struct rtw89_vif *)vif->drv_priv;
-	addr_cam = rtw89_get_addr_cam_of(rtwvif, rtwsta);
-
 	info = IEEE80211_SKB_CB(skb);
 	key = info->control.hw_key;
-	sec_cam = addr_cam->sec_entries[key->hw_key_idx];
+	sec_cam_idx = key->hw_key_idx;
+	sec_cam = cam_info->sec_entries[sec_cam_idx];
 	if (!sec_cam) {
 		rtw89_warn(rtwdev, "sec cam entry is empty\n");
 		return;
diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index 0648458110cef..32ae500579bb3 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -3249,7 +3249,6 @@ struct rtw89_addr_cam_entry {
 	DECLARE_BITMAP(sec_cam_map, RTW89_SEC_CAM_IN_ADDR_CAM);
 	u8 sec_ent_keyid[RTW89_SEC_CAM_IN_ADDR_CAM];
 	u8 sec_ent[RTW89_SEC_CAM_IN_ADDR_CAM];
-	struct rtw89_sec_cam_entry *sec_entries[RTW89_SEC_CAM_IN_ADDR_CAM];
 };
 
 struct rtw89_bssid_cam_entry {
@@ -4436,6 +4435,7 @@ struct rtw89_cam_info {
 	DECLARE_BITMAP(sec_cam_map, RTW89_MAX_SEC_CAM_NUM);
 	DECLARE_BITMAP(ba_cam_map, RTW89_MAX_BA_CAM_NUM);
 	struct rtw89_ba_cam_entry ba_cam_entry[RTW89_MAX_BA_CAM_NUM];
+	const struct rtw89_sec_cam_entry *sec_entries[RTW89_MAX_SEC_CAM_NUM];
 };
 
 enum rtw89_sar_sources {
diff --git a/drivers/net/wireless/realtek/rtw89/debug.c b/drivers/net/wireless/realtek/rtw89/debug.c
index affffc4092ba3..210f192ac9ec4 100644
--- a/drivers/net/wireless/realtek/rtw89/debug.c
+++ b/drivers/net/wireless/realtek/rtw89/debug.c
@@ -3645,17 +3645,21 @@ static int rtw89_debug_priv_phy_info_get(struct seq_file *m, void *v)
 }
 
 static void rtw89_dump_addr_cam(struct seq_file *m,
+				struct rtw89_dev *rtwdev,
 				struct rtw89_addr_cam_entry *addr_cam)
 {
-	struct rtw89_sec_cam_entry *sec_entry;
+	struct rtw89_cam_info *cam_info = &rtwdev->cam_info;
+	const struct rtw89_sec_cam_entry *sec_entry;
+	u8 sec_cam_idx;
 	int i;
 
 	seq_printf(m, "\taddr_cam_idx=%u\n", addr_cam->addr_cam_idx);
 	seq_printf(m, "\t-> bssid_cam_idx=%u\n", addr_cam->bssid_cam_idx);
 	seq_printf(m, "\tsec_cam_bitmap=%*ph\n", (int)sizeof(addr_cam->sec_cam_map),
 		   addr_cam->sec_cam_map);
-	for (i = 0; i < RTW89_SEC_CAM_IN_ADDR_CAM; i++) {
-		sec_entry = addr_cam->sec_entries[i];
+	for_each_set_bit(i, addr_cam->sec_cam_map, RTW89_SEC_CAM_IN_ADDR_CAM) {
+		sec_cam_idx = addr_cam->sec_ent[i];
+		sec_entry = cam_info->sec_entries[sec_cam_idx];
 		if (!sec_entry)
 			continue;
 		seq_printf(m, "\tsec[%d]: sec_cam_idx %u", i, sec_entry->sec_cam_idx);
@@ -3694,12 +3698,13 @@ static
 void rtw89_vif_ids_get_iter(void *data, u8 *mac, struct ieee80211_vif *vif)
 {
 	struct rtw89_vif *rtwvif = (struct rtw89_vif *)vif->drv_priv;
+	struct rtw89_dev *rtwdev = rtwvif->rtwdev;
 	struct seq_file *m = (struct seq_file *)data;
 	struct rtw89_bssid_cam_entry *bssid_cam = &rtwvif->bssid_cam;
 
 	seq_printf(m, "VIF [%d] %pM\n", rtwvif->mac_id, rtwvif->mac_addr);
 	seq_printf(m, "\tbssid_cam_idx=%u\n", bssid_cam->bssid_cam_idx);
-	rtw89_dump_addr_cam(m, &rtwvif->addr_cam);
+	rtw89_dump_addr_cam(m, rtwdev, &rtwvif->addr_cam);
 	rtw89_dump_pkt_offload(m, &rtwvif->general_pkt_list, "\tpkt_ofld[GENERAL]: ");
 }
 
@@ -3726,11 +3731,12 @@ static void rtw89_dump_ba_cam(struct seq_file *m, struct rtw89_sta *rtwsta)
 static void rtw89_sta_ids_get_iter(void *data, struct ieee80211_sta *sta)
 {
 	struct rtw89_sta *rtwsta = (struct rtw89_sta *)sta->drv_priv;
+	struct rtw89_dev *rtwdev = rtwsta->rtwdev;
 	struct seq_file *m = (struct seq_file *)data;
 
 	seq_printf(m, "STA [%d] %pM %s\n", rtwsta->mac_id, sta->addr,
 		   sta->tdls ? "(TDLS)" : "");
-	rtw89_dump_addr_cam(m, &rtwsta->addr_cam);
+	rtw89_dump_addr_cam(m, rtwdev, &rtwsta->addr_cam);
 	rtw89_dump_ba_cam(m, rtwsta);
 }
 
-- 
GitLab


From e9f1a901c9cc67ffb610ada8c2f4a6382ceb045a Mon Sep 17 00:00:00 2001
From: Zong-Zhe Yang <kevin_yang@realtek.com>
Date: Thu, 9 May 2024 17:06:45 +0800
Subject: [PATCH 038/950] wifi: rtw89: switch to register vif_cfg_changed and
 link_info_changed

For impending MLO support, we drop bss_info_changed callback ahead and
switch to register new callbacks, vif_cfg_changed and link_info_changed,
which are introduced by mac80211 for multi-link point of view.

Besides, there is a place where we called ieee80211_find_sta() under
station mode. To work on both non-MLD and MLD connection, we should
call ieee80211_find_sta() with vif->cfg.ap_addr.

Signed-off-by: Zong-Zhe Yang <kevin_yang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://msgid.link/20240509090646.35304-4-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/mac80211.c | 42 ++++++++++++-------
 1 file changed, 27 insertions(+), 15 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/mac80211.c b/drivers/net/wireless/realtek/rtw89/mac80211.c
index 1ec97250e88e5..41b286da3d591 100644
--- a/drivers/net/wireless/realtek/rtw89/mac80211.c
+++ b/drivers/net/wireless/realtek/rtw89/mac80211.c
@@ -397,15 +397,14 @@ static void rtw89_conf_tx(struct rtw89_dev *rtwdev,
 }
 
 static void rtw89_station_mode_sta_assoc(struct rtw89_dev *rtwdev,
-					 struct ieee80211_vif *vif,
-					 struct ieee80211_bss_conf *conf)
+					 struct ieee80211_vif *vif)
 {
 	struct ieee80211_sta *sta;
 
 	if (vif->type != NL80211_IFTYPE_STATION)
 		return;
 
-	sta = ieee80211_find_sta(vif, conf->bssid);
+	sta = ieee80211_find_sta(vif, vif->cfg.ap_addr);
 	if (!sta) {
 		rtw89_err(rtwdev, "can't find sta to set sta_assoc state\n");
 		return;
@@ -416,10 +415,8 @@ static void rtw89_station_mode_sta_assoc(struct rtw89_dev *rtwdev,
 	rtw89_core_sta_assoc(rtwdev, vif, sta);
 }
 
-static void rtw89_ops_bss_info_changed(struct ieee80211_hw *hw,
-				       struct ieee80211_vif *vif,
-				       struct ieee80211_bss_conf *conf,
-				       u64 changed)
+static void rtw89_ops_vif_cfg_changed(struct ieee80211_hw *hw,
+				      struct ieee80211_vif *vif, u64 changed)
 {
 	struct rtw89_dev *rtwdev = hw->priv;
 	struct rtw89_vif *rtwvif = (struct rtw89_vif *)vif->drv_priv;
@@ -429,7 +426,7 @@ static void rtw89_ops_bss_info_changed(struct ieee80211_hw *hw,
 
 	if (changed & BSS_CHANGED_ASSOC) {
 		if (vif->cfg.assoc) {
-			rtw89_station_mode_sta_assoc(rtwdev, vif, conf);
+			rtw89_station_mode_sta_assoc(rtwdev, vif);
 			rtw89_phy_set_bss_color(rtwdev, vif);
 			rtw89_chip_cfg_txpwr_ul_tb_offset(rtwdev, vif);
 			rtw89_mac_port_update(rtwdev, rtwvif);
@@ -445,6 +442,26 @@ static void rtw89_ops_bss_info_changed(struct ieee80211_hw *hw,
 		}
 	}
 
+	if (changed & BSS_CHANGED_PS)
+		rtw89_recalc_lps(rtwdev);
+
+	if (changed & BSS_CHANGED_ARP_FILTER)
+		rtwvif->ip_addr = vif->cfg.arp_addr_list[0];
+
+	mutex_unlock(&rtwdev->mutex);
+}
+
+static void rtw89_ops_link_info_changed(struct ieee80211_hw *hw,
+					struct ieee80211_vif *vif,
+					struct ieee80211_bss_conf *conf,
+					u64 changed)
+{
+	struct rtw89_dev *rtwdev = hw->priv;
+	struct rtw89_vif *rtwvif = (struct rtw89_vif *)vif->drv_priv;
+
+	mutex_lock(&rtwdev->mutex);
+	rtw89_leave_ps_mode(rtwdev);
+
 	if (changed & BSS_CHANGED_BSSID) {
 		ether_addr_copy(rtwvif->bssid, conf->bssid);
 		rtw89_cam_bssid_changed(rtwdev, rtwvif);
@@ -470,12 +487,6 @@ static void rtw89_ops_bss_info_changed(struct ieee80211_hw *hw,
 	if (changed & BSS_CHANGED_CQM)
 		rtw89_fw_h2c_set_bcn_fltr_cfg(rtwdev, vif, true);
 
-	if (changed & BSS_CHANGED_PS)
-		rtw89_recalc_lps(rtwdev);
-
-	if (changed & BSS_CHANGED_ARP_FILTER)
-		rtwvif->ip_addr = vif->cfg.arp_addr_list[0];
-
 	mutex_unlock(&rtwdev->mutex);
 }
 
@@ -1143,7 +1154,8 @@ const struct ieee80211_ops rtw89_ops = {
 	.change_interface       = rtw89_ops_change_interface,
 	.remove_interface	= rtw89_ops_remove_interface,
 	.configure_filter	= rtw89_ops_configure_filter,
-	.bss_info_changed	= rtw89_ops_bss_info_changed,
+	.vif_cfg_changed	= rtw89_ops_vif_cfg_changed,
+	.link_info_changed	= rtw89_ops_link_info_changed,
 	.start_ap		= rtw89_ops_start_ap,
 	.stop_ap		= rtw89_ops_stop_ap,
 	.set_tim		= rtw89_ops_set_tim,
-- 
GitLab


From 578bdd984f4562a47ec8d57742affd688688a0a3 Mon Sep 17 00:00:00 2001
From: Zong-Zhe Yang <kevin_yang@realtek.com>
Date: Thu, 9 May 2024 17:06:46 +0800
Subject: [PATCH 039/950] wifi: rtw89: support mac_id number according to chip

On 802.11be chips, to consider MLO, HW doesn't design number
of support mac_id as large as before. And, it might be various
according to chip. For example, old chips support mac_id up to
128, but RTL8922a only supports mac_id up to 32.

Besides, the mac_id acquiring function will be extended when
impending MLO support.

Signed-off-by: Zong-Zhe Yang <kevin_yang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://msgid.link/20240509090646.35304-5-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.c     | 28 +++++++++++++++----
 drivers/net/wireless/realtek/rtw89/core.h     |  3 ++
 drivers/net/wireless/realtek/rtw89/mac.c      |  7 ++---
 drivers/net/wireless/realtek/rtw89/rtw8851b.c |  1 +
 drivers/net/wireless/realtek/rtw89/rtw8852a.c |  1 +
 drivers/net/wireless/realtek/rtw89/rtw8852b.c |  1 +
 drivers/net/wireless/realtek/rtw89/rtw8852c.c |  1 +
 drivers/net/wireless/realtek/rtw89/rtw8922a.c |  1 +
 8 files changed, 34 insertions(+), 9 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c
index 1382bd24ba3ba..8b6cb310eabac 100644
--- a/drivers/net/wireless/realtek/rtw89/core.c
+++ b/drivers/net/wireless/realtek/rtw89/core.c
@@ -3343,14 +3343,13 @@ int rtw89_core_sta_add(struct rtw89_dev *rtwdev,
 					 BTC_ROLE_MSTS_STA_CONN_START);
 		rtw89_chip_rfk_channel(rtwdev);
 	} else if (vif->type == NL80211_IFTYPE_AP || sta->tdls) {
-		rtwsta->mac_id = rtw89_core_acquire_bit_map(rtwdev->mac_id_map,
-							    RTW89_MAX_MAC_ID_NUM);
+		rtwsta->mac_id = rtw89_acquire_mac_id(rtwdev);
 		if (rtwsta->mac_id == RTW89_MAX_MAC_ID_NUM)
 			return -ENOSPC;
 
 		ret = rtw89_mac_set_macid_pause(rtwdev, rtwsta->mac_id, false);
 		if (ret) {
-			rtw89_core_release_bit_map(rtwdev->mac_id_map, rtwsta->mac_id);
+			rtw89_release_mac_id(rtwdev, rtwsta->mac_id);
 			rtw89_warn(rtwdev, "failed to send h2c macid pause\n");
 			return ret;
 		}
@@ -3358,7 +3357,7 @@ int rtw89_core_sta_add(struct rtw89_dev *rtwdev,
 		ret = rtw89_fw_h2c_role_maintain(rtwdev, rtwvif, rtwsta,
 						 RTW89_ROLE_CREATE);
 		if (ret) {
-			rtw89_core_release_bit_map(rtwdev->mac_id_map, rtwsta->mac_id);
+			rtw89_release_mac_id(rtwdev, rtwsta->mac_id);
 			rtw89_warn(rtwdev, "failed to send h2c role info\n");
 			return ret;
 		}
@@ -3531,7 +3530,7 @@ int rtw89_core_sta_remove(struct rtw89_dev *rtwdev,
 		rtw89_btc_ntfy_role_info(rtwdev, rtwvif, rtwsta,
 					 BTC_ROLE_MSTS_STA_DIS_CONN);
 	} else if (vif->type == NL80211_IFTYPE_AP || sta->tdls) {
-		rtw89_core_release_bit_map(rtwdev->mac_id_map, rtwsta->mac_id);
+		rtw89_release_mac_id(rtwdev, rtwsta->mac_id);
 
 		ret = rtw89_fw_h2c_role_maintain(rtwdev, rtwvif, rtwsta,
 						 RTW89_ROLE_REMOVE);
@@ -4181,6 +4180,25 @@ void rtw89_core_stop(struct rtw89_dev *rtwdev)
 	rtw89_hci_reset(rtwdev);
 }
 
+u8 rtw89_acquire_mac_id(struct rtw89_dev *rtwdev)
+{
+	const struct rtw89_chip_info *chip = rtwdev->chip;
+	u8 mac_id_num = chip->support_macid_num;
+	u8 mac_id;
+
+	mac_id = find_first_zero_bit(rtwdev->mac_id_map, mac_id_num);
+	if (mac_id == mac_id_num)
+		return RTW89_MAX_MAC_ID_NUM;
+
+	set_bit(mac_id, rtwdev->mac_id_map);
+	return mac_id;
+}
+
+void rtw89_release_mac_id(struct rtw89_dev *rtwdev, u8 mac_id)
+{
+	clear_bit(mac_id, rtwdev->mac_id_map);
+}
+
 int rtw89_core_init(struct rtw89_dev *rtwdev)
 {
 	struct rtw89_btc *btc = &rtwdev->btc;
diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index 32ae500579bb3..c0f2afb4888a9 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -4143,6 +4143,7 @@ struct rtw89_chip_info {
 	u8 wde_qempty_acq_grpnum;
 	u8 wde_qempty_mgq_grpsel;
 	u32 rf_base_addr[2];
+	u8 support_macid_num;
 	u8 support_chanctx_num;
 	u8 support_bands;
 	u16 support_bandwidths;
@@ -6470,6 +6471,8 @@ struct rtw89_dev *rtw89_alloc_ieee80211_hw(struct device *device,
 					   u32 bus_data_size,
 					   const struct rtw89_chip_info *chip);
 void rtw89_free_ieee80211_hw(struct rtw89_dev *rtwdev);
+u8 rtw89_acquire_mac_id(struct rtw89_dev *rtwdev);
+void rtw89_release_mac_id(struct rtw89_dev *rtwdev, u8 mac_id);
 void rtw89_core_set_chip_txpwr(struct rtw89_dev *rtwdev);
 void rtw89_get_default_chandef(struct cfg80211_chan_def *chandef);
 void rtw89_get_channel_params(const struct cfg80211_chan_def *chandef,
diff --git a/drivers/net/wireless/realtek/rtw89/mac.c b/drivers/net/wireless/realtek/rtw89/mac.c
index 3fe0046f6eaa2..baefc30b88c4d 100644
--- a/drivers/net/wireless/realtek/rtw89/mac.c
+++ b/drivers/net/wireless/realtek/rtw89/mac.c
@@ -4664,8 +4664,7 @@ int rtw89_mac_add_vif(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
 {
 	int ret;
 
-	rtwvif->mac_id = rtw89_core_acquire_bit_map(rtwdev->mac_id_map,
-						    RTW89_MAX_MAC_ID_NUM);
+	rtwvif->mac_id = rtw89_acquire_mac_id(rtwdev);
 	if (rtwvif->mac_id == RTW89_MAX_MAC_ID_NUM)
 		return -ENOSPC;
 
@@ -4676,7 +4675,7 @@ int rtw89_mac_add_vif(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
 	return 0;
 
 release_mac_id:
-	rtw89_core_release_bit_map(rtwdev->mac_id_map, rtwvif->mac_id);
+	rtw89_release_mac_id(rtwdev, rtwvif->mac_id);
 
 	return ret;
 }
@@ -4686,7 +4685,7 @@ int rtw89_mac_remove_vif(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
 	int ret;
 
 	ret = rtw89_mac_vif_deinit(rtwdev, rtwvif);
-	rtw89_core_release_bit_map(rtwdev->mac_id_map, rtwvif->mac_id);
+	rtw89_release_mac_id(rtwdev, rtwvif->mac_id);
 
 	return ret;
 }
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8851b.c b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
index 87b51823244dc..78e276f321c20 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8851b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
@@ -2447,6 +2447,7 @@ const struct rtw89_chip_info rtw8851b_chip_info = {
 	.dig_table		= NULL,
 	.dig_regs		= &rtw8851b_dig_regs,
 	.tssi_dbw_table		= NULL,
+	.support_macid_num	= RTW89_MAX_MAC_ID_NUM,
 	.support_chanctx_num	= 0,
 	.support_rnr		= false,
 	.support_bands		= BIT(NL80211_BAND_2GHZ) |
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852a.c b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
index e93cee1456bda..aebbceea93f84 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852a.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
@@ -2162,6 +2162,7 @@ const struct rtw89_chip_info rtw8852a_chip_info = {
 	.dig_table		= &rtw89_8852a_phy_dig_table,
 	.dig_regs		= &rtw8852a_dig_regs,
 	.tssi_dbw_table		= NULL,
+	.support_macid_num	= RTW89_MAX_MAC_ID_NUM,
 	.support_chanctx_num	= 1,
 	.support_rnr		= false,
 	.support_bands		= BIT(NL80211_BAND_2GHZ) |
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852b.c b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
index d351096fa4b41..53ae00b5ab7cc 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
@@ -2610,6 +2610,7 @@ const struct rtw89_chip_info rtw8852b_chip_info = {
 	.dig_table		= NULL,
 	.dig_regs		= &rtw8852b_dig_regs,
 	.tssi_dbw_table		= NULL,
+	.support_macid_num	= RTW89_MAX_MAC_ID_NUM,
 	.support_chanctx_num	= 0,
 	.support_rnr		= false,
 	.support_bands		= BIT(NL80211_BAND_2GHZ) |
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852c.c b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
index 3571b41786d7c..544ea1d3b577f 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852c.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
@@ -2941,6 +2941,7 @@ const struct rtw89_chip_info rtw8852c_chip_info = {
 	.dig_table		= NULL,
 	.dig_regs		= &rtw8852c_dig_regs,
 	.tssi_dbw_table		= &rtw89_8852c_tssi_dbw_table,
+	.support_macid_num	= RTW89_MAX_MAC_ID_NUM,
 	.support_chanctx_num	= 2,
 	.support_rnr		= false,
 	.support_bands		= BIT(NL80211_BAND_2GHZ) |
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8922a.c b/drivers/net/wireless/realtek/rtw89/rtw8922a.c
index 3b3ea3a7c19ae..cc4f251caadd6 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8922a.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8922a.c
@@ -2544,6 +2544,7 @@ const struct rtw89_chip_info rtw8922a_chip_info = {
 	.dig_table		= NULL,
 	.dig_regs		= &rtw8922a_dig_regs,
 	.tssi_dbw_table		= NULL,
+	.support_macid_num	= 32,
 	.support_chanctx_num	= 2,
 	.support_rnr		= true,
 	.support_bands		= BIT(NL80211_BAND_2GHZ) |
-- 
GitLab


From 02b682d54598f61cbb7dbb14d98ec1801112b878 Mon Sep 17 00:00:00 2001
From: Andrii Batyiev <batyiev@gmail.com>
Date: Thu, 9 May 2024 13:11:25 +0300
Subject: [PATCH 040/950] wifi: iwlegacy: do not skip frames with bad FCS

Monitor/sniffer mode benefits from all types of frames, even if FCS
check fails. But we must mark frames as such.

Tested on iwl3945 only.

Signed-off-by: Andrii Batyiev <batyiev@gmail.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://msgid.link/20240509101140.32664-1-batyiev@gmail.com
---
 drivers/net/wireless/intel/iwlegacy/3945.c     | 2 +-
 drivers/net/wireless/intel/iwlegacy/4965-mac.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlegacy/3945.c b/drivers/net/wireless/intel/iwlegacy/3945.c
index a773939b8c2aa..1fab7849f56d1 100644
--- a/drivers/net/wireless/intel/iwlegacy/3945.c
+++ b/drivers/net/wireless/intel/iwlegacy/3945.c
@@ -566,7 +566,7 @@ il3945_hdl_rx(struct il_priv *il, struct il_rx_buf *rxb)
 	if (!(rx_end->status & RX_RES_STATUS_NO_CRC32_ERROR) ||
 	    !(rx_end->status & RX_RES_STATUS_NO_RXE_OVERFLOW)) {
 		D_RX("Bad CRC or FIFO: 0x%08X.\n", rx_end->status);
-		return;
+		rx_status.flag |= RX_FLAG_FAILED_FCS_CRC;
 	}
 
 	/* Convert 3945's rssi indicator to dBm */
diff --git a/drivers/net/wireless/intel/iwlegacy/4965-mac.c b/drivers/net/wireless/intel/iwlegacy/4965-mac.c
index 4beb7be6d51df..d018f56be9664 100644
--- a/drivers/net/wireless/intel/iwlegacy/4965-mac.c
+++ b/drivers/net/wireless/intel/iwlegacy/4965-mac.c
@@ -664,7 +664,7 @@ il4965_hdl_rx(struct il_priv *il, struct il_rx_buf *rxb)
 	if (!(rx_pkt_status & RX_RES_STATUS_NO_CRC32_ERROR) ||
 	    !(rx_pkt_status & RX_RES_STATUS_NO_RXE_OVERFLOW)) {
 		D_RX("Bad CRC or FIFO: 0x%08X.\n", le32_to_cpu(rx_pkt_status));
-		return;
+		rx_status.flag |= RX_FLAG_FAILED_FCS_CRC;
 	}
 
 	/* This will be used in several places later */
-- 
GitLab


From c636fa85feb450ca414a10010ed05361a73c93a6 Mon Sep 17 00:00:00 2001
From: Samasth Norway Ananda <samasth.norway.ananda@oracle.com>
Date: Thu, 9 May 2024 16:10:37 -0700
Subject: [PATCH 041/950] wifi: brcmsmac: LCN PHY code is used for BCM4313
 2G-only device

The band_idx variable in the function wlc_lcnphy_tx_iqlo_cal() will
never be set to 1 as BCM4313 is the only device for which the LCN PHY
code is used. This is a 2G-only device.

Fixes: 5b435de0d786 ("net: wireless: add brcm80211 drivers")
Signed-off-by: Samasth Norway Ananda <samasth.norway.ananda@oracle.com>
Acked-by: Arend van Spriel <arend.vanspriel@broadcom.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://msgid.link/20240509231037.2014109-1-samasth.norway.ananda@oracle.com
---
 .../broadcom/brcm80211/brcmsmac/phy/phy_lcn.c  | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_lcn.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_lcn.c
index aae2cf95fe958..e472591f321bd 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_lcn.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_lcn.c
@@ -2567,7 +2567,6 @@ wlc_lcnphy_tx_iqlo_cal(struct brcms_phy *pi,
 
 	struct lcnphy_txgains cal_gains, temp_gains;
 	u16 hash;
-	u8 band_idx;
 	int j;
 	u16 ncorr_override[5];
 	u16 syst_coeffs[] = { 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
@@ -2599,6 +2598,9 @@ wlc_lcnphy_tx_iqlo_cal(struct brcms_phy *pi,
 	u16 *values_to_save;
 	struct brcms_phy_lcnphy *pi_lcn = pi->u.pi_lcnphy;
 
+	if (WARN_ON(CHSPEC_IS5G(pi->radio_chanspec)))
+		return;
+
 	values_to_save = kmalloc_array(20, sizeof(u16), GFP_ATOMIC);
 	if (NULL == values_to_save)
 		return;
@@ -2662,20 +2664,18 @@ wlc_lcnphy_tx_iqlo_cal(struct brcms_phy *pi,
 	hash = (target_gains->gm_gain << 8) |
 	       (target_gains->pga_gain << 4) | (target_gains->pad_gain);
 
-	band_idx = (CHSPEC_IS5G(pi->radio_chanspec) ? 1 : 0);
-
 	cal_gains = *target_gains;
 	memset(ncorr_override, 0, sizeof(ncorr_override));
-	for (j = 0; j < iqcal_gainparams_numgains_lcnphy[band_idx]; j++) {
-		if (hash == tbl_iqcal_gainparams_lcnphy[band_idx][j][0]) {
+	for (j = 0; j < iqcal_gainparams_numgains_lcnphy[0]; j++) {
+		if (hash == tbl_iqcal_gainparams_lcnphy[0][j][0]) {
 			cal_gains.gm_gain =
-				tbl_iqcal_gainparams_lcnphy[band_idx][j][1];
+				tbl_iqcal_gainparams_lcnphy[0][j][1];
 			cal_gains.pga_gain =
-				tbl_iqcal_gainparams_lcnphy[band_idx][j][2];
+				tbl_iqcal_gainparams_lcnphy[0][j][2];
 			cal_gains.pad_gain =
-				tbl_iqcal_gainparams_lcnphy[band_idx][j][3];
+				tbl_iqcal_gainparams_lcnphy[0][j][3];
 			memcpy(ncorr_override,
-			       &tbl_iqcal_gainparams_lcnphy[band_idx][j][3],
+			       &tbl_iqcal_gainparams_lcnphy[0][j][3],
 			       sizeof(ncorr_override));
 			break;
 		}
-- 
GitLab


From 8e1debd82466a3fe711784ab37e6b54e56011267 Mon Sep 17 00:00:00 2001
From: Sebastian Gottschall <s.gottschall@dd-wrt.com>
Date: Mon, 13 May 2024 17:22:25 +0300
Subject: [PATCH 042/950] wifi: ath10k: add LED and GPIO controlling support
 for various chipsets

Adds LED and GPIO Control support for 988x, 9887, 9888, 99x0, 9984
based chipsets with on chipset connected led's using WMI Firmware API.
The LED device will get available named as "ath10k-phyX" at sysfs and
can be controlled with various triggers.
Adds also debugfs interface for gpio control.

Signed-off-by: Sebastian Gottschall <s.gottschall@dd-wrt.com>
Reviewed-by: Steve deRosier <derosier@cal-sierra.com>
[kvalo: major reorg and cleanup]
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
[ansuel: rebase and small cleanup]
Signed-off-by: Christian Marangi <ansuelsmth@gmail.com>
Tested-by: Stefan Lippers-Hollmann <s.l-h@gmx.de>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20230611080505.17393-1-ansuelsmth@gmail.com
---
 drivers/net/wireless/ath/ath10k/Kconfig   |  6 ++
 drivers/net/wireless/ath/ath10k/Makefile  |  1 +
 drivers/net/wireless/ath/ath10k/core.c    | 32 ++++++++
 drivers/net/wireless/ath/ath10k/core.h    |  8 ++
 drivers/net/wireless/ath/ath10k/hw.h      |  1 +
 drivers/net/wireless/ath/ath10k/leds.c    | 90 +++++++++++++++++++++++
 drivers/net/wireless/ath/ath10k/leds.h    | 34 +++++++++
 drivers/net/wireless/ath/ath10k/mac.c     |  1 +
 drivers/net/wireless/ath/ath10k/wmi-ops.h | 32 ++++++++
 drivers/net/wireless/ath/ath10k/wmi-tlv.c |  2 +
 drivers/net/wireless/ath/ath10k/wmi.c     | 54 ++++++++++++++
 drivers/net/wireless/ath/ath10k/wmi.h     | 35 +++++++++
 12 files changed, 296 insertions(+)
 create mode 100644 drivers/net/wireless/ath/ath10k/leds.c
 create mode 100644 drivers/net/wireless/ath/ath10k/leds.h

diff --git a/drivers/net/wireless/ath/ath10k/Kconfig b/drivers/net/wireless/ath/ath10k/Kconfig
index e6ea884cafc19..76572cd2e1bae 100644
--- a/drivers/net/wireless/ath/ath10k/Kconfig
+++ b/drivers/net/wireless/ath/ath10k/Kconfig
@@ -67,6 +67,12 @@ config ATH10K_DEBUGFS
 
 	  If unsure, say Y to make it easier to debug problems.
 
+config ATH10K_LEDS
+	bool
+	depends on ATH10K
+	depends on LEDS_CLASS=y || LEDS_CLASS=MAC80211
+	default y
+
 config ATH10K_SPECTRAL
 	bool "Atheros ath10k spectral scan support"
 	depends on ATH10K_DEBUGFS
diff --git a/drivers/net/wireless/ath/ath10k/Makefile b/drivers/net/wireless/ath/ath10k/Makefile
index 142c777b287f4..02bf9b629038d 100644
--- a/drivers/net/wireless/ath/ath10k/Makefile
+++ b/drivers/net/wireless/ath/ath10k/Makefile
@@ -19,6 +19,7 @@ ath10k_core-$(CONFIG_ATH10K_SPECTRAL) += spectral.o
 ath10k_core-$(CONFIG_NL80211_TESTMODE) += testmode.o
 ath10k_core-$(CONFIG_ATH10K_TRACING) += trace.o
 ath10k_core-$(CONFIG_THERMAL) += thermal.o
+ath10k_core-$(CONFIG_ATH10K_LEDS) += leds.o
 ath10k_core-$(CONFIG_MAC80211_DEBUGFS) += debugfs_sta.o
 ath10k_core-$(CONFIG_PM) += wow.o
 ath10k_core-$(CONFIG_DEV_COREDUMP) += coredump.o
diff --git a/drivers/net/wireless/ath/ath10k/core.c b/drivers/net/wireless/ath/ath10k/core.c
index bdf0552cd1c30..b3294287bce1f 100644
--- a/drivers/net/wireless/ath/ath10k/core.c
+++ b/drivers/net/wireless/ath/ath10k/core.c
@@ -27,6 +27,7 @@
 #include "testmode.h"
 #include "wmi-ops.h"
 #include "coredump.h"
+#include "leds.h"
 
 unsigned int ath10k_debug_mask;
 EXPORT_SYMBOL(ath10k_debug_mask);
@@ -68,6 +69,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.name = "qca988x hw2.0",
 		.patch_load_addr = QCA988X_HW_2_0_PATCH_LOAD_ADDR,
 		.uart_pin = 7,
+		.led_pin = 1,
 		.cc_wraparound_type = ATH10K_HW_CC_WRAP_SHIFTED_ALL,
 		.otp_exe_param = 0,
 		.channel_counters_freq_hz = 88000,
@@ -108,6 +110,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.name = "qca988x hw2.0 ubiquiti",
 		.patch_load_addr = QCA988X_HW_2_0_PATCH_LOAD_ADDR,
 		.uart_pin = 7,
+		.led_pin = 0,
 		.cc_wraparound_type = ATH10K_HW_CC_WRAP_SHIFTED_ALL,
 		.otp_exe_param = 0,
 		.channel_counters_freq_hz = 88000,
@@ -149,6 +152,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.name = "qca9887 hw1.0",
 		.patch_load_addr = QCA9887_HW_1_0_PATCH_LOAD_ADDR,
 		.uart_pin = 7,
+		.led_pin = 1,
 		.cc_wraparound_type = ATH10K_HW_CC_WRAP_SHIFTED_ALL,
 		.otp_exe_param = 0,
 		.channel_counters_freq_hz = 88000,
@@ -190,6 +194,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.name = "qca6174 hw3.2 sdio",
 		.patch_load_addr = QCA6174_HW_3_0_PATCH_LOAD_ADDR,
 		.uart_pin = 19,
+		.led_pin = 0,
 		.otp_exe_param = 0,
 		.channel_counters_freq_hz = 88000,
 		.max_probe_resp_desc_thres = 0,
@@ -226,6 +231,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.name = "qca6164 hw2.1",
 		.patch_load_addr = QCA6174_HW_2_1_PATCH_LOAD_ADDR,
 		.uart_pin = 6,
+		.led_pin = 0,
 		.otp_exe_param = 0,
 		.channel_counters_freq_hz = 88000,
 		.max_probe_resp_desc_thres = 0,
@@ -266,6 +272,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.name = "qca6174 hw2.1",
 		.patch_load_addr = QCA6174_HW_2_1_PATCH_LOAD_ADDR,
 		.uart_pin = 6,
+		.led_pin = 0,
 		.otp_exe_param = 0,
 		.channel_counters_freq_hz = 88000,
 		.max_probe_resp_desc_thres = 0,
@@ -306,6 +313,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.name = "qca6174 hw3.0",
 		.patch_load_addr = QCA6174_HW_3_0_PATCH_LOAD_ADDR,
 		.uart_pin = 6,
+		.led_pin = 0,
 		.otp_exe_param = 0,
 		.channel_counters_freq_hz = 88000,
 		.max_probe_resp_desc_thres = 0,
@@ -346,6 +354,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.name = "qca6174 hw3.2",
 		.patch_load_addr = QCA6174_HW_3_0_PATCH_LOAD_ADDR,
 		.uart_pin = 6,
+		.led_pin = 0,
 		.otp_exe_param = 0,
 		.channel_counters_freq_hz = 88000,
 		.max_probe_resp_desc_thres = 0,
@@ -390,6 +399,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.name = "qca99x0 hw2.0",
 		.patch_load_addr = QCA99X0_HW_2_0_PATCH_LOAD_ADDR,
 		.uart_pin = 7,
+		.led_pin = 17,
 		.otp_exe_param = 0x00000700,
 		.continuous_frag_desc = true,
 		.cck_rate_map_rev2 = true,
@@ -436,6 +446,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.name = "qca9984/qca9994 hw1.0",
 		.patch_load_addr = QCA9984_HW_1_0_PATCH_LOAD_ADDR,
 		.uart_pin = 7,
+		.led_pin = 17,
 		.cc_wraparound_type = ATH10K_HW_CC_WRAP_SHIFTED_EACH,
 		.otp_exe_param = 0x00000700,
 		.continuous_frag_desc = true,
@@ -488,6 +499,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.name = "qca9888 hw2.0",
 		.patch_load_addr = QCA9888_HW_2_0_PATCH_LOAD_ADDR,
 		.uart_pin = 7,
+		.led_pin = 17,
 		.cc_wraparound_type = ATH10K_HW_CC_WRAP_SHIFTED_EACH,
 		.otp_exe_param = 0x00000700,
 		.continuous_frag_desc = true,
@@ -538,6 +550,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.name = "qca9377 hw1.0",
 		.patch_load_addr = QCA9377_HW_1_0_PATCH_LOAD_ADDR,
 		.uart_pin = 6,
+		.led_pin = 0,
 		.otp_exe_param = 0,
 		.channel_counters_freq_hz = 88000,
 		.max_probe_resp_desc_thres = 0,
@@ -578,6 +591,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.name = "qca9377 hw1.1",
 		.patch_load_addr = QCA9377_HW_1_0_PATCH_LOAD_ADDR,
 		.uart_pin = 6,
+		.led_pin = 0,
 		.otp_exe_param = 0,
 		.channel_counters_freq_hz = 88000,
 		.max_probe_resp_desc_thres = 0,
@@ -620,6 +634,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.name = "qca9377 hw1.1 sdio",
 		.patch_load_addr = QCA9377_HW_1_0_PATCH_LOAD_ADDR,
 		.uart_pin = 19,
+		.led_pin = 0,
 		.otp_exe_param = 0,
 		.channel_counters_freq_hz = 88000,
 		.max_probe_resp_desc_thres = 0,
@@ -653,6 +668,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.name = "qca4019 hw1.0",
 		.patch_load_addr = QCA4019_HW_1_0_PATCH_LOAD_ADDR,
 		.uart_pin = 7,
+		.led_pin = 0,
 		.cc_wraparound_type = ATH10K_HW_CC_WRAP_SHIFTED_EACH,
 		.otp_exe_param = 0x0010000,
 		.continuous_frag_desc = true,
@@ -698,6 +714,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.dev_id = 0,
 		.bus = ATH10K_BUS_SNOC,
 		.name = "wcn3990 hw1.0",
+		.led_pin = 0,
 		.continuous_frag_desc = true,
 		.tx_chain_mask = 0x7,
 		.rx_chain_mask = 0x7,
@@ -3224,6 +3241,10 @@ int ath10k_core_start(struct ath10k *ar, enum ath10k_firmware_mode mode,
 		goto err_hif_stop;
 	}
 
+	status = ath10k_leds_start(ar);
+	if (status)
+		goto err_hif_stop;
+
 	return 0;
 
 err_hif_stop:
@@ -3482,9 +3503,18 @@ static void ath10k_core_register_work(struct work_struct *work)
 		goto err_spectral_destroy;
 	}
 
+	status = ath10k_leds_register(ar);
+	if (status) {
+		ath10k_err(ar, "could not register leds: %d\n",
+			   status);
+		goto err_thermal_unregister;
+	}
+
 	set_bit(ATH10K_FLAG_CORE_REGISTERED, &ar->dev_flags);
 	return;
 
+err_thermal_unregister:
+	ath10k_thermal_unregister(ar);
 err_spectral_destroy:
 	ath10k_spectral_destroy(ar);
 err_debug_destroy:
@@ -3520,6 +3550,8 @@ void ath10k_core_unregister(struct ath10k *ar)
 	if (!test_bit(ATH10K_FLAG_CORE_REGISTERED, &ar->dev_flags))
 		return;
 
+	ath10k_leds_unregister(ar);
+
 	ath10k_thermal_unregister(ar);
 	/* Stop spectral before unregistering from mac80211 to remove the
 	 * relayfs debugfs file cleanly. Otherwise the parent debugfs tree
diff --git a/drivers/net/wireless/ath/ath10k/core.h b/drivers/net/wireless/ath/ath10k/core.h
index b00099f0b24e7..446dca74f06a6 100644
--- a/drivers/net/wireless/ath/ath10k/core.h
+++ b/drivers/net/wireless/ath/ath10k/core.h
@@ -15,6 +15,7 @@
 #include <linux/pci.h>
 #include <linux/uuid.h>
 #include <linux/time.h>
+#include <linux/leds.h>
 
 #include "htt.h"
 #include "htc.h"
@@ -1258,6 +1259,13 @@ struct ath10k {
 		bool utf_monitor;
 	} testmode;
 
+	struct {
+		struct gpio_led wifi_led;
+		struct led_classdev cdev;
+		char label[48];
+		u32 gpio_state_pin;
+	} leds;
+
 	struct {
 		/* protected by data_lock */
 		u32 rx_crc_err_drop;
diff --git a/drivers/net/wireless/ath/ath10k/hw.h b/drivers/net/wireless/ath/ath10k/hw.h
index 48897e5eca06a..442091c6dfd20 100644
--- a/drivers/net/wireless/ath/ath10k/hw.h
+++ b/drivers/net/wireless/ath/ath10k/hw.h
@@ -512,6 +512,7 @@ struct ath10k_hw_params {
 	const char *name;
 	u32 patch_load_addr;
 	int uart_pin;
+	int led_pin;
 	u32 otp_exe_param;
 
 	/* Type of hw cycle counter wraparound logic, for more info
diff --git a/drivers/net/wireless/ath/ath10k/leds.c b/drivers/net/wireless/ath/ath10k/leds.c
new file mode 100644
index 0000000000000..9b1d04eb4265b
--- /dev/null
+++ b/drivers/net/wireless/ath/ath10k/leds.c
@@ -0,0 +1,90 @@
+// SPDX-License-Identifier: ISC
+/*
+ * Copyright (c) 2005-2011 Atheros Communications Inc.
+ * Copyright (c) 2011-2017 Qualcomm Atheros, Inc.
+ * Copyright (c) 2018 Sebastian Gottschall <s.gottschall@dd-wrt.com>
+ * Copyright (c) 2018 The Linux Foundation. All rights reserved.
+ */
+
+#include <linux/leds.h>
+
+#include "core.h"
+#include "wmi.h"
+#include "wmi-ops.h"
+
+#include "leds.h"
+
+static int ath10k_leds_set_brightness_blocking(struct led_classdev *led_cdev,
+					       enum led_brightness brightness)
+{
+	struct ath10k *ar = container_of(led_cdev, struct ath10k,
+					 leds.cdev);
+	struct gpio_led *led = &ar->leds.wifi_led;
+
+	mutex_lock(&ar->conf_mutex);
+
+	if (ar->state != ATH10K_STATE_ON)
+		goto out;
+
+	ar->leds.gpio_state_pin = (brightness != LED_OFF) ^ led->active_low;
+	ath10k_wmi_gpio_output(ar, led->gpio, ar->leds.gpio_state_pin);
+
+out:
+	mutex_unlock(&ar->conf_mutex);
+
+	return 0;
+}
+
+int ath10k_leds_start(struct ath10k *ar)
+{
+	if (ar->hw_params.led_pin == 0)
+		/* leds not supported */
+		return 0;
+
+	/* under some circumstances, the gpio pin gets reconfigured
+	 * to default state by the firmware, so we need to
+	 * reconfigure it this behaviour has only ben seen on
+	 * QCA9984 and QCA99XX devices so far
+	 */
+	ath10k_wmi_gpio_config(ar, ar->hw_params.led_pin, 0,
+			       WMI_GPIO_PULL_NONE, WMI_GPIO_INTTYPE_DISABLE);
+	ath10k_wmi_gpio_output(ar, ar->hw_params.led_pin, 1);
+
+	return 0;
+}
+
+int ath10k_leds_register(struct ath10k *ar)
+{
+	int ret;
+
+	if (ar->hw_params.led_pin == 0)
+		/* leds not supported */
+		return 0;
+
+	snprintf(ar->leds.label, sizeof(ar->leds.label), "ath10k-%s",
+		 wiphy_name(ar->hw->wiphy));
+	ar->leds.wifi_led.active_low = 1;
+	ar->leds.wifi_led.gpio = ar->hw_params.led_pin;
+	ar->leds.wifi_led.name = ar->leds.label;
+	ar->leds.wifi_led.default_state = LEDS_GPIO_DEFSTATE_KEEP;
+
+	ar->leds.cdev.name = ar->leds.label;
+	ar->leds.cdev.brightness_set_blocking = ath10k_leds_set_brightness_blocking;
+	ar->leds.cdev.default_trigger = ar->leds.wifi_led.default_trigger;
+
+	ret = led_classdev_register(wiphy_dev(ar->hw->wiphy), &ar->leds.cdev);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+void ath10k_leds_unregister(struct ath10k *ar)
+{
+	if (ar->hw_params.led_pin == 0)
+		/* leds not supported */
+		return;
+
+	led_classdev_unregister(&ar->leds.cdev);
+}
+
diff --git a/drivers/net/wireless/ath/ath10k/leds.h b/drivers/net/wireless/ath/ath10k/leds.h
new file mode 100644
index 0000000000000..56325b0875e5c
--- /dev/null
+++ b/drivers/net/wireless/ath/ath10k/leds.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: ISC */
+/*
+ * Copyright (c) 2005-2011 Atheros Communications Inc.
+ * Copyright (c) 2011-2017 Qualcomm Atheros, Inc.
+ * Copyright (c) 2018 Sebastian Gottschall <s.gottschall@dd-wrt.com>
+ * Copyright (c) 2018 The Linux Foundation. All rights reserved.
+ */
+
+#ifndef _LEDS_H_
+#define _LEDS_H_
+
+#include "core.h"
+
+#ifdef CONFIG_ATH10K_LEDS
+void ath10k_leds_unregister(struct ath10k *ar);
+int ath10k_leds_start(struct ath10k *ar);
+int ath10k_leds_register(struct ath10k *ar);
+#else
+static inline void ath10k_leds_unregister(struct ath10k *ar)
+{
+}
+
+static inline int ath10k_leds_start(struct ath10k *ar)
+{
+	return 0;
+}
+
+static inline int ath10k_leds_register(struct ath10k *ar)
+{
+	return 0;
+}
+
+#endif
+#endif /* _LEDS_H_ */
diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c
index e322b528baafc..3bf67b2ecd6dd 100644
--- a/drivers/net/wireless/ath/ath10k/mac.c
+++ b/drivers/net/wireless/ath/ath10k/mac.c
@@ -25,6 +25,7 @@
 #include "wmi-tlv.h"
 #include "wmi-ops.h"
 #include "wow.h"
+#include "leds.h"
 
 /*********/
 /* Rates */
diff --git a/drivers/net/wireless/ath/ath10k/wmi-ops.h b/drivers/net/wireless/ath/ath10k/wmi-ops.h
index aa57d807491ca..f3f6b5954b270 100644
--- a/drivers/net/wireless/ath/ath10k/wmi-ops.h
+++ b/drivers/net/wireless/ath/ath10k/wmi-ops.h
@@ -226,7 +226,10 @@ struct wmi_ops {
 			 const struct wmi_bb_timing_cfg_arg *arg);
 	struct sk_buff *(*gen_per_peer_per_tid_cfg)(struct ath10k *ar,
 						    const struct wmi_per_peer_per_tid_cfg_arg *arg);
+	struct sk_buff *(*gen_gpio_config)(struct ath10k *ar, u32 gpio_num,
+					   u32 input, u32 pull_type, u32 intr_mode);
 
+	struct sk_buff *(*gen_gpio_output)(struct ath10k *ar, u32 gpio_num, u32 set);
 };
 
 int ath10k_wmi_cmd_send(struct ath10k *ar, struct sk_buff *skb, u32 cmd_id);
@@ -1122,6 +1125,35 @@ ath10k_wmi_force_fw_hang(struct ath10k *ar,
 	return ath10k_wmi_cmd_send(ar, skb, ar->wmi.cmd->force_fw_hang_cmdid);
 }
 
+static inline int ath10k_wmi_gpio_config(struct ath10k *ar, u32 gpio_num,
+					 u32 input, u32 pull_type, u32 intr_mode)
+{
+	struct sk_buff *skb;
+
+	if (!ar->wmi.ops->gen_gpio_config)
+		return -EOPNOTSUPP;
+
+	skb = ar->wmi.ops->gen_gpio_config(ar, gpio_num, input, pull_type, intr_mode);
+	if (IS_ERR(skb))
+		return PTR_ERR(skb);
+
+	return ath10k_wmi_cmd_send(ar, skb, ar->wmi.cmd->gpio_config_cmdid);
+}
+
+static inline int ath10k_wmi_gpio_output(struct ath10k *ar, u32 gpio_num, u32 set)
+{
+	struct sk_buff *skb;
+
+	if (!ar->wmi.ops->gen_gpio_config)
+		return -EOPNOTSUPP;
+
+	skb = ar->wmi.ops->gen_gpio_output(ar, gpio_num, set);
+	if (IS_ERR(skb))
+		return PTR_ERR(skb);
+
+	return ath10k_wmi_cmd_send(ar, skb, ar->wmi.cmd->gpio_output_cmdid);
+}
+
 static inline int
 ath10k_wmi_dbglog_cfg(struct ath10k *ar, u64 module_enable, u32 log_level)
 {
diff --git a/drivers/net/wireless/ath/ath10k/wmi-tlv.c b/drivers/net/wireless/ath/ath10k/wmi-tlv.c
index aed97fd121bab..dbaf26d6a7a61 100644
--- a/drivers/net/wireless/ath/ath10k/wmi-tlv.c
+++ b/drivers/net/wireless/ath/ath10k/wmi-tlv.c
@@ -4606,6 +4606,8 @@ static const struct wmi_ops wmi_tlv_ops = {
 	.gen_echo = ath10k_wmi_tlv_op_gen_echo,
 	.gen_vdev_spectral_conf = ath10k_wmi_tlv_op_gen_vdev_spectral_conf,
 	.gen_vdev_spectral_enable = ath10k_wmi_tlv_op_gen_vdev_spectral_enable,
+	/* .gen_gpio_config not implemented */
+	/* .gen_gpio_output not implemented */
 };
 
 static const struct wmi_peer_flags_map wmi_tlv_peer_flags_map = {
diff --git a/drivers/net/wireless/ath/ath10k/wmi.c b/drivers/net/wireless/ath/ath10k/wmi.c
index 80d255aaff1be..fe23445983649 100644
--- a/drivers/net/wireless/ath/ath10k/wmi.c
+++ b/drivers/net/wireless/ath/ath10k/wmi.c
@@ -7493,6 +7493,49 @@ ath10k_wmi_op_gen_peer_set_param(struct ath10k *ar, u32 vdev_id,
 	return skb;
 }
 
+static struct sk_buff *ath10k_wmi_op_gen_gpio_config(struct ath10k *ar,
+						     u32 gpio_num, u32 input,
+						     u32 pull_type, u32 intr_mode)
+{
+	struct wmi_gpio_config_cmd *cmd;
+	struct sk_buff *skb;
+
+	skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd));
+	if (!skb)
+		return ERR_PTR(-ENOMEM);
+
+	cmd = (struct wmi_gpio_config_cmd *)skb->data;
+	cmd->pull_type = __cpu_to_le32(pull_type);
+	cmd->gpio_num = __cpu_to_le32(gpio_num);
+	cmd->input = __cpu_to_le32(input);
+	cmd->intr_mode = __cpu_to_le32(intr_mode);
+
+	ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi gpio_config gpio_num 0x%08x input 0x%08x pull_type 0x%08x intr_mode 0x%08x\n",
+		   gpio_num, input, pull_type, intr_mode);
+
+	return skb;
+}
+
+static struct sk_buff *ath10k_wmi_op_gen_gpio_output(struct ath10k *ar,
+						     u32 gpio_num, u32 set)
+{
+	struct wmi_gpio_output_cmd *cmd;
+	struct sk_buff *skb;
+
+	skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd));
+	if (!skb)
+		return ERR_PTR(-ENOMEM);
+
+	cmd = (struct wmi_gpio_output_cmd *)skb->data;
+	cmd->gpio_num = __cpu_to_le32(gpio_num);
+	cmd->set = __cpu_to_le32(set);
+
+	ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi gpio_output gpio_num 0x%08x set 0x%08x\n",
+		   gpio_num, set);
+
+	return skb;
+}
+
 static struct sk_buff *
 ath10k_wmi_op_gen_set_psmode(struct ath10k *ar, u32 vdev_id,
 			     enum wmi_sta_ps_mode psmode)
@@ -9157,6 +9200,9 @@ static const struct wmi_ops wmi_ops = {
 	.fw_stats_fill = ath10k_wmi_main_op_fw_stats_fill,
 	.get_vdev_subtype = ath10k_wmi_op_get_vdev_subtype,
 	.gen_echo = ath10k_wmi_op_gen_echo,
+	.gen_gpio_config = ath10k_wmi_op_gen_gpio_config,
+	.gen_gpio_output = ath10k_wmi_op_gen_gpio_output,
+
 	/* .gen_bcn_tmpl not implemented */
 	/* .gen_prb_tmpl not implemented */
 	/* .gen_p2p_go_bcn_ie not implemented */
@@ -9227,6 +9273,8 @@ static const struct wmi_ops wmi_10_1_ops = {
 	.fw_stats_fill = ath10k_wmi_10x_op_fw_stats_fill,
 	.get_vdev_subtype = ath10k_wmi_op_get_vdev_subtype,
 	.gen_echo = ath10k_wmi_op_gen_echo,
+	.gen_gpio_config = ath10k_wmi_op_gen_gpio_config,
+	.gen_gpio_output = ath10k_wmi_op_gen_gpio_output,
 	/* .gen_bcn_tmpl not implemented */
 	/* .gen_prb_tmpl not implemented */
 	/* .gen_p2p_go_bcn_ie not implemented */
@@ -9299,6 +9347,8 @@ static const struct wmi_ops wmi_10_2_ops = {
 	.gen_delba_send = ath10k_wmi_op_gen_delba_send,
 	.fw_stats_fill = ath10k_wmi_10x_op_fw_stats_fill,
 	.get_vdev_subtype = ath10k_wmi_op_get_vdev_subtype,
+	.gen_gpio_config = ath10k_wmi_op_gen_gpio_config,
+	.gen_gpio_output = ath10k_wmi_op_gen_gpio_output,
 	/* .gen_pdev_enable_adaptive_cca not implemented */
 };
 
@@ -9370,6 +9420,8 @@ static const struct wmi_ops wmi_10_2_4_ops = {
 		ath10k_wmi_op_gen_pdev_enable_adaptive_cca,
 	.get_vdev_subtype = ath10k_wmi_10_2_4_op_get_vdev_subtype,
 	.gen_bb_timing = ath10k_wmi_10_2_4_op_gen_bb_timing,
+	.gen_gpio_config = ath10k_wmi_op_gen_gpio_config,
+	.gen_gpio_output = ath10k_wmi_op_gen_gpio_output,
 	/* .gen_bcn_tmpl not implemented */
 	/* .gen_prb_tmpl not implemented */
 	/* .gen_p2p_go_bcn_ie not implemented */
@@ -9451,6 +9503,8 @@ static const struct wmi_ops wmi_10_4_ops = {
 	.gen_pdev_bss_chan_info_req = ath10k_wmi_10_2_op_gen_pdev_bss_chan_info,
 	.gen_echo = ath10k_wmi_op_gen_echo,
 	.gen_pdev_get_tpc_config = ath10k_wmi_10_2_4_op_gen_pdev_get_tpc_config,
+	.gen_gpio_config = ath10k_wmi_op_gen_gpio_config,
+	.gen_gpio_output = ath10k_wmi_op_gen_gpio_output,
 };
 
 int ath10k_wmi_attach(struct ath10k *ar)
diff --git a/drivers/net/wireless/ath/ath10k/wmi.h b/drivers/net/wireless/ath/ath10k/wmi.h
index 2379501225a4a..0faefc0a9a405 100644
--- a/drivers/net/wireless/ath/ath10k/wmi.h
+++ b/drivers/net/wireless/ath/ath10k/wmi.h
@@ -3034,6 +3034,41 @@ enum wmi_10_4_feature_mask {
 
 };
 
+/* WMI_GPIO_CONFIG_CMDID */
+enum {
+	WMI_GPIO_PULL_NONE,
+	WMI_GPIO_PULL_UP,
+	WMI_GPIO_PULL_DOWN,
+};
+
+enum {
+	WMI_GPIO_INTTYPE_DISABLE,
+	WMI_GPIO_INTTYPE_RISING_EDGE,
+	WMI_GPIO_INTTYPE_FALLING_EDGE,
+	WMI_GPIO_INTTYPE_BOTH_EDGE,
+	WMI_GPIO_INTTYPE_LEVEL_LOW,
+	WMI_GPIO_INTTYPE_LEVEL_HIGH
+};
+
+/* WMI_GPIO_CONFIG_CMDID */
+struct wmi_gpio_config_cmd {
+	__le32 gpio_num;             /* GPIO number to be setup */
+	__le32 input;                /* 0 - Output/ 1 - Input */
+	__le32 pull_type;            /* Pull type defined above */
+	__le32 intr_mode;            /* Interrupt mode defined above (Input) */
+} __packed;
+
+/* WMI_GPIO_OUTPUT_CMDID */
+struct wmi_gpio_output_cmd {
+	__le32 gpio_num;    /* GPIO number to be setup */
+	__le32 set;         /* Set the GPIO pin*/
+} __packed;
+
+/* WMI_GPIO_INPUT_EVENTID */
+struct wmi_gpio_input_event {
+	__le32 gpio_num;    /* GPIO number which changed state */
+} __packed;
+
 struct wmi_ext_resource_config_10_4_cmd {
 	/* contains enum wmi_host_platform_type */
 	__le32 host_platform_config;
-- 
GitLab


From 3745d7963cc34c08ee4dda4f3c81981e277f0d96 Mon Sep 17 00:00:00 2001
From: Pradeep Kumar Chitrapu <quic_pradeepc@quicinc.com>
Date: Wed, 8 May 2024 10:36:50 -0700
Subject: [PATCH 043/950] wifi: ath12k: add channel 2 into 6 GHz channel list

Add support for the 6 GHz channel 2 with center frequency
5935 MHz and operating class 136 per IEEE Std 802.11ax-2021,
Table E-4.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.0.1-00029-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Signed-off-by: Pradeep Kumar Chitrapu <quic_pradeepc@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240508173655.22191-2-quic_pradeepc@quicinc.com
---
 drivers/net/wireless/ath/ath12k/core.h | 2 +-
 drivers/net/wireless/ath/ath12k/mac.c  | 4 ++++
 2 files changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath12k/core.h b/drivers/net/wireless/ath/ath12k/core.h
index c6b7524ce3a05..6da242c0d51da 100644
--- a/drivers/net/wireless/ath/ath12k/core.h
+++ b/drivers/net/wireless/ath/ath12k/core.h
@@ -450,7 +450,7 @@ struct ath12k_sta {
 #define ATH12K_MIN_5G_FREQ 4150
 #define ATH12K_MIN_6G_FREQ 5925
 #define ATH12K_MAX_6G_FREQ 7115
-#define ATH12K_NUM_CHANS 100
+#define ATH12K_NUM_CHANS 101
 #define ATH12K_MAX_5G_CHAN 173
 
 enum ath12k_hw_state {
diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index 96dc5c2e096fb..ae9f41a17b4f6 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -91,6 +91,10 @@ static const struct ieee80211_channel ath12k_5ghz_channels[] = {
 };
 
 static const struct ieee80211_channel ath12k_6ghz_channels[] = {
+	/* Operating Class 136 */
+	CHAN6G(2, 5935, 0),
+
+	/* Operating Classes 131-135 */
 	CHAN6G(1, 5955, 0),
 	CHAN6G(5, 5975, 0),
 	CHAN6G(9, 5995, 0),
-- 
GitLab


From c3c84a74bd797f76d7da036c9fef947d674bbc18 Mon Sep 17 00:00:00 2001
From: Pradeep Kumar Chitrapu <quic_pradeepc@quicinc.com>
Date: Wed, 8 May 2024 10:36:51 -0700
Subject: [PATCH 044/950] wifi: ath12k: Correct 6 GHz frequency value in rx
 status

The frequency in the rx status is currently being filled
incorrectly for the 6 GHz band. The channel number received is
invalid in this case, resulting in packet drops. Fix this
issue by correcting the frequency calculation.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.0.1-00029-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Fixes: d889913205cf ("wifi: ath12k: driver for Qualcomm Wi-Fi 7 devices")
Signed-off-by: Pradeep Kumar Chitrapu <quic_pradeepc@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240508173655.22191-3-quic_pradeepc@quicinc.com
---
 drivers/net/wireless/ath/ath12k/dp_rx.c |  9 ++++++---
 drivers/net/wireless/ath/ath12k/wmi.c   | 10 +++++++---
 2 files changed, 13 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/dp_rx.c b/drivers/net/wireless/ath/ath12k/dp_rx.c
index 37205e894afee..d8998ac3a482d 100644
--- a/drivers/net/wireless/ath/ath12k/dp_rx.c
+++ b/drivers/net/wireless/ath/ath12k/dp_rx.c
@@ -2359,8 +2359,10 @@ void ath12k_dp_rx_h_ppdu(struct ath12k *ar, struct hal_rx_desc *rx_desc,
 	channel_num = meta_data;
 	center_freq = meta_data >> 16;
 
-	if (center_freq >= 5935 && center_freq <= 7105) {
+	if (center_freq >= ATH12K_MIN_6G_FREQ &&
+	    center_freq <= ATH12K_MAX_6G_FREQ) {
 		rx_status->band = NL80211_BAND_6GHZ;
+		rx_status->freq = center_freq;
 	} else if (channel_num >= 1 && channel_num <= 14) {
 		rx_status->band = NL80211_BAND_2GHZ;
 	} else if (channel_num >= 36 && channel_num <= 173) {
@@ -2378,8 +2380,9 @@ void ath12k_dp_rx_h_ppdu(struct ath12k *ar, struct hal_rx_desc *rx_desc,
 				rx_desc, sizeof(*rx_desc));
 	}
 
-	rx_status->freq = ieee80211_channel_to_frequency(channel_num,
-							 rx_status->band);
+	if (rx_status->band != NL80211_BAND_6GHZ)
+		rx_status->freq = ieee80211_channel_to_frequency(channel_num,
+								 rx_status->band);
 
 	ath12k_dp_rx_h_rate(ar, rx_desc, rx_status);
 }
diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index 3004c7463be99..a592b75e5ef39 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -6022,8 +6022,10 @@ static void ath12k_mgmt_rx_event(struct ath12k_base *ab, struct sk_buff *skb)
 	if (rx_ev.status & WMI_RX_STATUS_ERR_MIC)
 		status->flag |= RX_FLAG_MMIC_ERROR;
 
-	if (rx_ev.chan_freq >= ATH12K_MIN_6G_FREQ) {
+	if (rx_ev.chan_freq >= ATH12K_MIN_6G_FREQ &&
+	    rx_ev.chan_freq <= ATH12K_MAX_6G_FREQ) {
 		status->band = NL80211_BAND_6GHZ;
+		status->freq = rx_ev.chan_freq;
 	} else if (rx_ev.channel >= 1 && rx_ev.channel <= 14) {
 		status->band = NL80211_BAND_2GHZ;
 	} else if (rx_ev.channel >= 36 && rx_ev.channel <= ATH12K_MAX_5G_CHAN) {
@@ -6044,8 +6046,10 @@ static void ath12k_mgmt_rx_event(struct ath12k_base *ab, struct sk_buff *skb)
 
 	sband = &ar->mac.sbands[status->band];
 
-	status->freq = ieee80211_channel_to_frequency(rx_ev.channel,
-						      status->band);
+	if (status->band != NL80211_BAND_6GHZ)
+		status->freq = ieee80211_channel_to_frequency(rx_ev.channel,
+							      status->band);
+
 	status->signal = rx_ev.snr + ATH12K_DEFAULT_NOISE_FLOOR;
 	status->rate_idx = ath12k_mac_bitrate_to_idx(sband, rx_ev.rate / 100);
 
-- 
GitLab


From 70e3be54bbddc39123b8785408fb9aeb8f822ab6 Mon Sep 17 00:00:00 2001
From: Pradeep Kumar Chitrapu <quic_pradeepc@quicinc.com>
Date: Wed, 8 May 2024 10:36:52 -0700
Subject: [PATCH 045/950] wifi: ath12k: fix survey dump collection in 6 GHz

When ath12k receives survey request, choose the 6 GHz band
when enabled. Without this, survey requests do not include
any 6 GHz band results, leading to failures in auto channel
selection.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.0.1-00029-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Signed-off-by: Pradeep Kumar Chitrapu <quic_pradeepc@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240508173655.22191-4-quic_pradeepc@quicinc.com
---
 drivers/net/wireless/ath/ath12k/mac.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index ae9f41a17b4f6..8af450cdace66 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -8031,6 +8031,17 @@ static int ath12k_mac_op_get_survey(struct ieee80211_hw *hw, int idx,
 
 	if (!sband)
 		sband = hw->wiphy->bands[NL80211_BAND_5GHZ];
+	if (sband && idx >= sband->n_channels) {
+		idx -= sband->n_channels;
+		sband = NULL;
+	}
+
+	if (!sband)
+		sband = hw->wiphy->bands[NL80211_BAND_6GHZ];
+	if (!sband || idx >= sband->n_channels) {
+		idx -= sband->n_channels;
+		sband = NULL;
+	}
 
 	if (!sband || idx >= sband->n_channels)
 		return -ENOENT;
-- 
GitLab


From 112dbc6af807021ac65f46300d564163ec4710a9 Mon Sep 17 00:00:00 2001
From: Pradeep Kumar Chitrapu <quic_pradeepc@quicinc.com>
Date: Wed, 8 May 2024 10:36:53 -0700
Subject: [PATCH 046/950] wifi: ath12k: add 6 GHz params in peer assoc command

Currently A-MPDU aggregation parameters are not being configured
during peer association for 6 GHz band. Hence, extract these
parameters from station's capabilities received in association
request and send to firmware. Without this, A-MPDU aggregation
is not happening in 6 GHz band.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.0.1-00029-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Co-developed-by: Avula Sri Charan <quic_asrichar@quicinc.com>
Signed-off-by: Avula Sri Charan <quic_asrichar@quicinc.com>
Signed-off-by: Pradeep Kumar Chitrapu <quic_pradeepc@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240508173655.22191-5-quic_pradeepc@quicinc.com
---
 drivers/net/wireless/ath/ath12k/mac.c | 57 ++++++++++++++++++++++++++-
 1 file changed, 56 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index 8af450cdace66..b9b9f4d17b348 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -2032,6 +2032,60 @@ static void ath12k_peer_assoc_h_he(struct ath12k *ar,
 	}
 }
 
+static void ath12k_peer_assoc_h_he_6ghz(struct ath12k *ar,
+					struct ieee80211_vif *vif,
+					struct ieee80211_sta *sta,
+					struct ath12k_wmi_peer_assoc_arg *arg)
+{
+	const struct ieee80211_sta_he_cap *he_cap = &sta->deflink.he_cap;
+	struct cfg80211_chan_def def;
+	enum nl80211_band band;
+	u8 ampdu_factor, mpdu_density;
+
+	if (WARN_ON(ath12k_mac_vif_chan(vif, &def)))
+		return;
+
+	band = def.chan->band;
+
+	if (!arg->he_flag || band != NL80211_BAND_6GHZ || !sta->deflink.he_6ghz_capa.capa)
+		return;
+
+	if (sta->deflink.bandwidth == IEEE80211_STA_RX_BW_40)
+		arg->bw_40 = true;
+
+	if (sta->deflink.bandwidth == IEEE80211_STA_RX_BW_80)
+		arg->bw_80 = true;
+
+	if (sta->deflink.bandwidth == IEEE80211_STA_RX_BW_160)
+		arg->bw_160 = true;
+
+	if (sta->deflink.bandwidth == IEEE80211_STA_RX_BW_320)
+		arg->bw_320 = true;
+
+	arg->peer_he_caps_6ghz = le16_to_cpu(sta->deflink.he_6ghz_capa.capa);
+
+	mpdu_density = u32_get_bits(arg->peer_he_caps_6ghz,
+				    IEEE80211_HE_6GHZ_CAP_MIN_MPDU_START);
+	arg->peer_mpdu_density = ath12k_parse_mpdudensity(mpdu_density);
+
+	/* From IEEE Std 802.11ax-2021 - Section 10.12.2: An HE STA shall be capable of
+	 * receiving A-MPDU where the A-MPDU pre-EOF padding length is up to the value
+	 * indicated by the Maximum A-MPDU Length Exponent Extension field in the HE
+	 * Capabilities element and the Maximum A-MPDU Length Exponent field in HE 6 GHz
+	 * Band Capabilities element in the 6 GHz band.
+	 *
+	 * Here, we are extracting the Max A-MPDU Exponent Extension from HE caps and
+	 * factor is the Maximum A-MPDU Length Exponent from HE 6 GHZ Band capability.
+	 */
+	ampdu_factor = u8_get_bits(he_cap->he_cap_elem.mac_cap_info[3],
+				   IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_MASK) +
+			u32_get_bits(arg->peer_he_caps_6ghz,
+				     IEEE80211_HE_6GHZ_CAP_MAX_AMPDU_LEN_EXP);
+
+	arg->peer_max_mpdu = (1u << (IEEE80211_HE_6GHZ_MAX_AMPDU_FACTOR +
+				     ampdu_factor)) - 1;
+}
+
 static void ath12k_peer_assoc_h_smps(struct ieee80211_sta *sta,
 				     struct ath12k_wmi_peer_assoc_arg *arg)
 {
@@ -2504,6 +2558,7 @@ static void ath12k_peer_assoc_prepare(struct ath12k *ar,
 	ath12k_peer_assoc_h_ht(ar, vif, sta, arg);
 	ath12k_peer_assoc_h_vht(ar, vif, sta, arg);
 	ath12k_peer_assoc_h_he(ar, vif, sta, arg);
+	ath12k_peer_assoc_h_he_6ghz(ar, vif, sta, arg);
 	ath12k_peer_assoc_h_eht(ar, vif, sta, arg);
 	ath12k_peer_assoc_h_qos(ar, vif, sta, arg);
 	ath12k_peer_assoc_h_phymode(ar, vif, sta, arg);
@@ -8701,7 +8756,7 @@ static int ath12k_mac_hw_register(struct ath12k_hw *ah)
 	ieee80211_hw_set(hw, SUPPORTS_TX_FRAG);
 	ieee80211_hw_set(hw, REPORTS_LOW_ACK);
 
-	if (ht_cap & WMI_HT_CAP_ENABLED) {
+	if ((ht_cap & WMI_HT_CAP_ENABLED) || ar->supports_6ghz) {
 		ieee80211_hw_set(hw, AMPDU_AGGREGATION);
 		ieee80211_hw_set(hw, TX_AMPDU_SETUP_IN_HW);
 		ieee80211_hw_set(hw, SUPPORTS_REORDERING_BUFFER);
-- 
GitLab


From f0e61dc7ecf9a709d22265a17d553fd314e3f986 Mon Sep 17 00:00:00 2001
From: Pradeep Kumar Chitrapu <quic_pradeepc@quicinc.com>
Date: Wed, 8 May 2024 10:36:54 -0700
Subject: [PATCH 047/950] wifi: ath12k: refactor SMPS configuration

Move fetching SMPS value to a new function and use u16_get_bits
to extract it from capabilities. This will help in extending the
functionality when SMPS support in 6 GHz band gets added in
subsequent patches.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.0.1-00029-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Signed-off-by: Pradeep Kumar Chitrapu <quic_pradeepc@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240508173655.22191-6-quic_pradeepc@quicinc.com
---
 drivers/net/wireless/ath/ath12k/mac.c | 32 ++++++++++++++++-----------
 1 file changed, 19 insertions(+), 13 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index b9b9f4d17b348..0e9b6b7b83d79 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -2086,18 +2086,29 @@ static void ath12k_peer_assoc_h_he_6ghz(struct ath12k *ar,
 				     ampdu_factor)) - 1;
 }
 
+static int ath12k_get_smps_from_capa(const struct ieee80211_sta_ht_cap *ht_cap,
+				     int *smps)
+{
+	if (!ht_cap->ht_supported)
+		return -EOPNOTSUPP;
+
+	*smps = u16_get_bits(ht_cap->cap, IEEE80211_HT_CAP_SM_PS);
+
+	if (*smps >= ARRAY_SIZE(ath12k_smps_map))
+		return -EINVAL;
+
+	return 0;
+}
+
 static void ath12k_peer_assoc_h_smps(struct ieee80211_sta *sta,
 				     struct ath12k_wmi_peer_assoc_arg *arg)
 {
 	const struct ieee80211_sta_ht_cap *ht_cap = &sta->deflink.ht_cap;
 	int smps;
 
-	if (!ht_cap->ht_supported)
+	if (ath12k_get_smps_from_capa(ht_cap, &smps))
 		return;
 
-	smps = ht_cap->cap & IEEE80211_HT_CAP_SM_PS;
-	smps >>= IEEE80211_HT_CAP_SM_PS_SHIFT;
-
 	switch (smps) {
 	case WLAN_HT_CAP_SM_PS_STATIC:
 		arg->static_mimops_flag = true;
@@ -2571,16 +2582,11 @@ static int ath12k_setup_peer_smps(struct ath12k *ar, struct ath12k_vif *arvif,
 				  const u8 *addr,
 				  const struct ieee80211_sta_ht_cap *ht_cap)
 {
-	int smps;
+	int smps, ret = 0;
 
-	if (!ht_cap->ht_supported)
-		return 0;
-
-	smps = ht_cap->cap & IEEE80211_HT_CAP_SM_PS;
-	smps >>= IEEE80211_HT_CAP_SM_PS_SHIFT;
-
-	if (smps >= ARRAY_SIZE(ath12k_smps_map))
-		return -EINVAL;
+	ret = ath12k_get_smps_from_capa(ht_cap, &smps);
+	if (ret < 0)
+		return ret;
 
 	return ath12k_wmi_set_peer_param(ar, addr, arvif->vdev_id,
 					 WMI_PEER_MIMO_PS_STATE,
-- 
GitLab


From 97b7cbb7a3cbeee87ed82af67bca881ec8881d83 Mon Sep 17 00:00:00 2001
From: Pradeep Kumar Chitrapu <quic_pradeepc@quicinc.com>
Date: Wed, 8 May 2024 10:36:55 -0700
Subject: [PATCH 048/950] wifi: ath12k: support SMPS configuration for 6 GHz

Parse SMPS configuration from IEs and configure. Without this,
SMPS is not enabled for 6 GHz band. This is disabled for
WCN7850 as hardware does not support it.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.0.1-00029-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Signed-off-by: Pradeep Kumar Chitrapu <quic_pradeepc@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240508173655.22191-7-quic_pradeepc@quicinc.com
---
 drivers/net/wireless/ath/ath12k/hw.c  |  3 +++
 drivers/net/wireless/ath/ath12k/hw.h  |  1 +
 drivers/net/wireless/ath/ath12k/mac.c | 26 ++++++++++++++++++--------
 3 files changed, 22 insertions(+), 8 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/hw.c b/drivers/net/wireless/ath/ath12k/hw.c
index 06f4432164886..b3ba753d4a855 100644
--- a/drivers/net/wireless/ath/ath12k/hw.c
+++ b/drivers/net/wireless/ath/ath12k/hw.c
@@ -926,6 +926,7 @@ static const struct ath12k_hw_params ath12k_hw_params[] = {
 		.supports_sta_ps = false,
 
 		.acpi_guid = NULL,
+		.supports_dynamic_smps_6ghz = true,
 	},
 	{
 		.name = "wcn7850 hw2.0",
@@ -1001,6 +1002,7 @@ static const struct ath12k_hw_params ath12k_hw_params[] = {
 		.supports_sta_ps = true,
 
 		.acpi_guid = &wcn7850_uuid,
+		.supports_dynamic_smps_6ghz = false,
 	},
 	{
 		.name = "qcn9274 hw2.0",
@@ -1071,6 +1073,7 @@ static const struct ath12k_hw_params ath12k_hw_params[] = {
 		.supports_sta_ps = false,
 
 		.acpi_guid = NULL,
+		.supports_dynamic_smps_6ghz = true,
 	},
 };
 
diff --git a/drivers/net/wireless/ath/ath12k/hw.h b/drivers/net/wireless/ath/ath12k/hw.h
index 2a5a9d638d934..7422d32585484 100644
--- a/drivers/net/wireless/ath/ath12k/hw.h
+++ b/drivers/net/wireless/ath/ath12k/hw.h
@@ -215,6 +215,7 @@ struct ath12k_hw_params {
 	bool supports_sta_ps;
 
 	const guid_t *acpi_guid;
+	bool supports_dynamic_smps_6ghz;
 };
 
 struct ath12k_hw_ops {
diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index 0e9b6b7b83d79..ea0a9ccc8e927 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -2087,12 +2087,17 @@ static void ath12k_peer_assoc_h_he_6ghz(struct ath12k *ar,
 }
 
 static int ath12k_get_smps_from_capa(const struct ieee80211_sta_ht_cap *ht_cap,
+				     const struct ieee80211_he_6ghz_capa *he_6ghz_capa,
 				     int *smps)
 {
-	if (!ht_cap->ht_supported)
+	if (!ht_cap->ht_supported && !he_6ghz_capa->capa)
 		return -EOPNOTSUPP;
 
-	*smps = u16_get_bits(ht_cap->cap, IEEE80211_HT_CAP_SM_PS);
+	if (ht_cap->ht_supported)
+		*smps = u16_get_bits(ht_cap->cap, IEEE80211_HT_CAP_SM_PS);
+	else
+		*smps = le16_get_bits(he_6ghz_capa->capa,
+				      IEEE80211_HE_6GHZ_CAP_SM_PS);
 
 	if (*smps >= ARRAY_SIZE(ath12k_smps_map))
 		return -EINVAL;
@@ -2103,10 +2108,11 @@ static int ath12k_get_smps_from_capa(const struct ieee80211_sta_ht_cap *ht_cap,
 static void ath12k_peer_assoc_h_smps(struct ieee80211_sta *sta,
 				     struct ath12k_wmi_peer_assoc_arg *arg)
 {
+	const struct ieee80211_he_6ghz_capa *he_6ghz_capa = &sta->deflink.he_6ghz_capa;
 	const struct ieee80211_sta_ht_cap *ht_cap = &sta->deflink.ht_cap;
 	int smps;
 
-	if (ath12k_get_smps_from_capa(ht_cap, &smps))
+	if (ath12k_get_smps_from_capa(ht_cap, he_6ghz_capa, &smps))
 		return;
 
 	switch (smps) {
@@ -2580,11 +2586,12 @@ static void ath12k_peer_assoc_prepare(struct ath12k *ar,
 
 static int ath12k_setup_peer_smps(struct ath12k *ar, struct ath12k_vif *arvif,
 				  const u8 *addr,
-				  const struct ieee80211_sta_ht_cap *ht_cap)
+				  const struct ieee80211_sta_ht_cap *ht_cap,
+				  const struct ieee80211_he_6ghz_capa *he_6ghz_capa)
 {
 	int smps, ret = 0;
 
-	ret = ath12k_get_smps_from_capa(ht_cap, &smps);
+	ret = ath12k_get_smps_from_capa(ht_cap, he_6ghz_capa, &smps);
 	if (ret < 0)
 		return ret;
 
@@ -2637,7 +2644,8 @@ static void ath12k_bss_assoc(struct ath12k *ar,
 	}
 
 	ret = ath12k_setup_peer_smps(ar, arvif, bss_conf->bssid,
-				     &ap_sta->deflink.ht_cap);
+				     &ap_sta->deflink.ht_cap,
+				     &ap_sta->deflink.he_6ghz_capa);
 	if (ret) {
 		ath12k_warn(ar->ab, "failed to setup peer SMPS for vdev %d: %d\n",
 			    arvif->vdev_id, ret);
@@ -3944,7 +3952,8 @@ static int ath12k_station_assoc(struct ath12k *ar,
 		return 0;
 
 	ret = ath12k_setup_peer_smps(ar, arvif, sta->addr,
-				     &sta->deflink.ht_cap);
+				     &sta->deflink.ht_cap,
+				     &sta->deflink.he_6ghz_capa);
 	if (ret) {
 		ath12k_warn(ar->ab, "failed to setup peer SMPS for vdev %d: %d\n",
 			    arvif->vdev_id, ret);
@@ -8777,7 +8786,8 @@ static int ath12k_mac_hw_register(struct ath12k_hw *ah)
 	 * for each band for a dual band capable radio. It will be tricky to
 	 * handle it when the ht capability different for each band.
 	 */
-	if (ht_cap & WMI_HT_CAP_DYNAMIC_SMPS)
+	if (ht_cap & WMI_HT_CAP_DYNAMIC_SMPS ||
+	    (ar->supports_6ghz && ab->hw_params->supports_dynamic_smps_6ghz))
 		wiphy->features |= NL80211_FEATURE_DYNAMIC_SMPS;
 
 	wiphy->max_scan_ssids = WLAN_SCAN_PARAMS_MAX_SSID;
-- 
GitLab


From 519a545cfee790024c623c7aacd165f7431773d5 Mon Sep 17 00:00:00 2001
From: Aloka Dixit <quic_alokad@quicinc.com>
Date: Wed, 8 May 2024 13:29:04 -0700
Subject: [PATCH 049/950] wifi: ath12k: advertise driver capabilities for
 MBSSID and EMA

Advertise the driver support for multiple BSSID (MBSSID) and
enhanced multi-BSSID advertisements (EMA) by setting extended
capabilities.

Configure mbssid_max_interfaces and ema_max_profile_periodicity
fields in structure wiphy which are used to advertise maximum number
of interfaces and profile periodicity supported by the driver.

Add new WMI fields to configure maximum vdev count supported for
MBSSID and profile periodicity in case of EMA.

Set WMI_RSRC_CFG_FLAGS2_CALC_NEXT_DTIM_COUNT_SET flag to allow
firmware to track and update the DTIM counts for each nontransmitted
profile.

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

Signed-off-by: Aloka Dixit <quic_alokad@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240508202912.11902-2-quic_alokad@quicinc.com
---
 drivers/net/wireless/ath/ath12k/hw.h  | 1 +
 drivers/net/wireless/ath/ath12k/mac.c | 7 +++++++
 drivers/net/wireless/ath/ath12k/wmi.c | 7 ++++++-
 drivers/net/wireless/ath/ath12k/wmi.h | 3 +++
 4 files changed, 17 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath12k/hw.h b/drivers/net/wireless/ath/ath12k/hw.h
index 7422d32585484..af33bf11416b7 100644
--- a/drivers/net/wireless/ath/ath12k/hw.h
+++ b/drivers/net/wireless/ath/ath12k/hw.h
@@ -80,6 +80,7 @@
 #define TARGET_RX_BATCHMODE		1
 #define TARGET_RX_PEER_METADATA_VER_V1A	2
 #define TARGET_RX_PEER_METADATA_VER_V1B	3
+#define TARGET_EMA_MAX_PROFILE_PERIOD	8
 
 #define ATH12K_HW_DEFAULT_QUEUE		0
 #define ATH12K_HW_MAX_QUEUES		4
diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index ea0a9ccc8e927..9d82f289b23b7 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -8574,19 +8574,23 @@ static int ath12k_mac_setup_iface_combinations(struct ath12k_hw *ah)
 
 static const u8 ath12k_if_types_ext_capa[] = {
 	[0] = WLAN_EXT_CAPA1_EXT_CHANNEL_SWITCHING,
+	[2] = WLAN_EXT_CAPA3_MULTI_BSSID_SUPPORT,
 	[7] = WLAN_EXT_CAPA8_OPMODE_NOTIF,
 };
 
 static const u8 ath12k_if_types_ext_capa_sta[] = {
 	[0] = WLAN_EXT_CAPA1_EXT_CHANNEL_SWITCHING,
+	[2] = WLAN_EXT_CAPA3_MULTI_BSSID_SUPPORT,
 	[7] = WLAN_EXT_CAPA8_OPMODE_NOTIF,
 	[9] = WLAN_EXT_CAPA10_TWT_REQUESTER_SUPPORT,
 };
 
 static const u8 ath12k_if_types_ext_capa_ap[] = {
 	[0] = WLAN_EXT_CAPA1_EXT_CHANNEL_SWITCHING,
+	[2] = WLAN_EXT_CAPA3_MULTI_BSSID_SUPPORT,
 	[7] = WLAN_EXT_CAPA8_OPMODE_NOTIF,
 	[9] = WLAN_EXT_CAPA10_TWT_RESPONDER_SUPPORT,
+	[10] = WLAN_EXT_CAPA11_EMA_SUPPORT,
 };
 
 static const struct wiphy_iftype_ext_capab ath12k_iftypes_ext_capa[] = {
@@ -8826,6 +8830,9 @@ static int ath12k_mac_hw_register(struct ath12k_hw *ah)
 	wiphy->iftype_ext_capab = ath12k_iftypes_ext_capa;
 	wiphy->num_iftype_ext_capab = ARRAY_SIZE(ath12k_iftypes_ext_capa);
 
+	wiphy->mbssid_max_interfaces = TARGET_NUM_VDEVS;
+	wiphy->ema_max_profile_periodicity = TARGET_EMA_MAX_PROFILE_PERIOD;
+
 	if (is_6ghz) {
 		wiphy_ext_feature_set(wiphy,
 				      NL80211_EXT_FEATURE_FILS_DISCOVERY);
diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index a592b75e5ef39..3da16d4abb5ac 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -228,6 +228,9 @@ void ath12k_wmi_init_qcn9274(struct ath12k_base *ab,
 	config->peer_map_unmap_version = 0x32;
 	config->twt_ap_pdev_count = ab->num_radios;
 	config->twt_ap_sta_count = 1000;
+	config->ema_max_vap_cnt = ab->num_radios;
+	config->ema_max_profile_period = TARGET_EMA_MAX_PROFILE_PERIOD;
+	config->beacon_tx_offload_max_vdev += config->ema_max_vap_cnt;
 
 	if (test_bit(WMI_TLV_SERVICE_PEER_METADATA_V1A_V1B_SUPPORT, ab->wmi_ab.svc_map))
 		config->dp_peer_meta_data_ver = TARGET_RX_PEER_METADATA_VER_V1B;
@@ -3475,9 +3478,11 @@ ath12k_wmi_copy_resource_config(struct ath12k_wmi_resource_config_params *wmi_cf
 	wmi_cfg->twt_ap_sta_count = cpu_to_le32(tg_cfg->twt_ap_sta_count);
 	wmi_cfg->flags2 = le32_encode_bits(tg_cfg->dp_peer_meta_data_ver,
 					   WMI_RSRC_CFG_FLAGS2_RX_PEER_METADATA_VERSION);
-
 	wmi_cfg->host_service_flags = cpu_to_le32(tg_cfg->is_reg_cc_ext_event_supported <<
 				WMI_RSRC_CFG_HOST_SVC_FLAG_REG_CC_EXT_SUPPORT_BIT);
+	wmi_cfg->ema_max_vap_cnt = cpu_to_le32(tg_cfg->ema_max_vap_cnt);
+	wmi_cfg->ema_max_profile_period = cpu_to_le32(tg_cfg->ema_max_profile_period);
+	wmi_cfg->flags2 |= cpu_to_le32(WMI_RSRC_CFG_FLAGS2_CALC_NEXT_DTIM_COUNT_SET);
 }
 
 static int ath12k_init_cmd_send(struct ath12k_wmi_pdev *wmi,
diff --git a/drivers/net/wireless/ath/ath12k/wmi.h b/drivers/net/wireless/ath/ath12k/wmi.h
index 496866673aead..e71e6c73f2495 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.h
+++ b/drivers/net/wireless/ath/ath12k/wmi.h
@@ -2356,6 +2356,8 @@ struct ath12k_wmi_resource_config_arg {
 	u32 twt_ap_sta_count;
 	bool is_reg_cc_ext_event_supported;
 	u8  dp_peer_meta_data_ver;
+	u32 ema_max_vap_cnt;
+	u32 ema_max_profile_period;
 };
 
 struct ath12k_wmi_init_cmd_arg {
@@ -2410,6 +2412,7 @@ struct wmi_init_cmd {
 #define WMI_RSRC_CFG_HOST_SVC_FLAG_REG_CC_EXT_SUPPORT_BIT 4
 #define WMI_RSRC_CFG_FLAGS2_RX_PEER_METADATA_VERSION		GENMASK(5, 4)
 #define WMI_RSRC_CFG_FLAG1_BSS_CHANNEL_INFO_64	BIT(5)
+#define WMI_RSRC_CFG_FLAGS2_CALC_NEXT_DTIM_COUNT_SET      BIT(9)
 
 struct ath12k_wmi_resource_config_params {
 	__le32 tlv_header;
-- 
GitLab


From ea68f1bba61632652f722e5979a8a853cfa55eff Mon Sep 17 00:00:00 2001
From: Aloka Dixit <quic_alokad@quicinc.com>
Date: Wed, 8 May 2024 13:29:05 -0700
Subject: [PATCH 050/950] wifi: ath12k: configure MBSSID params in vdev
 create/start

Configure multiple BSSID flags and vdev_id of the transmited profile
in vdev create/start commands depending on the service bit
WMI_TLV_SERVICE_MBSS_PARAM_IN_VDEV_START_SUPPORT.

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

Signed-off-by: Aloka Dixit <quic_alokad@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240508202912.11902-3-quic_alokad@quicinc.com
---
 drivers/net/wireless/ath/ath12k/mac.c | 66 ++++++++++++++++++++++++---
 drivers/net/wireless/ath/ath12k/wmi.c |  3 ++
 drivers/net/wireless/ath/ath12k/wmi.h |  7 +++
 3 files changed, 70 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index 9d82f289b23b7..5967c94fe8f27 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -5984,17 +5984,59 @@ ath12k_mac_get_vdev_stats_id(struct ath12k_vif *arvif)
 	return vdev_stats_id;
 }
 
-static void ath12k_mac_setup_vdev_create_arg(struct ath12k_vif *arvif,
-					     struct ath12k_wmi_vdev_create_arg *arg)
+static int ath12k_mac_setup_vdev_params_mbssid(struct ath12k_vif *arvif,
+					       u32 *flags, u32 *tx_vdev_id)
+{
+	struct ieee80211_vif *tx_vif = arvif->vif->mbssid_tx_vif;
+	struct ath12k *ar = arvif->ar;
+	struct ath12k_vif *tx_arvif;
+
+	if (!tx_vif)
+		return 0;
+
+	tx_arvif = ath12k_vif_to_arvif(tx_vif);
+
+	if (arvif->vif->bss_conf.nontransmitted) {
+		if (ar->ah->hw->wiphy != ieee80211_vif_to_wdev(tx_vif)->wiphy)
+			return -EINVAL;
+
+		*flags = WMI_VDEV_MBSSID_FLAGS_NON_TRANSMIT_AP;
+		*tx_vdev_id = tx_arvif->vdev_id;
+	} else if (tx_arvif == arvif) {
+		*flags = WMI_VDEV_MBSSID_FLAGS_TRANSMIT_AP;
+	} else {
+		return -EINVAL;
+	}
+
+	if (arvif->vif->bss_conf.ema_ap)
+		*flags |= WMI_VDEV_MBSSID_FLAGS_EMA_MODE;
+
+	return 0;
+}
+
+static int ath12k_mac_setup_vdev_create_arg(struct ath12k_vif *arvif,
+					    struct ath12k_wmi_vdev_create_arg *arg)
 {
 	struct ath12k *ar = arvif->ar;
 	struct ath12k_pdev *pdev = ar->pdev;
+	int ret;
 
 	arg->if_id = arvif->vdev_id;
 	arg->type = arvif->vdev_type;
 	arg->subtype = arvif->vdev_subtype;
 	arg->pdev_id = pdev->pdev_id;
 
+	arg->mbssid_flags = WMI_VDEV_MBSSID_FLAGS_NON_MBSSID_AP;
+	arg->mbssid_tx_vdev_id = 0;
+	if (!test_bit(WMI_TLV_SERVICE_MBSS_PARAM_IN_VDEV_START_SUPPORT,
+		      ar->ab->wmi_ab.svc_map)) {
+		ret = ath12k_mac_setup_vdev_params_mbssid(arvif,
+							  &arg->mbssid_flags,
+							  &arg->mbssid_tx_vdev_id);
+		if (ret)
+			return ret;
+	}
+
 	if (pdev->cap.supported_bands & WMI_HOST_WLAN_2G_CAP) {
 		arg->chains[NL80211_BAND_2GHZ].tx = ar->num_tx_chains;
 		arg->chains[NL80211_BAND_2GHZ].rx = ar->num_rx_chains;
@@ -6010,6 +6052,7 @@ static void ath12k_mac_setup_vdev_create_arg(struct ath12k_vif *arvif,
 	}
 
 	arg->if_stats_id = ath12k_mac_get_vdev_stats_id(arvif);
+	return 0;
 }
 
 static u32
@@ -6191,7 +6234,12 @@ static int ath12k_mac_vdev_create(struct ath12k *ar, struct ieee80211_vif *vif)
 	for (i = 0; i < ARRAY_SIZE(vif->hw_queue); i++)
 		vif->hw_queue[i] = i % (ATH12K_HW_MAX_QUEUES - 1);
 
-	ath12k_mac_setup_vdev_create_arg(arvif, &vdev_arg);
+	ret = ath12k_mac_setup_vdev_create_arg(arvif, &vdev_arg);
+	if (ret) {
+		ath12k_warn(ab, "failed to create vdev parameters %d: %d\n",
+			    arvif->vdev_id, ret);
+		goto err;
+	}
 
 	ret = ath12k_wmi_vdev_create(ar, vif->addr, &vdev_arg);
 	if (ret) {
@@ -6933,10 +6981,16 @@ ath12k_mac_vdev_start_restart(struct ath12k_vif *arvif,
 	arg.pref_tx_streams = ar->num_tx_chains;
 	arg.pref_rx_streams = ar->num_rx_chains;
 
-	/* Fill the MBSSID flags to indicate AP is non MBSSID by default
-	 * Corresponding flags would be updated with MBSSID support.
-	 */
 	arg.mbssid_flags = WMI_VDEV_MBSSID_FLAGS_NON_MBSSID_AP;
+	arg.mbssid_tx_vdev_id = 0;
+	if (test_bit(WMI_TLV_SERVICE_MBSS_PARAM_IN_VDEV_START_SUPPORT,
+		     ar->ab->wmi_ab.svc_map)) {
+		ret = ath12k_mac_setup_vdev_params_mbssid(arvif,
+							  &arg.mbssid_flags,
+							  &arg.mbssid_tx_vdev_id);
+		if (ret)
+			return ret;
+	}
 
 	if (arvif->vdev_type == WMI_VDEV_TYPE_AP) {
 		arg.ssid = arvif->u.ap.ssid;
diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index 3da16d4abb5ac..e77132d6aa831 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -844,6 +844,8 @@ int ath12k_wmi_vdev_create(struct ath12k *ar, u8 *macaddr,
 	cmd->vdev_subtype = cpu_to_le32(args->subtype);
 	cmd->num_cfg_txrx_streams = cpu_to_le32(WMI_NUM_SUPPORTED_BAND_MAX);
 	cmd->pdev_id = cpu_to_le32(args->pdev_id);
+	cmd->mbssid_flags = cpu_to_le32(args->mbssid_flags);
+	cmd->mbssid_tx_vdev_id = cpu_to_le32(args->mbssid_tx_vdev_id);
 	cmd->vdev_stats_id = cpu_to_le32(args->if_stats_id);
 	ether_addr_copy(cmd->vdev_macaddr.addr, macaddr);
 
@@ -1049,6 +1051,7 @@ int ath12k_wmi_vdev_start(struct ath12k *ar, struct wmi_vdev_start_req_arg *arg,
 	cmd->he_ops = cpu_to_le32(arg->he_ops);
 	cmd->punct_bitmap = cpu_to_le32(arg->punct_bitmap);
 	cmd->mbssid_flags = cpu_to_le32(arg->mbssid_flags);
+	cmd->mbssid_tx_vdev_id = cpu_to_le32(arg->mbssid_tx_vdev_id);
 
 	if (!restart) {
 		if (arg->ssid) {
diff --git a/drivers/net/wireless/ath/ath12k/wmi.h b/drivers/net/wireless/ath/ath12k/wmi.h
index e71e6c73f2495..86a0ef09aa392 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.h
+++ b/drivers/net/wireless/ath/ath12k/wmi.h
@@ -2154,6 +2154,7 @@ enum wmi_tlv_service {
 	WMI_TLV_SERVICE_PER_PEER_HTT_STATS_RESET = 213,
 	WMI_TLV_SERVICE_FREQINFO_IN_METADATA = 219,
 	WMI_TLV_SERVICE_EXT2_MSG = 220,
+	WMI_TLV_SERVICE_MBSS_PARAM_IN_VDEV_START_SUPPORT = 253,
 
 	WMI_MAX_EXT_SERVICE = 256,
 
@@ -2729,6 +2730,8 @@ struct ath12k_wmi_vdev_create_arg {
 	} chains[NUM_NL80211_BANDS];
 	u32 pdev_id;
 	u8 if_stats_id;
+	u32 mbssid_flags;
+	u32 mbssid_tx_vdev_id;
 };
 
 #define ATH12K_MAX_VDEV_STATS_ID	0x30
@@ -2795,6 +2798,10 @@ struct ath12k_wmi_ssid_params {
 
 enum wmi_vdev_mbssid_flags {
 	WMI_VDEV_MBSSID_FLAGS_NON_MBSSID_AP	= BIT(0),
+	WMI_VDEV_MBSSID_FLAGS_TRANSMIT_AP	= BIT(1),
+	WMI_VDEV_MBSSID_FLAGS_NON_TRANSMIT_AP	= BIT(2),
+	WMI_VDEV_MBSSID_FLAGS_EMA_MODE		= BIT(3),
+	WMI_VDEV_MBSSID_FLAGS_SCAN_MODE_VAP	= BIT(4),
 };
 
 struct wmi_vdev_start_request_cmd {
-- 
GitLab


From 5fbd97f25c4c62eba921b8bc13a45f0210437787 Mon Sep 17 00:00:00 2001
From: Aloka Dixit <quic_alokad@quicinc.com>
Date: Wed, 8 May 2024 13:29:06 -0700
Subject: [PATCH 051/950] wifi: ath12k: rename MBSSID fields in wmi_vdev_up_cmd

Rename trans_bssid to tx_vdev_bssid to make it similar to vdev_bssid.

Rename profile_num to nontx_profile_cnt, and profile_idx to
nontx_profile_idx which make it clear that these configurations
correspond to nontransmitted MBSSID profiles.

These members are currently unused in the driver.

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

Signed-off-by: Aloka Dixit <quic_alokad@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240508202912.11902-4-quic_alokad@quicinc.com
---
 drivers/net/wireless/ath/ath12k/wmi.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/wmi.h b/drivers/net/wireless/ath/ath12k/wmi.h
index 86a0ef09aa392..4051ed5a0b0a7 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.h
+++ b/drivers/net/wireless/ath/ath12k/wmi.h
@@ -2768,9 +2768,9 @@ struct wmi_vdev_up_cmd {
 	__le32 vdev_id;
 	__le32 vdev_assoc_id;
 	struct ath12k_wmi_mac_addr_params vdev_bssid;
-	struct ath12k_wmi_mac_addr_params trans_bssid;
-	__le32 profile_idx;
-	__le32 profile_num;
+	struct ath12k_wmi_mac_addr_params tx_vdev_bssid;
+	__le32 nontx_profile_idx;
+	__le32 nontx_profile_cnt;
 } __packed;
 
 struct wmi_vdev_stop_cmd {
-- 
GitLab


From 51c47463543ef4f1f0cf2354527baa297a754995 Mon Sep 17 00:00:00 2001
From: Aloka Dixit <quic_alokad@quicinc.com>
Date: Wed, 8 May 2024 13:29:07 -0700
Subject: [PATCH 052/950] wifi: ath12k: create a structure for WMI vdev up
 parameters

Host needs to send multiple BSSID configurations to firmware for
each vdev in ath12k_wmi_vdev_up() for AP mode. This function accepts
individual input parameters hence any new argument will require changes
to all callers. Most of these will use default value (0 or NULL).
Create a structure for the function arguments and include objects with
all members initialized to zero to minimize future changes.

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

Signed-off-by: Aloka Dixit <quic_alokad@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240508202912.11902-5-quic_alokad@quicinc.com
---
 drivers/net/wireless/ath/ath12k/mac.c | 30 ++++++++++++++++++++-------
 drivers/net/wireless/ath/ath12k/wmi.c | 10 ++++-----
 drivers/net/wireless/ath/ath12k/wmi.h |  9 ++++++--
 3 files changed, 35 insertions(+), 14 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index 5967c94fe8f27..c6fa68aafdd82 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -867,9 +867,12 @@ static int ath12k_mac_vdev_setup_sync(struct ath12k *ar)
 
 static int ath12k_monitor_vdev_up(struct ath12k *ar, int vdev_id)
 {
+	struct ath12k_wmi_vdev_up_params params = {};
 	int ret;
 
-	ret = ath12k_wmi_vdev_up(ar, vdev_id, 0, ar->mac_addr);
+	params.vdev_id = vdev_id;
+	params.bssid = ar->mac_addr;
+	ret = ath12k_wmi_vdev_up(ar, &params);
 	if (ret) {
 		ath12k_warn(ar->ab, "failed to put up monitor vdev %i: %d\n",
 			    vdev_id, ret);
@@ -886,6 +889,7 @@ static int ath12k_mac_monitor_vdev_start(struct ath12k *ar, int vdev_id,
 {
 	struct ieee80211_channel *channel;
 	struct wmi_vdev_start_req_arg arg = {};
+	struct ath12k_wmi_vdev_up_params params = {};
 	int ret;
 
 	lockdep_assert_held(&ar->conf_mutex);
@@ -926,7 +930,9 @@ static int ath12k_mac_monitor_vdev_start(struct ath12k *ar, int vdev_id,
 		return ret;
 	}
 
-	ret = ath12k_wmi_vdev_up(ar, vdev_id, 0, ar->mac_addr);
+	params.vdev_id = vdev_id;
+	params.bssid = ar->mac_addr;
+	ret = ath12k_wmi_vdev_up(ar, &params);
 	if (ret) {
 		ath12k_warn(ar->ab, "failed to put up monitor vdev %i: %d\n",
 			    vdev_id, ret);
@@ -1362,6 +1368,7 @@ free_bcn_skb:
 static void ath12k_control_beaconing(struct ath12k_vif *arvif,
 				     struct ieee80211_bss_conf *info)
 {
+	struct ath12k_wmi_vdev_up_params params = {};
 	struct ath12k *ar = arvif->ar;
 	int ret;
 
@@ -1389,8 +1396,10 @@ static void ath12k_control_beaconing(struct ath12k_vif *arvif,
 
 	ether_addr_copy(arvif->bssid, info->bssid);
 
-	ret = ath12k_wmi_vdev_up(arvif->ar, arvif->vdev_id, arvif->aid,
-				 arvif->bssid);
+	params.vdev_id = arvif->vdev_id;
+	params.aid = arvif->aid;
+	params.bssid = arvif->bssid;
+	ret = ath12k_wmi_vdev_up(arvif->ar, &params);
 	if (ret) {
 		ath12k_warn(ar->ab, "failed to bring up vdev %d: %i\n",
 			    arvif->vdev_id, ret);
@@ -2605,6 +2614,7 @@ static void ath12k_bss_assoc(struct ath12k *ar,
 			     struct ieee80211_bss_conf *bss_conf)
 {
 	struct ieee80211_vif *vif = arvif->vif;
+	struct ath12k_wmi_vdev_up_params params = {};
 	struct ath12k_wmi_peer_assoc_arg peer_arg;
 	struct ieee80211_sta *ap_sta;
 	struct ath12k_peer *peer;
@@ -2657,7 +2667,10 @@ static void ath12k_bss_assoc(struct ath12k *ar,
 	arvif->aid = vif->cfg.aid;
 	ether_addr_copy(arvif->bssid, bss_conf->bssid);
 
-	ret = ath12k_wmi_vdev_up(ar, arvif->vdev_id, arvif->aid, arvif->bssid);
+	params.vdev_id = arvif->vdev_id;
+	params.aid = arvif->aid;
+	params.bssid = arvif->bssid;
+	ret = ath12k_wmi_vdev_up(ar, &params);
 	if (ret) {
 		ath12k_warn(ar->ab, "failed to set vdev %d up: %d\n",
 			    arvif->vdev_id, ret);
@@ -7184,6 +7197,7 @@ ath12k_mac_update_vif_chan(struct ath12k *ar,
 			   struct ieee80211_vif_chanctx_switch *vifs,
 			   int n_vifs)
 {
+	struct ath12k_wmi_vdev_up_params params = {};
 	struct ath12k_base *ab = ar->ab;
 	struct ath12k_vif *arvif;
 	int ret;
@@ -7264,8 +7278,10 @@ ath12k_mac_update_vif_chan(struct ath12k *ar,
 			ath12k_warn(ab, "failed to update bcn tmpl during csa: %d\n",
 				    ret);
 
-		ret = ath12k_wmi_vdev_up(arvif->ar, arvif->vdev_id, arvif->aid,
-					 arvif->bssid);
+		params.vdev_id = arvif->vdev_id;
+		params.aid = arvif->aid;
+		params.bssid = arvif->bssid;
+		ret = ath12k_wmi_vdev_up(arvif->ar, &params);
 		if (ret) {
 			ath12k_warn(ab, "failed to bring vdev up %d: %d\n",
 				    arvif->vdev_id, ret);
diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index e77132d6aa831..6e73194a849e9 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -1103,7 +1103,7 @@ int ath12k_wmi_vdev_start(struct ath12k *ar, struct wmi_vdev_start_req_arg *arg,
 	return ret;
 }
 
-int ath12k_wmi_vdev_up(struct ath12k *ar, u32 vdev_id, u32 aid, const u8 *bssid)
+int ath12k_wmi_vdev_up(struct ath12k *ar, struct ath12k_wmi_vdev_up_params *params)
 {
 	struct ath12k_wmi_pdev *wmi = ar->wmi;
 	struct wmi_vdev_up_cmd *cmd;
@@ -1118,14 +1118,14 @@ int ath12k_wmi_vdev_up(struct ath12k *ar, u32 vdev_id, u32 aid, const u8 *bssid)
 
 	cmd->tlv_header = ath12k_wmi_tlv_cmd_hdr(WMI_TAG_VDEV_UP_CMD,
 						 sizeof(*cmd));
-	cmd->vdev_id = cpu_to_le32(vdev_id);
-	cmd->vdev_assoc_id = cpu_to_le32(aid);
+	cmd->vdev_id = cpu_to_le32(params->vdev_id);
+	cmd->vdev_assoc_id = cpu_to_le32(params->aid);
 
-	ether_addr_copy(cmd->vdev_bssid.addr, bssid);
+	ether_addr_copy(cmd->vdev_bssid.addr, params->bssid);
 
 	ath12k_dbg(ar->ab, ATH12K_DBG_WMI,
 		   "WMI mgmt vdev up id 0x%x assoc id %d bssid %pM\n",
-		   vdev_id, aid, bssid);
+		   params->vdev_id, params->aid, params->bssid);
 
 	ret = ath12k_wmi_cmd_send(wmi, skb, WMI_VDEV_UP_CMDID);
 	if (ret) {
diff --git a/drivers/net/wireless/ath/ath12k/wmi.h b/drivers/net/wireless/ath/ath12k/wmi.h
index 4051ed5a0b0a7..12c6cfb943c88 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.h
+++ b/drivers/net/wireless/ath/ath12k/wmi.h
@@ -2763,6 +2763,12 @@ struct wmi_vdev_delete_cmd {
 	__le32 vdev_id;
 } __packed;
 
+struct ath12k_wmi_vdev_up_params {
+	u32 vdev_id;
+	u32 aid;
+	const u8 *bssid;
+};
+
 struct wmi_vdev_up_cmd {
 	__le32 tlv_header;
 	__le32 vdev_id;
@@ -4893,8 +4899,7 @@ int ath12k_wmi_bcn_tmpl(struct ath12k *ar, u32 vdev_id,
 			struct ieee80211_mutable_offsets *offs,
 			struct sk_buff *bcn);
 int ath12k_wmi_vdev_down(struct ath12k *ar, u8 vdev_id);
-int ath12k_wmi_vdev_up(struct ath12k *ar, u32 vdev_id, u32 aid,
-		       const u8 *bssid);
+int ath12k_wmi_vdev_up(struct ath12k *ar, struct ath12k_wmi_vdev_up_params *params);
 int ath12k_wmi_vdev_stop(struct ath12k *ar, u8 vdev_id);
 int ath12k_wmi_vdev_start(struct ath12k *ar, struct wmi_vdev_start_req_arg *arg,
 			  bool restart);
-- 
GitLab


From 84edf47bcb31746a4070bc4783546132d855ed4b Mon Sep 17 00:00:00 2001
From: Aloka Dixit <quic_alokad@quicinc.com>
Date: Wed, 8 May 2024 13:29:08 -0700
Subject: [PATCH 053/950] wifi: ath12k: configure MBSSID parameters in AP mode

Include MBSSID parameters in WMI vdev up operation.

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

Signed-off-by: Aloka Dixit <quic_alokad@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240508202912.11902-6-quic_alokad@quicinc.com
---
 drivers/net/wireless/ath/ath12k/mac.c | 15 ++++++++++++++-
 drivers/net/wireless/ath/ath12k/wmi.c |  6 ++++++
 drivers/net/wireless/ath/ath12k/wmi.h |  3 +++
 3 files changed, 23 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index c6fa68aafdd82..3f57acc16c405 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -1399,6 +1399,11 @@ static void ath12k_control_beaconing(struct ath12k_vif *arvif,
 	params.vdev_id = arvif->vdev_id;
 	params.aid = arvif->aid;
 	params.bssid = arvif->bssid;
+	if (arvif->vif->mbssid_tx_vif) {
+		params.tx_bssid = ath12k_vif_to_arvif(arvif->vif->mbssid_tx_vif)->bssid;
+		params.nontx_profile_idx = info->bssid_index;
+		params.nontx_profile_cnt = 1 << info->bssid_indicator;
+	}
 	ret = ath12k_wmi_vdev_up(arvif->ar, &params);
 	if (ret) {
 		ath12k_warn(ar->ab, "failed to bring up vdev %d: %i\n",
@@ -7199,6 +7204,7 @@ ath12k_mac_update_vif_chan(struct ath12k *ar,
 {
 	struct ath12k_wmi_vdev_up_params params = {};
 	struct ath12k_base *ab = ar->ab;
+	struct ieee80211_vif *vif;
 	struct ath12k_vif *arvif;
 	int ret;
 	int i;
@@ -7241,7 +7247,8 @@ ath12k_mac_update_vif_chan(struct ath12k *ar,
 	/* TODO: Update ar->rx_channel */
 
 	for (i = 0; i < n_vifs; i++) {
-		arvif = ath12k_vif_to_arvif(vifs[i].vif);
+		vif = vifs[i].vif;
+		arvif = ath12k_vif_to_arvif(vif);
 
 		if (WARN_ON(!arvif->is_started))
 			continue;
@@ -7278,9 +7285,15 @@ ath12k_mac_update_vif_chan(struct ath12k *ar,
 			ath12k_warn(ab, "failed to update bcn tmpl during csa: %d\n",
 				    ret);
 
+		memset(&params, 0, sizeof(params));
 		params.vdev_id = arvif->vdev_id;
 		params.aid = arvif->aid;
 		params.bssid = arvif->bssid;
+		if (vif->mbssid_tx_vif) {
+			params.tx_bssid = ath12k_vif_to_arvif(vif->mbssid_tx_vif)->bssid;
+			params.nontx_profile_idx = vif->bss_conf.bssid_index;
+			params.nontx_profile_cnt = 1 << vif->bss_conf.bssid_indicator;
+		}
 		ret = ath12k_wmi_vdev_up(arvif->ar, &params);
 		if (ret) {
 			ath12k_warn(ab, "failed to bring vdev up %d: %d\n",
diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index 6e73194a849e9..4d5b02caee137 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -1123,6 +1123,12 @@ int ath12k_wmi_vdev_up(struct ath12k *ar, struct ath12k_wmi_vdev_up_params *para
 
 	ether_addr_copy(cmd->vdev_bssid.addr, params->bssid);
 
+	if (params->tx_bssid) {
+		ether_addr_copy(cmd->tx_vdev_bssid.addr, params->tx_bssid);
+		cmd->nontx_profile_idx = cpu_to_le32(params->nontx_profile_idx);
+		cmd->nontx_profile_cnt = cpu_to_le32(params->nontx_profile_cnt);
+	}
+
 	ath12k_dbg(ar->ab, ATH12K_DBG_WMI,
 		   "WMI mgmt vdev up id 0x%x assoc id %d bssid %pM\n",
 		   params->vdev_id, params->aid, params->bssid);
diff --git a/drivers/net/wireless/ath/ath12k/wmi.h b/drivers/net/wireless/ath/ath12k/wmi.h
index 12c6cfb943c88..9b0166a5a575d 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.h
+++ b/drivers/net/wireless/ath/ath12k/wmi.h
@@ -2767,6 +2767,9 @@ struct ath12k_wmi_vdev_up_params {
 	u32 vdev_id;
 	u32 aid;
 	const u8 *bssid;
+	const u8 *tx_bssid;
+	u32 nontx_profile_idx;
+	u32 nontx_profile_cnt;
 };
 
 struct wmi_vdev_up_cmd {
-- 
GitLab


From 9fd28936b641ab05ab244a85991e95c5be31e1a2 Mon Sep 17 00:00:00 2001
From: Aloka Dixit <quic_alokad@quicinc.com>
Date: Wed, 8 May 2024 13:29:09 -0700
Subject: [PATCH 054/950] wifi: ath12k: refactor arvif security parameter
 configuration

Configure security parameters in a separate function to make it
easier to support setting the same for nontransmitted profiles.

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

Signed-off-by: Aloka Dixit <quic_alokad@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240508202912.11902-7-quic_alokad@quicinc.com
---
 drivers/net/wireless/ath/ath12k/mac.c | 33 +++++++++++++++++----------
 1 file changed, 21 insertions(+), 12 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index 3f57acc16c405..6720ec0d7fdd6 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -1299,6 +1299,26 @@ static int ath12k_mac_remove_vendor_ie(struct sk_buff *skb, unsigned int oui,
 	return 0;
 }
 
+static void ath12k_mac_set_arvif_ies(struct ath12k_vif *arvif, struct sk_buff *bcn)
+{
+	struct ieee80211_mgmt *mgmt = (struct ieee80211_mgmt *)bcn->data;
+	const u8 *start, *tail;
+	u16 rem_len;
+
+	start = bcn->data + ieee80211_get_hdrlen_from_skb(bcn) + sizeof(mgmt->u.beacon);
+	tail = skb_tail_pointer(bcn);
+	rem_len = tail - start;
+
+	arvif->rsnie_present = false;
+	arvif->wpaie_present = false;
+
+	if (cfg80211_find_ie(WLAN_EID_RSN, start, rem_len))
+		arvif->rsnie_present = true;
+	if (cfg80211_find_vendor_ie(WLAN_OUI_MICROSOFT, WLAN_OUI_TYPE_MICROSOFT_WPA,
+				    start, rem_len))
+		arvif->wpaie_present = true;
+}
+
 static int ath12k_mac_setup_bcn_tmpl(struct ath12k_vif *arvif)
 {
 	struct ath12k *ar = arvif->ar;
@@ -1307,8 +1327,6 @@ static int ath12k_mac_setup_bcn_tmpl(struct ath12k_vif *arvif)
 	struct ieee80211_vif *vif = arvif->vif;
 	struct ieee80211_mutable_offsets offs = {};
 	struct sk_buff *bcn;
-	struct ieee80211_mgmt *mgmt;
-	u8 *ies;
 	int ret;
 
 	if (arvif->vdev_type != WMI_VDEV_TYPE_AP)
@@ -1320,16 +1338,7 @@ static int ath12k_mac_setup_bcn_tmpl(struct ath12k_vif *arvif)
 		return -EPERM;
 	}
 
-	ies = bcn->data + ieee80211_get_hdrlen_from_skb(bcn);
-	ies += sizeof(mgmt->u.beacon);
-
-	if (cfg80211_find_ie(WLAN_EID_RSN, ies, (skb_tail_pointer(bcn) - ies)))
-		arvif->rsnie_present = true;
-
-	if (cfg80211_find_vendor_ie(WLAN_OUI_MICROSOFT,
-				    WLAN_OUI_TYPE_MICROSOFT_WPA,
-				    ies, (skb_tail_pointer(bcn) - ies)))
-		arvif->wpaie_present = true;
+	ath12k_mac_set_arvif_ies(arvif, bcn);
 
 	if (arvif->vif->type == NL80211_IFTYPE_AP && arvif->vif->p2p) {
 		ret = ath12k_mac_setup_bcn_p2p_ie(arvif, bcn);
-- 
GitLab


From 8c6faa56bfb245a165820f46b8ea90e6ae1f24f5 Mon Sep 17 00:00:00 2001
From: Aloka Dixit <quic_alokad@quicinc.com>
Date: Wed, 8 May 2024 13:29:10 -0700
Subject: [PATCH 055/950] wifi: ath12k: add MBSSID beacon support

- A single beacon template is used for one multiple BSSID group as
only one interface from group transmits the beacons. But firmware
requires the host to send this template each time a nontransmitted
interface is brought up. Hence, modify existing logic to retrieve
the template from vif context of the transmitting interface. Also,
firmware crashes if host sends a template for a nontransmitted
interface which is already up, add a check to avoid this.
- Set rsnie_present and wpaie_present fields for nontransmitted VAPs.
- Send offset to the multiple BSSID element in the beacon template
firmware.

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

Signed-off-by: Aloka Dixit <quic_alokad@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240508202912.11902-8-quic_alokad@quicinc.com
---
 drivers/net/wireless/ath/ath12k/mac.c | 97 +++++++++++++++++++++++++--
 drivers/net/wireless/ath/ath12k/wmi.c |  1 +
 2 files changed, 94 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index 6720ec0d7fdd6..2cfed85990a98 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -1299,11 +1299,14 @@ static int ath12k_mac_remove_vendor_ie(struct sk_buff *skb, unsigned int oui,
 	return 0;
 }
 
-static void ath12k_mac_set_arvif_ies(struct ath12k_vif *arvif, struct sk_buff *bcn)
+static void ath12k_mac_set_arvif_ies(struct ath12k_vif *arvif, struct sk_buff *bcn,
+				     u8 bssid_index, bool *nontx_profile_found)
 {
 	struct ieee80211_mgmt *mgmt = (struct ieee80211_mgmt *)bcn->data;
+	const struct element *elem, *nontx, *index, *nie;
 	const u8 *start, *tail;
 	u16 rem_len;
+	u8 i;
 
 	start = bcn->data + ieee80211_get_hdrlen_from_skb(bcn) + sizeof(mgmt->u.beacon);
 	tail = skb_tail_pointer(bcn);
@@ -1317,28 +1320,114 @@ static void ath12k_mac_set_arvif_ies(struct ath12k_vif *arvif, struct sk_buff *b
 	if (cfg80211_find_vendor_ie(WLAN_OUI_MICROSOFT, WLAN_OUI_TYPE_MICROSOFT_WPA,
 				    start, rem_len))
 		arvif->wpaie_present = true;
+
+	/* Return from here for the transmitted profile */
+	if (!bssid_index)
+		return;
+
+	/* Initial rsnie_present for the nontransmitted profile is set to be same as that
+	 * of the transmitted profile. It will be changed if security configurations are
+	 * different.
+	 */
+	*nontx_profile_found = false;
+	for_each_element_id(elem, WLAN_EID_MULTIPLE_BSSID, start, rem_len) {
+		/* Fixed minimum MBSSID element length with at least one
+		 * nontransmitted BSSID profile is 12 bytes as given below;
+		 * 1 (max BSSID indicator) +
+		 * 2 (Nontransmitted BSSID profile: Subelement ID + length) +
+		 * 4 (Nontransmitted BSSID Capabilities: tag + length + info)
+		 * 2 (Nontransmitted BSSID SSID: tag + length)
+		 * 3 (Nontransmitted BSSID Index: tag + length + BSSID index
+		 */
+		if (elem->datalen < 12 || elem->data[0] < 1)
+			continue; /* Max BSSID indicator must be >=1 */
+
+		for_each_element(nontx, elem->data + 1, elem->datalen - 1) {
+			start = nontx->data;
+
+			if (nontx->id != 0 || nontx->datalen < 4)
+				continue; /* Invalid nontransmitted profile */
+
+			if (nontx->data[0] != WLAN_EID_NON_TX_BSSID_CAP ||
+			    nontx->data[1] != 2) {
+				continue; /* Missing nontransmitted BSS capabilities */
+			}
+
+			if (nontx->data[4] != WLAN_EID_SSID)
+				continue; /* Missing SSID for nontransmitted BSS */
+
+			index = cfg80211_find_elem(WLAN_EID_MULTI_BSSID_IDX,
+						   start, nontx->datalen);
+			if (!index || index->datalen < 1 || index->data[0] == 0)
+				continue; /* Invalid MBSSID Index element */
+
+			if (index->data[0] == bssid_index) {
+				*nontx_profile_found = true;
+				if (cfg80211_find_ie(WLAN_EID_RSN,
+						     nontx->data,
+						     nontx->datalen)) {
+					arvif->rsnie_present = true;
+					return;
+				} else if (!arvif->rsnie_present) {
+					return; /* Both tx and nontx BSS are open */
+				}
+
+				nie = cfg80211_find_ext_elem(WLAN_EID_EXT_NON_INHERITANCE,
+							     nontx->data,
+							     nontx->datalen);
+				if (!nie || nie->datalen < 2)
+					return; /* Invalid non-inheritance element */
+
+				for (i = 1; i < nie->datalen - 1; i++) {
+					if (nie->data[i] == WLAN_EID_RSN) {
+						arvif->rsnie_present = false;
+						break;
+					}
+				}
+
+				return;
+			}
+		}
+	}
 }
 
 static int ath12k_mac_setup_bcn_tmpl(struct ath12k_vif *arvif)
 {
+	struct ath12k_vif *tx_arvif = arvif;
 	struct ath12k *ar = arvif->ar;
 	struct ath12k_base *ab = ar->ab;
-	struct ieee80211_hw *hw = ath12k_ar_to_hw(ar);
 	struct ieee80211_vif *vif = arvif->vif;
 	struct ieee80211_mutable_offsets offs = {};
+	bool nontx_profile_found = false;
 	struct sk_buff *bcn;
 	int ret;
 
 	if (arvif->vdev_type != WMI_VDEV_TYPE_AP)
 		return 0;
 
-	bcn = ieee80211_beacon_get_template(hw, vif, &offs, 0);
+	if (vif->mbssid_tx_vif) {
+		tx_arvif = ath12k_vif_to_arvif(vif->mbssid_tx_vif);
+		if (tx_arvif != arvif && arvif->is_up)
+			return 0;
+	}
+
+	bcn = ieee80211_beacon_get_template(ath12k_ar_to_hw(tx_arvif->ar), tx_arvif->vif,
+					    &offs, 0);
 	if (!bcn) {
 		ath12k_warn(ab, "failed to get beacon template from mac80211\n");
 		return -EPERM;
 	}
 
-	ath12k_mac_set_arvif_ies(arvif, bcn);
+	if (tx_arvif == arvif) {
+		ath12k_mac_set_arvif_ies(arvif, bcn, 0, NULL);
+	} else {
+		ath12k_mac_set_arvif_ies(arvif, bcn,
+					 arvif->vif->bss_conf.bssid_index,
+					 &nontx_profile_found);
+		if (!nontx_profile_found)
+			ath12k_warn(ab,
+				    "nontransmitted profile not found in beacon template\n");
+	}
 
 	if (arvif->vif->type == NL80211_IFTYPE_AP && arvif->vif->p2p) {
 		ret = ath12k_mac_setup_bcn_p2p_ie(arvif, bcn);
diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index 4d5b02caee137..57fb01d66a0d2 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -1813,6 +1813,7 @@ int ath12k_wmi_bcn_tmpl(struct ath12k *ar, u32 vdev_id,
 	cmd->csa_switch_count_offset = cpu_to_le32(offs->cntdwn_counter_offs[0]);
 	cmd->ext_csa_switch_count_offset = cpu_to_le32(offs->cntdwn_counter_offs[1]);
 	cmd->buf_len = cpu_to_le32(bcn->len);
+	cmd->mbssid_ie_offset = cpu_to_le32(offs->mbssid_off);
 
 	ptr = skb->data + sizeof(*cmd);
 
-- 
GitLab


From f27fbd76a98feca81688175985fbfa31bad8cd75 Mon Sep 17 00:00:00 2001
From: Aloka Dixit <quic_alokad@quicinc.com>
Date: Wed, 8 May 2024 13:29:11 -0700
Subject: [PATCH 056/950] wifi: ath12k: add EMA beacon support

Add new function ath12k_mac_setup_bcn_tmpl_ema() which retrieves
a list of EMA (Enhanced Multi-BSSID Advertisements) beacon templates
from mac80211 and sends all to firmware. Add support to send EMA
configurations to firmware by adding a new parameter 'ema_params' in
struct wmi_bcn_tmpl_cmd.

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

Signed-off-by: Aloka Dixit <quic_alokad@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240508202912.11902-9-quic_alokad@quicinc.com
---
 drivers/net/wireless/ath/ath12k/mac.c | 55 ++++++++++++++++++++++++++-
 drivers/net/wireless/ath/ath12k/wmi.c | 13 ++++++-
 drivers/net/wireless/ath/ath12k/wmi.h | 18 ++++++++-
 3 files changed, 83 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index 2cfed85990a98..e86af398b359d 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -1391,6 +1391,56 @@ static void ath12k_mac_set_arvif_ies(struct ath12k_vif *arvif, struct sk_buff *b
 	}
 }
 
+static int ath12k_mac_setup_bcn_tmpl_ema(struct ath12k_vif *arvif)
+{
+	struct ieee80211_bss_conf *bss_conf = &arvif->vif->bss_conf;
+	struct ath12k_wmi_bcn_tmpl_ema_arg ema_args;
+	struct ieee80211_ema_beacons *beacons;
+	struct ath12k_vif *tx_arvif;
+	bool nontx_profile_found = false;
+	int ret = 0;
+	u8 i;
+
+	tx_arvif = ath12k_vif_to_arvif(arvif->vif->mbssid_tx_vif);
+	beacons = ieee80211_beacon_get_template_ema_list(ath12k_ar_to_hw(tx_arvif->ar),
+							 tx_arvif->vif, 0);
+	if (!beacons || !beacons->cnt) {
+		ath12k_warn(arvif->ar->ab,
+			    "failed to get ema beacon templates from mac80211\n");
+		return -EPERM;
+	}
+
+	if (tx_arvif == arvif)
+		ath12k_mac_set_arvif_ies(arvif, beacons->bcn[0].skb, 0, NULL);
+
+	for (i = 0; i < beacons->cnt; i++) {
+		if (tx_arvif != arvif && !nontx_profile_found)
+			ath12k_mac_set_arvif_ies(arvif, beacons->bcn[i].skb,
+						 bss_conf->bssid_index,
+						 &nontx_profile_found);
+
+		ema_args.bcn_cnt = beacons->cnt;
+		ema_args.bcn_index = i;
+		ret = ath12k_wmi_bcn_tmpl(tx_arvif->ar, tx_arvif->vdev_id,
+					  &beacons->bcn[i].offs,
+					  beacons->bcn[i].skb, &ema_args);
+		if (ret) {
+			ath12k_warn(tx_arvif->ar->ab,
+				    "failed to set ema beacon template id %i error %d\n",
+				    i, ret);
+			break;
+		}
+	}
+
+	if (tx_arvif != arvif && !nontx_profile_found)
+		ath12k_warn(arvif->ar->ab,
+			    "nontransmitted bssid index %u not found in beacon template\n",
+			    bss_conf->bssid_index);
+
+	ieee80211_beacon_free_ema_list(beacons);
+	return ret;
+}
+
 static int ath12k_mac_setup_bcn_tmpl(struct ath12k_vif *arvif)
 {
 	struct ath12k_vif *tx_arvif = arvif;
@@ -1409,6 +1459,9 @@ static int ath12k_mac_setup_bcn_tmpl(struct ath12k_vif *arvif)
 		tx_arvif = ath12k_vif_to_arvif(vif->mbssid_tx_vif);
 		if (tx_arvif != arvif && arvif->is_up)
 			return 0;
+
+		if (vif->bss_conf.ema_ap)
+			return ath12k_mac_setup_bcn_tmpl_ema(arvif);
 	}
 
 	bcn = ieee80211_beacon_get_template(ath12k_ar_to_hw(tx_arvif->ar), tx_arvif->vif,
@@ -1452,7 +1505,7 @@ static int ath12k_mac_setup_bcn_tmpl(struct ath12k_vif *arvif)
 		}
 	}
 
-	ret = ath12k_wmi_bcn_tmpl(ar, arvif->vdev_id, &offs, bcn);
+	ret = ath12k_wmi_bcn_tmpl(ar, arvif->vdev_id, &offs, bcn, NULL);
 
 	if (ret)
 		ath12k_warn(ab, "failed to submit beacon template command: %d\n",
diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index 57fb01d66a0d2..99106b088311c 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -1788,13 +1788,15 @@ int ath12k_wmi_p2p_go_bcn_ie(struct ath12k *ar, u32 vdev_id,
 
 int ath12k_wmi_bcn_tmpl(struct ath12k *ar, u32 vdev_id,
 			struct ieee80211_mutable_offsets *offs,
-			struct sk_buff *bcn)
+			struct sk_buff *bcn,
+			struct ath12k_wmi_bcn_tmpl_ema_arg *ema_args)
 {
 	struct ath12k_wmi_pdev *wmi = ar->wmi;
 	struct wmi_bcn_tmpl_cmd *cmd;
 	struct ath12k_wmi_bcn_prb_info_params *bcn_prb_info;
 	struct wmi_tlv *tlv;
 	struct sk_buff *skb;
+	u32 ema_params = 0;
 	void *ptr;
 	int ret, len;
 	size_t aligned_len = roundup(bcn->len, 4);
@@ -1814,6 +1816,15 @@ int ath12k_wmi_bcn_tmpl(struct ath12k *ar, u32 vdev_id,
 	cmd->ext_csa_switch_count_offset = cpu_to_le32(offs->cntdwn_counter_offs[1]);
 	cmd->buf_len = cpu_to_le32(bcn->len);
 	cmd->mbssid_ie_offset = cpu_to_le32(offs->mbssid_off);
+	if (ema_args) {
+		u32p_replace_bits(&ema_params, ema_args->bcn_cnt, WMI_EMA_BEACON_CNT);
+		u32p_replace_bits(&ema_params, ema_args->bcn_index, WMI_EMA_BEACON_IDX);
+		if (ema_args->bcn_index == 0)
+			u32p_replace_bits(&ema_params, 1, WMI_EMA_BEACON_FIRST);
+		if (ema_args->bcn_index + 1 == ema_args->bcn_cnt)
+			u32p_replace_bits(&ema_params, 1, WMI_EMA_BEACON_LAST);
+		cmd->ema_params = cpu_to_le32(ema_params);
+	}
 
 	ptr = skb->data + sizeof(*cmd);
 
diff --git a/drivers/net/wireless/ath/ath12k/wmi.h b/drivers/net/wireless/ath/ath12k/wmi.h
index 9b0166a5a575d..7f83c4583919a 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.h
+++ b/drivers/net/wireless/ath/ath12k/wmi.h
@@ -3533,6 +3533,16 @@ struct ath12k_wmi_p2p_noa_info {
 
 #define WMI_BEACON_TX_BUFFER_SIZE	512
 
+#define WMI_EMA_BEACON_CNT      GENMASK(7, 0)
+#define WMI_EMA_BEACON_IDX      GENMASK(15, 8)
+#define WMI_EMA_BEACON_FIRST    GENMASK(23, 16)
+#define WMI_EMA_BEACON_LAST     GENMASK(31, 24)
+
+struct ath12k_wmi_bcn_tmpl_ema_arg {
+	u8 bcn_cnt;
+	u8 bcn_index;
+};
+
 struct wmi_bcn_tmpl_cmd {
 	__le32 tlv_header;
 	__le32 vdev_id;
@@ -3543,6 +3553,11 @@ struct wmi_bcn_tmpl_cmd {
 	__le32 csa_event_bitmap;
 	__le32 mbssid_ie_offset;
 	__le32 esp_ie_offset;
+	__le32 csc_switch_count_offset;
+	__le32 csc_event_bitmap;
+	__le32 mu_edca_ie_offset;
+	__le32 feature_enable_bitmap;
+	__le32 ema_params;
 } __packed;
 
 struct wmi_p2p_go_set_beacon_ie_cmd {
@@ -4900,7 +4915,8 @@ int ath12k_wmi_p2p_go_bcn_ie(struct ath12k *ar, u32 vdev_id,
 			     const u8 *p2p_ie);
 int ath12k_wmi_bcn_tmpl(struct ath12k *ar, u32 vdev_id,
 			struct ieee80211_mutable_offsets *offs,
-			struct sk_buff *bcn);
+			struct sk_buff *bcn,
+			struct ath12k_wmi_bcn_tmpl_ema_arg *ema_args);
 int ath12k_wmi_vdev_down(struct ath12k *ar, u8 vdev_id);
 int ath12k_wmi_vdev_up(struct ath12k *ar, struct ath12k_wmi_vdev_up_params *params);
 int ath12k_wmi_vdev_stop(struct ath12k *ar, u8 vdev_id);
-- 
GitLab


From c740a18f62f5bbf2c88c3160d189704cbe001255 Mon Sep 17 00:00:00 2001
From: Aloka Dixit <quic_alokad@quicinc.com>
Date: Wed, 8 May 2024 13:29:12 -0700
Subject: [PATCH 057/950] wifi: ath12k: skip sending vdev down for channel
 switch

Remove the unnecessary WMI vdev down operation as firmware
internally does so already as part of WMI vdev restart.
Repeated vdev down results in a firmware crash during channel
switch operation when multiple BSSID advertisements are enabled:
ath12k_pci 0000:06:00.0: firmware crashed: MHI_CB_SYS_ERROR
ath12k_pci 0000:06:00.0: failed to send WMI_VDEV_SET_PARAM_CMDID
ath12k_pci 0000:06:00.0: failed to set vdev 5 HE MU mode: -108 param_value 7b
ath12k_pci 0000:06:00.0: failed to set he mode vdev 5
ath12k_pci 0000:06:00.0: failed to restart vdev 5: -108
ath12k_pci 0000:06:00.0: failed to send WMI_VDEV_SET_PARAM_CMDID
ath12k_pci 0000:06:00.0: failed to set vdev 4 HE MU mode: -108 param_value 7b
ath12k_pci 0000:06:00.0: failed to set he mode vdev 4
ath12k_pci 0000:06:00.0: failed to restart vdev 4: -108
ath12k_pci 0000:06:00.0: failed to send WMI_VDEV_SET_PARAM_CMDID

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

Signed-off-by: Aloka Dixit <quic_alokad@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240508202912.11902-10-quic_alokad@quicinc.com
---
 drivers/net/wireless/ath/ath12k/mac.c | 29 +++------------------------
 1 file changed, 3 insertions(+), 26 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index e86af398b359d..33741ebecdf6c 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -7364,9 +7364,10 @@ ath12k_mac_update_vif_chan(struct ath12k *ar,
 	lockdep_assert_held(&ar->conf_mutex);
 
 	for (i = 0; i < n_vifs; i++) {
-		arvif = ath12k_vif_to_arvif(vifs[i].vif);
+		vif = vifs[i].vif;
+		arvif = ath12k_vif_to_arvif(vif);
 
-		if (vifs[i].vif->type == NL80211_IFTYPE_MONITOR)
+		if (vif->type == NL80211_IFTYPE_MONITOR)
 			monitor_vif = true;
 
 		ath12k_dbg(ab, ATH12K_DBG_MAC,
@@ -7377,30 +7378,6 @@ ath12k_mac_update_vif_chan(struct ath12k *ar,
 			   vifs[i].old_ctx->def.width,
 			   vifs[i].new_ctx->def.width);
 
-		if (WARN_ON(!arvif->is_started))
-			continue;
-
-		if (WARN_ON(!arvif->is_up))
-			continue;
-
-		ret = ath12k_wmi_vdev_down(ar, arvif->vdev_id);
-		if (ret) {
-			ath12k_warn(ab, "failed to down vdev %d: %d\n",
-				    arvif->vdev_id, ret);
-			continue;
-		}
-	}
-
-	/* All relevant vdevs are downed and associated channel resources
-	 * should be available for the channel switch now.
-	 */
-
-	/* TODO: Update ar->rx_channel */
-
-	for (i = 0; i < n_vifs; i++) {
-		vif = vifs[i].vif;
-		arvif = ath12k_vif_to_arvif(vif);
-
 		if (WARN_ON(!arvif->is_started))
 			continue;
 
-- 
GitLab


From 0ce9ab2785e4e9ca0752390d8e5ab65bd08f0e78 Mon Sep 17 00:00:00 2001
From: Nithyanantham Paramasivam <quic_nithp@quicinc.com>
Date: Fri, 10 May 2024 12:34:27 +0530
Subject: [PATCH 058/950] wifi: ath12k: Fix tx completion ring (WBM2SW) setup
 failure

We observe intermittent ping failures from the access point (AP) to
station (STA) in any mode (AP-STA or Mesh) configured. Specifically,
the transmission completion status is not received at tx completion
ring id 4 (WBM2SW ring4) for the packets transmitted via TCL DATA
ring id 3. This prevents freeing up tx descriptors and leads
to buffer exhaustion.

Currently, during initialization of the WBM2SW ring, we are directly
mapping the ring number to the ring mask to obtain the ring mask
group index. This approach is causing setup failures for WBM2SW
ring 4. Similarly, during runtime, when receiving incoming
transmission completion status, the validation of the ring number by
mapping the interrupted ring mask. This is resulting in
validation failure. Thereby preventing entry into the completion
handler ath12k_dp_tx_completion_handler().

The existing design assumed that the ring numbers would always be
sequential and could be directly mapped with the ring mask. However,
this assumption does not hold true for WBM2SW ring 4. Therefore,
modify the design such that, instead of mapping the ring number,
the ring ID is mapped with the ring mask.

According to this design:

1. During initialization of the WBM2SW ring, mapping the ring ID
to the ring mask will ensure obtaining the correct ring mask group
ID.

2. During runtime, validating the interrupted ring mask group ID
within the transmission completion group is sufficient. This
approach allows the ring ID to be derived from the interrupted ring
mask and enables entry into the completion handler.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.0.1-00029-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Fixes: d889913205cf ("wifi: ath12k: driver for Qualcomm Wi-Fi 7 devices")
Signed-off-by: Nithyanantham Paramasivam <quic_nithp@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240510070427.206152-1-quic_nithp@quicinc.com
---
 drivers/net/wireless/ath/ath12k/dp.c | 18 +++++++++++++-----
 drivers/net/wireless/ath/ath12k/hw.c |  2 +-
 2 files changed, 14 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/dp.c b/drivers/net/wireless/ath/ath12k/dp.c
index 412ab08e6cca2..c04fa3eb57d69 100644
--- a/drivers/net/wireless/ath/ath12k/dp.c
+++ b/drivers/net/wireless/ath/ath12k/dp.c
@@ -132,7 +132,9 @@ static int ath12k_dp_srng_find_ring_in_mask(int ring_num, const u8 *grp_mask)
 static int ath12k_dp_srng_calculate_msi_group(struct ath12k_base *ab,
 					      enum hal_ring_type type, int ring_num)
 {
+	const struct ath12k_hal_tcl_to_wbm_rbm_map *map;
 	const u8 *grp_mask;
+	int i;
 
 	switch (type) {
 	case HAL_WBM2SW_RELEASE:
@@ -140,6 +142,14 @@ static int ath12k_dp_srng_calculate_msi_group(struct ath12k_base *ab,
 			grp_mask = &ab->hw_params->ring_mask->rx_wbm_rel[0];
 			ring_num = 0;
 		} else {
+			map = ab->hw_params->hal_ops->tcl_to_wbm_rbm_map;
+			for (i = 0; i < ab->hw_params->max_tx_ring; i++) {
+				if (ring_num == map[i].wbm_ring_num) {
+					ring_num = i;
+					break;
+				}
+			}
+
 			grp_mask = &ab->hw_params->ring_mask->tx[0];
 		}
 		break;
@@ -867,11 +877,9 @@ int ath12k_dp_service_srng(struct ath12k_base *ab,
 	enum dp_monitor_mode monitor_mode;
 	u8 ring_mask;
 
-	while (i < ab->hw_params->max_tx_ring) {
-		if (ab->hw_params->ring_mask->tx[grp_id] &
-			BIT(ab->hw_params->hal_ops->tcl_to_wbm_rbm_map[i].wbm_ring_num))
-			ath12k_dp_tx_completion_handler(ab, i);
-		i++;
+	if (ab->hw_params->ring_mask->tx[grp_id]) {
+		i = fls(ab->hw_params->ring_mask->tx[grp_id]) - 1;
+		ath12k_dp_tx_completion_handler(ab, i);
 	}
 
 	if (ab->hw_params->ring_mask->rx_err[grp_id]) {
diff --git a/drivers/net/wireless/ath/ath12k/hw.c b/drivers/net/wireless/ath/ath12k/hw.c
index b3ba753d4a855..5a1d406e6b1f9 100644
--- a/drivers/net/wireless/ath/ath12k/hw.c
+++ b/drivers/net/wireless/ath/ath12k/hw.c
@@ -580,8 +580,8 @@ static const struct ath12k_hw_ring_mask ath12k_hw_ring_mask_qcn9274 = {
 static const struct ath12k_hw_ring_mask ath12k_hw_ring_mask_wcn7850 = {
 	.tx  = {
 		ATH12K_TX_RING_MASK_0,
+		ATH12K_TX_RING_MASK_1,
 		ATH12K_TX_RING_MASK_2,
-		ATH12K_TX_RING_MASK_4,
 	},
 	.rx_mon_dest = {
 	},
-- 
GitLab


From 3a29442a17413e9e64f00db3b98dbf911324cb86 Mon Sep 17 00:00:00 2001
From: Kang Yang <quic_kangyang@quicinc.com>
Date: Fri, 10 May 2024 19:12:38 +0800
Subject: [PATCH 059/950] wifi: ath12k: remove redundant peer delete for
 WCN7850

ath12k_mac_op_unassign_vif_chanctx() will do peer delete for WCN7850's monitor
interface. But for host no need to do peer create/delete for monitor interface
because firmware doesn't require it, QCN9274 is the same. Also, the first
judgement is true only for WCN7850, so this logic won't affect QCN9274 at any
time.

So remove this peer delete.

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Signed-off-by: Kang Yang <quic_kangyang@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240510111238.1113-1-quic_kangyang@quicinc.com
---
 drivers/net/wireless/ath/ath12k/mac.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index 33741ebecdf6c..784964ae03ec5 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -7651,11 +7651,6 @@ ath12k_mac_op_unassign_vif_chanctx(struct ieee80211_hw *hw,
 
 	WARN_ON(!arvif->is_started);
 
-	if (ab->hw_params->vdev_start_delay &&
-	    arvif->vdev_type == WMI_VDEV_TYPE_MONITOR &&
-	    ath12k_peer_find_by_addr(ab, ar->mac_addr))
-		ath12k_peer_delete(ar, arvif->vdev_id, ar->mac_addr);
-
 	if (arvif->vdev_type == WMI_VDEV_TYPE_MONITOR) {
 		ret = ath12k_mac_monitor_stop(ar);
 		if (ret) {
-- 
GitLab


From 28bfc1c9c9d0e2165ee9e3b50793b8b463e52e01 Mon Sep 17 00:00:00 2001
From: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Date: Tue, 14 May 2024 12:04:11 +0530
Subject: [PATCH 060/950] wifi: ath12k: remove duplicate definition of
 MAX_RADIOS

Remove the duplicate definition of MAX_RADIOS from the core header file.

No functional changes, compile tested only.

Signed-off-by: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240514063412.3483723-2-quic_periyasa@quicinc.com
---
 drivers/net/wireless/ath/ath12k/core.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/core.h b/drivers/net/wireless/ath/ath12k/core.h
index 6da242c0d51da..7d20b09c52e66 100644
--- a/drivers/net/wireless/ath/ath12k/core.h
+++ b/drivers/net/wireless/ath/ath12k/core.h
@@ -180,8 +180,6 @@ struct ath12k_he {
 	u32 heop_param;
 };
 
-#define MAX_RADIOS 3
-
 enum {
 	WMI_HOST_TP_SCALE_MAX   = 0,
 	WMI_HOST_TP_SCALE_50    = 1,
-- 
GitLab


From 7678f8bfd74c324bd10499cf1d05e5720d9449b2 Mon Sep 17 00:00:00 2001
From: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Date: Tue, 14 May 2024 12:04:12 +0530
Subject: [PATCH 061/950] wifi: ath12k: use correct MAX_RADIOS

The current value of the MAX_RADIOS definition is 3. This is incorrect
because no device supports more than 2 radios.

An incorrect MAX_RADIOS value can lead to:
 - unnecessary memory allocation for pdev related entities.
 - invalid pdev id validation.
 - Misconceptions for code readers.

Therefore, modify the MAX_RADIOS definition as 2.

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

Signed-off-by: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240514063412.3483723-3-quic_periyasa@quicinc.com
---
 drivers/net/wireless/ath/ath12k/wmi.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath12k/wmi.h b/drivers/net/wireless/ath/ath12k/wmi.h
index 7f83c4583919a..c2b86e187a03f 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.h
+++ b/drivers/net/wireless/ath/ath12k/wmi.h
@@ -4804,7 +4804,7 @@ struct wmi_probe_tmpl_cmd {
 	__le32 buf_len;
 } __packed;
 
-#define MAX_RADIOS 3
+#define MAX_RADIOS 2
 
 #define WMI_SERVICE_READY_TIMEOUT_HZ (5 * HZ)
 #define WMI_SEND_TIMEOUT_HZ (3 * HZ)
-- 
GitLab


From 637c435f08ea7e77c53a2ad590b651d0de225e3b Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Thu, 16 May 2024 11:30:41 +0300
Subject: [PATCH 062/950] wifi: ath11k: Fix error path in
 ath11k_pcic_ext_irq_config

If one of the dummy allocation fails in ath11k_pcic_ext_irq_config(),
the previous allocated devices might leak due to returning without
deallocating the devices.

Instead of returning on the error path, deallocate all the previously
allocated net_devices and then return.

Fixes: bca592ead825 ("wifi: ath11k: allocate dummy net_device dynamically")
Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240508185902.70975-1-leitao@debian.org
---
 drivers/net/wireless/ath/ath11k/pcic.c | 25 +++++++++++++++++--------
 1 file changed, 17 insertions(+), 8 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/pcic.c b/drivers/net/wireless/ath/ath11k/pcic.c
index 79eb3f9c902f4..debe7c5919ef0 100644
--- a/drivers/net/wireless/ath/ath11k/pcic.c
+++ b/drivers/net/wireless/ath/ath11k/pcic.c
@@ -561,6 +561,7 @@ static int ath11k_pcic_ext_irq_config(struct ath11k_base *ab)
 {
 	int i, j, n, ret, num_vectors = 0;
 	u32 user_base_data = 0, base_vector = 0;
+	struct ath11k_ext_irq_grp *irq_grp;
 	unsigned long irq_flags;
 
 	ret = ath11k_pcic_get_user_msi_assignment(ab, "DP", &num_vectors,
@@ -574,14 +575,16 @@ static int ath11k_pcic_ext_irq_config(struct ath11k_base *ab)
 		irq_flags |= IRQF_NOBALANCING;
 
 	for (i = 0; i < ATH11K_EXT_IRQ_GRP_NUM_MAX; i++) {
-		struct ath11k_ext_irq_grp *irq_grp = &ab->ext_irq_grp[i];
+		irq_grp = &ab->ext_irq_grp[i];
 		u32 num_irq = 0;
 
 		irq_grp->ab = ab;
 		irq_grp->grp_id = i;
 		irq_grp->napi_ndev = alloc_netdev_dummy(0);
-		if (!irq_grp->napi_ndev)
-			return -ENOMEM;
+		if (!irq_grp->napi_ndev) {
+			ret = -ENOMEM;
+			goto fail_allocate;
+		}
 
 		netif_napi_add(irq_grp->napi_ndev, &irq_grp->napi,
 			       ath11k_pcic_ext_grp_napi_poll);
@@ -606,11 +609,8 @@ static int ath11k_pcic_ext_irq_config(struct ath11k_base *ab)
 			int irq = ath11k_pcic_get_msi_irq(ab, vector);
 
 			if (irq < 0) {
-				for (n = 0; n <= i; n++) {
-					irq_grp = &ab->ext_irq_grp[n];
-					free_netdev(irq_grp->napi_ndev);
-				}
-				return irq;
+				ret = irq;
+				goto fail_irq;
 			}
 
 			ab->irq_num[irq_idx] = irq;
@@ -635,6 +635,15 @@ static int ath11k_pcic_ext_irq_config(struct ath11k_base *ab)
 	}
 
 	return 0;
+fail_irq:
+	/* i ->napi_ndev was properly allocated. Free it also */
+	i += 1;
+fail_allocate:
+	for (n = 0; n < i; n++) {
+		irq_grp = &ab->ext_irq_grp[n];
+		free_netdev(irq_grp->napi_ndev);
+	}
+	return ret;
 }
 
 int ath11k_pcic_config_irq(struct ath11k_base *ab)
-- 
GitLab


From ed61863debb2df0856524b5c61d2a7f7731c2e83 Mon Sep 17 00:00:00 2001
From: Lingbo Kong <quic_lingbok@quicinc.com>
Date: Thu, 16 May 2024 11:30:44 +0300
Subject: [PATCH 063/950] wifi: ath12k: fix ack signal strength calculation

Currently, the calculation of ack signal strength is incorrect.

This is because before calculating the ack signal strength, ath12k need
to determine whether the hardware and firmware support db2dbm. If the
hardware and firmware support db2dbm, do not need to add noise floor,
otherwise, need to add noise floor.

Besides, the value of ack_rssi passed by firmware to ath12k should be a
signed number, so change its type to s8.

This patch affects QCN9274 and WCN7850 because they have the same issue.

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3
Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.0.1-00029-QCAHKSWPL_SILICONZ-1

Signed-off-by: Lingbo Kong <quic_lingbok@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240511030917.65811-1-quic_lingbok@quicinc.com
---
 drivers/net/wireless/ath/ath12k/dp_tx.c  | 16 ++++++++++++----
 drivers/net/wireless/ath/ath12k/dp_tx.h  |  2 +-
 drivers/net/wireless/ath/ath12k/hal_tx.h |  4 ++--
 3 files changed, 15 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/dp_tx.c b/drivers/net/wireless/ath/ath12k/dp_tx.c
index 32496015cf9a1..f57bc8d69715e 100644
--- a/drivers/net/wireless/ath/ath12k/dp_tx.c
+++ b/drivers/net/wireless/ath/ath12k/dp_tx.c
@@ -393,8 +393,12 @@ ath12k_dp_tx_htt_tx_complete_buf(struct ath12k_base *ab,
 	if (ts->acked) {
 		if (!(info->flags & IEEE80211_TX_CTL_NO_ACK)) {
 			info->flags |= IEEE80211_TX_STAT_ACK;
-			info->status.ack_signal = ATH12K_DEFAULT_NOISE_FLOOR +
-						  ts->ack_rssi;
+			info->status.ack_signal = ts->ack_rssi;
+
+			if (!test_bit(WMI_TLV_SERVICE_HW_DB2DBM_CONVERSION_SUPPORT,
+				      ab->wmi_ab.svc_map))
+				info->status.ack_signal += ATH12K_DEFAULT_NOISE_FLOOR;
+
 			info->status.flags = IEEE80211_TX_STATUS_ACK_SIGNAL_VALID;
 		} else {
 			info->flags |= IEEE80211_TX_STAT_NOACK_TRANSMITTED;
@@ -486,8 +490,12 @@ static void ath12k_dp_tx_complete_msdu(struct ath12k *ar,
 	case HAL_WBM_TQM_REL_REASON_FRAME_ACKED:
 		if (!(info->flags & IEEE80211_TX_CTL_NO_ACK)) {
 			info->flags |= IEEE80211_TX_STAT_ACK;
-			info->status.ack_signal = ATH12K_DEFAULT_NOISE_FLOOR +
-						  ts->ack_rssi;
+			info->status.ack_signal = ts->ack_rssi;
+
+			if (!test_bit(WMI_TLV_SERVICE_HW_DB2DBM_CONVERSION_SUPPORT,
+				      ab->wmi_ab.svc_map))
+				info->status.ack_signal += ATH12K_DEFAULT_NOISE_FLOOR;
+
 			info->status.flags = IEEE80211_TX_STATUS_ACK_SIGNAL_VALID;
 		}
 		break;
diff --git a/drivers/net/wireless/ath/ath12k/dp_tx.h b/drivers/net/wireless/ath/ath12k/dp_tx.h
index 7faa81faf6a72..55ff8cc721e37 100644
--- a/drivers/net/wireless/ath/ath12k/dp_tx.h
+++ b/drivers/net/wireless/ath/ath12k/dp_tx.h
@@ -12,7 +12,7 @@
 
 struct ath12k_dp_htt_wbm_tx_status {
 	bool acked;
-	int ack_rssi;
+	s8 ack_rssi;
 };
 
 int ath12k_dp_tx_htt_h2t_ver_req_msg(struct ath12k_base *ab);
diff --git a/drivers/net/wireless/ath/ath12k/hal_tx.h b/drivers/net/wireless/ath/ath12k/hal_tx.h
index 7c837094a6f79..3cf5973771d78 100644
--- a/drivers/net/wireless/ath/ath12k/hal_tx.h
+++ b/drivers/net/wireless/ath/ath12k/hal_tx.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2022, 2024 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH12K_HAL_TX_H
@@ -57,7 +57,7 @@ struct hal_tx_info {
 struct hal_tx_status {
 	enum hal_wbm_rel_src_module buf_rel_source;
 	enum hal_wbm_tqm_rel_reason status;
-	u8 ack_rssi;
+	s8 ack_rssi;
 	u32 flags; /* %HAL_TX_STATUS_FLAGS_ */
 	u32 ppdu_id;
 	u8 try_cnt;
-- 
GitLab


From 6fe46d5c0a84471e06fa5b22d7f4253ebf98b071 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Alexis=20Lothor=C3=A9?= <alexis.lothore@bootlin.com>
Date: Tue, 14 May 2024 17:51:19 +0200
Subject: [PATCH 064/950] wifi: wilc1000: set net device registration as last
 step during interface creation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

net device registration is currently done in wilc_netdev_ifc_init but
other initialization operations are still done after this registration.
Since net device is assumed to be usable right after registration, it
should be the very last step of initialization.

Move netdev registration at the very end of wilc_netdev_ifc_init to let
this function completely initialize netdevice before registering it.

Signed-off-by: Alexis Lothoré <alexis.lothore@bootlin.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://msgid.link/20240514-mac_addr_at_probe-v2-1-afef09f1cd10@bootlin.com
---
 .../net/wireless/microchip/wilc1000/netdev.c  | 31 ++++++++++---------
 1 file changed, 16 insertions(+), 15 deletions(-)

diff --git a/drivers/net/wireless/microchip/wilc1000/netdev.c b/drivers/net/wireless/microchip/wilc1000/netdev.c
index 73f56f7b002bf..acc9b9a645524 100644
--- a/drivers/net/wireless/microchip/wilc1000/netdev.c
+++ b/drivers/net/wireless/microchip/wilc1000/netdev.c
@@ -965,16 +965,6 @@ struct wilc_vif *wilc_netdev_ifc_init(struct wilc *wl, const char *name,
 	vif->priv.wdev.iftype = type;
 	vif->priv.dev = ndev;
 
-	if (rtnl_locked)
-		ret = cfg80211_register_netdevice(ndev);
-	else
-		ret = register_netdev(ndev);
-
-	if (ret) {
-		ret = -EFAULT;
-		goto error;
-	}
-
 	ndev->needs_free_netdev = true;
 	vif->iftype = vif_type;
 	vif->idx = wilc_get_available_idx(wl);
@@ -985,13 +975,24 @@ struct wilc_vif *wilc_netdev_ifc_init(struct wilc *wl, const char *name,
 	mutex_unlock(&wl->vif_mutex);
 	synchronize_rcu();
 
-	return vif;
-
-error:
 	if (rtnl_locked)
-		cfg80211_unregister_netdevice(ndev);
+		ret = cfg80211_register_netdevice(ndev);
 	else
-		unregister_netdev(ndev);
+		ret = register_netdev(ndev);
+
+	if (ret) {
+		ret = -EFAULT;
+		goto error_remove_vif;
+	}
+
+	return vif;
+
+error_remove_vif:
+	mutex_lock(&wl->vif_mutex);
+	list_del_rcu(&vif->list);
+	wl->vif_num -= 1;
+	mutex_unlock(&wl->vif_mutex);
+	synchronize_rcu();
 	free_netdev(ndev);
 	return ERR_PTR(ret);
 }
-- 
GitLab


From ec99908906e9e322b3d0a34822be44a4659452de Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Alexis=20Lothor=C3=A9?= <alexis.lothore@bootlin.com>
Date: Tue, 14 May 2024 17:51:20 +0200
Subject: [PATCH 065/950] wifi: wilc1000: register net device only after bus
 being fully initialized
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

SDIO/SPI probes functions automatically add a default wlan interface on top
of registered wiphy, through wilc_cfg80211_init which in turn calls
wilc_netdev_ifc_init. However, bus is still not fully initialized when we
register corresponding net device (for example we still miss some private
driver data pointers), which for example makes it impossible to
retrieve MAC address from chip (which is supposed to be set on net device
before its registration) before registering net device. More generally, net
device registration should not be done until driver has fully initialized
everything and is ready to handle any operation  on the net device.

Prevent net device from being registered so early by doing it at the end of
probe functions. Apply this logic to both sdio and spi buses.

Signed-off-by: Alexis Lothoré <alexis.lothore@bootlin.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://msgid.link/20240514-mac_addr_at_probe-v2-2-afef09f1cd10@bootlin.com
---
 drivers/net/wireless/microchip/wilc1000/cfg80211.c | 10 ----------
 drivers/net/wireless/microchip/wilc1000/netdev.c   |  1 +
 drivers/net/wireless/microchip/wilc1000/sdio.c     | 14 ++++++++++++--
 drivers/net/wireless/microchip/wilc1000/spi.c      | 11 +++++++++--
 4 files changed, 22 insertions(+), 14 deletions(-)

diff --git a/drivers/net/wireless/microchip/wilc1000/cfg80211.c b/drivers/net/wireless/microchip/wilc1000/cfg80211.c
index 7d9fb9f2d5279..f716981f62ad4 100644
--- a/drivers/net/wireless/microchip/wilc1000/cfg80211.c
+++ b/drivers/net/wireless/microchip/wilc1000/cfg80211.c
@@ -1773,7 +1773,6 @@ int wilc_cfg80211_init(struct wilc **wilc, struct device *dev, int io_type,
 		       const struct wilc_hif_func *ops)
 {
 	struct wilc *wl;
-	struct wilc_vif *vif;
 	int ret, i;
 
 	wl = wilc_create_wiphy(dev);
@@ -1802,18 +1801,9 @@ int wilc_cfg80211_init(struct wilc **wilc, struct device *dev, int io_type,
 		ret = -ENOMEM;
 		goto free_cfg;
 	}
-	vif = wilc_netdev_ifc_init(wl, "wlan%d", WILC_STATION_MODE,
-				   NL80211_IFTYPE_STATION, false);
-	if (IS_ERR(vif)) {
-		ret = PTR_ERR(vif);
-		goto free_hq;
-	}
 
 	return 0;
 
-free_hq:
-	destroy_workqueue(wl->hif_workqueue);
-
 free_cfg:
 	wilc_wlan_cfg_deinit(wl);
 
diff --git a/drivers/net/wireless/microchip/wilc1000/netdev.c b/drivers/net/wireless/microchip/wilc1000/netdev.c
index acc9b9a645524..166165ee7712e 100644
--- a/drivers/net/wireless/microchip/wilc1000/netdev.c
+++ b/drivers/net/wireless/microchip/wilc1000/netdev.c
@@ -996,6 +996,7 @@ error_remove_vif:
 	free_netdev(ndev);
 	return ERR_PTR(ret);
 }
+EXPORT_SYMBOL_GPL(wilc_netdev_ifc_init);
 
 MODULE_DESCRIPTION("Atmel WILC1000 core wireless driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/wireless/microchip/wilc1000/sdio.c b/drivers/net/wireless/microchip/wilc1000/sdio.c
index 52a770c5e76f3..a841dad084103 100644
--- a/drivers/net/wireless/microchip/wilc1000/sdio.c
+++ b/drivers/net/wireless/microchip/wilc1000/sdio.c
@@ -136,9 +136,11 @@ out:
 static int wilc_sdio_probe(struct sdio_func *func,
 			   const struct sdio_device_id *id)
 {
+	struct wilc_sdio *sdio_priv;
+	struct wilc_vif *vif;
 	struct wilc *wilc;
 	int ret;
-	struct wilc_sdio *sdio_priv;
+
 
 	sdio_priv = kzalloc(sizeof(*sdio_priv), GFP_KERNEL);
 	if (!sdio_priv)
@@ -176,9 +178,17 @@ static int wilc_sdio_probe(struct sdio_func *func,
 	}
 	clk_prepare_enable(wilc->rtc_clk);
 
+	vif = wilc_netdev_ifc_init(wilc, "wlan%d", WILC_STATION_MODE,
+				   NL80211_IFTYPE_STATION, false);
+	if (IS_ERR(vif)) {
+		ret = PTR_ERR(vif);
+		goto clk_disable_unprepare;
+	}
+
 	dev_info(&func->dev, "Driver Initializing success\n");
 	return 0;
-
+clk_disable_unprepare:
+	clk_disable_unprepare(wilc->rtc_clk);
 dispose_irq:
 	irq_dispose_mapping(wilc->dev_irq_num);
 	wilc_netdev_cleanup(wilc);
diff --git a/drivers/net/wireless/microchip/wilc1000/spi.c b/drivers/net/wireless/microchip/wilc1000/spi.c
index 61c3572ce3217..add0e70a09eae 100644
--- a/drivers/net/wireless/microchip/wilc1000/spi.c
+++ b/drivers/net/wireless/microchip/wilc1000/spi.c
@@ -206,9 +206,10 @@ static void wilc_wlan_power(struct wilc *wilc, bool on)
 
 static int wilc_bus_probe(struct spi_device *spi)
 {
-	int ret;
-	struct wilc *wilc;
 	struct wilc_spi *spi_priv;
+	struct wilc_vif *vif;
+	struct wilc *wilc;
+	int ret;
 
 	spi_priv = kzalloc(sizeof(*spi_priv), GFP_KERNEL);
 	if (!spi_priv)
@@ -250,6 +251,12 @@ static int wilc_bus_probe(struct spi_device *spi)
 		goto power_down;
 
 	wilc_wlan_power(wilc, false);
+	vif = wilc_netdev_ifc_init(wilc, "wlan%d", WILC_STATION_MODE,
+				   NL80211_IFTYPE_STATION, false);
+	if (IS_ERR(vif)) {
+		ret = PTR_ERR(vif);
+		goto power_down;
+	}
 	return 0;
 
 power_down:
-- 
GitLab


From 5f1191ed386cf5d21eb82195d252b9ff9549db09 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Alexis=20Lothor=C3=A9?= <alexis.lothore@bootlin.com>
Date: Tue, 14 May 2024 17:51:21 +0200
Subject: [PATCH 066/950] wifi: wilc1000: set wilc_set_mac_address parameter as
 const
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Any attempt to provide a const mac address to wilc_set_mac_address results
in the following warning:

warning: passing argument 2 of 'wilc_set_mac_address' discards 'const'
qualifier from pointer target type [-Wdiscarded-qualifiers]
[...]
drivers/net/wireless/microchip/wilc1000/hif.h:170:52: note: expected 'u8 *'
{aka 'unsigned char *'} but argument is of type 'const unsigned char *'a
int wilc_set_mac_address(struct wilc_vif *vif, u8 *mac_addr);

Instead of using an explicit cast each time we need provide a MAC address,
set the function parameter as const

Signed-off-by: Alexis Lothoré <alexis.lothore@bootlin.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://msgid.link/20240514-mac_addr_at_probe-v2-3-afef09f1cd10@bootlin.com
---
 drivers/net/wireless/microchip/wilc1000/hif.c    | 4 ++--
 drivers/net/wireless/microchip/wilc1000/hif.h    | 2 +-
 drivers/net/wireless/microchip/wilc1000/netdev.c | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/microchip/wilc1000/hif.c b/drivers/net/wireless/microchip/wilc1000/hif.c
index 919de6ffb8217..c6892b7e190fc 100644
--- a/drivers/net/wireless/microchip/wilc1000/hif.c
+++ b/drivers/net/wireless/microchip/wilc1000/hif.c
@@ -1293,7 +1293,7 @@ int wilc_get_mac_address(struct wilc_vif *vif, u8 *mac_addr)
 	return result;
 }
 
-int wilc_set_mac_address(struct wilc_vif *vif, u8 *mac_addr)
+int wilc_set_mac_address(struct wilc_vif *vif, const u8 *mac_addr)
 {
 	struct wid wid;
 	int result;
@@ -1301,7 +1301,7 @@ int wilc_set_mac_address(struct wilc_vif *vif, u8 *mac_addr)
 	wid.id = WID_MAC_ADDR;
 	wid.type = WID_STR;
 	wid.size = ETH_ALEN;
-	wid.val = mac_addr;
+	wid.val = (u8 *)mac_addr;
 
 	result = wilc_send_config_pkt(vif, WILC_SET_CFG, &wid, 1);
 	if (result)
diff --git a/drivers/net/wireless/microchip/wilc1000/hif.h b/drivers/net/wireless/microchip/wilc1000/hif.h
index 0d380586b1d9c..96eeaf31d2377 100644
--- a/drivers/net/wireless/microchip/wilc1000/hif.h
+++ b/drivers/net/wireless/microchip/wilc1000/hif.h
@@ -167,7 +167,7 @@ int wilc_add_rx_gtk(struct wilc_vif *vif, const u8 *rx_gtk, u8 gtk_key_len,
 		    u8 cipher_mode);
 int wilc_set_pmkid_info(struct wilc_vif *vif, struct wilc_pmkid_attr *pmkid);
 int wilc_get_mac_address(struct wilc_vif *vif, u8 *mac_addr);
-int wilc_set_mac_address(struct wilc_vif *vif, u8 *mac_addr);
+int wilc_set_mac_address(struct wilc_vif *vif, const u8 *mac_addr);
 int wilc_set_join_req(struct wilc_vif *vif, u8 *bssid, const u8 *ies,
 		      size_t ies_len);
 int wilc_disconnect(struct wilc_vif *vif);
diff --git a/drivers/net/wireless/microchip/wilc1000/netdev.c b/drivers/net/wireless/microchip/wilc1000/netdev.c
index 166165ee7712e..2ee3d98278266 100644
--- a/drivers/net/wireless/microchip/wilc1000/netdev.c
+++ b/drivers/net/wireless/microchip/wilc1000/netdev.c
@@ -678,7 +678,7 @@ static int wilc_set_mac_addr(struct net_device *dev, void *p)
 	}
 	rcu_read_unlock();
 
-	result = wilc_set_mac_address(vif, (u8 *)addr->sa_data);
+	result = wilc_set_mac_address(vif, addr->sa_data);
 	if (result)
 		return result;
 
-- 
GitLab


From 59cf9277c1fe6f8a72af83bf4a1d9b3f22124750 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Alexis=20Lothor=C3=A9?= <alexis.lothore@bootlin.com>
Date: Tue, 14 May 2024 17:51:22 +0200
Subject: [PATCH 067/950] wifi: wilc1000: add function to read mac address from
 eFuse
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

wilc driver currently reads and sets mac address by firmware calls. It
means that we can not access mac address if no interface has been brought
up (so firmware is up and running). Another way to get mac address is to
read it directly from eFUSE.

Add a function helper to read the mac address written in eFuse, without
firmware assistance

Signed-off-by: Alexis Lothoré <alexis.lothore@bootlin.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://msgid.link/20240514-mac_addr_at_probe-v2-4-afef09f1cd10@bootlin.com
---
 drivers/net/wireless/microchip/wilc1000/fw.h  | 13 +++++
 .../net/wireless/microchip/wilc1000/netdev.h  |  2 +
 .../net/wireless/microchip/wilc1000/wlan.c    | 49 +++++++++++++++++++
 .../net/wireless/microchip/wilc1000/wlan.h    |  1 +
 4 files changed, 65 insertions(+)

diff --git a/drivers/net/wireless/microchip/wilc1000/fw.h b/drivers/net/wireless/microchip/wilc1000/fw.h
index 5c5cac4aab029..7a930e89614ca 100644
--- a/drivers/net/wireless/microchip/wilc1000/fw.h
+++ b/drivers/net/wireless/microchip/wilc1000/fw.h
@@ -13,6 +13,12 @@
 #define WILC_MAX_RATES_SUPPORTED		12
 #define WILC_MAX_NUM_PMKIDS			16
 #define WILC_MAX_NUM_SCANNED_CH			14
+#define WILC_NVMEM_MAX_NUM_BANK			6
+#define WILC_NVMEM_BANK_BASE			0x30000000
+#define WILC_NVMEM_LOW_BANK_OFFSET		0x102c
+#define WILC_NVMEM_HIGH_BANK_OFFSET		0x1380
+#define WILC_NVMEM_IS_BANK_USED			BIT(31)
+#define WILC_NVMEM_IS_BANK_INVALID		BIT(30)
 
 struct wilc_assoc_resp {
 	__le16 capab_info;
@@ -127,4 +133,11 @@ struct wilc_external_auth_param {
 	__le32 key_mgmt_suites;
 	__le16 status;
 } __packed;
+
+static inline u32 get_bank_offset_from_bank_index(unsigned int i)
+{
+	return (((i) < 2) ? WILC_NVMEM_LOW_BANK_OFFSET + ((i) * 32) :
+		WILC_NVMEM_HIGH_BANK_OFFSET + ((i) - 2) * 16);
+}
+
 #endif
diff --git a/drivers/net/wireless/microchip/wilc1000/netdev.h b/drivers/net/wireless/microchip/wilc1000/netdev.h
index eecee3973d6a4..20ba030022a15 100644
--- a/drivers/net/wireless/microchip/wilc1000/netdev.h
+++ b/drivers/net/wireless/microchip/wilc1000/netdev.h
@@ -14,6 +14,7 @@
 #include <linux/if_arp.h>
 #include <linux/gpio/consumer.h>
 #include <linux/rculist.h>
+#include <uapi/linux/if_ether.h>
 
 #include "hif.h"
 #include "wlan.h"
@@ -278,6 +279,7 @@ struct wilc {
 	struct ieee80211_rate bitrates[ARRAY_SIZE(wilc_bitrates)];
 	struct ieee80211_supported_band band;
 	u32 cipher_suites[ARRAY_SIZE(wilc_cipher_suites)];
+	u8 nv_mac_address[ETH_ALEN];
 };
 
 struct wilc_wfi_mon_priv {
diff --git a/drivers/net/wireless/microchip/wilc1000/wlan.c b/drivers/net/wireless/microchip/wilc1000/wlan.c
index 37c32d17856ea..b3fee8c8b7ad4 100644
--- a/drivers/net/wireless/microchip/wilc1000/wlan.c
+++ b/drivers/net/wireless/microchip/wilc1000/wlan.c
@@ -1472,6 +1472,55 @@ u32 wilc_get_chipid(struct wilc *wilc, bool update)
 	return wilc->chipid;
 }
 
+int wilc_load_mac_from_nv(struct wilc *wl)
+{
+	int ret = -EINVAL;
+	unsigned int i;
+
+	acquire_bus(wl, WILC_BUS_ACQUIRE_AND_WAKEUP);
+
+	for (i = 0; i < WILC_NVMEM_MAX_NUM_BANK; i++) {
+		int bank_offset = get_bank_offset_from_bank_index(i);
+		u32 reg1, reg2;
+		u8 invalid;
+		u8 used;
+
+		ret = wl->hif_func->hif_read_reg(wl,
+						 WILC_NVMEM_BANK_BASE + bank_offset,
+						 &reg1);
+		if (ret) {
+			pr_err("Can not read address %d lower part", i);
+			break;
+		}
+		ret = wl->hif_func->hif_read_reg(wl,
+						 WILC_NVMEM_BANK_BASE + bank_offset + 4,
+						 &reg2);
+		if (ret) {
+			pr_err("Can not read address %d upper part", i);
+			break;
+		}
+
+		used = FIELD_GET(WILC_NVMEM_IS_BANK_USED, reg1);
+		invalid = FIELD_GET(WILC_NVMEM_IS_BANK_INVALID, reg1);
+		if (!used || invalid)
+			continue;
+
+		wl->nv_mac_address[0] = FIELD_GET(GENMASK(23, 16), reg1);
+		wl->nv_mac_address[1] = FIELD_GET(GENMASK(15, 8), reg1);
+		wl->nv_mac_address[2] = FIELD_GET(GENMASK(7, 0), reg1);
+		wl->nv_mac_address[3] = FIELD_GET(GENMASK(31, 24), reg2);
+		wl->nv_mac_address[4] = FIELD_GET(GENMASK(23, 16), reg2);
+		wl->nv_mac_address[5] = FIELD_GET(GENMASK(15, 8), reg2);
+
+		ret = 0;
+		break;
+	}
+
+	release_bus(wl, WILC_BUS_RELEASE_ALLOW_SLEEP);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(wilc_load_mac_from_nv);
+
 int wilc_wlan_init(struct net_device *dev)
 {
 	int ret = 0;
diff --git a/drivers/net/wireless/microchip/wilc1000/wlan.h b/drivers/net/wireless/microchip/wilc1000/wlan.h
index 54643d8fef04e..d72a0a81bbda2 100644
--- a/drivers/net/wireless/microchip/wilc1000/wlan.h
+++ b/drivers/net/wireless/microchip/wilc1000/wlan.h
@@ -445,4 +445,5 @@ int wilc_send_config_pkt(struct wilc_vif *vif, u8 mode, struct wid *wids,
 			 u32 count);
 int wilc_wlan_init(struct net_device *dev);
 u32 wilc_get_chipid(struct wilc *wilc, bool update);
+int wilc_load_mac_from_nv(struct wilc *wilc);
 #endif
-- 
GitLab


From a5d6b1d453a149e70452d5e69320db04afb520e2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Alexis=20Lothor=C3=A9?= <alexis.lothore@bootlin.com>
Date: Tue, 14 May 2024 17:51:23 +0200
Subject: [PATCH 068/950] wifi: wilc1000: make sdio deinit function really
 deinit the sdio card
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In order to be able to read raw registers (eg the nv mac address) in
wilc1000 during probe before the firmware is loaded and running, we need to
run the basic sdio functions initialization, but then we also need to
properly deinitialize those right after, to preserve the current driver
behavior (keeping the chip idle/unconfigured until the corresponding
interface is brought up). Calling wilc_sdio_deinit in its current form is
not enough because it merely resets an internal flag.

Implement a deinit sequence which symmetrically reset all steps performed
in wilc_sdio_init (only for parts activating/deactivating features, for the
sake of simplicity, let's ignore blocks size configuration reset)

Signed-off-by: Alexis Lothoré <alexis.lothore@bootlin.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://msgid.link/20240514-mac_addr_at_probe-v2-5-afef09f1cd10@bootlin.com
---
 .../net/wireless/microchip/wilc1000/sdio.c    | 45 +++++++++++++++++++
 1 file changed, 45 insertions(+)

diff --git a/drivers/net/wireless/microchip/wilc1000/sdio.c b/drivers/net/wireless/microchip/wilc1000/sdio.c
index a841dad084103..04d6565df2cb3 100644
--- a/drivers/net/wireless/microchip/wilc1000/sdio.c
+++ b/drivers/net/wireless/microchip/wilc1000/sdio.c
@@ -627,7 +627,52 @@ static int wilc_sdio_read(struct wilc *wilc, u32 addr, u8 *buf, u32 size)
 
 static int wilc_sdio_deinit(struct wilc *wilc)
 {
+	struct sdio_func *func = dev_to_sdio_func(wilc->dev);
 	struct wilc_sdio *sdio_priv = wilc->bus_data;
+	struct sdio_cmd52 cmd;
+	int ret;
+
+	cmd.read_write = 1;
+	cmd.function = 0;
+	cmd.raw = 1;
+
+	/* Disable all functions interrupts */
+	cmd.address = SDIO_CCCR_IENx;
+	cmd.data = 0;
+	ret = wilc_sdio_cmd52(wilc, &cmd);
+	if (ret) {
+		dev_err(&func->dev, "Failed to disable functions interrupts\n");
+		return ret;
+	}
+
+	/* Disable all functions */
+	cmd.address = SDIO_CCCR_IOEx;
+	cmd.data = 0;
+	ret = wilc_sdio_cmd52(wilc, &cmd);
+	if (ret) {
+		dev_err(&func->dev,
+			"Failed to reset all functions\n");
+		return ret;
+	}
+
+	/* Disable CSA */
+	cmd.read_write = 0;
+	cmd.address = SDIO_FBR_BASE(1);
+	ret = wilc_sdio_cmd52(wilc, &cmd);
+	if (ret) {
+		dev_err(&func->dev,
+			"Failed to read CSA for function 1\n");
+		return ret;
+	}
+	cmd.read_write = 1;
+	cmd.address = SDIO_FBR_BASE(1);
+	cmd.data &= ~SDIO_FBR_ENABLE_CSA;
+	ret = wilc_sdio_cmd52(wilc, &cmd);
+	if (ret) {
+		dev_err(&func->dev,
+			"Failed to disable CSA for function 1\n");
+		return ret;
+	}
 
 	sdio_priv->isinit = false;
 	return 0;
-- 
GitLab


From 83d9b54ee5d4c12d00f2cbf71d827e31994c5a6c Mon Sep 17 00:00:00 2001
From: Ajay Singh <ajay.kathat@microchip.com>
Date: Tue, 14 May 2024 17:51:24 +0200
Subject: [PATCH 069/950] wifi: wilc1000: read MAC address from fuse at probe
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The default netdev interface exposed by WILC1000 is registered at probe,
but the chip mac address is not known until ndo_open, which will load and
start chip firmware and then retrieve stored MAC address from it. As a
consequence, the interface has uninitialized value (00:00:00:00:00) until a
user brings up the interface.

Fix MAC address at probe by setting the following steps:
- at probe, read MAC address directly from fuse
- whenever a new netdevice is created, apply saved mac address (which can
  be a user-provided address, or the eFuse Mac address if no address has
  been passed by user)
- whenever an interface is brought up for the first time (and so the
  firmware is loaded and started), enforce netdevice mac address to the
  chip (in case user has changed it)

Reported-by: Heiko Thiery <heiko.thiery@gmail.com>
Closes: https://lore.kernel.org/netdev/CAEyMn7aV-B4OEhHR4Ad0LM3sKCz1-nDqSb9uZNmRWR-hMZ=z+A@mail.gmail.com/T/
Signed-off-by: Ajay Singh <ajay.kathat@microchip.com>
Co-developed-by: Alexis Lothoré <alexis.lothore@bootlin.com>
Signed-off-by: Alexis Lothoré <alexis.lothore@bootlin.com>
Tested-by: Heiko Thiery <heiko.thiery@gmail.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://msgid.link/20240514-mac_addr_at_probe-v2-6-afef09f1cd10@bootlin.com
---
 .../net/wireless/microchip/wilc1000/netdev.c  | 38 +++++++++++--------
 .../net/wireless/microchip/wilc1000/sdio.c    | 14 +++++++
 drivers/net/wireless/microchip/wilc1000/spi.c |  6 +++
 3 files changed, 42 insertions(+), 16 deletions(-)

diff --git a/drivers/net/wireless/microchip/wilc1000/netdev.c b/drivers/net/wireless/microchip/wilc1000/netdev.c
index 2ee3d98278266..4e2698528a49a 100644
--- a/drivers/net/wireless/microchip/wilc1000/netdev.c
+++ b/drivers/net/wireless/microchip/wilc1000/netdev.c
@@ -588,7 +588,6 @@ static int wilc_mac_open(struct net_device *ndev)
 	struct wilc *wl = vif->wilc;
 	int ret = 0;
 	struct mgmt_frame_regs mgmt_regs = {};
-	u8 addr[ETH_ALEN] __aligned(2);
 
 	if (!wl || !wl->dev) {
 		netdev_err(ndev, "device not ready\n");
@@ -607,25 +606,19 @@ static int wilc_mac_open(struct net_device *ndev)
 		return ret;
 	}
 
-	wilc_set_operation_mode(vif, wilc_get_vif_idx(vif), vif->iftype,
-				vif->idx);
-
-	if (is_valid_ether_addr(ndev->dev_addr)) {
-		ether_addr_copy(addr, ndev->dev_addr);
-		wilc_set_mac_address(vif, addr);
-	} else {
-		wilc_get_mac_address(vif, addr);
-		eth_hw_addr_set(ndev, addr);
-	}
 	netdev_dbg(ndev, "Mac address: %pM\n", ndev->dev_addr);
-
-	if (!is_valid_ether_addr(ndev->dev_addr)) {
-		netdev_err(ndev, "Wrong MAC address\n");
+	ret = wilc_set_mac_address(vif, ndev->dev_addr);
+	if (ret) {
+		netdev_err(ndev, "Failed to enforce MAC address in chip");
 		wilc_deinit_host_int(ndev);
-		wilc_wlan_deinitialize(ndev);
-		return -EINVAL;
+		if (!wl->open_ifcs)
+			wilc_wlan_deinitialize(ndev);
+		return ret;
 	}
 
+	wilc_set_operation_mode(vif, wilc_get_vif_idx(vif), vif->iftype,
+				vif->idx);
+
 	mgmt_regs.interface_stypes = vif->mgmt_reg_stypes;
 	/* so we detect a change */
 	vif->mgmt_reg_stypes = 0;
@@ -941,6 +934,7 @@ struct wilc_vif *wilc_netdev_ifc_init(struct wilc *wl, const char *name,
 				      int vif_type, enum nl80211_iftype type,
 				      bool rtnl_locked)
 {
+	u8 mac_address[ETH_ALEN];
 	struct net_device *ndev;
 	struct wilc_vif *vif;
 	int ret;
@@ -969,6 +963,18 @@ struct wilc_vif *wilc_netdev_ifc_init(struct wilc *wl, const char *name,
 	vif->iftype = vif_type;
 	vif->idx = wilc_get_available_idx(wl);
 	vif->mac_opened = 0;
+
+	memcpy(mac_address, wl->nv_mac_address, ETH_ALEN);
+	/* WILC firmware uses locally administered MAC address for the
+	 * second virtual interface (bit 1 of first byte set), but
+	 * since it is possibly not loaded/running yet, reproduce this behavior
+	 * in the driver during interface creation.
+	 */
+	if (vif->idx)
+		mac_address[0] |= 0x2;
+
+	eth_hw_addr_set(vif->ndev, mac_address);
+
 	mutex_lock(&wl->vif_mutex);
 	list_add_tail_rcu(&vif->list, &wl->vif_list);
 	wl->vif_num += 1;
diff --git a/drivers/net/wireless/microchip/wilc1000/sdio.c b/drivers/net/wireless/microchip/wilc1000/sdio.c
index 04d6565df2cb3..e6e20c86b7917 100644
--- a/drivers/net/wireless/microchip/wilc1000/sdio.c
+++ b/drivers/net/wireless/microchip/wilc1000/sdio.c
@@ -24,6 +24,9 @@ MODULE_DEVICE_TABLE(sdio, wilc_sdio_ids);
 
 #define WILC_SDIO_BLOCK_SIZE 512
 
+static int wilc_sdio_init(struct wilc *wilc, bool resume);
+static int wilc_sdio_deinit(struct wilc *wilc);
+
 struct wilc_sdio {
 	bool irq_gpio;
 	u32 block_size;
@@ -178,6 +181,16 @@ static int wilc_sdio_probe(struct sdio_func *func,
 	}
 	clk_prepare_enable(wilc->rtc_clk);
 
+	wilc_sdio_init(wilc, false);
+
+	ret = wilc_load_mac_from_nv(wilc);
+	if (ret) {
+		pr_err("Can not retrieve MAC address from chip\n");
+		goto clk_disable_unprepare;
+	}
+
+	wilc_sdio_deinit(wilc);
+
 	vif = wilc_netdev_ifc_init(wilc, "wlan%d", WILC_STATION_MODE,
 				   NL80211_IFTYPE_STATION, false);
 	if (IS_ERR(vif)) {
@@ -187,6 +200,7 @@ static int wilc_sdio_probe(struct sdio_func *func,
 
 	dev_info(&func->dev, "Driver Initializing success\n");
 	return 0;
+
 clk_disable_unprepare:
 	clk_disable_unprepare(wilc->rtc_clk);
 dispose_irq:
diff --git a/drivers/net/wireless/microchip/wilc1000/spi.c b/drivers/net/wireless/microchip/wilc1000/spi.c
index add0e70a09eae..5ff940c53ad9c 100644
--- a/drivers/net/wireless/microchip/wilc1000/spi.c
+++ b/drivers/net/wireless/microchip/wilc1000/spi.c
@@ -250,6 +250,12 @@ static int wilc_bus_probe(struct spi_device *spi)
 	if (ret)
 		goto power_down;
 
+	ret = wilc_load_mac_from_nv(wilc);
+	if (ret) {
+		pr_err("Can not retrieve MAC address from chip\n");
+		goto power_down;
+	}
+
 	wilc_wlan_power(wilc, false);
 	vif = wilc_netdev_ifc_init(wilc, "wlan%d", WILC_STATION_MODE,
 				   NL80211_IFTYPE_STATION, false);
-- 
GitLab


From a17b9f590f6ec2b9f1b12b1db3bf1d181de6b272 Mon Sep 17 00:00:00 2001
From: Rafael Beims <rafael.beims@toradex.com>
Date: Fri, 10 May 2024 13:04:58 +0200
Subject: [PATCH 070/950] wifi: mwifiex: Fix interface type change

When changing the interface type we also need to update the bss_num, the
driver private data is searched based on a unique (bss_type, bss_num)
tuple, therefore every time bss_type changes, bss_num must also change.

This fixes for example an issue in which, after the mode changed, a
wireless scan on the changed interface would not finish, leading to
repeated -EBUSY messages to userspace when other scan requests were
sent.

Fixes: c606008b7062 ("mwifiex: Properly initialize private structure on interface type changes")
Cc: stable@vger.kernel.org
Signed-off-by: Rafael Beims <rafael.beims@toradex.com>
Signed-off-by: Francesco Dolcini <francesco.dolcini@toradex.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://msgid.link/20240510110458.15475-1-francesco@dolcini.it
---
 drivers/net/wireless/marvell/mwifiex/cfg80211.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/wireless/marvell/mwifiex/cfg80211.c b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
index b909a7665e9cc..155eb0fab12a4 100644
--- a/drivers/net/wireless/marvell/mwifiex/cfg80211.c
+++ b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
@@ -926,6 +926,8 @@ mwifiex_init_new_priv_params(struct mwifiex_private *priv,
 		return -EOPNOTSUPP;
 	}
 
+	priv->bss_num = mwifiex_get_unused_bss_num(adapter, priv->bss_type);
+
 	spin_lock_irqsave(&adapter->main_proc_lock, flags);
 	adapter->main_locked = false;
 	spin_unlock_irqrestore(&adapter->main_proc_lock, flags);
-- 
GitLab


From 117bbc0e43adc6f76a3fc39a98f75a811a853459 Mon Sep 17 00:00:00 2001
From: Matthew Auld <matthew.auld@intel.com>
Date: Thu, 29 Feb 2024 10:51:13 +0000
Subject: [PATCH 071/950] drm/buddy: stop using PAGE_SIZE
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The drm_buddy minimum page-size requirements should be distinct from the
CPU PAGE_SIZE. Only restriction is that the minimum page-size is at
least 4K.

Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Arunpravin Paneer Selvam <Arunpravin.PaneerSelvam@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Arunpravin Paneer Selvam <Arunpravin.PaneerSelvam@amd.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Link: https://patchwork.freedesktop.org/patch/msgid/20240229105112.250077-3-matthew.auld@intel.com
Signed-off-by: Christian König <christian.koenig@amd.com>
---
 drivers/gpu/drm/drm_buddy.c | 2 +-
 include/drm/drm_buddy.h     | 6 +++---
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/drm_buddy.c b/drivers/gpu/drm/drm_buddy.c
index 5ebdd6f8f36e6..f999568d69c10 100644
--- a/drivers/gpu/drm/drm_buddy.c
+++ b/drivers/gpu/drm/drm_buddy.c
@@ -102,7 +102,7 @@ int drm_buddy_init(struct drm_buddy *mm, u64 size, u64 chunk_size)
 	if (size < chunk_size)
 		return -EINVAL;
 
-	if (chunk_size < PAGE_SIZE)
+	if (chunk_size < SZ_4K)
 		return -EINVAL;
 
 	if (!is_power_of_2(chunk_size))
diff --git a/include/drm/drm_buddy.h b/include/drm/drm_buddy.h
index a5b39fc01003a..19ed661a32f3b 100644
--- a/include/drm/drm_buddy.h
+++ b/include/drm/drm_buddy.h
@@ -53,8 +53,8 @@ struct drm_buddy_block {
 	struct list_head tmp_link;
 };
 
-/* Order-zero must be at least PAGE_SIZE */
-#define DRM_BUDDY_MAX_ORDER (63 - PAGE_SHIFT)
+/* Order-zero must be at least SZ_4K */
+#define DRM_BUDDY_MAX_ORDER (63 - 12)
 
 /*
  * Binary Buddy System.
@@ -82,7 +82,7 @@ struct drm_buddy {
 	unsigned int n_roots;
 	unsigned int max_order;
 
-	/* Must be at least PAGE_SIZE */
+	/* Must be at least SZ_4K */
 	u64 chunk_size;
 	u64 size;
 	u64 avail;
-- 
GitLab


From 520fb7f183e9b4d0ad7a2f084f3c4987845425e2 Mon Sep 17 00:00:00 2001
From: Matthew Auld <matthew.auld@intel.com>
Date: Thu, 29 Feb 2024 10:51:14 +0000
Subject: [PATCH 072/950] drm/tests/buddy: stop using PAGE_SIZE
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Gives the wrong impression that min page-size has to be tied to the CPU
PAGE_SIZE.

Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Arunpravin Paneer Selvam <Arunpravin.PaneerSelvam@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Arunpravin Paneer Selvam <Arunpravin.PaneerSelvam@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240229105112.250077-4-matthew.auld@intel.com
Signed-off-by: Christian König <christian.koenig@amd.com>
---
 drivers/gpu/drm/tests/drm_buddy_test.c | 42 +++++++++++++-------------
 1 file changed, 21 insertions(+), 21 deletions(-)

diff --git a/drivers/gpu/drm/tests/drm_buddy_test.c b/drivers/gpu/drm/tests/drm_buddy_test.c
index e48863a445564..f2397696d2526 100644
--- a/drivers/gpu/drm/tests/drm_buddy_test.c
+++ b/drivers/gpu/drm/tests/drm_buddy_test.c
@@ -329,8 +329,8 @@ static void drm_test_buddy_alloc_pathological(struct kunit *test)
 	 * Eventually we will have a fully 50% fragmented mm.
 	 */
 
-	mm_size = PAGE_SIZE << max_order;
-	KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_init(&mm, mm_size, PAGE_SIZE),
+	mm_size = SZ_4K << max_order;
+	KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_init(&mm, mm_size, SZ_4K),
 			       "buddy_init failed\n");
 
 	KUNIT_EXPECT_EQ(test, mm.max_order, max_order);
@@ -344,7 +344,7 @@ static void drm_test_buddy_alloc_pathological(struct kunit *test)
 		}
 
 		for (order = top; order--;) {
-			size = get_size(order, PAGE_SIZE);
+			size = get_size(order, mm.chunk_size);
 			KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, start,
 									    mm_size, size, size,
 										&tmp, flags),
@@ -358,7 +358,7 @@ static void drm_test_buddy_alloc_pathological(struct kunit *test)
 		}
 
 		/* There should be one final page for this sub-allocation */
-		size = get_size(0, PAGE_SIZE);
+		size = get_size(0, mm.chunk_size);
 		KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, start, mm_size,
 								    size, size, &tmp, flags),
 							   "buddy_alloc hit -ENOMEM for hole\n");
@@ -368,7 +368,7 @@ static void drm_test_buddy_alloc_pathological(struct kunit *test)
 
 		list_move_tail(&block->link, &holes);
 
-		size = get_size(top, PAGE_SIZE);
+		size = get_size(top, mm.chunk_size);
 		KUNIT_ASSERT_TRUE_MSG(test, drm_buddy_alloc_blocks(&mm, start, mm_size,
 								   size, size, &tmp, flags),
 							  "buddy_alloc unexpectedly succeeded at top-order %d/%d, it should be full!",
@@ -379,7 +379,7 @@ static void drm_test_buddy_alloc_pathological(struct kunit *test)
 
 	/* Nothing larger than blocks of chunk_size now available */
 	for (order = 1; order <= max_order; order++) {
-		size = get_size(order, PAGE_SIZE);
+		size = get_size(order, mm.chunk_size);
 		KUNIT_ASSERT_TRUE_MSG(test, drm_buddy_alloc_blocks(&mm, start, mm_size,
 								   size, size, &tmp, flags),
 							  "buddy_alloc unexpectedly succeeded at order %d, it should be full!",
@@ -408,14 +408,14 @@ static void drm_test_buddy_alloc_pessimistic(struct kunit *test)
 	 * page left.
 	 */
 
-	mm_size = PAGE_SIZE << max_order;
-	KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_init(&mm, mm_size, PAGE_SIZE),
+	mm_size = SZ_4K << max_order;
+	KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_init(&mm, mm_size, SZ_4K),
 			       "buddy_init failed\n");
 
 	KUNIT_EXPECT_EQ(test, mm.max_order, max_order);
 
 	for (order = 0; order < max_order; order++) {
-		size = get_size(order, PAGE_SIZE);
+		size = get_size(order, mm.chunk_size);
 		KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, start, mm_size,
 								    size, size, &tmp, flags),
 							   "buddy_alloc hit -ENOMEM with order=%d\n",
@@ -428,7 +428,7 @@ static void drm_test_buddy_alloc_pessimistic(struct kunit *test)
 	}
 
 	/* And now the last remaining block available */
-	size = get_size(0, PAGE_SIZE);
+	size = get_size(0, mm.chunk_size);
 	KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, start, mm_size,
 							    size, size, &tmp, flags),
 						   "buddy_alloc hit -ENOMEM on final alloc\n");
@@ -440,7 +440,7 @@ static void drm_test_buddy_alloc_pessimistic(struct kunit *test)
 
 	/* Should be completely full! */
 	for (order = max_order; order--;) {
-		size = get_size(order, PAGE_SIZE);
+		size = get_size(order, mm.chunk_size);
 		KUNIT_ASSERT_TRUE_MSG(test, drm_buddy_alloc_blocks(&mm, start, mm_size,
 								   size, size, &tmp, flags),
 							  "buddy_alloc unexpectedly succeeded, it should be full!");
@@ -456,7 +456,7 @@ static void drm_test_buddy_alloc_pessimistic(struct kunit *test)
 		list_del(&block->link);
 		drm_buddy_free_block(&mm, block);
 
-		size = get_size(order, PAGE_SIZE);
+		size = get_size(order, mm.chunk_size);
 		KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, start, mm_size,
 								    size, size, &tmp, flags),
 							   "buddy_alloc hit -ENOMEM with order=%d\n",
@@ -471,7 +471,7 @@ static void drm_test_buddy_alloc_pessimistic(struct kunit *test)
 	}
 
 	/* To confirm, now the whole mm should be available */
-	size = get_size(max_order, PAGE_SIZE);
+	size = get_size(max_order, mm.chunk_size);
 	KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, start, mm_size,
 							    size, size, &tmp, flags),
 						   "buddy_alloc (realloc) hit -ENOMEM with order=%d\n",
@@ -502,15 +502,15 @@ static void drm_test_buddy_alloc_optimistic(struct kunit *test)
 	 * try to allocate them all.
 	 */
 
-	mm_size = PAGE_SIZE * ((1 << (max_order + 1)) - 1);
+	mm_size = SZ_4K * ((1 << (max_order + 1)) - 1);
 
-	KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_init(&mm, mm_size, PAGE_SIZE),
+	KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_init(&mm, mm_size, SZ_4K),
 			       "buddy_init failed\n");
 
 	KUNIT_EXPECT_EQ(test, mm.max_order, max_order);
 
 	for (order = 0; order <= max_order; order++) {
-		size = get_size(order, PAGE_SIZE);
+		size = get_size(order, mm.chunk_size);
 		KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, start, mm_size,
 								    size, size, &tmp, flags),
 							   "buddy_alloc hit -ENOMEM with order=%d\n",
@@ -523,7 +523,7 @@ static void drm_test_buddy_alloc_optimistic(struct kunit *test)
 	}
 
 	/* Should be completely full! */
-	size = get_size(0, PAGE_SIZE);
+	size = get_size(0, mm.chunk_size);
 	KUNIT_ASSERT_TRUE_MSG(test, drm_buddy_alloc_blocks(&mm, start, mm_size,
 							   size, size, &tmp, flags),
 						  "buddy_alloc unexpectedly succeeded, it should be full!");
@@ -540,7 +540,7 @@ static void drm_test_buddy_alloc_limit(struct kunit *test)
 	LIST_HEAD(allocated);
 	struct drm_buddy mm;
 
-	KUNIT_EXPECT_FALSE(test, drm_buddy_init(&mm, size, PAGE_SIZE));
+	KUNIT_EXPECT_FALSE(test, drm_buddy_init(&mm, size, SZ_4K));
 
 	KUNIT_EXPECT_EQ_MSG(test, mm.max_order, DRM_BUDDY_MAX_ORDER,
 			    "mm.max_order(%d) != %d\n", mm.max_order,
@@ -548,7 +548,7 @@ static void drm_test_buddy_alloc_limit(struct kunit *test)
 
 	size = mm.chunk_size << mm.max_order;
 	KUNIT_EXPECT_FALSE(test, drm_buddy_alloc_blocks(&mm, start, size, size,
-							PAGE_SIZE, &allocated, flags));
+							mm.chunk_size, &allocated, flags));
 
 	block = list_first_entry_or_null(&allocated, struct drm_buddy_block, link);
 	KUNIT_EXPECT_TRUE(test, block);
@@ -558,10 +558,10 @@ static void drm_test_buddy_alloc_limit(struct kunit *test)
 						drm_buddy_block_order(block), mm.max_order);
 
 	KUNIT_EXPECT_EQ_MSG(test, drm_buddy_block_size(&mm, block),
-			    BIT_ULL(mm.max_order) * PAGE_SIZE,
+			    BIT_ULL(mm.max_order) * mm.chunk_size,
 						"block size(%llu) != %llu\n",
 						drm_buddy_block_size(&mm, block),
-						BIT_ULL(mm.max_order) * PAGE_SIZE);
+						BIT_ULL(mm.max_order) * mm.chunk_size);
 
 	drm_buddy_free_list(&mm, &allocated);
 	drm_buddy_fini(&mm);
-- 
GitLab


From 94133cf24bb33889aac267a7f0e3e6a08b8a8e5a Mon Sep 17 00:00:00 2001
From: Mykyta Yatsenko <yatsenko@meta.com>
Date: Tue, 14 May 2024 14:12:21 +0100
Subject: [PATCH 073/950] bpftool: Introduce btf c dump sorting

Sort bpftool c dump output; aiming to simplify vmlinux.h diffing and
forcing more natural type definitions ordering.

Definitions are sorted first by their BTF kind ranks, then by their base
type name and by their own name.

Type ranks

Assign ranks to btf kinds (defined in function btf_type_rank) to set
next order:
1. Anonymous enums/enums64
2. Named enums/enums64
3. Trivial types typedefs (ints, then floats)
4. Structs/Unions
5. Function prototypes
6. Forward declarations

Type rank is set to maximum for unnamed reference types, structs and
unions to avoid emitting those types early. They will be emitted as
part of the type chain starting with named type.

Lexicographical ordering

Each type is assigned a sort_name and own_name.
sort_name is the resolved name of the final base type for reference
types (typedef, pointer, array etc). Sorting by sort_name allows to
group typedefs of the same base type. sort_name for non-reference type
is the same as own_name. own_name is a direct name of particular type,
is used as final sorting step.

Signed-off-by: Mykyta Yatsenko <yatsenko@meta.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Tested-by: Andrii Nakryiko <andrii@kernel.org>
Reviewed-by: Quentin Monnet <qmo@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20240514131221.20585-1-yatsenko@meta.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../bpf/bpftool/Documentation/bpftool-btf.rst |   6 +-
 tools/bpf/bpftool/bash-completion/bpftool     |   3 +
 tools/bpf/bpftool/btf.c                       | 138 +++++++++++++++++-
 3 files changed, 140 insertions(+), 7 deletions(-)

diff --git a/tools/bpf/bpftool/Documentation/bpftool-btf.rst b/tools/bpf/bpftool/Documentation/bpftool-btf.rst
index eaba24320fb26..3f6bca03ad2e6 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-btf.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-btf.rst
@@ -28,7 +28,7 @@ BTF COMMANDS
 | **bpftool** **btf help**
 |
 | *BTF_SRC* := { **id** *BTF_ID* | **prog** *PROG* | **map** *MAP* [{**key** | **value** | **kv** | **all**}] | **file** *FILE* }
-| *FORMAT* := { **raw** | **c** }
+| *FORMAT* := { **raw** | **c** [**unsorted**] }
 | *MAP* := { **id** *MAP_ID* | **pinned** *FILE* }
 | *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* | **name** *PROG_NAME* }
 
@@ -63,7 +63,9 @@ bpftool btf dump *BTF_SRC*
     pahole.
 
     **format** option can be used to override default (raw) output format. Raw
-    (**raw**) or C-syntax (**c**) output formats are supported.
+    (**raw**) or C-syntax (**c**) output formats are supported. With C-style
+    formatting, the output is sorted by default. Use the **unsorted** option
+    to avoid sorting the output.
 
 bpftool btf help
     Print short help message.
diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool
index 04afe2ac22282..be99d49b87144 100644
--- a/tools/bpf/bpftool/bash-completion/bpftool
+++ b/tools/bpf/bpftool/bash-completion/bpftool
@@ -930,6 +930,9 @@ _bpftool()
                         format)
                             COMPREPLY=( $( compgen -W "c raw" -- "$cur" ) )
                             ;;
+                        c)
+                            COMPREPLY=( $( compgen -W "unsorted" -- "$cur" ) )
+                            ;;
                         *)
                             # emit extra options
                             case ${words[3]} in
diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c
index 91fcb75babe33..af047dedde389 100644
--- a/tools/bpf/bpftool/btf.c
+++ b/tools/bpf/bpftool/btf.c
@@ -43,6 +43,13 @@ static const char * const btf_kind_str[NR_BTF_KINDS] = {
 	[BTF_KIND_ENUM64]	= "ENUM64",
 };
 
+struct sort_datum {
+	int index;
+	int type_rank;
+	const char *sort_name;
+	const char *own_name;
+};
+
 static const char *btf_int_enc_str(__u8 encoding)
 {
 	switch (encoding) {
@@ -460,9 +467,122 @@ static void __printf(2, 0) btf_dump_printf(void *ctx,
 	vfprintf(stdout, fmt, args);
 }
 
+static int btf_type_rank(const struct btf *btf, __u32 index, bool has_name)
+{
+	const struct btf_type *t = btf__type_by_id(btf, index);
+	const int kind = btf_kind(t);
+	const int max_rank = 10;
+
+	if (t->name_off)
+		has_name = true;
+
+	switch (kind) {
+	case BTF_KIND_ENUM:
+	case BTF_KIND_ENUM64:
+		return has_name ? 1 : 0;
+	case BTF_KIND_INT:
+	case BTF_KIND_FLOAT:
+		return 2;
+	case BTF_KIND_STRUCT:
+	case BTF_KIND_UNION:
+		return has_name ? 3 : max_rank;
+	case BTF_KIND_FUNC_PROTO:
+		return has_name ? 4 : max_rank;
+	case BTF_KIND_ARRAY:
+		if (has_name)
+			return btf_type_rank(btf, btf_array(t)->type, has_name);
+		return max_rank;
+	case BTF_KIND_TYPE_TAG:
+	case BTF_KIND_CONST:
+	case BTF_KIND_PTR:
+	case BTF_KIND_VOLATILE:
+	case BTF_KIND_RESTRICT:
+	case BTF_KIND_TYPEDEF:
+	case BTF_KIND_DECL_TAG:
+		if (has_name)
+			return btf_type_rank(btf, t->type, has_name);
+		return max_rank;
+	default:
+		return max_rank;
+	}
+}
+
+static const char *btf_type_sort_name(const struct btf *btf, __u32 index, bool from_ref)
+{
+	const struct btf_type *t = btf__type_by_id(btf, index);
+
+	switch (btf_kind(t)) {
+	case BTF_KIND_ENUM:
+	case BTF_KIND_ENUM64: {
+		int name_off = t->name_off;
+
+		/* Use name of the first element for anonymous enums if allowed */
+		if (!from_ref && !t->name_off && btf_vlen(t))
+			name_off = btf_enum(t)->name_off;
+
+		return btf__name_by_offset(btf, name_off);
+	}
+	case BTF_KIND_ARRAY:
+		return btf_type_sort_name(btf, btf_array(t)->type, true);
+	case BTF_KIND_TYPE_TAG:
+	case BTF_KIND_CONST:
+	case BTF_KIND_PTR:
+	case BTF_KIND_VOLATILE:
+	case BTF_KIND_RESTRICT:
+	case BTF_KIND_TYPEDEF:
+	case BTF_KIND_DECL_TAG:
+		return btf_type_sort_name(btf, t->type, true);
+	default:
+		return btf__name_by_offset(btf, t->name_off);
+	}
+	return NULL;
+}
+
+static int btf_type_compare(const void *left, const void *right)
+{
+	const struct sort_datum *d1 = (const struct sort_datum *)left;
+	const struct sort_datum *d2 = (const struct sort_datum *)right;
+	int r;
+
+	if (d1->type_rank != d2->type_rank)
+		return d1->type_rank < d2->type_rank ? -1 : 1;
+
+	r = strcmp(d1->sort_name, d2->sort_name);
+	if (r)
+		return r;
+
+	return strcmp(d1->own_name, d2->own_name);
+}
+
+static struct sort_datum *sort_btf_c(const struct btf *btf)
+{
+	struct sort_datum *datums;
+	int n;
+
+	n = btf__type_cnt(btf);
+	datums = malloc(sizeof(struct sort_datum) * n);
+	if (!datums)
+		return NULL;
+
+	for (int i = 0; i < n; ++i) {
+		struct sort_datum *d = datums + i;
+		const struct btf_type *t = btf__type_by_id(btf, i);
+
+		d->index = i;
+		d->type_rank = btf_type_rank(btf, i, false);
+		d->sort_name = btf_type_sort_name(btf, i, false);
+		d->own_name = btf__name_by_offset(btf, t->name_off);
+	}
+
+	qsort(datums, n, sizeof(struct sort_datum), btf_type_compare);
+
+	return datums;
+}
+
 static int dump_btf_c(const struct btf *btf,
-		      __u32 *root_type_ids, int root_type_cnt)
+		      __u32 *root_type_ids, int root_type_cnt, bool sort_dump)
 {
+	struct sort_datum *datums = NULL;
 	struct btf_dump *d;
 	int err = 0, i;
 
@@ -486,8 +606,12 @@ static int dump_btf_c(const struct btf *btf,
 	} else {
 		int cnt = btf__type_cnt(btf);
 
+		if (sort_dump)
+			datums = sort_btf_c(btf);
 		for (i = 1; i < cnt; i++) {
-			err = btf_dump__dump_type(d, i);
+			int idx = datums ? datums[i].index : i;
+
+			err = btf_dump__dump_type(d, idx);
 			if (err)
 				goto done;
 		}
@@ -500,6 +624,7 @@ static int dump_btf_c(const struct btf *btf,
 	printf("#endif /* __VMLINUX_H__ */\n");
 
 done:
+	free(datums);
 	btf_dump__free(d);
 	return err;
 }
@@ -549,10 +674,10 @@ static bool btf_is_kernel_module(__u32 btf_id)
 
 static int do_dump(int argc, char **argv)
 {
+	bool dump_c = false, sort_dump_c = true;
 	struct btf *btf = NULL, *base = NULL;
 	__u32 root_type_ids[2];
 	int root_type_cnt = 0;
-	bool dump_c = false;
 	__u32 btf_id = -1;
 	const char *src;
 	int fd = -1;
@@ -663,6 +788,9 @@ static int do_dump(int argc, char **argv)
 				goto done;
 			}
 			NEXT_ARG();
+		} else if (is_prefix(*argv, "unsorted")) {
+			sort_dump_c = false;
+			NEXT_ARG();
 		} else {
 			p_err("unrecognized option: '%s'", *argv);
 			err = -EINVAL;
@@ -691,7 +819,7 @@ static int do_dump(int argc, char **argv)
 			err = -ENOTSUP;
 			goto done;
 		}
-		err = dump_btf_c(btf, root_type_ids, root_type_cnt);
+		err = dump_btf_c(btf, root_type_ids, root_type_cnt, sort_dump_c);
 	} else {
 		err = dump_btf_raw(btf, root_type_ids, root_type_cnt);
 	}
@@ -1063,7 +1191,7 @@ static int do_help(int argc, char **argv)
 		"       %1$s %2$s help\n"
 		"\n"
 		"       BTF_SRC := { id BTF_ID | prog PROG | map MAP [{key | value | kv | all}] | file FILE }\n"
-		"       FORMAT  := { raw | c }\n"
+		"       FORMAT  := { raw | c [unsorted] }\n"
 		"       " HELP_SPEC_MAP "\n"
 		"       " HELP_SPEC_PROGRAM "\n"
 		"       " HELP_SPEC_OPTIONS " |\n"
-- 
GitLab


From e7b64f9d3f5b10186038201e0b91f734cbd7fc3d Mon Sep 17 00:00:00 2001
From: Artem Savkov <asavkov@redhat.com>
Date: Mon, 13 May 2024 13:26:58 +0200
Subject: [PATCH 074/950] bpftool: Fix make dependencies for vmlinux.h

With pre-generated vmlinux.h there is no dependency on neither vmlinux
nor bootstrap bpftool. Define dependencies separately for both modes.
This avoids needless rebuilds in some corner cases.

Suggested-by: Jan Stancek <jstancek@redhat.com>
Signed-off-by: Artem Savkov <asavkov@redhat.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Quentin Monnet <qmo@kernel.org>
Link: https://lore.kernel.org/bpf/20240513112658.43691-1-asavkov@redhat.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/bpf/bpftool/Makefile | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
index dfa4f1bebbb31..ba927379eb201 100644
--- a/tools/bpf/bpftool/Makefile
+++ b/tools/bpf/bpftool/Makefile
@@ -204,10 +204,11 @@ ifeq ($(feature-clang-bpf-co-re),1)
 
 BUILD_BPF_SKELS := 1
 
-$(OUTPUT)vmlinux.h: $(VMLINUX_BTF) $(BPFTOOL_BOOTSTRAP)
 ifeq ($(VMLINUX_H),)
+$(OUTPUT)vmlinux.h: $(VMLINUX_BTF) $(BPFTOOL_BOOTSTRAP)
 	$(QUIET_GEN)$(BPFTOOL_BOOTSTRAP) btf dump file $< format c > $@
 else
+$(OUTPUT)vmlinux.h: $(VMLINUX_H)
 	$(Q)cp "$(VMLINUX_H)" $@
 endif
 
-- 
GitLab


From 34021caef79f76e70ac31247d321ecd0683c4939 Mon Sep 17 00:00:00 2001
From: Alan Maguire <alan.maguire@oracle.com>
Date: Tue, 14 May 2024 17:27:16 +0100
Subject: [PATCH 075/950] kbuild, bpf: Use test-ge check for v1.25-only pahole

There is no need to set the pahole v1.25-only flags in an
"ifeq" version clause; we are already in a <= v1.25 branch
of "ifeq", so that combined with a "test-ge" v1.25 ensures the
flags will be applied for v1.25 only.

Suggested-by: Masahiro Yamada <masahiroy@kernel.org>
Signed-off-by: Alan Maguire <alan.maguire@oracle.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20240514162716.2448265-1-alan.maguire@oracle.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 scripts/Makefile.btf | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/scripts/Makefile.btf b/scripts/Makefile.btf
index 2d6e5ed9081e3..bca8a8f26ea4c 100644
--- a/scripts/Makefile.btf
+++ b/scripts/Makefile.btf
@@ -14,9 +14,7 @@ pahole-flags-$(call test-ge, $(pahole-ver), 121)	+= --btf_gen_floats
 
 pahole-flags-$(call test-ge, $(pahole-ver), 122)	+= -j
 
-ifeq ($(pahole-ver), 125)
-pahole-flags-y	+= --skip_encoding_btf_inconsistent_proto --btf_gen_optimized
-endif
+pahole-flags-$(call test-ge, $(pahole-ver), 125)	+= --skip_encoding_btf_inconsistent_proto --btf_gen_optimized
 
 else
 
-- 
GitLab


From 6f130e4d4a5f7174f98300376f3994817ad7e21c Mon Sep 17 00:00:00 2001
From: Mohammad Shehar Yaar Tausif <sheharyaar48@gmail.com>
Date: Thu, 16 May 2024 12:54:11 +0530
Subject: [PATCH 076/950] bpf: Fix order of args in call to bpf_map_kvcalloc

The original function call passed size of smap->bucket before the number of
buckets which raises the error 'calloc-transposed-args' on compilation.

Signed-off-by: Mohammad Shehar Yaar Tausif <sheharyaar48@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20240516072411.42016-1-sheharyaar48@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/bpf_local_storage.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c
index 976cb258a0edb..c938dea5ddbf3 100644
--- a/kernel/bpf/bpf_local_storage.c
+++ b/kernel/bpf/bpf_local_storage.c
@@ -782,8 +782,8 @@ bpf_local_storage_map_alloc(union bpf_attr *attr,
 	nbuckets = max_t(u32, 2, nbuckets);
 	smap->bucket_log = ilog2(nbuckets);
 
-	smap->buckets = bpf_map_kvcalloc(&smap->map, sizeof(*smap->buckets),
-					 nbuckets, GFP_USER | __GFP_NOWARN);
+	smap->buckets = bpf_map_kvcalloc(&smap->map, nbuckets,
+					 sizeof(*smap->buckets), GFP_USER | __GFP_NOWARN);
 	if (!smap->buckets) {
 		err = -ENOMEM;
 		goto free_smap;
-- 
GitLab


From 2785ea9673a7305abeea87111849a4e04b0f4626 Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Wed, 15 May 2024 18:28:24 +0300
Subject: [PATCH 077/950] wifi: rt2x00: remove unused delayed work data from
 link description

Remove unused 'agc_work' and 'vco_work' members of 'struct link'.
This follows commit d96324703ffa ("rt2x00: merge agc and vco works
with link tuner") where AGC and VCO calibration code was completely
redesigned. Compile tested only.

Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Acked-by: Stanislaw Gruszka <stf_xl@wp.pl>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://msgid.link/20240515152824.143537-1-dmantipov@yandex.ru
---
 drivers/net/wireless/ralink/rt2x00/rt2x00.h | 10 ----------
 1 file changed, 10 deletions(-)

diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00.h b/drivers/net/wireless/ralink/rt2x00/rt2x00.h
index 82af01448a0a8..bb648f95dfdd9 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2x00.h
+++ b/drivers/net/wireless/ralink/rt2x00/rt2x00.h
@@ -335,16 +335,6 @@ struct link {
 	struct delayed_work watchdog_work;
 	unsigned int watchdog_interval;
 	unsigned int watchdog;
-
-	/*
-	 * Work structure for scheduling periodic AGC adjustments.
-	 */
-	struct delayed_work agc_work;
-
-	/*
-	 * Work structure for scheduling periodic VCO calibration.
-	 */
-	struct delayed_work vco_work;
 };
 
 enum rt2x00_delayed_flags {
-- 
GitLab


From dc21c6cc3d6986d938efbf95de62473982c98dec Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 15 May 2024 13:23:39 +0000
Subject: [PATCH 078/950] netfilter: nfnetlink_queue: acquire rcu_read_lock()
 in instance_destroy_rcu()

syzbot reported that nf_reinject() could be called without rcu_read_lock() :

WARNING: suspicious RCU usage
6.9.0-rc7-syzkaller-02060-g5c1672705a1a #0 Not tainted

net/netfilter/nfnetlink_queue.c:263 suspicious rcu_dereference_check() usage!

other info that might help us debug this:

rcu_scheduler_active = 2, debug_locks = 1
2 locks held by syz-executor.4/13427:
  #0: ffffffff8e334f60 (rcu_callback){....}-{0:0}, at: rcu_lock_acquire include/linux/rcupdate.h:329 [inline]
  #0: ffffffff8e334f60 (rcu_callback){....}-{0:0}, at: rcu_do_batch kernel/rcu/tree.c:2190 [inline]
  #0: ffffffff8e334f60 (rcu_callback){....}-{0:0}, at: rcu_core+0xa86/0x1830 kernel/rcu/tree.c:2471
  #1: ffff88801ca92958 (&inst->lock){+.-.}-{2:2}, at: spin_lock_bh include/linux/spinlock.h:356 [inline]
  #1: ffff88801ca92958 (&inst->lock){+.-.}-{2:2}, at: nfqnl_flush net/netfilter/nfnetlink_queue.c:405 [inline]
  #1: ffff88801ca92958 (&inst->lock){+.-.}-{2:2}, at: instance_destroy_rcu+0x30/0x220 net/netfilter/nfnetlink_queue.c:172

stack backtrace:
CPU: 0 PID: 13427 Comm: syz-executor.4 Not tainted 6.9.0-rc7-syzkaller-02060-g5c1672705a1a #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 04/02/2024
Call Trace:
 <IRQ>
  __dump_stack lib/dump_stack.c:88 [inline]
  dump_stack_lvl+0x241/0x360 lib/dump_stack.c:114
  lockdep_rcu_suspicious+0x221/0x340 kernel/locking/lockdep.c:6712
  nf_reinject net/netfilter/nfnetlink_queue.c:323 [inline]
  nfqnl_reinject+0x6ec/0x1120 net/netfilter/nfnetlink_queue.c:397
  nfqnl_flush net/netfilter/nfnetlink_queue.c:410 [inline]
  instance_destroy_rcu+0x1ae/0x220 net/netfilter/nfnetlink_queue.c:172
  rcu_do_batch kernel/rcu/tree.c:2196 [inline]
  rcu_core+0xafd/0x1830 kernel/rcu/tree.c:2471
  handle_softirqs+0x2d6/0x990 kernel/softirq.c:554
  __do_softirq kernel/softirq.c:588 [inline]
  invoke_softirq kernel/softirq.c:428 [inline]
  __irq_exit_rcu+0xf4/0x1c0 kernel/softirq.c:637
  irq_exit_rcu+0x9/0x30 kernel/softirq.c:649
  instr_sysvec_apic_timer_interrupt arch/x86/kernel/apic/apic.c:1043 [inline]
  sysvec_apic_timer_interrupt+0xa6/0xc0 arch/x86/kernel/apic/apic.c:1043
 </IRQ>
 <TASK>

Fixes: 9872bec773c2 ("[NETFILTER]: nfnetlink: use RCU for queue instances hash")
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nfnetlink_queue.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index 00f4bd21c59b4..f1c31757e4969 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -169,7 +169,9 @@ instance_destroy_rcu(struct rcu_head *head)
 	struct nfqnl_instance *inst = container_of(head, struct nfqnl_instance,
 						   rcu);
 
+	rcu_read_lock();
 	nfqnl_flush(inst, NULL, 0);
+	rcu_read_unlock();
 	kfree(inst);
 	module_put(THIS_MODULE);
 }
-- 
GitLab


From 21ae74e1bf18331ae5e279bd96304b3630828009 Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Date: Fri, 17 May 2024 10:00:28 +0300
Subject: [PATCH 079/950] wifi: ath10k: fix QCOM_RPROC_COMMON dependency

If ath10k_snoc is built-in, while Qualcomm remoteprocs are built as
modules, compilation fails with:

/usr/bin/aarch64-linux-gnu-ld: drivers/net/wireless/ath/ath10k/snoc.o: in function `ath10k_modem_init':
drivers/net/wireless/ath/ath10k/snoc.c:1534: undefined reference to `qcom_register_ssr_notifier'
/usr/bin/aarch64-linux-gnu-ld: drivers/net/wireless/ath/ath10k/snoc.o: in function `ath10k_modem_deinit':
drivers/net/wireless/ath/ath10k/snoc.c:1551: undefined reference to `qcom_unregister_ssr_notifier'

Add corresponding dependency to ATH10K_SNOC Kconfig entry so that it's
built as module if QCOM_RPROC_COMMON is built as module too.

Fixes: 747ff7d3d742 ("ath10k: Don't always treat modem stop events as crashes")
Cc: stable@vger.kernel.org
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240511-ath10k-snoc-dep-v1-1-9666e3af5c27@linaro.org
---
 drivers/net/wireless/ath/ath10k/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/ath/ath10k/Kconfig b/drivers/net/wireless/ath/ath10k/Kconfig
index e6ea884cafc19..4f385f4a8cef2 100644
--- a/drivers/net/wireless/ath/ath10k/Kconfig
+++ b/drivers/net/wireless/ath/ath10k/Kconfig
@@ -45,6 +45,7 @@ config ATH10K_SNOC
 	depends on ATH10K
 	depends on ARCH_QCOM || COMPILE_TEST
 	depends on QCOM_SMEM
+	depends on QCOM_RPROC_COMMON || QCOM_RPROC_COMMON=n
 	select QCOM_SCM
 	select QCOM_QMI_HELPERS
 	help
-- 
GitLab


From 26dd8ccdba4d492d00e35c410bc4314e043bdf73 Mon Sep 17 00:00:00 2001
From: Muna Sinada <quic_msinada@quicinc.com>
Date: Fri, 17 May 2024 10:00:30 +0300
Subject: [PATCH 080/950] wifi: ath12k: dynamic VLAN support

Add support for dynamic VLAN. VLAN group traffic is encapsulated and
encrypted in mac80211 and driver needs to set flags for the VLAN group
traffic to skip hardware encapsulation and encryption.

VLAN group traffic utilizes ext MSDU and HTT Metadata to set
encapsulation type to RAW and encryption type to OPEN in order to
inform firmware to skip hardware encapsulation and encryption.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.0.1-00029-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Signed-off-by: Muna Sinada <quic_msinada@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240515192830.995013-1-quic_msinada@quicinc.com
---
 drivers/net/wireless/ath/ath12k/dp_tx.c    | 60 ++++++++++++++++++++++
 drivers/net/wireless/ath/ath12k/hal_desc.h | 25 +++++++++
 drivers/net/wireless/ath/ath12k/hw.c       |  6 ++-
 3 files changed, 89 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/dp_tx.c b/drivers/net/wireless/ath/ath12k/dp_tx.c
index f57bc8d69715e..c4cfa7cf7cb93 100644
--- a/drivers/net/wireless/ath/ath12k/dp_tx.c
+++ b/drivers/net/wireless/ath/ath12k/dp_tx.c
@@ -124,6 +124,44 @@ static void ath12k_hal_tx_cmd_ext_desc_setup(struct ath12k_base *ab,
 						 HAL_TX_MSDU_EXT_INFO1_ENCRYPT_TYPE);
 }
 
+#define HTT_META_DATA_ALIGNMENT 0x8
+
+static void *ath12k_dp_metadata_align_skb(struct sk_buff *skb, u8 tail_len)
+{
+	struct sk_buff *tail;
+	void *metadata;
+
+	if (unlikely(skb_cow_data(skb, tail_len, &tail) < 0))
+		return NULL;
+
+	metadata = pskb_put(skb, tail, tail_len);
+	memset(metadata, 0, tail_len);
+	return metadata;
+}
+
+/* Preparing HTT Metadata when utilized with ext MSDU */
+static int ath12k_dp_prepare_htt_metadata(struct sk_buff *skb)
+{
+	struct hal_tx_msdu_metadata *desc_ext;
+	u8 htt_desc_size;
+	/* Size rounded of multiple of 8 bytes */
+	u8 htt_desc_size_aligned;
+
+	htt_desc_size = sizeof(struct hal_tx_msdu_metadata);
+	htt_desc_size_aligned = ALIGN(htt_desc_size, HTT_META_DATA_ALIGNMENT);
+
+	desc_ext = ath12k_dp_metadata_align_skb(skb, htt_desc_size_aligned);
+	if (!desc_ext)
+		return -ENOMEM;
+
+	desc_ext->info0 = le32_encode_bits(1, HAL_TX_MSDU_METADATA_INFO0_ENCRYPT_FLAG) |
+			  le32_encode_bits(0, HAL_TX_MSDU_METADATA_INFO0_ENCRYPT_TYPE) |
+			  le32_encode_bits(1,
+					   HAL_TX_MSDU_METADATA_INFO0_HOST_TX_DESC_POOL);
+
+	return 0;
+}
+
 int ath12k_dp_tx(struct ath12k *ar, struct ath12k_vif *arvif,
 		 struct sk_buff *skb)
 {
@@ -145,6 +183,7 @@ int ath12k_dp_tx(struct ath12k *ar, struct ath12k_vif *arvif,
 	u8 ring_selector, ring_map = 0;
 	bool tcl_ring_retry;
 	bool msdu_ext_desc = false;
+	bool add_htt_metadata = false;
 
 	if (test_bit(ATH12K_FLAG_CRASH_FLUSH, &ar->ab->dev_flags))
 		return -ESHUTDOWN;
@@ -248,6 +287,18 @@ tcl_ring_sel:
 		goto fail_remove_tx_buf;
 	}
 
+	if (!test_bit(ATH12K_FLAG_HW_CRYPTO_DISABLED, &ar->ab->dev_flags) &&
+	    !(skb_cb->flags & ATH12K_SKB_HW_80211_ENCAP) &&
+	    !(skb_cb->flags & ATH12K_SKB_CIPHER_SET) &&
+	    ieee80211_has_protected(hdr->frame_control)) {
+		/* Add metadata for sw encrypted vlan group traffic */
+		add_htt_metadata = true;
+		msdu_ext_desc = true;
+		ti.flags0 |= u32_encode_bits(1, HAL_TCL_DATA_CMD_INFO2_TO_FW);
+		ti.encap_type = HAL_TCL_ENCAP_TYPE_RAW;
+		ti.encrypt_type = HAL_ENCRYPT_TYPE_OPEN;
+	}
+
 	tx_desc->skb = skb;
 	tx_desc->mac_id = ar->pdev_idx;
 	ti.desc_id = tx_desc->desc_id;
@@ -269,6 +320,15 @@ tcl_ring_sel:
 		msg = (struct hal_tx_msdu_ext_desc *)skb_ext_desc->data;
 		ath12k_hal_tx_cmd_ext_desc_setup(ab, msg, &ti);
 
+		if (add_htt_metadata) {
+			ret = ath12k_dp_prepare_htt_metadata(skb_ext_desc);
+			if (ret < 0) {
+				ath12k_dbg(ab, ATH12K_DBG_DP_TX,
+					   "Failed to add HTT meta data, dropping packet\n");
+				goto fail_unmap_dma;
+			}
+		}
+
 		ti.paddr = dma_map_single(ab->dev, skb_ext_desc->data,
 					  skb_ext_desc->len, DMA_TO_DEVICE);
 		ret = dma_mapping_error(ab->dev, ti.paddr);
diff --git a/drivers/net/wireless/ath/ath12k/hal_desc.h b/drivers/net/wireless/ath/ath12k/hal_desc.h
index 814c02f876d64..02b7db06b24ee 100644
--- a/drivers/net/wireless/ath/ath12k/hal_desc.h
+++ b/drivers/net/wireless/ath/ath12k/hal_desc.h
@@ -2984,4 +2984,29 @@ struct hal_mon_dest_desc {
  *	updated by SRNG.
  */
 
+#define HAL_TX_MSDU_METADATA_INFO0_ENCRYPT_FLAG		BIT(8)
+#define HAL_TX_MSDU_METADATA_INFO0_ENCRYPT_TYPE		GENMASK(16, 15)
+#define HAL_TX_MSDU_METADATA_INFO0_HOST_TX_DESC_POOL	BIT(31)
+
+struct hal_tx_msdu_metadata {
+	__le32 info0;
+	__le32 rsvd0[6];
+} __packed;
+
+/* hal_tx_msdu_metadata
+ * valid_encrypt_type
+ *		if set, encrypt type is valid
+ * encrypt_type
+ *		0 = NO_ENCRYPT,
+ *		1 = ENCRYPT,
+ *		2 ~ 3 - Reserved
+ * host_tx_desc_pool
+ *		If set, Firmware allocates tx_descriptors
+ *		in WAL_BUFFERID_TX_HOST_DATA_EXP,instead
+ *		of WAL_BUFFERID_TX_TCL_DATA_EXP.
+ *		Use cases:
+ *		Any time firmware uses TQM-BYPASS for Data
+ *		TID, firmware expect host to set this bit.
+ */
+
 #endif /* ATH12K_HAL_DESC_H */
diff --git a/drivers/net/wireless/ath/ath12k/hw.c b/drivers/net/wireless/ath/ath12k/hw.c
index 5a1d406e6b1f9..b45f929a02045 100644
--- a/drivers/net/wireless/ath/ath12k/hw.c
+++ b/drivers/net/wireless/ath/ath12k/hw.c
@@ -891,7 +891,8 @@ static const struct ath12k_hw_params ath12k_hw_params[] = {
 
 		.interface_modes = BIT(NL80211_IFTYPE_STATION) |
 					BIT(NL80211_IFTYPE_AP) |
-					BIT(NL80211_IFTYPE_MESH_POINT),
+					BIT(NL80211_IFTYPE_MESH_POINT) |
+					BIT(NL80211_IFTYPE_AP_VLAN),
 		.supports_monitor = false,
 
 		.idle_ps = false,
@@ -1038,7 +1039,8 @@ static const struct ath12k_hw_params ath12k_hw_params[] = {
 
 		.interface_modes = BIT(NL80211_IFTYPE_STATION) |
 					BIT(NL80211_IFTYPE_AP) |
-					BIT(NL80211_IFTYPE_MESH_POINT),
+					BIT(NL80211_IFTYPE_MESH_POINT) |
+					BIT(NL80211_IFTYPE_AP_VLAN),
 		.supports_monitor = false,
 
 		.idle_ps = false,
-- 
GitLab


From c1193d9bbbd379defe9be3c6de566de684de8a6f Mon Sep 17 00:00:00 2001
From: Alexander Maltsev <keltar.gw@gmail.com>
Date: Wed, 17 Apr 2024 18:51:41 +0500
Subject: [PATCH 081/950] netfilter: ipset: Add list flush to cancel_gc

Flushing list in cancel_gc drops references to other lists right away,
without waiting for RCU to destroy list. Fixes race when referenced
ipsets can't be destroyed while referring list is scheduled for destroy.

Fixes: 97f7cf1cd80e ("netfilter: ipset: fix performance regression in swap operation")
Signed-off-by: Alexander Maltsev <keltar.gw@gmail.com>
Acked-by: Jozsef Kadlecsik <kadlec@netfilter.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/ipset/ip_set_list_set.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c
index 6c3f28bc59b32..54e2a1dd7f5f5 100644
--- a/net/netfilter/ipset/ip_set_list_set.c
+++ b/net/netfilter/ipset/ip_set_list_set.c
@@ -549,6 +549,9 @@ list_set_cancel_gc(struct ip_set *set)
 
 	if (SET_WITH_TIMEOUT(set))
 		timer_shutdown_sync(&map->gc);
+
+	/* Flush list to drop references to other ipsets */
+	list_set_flush(set);
 }
 
 static const struct ip_set_type_variant set_variant = {
-- 
GitLab


From aff5c01fa1284d606f8e7cbdaafeef2511bb46c1 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Thu, 9 May 2024 23:02:24 +0200
Subject: [PATCH 082/950] netfilter: nft_payload: restore vlan q-in-q match
 support

Revert f6ae9f120dad ("netfilter: nft_payload: add C-VLAN support").

f41f72d09ee1 ("netfilter: nft_payload: simplify vlan header handling")
already allows to match on inner vlan tags by subtract the vlan header
size to the payload offset which has been popped and stored in skbuff
metadata fields.

Fixes: f6ae9f120dad ("netfilter: nft_payload: add C-VLAN support")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nft_payload.c | 23 +++++++----------------
 1 file changed, 7 insertions(+), 16 deletions(-)

diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c
index 0a689c8e0295d..a3cb5dbcb362c 100644
--- a/net/netfilter/nft_payload.c
+++ b/net/netfilter/nft_payload.c
@@ -45,36 +45,27 @@ nft_payload_copy_vlan(u32 *d, const struct sk_buff *skb, u8 offset, u8 len)
 	int mac_off = skb_mac_header(skb) - skb->data;
 	u8 *vlanh, *dst_u8 = (u8 *) d;
 	struct vlan_ethhdr veth;
-	u8 vlan_hlen = 0;
-
-	if ((skb->protocol == htons(ETH_P_8021AD) ||
-	     skb->protocol == htons(ETH_P_8021Q)) &&
-	    offset >= VLAN_ETH_HLEN && offset < VLAN_ETH_HLEN + VLAN_HLEN)
-		vlan_hlen += VLAN_HLEN;
 
 	vlanh = (u8 *) &veth;
-	if (offset < VLAN_ETH_HLEN + vlan_hlen) {
+	if (offset < VLAN_ETH_HLEN) {
 		u8 ethlen = len;
 
-		if (vlan_hlen &&
-		    skb_copy_bits(skb, mac_off, &veth, VLAN_ETH_HLEN) < 0)
-			return false;
-		else if (!nft_payload_rebuild_vlan_hdr(skb, mac_off, &veth))
+		if (!nft_payload_rebuild_vlan_hdr(skb, mac_off, &veth))
 			return false;
 
-		if (offset + len > VLAN_ETH_HLEN + vlan_hlen)
-			ethlen -= offset + len - VLAN_ETH_HLEN - vlan_hlen;
+		if (offset + len > VLAN_ETH_HLEN)
+			ethlen -= offset + len - VLAN_ETH_HLEN;
 
-		memcpy(dst_u8, vlanh + offset - vlan_hlen, ethlen);
+		memcpy(dst_u8, vlanh + offset, ethlen);
 
 		len -= ethlen;
 		if (len == 0)
 			return true;
 
 		dst_u8 += ethlen;
-		offset = ETH_HLEN + vlan_hlen;
+		offset = ETH_HLEN;
 	} else {
-		offset -= VLAN_HLEN + vlan_hlen;
+		offset -= VLAN_HLEN;
 	}
 
 	return skb_copy_bits(skb, offset + mac_off, dst_u8, len) == 0;
-- 
GitLab


From 33370412eced2dc7f81f4324e109d69319cafd82 Mon Sep 17 00:00:00 2001
From: Baochen Qiang <quic_bqiang@quicinc.com>
Date: Mon, 20 May 2024 14:58:28 +0300
Subject: [PATCH 083/950] wifi: ath12k: fix Smatch warnings on
 ath12k_core_suspend()

Smatch is throwing below warning:

Commit 692921ead832 ("wifi: ath12k: flush all packets before
suspend") leads to the following Smatch static checker warning:

	drivers/net/wireless/ath/ath12k/core.c:58 ath12k_core_suspend()
	warn: sleeping in atomic context

and also gives the reason:

drivers/net/wireless/ath/ath12k/core.c
    48         int ret, i;
    49
    50         if (!ab->hw_params->supports_suspend)
    51                 return -EOPNOTSUPP;
    52
    53         rcu_read_lock();
               ^^^^^^^^^^^^^^^
Disables preemption.

    54         for (i = 0; i < ab->num_radios; i++) {
    55                 ar = ath12k_mac_get_ar_by_pdev_id(ab, i);
    56                 if (!ar)
    57                         continue;
--> 58                 ret = ath12k_mac_wait_tx_complete(ar);
                                        ^^^^^^^
Sleeping in atomic context.

    59                 if (ret) {
    60                         ath12k_warn(ab, "failed to wait tx complete: %d\n", ret);
    61                         rcu_read_unlock();
    62                         return ret;
    63                 }
    64         }
    65         rcu_read_unlock();

But it is weird that no warning on this in run time even with
CONFIG_DEBUG_ATOMIC_SLEEP=y. With some debug it is found that this is
because: when system goes to suspend, ath12k_mac_op_stop() gets called
where then in ath12k_mac_stop() ab->pdevs_active[ar->pdev_idx] is cleared.
This results in ath12k_mac_get_ar_by_pdev_id() always returning a NULL ar,
and thereby ath12k_mac_wait_tx_complete() never gets a chance to run.

Fix it by retrieving ar directly from ab->pdevs[].ar instead of using
ath12k_mac_get_ar_by_pdev_id(). Since ab->pdevs[].ar is set at boot time
and won't get cleared when suspend, ath12k_mac_wait_tx_complete() won't
be skipped. In addition, with ath12k_mac_get_ar_by_pdev_id() removed,
rcu_read_lock()/unlock() are not needed any more, so remove them. This
also fixes the warning above.

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0-03427-QCAHMTSWPL_V1.0_V2.0_SILICONZ-1.15378.4

Fixes: 692921ead832 ("wifi: ath12k: flush all packets before suspend")
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Closes: https://lore.kernel.org/ath12k/7a96ca11-80b5-4751-8cfc-fa637f3aa63a@moroto.mountain/
Signed-off-by: Baochen Qiang <quic_bqiang@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240511095045.9623-1-quic_bqiang@quicinc.com
---
 drivers/net/wireless/ath/ath12k/core.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/core.c b/drivers/net/wireless/ath/ath12k/core.c
index 9482d5db71e77..e7f628e935e4a 100644
--- a/drivers/net/wireless/ath/ath12k/core.c
+++ b/drivers/net/wireless/ath/ath12k/core.c
@@ -50,19 +50,16 @@ int ath12k_core_suspend(struct ath12k_base *ab)
 	if (!ab->hw_params->supports_suspend)
 		return -EOPNOTSUPP;
 
-	rcu_read_lock();
 	for (i = 0; i < ab->num_radios; i++) {
-		ar = ath12k_mac_get_ar_by_pdev_id(ab, i);
+		ar = ab->pdevs[i].ar;
 		if (!ar)
 			continue;
 		ret = ath12k_mac_wait_tx_complete(ar);
 		if (ret) {
 			ath12k_warn(ab, "failed to wait tx complete: %d\n", ret);
-			rcu_read_unlock();
 			return ret;
 		}
 	}
-	rcu_read_unlock();
 
 	/* PM framework skips suspend_late/resume_early callbacks
 	 * if other devices report errors in their suspend callbacks.
-- 
GitLab


From e8dc41afca161b988e6d462f4d0803d247e22250 Mon Sep 17 00:00:00 2001
From: Shengjiu Wang <shengjiu.wang@nxp.com>
Date: Sat, 11 May 2024 10:55:25 +0800
Subject: [PATCH 084/950] pmdomain: imx: gpcv2: Add delay after power up
 handshake

AudioMix BLK-CTRL on i.MX8MP encountered an accessing register issue
after power up.

[    2.181035] Kernel panic - not syncing: Asynchronous SError Interrupt
[    2.181038] CPU: 1 PID: 48 Comm: kworker/u16:2 Not tainted 6.9.0-rc5-next-20240424-00003-g21cec88845c6 #171
[    2.181047] Hardware name: NXP i.MX8MPlus EVK board (DT)
[    2.181050] Workqueue: events_unbound deferred_probe_work_func
[    2.181064] Call trace:
[...]
[    2.181142]  arm64_serror_panic+0x6c/0x78
[    2.181149]  do_serror+0x3c/0x70
[    2.181157]  el1h_64_error_handler+0x30/0x48
[    2.181164]  el1h_64_error+0x64/0x68
[    2.181171]  clk_imx8mp_audiomix_runtime_resume+0x34/0x44
[    2.181183]  __genpd_runtime_resume+0x30/0x80
[    2.181195]  genpd_runtime_resume+0x110/0x244
[    2.181205]  __rpm_callback+0x48/0x1d8
[    2.181213]  rpm_callback+0x68/0x74
[    2.181224]  rpm_resume+0x468/0x6c0
[    2.181234]  __pm_runtime_resume+0x50/0x94
[    2.181243]  pm_runtime_get_suppliers+0x60/0x8c
[    2.181258]  __driver_probe_device+0x48/0x12c
[    2.181268]  driver_probe_device+0xd8/0x15c
[    2.181278]  __device_attach_driver+0xb8/0x134
[    2.181290]  bus_for_each_drv+0x84/0xe0
[    2.181302]  __device_attach+0x9c/0x188
[    2.181312]  device_initial_probe+0x14/0x20
[    2.181323]  bus_probe_device+0xac/0xb0
[    2.181334]  deferred_probe_work_func+0x88/0xc0
[    2.181344]  process_one_work+0x150/0x290
[    2.181357]  worker_thread+0x2f8/0x408
[    2.181370]  kthread+0x110/0x114
[    2.181381]  ret_from_fork+0x10/0x20
[    2.181391] SMP: stopping secondary CPUs

According to comments in power up handshake:

	/* request the ADB400 to power up */
	if (domain->bits.hskreq) {
		regmap_update_bits(domain->regmap, domain->regs->hsk,
				   domain->bits.hskreq, domain->bits.hskreq);

		/*
		 * ret = regmap_read_poll_timeout(domain->regmap, domain->regs->hsk, reg_val,
		 *				  (reg_val & domain->bits.hskack), 0,
		 *				  USEC_PER_MSEC);
		 * Technically we need the commented code to wait handshake. But that needs
		 * the BLK-CTL module BUS clk-en bit being set.
		 *
		 * There is a separate BLK-CTL module and we will have such a driver for it,
		 * that driver will set the BUS clk-en bit and handshake will be triggered
		 * automatically there. Just add a delay and suppose the handshake finish
		 * after that.
		 */
	}

The BLK-CTL module needs to add delay to wait for a handshake request finished.
For some BLK-CTL module (eg. AudioMix on i.MX8MP) doesn't have BUS clk-en
bit, it is better to add delay in this driver, as the BLK-CTL module doesn't
need to care about how it is powered up.

regmap_read_bypassed() is to make sure the above write IO transaction already
reaches target before udelay().

Fixes: 1496dd413b2e ("clk: imx: imx8mp: Add pm_runtime support for power saving")
Reported-by: Francesco Dolcini <francesco@dolcini.it>
Closes: https://lore.kernel.org/all/66293535.170a0220.21fe.a2e7@mx.google.com/
Suggested-by: Frank Li <frank.li@nxp.com>
Signed-off-by: Shengjiu Wang <shengjiu.wang@nxp.com>
Tested-by: Adam Ford <aford173@gmail.com>
Tested-by: Alexander Stein <alexander.stein@ew.tq-group.com>
Link: https://lore.kernel.org/r/1715396125-3724-1-git-send-email-shengjiu.wang@nxp.com
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/pmdomain/imx/gpcv2.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/pmdomain/imx/gpcv2.c b/drivers/pmdomain/imx/gpcv2.c
index 4b828d74a6064..856eaac0ec140 100644
--- a/drivers/pmdomain/imx/gpcv2.c
+++ b/drivers/pmdomain/imx/gpcv2.c
@@ -393,6 +393,17 @@ static int imx_pgc_power_up(struct generic_pm_domain *genpd)
 		 * automatically there. Just add a delay and suppose the handshake finish
 		 * after that.
 		 */
+
+		/*
+		 * For some BLK-CTL module (eg. AudioMix on i.MX8MP) doesn't have BUS
+		 * clk-en bit, it is better to add delay here, as the BLK-CTL module
+		 * doesn't need to care about how it is powered up.
+		 *
+		 * regmap_read_bypassed() is to make sure the above write IO transaction
+		 * already reaches target before udelay()
+		 */
+		regmap_read_bypassed(domain->regmap, domain->regs->hsk, &reg_val);
+		udelay(5);
 	}
 
 	/* Disable reset clocks for all devices in the domain */
-- 
GitLab


From 25460d6f39024cc3b8241b14c7ccf0d6f11a736a Mon Sep 17 00:00:00 2001
From: Nikita Zhandarovich <n.zhandarovich@fintech.ru>
Date: Mon, 8 Apr 2024 07:10:39 -0700
Subject: [PATCH 085/950] net/9p: fix uninit-value in p9_client_rpc()

Syzbot with the help of KMSAN reported the following error:

BUG: KMSAN: uninit-value in trace_9p_client_res include/trace/events/9p.h:146 [inline]
BUG: KMSAN: uninit-value in p9_client_rpc+0x1314/0x1340 net/9p/client.c:754
 trace_9p_client_res include/trace/events/9p.h:146 [inline]
 p9_client_rpc+0x1314/0x1340 net/9p/client.c:754
 p9_client_create+0x1551/0x1ff0 net/9p/client.c:1031
 v9fs_session_init+0x1b9/0x28e0 fs/9p/v9fs.c:410
 v9fs_mount+0xe2/0x12b0 fs/9p/vfs_super.c:122
 legacy_get_tree+0x114/0x290 fs/fs_context.c:662
 vfs_get_tree+0xa7/0x570 fs/super.c:1797
 do_new_mount+0x71f/0x15e0 fs/namespace.c:3352
 path_mount+0x742/0x1f20 fs/namespace.c:3679
 do_mount fs/namespace.c:3692 [inline]
 __do_sys_mount fs/namespace.c:3898 [inline]
 __se_sys_mount+0x725/0x810 fs/namespace.c:3875
 __x64_sys_mount+0xe4/0x150 fs/namespace.c:3875
 do_syscall_64+0xd5/0x1f0
 entry_SYSCALL_64_after_hwframe+0x6d/0x75

Uninit was created at:
 __alloc_pages+0x9d6/0xe70 mm/page_alloc.c:4598
 __alloc_pages_node include/linux/gfp.h:238 [inline]
 alloc_pages_node include/linux/gfp.h:261 [inline]
 alloc_slab_page mm/slub.c:2175 [inline]
 allocate_slab mm/slub.c:2338 [inline]
 new_slab+0x2de/0x1400 mm/slub.c:2391
 ___slab_alloc+0x1184/0x33d0 mm/slub.c:3525
 __slab_alloc mm/slub.c:3610 [inline]
 __slab_alloc_node mm/slub.c:3663 [inline]
 slab_alloc_node mm/slub.c:3835 [inline]
 kmem_cache_alloc+0x6d3/0xbe0 mm/slub.c:3852
 p9_tag_alloc net/9p/client.c:278 [inline]
 p9_client_prepare_req+0x20a/0x1770 net/9p/client.c:641
 p9_client_rpc+0x27e/0x1340 net/9p/client.c:688
 p9_client_create+0x1551/0x1ff0 net/9p/client.c:1031
 v9fs_session_init+0x1b9/0x28e0 fs/9p/v9fs.c:410
 v9fs_mount+0xe2/0x12b0 fs/9p/vfs_super.c:122
 legacy_get_tree+0x114/0x290 fs/fs_context.c:662
 vfs_get_tree+0xa7/0x570 fs/super.c:1797
 do_new_mount+0x71f/0x15e0 fs/namespace.c:3352
 path_mount+0x742/0x1f20 fs/namespace.c:3679
 do_mount fs/namespace.c:3692 [inline]
 __do_sys_mount fs/namespace.c:3898 [inline]
 __se_sys_mount+0x725/0x810 fs/namespace.c:3875
 __x64_sys_mount+0xe4/0x150 fs/namespace.c:3875
 do_syscall_64+0xd5/0x1f0
 entry_SYSCALL_64_after_hwframe+0x6d/0x75

If p9_check_errors() fails early in p9_client_rpc(), req->rc.tag
will not be properly initialized. However, trace_9p_client_res()
ends up trying to print it out anyway before p9_client_rpc()
finishes.

Fix this issue by assigning default values to p9_fcall fields
such as 'tag' and (just in case KMSAN unearths something new) 'id'
during the tag allocation stage.

Reported-and-tested-by: syzbot+ff14db38f56329ef68df@syzkaller.appspotmail.com
Fixes: 348b59012e5c ("net/9p: Convert net/9p protocol dumps to tracepoints")
Signed-off-by: Nikita Zhandarovich <n.zhandarovich@fintech.ru>
Reviewed-by: Christian Schoenebeck <linux_oss@crudebyte.com>
Cc: stable@vger.kernel.org
Message-ID: <20240408141039.30428-1-n.zhandarovich@fintech.ru>
Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
---
 net/9p/client.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/9p/client.c b/net/9p/client.c
index f7e90b4769bba..b05f73c291b4b 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -235,6 +235,8 @@ static int p9_fcall_init(struct p9_client *c, struct p9_fcall *fc,
 	if (!fc->sdata)
 		return -ENOMEM;
 	fc->capacity = alloc_msize;
+	fc->id = 0;
+	fc->tag = P9_NOTAG;
 	return 0;
 }
 
-- 
GitLab


From 39bc27bd688066a63e56f7f64ad34fae03fbe3b8 Mon Sep 17 00:00:00 2001
From: "Wachowski, Karol" <karol.wachowski@intel.com>
Date: Mon, 20 May 2024 12:05:14 +0200
Subject: [PATCH 086/950] drm/shmem-helper: Fix BUG_ON() on mmap(PROT_WRITE,
 MAP_PRIVATE)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Lack of check for copy-on-write (COW) mapping in drm_gem_shmem_mmap
allows users to call mmap with PROT_WRITE and MAP_PRIVATE flag
causing a kernel panic due to BUG_ON in vmf_insert_pfn_prot:
BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags));

Return -EINVAL early if COW mapping is detected.

This bug affects all drm drivers using default shmem helpers.
It can be reproduced by this simple example:
void *ptr = mmap(0, size, PROT_WRITE, MAP_PRIVATE, fd, mmap_offset);
ptr[0] = 0;

Fixes: 2194a63a818d ("drm: Add library for shmem backed GEM objects")
Cc: Noralf Trønnes <noralf@tronnes.org>
Cc: Eric Anholt <eric@anholt.net>
Cc: Rob Herring <robh@kernel.org>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Maxime Ripard <mripard@kernel.org>
Cc: Thomas Zimmermann <tzimmermann@suse.de>
Cc: David Airlie <airlied@gmail.com>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: dri-devel@lists.freedesktop.org
Cc: <stable@vger.kernel.org> # v5.2+
Signed-off-by: Wachowski, Karol <karol.wachowski@intel.com>
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20240520100514.925681-1-jacek.lawrynowicz@linux.intel.com
---
 drivers/gpu/drm/drm_gem_shmem_helper.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c
index e435f986cd135..1ff0678be7c75 100644
--- a/drivers/gpu/drm/drm_gem_shmem_helper.c
+++ b/drivers/gpu/drm/drm_gem_shmem_helper.c
@@ -610,6 +610,9 @@ int drm_gem_shmem_mmap(struct drm_gem_shmem_object *shmem, struct vm_area_struct
 		return ret;
 	}
 
+	if (is_cow_mapping(vma->vm_flags))
+		return -EINVAL;
+
 	dma_resv_lock(shmem->base.resv, NULL);
 	ret = drm_gem_shmem_get_pages(shmem);
 	dma_resv_unlock(shmem->base.resv);
-- 
GitLab


From d3a043733f25d743f3aa617c7f82dbcb5ee2211a Mon Sep 17 00:00:00 2001
From: Nilay Shroff <nilay@linux.ibm.com>
Date: Thu, 16 May 2024 17:43:51 +0530
Subject: [PATCH 087/950] nvme-multipath: find NUMA path only for online
 numa-node

In current native multipath design when a shared namespace is created,
we loop through each possible numa-node, calculate the NUMA distance of
that node from each nvme controller and then cache the optimal IO path
for future reference while sending IO. The issue with this design is that
we may refer to the NUMA distance table for an offline node which may not
be populated at the time and so we may inadvertently end up finding and
caching a non-optimal path for IO. Then latter when the corresponding
numa-node becomes online and hence the NUMA distance table entry for that
node is created, ideally we should re-calculate the multipath node distance
for the newly added node however that doesn't happen unless we rescan/reset
the controller. So essentially, we may keep using non-optimal IO path for a
node which is made online after namespace is created.
This patch helps fix this issue ensuring that when a shared namespace is
created, we calculate the multipath node distance for each online numa-node
instead of each possible numa-node. Then latter when a node becomes online
and we receive any IO on that newly added node, we would calculate the
multipath node distance for newly added node but this time NUMA distance
table would have been already populated for newly added node. Hence we
would be able to correctly calculate the multipath node distance and choose
the optimal path for the IO.

Signed-off-by: Nilay Shroff <nilay@linux.ibm.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/multipath.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index d16e976ae1a47..9c1e135b8df3b 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -595,7 +595,7 @@ static void nvme_mpath_set_live(struct nvme_ns *ns)
 		int node, srcu_idx;
 
 		srcu_idx = srcu_read_lock(&head->srcu);
-		for_each_node(node)
+		for_each_online_node(node)
 			__nvme_find_path(head, node);
 		srcu_read_unlock(&head->srcu, srcu_idx);
 	}
-- 
GitLab


From f4aba3471cfb9ccf69b476463f19b4c50fef6b14 Mon Sep 17 00:00:00 2001
From: Ivan Babrou <ivan@cloudflare.com>
Date: Mon, 20 May 2024 15:51:49 -0700
Subject: [PATCH 088/950] bpftool: Un-const bpf_func_info to fix it for llvm 17
 and newer

LLVM 17 started treating const structs as constants:

* https://github.com/llvm/llvm-project/commit/0b2d5b967d98

Combined with pointer laundering via ptr_to_u64, which takes a const ptr,
but in reality treats the underlying memory as mutable, this makes clang
always pass zero to btf__type_by_id, which breaks full name resolution.

Disassembly before (LLVM 16) and after (LLVM 17):

    -    8b 75 cc                 mov    -0x34(%rbp),%esi
    -    e8 47 8d 02 00           call   3f5b0 <btf__type_by_id>
    +    31 f6                    xor    %esi,%esi
    +    e8 a9 8c 02 00           call   3f510 <btf__type_by_id>

It's a bigger project to fix this properly (and a question whether LLVM
itself should detect this), but for right now let's just fix bpftool.

For more information, see this thread in bpf mailing list:

* https://lore.kernel.org/bpf/CABWYdi0ymezpYsQsPv7qzpx2fWuTkoD1-wG1eT-9x-TSREFrQg@mail.gmail.com/T/

Fixes: b662000aff84 ("bpftool: Adding support for BTF program names")
Signed-off-by: Ivan Babrou <ivan@cloudflare.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Nick Desaulniers <ndesaulniers@google.com>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/bpf/20240520225149.5517-1-ivan@cloudflare.com
---
 tools/bpf/bpftool/common.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
index 958e92acca8e2..9b75639434b81 100644
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@@ -410,7 +410,7 @@ void get_prog_full_name(const struct bpf_prog_info *prog_info, int prog_fd,
 {
 	const char *prog_name = prog_info->name;
 	const struct btf_type *func_type;
-	const struct bpf_func_info finfo = {};
+	struct bpf_func_info finfo = {};
 	struct bpf_prog_info info = {};
 	__u32 info_len = sizeof(info);
 	struct btf *prog_btf = NULL;
-- 
GitLab


From 1b0215a3633a4c54ed7ec3af93e7a782dda8d965 Mon Sep 17 00:00:00 2001
From: Ying Zhang <yingzhang098@163.com>
Date: Tue, 21 May 2024 16:17:02 +0000
Subject: [PATCH 089/950] bpf: Remove unused variable "prev_state"

The variable "prev_state" is not used for any actual operations

v2: Fix commit message and description.

Signed-off-by: Ying Zhang <yingzhang098@163.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/bpf/20240521161702.4339-1-yingzhang098@163.com
---
 samples/bpf/cpustat_kern.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/samples/bpf/cpustat_kern.c b/samples/bpf/cpustat_kern.c
index 944f13fe164a8..7ec7143e27579 100644
--- a/samples/bpf/cpustat_kern.c
+++ b/samples/bpf/cpustat_kern.c
@@ -211,7 +211,7 @@ int bpf_prog1(struct cpu_args *ctx)
 SEC("tracepoint/power/cpu_frequency")
 int bpf_prog2(struct cpu_args *ctx)
 {
-	u64 *pts, *cstate, *pstate, prev_state, cur_ts, delta;
+	u64 *pts, *cstate, *pstate, cur_ts, delta;
 	u32 key, cpu, pstate_idx;
 	u64 *val;
 
@@ -232,7 +232,6 @@ int bpf_prog2(struct cpu_args *ctx)
 	if (!cstate)
 		return 0;
 
-	prev_state = *pstate;
 	*pstate = ctx->state;
 
 	if (!*pts) {
-- 
GitLab


From 8d00547ea8754afdc4a550af2fb7af2e3ba93cf8 Mon Sep 17 00:00:00 2001
From: Xu Kuohai <xukuohai@huaweicloud.com>
Date: Thu, 16 May 2024 10:09:28 +0800
Subject: [PATCH 090/950] MAINTAINERS: Add myself as reviewer of ARM64 BPF JIT

I am working on ARM64 BPF JIT for a while, hence add myself
as reviewer.

Signed-off-by: Xu Kuohai <xukuohai@huaweicloud.com>
Acked-by: Hengqi Chen <hengqi.chen@gmail.com>
Link: https://lore.kernel.org/r/20240516020928.156125-1-xukuohai@huaweicloud.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 MAINTAINERS | 1 +
 1 file changed, 1 insertion(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 3fdc3b09c1717..5e279e9ff63f7 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3816,6 +3816,7 @@ BPF JIT for ARM64
 M:	Daniel Borkmann <daniel@iogearbox.net>
 M:	Alexei Starovoitov <ast@kernel.org>
 M:	Puranjay Mohan <puranjay@kernel.org>
+R:	Xu Kuohai <xukuohai@huaweicloud.com>
 L:	bpf@vger.kernel.org
 S:	Supported
 F:	arch/arm64/net/
-- 
GitLab


From 6c8d7598dfed759bf1d9d0322b4c2b42eb7252d8 Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Fri, 17 May 2024 14:21:46 +0800
Subject: [PATCH 091/950] selftests/bpf: Fix prog numbers in test_sockmap

bpf_prog5 and bpf_prog7 are removed from progs/test_sockmap_kern.h in
commit d79a32129b21 ("bpf: Selftests, remove prints from sockmap tests"),
now there are only 9 progs in it, not 11:

	SEC("sk_skb1")
	int bpf_prog1(struct __sk_buff *skb)
	SEC("sk_skb2")
	int bpf_prog2(struct __sk_buff *skb)
	SEC("sk_skb3")
	int bpf_prog3(struct __sk_buff *skb)
	SEC("sockops")
	int bpf_sockmap(struct bpf_sock_ops *skops)
	SEC("sk_msg1")
	int bpf_prog4(struct sk_msg_md *msg)
	SEC("sk_msg2")
	int bpf_prog6(struct sk_msg_md *msg)
	SEC("sk_msg3")
	int bpf_prog8(struct sk_msg_md *msg)
	SEC("sk_msg4")
	int bpf_prog9(struct sk_msg_md *msg)
	SEC("sk_msg5")
	int bpf_prog10(struct sk_msg_md *msg)

This patch updates the array sizes of prog_fd[], prog_attach_type[] and
prog_type[] from 11 to 9 accordingly.

Fixes: d79a32129b21 ("bpf: Selftests, remove prints from sockmap tests")
Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/9c10d9f974f07fcb354a43a8eca67acb2fafc587.1715926605.git.tanggeliang@kylinos.cn
---
 tools/testing/selftests/bpf/test_sockmap.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index 92752f5eededf..4499b3cfc3a68 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -63,7 +63,7 @@ int passed;
 int failed;
 int map_fd[9];
 struct bpf_map *maps[9];
-int prog_fd[11];
+int prog_fd[9];
 
 int txmsg_pass;
 int txmsg_redir;
@@ -1793,8 +1793,6 @@ int prog_attach_type[] = {
 	BPF_SK_MSG_VERDICT,
 	BPF_SK_MSG_VERDICT,
 	BPF_SK_MSG_VERDICT,
-	BPF_SK_MSG_VERDICT,
-	BPF_SK_MSG_VERDICT,
 };
 
 int prog_type[] = {
@@ -1807,8 +1805,6 @@ int prog_type[] = {
 	BPF_PROG_TYPE_SK_MSG,
 	BPF_PROG_TYPE_SK_MSG,
 	BPF_PROG_TYPE_SK_MSG,
-	BPF_PROG_TYPE_SK_MSG,
-	BPF_PROG_TYPE_SK_MSG,
 };
 
 static int populate_progs(char *bpf_file)
-- 
GitLab


From ece4b296904167336d0aaab26bd7122018835202 Mon Sep 17 00:00:00 2001
From: Brad Cowie <brad@faucet.nz>
Date: Wed, 22 May 2024 17:07:11 +1200
Subject: [PATCH 092/950] net: netfilter: Make ct zone opts configurable for
 bpf ct helpers

Add ct zone id and direction to bpf_ct_opts so that arbitrary ct zones
can be used for xdp/tc bpf ct helper functions bpf_{xdp,skb}_ct_alloc
and bpf_{xdp,skb}_ct_lookup.

Signed-off-by: Brad Cowie <brad@faucet.nz>
Link: https://lore.kernel.org/r/20240522050712.732558-1-brad@faucet.nz
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 net/netfilter/nf_conntrack_bpf.c | 68 ++++++++++++++++++++++++++------
 1 file changed, 55 insertions(+), 13 deletions(-)

diff --git a/net/netfilter/nf_conntrack_bpf.c b/net/netfilter/nf_conntrack_bpf.c
index d2492d050fe60..4a136fc3a9c0f 100644
--- a/net/netfilter/nf_conntrack_bpf.c
+++ b/net/netfilter/nf_conntrack_bpf.c
@@ -32,7 +32,9 @@
  *		   -EINVAL - Passed NULL for bpf_tuple pointer
  *		   -EINVAL - opts->reserved is not 0
  *		   -EINVAL - netns_id is less than -1
- *		   -EINVAL - opts__sz isn't NF_BPF_CT_OPTS_SZ (12)
+ *		   -EINVAL - opts__sz isn't NF_BPF_CT_OPTS_SZ (16) or 12
+ *		   -EINVAL - opts->ct_zone_id set when
+			     opts__sz isn't NF_BPF_CT_OPTS_SZ (16)
  *		   -EPROTO - l4proto isn't one of IPPROTO_TCP or IPPROTO_UDP
  *		   -ENONET - No network namespace found for netns_id
  *		   -ENOENT - Conntrack lookup could not find entry for tuple
@@ -42,6 +44,8 @@
  *		 Values:
  *		   IPPROTO_TCP, IPPROTO_UDP
  * @dir:       - connection tracking tuple direction.
+ * @ct_zone_id - connection tracking zone id.
+ * @ct_zone_dir - connection tracking zone direction.
  * @reserved   - Reserved member, will be reused for more options in future
  *		 Values:
  *		   0
@@ -51,11 +55,13 @@ struct bpf_ct_opts {
 	s32 error;
 	u8 l4proto;
 	u8 dir;
-	u8 reserved[2];
+	u16 ct_zone_id;
+	u8 ct_zone_dir;
+	u8 reserved[3];
 };
 
 enum {
-	NF_BPF_CT_OPTS_SZ = 12,
+	NF_BPF_CT_OPTS_SZ = 16,
 };
 
 static int bpf_nf_ct_tuple_parse(struct bpf_sock_tuple *bpf_tuple,
@@ -104,12 +110,21 @@ __bpf_nf_ct_alloc_entry(struct net *net, struct bpf_sock_tuple *bpf_tuple,
 			u32 timeout)
 {
 	struct nf_conntrack_tuple otuple, rtuple;
+	struct nf_conntrack_zone ct_zone;
 	struct nf_conn *ct;
 	int err;
 
-	if (!opts || !bpf_tuple || opts->reserved[0] || opts->reserved[1] ||
-	    opts_len != NF_BPF_CT_OPTS_SZ)
+	if (!opts || !bpf_tuple)
 		return ERR_PTR(-EINVAL);
+	if (!(opts_len == NF_BPF_CT_OPTS_SZ || opts_len == 12))
+		return ERR_PTR(-EINVAL);
+	if (opts_len == NF_BPF_CT_OPTS_SZ) {
+		if (opts->reserved[0] || opts->reserved[1] || opts->reserved[2])
+			return ERR_PTR(-EINVAL);
+	} else {
+		if (opts->ct_zone_id)
+			return ERR_PTR(-EINVAL);
+	}
 
 	if (unlikely(opts->netns_id < BPF_F_CURRENT_NETNS))
 		return ERR_PTR(-EINVAL);
@@ -130,7 +145,16 @@ __bpf_nf_ct_alloc_entry(struct net *net, struct bpf_sock_tuple *bpf_tuple,
 			return ERR_PTR(-ENONET);
 	}
 
-	ct = nf_conntrack_alloc(net, &nf_ct_zone_dflt, &otuple, &rtuple,
+	if (opts_len == NF_BPF_CT_OPTS_SZ) {
+		if (opts->ct_zone_dir == 0)
+			opts->ct_zone_dir = NF_CT_DEFAULT_ZONE_DIR;
+		nf_ct_zone_init(&ct_zone,
+				opts->ct_zone_id, opts->ct_zone_dir, 0);
+	} else {
+		ct_zone = nf_ct_zone_dflt;
+	}
+
+	ct = nf_conntrack_alloc(net, &ct_zone, &otuple, &rtuple,
 				GFP_ATOMIC);
 	if (IS_ERR(ct))
 		goto out;
@@ -152,12 +176,21 @@ static struct nf_conn *__bpf_nf_ct_lookup(struct net *net,
 {
 	struct nf_conntrack_tuple_hash *hash;
 	struct nf_conntrack_tuple tuple;
+	struct nf_conntrack_zone ct_zone;
 	struct nf_conn *ct;
 	int err;
 
-	if (!opts || !bpf_tuple || opts->reserved[0] || opts->reserved[1] ||
-	    opts_len != NF_BPF_CT_OPTS_SZ)
+	if (!opts || !bpf_tuple)
 		return ERR_PTR(-EINVAL);
+	if (!(opts_len == NF_BPF_CT_OPTS_SZ || opts_len == 12))
+		return ERR_PTR(-EINVAL);
+	if (opts_len == NF_BPF_CT_OPTS_SZ) {
+		if (opts->reserved[0] || opts->reserved[1] || opts->reserved[2])
+			return ERR_PTR(-EINVAL);
+	} else {
+		if (opts->ct_zone_id)
+			return ERR_PTR(-EINVAL);
+	}
 	if (unlikely(opts->l4proto != IPPROTO_TCP && opts->l4proto != IPPROTO_UDP))
 		return ERR_PTR(-EPROTO);
 	if (unlikely(opts->netns_id < BPF_F_CURRENT_NETNS))
@@ -174,7 +207,16 @@ static struct nf_conn *__bpf_nf_ct_lookup(struct net *net,
 			return ERR_PTR(-ENONET);
 	}
 
-	hash = nf_conntrack_find_get(net, &nf_ct_zone_dflt, &tuple);
+	if (opts_len == NF_BPF_CT_OPTS_SZ) {
+		if (opts->ct_zone_dir == 0)
+			opts->ct_zone_dir = NF_CT_DEFAULT_ZONE_DIR;
+		nf_ct_zone_init(&ct_zone,
+				opts->ct_zone_id, opts->ct_zone_dir, 0);
+	} else {
+		ct_zone = nf_ct_zone_dflt;
+	}
+
+	hash = nf_conntrack_find_get(net, &ct_zone, &tuple);
 	if (opts->netns_id >= 0)
 		put_net(net);
 	if (!hash)
@@ -245,7 +287,7 @@ __bpf_kfunc_start_defs();
  * @opts	- Additional options for allocation (documented above)
  *		    Cannot be NULL
  * @opts__sz	- Length of the bpf_ct_opts structure
- *		    Must be NF_BPF_CT_OPTS_SZ (12)
+ *		    Must be NF_BPF_CT_OPTS_SZ (16) or 12
  */
 __bpf_kfunc struct nf_conn___init *
 bpf_xdp_ct_alloc(struct xdp_md *xdp_ctx, struct bpf_sock_tuple *bpf_tuple,
@@ -279,7 +321,7 @@ bpf_xdp_ct_alloc(struct xdp_md *xdp_ctx, struct bpf_sock_tuple *bpf_tuple,
  * @opts	- Additional options for lookup (documented above)
  *		    Cannot be NULL
  * @opts__sz	- Length of the bpf_ct_opts structure
- *		    Must be NF_BPF_CT_OPTS_SZ (12)
+ *		    Must be NF_BPF_CT_OPTS_SZ (16) or 12
  */
 __bpf_kfunc struct nf_conn *
 bpf_xdp_ct_lookup(struct xdp_md *xdp_ctx, struct bpf_sock_tuple *bpf_tuple,
@@ -312,7 +354,7 @@ bpf_xdp_ct_lookup(struct xdp_md *xdp_ctx, struct bpf_sock_tuple *bpf_tuple,
  * @opts	- Additional options for allocation (documented above)
  *		    Cannot be NULL
  * @opts__sz	- Length of the bpf_ct_opts structure
- *		    Must be NF_BPF_CT_OPTS_SZ (12)
+ *		    Must be NF_BPF_CT_OPTS_SZ (16) or 12
  */
 __bpf_kfunc struct nf_conn___init *
 bpf_skb_ct_alloc(struct __sk_buff *skb_ctx, struct bpf_sock_tuple *bpf_tuple,
@@ -347,7 +389,7 @@ bpf_skb_ct_alloc(struct __sk_buff *skb_ctx, struct bpf_sock_tuple *bpf_tuple,
  * @opts	- Additional options for lookup (documented above)
  *		    Cannot be NULL
  * @opts__sz	- Length of the bpf_ct_opts structure
- *		    Must be NF_BPF_CT_OPTS_SZ (12)
+ *		    Must be NF_BPF_CT_OPTS_SZ (16) or 12
  */
 __bpf_kfunc struct nf_conn *
 bpf_skb_ct_lookup(struct __sk_buff *skb_ctx, struct bpf_sock_tuple *bpf_tuple,
-- 
GitLab


From a87f34e742d279d54d529e4bc4763fdaab32a466 Mon Sep 17 00:00:00 2001
From: Brad Cowie <brad@faucet.nz>
Date: Wed, 22 May 2024 17:07:12 +1200
Subject: [PATCH 093/950] selftests/bpf: Update tests for new ct zone opts for
 nf_conntrack kfuncs

Add test for allocating and looking up ct entry in a
non-default ct zone with kfuncs bpf_{xdp,skb}_ct_alloc
and bpf_{xdp,skb}_ct_lookup.

Add negative tests for looking up ct entry in a different
ct zone to where it was allocated and with a different
direction.

Update reserved test for old struct definition to test for
ct_zone_id being set when opts size isn't NF_BPF_CT_OPTS_SZ (16).

Signed-off-by: Brad Cowie <brad@faucet.nz>
Link: https://lore.kernel.org/r/20240522050712.732558-2-brad@faucet.nz
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/testing/selftests/bpf/config            |   1 +
 .../testing/selftests/bpf/prog_tests/bpf_nf.c |   7 ++
 .../testing/selftests/bpf/progs/test_bpf_nf.c | 108 ++++++++++++++++++
 3 files changed, 116 insertions(+)

diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config
index eeabd798bc3ae..2fb16da78dce8 100644
--- a/tools/testing/selftests/bpf/config
+++ b/tools/testing/selftests/bpf/config
@@ -80,6 +80,7 @@ CONFIG_NETFILTER_XT_TARGET_CT=y
 CONFIG_NETKIT=y
 CONFIG_NF_CONNTRACK=y
 CONFIG_NF_CONNTRACK_MARK=y
+CONFIG_NF_CONNTRACK_ZONES=y
 CONFIG_NF_DEFRAG_IPV4=y
 CONFIG_NF_DEFRAG_IPV6=y
 CONFIG_NF_NAT=y
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_nf.c b/tools/testing/selftests/bpf/prog_tests/bpf_nf.c
index b30ff6b3b81ae..a4a1f93878d40 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_nf.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_nf.c
@@ -104,6 +104,7 @@ static void test_bpf_nf_ct(int mode)
 
 	ASSERT_EQ(skel->bss->test_einval_bpf_tuple, -EINVAL, "Test EINVAL for NULL bpf_tuple");
 	ASSERT_EQ(skel->bss->test_einval_reserved, -EINVAL, "Test EINVAL for reserved not set to 0");
+	ASSERT_EQ(skel->bss->test_einval_reserved_new, -EINVAL, "Test EINVAL for reserved in new struct not set to 0");
 	ASSERT_EQ(skel->bss->test_einval_netns_id, -EINVAL, "Test EINVAL for netns_id < -1");
 	ASSERT_EQ(skel->bss->test_einval_len_opts, -EINVAL, "Test EINVAL for len__opts != NF_BPF_CT_OPTS_SZ");
 	ASSERT_EQ(skel->bss->test_eproto_l4proto, -EPROTO, "Test EPROTO for l4proto != TCP or UDP");
@@ -122,6 +123,12 @@ static void test_bpf_nf_ct(int mode)
 	ASSERT_EQ(skel->bss->test_exist_lookup_mark, 43, "Test existing connection lookup ctmark");
 	ASSERT_EQ(skel->data->test_snat_addr, 0, "Test for source natting");
 	ASSERT_EQ(skel->data->test_dnat_addr, 0, "Test for destination natting");
+	ASSERT_EQ(skel->data->test_ct_zone_id_alloc_entry, 0, "Test for alloc new entry in specified ct zone");
+	ASSERT_EQ(skel->data->test_ct_zone_id_insert_entry, 0, "Test for insert new entry in specified ct zone");
+	ASSERT_EQ(skel->data->test_ct_zone_id_succ_lookup, 0, "Test for successful lookup in specified ct_zone");
+	ASSERT_EQ(skel->bss->test_ct_zone_dir_enoent_lookup, -ENOENT, "Test ENOENT for lookup with wrong ct zone dir");
+	ASSERT_EQ(skel->bss->test_ct_zone_id_enoent_lookup, -ENOENT, "Test ENOENT for lookup in wrong ct zone");
+
 end:
 	if (client_fd != -1)
 		close(client_fd);
diff --git a/tools/testing/selftests/bpf/progs/test_bpf_nf.c b/tools/testing/selftests/bpf/progs/test_bpf_nf.c
index 77ad8adf68daa..0289d8ce2b80d 100644
--- a/tools/testing/selftests/bpf/progs/test_bpf_nf.c
+++ b/tools/testing/selftests/bpf/progs/test_bpf_nf.c
@@ -9,10 +9,14 @@
 #define EINVAL 22
 #define ENOENT 2
 
+#define NF_CT_ZONE_DIR_ORIG (1 << IP_CT_DIR_ORIGINAL)
+#define NF_CT_ZONE_DIR_REPL (1 << IP_CT_DIR_REPLY)
+
 extern unsigned long CONFIG_HZ __kconfig;
 
 int test_einval_bpf_tuple = 0;
 int test_einval_reserved = 0;
+int test_einval_reserved_new = 0;
 int test_einval_netns_id = 0;
 int test_einval_len_opts = 0;
 int test_eproto_l4proto = 0;
@@ -22,6 +26,11 @@ int test_eafnosupport = 0;
 int test_alloc_entry = -EINVAL;
 int test_insert_entry = -EAFNOSUPPORT;
 int test_succ_lookup = -ENOENT;
+int test_ct_zone_id_alloc_entry = -EINVAL;
+int test_ct_zone_id_insert_entry = -EAFNOSUPPORT;
+int test_ct_zone_id_succ_lookup = -ENOENT;
+int test_ct_zone_dir_enoent_lookup = 0;
+int test_ct_zone_id_enoent_lookup = 0;
 u32 test_delta_timeout = 0;
 u32 test_status = 0;
 u32 test_insert_lookup_mark = 0;
@@ -45,6 +54,17 @@ struct bpf_ct_opts___local {
 	s32 netns_id;
 	s32 error;
 	u8 l4proto;
+	u8 dir;
+	u8 reserved[2];
+};
+
+struct bpf_ct_opts___new {
+	s32 netns_id;
+	s32 error;
+	u8 l4proto;
+	u8 dir;
+	u16 ct_zone_id;
+	u8 ct_zone_dir;
 	u8 reserved[3];
 } __attribute__((preserve_access_index));
 
@@ -220,10 +240,97 @@ nf_ct_test(struct nf_conn *(*lookup_fn)(void *, struct bpf_sock_tuple *, u32,
 	}
 }
 
+static __always_inline void
+nf_ct_opts_new_test(struct nf_conn *(*lookup_fn)(void *, struct bpf_sock_tuple *, u32,
+						 struct bpf_ct_opts___new *, u32),
+		    struct nf_conn *(*alloc_fn)(void *, struct bpf_sock_tuple *, u32,
+						struct bpf_ct_opts___new *, u32),
+		    void *ctx)
+{
+	struct bpf_ct_opts___new opts_def = { .l4proto = IPPROTO_TCP, .netns_id = -1 };
+	struct bpf_sock_tuple bpf_tuple;
+	struct nf_conn *ct;
+
+	__builtin_memset(&bpf_tuple, 0, sizeof(bpf_tuple.ipv4));
+
+	opts_def.reserved[0] = 1;
+	ct = lookup_fn(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def,
+		       sizeof(opts_def));
+	opts_def.reserved[0] = 0;
+	if (ct)
+		bpf_ct_release(ct);
+	else
+		test_einval_reserved_new = opts_def.error;
+
+	bpf_tuple.ipv4.saddr = bpf_get_prandom_u32(); /* src IP */
+	bpf_tuple.ipv4.daddr = bpf_get_prandom_u32(); /* dst IP */
+	bpf_tuple.ipv4.sport = bpf_get_prandom_u32(); /* src port */
+	bpf_tuple.ipv4.dport = bpf_get_prandom_u32(); /* dst port */
+
+	/* use non-default ct zone */
+	opts_def.ct_zone_id = 10;
+	opts_def.ct_zone_dir = NF_CT_ZONE_DIR_ORIG;
+	ct = alloc_fn(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def,
+		      sizeof(opts_def));
+	if (ct) {
+		__u16 sport = bpf_get_prandom_u32();
+		__u16 dport = bpf_get_prandom_u32();
+		union nf_inet_addr saddr = {};
+		union nf_inet_addr daddr = {};
+		struct nf_conn *ct_ins;
+
+		bpf_ct_set_timeout(ct, 10000);
+
+		/* snat */
+		saddr.ip = bpf_get_prandom_u32();
+		bpf_ct_set_nat_info(ct, &saddr, sport, NF_NAT_MANIP_SRC___local);
+		/* dnat */
+		daddr.ip = bpf_get_prandom_u32();
+		bpf_ct_set_nat_info(ct, &daddr, dport, NF_NAT_MANIP_DST___local);
+
+		ct_ins = bpf_ct_insert_entry(ct);
+		if (ct_ins) {
+			struct nf_conn *ct_lk;
+
+			/* entry should exist in same ct zone we inserted it */
+			ct_lk = lookup_fn(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4),
+					  &opts_def, sizeof(opts_def));
+			if (ct_lk) {
+				bpf_ct_release(ct_lk);
+				test_ct_zone_id_succ_lookup = 0;
+			}
+
+			/* entry should not exist with wrong direction */
+			opts_def.ct_zone_dir = NF_CT_ZONE_DIR_REPL;
+			ct_lk = lookup_fn(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4),
+					  &opts_def, sizeof(opts_def));
+			opts_def.ct_zone_dir = NF_CT_ZONE_DIR_ORIG;
+			if (ct_lk)
+				bpf_ct_release(ct_lk);
+			else
+				test_ct_zone_dir_enoent_lookup = opts_def.error;
+
+			/* entry should not exist in default ct zone */
+			opts_def.ct_zone_id = 0;
+			ct_lk = lookup_fn(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4),
+					  &opts_def, sizeof(opts_def));
+			if (ct_lk)
+				bpf_ct_release(ct_lk);
+			else
+				test_ct_zone_id_enoent_lookup = opts_def.error;
+
+			bpf_ct_release(ct_ins);
+			test_ct_zone_id_insert_entry = 0;
+		}
+		test_ct_zone_id_alloc_entry = 0;
+	}
+}
+
 SEC("xdp")
 int nf_xdp_ct_test(struct xdp_md *ctx)
 {
 	nf_ct_test((void *)bpf_xdp_ct_lookup, (void *)bpf_xdp_ct_alloc, ctx);
+	nf_ct_opts_new_test((void *)bpf_xdp_ct_lookup, (void *)bpf_xdp_ct_alloc, ctx);
 	return 0;
 }
 
@@ -231,6 +338,7 @@ SEC("tc")
 int nf_skb_ct_test(struct __sk_buff *ctx)
 {
 	nf_ct_test((void *)bpf_skb_ct_lookup, (void *)bpf_skb_ct_alloc, ctx);
+	nf_ct_opts_new_test((void *)bpf_skb_ct_lookup, (void *)bpf_skb_ct_alloc, ctx);
 	return 0;
 }
 
-- 
GitLab


From 669b692247d4516e252c898c0e7366a09d84d1be Mon Sep 17 00:00:00 2001
From: Po-Hao Huang <phhuang@realtek.com>
Date: Fri, 17 May 2024 09:33:50 +0800
Subject: [PATCH 094/950] wifi: rtw89: fix HW scan not aborting properly

There is a length limit on the commands we send to firmware, so
dividing to two commands is sometimes required when scanning.
When aborting scan, we should not send second scan command to
firmware after the first one is finished. This could cause some
unexpected errors when we cannot receive firmware events
(e.g. in suspend).

Another case is scan happens before suspending, ieee80211_do_stop() is
called to abort scan and driver indicate scan completion by
ieee80211_scan_completed(), which queues event to scan work. But scan work
might be late to execute after ieee80211_do_stop(). To correct this, driver
indicates ieee80211_scan_completed() before returning, so that
ieee80211_do_stop() can flush scan work properly.

Fixes: bcbefbd032df ("wifi: rtw89: add wait/completion for abort scan")
Cc: stable@vger.kernel.org
Co-developed-by: Chih-Kang Chang <gary.chang@realtek.com>
Signed-off-by: Chih-Kang Chang <gary.chang@realtek.com>
Signed-off-by: Po-Hao Huang <phhuang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://msgid.link/20240517013350.11278-1-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/fw.c  | 9 ++++++++-
 drivers/net/wireless/realtek/rtw89/mac.c | 5 ++++-
 2 files changed, 12 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index 044a5b90c7f4e..f5cd06c35982e 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -6245,7 +6245,14 @@ void rtw89_hw_scan_abort(struct rtw89_dev *rtwdev, struct ieee80211_vif *vif)
 
 	ret = rtw89_hw_scan_offload(rtwdev, vif, false);
 	if (ret)
-		rtw89_hw_scan_complete(rtwdev, vif, true);
+		rtw89_warn(rtwdev, "rtw89_hw_scan_offload failed ret %d\n", ret);
+
+	/* Indicate ieee80211_scan_completed() before returning, which is safe
+	 * because scan abort command always waits for completion of
+	 * RTW89_SCAN_END_SCAN_NOTIFY, so that ieee80211_stop() can flush scan
+	 * work properly.
+	 */
+	rtw89_hw_scan_complete(rtwdev, vif, true);
 }
 
 static bool rtw89_is_any_vif_connected_or_connecting(struct rtw89_dev *rtwdev)
diff --git a/drivers/net/wireless/realtek/rtw89/mac.c b/drivers/net/wireless/realtek/rtw89/mac.c
index baefc30b88c4d..824ece03d92d2 100644
--- a/drivers/net/wireless/realtek/rtw89/mac.c
+++ b/drivers/net/wireless/realtek/rtw89/mac.c
@@ -4756,6 +4756,9 @@ rtw89_mac_c2h_scanofld_rsp(struct rtw89_dev *rtwdev, struct sk_buff *skb,
 		}
 		return;
 	case RTW89_SCAN_END_SCAN_NOTIFY:
+		if (rtwdev->scan_info.abort)
+			return;
+
 		if (rtwvif && rtwvif->scan_req &&
 		    last_chan < rtwvif->scan_req->n_channels) {
 			ret = rtw89_hw_scan_offload(rtwdev, vif, true);
@@ -4764,7 +4767,7 @@ rtw89_mac_c2h_scanofld_rsp(struct rtw89_dev *rtwdev, struct sk_buff *skb,
 				rtw89_warn(rtwdev, "HW scan failed: %d\n", ret);
 			}
 		} else {
-			rtw89_hw_scan_complete(rtwdev, vif, rtwdev->scan_info.abort);
+			rtw89_hw_scan_complete(rtwdev, vif, false);
 		}
 		break;
 	case RTW89_SCAN_ENTER_OP_NOTIFY:
-- 
GitLab


From 2c1fc7c24cd47396580c5a7b238673da618aeedd Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Fri, 17 May 2024 09:35:43 +0800
Subject: [PATCH 095/950] wifi: rtw89: 8852b: restore setting for RFE type 5
 after device resume

The RFE type 5 set SPS analog parameters only once at probe stage, but the
setting is missing after suspend/resume, so remove restriction and set the
value when card power on/off.

Fixes: 3ef60f44830a ("wifi: rtw89: 8852b: update hardware parameters for RFE type 5")
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://msgid.link/20240517013543.11533-1-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/rtw8852b.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852b.c b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
index 53ae00b5ab7cc..517ad1a763fa4 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
@@ -403,6 +403,8 @@ static int rtw8852b_pwr_on_func(struct rtw89_dev *rtwdev)
 	u32 val32;
 	u32 ret;
 
+	rtw8852b_pwr_sps_ana(rtwdev);
+
 	rtw89_write32_clr(rtwdev, R_AX_SYS_PW_CTRL, B_AX_AFSM_WLSUS_EN |
 						    B_AX_AFSM_PCIE_SUS_EN);
 	rtw89_write32_set(rtwdev, R_AX_SYS_PW_CTRL, B_AX_DIS_WLBT_PDNSUSEN_SOPC);
@@ -530,9 +532,7 @@ static int rtw8852b_pwr_off_func(struct rtw89_dev *rtwdev)
 	u32 val32;
 	u32 ret;
 
-	/* Only do once during probe stage after reading efuse */
-	if (!test_bit(RTW89_FLAG_PROBE_DONE, rtwdev->flags))
-		rtw8852b_pwr_sps_ana(rtwdev);
+	rtw8852b_pwr_sps_ana(rtwdev);
 
 	ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_ANAPAR_WL, XTAL_SI_RFC2RF,
 				      XTAL_SI_RFC2RF);
-- 
GitLab


From d5b96a4a31593a609acd564cfa54f269461a33f0 Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Fri, 17 May 2024 09:36:39 +0800
Subject: [PATCH 096/950] wifi: rtw89: correct hardware value of nominal packet
 padding for WiFi 7 chips

The hardware value of 3 for WiFi 7 chips is padding 16 or 20us selected
by hardware automatically. Correct the value to resolve interoperability
problem. Also define enum to be more readable.

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://msgid.link/20240517013639.11643-1-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.h |  7 +++++++
 drivers/net/wireless/realtek/rtw89/fw.c   | 12 ++++++------
 2 files changed, 13 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index c0f2afb4888a9..523ea9f5e6b19 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -884,6 +884,13 @@ enum rtw89_ps_mode {
 #define RTW89_BYR_BW_NUM (RTW89_CHANNEL_WIDTH_320 + 1)
 #define RTW89_PPE_BW_NUM (RTW89_CHANNEL_WIDTH_320 + 1)
 
+enum rtw89_pe_duration {
+	RTW89_PE_DURATION_0 = 0,
+	RTW89_PE_DURATION_8 = 1,
+	RTW89_PE_DURATION_16 = 2,
+	RTW89_PE_DURATION_16_20 = 3,
+};
+
 enum rtw89_ru_bandwidth {
 	RTW89_RU26 = 0,
 	RTW89_RU52 = 1,
diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index f5cd06c35982e..1ea2b662fc89c 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -2752,11 +2752,11 @@ static void __get_sta_he_pkt_padding(struct rtw89_dev *rtwdev,
 		ppe8 = (ppe >> sh) & IEEE80211_PPE_THRES_NSS_MASK;
 
 		if (ppe16 != 7 && ppe8 == 7)
-			pads[i] = 2;
+			pads[i] = RTW89_PE_DURATION_16;
 		else if (ppe8 != 7)
-			pads[i] = 1;
+			pads[i] = RTW89_PE_DURATION_8;
 		else
-			pads[i] = 0;
+			pads[i] = RTW89_PE_DURATION_0;
 	}
 }
 
@@ -2889,11 +2889,11 @@ static void __get_sta_eht_pkt_padding(struct rtw89_dev *rtwdev,
 		ppe8 = (ppe >> sh) & IEEE80211_PPE_THRES_NSS_MASK;
 
 		if (ppe16 != 7 && ppe8 == 7)
-			pads[i] = 2;
+			pads[i] = RTW89_PE_DURATION_16_20;
 		else if (ppe8 != 7)
-			pads[i] = 1;
+			pads[i] = RTW89_PE_DURATION_8;
 		else
-			pads[i] = 0;
+			pads[i] = RTW89_PE_DURATION_0;
 	}
 }
 
-- 
GitLab


From 5134acb15d9ef27aa2b90aad46d4e89fcef79fdc Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Wed, 22 May 2024 10:32:43 -0700
Subject: [PATCH 097/950] efi/libstub: zboot.lds: Discard .discard sections

When building ARCH=loongarch defconfig + CONFIG_UNWINDER_ORC=y using
LLVM, there is a warning from ld.lld when linking the EFI zboot image
due to the use of unreachable() in number() in vsprintf.c:

  ld.lld: warning: drivers/firmware/efi/libstub/lib.a(vsprintf.stub.o):(.discard.unreachable+0x0): has non-ABS relocation R_LARCH_32_PCREL against symbol ''

If the compiler cannot eliminate the default case for any reason, the
.discard.unreachable section will remain in the final binary but the
entire point of any section prefixed with .discard is that it is only
used at compile time, so it can be discarded via /DISCARD/ in a linker
script. The asm-generic vmlinux.lds.h includes .discard and .discard.*
in the COMMON_DISCARDS macro but that is not used for zboot.lds, as it
is not a kernel image linker script.

Add .discard and .discard.* to /DISCARD/ in zboot.lds, so that any
sections meant to be discarded at link time are not included in the
final zboot image. This issue is not specific to LoongArch, it is just
the first architecture to select CONFIG_OBJTOOL, which defines
annotate_unreachable() as an asm statement to add the
.discard.unreachable section, and use the EFI stub.

Closes: https://github.com/ClangBuiltLinux/linux/issues/2023
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Acked-by: Huacai Chen <chenhuacai@loongson.cn>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 drivers/firmware/efi/libstub/zboot.lds | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/firmware/efi/libstub/zboot.lds b/drivers/firmware/efi/libstub/zboot.lds
index ac8c0ef851581..af2c82f7bd902 100644
--- a/drivers/firmware/efi/libstub/zboot.lds
+++ b/drivers/firmware/efi/libstub/zboot.lds
@@ -41,6 +41,7 @@ SECTIONS
 	}
 
 	/DISCARD/ : {
+		*(.discard .discard.*)
 		*(.modinfo .init.modinfo)
 	}
 }
-- 
GitLab


From 7c23b186ab892088f76a3ad9dbff1685ffe2e832 Mon Sep 17 00:00:00 2001
From: "Guilherme G. Piccoli" <gpiccoli@igalia.com>
Date: Sun, 19 May 2024 13:33:53 -0300
Subject: [PATCH 098/950] efi: pstore: Return proper errors on UEFI failures

Right now efi-pstore either returns 0 (success) or -EIO; but we
do have a function to convert UEFI errors in different standard
error codes, helping to narrow down potential issues more accurately.

So, let's use this helper here.

Signed-off-by: Guilherme G. Piccoli <gpiccoli@igalia.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 drivers/firmware/efi/efi-pstore.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/firmware/efi/efi-pstore.c b/drivers/firmware/efi/efi-pstore.c
index 5b9dc26e6bcb9..552c78f5f0590 100644
--- a/drivers/firmware/efi/efi-pstore.c
+++ b/drivers/firmware/efi/efi-pstore.c
@@ -136,7 +136,7 @@ static int efi_pstore_read_func(struct pstore_record *record,
 				     &size, record->buf);
 	if (status != EFI_SUCCESS) {
 		kfree(record->buf);
-		return -EIO;
+		return efi_status_to_err(status);
 	}
 
 	/*
@@ -189,7 +189,7 @@ static ssize_t efi_pstore_read(struct pstore_record *record)
 			return 0;
 
 		if (status != EFI_SUCCESS)
-			return -EIO;
+			return efi_status_to_err(status);
 
 		/* skip variables that don't concern us */
 		if (efi_guidcmp(guid, LINUX_EFI_CRASH_GUID))
@@ -227,7 +227,7 @@ static int efi_pstore_write(struct pstore_record *record)
 					    record->size, record->psi->buf,
 					    true);
 	efivar_unlock();
-	return status == EFI_SUCCESS ? 0 : -EIO;
+	return efi_status_to_err(status);
 };
 
 static int efi_pstore_erase(struct pstore_record *record)
@@ -238,7 +238,7 @@ static int efi_pstore_erase(struct pstore_record *record)
 				     PSTORE_EFI_ATTRIBUTES, 0, NULL);
 
 	if (status != EFI_SUCCESS && status != EFI_NOT_FOUND)
-		return -EIO;
+		return efi_status_to_err(status);
 	return 0;
 }
 
-- 
GitLab


From 5716146295183651cfd89ae2ea46c5ef0d31faa8 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 15 May 2024 09:38:35 +0200
Subject: [PATCH 099/950] wifi: regulatory: remove extra documentation

The struct member country_ie_checksum doesn't exist, so
don't document it.

Link: https://msgid.link/20240515093852.ebcc9673558b.Ie0b58c1249c6375c60859fa6474d7cdd8862b065@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/regulatory.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/include/net/regulatory.h b/include/net/regulatory.h
index ebf9e028d1ef9..a103f4c8cf756 100644
--- a/include/net/regulatory.h
+++ b/include/net/regulatory.h
@@ -71,8 +71,6 @@ enum environment_cap {
  *	CRDA and can be used by other regulatory requests. When a
  *	the last request is not yet processed we must yield until it
  *	is processed before processing any new requests.
- * @country_ie_checksum: checksum of the last processed and accepted
- *	country IE
  * @country_ie_env: lets us know if the AP is telling us we are outdoor,
  *	indoor, or if it doesn't matter
  * @list: used to insert into the reg_requests_list linked list
-- 
GitLab


From 3bb8dce41c023e39ec4d79a83742403b5064a276 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 15 May 2024 09:38:36 +0200
Subject: [PATCH 100/950] wifi: ieee80211: add missing doc short descriptions

Some structures erroneously don't have a short description,
add the missing descriptions.

Link: https://msgid.link/20240515093852.16f4355e918e.I940276a4fb006ada68ab1a3e6077e3229fff0f14@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index de2dce743ee2c..713266ce48a71 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -1101,7 +1101,7 @@ enum ieee80211_vht_opmode_bits {
 };
 
 /**
- * enum ieee80211_s1g_chanwidth
+ * enum ieee80211_s1g_chanwidth - S1G channel widths
  * These are defined in IEEE802.11-2016ah Table 10-20
  * as BSS Channel Width
  *
@@ -4145,7 +4145,7 @@ enum ieee80211_idle_options {
 };
 
 /**
- * struct ieee80211_bss_max_idle_period_ie
+ * struct ieee80211_bss_max_idle_period_ie - BSS max idle period element struct
  *
  * This structure refers to "BSS Max idle period element"
  *
@@ -4180,7 +4180,7 @@ enum ieee80211_sa_query_action {
 };
 
 /**
- * struct ieee80211_bssid_index
+ * struct ieee80211_bssid_index - multiple BSSID index element structure
  *
  * This structure refers to "Multiple BSSID-index element"
  *
@@ -4195,7 +4195,8 @@ struct ieee80211_bssid_index {
 };
 
 /**
- * struct ieee80211_multiple_bssid_configuration
+ * struct ieee80211_multiple_bssid_configuration - multiple BSSID configuration
+ *	element structure
  *
  * This structure refers to "Multiple BSSID Configuration element"
  *
-- 
GitLab


From 1c26f09b20bafc92e0de80e84942be77d4d3c61e Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 15 May 2024 09:38:37 +0200
Subject: [PATCH 101/950] wifi: radiotap: document ieee80211_get_radiotap_len()
 return value

Document the return value of ieee80211_get_radiotap_len() in
the proper kernel-doc format.

Link: https://msgid.link/20240515093852.143aadfdb094.I8795ec1e8cfd7106d58325fb514bae92625fb45c@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/ieee80211_radiotap.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/include/net/ieee80211_radiotap.h b/include/net/ieee80211_radiotap.h
index 925bac726a92b..91762faecc13d 100644
--- a/include/net/ieee80211_radiotap.h
+++ b/include/net/ieee80211_radiotap.h
@@ -582,6 +582,7 @@ enum ieee80211_radiotap_eht_usig_tb {
 /**
  * ieee80211_get_radiotap_len - get radiotap header length
  * @data: pointer to the header
+ * Return: the radiotap header length
  */
 static inline u16 ieee80211_get_radiotap_len(const char *data)
 {
-- 
GitLab


From 54856871298c9a8717450351699a8e6fe706101c Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 15 May 2024 09:38:38 +0200
Subject: [PATCH 102/950] wifi: ieee80211: remove ieee80211_next_tbtt_present()

This is actually completely equivalent to the other function
ieee80211_is_s1g_short_beacon(), but open-codes the logic.
Implement the necessary logic in ieee80211_is_s1g_short_beacon()
and remove ieee80211_next_tbtt_present().

Link: https://msgid.link/20240515093852.774ced74dea8.I152525b4cff6e6a25be6c48fe6a4b89f17bab8a9@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h | 20 +++++---------------
 1 file changed, 5 insertions(+), 15 deletions(-)

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 713266ce48a71..72b351abb4f67 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -604,25 +604,15 @@ static inline bool ieee80211_is_s1g_beacon(__le16 fc)
 }
 
 /**
- * ieee80211_next_tbtt_present - check if IEEE80211_FTYPE_EXT &&
- * IEEE80211_STYPE_S1G_BEACON && IEEE80211_S1G_BCN_NEXT_TBTT
- * @fc: frame control bytes in little-endian byteorder
- */
-static inline bool ieee80211_next_tbtt_present(__le16 fc)
-{
-	return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) ==
-	       cpu_to_le16(IEEE80211_FTYPE_EXT | IEEE80211_STYPE_S1G_BEACON) &&
-	       fc & cpu_to_le16(IEEE80211_S1G_BCN_NEXT_TBTT);
-}
-
-/**
- * ieee80211_is_s1g_short_beacon - check if next tbtt present bit is set. Only
- * true for S1G beacons when they're short.
+ * ieee80211_is_s1g_short_beacon - check if frame is an S1G short beacon
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is an S1G short beacon,
+ *	i.e. it is an S1G beacon with 'next TBTT' flag set
  */
 static inline bool ieee80211_is_s1g_short_beacon(__le16 fc)
 {
-	return ieee80211_is_s1g_beacon(fc) && ieee80211_next_tbtt_present(fc);
+	return ieee80211_is_s1g_beacon(fc) &&
+		(fc & cpu_to_le16(IEEE80211_S1G_BCN_NEXT_TBTT));
 }
 
 /**
-- 
GitLab


From 3c75e99c7036a87f159dbd526060554afb3482f5 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 15 May 2024 09:38:39 +0200
Subject: [PATCH 103/950] wifi: ieee80211: document function return values

These are all missing, as pointed out when running kernel-doc.
Add return value documentation and fix some small things while
at it.

Link: https://msgid.link/20240515093852.1cd5ad8f354d.Idc16e9767fa42de80b659c32efc58aea38c26996@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h | 106 ++++++++++++++++++++++++++++++--------
 1 file changed, 84 insertions(+), 22 deletions(-)

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 72b351abb4f67..595f83783f0e9 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -373,6 +373,7 @@ struct ieee80211_trigger {
 /**
  * ieee80211_has_tods - check if IEEE80211_FCTL_TODS is set
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame has to-DS set
  */
 static inline bool ieee80211_has_tods(__le16 fc)
 {
@@ -382,6 +383,7 @@ static inline bool ieee80211_has_tods(__le16 fc)
 /**
  * ieee80211_has_fromds - check if IEEE80211_FCTL_FROMDS is set
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame has from-DS set
  */
 static inline bool ieee80211_has_fromds(__le16 fc)
 {
@@ -391,6 +393,7 @@ static inline bool ieee80211_has_fromds(__le16 fc)
 /**
  * ieee80211_has_a4 - check if IEEE80211_FCTL_TODS and IEEE80211_FCTL_FROMDS are set
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not it's a 4-address frame (from-DS and to-DS set)
  */
 static inline bool ieee80211_has_a4(__le16 fc)
 {
@@ -401,6 +404,7 @@ static inline bool ieee80211_has_a4(__le16 fc)
 /**
  * ieee80211_has_morefrags - check if IEEE80211_FCTL_MOREFRAGS is set
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame has more fragments (more frags bit set)
  */
 static inline bool ieee80211_has_morefrags(__le16 fc)
 {
@@ -410,6 +414,7 @@ static inline bool ieee80211_has_morefrags(__le16 fc)
 /**
  * ieee80211_has_retry - check if IEEE80211_FCTL_RETRY is set
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the retry flag is set
  */
 static inline bool ieee80211_has_retry(__le16 fc)
 {
@@ -419,6 +424,7 @@ static inline bool ieee80211_has_retry(__le16 fc)
 /**
  * ieee80211_has_pm - check if IEEE80211_FCTL_PM is set
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the power management flag is set
  */
 static inline bool ieee80211_has_pm(__le16 fc)
 {
@@ -428,6 +434,7 @@ static inline bool ieee80211_has_pm(__le16 fc)
 /**
  * ieee80211_has_moredata - check if IEEE80211_FCTL_MOREDATA is set
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the more data flag is set
  */
 static inline bool ieee80211_has_moredata(__le16 fc)
 {
@@ -437,6 +444,7 @@ static inline bool ieee80211_has_moredata(__le16 fc)
 /**
  * ieee80211_has_protected - check if IEEE80211_FCTL_PROTECTED is set
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the protected flag is set
  */
 static inline bool ieee80211_has_protected(__le16 fc)
 {
@@ -446,6 +454,7 @@ static inline bool ieee80211_has_protected(__le16 fc)
 /**
  * ieee80211_has_order - check if IEEE80211_FCTL_ORDER is set
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the order flag is set
  */
 static inline bool ieee80211_has_order(__le16 fc)
 {
@@ -455,6 +464,7 @@ static inline bool ieee80211_has_order(__le16 fc)
 /**
  * ieee80211_is_mgmt - check if type is IEEE80211_FTYPE_MGMT
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame type is management
  */
 static inline bool ieee80211_is_mgmt(__le16 fc)
 {
@@ -465,6 +475,7 @@ static inline bool ieee80211_is_mgmt(__le16 fc)
 /**
  * ieee80211_is_ctl - check if type is IEEE80211_FTYPE_CTL
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame type is control
  */
 static inline bool ieee80211_is_ctl(__le16 fc)
 {
@@ -475,6 +486,7 @@ static inline bool ieee80211_is_ctl(__le16 fc)
 /**
  * ieee80211_is_data - check if type is IEEE80211_FTYPE_DATA
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is a data frame
  */
 static inline bool ieee80211_is_data(__le16 fc)
 {
@@ -485,6 +497,7 @@ static inline bool ieee80211_is_data(__le16 fc)
 /**
  * ieee80211_is_ext - check if type is IEEE80211_FTYPE_EXT
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame type is extended
  */
 static inline bool ieee80211_is_ext(__le16 fc)
 {
@@ -496,6 +509,7 @@ static inline bool ieee80211_is_ext(__le16 fc)
 /**
  * ieee80211_is_data_qos - check if type is IEEE80211_FTYPE_DATA and IEEE80211_STYPE_QOS_DATA is set
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is a QoS data frame
  */
 static inline bool ieee80211_is_data_qos(__le16 fc)
 {
@@ -510,6 +524,8 @@ static inline bool ieee80211_is_data_qos(__le16 fc)
 /**
  * ieee80211_is_data_present - check if type is IEEE80211_FTYPE_DATA and has data
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is a QoS data frame that has data
+ *	(i.e. is not null data)
  */
 static inline bool ieee80211_is_data_present(__le16 fc)
 {
@@ -524,6 +540,7 @@ static inline bool ieee80211_is_data_present(__le16 fc)
 /**
  * ieee80211_is_assoc_req - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_ASSOC_REQ
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is an association request
  */
 static inline bool ieee80211_is_assoc_req(__le16 fc)
 {
@@ -534,6 +551,7 @@ static inline bool ieee80211_is_assoc_req(__le16 fc)
 /**
  * ieee80211_is_assoc_resp - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_ASSOC_RESP
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is an association response
  */
 static inline bool ieee80211_is_assoc_resp(__le16 fc)
 {
@@ -544,6 +562,7 @@ static inline bool ieee80211_is_assoc_resp(__le16 fc)
 /**
  * ieee80211_is_reassoc_req - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_REASSOC_REQ
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is a reassociation request
  */
 static inline bool ieee80211_is_reassoc_req(__le16 fc)
 {
@@ -554,6 +573,7 @@ static inline bool ieee80211_is_reassoc_req(__le16 fc)
 /**
  * ieee80211_is_reassoc_resp - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_REASSOC_RESP
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is a reassociation response
  */
 static inline bool ieee80211_is_reassoc_resp(__le16 fc)
 {
@@ -564,6 +584,7 @@ static inline bool ieee80211_is_reassoc_resp(__le16 fc)
 /**
  * ieee80211_is_probe_req - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_PROBE_REQ
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is a probe request
  */
 static inline bool ieee80211_is_probe_req(__le16 fc)
 {
@@ -574,6 +595,7 @@ static inline bool ieee80211_is_probe_req(__le16 fc)
 /**
  * ieee80211_is_probe_resp - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_PROBE_RESP
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is a probe response
  */
 static inline bool ieee80211_is_probe_resp(__le16 fc)
 {
@@ -584,6 +606,7 @@ static inline bool ieee80211_is_probe_resp(__le16 fc)
 /**
  * ieee80211_is_beacon - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_BEACON
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is a (regular, not S1G) beacon
  */
 static inline bool ieee80211_is_beacon(__le16 fc)
 {
@@ -595,6 +618,7 @@ static inline bool ieee80211_is_beacon(__le16 fc)
  * ieee80211_is_s1g_beacon - check if IEEE80211_FTYPE_EXT &&
  * IEEE80211_STYPE_S1G_BEACON
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is an S1G beacon
  */
 static inline bool ieee80211_is_s1g_beacon(__le16 fc)
 {
@@ -618,6 +642,7 @@ static inline bool ieee80211_is_s1g_short_beacon(__le16 fc)
 /**
  * ieee80211_is_atim - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_ATIM
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is an ATIM frame
  */
 static inline bool ieee80211_is_atim(__le16 fc)
 {
@@ -628,6 +653,7 @@ static inline bool ieee80211_is_atim(__le16 fc)
 /**
  * ieee80211_is_disassoc - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_DISASSOC
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is a disassociation frame
  */
 static inline bool ieee80211_is_disassoc(__le16 fc)
 {
@@ -638,6 +664,7 @@ static inline bool ieee80211_is_disassoc(__le16 fc)
 /**
  * ieee80211_is_auth - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_AUTH
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is an authentication frame
  */
 static inline bool ieee80211_is_auth(__le16 fc)
 {
@@ -648,6 +675,7 @@ static inline bool ieee80211_is_auth(__le16 fc)
 /**
  * ieee80211_is_deauth - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_DEAUTH
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is a deauthentication frame
  */
 static inline bool ieee80211_is_deauth(__le16 fc)
 {
@@ -658,6 +686,7 @@ static inline bool ieee80211_is_deauth(__le16 fc)
 /**
  * ieee80211_is_action - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_ACTION
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is an action frame
  */
 static inline bool ieee80211_is_action(__le16 fc)
 {
@@ -668,6 +697,7 @@ static inline bool ieee80211_is_action(__le16 fc)
 /**
  * ieee80211_is_back_req - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_BACK_REQ
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is a block-ACK request frame
  */
 static inline bool ieee80211_is_back_req(__le16 fc)
 {
@@ -678,6 +708,7 @@ static inline bool ieee80211_is_back_req(__le16 fc)
 /**
  * ieee80211_is_back - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_BACK
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is a block-ACK frame
  */
 static inline bool ieee80211_is_back(__le16 fc)
 {
@@ -688,6 +719,7 @@ static inline bool ieee80211_is_back(__le16 fc)
 /**
  * ieee80211_is_pspoll - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_PSPOLL
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is a PS-poll frame
  */
 static inline bool ieee80211_is_pspoll(__le16 fc)
 {
@@ -698,6 +730,7 @@ static inline bool ieee80211_is_pspoll(__le16 fc)
 /**
  * ieee80211_is_rts - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_RTS
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is an RTS frame
  */
 static inline bool ieee80211_is_rts(__le16 fc)
 {
@@ -708,6 +741,7 @@ static inline bool ieee80211_is_rts(__le16 fc)
 /**
  * ieee80211_is_cts - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_CTS
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is a CTS frame
  */
 static inline bool ieee80211_is_cts(__le16 fc)
 {
@@ -718,6 +752,7 @@ static inline bool ieee80211_is_cts(__le16 fc)
 /**
  * ieee80211_is_ack - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_ACK
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is an ACK frame
  */
 static inline bool ieee80211_is_ack(__le16 fc)
 {
@@ -728,6 +763,7 @@ static inline bool ieee80211_is_ack(__le16 fc)
 /**
  * ieee80211_is_cfend - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_CFEND
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is a CF-end frame
  */
 static inline bool ieee80211_is_cfend(__le16 fc)
 {
@@ -738,6 +774,7 @@ static inline bool ieee80211_is_cfend(__le16 fc)
 /**
  * ieee80211_is_cfendack - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_CFENDACK
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is a CF-end-ack frame
  */
 static inline bool ieee80211_is_cfendack(__le16 fc)
 {
@@ -748,6 +785,7 @@ static inline bool ieee80211_is_cfendack(__le16 fc)
 /**
  * ieee80211_is_nullfunc - check if frame is a regular (non-QoS) nullfunc frame
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is a nullfunc frame
  */
 static inline bool ieee80211_is_nullfunc(__le16 fc)
 {
@@ -758,6 +796,7 @@ static inline bool ieee80211_is_nullfunc(__le16 fc)
 /**
  * ieee80211_is_qos_nullfunc - check if frame is a QoS nullfunc frame
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is a QoS nullfunc frame
  */
 static inline bool ieee80211_is_qos_nullfunc(__le16 fc)
 {
@@ -768,6 +807,7 @@ static inline bool ieee80211_is_qos_nullfunc(__le16 fc)
 /**
  * ieee80211_is_trigger - check if frame is trigger frame
  * @fc: frame control field in little-endian byteorder
+ * Return: whether or not the frame is a trigger frame
  */
 static inline bool ieee80211_is_trigger(__le16 fc)
 {
@@ -778,6 +818,7 @@ static inline bool ieee80211_is_trigger(__le16 fc)
 /**
  * ieee80211_is_any_nullfunc - check if frame is regular or QoS nullfunc frame
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is a nullfunc or QoS nullfunc frame
  */
 static inline bool ieee80211_is_any_nullfunc(__le16 fc)
 {
@@ -787,6 +828,8 @@ static inline bool ieee80211_is_any_nullfunc(__le16 fc)
 /**
  * ieee80211_is_first_frag - check if IEEE80211_SCTL_FRAG is not set
  * @seq_ctrl: frame sequence control bytes in little-endian byteorder
+ * Return: whether or not the frame is the first fragment (also true if
+ *	it's not fragmented at all)
  */
 static inline bool ieee80211_is_first_frag(__le16 seq_ctrl)
 {
@@ -796,6 +839,7 @@ static inline bool ieee80211_is_first_frag(__le16 seq_ctrl)
 /**
  * ieee80211_is_frag - check if a frame is a fragment
  * @hdr: 802.11 header of the frame
+ * Return: whether or not the frame is a fragment
  */
 static inline bool ieee80211_is_frag(struct ieee80211_hdr *hdr)
 {
@@ -2349,6 +2393,8 @@ struct ieee80211_eht_operation_info {
  * @max_vht_nss: current maximum NSS as advertised by the STA in
  *	operating mode notification, can be 0 in which case the
  *	capability data will be used to derive this (from MCS support)
+ * Return: The maximum NSS that can be used for the given bandwidth/MCS
+ *	combination
  *
  * Due to the VHT Extended NSS Bandwidth Support, the maximum NSS can
  * vary for a given BW/MCS. This function parses the data.
@@ -4317,6 +4363,7 @@ struct ieee80211_he_6ghz_capa {
 /**
  * ieee80211_get_qos_ctl - get pointer to qos control bytes
  * @hdr: the frame
+ * Return: a pointer to the QoS control field in the frame header
  *
  * The qos ctrl bytes come after the frame_control, duration, seq_num
  * and 3 or 4 addresses of length ETH_ALEN. Checks frame_control to choose
@@ -4339,6 +4386,7 @@ static inline u8 *ieee80211_get_qos_ctl(struct ieee80211_hdr *hdr)
 /**
  * ieee80211_get_tid - get qos TID
  * @hdr: the frame
+ * Return: the TID from the QoS control field
  */
 static inline u8 ieee80211_get_tid(struct ieee80211_hdr *hdr)
 {
@@ -4350,6 +4398,7 @@ static inline u8 ieee80211_get_tid(struct ieee80211_hdr *hdr)
 /**
  * ieee80211_get_SA - get pointer to SA
  * @hdr: the frame
+ * Return: a pointer to the source address (SA)
  *
  * Given an 802.11 frame, this function returns the offset
  * to the source address (SA). It does not verify that the
@@ -4369,6 +4418,7 @@ static inline u8 *ieee80211_get_SA(struct ieee80211_hdr *hdr)
 /**
  * ieee80211_get_DA - get pointer to DA
  * @hdr: the frame
+ * Return: a pointer to the destination address (DA)
  *
  * Given an 802.11 frame, this function returns the offset
  * to the destination address (DA). It does not verify that
@@ -4387,6 +4437,7 @@ static inline u8 *ieee80211_get_DA(struct ieee80211_hdr *hdr)
 /**
  * ieee80211_is_bufferable_mmpdu - check if frame is bufferable MMPDU
  * @skb: the skb to check, starting with the 802.11 header
+ * Return: whether or not the MMPDU is bufferable
  */
 static inline bool ieee80211_is_bufferable_mmpdu(struct sk_buff *skb)
 {
@@ -4425,6 +4476,7 @@ static inline bool ieee80211_is_bufferable_mmpdu(struct sk_buff *skb)
 /**
  * _ieee80211_is_robust_mgmt_frame - check if frame is a robust management frame
  * @hdr: the frame (buffer must include at least the first octet of payload)
+ * Return: whether or not the frame is a robust management frame
  */
 static inline bool _ieee80211_is_robust_mgmt_frame(struct ieee80211_hdr *hdr)
 {
@@ -4461,6 +4513,7 @@ static inline bool _ieee80211_is_robust_mgmt_frame(struct ieee80211_hdr *hdr)
 /**
  * ieee80211_is_robust_mgmt_frame - check if skb contains a robust mgmt frame
  * @skb: the skb containing the frame, length will be checked
+ * Return: whether or not the frame is a robust management frame
  */
 static inline bool ieee80211_is_robust_mgmt_frame(struct sk_buff *skb)
 {
@@ -4473,6 +4526,7 @@ static inline bool ieee80211_is_robust_mgmt_frame(struct sk_buff *skb)
  * ieee80211_is_public_action - check if frame is a public action frame
  * @hdr: the frame
  * @len: length of the frame
+ * Return: whether or not the frame is a public action frame
  */
 static inline bool ieee80211_is_public_action(struct ieee80211_hdr *hdr,
 					      size_t len)
@@ -4518,8 +4572,9 @@ ieee80211_is_protected_dual_of_public_action(struct sk_buff *skb)
 
 /**
  * _ieee80211_is_group_privacy_action - check if frame is a group addressed
- * privacy action frame
+ *	privacy action frame
  * @hdr: the frame
+ * Return: whether or not the frame is a group addressed privacy action frame
  */
 static inline bool _ieee80211_is_group_privacy_action(struct ieee80211_hdr *hdr)
 {
@@ -4535,8 +4590,9 @@ static inline bool _ieee80211_is_group_privacy_action(struct ieee80211_hdr *hdr)
 
 /**
  * ieee80211_is_group_privacy_action - check if frame is a group addressed
- * privacy action frame
+ *	privacy action frame
  * @skb: the skb containing the frame, length will be checked
+ * Return: whether or not the frame is a group addressed privacy action frame
  */
 static inline bool ieee80211_is_group_privacy_action(struct sk_buff *skb)
 {
@@ -4548,6 +4604,7 @@ static inline bool ieee80211_is_group_privacy_action(struct sk_buff *skb)
 /**
  * ieee80211_tu_to_usec - convert time units (TU) to microseconds
  * @tu: the TUs
+ * Return: the time value converted to microseconds
  */
 static inline unsigned long ieee80211_tu_to_usec(unsigned long tu)
 {
@@ -4559,6 +4616,7 @@ static inline unsigned long ieee80211_tu_to_usec(unsigned long tu)
  * @tim: the TIM IE
  * @tim_len: length of the TIM IE
  * @aid: the AID to look for
+ * Return: whether or not traffic is indicated in the TIM for the given AID
  */
 static inline bool ieee80211_check_tim(const struct ieee80211_tim_ie *tim,
 				       u8 tim_len, u16 aid)
@@ -4585,8 +4643,10 @@ static inline bool ieee80211_check_tim(const struct ieee80211_tim_ie *tim,
 }
 
 /**
- * ieee80211_get_tdls_action - get tdls packet action (or -1, if not tdls packet)
+ * ieee80211_get_tdls_action - get TDLS action code
  * @skb: the skb containing the frame, length will not be checked
+ * Return: the TDLS action code, or -1 if it's not an encapsulated TDLS action
+ *	frame
  *
  * This function assumes the frame is a data frame, and that the network header
  * is in the correct place.
@@ -4626,6 +4686,7 @@ static inline int ieee80211_get_tdls_action(struct sk_buff *skb)
 /**
  * ieee80211_action_contains_tpc - checks if the frame contains TPC element
  * @skb: the skb containing the frame, length will be checked
+ * Return: %true if the frame contains a TPC element, %false otherwise
  *
  * This function checks if it's either TPC report action frame or Link
  * Measurement report action frame as defined in IEEE Std. 802.11-2012 8.5.2.5
@@ -4743,6 +4804,7 @@ struct element {
  * @element: element pointer after for_each_element() or friends
  * @data: same data pointer as passed to for_each_element() or friends
  * @datalen: same data length as passed to for_each_element() or friends
+ * Return: %true if all elements were iterated, %false otherwise; see notes
  *
  * This function returns %true if all the data was parsed or considered
  * while walking the elements. Only use this if your for_each_element()
@@ -4946,6 +5008,7 @@ struct ieee80211_mle_tdls_common_info {
  * ieee80211_mle_common_size - check multi-link element common size
  * @data: multi-link element, must already be checked for size using
  *	ieee80211_mle_size_ok()
+ * Return: the size of the multi-link element's "common" subfield 
  */
 static inline u8 ieee80211_mle_common_size(const u8 *data)
 {
@@ -4978,11 +5041,10 @@ static inline u8 ieee80211_mle_common_size(const u8 *data)
 /**
  * ieee80211_mle_get_link_id - returns the link ID
  * @data: the basic multi link element
+ * Return: the link ID, or -1 if not present
  *
  * The element is assumed to be of the correct type (BASIC) and big enough,
  * this must be checked using ieee80211_mle_type_ok().
- *
- * If the BSS link ID can't be found, -1 will be returned
  */
 static inline int ieee80211_mle_get_link_id(const u8 *data)
 {
@@ -5002,12 +5064,10 @@ static inline int ieee80211_mle_get_link_id(const u8 *data)
 /**
  * ieee80211_mle_get_bss_param_ch_cnt - returns the BSS parameter change count
  * @data: pointer to the basic multi link element
+ * Return: the BSS Parameter Change Count field value, or -1 if not present
  *
  * The element is assumed to be of the correct type (BASIC) and big enough,
  * this must be checked using ieee80211_mle_type_ok().
- *
- * If the BSS parameter change count value can't be found (the presence bit
- * for it is clear), -1 will be returned.
  */
 static inline int
 ieee80211_mle_get_bss_param_ch_cnt(const u8 *data)
@@ -5030,13 +5090,13 @@ ieee80211_mle_get_bss_param_ch_cnt(const u8 *data)
 
 /**
  * ieee80211_mle_get_eml_med_sync_delay - returns the medium sync delay
- * @data: pointer to the multi link EHT IE
+ * @data: pointer to the multi-link element
+ * Return: the medium synchronization delay field value from the multi-link
+ *	element, or the default value (%IEEE80211_MED_SYNC_DELAY_DEFAULT)
+ *	if not present
  *
  * The element is assumed to be of the correct type (BASIC) and big enough,
  * this must be checked using ieee80211_mle_type_ok().
- *
- * If the medium synchronization is not present, then the default value is
- * returned.
  */
 static inline u16 ieee80211_mle_get_eml_med_sync_delay(const u8 *data)
 {
@@ -5060,12 +5120,12 @@ static inline u16 ieee80211_mle_get_eml_med_sync_delay(const u8 *data)
 
 /**
  * ieee80211_mle_get_eml_cap - returns the EML capability
- * @data: pointer to the multi link EHT IE
+ * @data: pointer to the multi-link element
+ * Return: the EML capability field value from the multi-link element,
+ *	or 0 if not present
  *
  * The element is assumed to be of the correct type (BASIC) and big enough,
  * this must be checked using ieee80211_mle_type_ok().
- *
- * If the EML capability is not present, 0 will be returned.
  */
 static inline u16 ieee80211_mle_get_eml_cap(const u8 *data)
 {
@@ -5091,13 +5151,12 @@ static inline u16 ieee80211_mle_get_eml_cap(const u8 *data)
 
 /**
  * ieee80211_mle_get_mld_capa_op - returns the MLD capabilities and operations.
- * @data: pointer to the multi link EHT IE
+ * @data: pointer to the multi-link element
+ * Return: the MLD capabilities and operations field value from the multi-link
+ *	element, or 0 if not present
  *
  * The element is assumed to be of the correct type (BASIC) and big enough,
  * this must be checked using ieee80211_mle_type_ok().
- *
- * If the MLD capabilities and operations field is not present, 0 will be
- * returned.
  */
 static inline u16 ieee80211_mle_get_mld_capa_op(const u8 *data)
 {
@@ -5128,12 +5187,11 @@ static inline u16 ieee80211_mle_get_mld_capa_op(const u8 *data)
 
 /**
  * ieee80211_mle_get_mld_id - returns the MLD ID
- * @data: pointer to the multi link element
+ * @data: pointer to the multi-link element
+ * Return: The MLD ID in the given multi-link element, or 0 if not present
  *
  * The element is assumed to be of the correct type (BASIC) and big enough,
  * this must be checked using ieee80211_mle_type_ok().
- *
- * If the MLD ID is not present, 0 will be returned.
  */
 static inline u8 ieee80211_mle_get_mld_id(const u8 *data)
 {
@@ -5168,6 +5226,7 @@ static inline u8 ieee80211_mle_get_mld_id(const u8 *data)
  * ieee80211_mle_size_ok - validate multi-link element size
  * @data: pointer to the element data
  * @len: length of the containing element
+ * Return: whether or not the multi-link element size is OK
  */
 static inline bool ieee80211_mle_size_ok(const u8 *data, size_t len)
 {
@@ -5237,6 +5296,7 @@ static inline bool ieee80211_mle_size_ok(const u8 *data, size_t len)
  * @data: pointer to the element data
  * @type: expected type of the element
  * @len: length of the containing element
+ * Return: whether or not the multi-link element type matches and size is OK
  */
 static inline bool ieee80211_mle_type_ok(const u8 *data, u8 type, size_t len)
 {
@@ -5280,6 +5340,7 @@ struct ieee80211_mle_per_sta_profile {
  *	profile size
  * @data: pointer to the sub element data
  * @len: length of the containing sub element
+ * Return: %true if the STA profile is large enough, %false otherwise
  */
 static inline bool ieee80211_mle_basic_sta_prof_size_ok(const u8 *data,
 							size_t len)
@@ -5364,6 +5425,7 @@ ieee80211_mle_basic_sta_prof_bss_param_ch_cnt(const struct ieee80211_mle_per_sta
  *	element sta profile size.
  * @data: pointer to the sub element data
  * @len: length of the containing sub element
+ * Return: %true if the STA profile is large enough, %false otherwise
  */
 static inline bool ieee80211_mle_reconf_sta_prof_size_ok(const u8 *data,
 							 size_t len)
-- 
GitLab


From 9d222c12834d80849afbad7b42822b8ffbbc025f Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 15 May 2024 09:38:40 +0200
Subject: [PATCH 104/950] wifi: ieee80211: document two FTM related functions

Add some documentation to ieee80211_is_timing_measurement()
and ieee80211_is_ftm().

Link: https://msgid.link/20240515093852.229aa69e972c.Ifae6762a698e79cd5a49a055fe4c32330e826200@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 595f83783f0e9..fb50a99daa93e 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -4731,6 +4731,11 @@ static inline bool ieee80211_action_contains_tpc(struct sk_buff *skb)
 	return true;
 }
 
+/**
+ * ieee80211_is_timing_measurement - check if frame is timing measurement response
+ * @skb: the SKB to check
+ * Return: whether or not the frame is a valid timing measurement response
+ */
 static inline bool ieee80211_is_timing_measurement(struct sk_buff *skb)
 {
 	struct ieee80211_mgmt *mgmt = (void *)skb->data;
@@ -4750,6 +4755,11 @@ static inline bool ieee80211_is_timing_measurement(struct sk_buff *skb)
 	return false;
 }
 
+/**
+ * ieee80211_is_ftm - check if frame is FTM response
+ * @skb: the SKB to check
+ * Return: whether or not the frame is a valid FTM response action frame
+ */
 static inline bool ieee80211_is_ftm(struct sk_buff *skb)
 {
 	struct ieee80211_mgmt *mgmt = (void *)skb->data;
-- 
GitLab


From 23daf1b4c91db9b26f8425cc7039cf96d22ccbfe Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 15 May 2024 14:16:00 +0200
Subject: [PATCH 105/950] wifi: nl80211: disallow setting special AP channel
 widths

Setting the AP channel width is meant for use with the normal
20/40/... MHz channel width progression, and switching around
in S1G or narrow channels isn't supported. Disallow that.

Reported-by: syzbot+bc0f5b92cc7091f45fb6@syzkaller.appspotmail.com
Link: https://msgid.link/20240515141600.d4a9590bfe32.I19a32d60097e81b527eafe6b0924f6c5fbb2dc45@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/nl80211.c | 27 +++++++++++++++++++++++++++
 1 file changed, 27 insertions(+)

diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 3c0bca4238d35..93c313149f571 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -3415,6 +3415,33 @@ static int __nl80211_set_channel(struct cfg80211_registered_device *rdev,
 			if (chandef.chan != cur_chan)
 				return -EBUSY;
 
+			/* only allow this for regular channel widths */
+			switch (wdev->links[link_id].ap.chandef.width) {
+			case NL80211_CHAN_WIDTH_20_NOHT:
+			case NL80211_CHAN_WIDTH_20:
+			case NL80211_CHAN_WIDTH_40:
+			case NL80211_CHAN_WIDTH_80:
+			case NL80211_CHAN_WIDTH_80P80:
+			case NL80211_CHAN_WIDTH_160:
+			case NL80211_CHAN_WIDTH_320:
+				break;
+			default:
+				return -EINVAL;
+			}
+
+			switch (chandef.width) {
+			case NL80211_CHAN_WIDTH_20_NOHT:
+			case NL80211_CHAN_WIDTH_20:
+			case NL80211_CHAN_WIDTH_40:
+			case NL80211_CHAN_WIDTH_80:
+			case NL80211_CHAN_WIDTH_80P80:
+			case NL80211_CHAN_WIDTH_160:
+			case NL80211_CHAN_WIDTH_320:
+				break;
+			default:
+				return -EINVAL;
+			}
+
 			result = rdev_set_ap_chanwidth(rdev, dev, link_id,
 						       &chandef);
 			if (result)
-- 
GitLab


From 2449db1f2186e6cd8410631d0ee9e951289fe5ae Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 6 May 2024 21:00:02 +0200
Subject: [PATCH 106/950] wifi: cfg80211: sort trace events again

They were meant to be split into ops and APIs, but some
ops were added in the wrong place. Fix that.

Reviewed-by: Miriam Rachel Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240506210002.0b3a86a5d8d7.I5591c03223bdb95597e181de63a2eded424de34c@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/trace.h | 138 +++++++++++++++++++++----------------------
 1 file changed, 69 insertions(+), 69 deletions(-)

diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index 9bf987519811c..b76e3b21051a2 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -2889,6 +2889,75 @@ DEFINE_EVENT(wiphy_wdev_link_evt, rdev_del_intf_link,
 	TP_ARGS(wiphy, wdev, link_id)
 );
 
+TRACE_EVENT(rdev_del_link_station,
+	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev,
+		 struct link_station_del_parameters *params),
+	TP_ARGS(wiphy, netdev, params),
+	TP_STRUCT__entry(
+		WIPHY_ENTRY
+		NETDEV_ENTRY
+		__array(u8, mld_mac, 6)
+		__field(u32, link_id)
+	),
+	TP_fast_assign(
+		WIPHY_ASSIGN;
+		NETDEV_ASSIGN;
+		memset(__entry->mld_mac, 0, 6);
+		if (params->mld_mac)
+			memcpy(__entry->mld_mac, params->mld_mac, 6);
+		__entry->link_id = params->link_id;
+	),
+	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", station mac: %pM"
+		  ", link id: %u",
+		  WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->mld_mac,
+		  __entry->link_id)
+);
+
+TRACE_EVENT(rdev_set_hw_timestamp,
+	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev,
+		 struct cfg80211_set_hw_timestamp *hwts),
+
+	TP_ARGS(wiphy, netdev, hwts),
+
+	TP_STRUCT__entry(
+		WIPHY_ENTRY
+		NETDEV_ENTRY
+		MAC_ENTRY(macaddr)
+		__field(bool, enable)
+	),
+
+	TP_fast_assign(
+		WIPHY_ASSIGN;
+		NETDEV_ASSIGN;
+		MAC_ASSIGN(macaddr, hwts->macaddr);
+		__entry->enable = hwts->enable;
+	),
+
+	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", mac %pM, enable: %u",
+		  WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->macaddr,
+		  __entry->enable)
+);
+
+TRACE_EVENT(rdev_set_ttlm,
+	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev,
+		 struct cfg80211_ttlm_params *params),
+	TP_ARGS(wiphy, netdev, params),
+	TP_STRUCT__entry(
+		WIPHY_ENTRY
+		NETDEV_ENTRY
+		__array(u8, dlink, sizeof(u16) * 8)
+		__array(u8, ulink, sizeof(u16) * 8)
+	),
+	TP_fast_assign(
+		WIPHY_ASSIGN;
+		NETDEV_ASSIGN;
+		memcpy(__entry->dlink, params->dlink, sizeof(params->dlink));
+		memcpy(__entry->ulink, params->ulink, sizeof(params->ulink));
+	),
+	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT,
+		  WIPHY_PR_ARG, NETDEV_PR_ARG)
+);
+
 /*************************************************************
  *	     cfg80211 exported functions traces		     *
  *************************************************************/
@@ -3923,55 +3992,6 @@ DEFINE_EVENT(link_station_add_mod, rdev_mod_link_station,
 	TP_ARGS(wiphy, netdev, params)
 );
 
-TRACE_EVENT(rdev_del_link_station,
-	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev,
-		 struct link_station_del_parameters *params),
-	TP_ARGS(wiphy, netdev, params),
-	TP_STRUCT__entry(
-		WIPHY_ENTRY
-		NETDEV_ENTRY
-		__array(u8, mld_mac, 6)
-		__field(u32, link_id)
-	),
-	TP_fast_assign(
-		WIPHY_ASSIGN;
-		NETDEV_ASSIGN;
-		memset(__entry->mld_mac, 0, 6);
-		if (params->mld_mac)
-			memcpy(__entry->mld_mac, params->mld_mac, 6);
-		__entry->link_id = params->link_id;
-	),
-	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", station mac: %pM"
-		  ", link id: %u",
-		  WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->mld_mac,
-		  __entry->link_id)
-);
-
-TRACE_EVENT(rdev_set_hw_timestamp,
-	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev,
-		 struct cfg80211_set_hw_timestamp *hwts),
-
-	TP_ARGS(wiphy, netdev, hwts),
-
-	TP_STRUCT__entry(
-		WIPHY_ENTRY
-		NETDEV_ENTRY
-		MAC_ENTRY(macaddr)
-		__field(bool, enable)
-	),
-
-	TP_fast_assign(
-		WIPHY_ASSIGN;
-		NETDEV_ASSIGN;
-		MAC_ASSIGN(macaddr, hwts->macaddr);
-		__entry->enable = hwts->enable;
-	),
-
-	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", mac %pM, enable: %u",
-		  WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->macaddr,
-		  __entry->enable)
-);
-
 TRACE_EVENT(cfg80211_links_removed,
 	TP_PROTO(struct net_device *netdev, u16 link_mask),
 	TP_ARGS(netdev, link_mask),
@@ -3987,26 +4007,6 @@ TRACE_EVENT(cfg80211_links_removed,
 		  __entry->link_mask)
 );
 
-TRACE_EVENT(rdev_set_ttlm,
-	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev,
-		 struct cfg80211_ttlm_params *params),
-	TP_ARGS(wiphy, netdev, params),
-	TP_STRUCT__entry(
-		WIPHY_ENTRY
-		NETDEV_ENTRY
-		__array(u8, dlink, sizeof(u16) * 8)
-		__array(u8, ulink, sizeof(u16) * 8)
-	),
-	TP_fast_assign(
-		WIPHY_ASSIGN;
-		NETDEV_ASSIGN;
-		memcpy(__entry->dlink, params->dlink, sizeof(params->dlink));
-		memcpy(__entry->ulink, params->ulink, sizeof(params->ulink));
-	),
-	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT,
-		  WIPHY_PR_ARG, NETDEV_PR_ARG)
-);
-
 #endif /* !__RDEV_OPS_TRACE || TRACE_HEADER_MULTI_READ */
 
 #undef TRACE_INCLUDE_PATH
-- 
GitLab


From eb745c7c854e200d7fd6ba0944691a1aaf882d4d Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 6 May 2024 21:00:03 +0200
Subject: [PATCH 107/950] wifi: cfg80211: add tracing for wiphy work

Add trace events to trace when wiphy works are queued (or
delayed ones scheduled), and other APIs are called. Also
add an event when the worker starts, before acquiring the
mutex, to be able to see potential delays due to locking.

Reviewed-by: Miriam Rachel Korenblit <miriam.rachel.korenblit@intel.com>
Reviewed-by: Benjamin Berg <benjamin.berg@intel.com>
Link: https://msgid.link/20240506210002.bf1840a1d22d.I4abba048c1c4017345640219cf1384a0b2288dd3@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/core.c  | 12 +++++++
 net/wireless/trace.h | 74 ++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 86 insertions(+)

diff --git a/net/wireless/core.c b/net/wireless/core.c
index 3fb1b637352a9..61f7cd8a8e9ce 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -421,6 +421,8 @@ static void cfg80211_wiphy_work(struct work_struct *work)
 
 	rdev = container_of(work, struct cfg80211_registered_device, wiphy_work);
 
+	trace_wiphy_work_worker_start(&rdev->wiphy);
+
 	wiphy_lock(&rdev->wiphy);
 	if (rdev->suspended)
 		goto out;
@@ -434,6 +436,7 @@ static void cfg80211_wiphy_work(struct work_struct *work)
 			schedule_work(work);
 		spin_unlock_irq(&rdev->wiphy_work_lock);
 
+		trace_wiphy_work_run(&rdev->wiphy, wk);
 		wk->func(&rdev->wiphy, wk);
 	} else {
 		spin_unlock_irq(&rdev->wiphy_work_lock);
@@ -1066,6 +1069,7 @@ void cfg80211_process_wiphy_works(struct cfg80211_registered_device *rdev,
 		list_del_init(&wk->entry);
 		spin_unlock_irqrestore(&rdev->wiphy_work_lock, flags);
 
+		trace_wiphy_work_run(&rdev->wiphy, wk);
 		wk->func(&rdev->wiphy, wk);
 
 		spin_lock_irqsave(&rdev->wiphy_work_lock, flags);
@@ -1610,6 +1614,8 @@ void wiphy_work_queue(struct wiphy *wiphy, struct wiphy_work *work)
 	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	unsigned long flags;
 
+	trace_wiphy_work_queue(wiphy, work);
+
 	spin_lock_irqsave(&rdev->wiphy_work_lock, flags);
 	if (list_empty(&work->entry))
 		list_add_tail(&work->entry, &rdev->wiphy_work_list);
@@ -1626,6 +1632,8 @@ void wiphy_work_cancel(struct wiphy *wiphy, struct wiphy_work *work)
 
 	lockdep_assert_held(&wiphy->mtx);
 
+	trace_wiphy_work_cancel(wiphy, work);
+
 	spin_lock_irqsave(&rdev->wiphy_work_lock, flags);
 	if (!list_empty(&work->entry))
 		list_del_init(&work->entry);
@@ -1639,6 +1647,8 @@ void wiphy_work_flush(struct wiphy *wiphy, struct wiphy_work *work)
 	unsigned long flags;
 	bool run;
 
+	trace_wiphy_work_flush(wiphy, work);
+
 	spin_lock_irqsave(&rdev->wiphy_work_lock, flags);
 	run = !work || !list_empty(&work->entry);
 	spin_unlock_irqrestore(&rdev->wiphy_work_lock, flags);
@@ -1660,6 +1670,8 @@ void wiphy_delayed_work_queue(struct wiphy *wiphy,
 			      struct wiphy_delayed_work *dwork,
 			      unsigned long delay)
 {
+	trace_wiphy_delayed_work_queue(wiphy, &dwork->work, delay);
+
 	if (!delay) {
 		del_timer(&dwork->timer);
 		wiphy_work_queue(wiphy, &dwork->work);
diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index b76e3b21051a2..14cfa0aba93a8 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -242,6 +242,80 @@
 		}						\
 	} while (0)
 
+/*************************************************************
+ *			wiphy work traces		     *
+ *************************************************************/
+
+DECLARE_EVENT_CLASS(wiphy_work_event,
+	TP_PROTO(struct wiphy *wiphy, struct wiphy_work *work),
+	TP_ARGS(wiphy, work),
+	TP_STRUCT__entry(
+		WIPHY_ENTRY
+		__field(void *, instance)
+		__field(void *, func)
+	),
+	TP_fast_assign(
+		WIPHY_ASSIGN;
+		__entry->instance = work;
+		__entry->func = work ? work->func : NULL;
+	),
+	TP_printk(WIPHY_PR_FMT " instance=%p func=%pS",
+		  WIPHY_PR_ARG, __entry->instance, __entry->func)
+);
+
+DEFINE_EVENT(wiphy_work_event, wiphy_work_queue,
+	TP_PROTO(struct wiphy *wiphy, struct wiphy_work *work),
+	TP_ARGS(wiphy, work)
+);
+
+DEFINE_EVENT(wiphy_work_event, wiphy_work_run,
+	TP_PROTO(struct wiphy *wiphy, struct wiphy_work *work),
+	TP_ARGS(wiphy, work)
+);
+
+DEFINE_EVENT(wiphy_work_event, wiphy_work_cancel,
+	TP_PROTO(struct wiphy *wiphy, struct wiphy_work *work),
+	TP_ARGS(wiphy, work)
+);
+
+DEFINE_EVENT(wiphy_work_event, wiphy_work_flush,
+	TP_PROTO(struct wiphy *wiphy, struct wiphy_work *work),
+	TP_ARGS(wiphy, work)
+);
+
+TRACE_EVENT(wiphy_delayed_work_queue,
+	TP_PROTO(struct wiphy *wiphy, struct wiphy_work *work,
+		 unsigned long delay),
+	TP_ARGS(wiphy, work, delay),
+	TP_STRUCT__entry(
+		WIPHY_ENTRY
+		__field(void *, instance)
+		__field(void *, func)
+		__field(unsigned long, delay)
+	),
+	TP_fast_assign(
+		WIPHY_ASSIGN;
+		__entry->instance = work;
+		__entry->func = work->func;
+		__entry->delay = delay;
+	),
+	TP_printk(WIPHY_PR_FMT " instance=%p func=%pS delay=%ld",
+		  WIPHY_PR_ARG, __entry->instance, __entry->func,
+		  __entry->delay)
+);
+
+TRACE_EVENT(wiphy_work_worker_start,
+	TP_PROTO(struct wiphy *wiphy),
+	TP_ARGS(wiphy),
+	TP_STRUCT__entry(
+		WIPHY_ENTRY
+	),
+	TP_fast_assign(
+		WIPHY_ASSIGN;
+	),
+	TP_printk(WIPHY_PR_FMT, WIPHY_PR_ARG)
+);
+
 /*************************************************************
  *			rdev->ops traces		     *
  *************************************************************/
-- 
GitLab


From 7aa5c8b4f9de463abc0407da38c9ffccdbc757d1 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 6 May 2024 21:14:22 +0200
Subject: [PATCH 108/950] wifi: mac80211: remove outdated comments

These comments are no longer correct, it's a wiphy work now
so it will go away immediately when canceled.

Reviewed-by: Miriam Rachel Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240506211422.68bc10efbd8a.If80f43f4c8b9db1f5266f70d93a805f8c7463fe2@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/cfg.c  | 4 ----
 net/mac80211/util.c | 4 ----
 2 files changed, 8 deletions(-)

diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index b08e5d7687e3f..88af2b8037cbe 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -3482,10 +3482,6 @@ static void ieee80211_end_cac(struct wiphy *wiphy,
 	lockdep_assert_wiphy(local->hw.wiphy);
 
 	list_for_each_entry(sdata, &local->interfaces, list) {
-		/* it might be waiting for the local->mtx, but then
-		 * by the time it gets it, sdata->wdev.cac_started
-		 * will no longer be true
-		 */
 		wiphy_delayed_work_cancel(wiphy,
 					  &sdata->deflink.dfs_cac_timer_work);
 
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 0b893e9589594..6139c930b572e 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -3456,10 +3456,6 @@ void ieee80211_dfs_cac_cancel(struct ieee80211_local *local)
 	lockdep_assert_wiphy(local->hw.wiphy);
 
 	list_for_each_entry(sdata, &local->interfaces, list) {
-		/* it might be waiting for the local->mtx, but then
-		 * by the time it gets it, sdata->wdev.cac_started
-		 * will no longer be true
-		 */
 		wiphy_delayed_work_cancel(local->hw.wiphy,
 					  &sdata->deflink.dfs_cac_timer_work);
 
-- 
GitLab


From 5c24e83f6895a01a8d79a79d3ec567bd0ec13b56 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 6 May 2024 21:19:34 +0200
Subject: [PATCH 109/950] wifi: mac80211: remove extra link STA functions

There's no need to have a lockdep assert and then call
another function, just move everything into one place.

Reviewed-by: Miriam Rachel Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240506211934.9759564a25f4.I88d43aa459d15c1d6230152e76b7757c2cdd6085@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/cfg.c | 49 ++++++++++++----------------------------------
 1 file changed, 13 insertions(+), 36 deletions(-)

diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 88af2b8037cbe..3673c7f6b21a3 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -4974,13 +4974,17 @@ static void ieee80211_del_intf_link(struct wiphy *wiphy,
 	ieee80211_vif_set_links(sdata, wdev->valid_links, 0);
 }
 
-static int sta_add_link_station(struct ieee80211_local *local,
-				struct ieee80211_sub_if_data *sdata,
-				struct link_station_parameters *params)
+static int
+ieee80211_add_link_station(struct wiphy *wiphy, struct net_device *dev,
+			   struct link_station_parameters *params)
 {
+	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
+	struct ieee80211_local *local = wiphy_priv(wiphy);
 	struct sta_info *sta;
 	int ret;
 
+	lockdep_assert_wiphy(local->hw.wiphy);
+
 	sta = sta_info_get_bss(sdata, params->mld_mac);
 	if (!sta)
 		return -ENOENT;
@@ -5006,23 +5010,15 @@ static int sta_add_link_station(struct ieee80211_local *local,
 }
 
 static int
-ieee80211_add_link_station(struct wiphy *wiphy, struct net_device *dev,
+ieee80211_mod_link_station(struct wiphy *wiphy, struct net_device *dev,
 			   struct link_station_parameters *params)
 {
 	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
 	struct ieee80211_local *local = wiphy_priv(wiphy);
-
-	lockdep_assert_wiphy(sdata->local->hw.wiphy);
-
-	return sta_add_link_station(local, sdata, params);
-}
-
-static int sta_mod_link_station(struct ieee80211_local *local,
-				struct ieee80211_sub_if_data *sdata,
-				struct link_station_parameters *params)
-{
 	struct sta_info *sta;
 
+	lockdep_assert_wiphy(local->hw.wiphy);
+
 	sta = sta_info_get_bss(sdata, params->mld_mac);
 	if (!sta)
 		return -ENOENT;
@@ -5034,22 +5030,14 @@ static int sta_mod_link_station(struct ieee80211_local *local,
 }
 
 static int
-ieee80211_mod_link_station(struct wiphy *wiphy, struct net_device *dev,
-			   struct link_station_parameters *params)
+ieee80211_del_link_station(struct wiphy *wiphy, struct net_device *dev,
+			   struct link_station_del_parameters *params)
 {
 	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
-	struct ieee80211_local *local = wiphy_priv(wiphy);
+	struct sta_info *sta;
 
 	lockdep_assert_wiphy(sdata->local->hw.wiphy);
 
-	return sta_mod_link_station(local, sdata, params);
-}
-
-static int sta_del_link_station(struct ieee80211_sub_if_data *sdata,
-				struct link_station_del_parameters *params)
-{
-	struct sta_info *sta;
-
 	sta = sta_info_get_bss(sdata, params->mld_mac);
 	if (!sta)
 		return -ENOENT;
@@ -5066,17 +5054,6 @@ static int sta_del_link_station(struct ieee80211_sub_if_data *sdata,
 	return 0;
 }
 
-static int
-ieee80211_del_link_station(struct wiphy *wiphy, struct net_device *dev,
-			   struct link_station_del_parameters *params)
-{
-	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
-
-	lockdep_assert_wiphy(sdata->local->hw.wiphy);
-
-	return sta_del_link_station(sdata, params);
-}
-
 static int ieee80211_set_hw_timestamp(struct wiphy *wiphy,
 				      struct net_device *dev,
 				      struct cfg80211_set_hw_timestamp *hwts)
-- 
GitLab


From e3bae9b22873338d1a7989a2568c5aca2c44bde7 Mon Sep 17 00:00:00 2001
From: Mukesh Sisodiya <mukesh.sisodiya@intel.com>
Date: Mon, 6 May 2024 21:37:53 +0200
Subject: [PATCH 110/950] wifi: mac80211: update 6 GHz AP power type before
 association

6 GHz AP power type details are required to set proper tx power
used to send frames.

Update AP power type received in beacon while preparing
for connection instead of after association so the frames
before association can use the correct tx power.

Reviewed-by: Miriam Rachel Korenblit <miriam.rachel.korenblit@intel.com>
Reviewed-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Mukesh Sisodiya <mukesh.sisodiya@intel.com>
Link: https://msgid.link/20240506214536.310434f55f76.I6aca291ee06265e3f63e0f9024ba19a850b53a33@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mlme.c | 55 ++++++++++++++++++++++-----------------------
 1 file changed, 27 insertions(+), 28 deletions(-)

diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index a5f2d3cfe60d2..e410a43dc681c 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -4445,40 +4445,12 @@ static bool ieee80211_assoc_config_link(struct ieee80211_link_data *link,
 	if (elems->he_operation &&
 	    link->u.mgd.conn.mode >= IEEE80211_CONN_MODE_HE &&
 	    elems->he_cap) {
-		const struct ieee80211_he_6ghz_oper *he_6ghz_oper;
-
 		ieee80211_he_cap_ie_to_sta_he_cap(sdata, sband,
 						  elems->he_cap,
 						  elems->he_cap_len,
 						  elems->he_6ghz_capa,
 						  link_sta);
 
-		he_6ghz_oper = ieee80211_he_6ghz_oper(elems->he_operation);
-
-		if (is_6ghz && he_6ghz_oper) {
-			switch (u8_get_bits(he_6ghz_oper->control,
-					    IEEE80211_HE_6GHZ_OPER_CTRL_REG_INFO)) {
-			case IEEE80211_6GHZ_CTRL_REG_LPI_AP:
-			case IEEE80211_6GHZ_CTRL_REG_INDOOR_LPI_AP:
-				bss_conf->power_type = IEEE80211_REG_LPI_AP;
-				break;
-			case IEEE80211_6GHZ_CTRL_REG_SP_AP:
-			case IEEE80211_6GHZ_CTRL_REG_INDOOR_SP_AP:
-				bss_conf->power_type = IEEE80211_REG_SP_AP;
-				break;
-			case IEEE80211_6GHZ_CTRL_REG_VLP_AP:
-				bss_conf->power_type = IEEE80211_REG_VLP_AP;
-				break;
-			default:
-				bss_conf->power_type = IEEE80211_REG_UNSET_AP;
-				break;
-			}
-		} else if (is_6ghz) {
-			link_info(link,
-				  "HE 6 GHz operation missing (on %d MHz), expect issues\n",
-				  bss_conf->chanreq.oper.chan->center_freq);
-		}
-
 		bss_conf->he_support = link_sta->pub->he_cap.has_he;
 		if (elems->rsnx && elems->rsnx_len &&
 		    (elems->rsnx[0] & WLAN_RSNX_CAPA_PROTECTED_TWT) &&
@@ -5020,6 +4992,23 @@ ieee80211_determine_our_sta_mode_assoc(struct ieee80211_sub_if_data *sdata,
 			       conn->bw_limit, tmp.bw_limit);
 }
 
+static enum ieee80211_ap_reg_power
+ieee80211_ap_power_type(u8 control)
+{
+	switch (u8_get_bits(control, IEEE80211_HE_6GHZ_OPER_CTRL_REG_INFO)) {
+	case IEEE80211_6GHZ_CTRL_REG_LPI_AP:
+	case IEEE80211_6GHZ_CTRL_REG_INDOOR_LPI_AP:
+		return IEEE80211_REG_LPI_AP;
+	case IEEE80211_6GHZ_CTRL_REG_SP_AP:
+	case IEEE80211_6GHZ_CTRL_REG_INDOOR_SP_AP:
+		return IEEE80211_REG_SP_AP;
+	case IEEE80211_6GHZ_CTRL_REG_VLP_AP:
+		return IEEE80211_REG_VLP_AP;
+	default:
+		return IEEE80211_REG_UNSET_AP;
+	}
+}
+
 static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata,
 				  struct ieee80211_link_data *link,
 				  int link_id,
@@ -5052,6 +5041,7 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata,
 	}
 
 	if (link && is_6ghz && conn->mode >= IEEE80211_CONN_MODE_HE) {
+		const struct ieee80211_he_6ghz_oper *he_6ghz_oper;
 		struct ieee80211_bss_conf *bss_conf;
 		u8 j = 0;
 
@@ -5072,6 +5062,15 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata,
 			       elems->tx_pwr_env_len[i]);
 			j++;
 		}
+
+		he_6ghz_oper = ieee80211_he_6ghz_oper(elems->he_operation);
+		if (he_6ghz_oper)
+			bss_conf->power_type =
+				ieee80211_ap_power_type(he_6ghz_oper->control);
+		else
+			link_info(link,
+				  "HE 6 GHz operation missing (on %d MHz), expect issues\n",
+				  cbss->channel->center_freq);
 	}
 	rcu_read_unlock();
 	/* the element data was RCU protected so no longer valid anyway */
-- 
GitLab


From 8592fd7ccc95a7cf222985e6297041463e8b4e9d Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 6 May 2024 21:37:54 +0200
Subject: [PATCH 111/950] wifi: ieee80211/ath11k: remove
 IEEE80211_MAX_NUM_PWR_LEVEL

The define IEEE80211_MAX_NUM_PWR_LEVEL doesn't make much
sense. Yes, that table has a maximum value of 8, and the
table will actually remain that way, but EHT introduced
a way to encode more levels for 320 MHz channels.

Remove IEEE80211_MAX_NUM_PWR_LEVEL and, for ath11k being
the only user, add ATH11K_NUM_PWR_LEVELS, where it makes
sense since it cannot support 320 MHz channels.

Acked-by: Kalle Valo <kvalo@kernel.org>
Link: https://msgid.link/20240506214536.9818e5471055.Icece7e47e963d6b68e0d97ba13c102b37fbaa689@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/ath/ath11k/core.h | 9 ++++++---
 drivers/net/wireless/ath/ath11k/mac.c  | 2 +-
 include/linux/ieee80211.h              | 5 -----
 3 files changed, 7 insertions(+), 9 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/core.h b/drivers/net/wireless/ath/ath11k/core.h
index 205f40ee6b666..df24f0e409afb 100644
--- a/drivers/net/wireless/ath/ath11k/core.h
+++ b/drivers/net/wireless/ath/ath11k/core.h
@@ -330,6 +330,9 @@ struct ath11k_chan_power_info {
 	s8 tx_power;
 };
 
+/* ath11k only deals with 160 MHz, so 8 subchannels */
+#define ATH11K_NUM_PWR_LEVELS	8
+
 /**
  * struct ath11k_reg_tpc_power_info - regulatory TPC power info
  * @is_psd_power: is PSD power or not
@@ -346,10 +349,10 @@ struct ath11k_reg_tpc_power_info {
 	u8 eirp_power;
 	enum wmi_reg_6ghz_ap_type ap_power_type;
 	u8 num_pwr_levels;
-	u8 reg_max[IEEE80211_MAX_NUM_PWR_LEVEL];
+	u8 reg_max[ATH11K_NUM_PWR_LEVELS];
 	u8 ap_constraint_power;
-	s8 tpe[IEEE80211_MAX_NUM_PWR_LEVEL];
-	struct ath11k_chan_power_info chan_power_info[IEEE80211_MAX_NUM_PWR_LEVEL];
+	s8 tpe[ATH11K_NUM_PWR_LEVELS];
+	struct ath11k_chan_power_info chan_power_info[ATH11K_NUM_PWR_LEVELS];
 };
 
 struct ath11k_vif {
diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c
index 4f62e38ba48b3..59e5e80857422 100644
--- a/drivers/net/wireless/ath/ath11k/mac.c
+++ b/drivers/net/wireless/ath/ath11k/mac.c
@@ -7688,7 +7688,7 @@ void ath11k_mac_fill_reg_tpc_info(struct ath11k *ar,
 	struct ieee80211_channel *chan, *temp_chan;
 	u8 pwr_lvl_idx, num_pwr_levels, pwr_reduction;
 	bool is_psd_power = false, is_tpe_present = false;
-	s8 max_tx_power[IEEE80211_MAX_NUM_PWR_LEVEL],
+	s8 max_tx_power[ATH11K_NUM_PWR_LEVELS],
 		psd_power, tx_power;
 	s8 eirp_power = 0;
 	u16 start_freq, center_freq;
diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index fb50a99daa93e..1c3a683a3ee22 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -2833,11 +2833,6 @@ struct ieee80211_he_6ghz_oper {
  * So it it totally max 8 Transmit Power Envelope element.
  */
 #define IEEE80211_TPE_MAX_IE_COUNT	8
-/*
- * In "Table 9-277—Meaning of Maximum Transmit Power Count subfield"
- * of "IEEE Std 802.11ax™‐2021", the max power level is 8.
- */
-#define IEEE80211_MAX_NUM_PWR_LEVEL	8
 
 #define IEEE80211_TPE_MAX_POWER_COUNT	8
 
-- 
GitLab


From caa12b3dd44996f63b8dd0d842c68866d4ead307 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 6 May 2024 21:37:55 +0200
Subject: [PATCH 112/950] wifi: ath11k: fix TPE power levels

The chanctx can be shared, but it seems like the TPE values for
this vif should only reflect the channel that the vif uses, which
is captured in bss_conf->chanreq.oper rather than the chanctx.
Use that when calculating defaults, a similar issue is where the
data from the AP is processed, but I'm moving that to mac80211.

Acked-by: Kalle Valo <kvalo@kernel.org>
Link: https://msgid.link/20240506214536.d99fcf5856b9.I359bb401ea74bf82dc981a86a7ca3fa44d169d2e@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/ath/ath11k/mac.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c
index 59e5e80857422..73876760afe92 100644
--- a/drivers/net/wireless/ath/ath11k/mac.c
+++ b/drivers/net/wireless/ath/ath11k/mac.c
@@ -7701,7 +7701,8 @@ void ath11k_mac_fill_reg_tpc_info(struct ath11k *ar,
 		is_tpe_present = true;
 		num_pwr_levels = arvif->reg_tpc_info.num_pwr_levels;
 	} else {
-		num_pwr_levels = ath11k_mac_get_num_pwr_levels(&ctx->def);
+		num_pwr_levels =
+			ath11k_mac_get_num_pwr_levels(&bss_conf->chanreq.oper);
 	}
 
 	for (pwr_lvl_idx = 0; pwr_lvl_idx < num_pwr_levels; pwr_lvl_idx++) {
-- 
GitLab


From 39dc8b8ea387ce7f4fe2d2d6d550ed52aa9aa040 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 6 May 2024 21:37:56 +0200
Subject: [PATCH 113/950] wifi: mac80211: pass parsed TPE data to drivers

Instead of passing the full TPE elements, in all their glory
and mixed up data formats for HE backward compatibility, parse
them fully into the right values, and pass that to the drivers.

Also introduce proper validation already in mac80211, so that
drivers don't need to do it, and parse the EHT portions.

The code now passes the values in the right order according to
the channel used by an interface, which could also be a subset
of the data advertised by the AP, if we couldn't connect with
the full bandwidth (for whatever reason.)

Also add kunit tests for the more complicated bits of it.

Reviewed-by: Miriam Rachel Korenblit <miriam.rachel.korenblit@intel.com>
Acked-by: Kalle Valo <kvalo@kernel.org>
Link: https://msgid.link/20240506214536.2aa839969b60.I265b28209e0b29772b2f125f7f83de44a4da877b@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/ath/ath11k/mac.c | 143 +++----------
 include/linux/ieee80211.h             | 102 +++++++--
 include/net/mac80211.h                |  41 +++-
 net/mac80211/ieee80211_i.h            |  13 +-
 net/mac80211/mlme.c                   | 230 ++++++++++++++++++---
 net/mac80211/parse.c                  |  92 ++++++++-
 net/mac80211/tests/Makefile           |   2 +-
 net/mac80211/tests/tpe.c              | 284 ++++++++++++++++++++++++++
 net/mac80211/util.c                   |  25 +++
 9 files changed, 761 insertions(+), 171 deletions(-)
 create mode 100644 net/mac80211/tests/tpe.c

diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c
index 73876760afe92..d4225bf30e51a 100644
--- a/drivers/net/wireless/ath/ath11k/mac.c
+++ b/drivers/net/wireless/ath/ath11k/mac.c
@@ -7507,32 +7507,6 @@ static int ath11k_mac_stop_vdev_early(struct ieee80211_hw *hw,
 	return 0;
 }
 
-static u8 ath11k_mac_get_tpe_count(u8 txpwr_intrprt, u8 txpwr_cnt)
-{
-	switch (txpwr_intrprt) {
-	/* Refer "Table 9-276-Meaning of Maximum Transmit Power Count subfield
-	 * if the Maximum Transmit Power Interpretation subfield is 0 or 2" of
-	 * "IEEE Std 802.11ax 2021".
-	 */
-	case IEEE80211_TPE_LOCAL_EIRP:
-	case IEEE80211_TPE_REG_CLIENT_EIRP:
-		txpwr_cnt = txpwr_cnt <= 3 ? txpwr_cnt : 3;
-		txpwr_cnt = txpwr_cnt + 1;
-		break;
-	/* Refer "Table 9-277-Meaning of Maximum Transmit Power Count subfield
-	 * if Maximum Transmit Power Interpretation subfield is 1 or 3" of
-	 * "IEEE Std 802.11ax 2021".
-	 */
-	case IEEE80211_TPE_LOCAL_EIRP_PSD:
-	case IEEE80211_TPE_REG_CLIENT_EIRP_PSD:
-		txpwr_cnt = txpwr_cnt <= 4 ? txpwr_cnt : 4;
-		txpwr_cnt = txpwr_cnt ? (BIT(txpwr_cnt - 1)) : 1;
-		break;
-	}
-
-	return txpwr_cnt;
-}
-
 static u8 ath11k_mac_get_num_pwr_levels(struct cfg80211_chan_def *chan_def)
 {
 	if (chan_def->chan->flags & IEEE80211_CHAN_PSD) {
@@ -7859,33 +7833,23 @@ static void ath11k_mac_parse_tx_pwr_env(struct ath11k *ar,
 	struct ath11k_base *ab = ar->ab;
 	struct ath11k_vif *arvif = ath11k_vif_to_arvif(vif);
 	struct ieee80211_bss_conf *bss_conf = &vif->bss_conf;
-	struct ieee80211_tx_pwr_env *single_tpe;
+	struct ieee80211_parsed_tpe_eirp *non_psd = NULL;
+	struct ieee80211_parsed_tpe_psd *psd = NULL;
 	enum wmi_reg_6ghz_client_type client_type;
 	struct cur_regulatory_info *reg_info;
+	u8 local_tpe_count, reg_tpe_count;
+	bool use_local_tpe;
 	int i;
-	u8 pwr_count, pwr_interpret, pwr_category;
-	u8 psd_index = 0, non_psd_index = 0, local_tpe_count = 0, reg_tpe_count = 0;
-	bool use_local_tpe, non_psd_set = false, psd_set = false;
 
 	reg_info = &ab->reg_info_store[ar->pdev_idx];
 	client_type = reg_info->client_type;
 
-	for (i = 0; i < bss_conf->tx_pwr_env_num; i++) {
-		single_tpe = &bss_conf->tx_pwr_env[i];
-		pwr_category = u8_get_bits(single_tpe->tx_power_info,
-					   IEEE80211_TX_PWR_ENV_INFO_CATEGORY);
-		pwr_interpret = u8_get_bits(single_tpe->tx_power_info,
-					    IEEE80211_TX_PWR_ENV_INFO_INTERPRET);
-
-		if (pwr_category == client_type) {
-			if (pwr_interpret == IEEE80211_TPE_LOCAL_EIRP ||
-			    pwr_interpret == IEEE80211_TPE_LOCAL_EIRP_PSD)
-				local_tpe_count++;
-			else if (pwr_interpret == IEEE80211_TPE_REG_CLIENT_EIRP ||
-				 pwr_interpret == IEEE80211_TPE_REG_CLIENT_EIRP_PSD)
-				reg_tpe_count++;
-		}
-	}
+	local_tpe_count =
+		bss_conf->tpe.max_local[client_type].valid +
+		bss_conf->tpe.psd_local[client_type].valid;
+	reg_tpe_count =
+		bss_conf->tpe.max_reg_client[client_type].valid +
+		bss_conf->tpe.psd_reg_client[client_type].valid;
 
 	if (!reg_tpe_count && !local_tpe_count) {
 		ath11k_warn(ab,
@@ -7898,83 +7862,44 @@ static void ath11k_mac_parse_tx_pwr_env(struct ath11k *ar,
 		use_local_tpe = false;
 	}
 
-	for (i = 0; i < bss_conf->tx_pwr_env_num; i++) {
-		single_tpe = &bss_conf->tx_pwr_env[i];
-		pwr_category = u8_get_bits(single_tpe->tx_power_info,
-					   IEEE80211_TX_PWR_ENV_INFO_CATEGORY);
-		pwr_interpret = u8_get_bits(single_tpe->tx_power_info,
-					    IEEE80211_TX_PWR_ENV_INFO_INTERPRET);
-
-		if (pwr_category != client_type)
-			continue;
-
-		/* get local transmit power envelope */
-		if (use_local_tpe) {
-			if (pwr_interpret == IEEE80211_TPE_LOCAL_EIRP) {
-				non_psd_index = i;
-				non_psd_set = true;
-			} else if (pwr_interpret == IEEE80211_TPE_LOCAL_EIRP_PSD) {
-				psd_index = i;
-				psd_set = true;
-			}
-		/* get regulatory transmit power envelope */
-		} else {
-			if (pwr_interpret == IEEE80211_TPE_REG_CLIENT_EIRP) {
-				non_psd_index = i;
-				non_psd_set = true;
-			} else if (pwr_interpret == IEEE80211_TPE_REG_CLIENT_EIRP_PSD) {
-				psd_index = i;
-				psd_set = true;
-			}
-		}
+	if (use_local_tpe) {
+		psd = &bss_conf->tpe.psd_local[client_type];
+		if (!psd->valid)
+			psd = NULL;
+		non_psd = &bss_conf->tpe.max_local[client_type];
+		if (!non_psd->valid)
+			non_psd = NULL;
+	} else {
+		psd = &bss_conf->tpe.psd_reg_client[client_type];
+		if (!psd->valid)
+			psd = NULL;
+		non_psd = &bss_conf->tpe.max_reg_client[client_type];
+		if (!non_psd->valid)
+			non_psd = NULL;
 	}
 
-	if (non_psd_set && !psd_set) {
-		single_tpe = &bss_conf->tx_pwr_env[non_psd_index];
-		pwr_count = u8_get_bits(single_tpe->tx_power_info,
-					IEEE80211_TX_PWR_ENV_INFO_COUNT);
-		pwr_interpret = u8_get_bits(single_tpe->tx_power_info,
-					    IEEE80211_TX_PWR_ENV_INFO_INTERPRET);
+	if (non_psd && !psd) {
 		arvif->reg_tpc_info.is_psd_power = false;
 		arvif->reg_tpc_info.eirp_power = 0;
 
-		arvif->reg_tpc_info.num_pwr_levels =
-			ath11k_mac_get_tpe_count(pwr_interpret, pwr_count);
+		arvif->reg_tpc_info.num_pwr_levels = non_psd->count;
 
 		for (i = 0; i < arvif->reg_tpc_info.num_pwr_levels; i++) {
 			ath11k_dbg(ab, ATH11K_DBG_MAC,
 				   "non PSD power[%d] : %d\n",
-				   i, single_tpe->tx_power[i]);
-			arvif->reg_tpc_info.tpe[i] = single_tpe->tx_power[i] / 2;
+				   i, non_psd->power[i]);
+			arvif->reg_tpc_info.tpe[i] = non_psd->power[i] / 2;
 		}
 	}
 
-	if (psd_set) {
-		single_tpe = &bss_conf->tx_pwr_env[psd_index];
-		pwr_count = u8_get_bits(single_tpe->tx_power_info,
-					IEEE80211_TX_PWR_ENV_INFO_COUNT);
-		pwr_interpret = u8_get_bits(single_tpe->tx_power_info,
-					    IEEE80211_TX_PWR_ENV_INFO_INTERPRET);
-		arvif->reg_tpc_info.is_psd_power = true;
+	if (psd) {
+		arvif->reg_tpc_info.num_pwr_levels = psd->count;
 
-		if (pwr_count == 0) {
+		for (i = 0; i < arvif->reg_tpc_info.num_pwr_levels; i++) {
 			ath11k_dbg(ab, ATH11K_DBG_MAC,
-				   "TPE PSD power : %d\n", single_tpe->tx_power[0]);
-			arvif->reg_tpc_info.num_pwr_levels =
-				ath11k_mac_get_num_pwr_levels(&ctx->def);
-
-			for (i = 0; i < arvif->reg_tpc_info.num_pwr_levels; i++)
-				arvif->reg_tpc_info.tpe[i] = single_tpe->tx_power[0] / 2;
-		} else {
-			arvif->reg_tpc_info.num_pwr_levels =
-				ath11k_mac_get_tpe_count(pwr_interpret, pwr_count);
-
-			for (i = 0; i < arvif->reg_tpc_info.num_pwr_levels; i++) {
-				ath11k_dbg(ab, ATH11K_DBG_MAC,
-					   "TPE PSD power[%d] : %d\n",
-					   i, single_tpe->tx_power[i]);
-				arvif->reg_tpc_info.tpe[i] = single_tpe->tx_power[i] / 2;
-			}
+				   "TPE PSD power[%d] : %d\n",
+				   i, psd->power[i]);
+			arvif->reg_tpc_info.tpe[i] = psd->power[i] / 2;
 		}
 	}
 }
diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 1c3a683a3ee22..769008a518094 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -2825,17 +2825,6 @@ struct ieee80211_he_6ghz_oper {
 	u8 minrate;
 } __packed;
 
-/*
- * In "9.4.2.161 Transmit Power Envelope element" of "IEEE Std 802.11ax-2021",
- * it show four types in "Table 9-275a-Maximum Transmit Power Interpretation
- * subfield encoding", and two category for each type in "Table E-12-Regulatory
- * Info subfield encoding in the United States".
- * So it it totally max 8 Transmit Power Envelope element.
- */
-#define IEEE80211_TPE_MAX_IE_COUNT	8
-
-#define IEEE80211_TPE_MAX_POWER_COUNT	8
-
 /* transmit power interpretation type of transmit power envelope element */
 enum ieee80211_tx_power_intrpt_type {
 	IEEE80211_TPE_LOCAL_EIRP,
@@ -2844,24 +2833,107 @@ enum ieee80211_tx_power_intrpt_type {
 	IEEE80211_TPE_REG_CLIENT_EIRP_PSD,
 };
 
+/* category type of transmit power envelope element */
+enum ieee80211_tx_power_category_6ghz {
+	IEEE80211_TPE_CAT_6GHZ_DEFAULT = 0,
+	IEEE80211_TPE_CAT_6GHZ_SUBORDINATE = 1,
+};
+
+/*
+ * For IEEE80211_TPE_LOCAL_EIRP / IEEE80211_TPE_REG_CLIENT_EIRP,
+ * setting to 63.5 dBm means no constraint.
+ */
+#define IEEE80211_TPE_MAX_TX_PWR_NO_CONSTRAINT	127
+
+/*
+ * For IEEE80211_TPE_LOCAL_EIRP_PSD / IEEE80211_TPE_REG_CLIENT_EIRP_PSD,
+ * setting to 127 indicates no PSD limit for the 20 MHz channel.
+ */
+#define IEEE80211_TPE_PSD_NO_LIMIT		127
+
 /**
  * struct ieee80211_tx_pwr_env - Transmit Power Envelope
- * @tx_power_info: Transmit Power Information field
- * @tx_power: Maximum Transmit Power field
+ * @info: Transmit Power Information field
+ * @variable: Maximum Transmit Power field
  *
  * This structure represents the payload of the "Transmit Power
  * Envelope element" as described in IEEE Std 802.11ax-2021 section
  * 9.4.2.161
  */
 struct ieee80211_tx_pwr_env {
-	u8 tx_power_info;
-	s8 tx_power[IEEE80211_TPE_MAX_POWER_COUNT];
+	u8 info;
+	u8 variable[];
 } __packed;
 
 #define IEEE80211_TX_PWR_ENV_INFO_COUNT 0x7
 #define IEEE80211_TX_PWR_ENV_INFO_INTERPRET 0x38
 #define IEEE80211_TX_PWR_ENV_INFO_CATEGORY 0xC0
 
+#define IEEE80211_TX_PWR_ENV_EXT_COUNT	0xF
+
+static inline bool ieee80211_valid_tpe_element(const u8 *data, u8 len)
+{
+	const struct ieee80211_tx_pwr_env *env = (const void *)data;
+	u8 count, interpret, category;
+	u8 needed = sizeof(*env);
+	u8 N; /* also called N in the spec */
+
+	if (len < needed)
+		return false;
+
+	count = u8_get_bits(env->info, IEEE80211_TX_PWR_ENV_INFO_COUNT);
+	interpret = u8_get_bits(env->info, IEEE80211_TX_PWR_ENV_INFO_INTERPRET);
+	category = u8_get_bits(env->info, IEEE80211_TX_PWR_ENV_INFO_CATEGORY);
+
+	switch (category) {
+	case IEEE80211_TPE_CAT_6GHZ_DEFAULT:
+	case IEEE80211_TPE_CAT_6GHZ_SUBORDINATE:
+		break;
+	default:
+		return false;
+	}
+
+	switch (interpret) {
+	case IEEE80211_TPE_LOCAL_EIRP:
+	case IEEE80211_TPE_REG_CLIENT_EIRP:
+		if (count > 3)
+			return false;
+
+		/* count == 0 encodes 1 value for 20 MHz, etc. */
+		needed += count + 1;
+
+		if (len < needed)
+			return false;
+
+		/* there can be extension fields not accounted for in 'count' */
+
+		return true;
+	case IEEE80211_TPE_LOCAL_EIRP_PSD:
+	case IEEE80211_TPE_REG_CLIENT_EIRP_PSD:
+		if (count > 4)
+			return false;
+
+		N = count ? 1 << (count - 1) : 1;
+		needed += N;
+
+		if (len < needed)
+			return false;
+
+		if (len > needed) {
+			u8 K = u8_get_bits(env->variable[N],
+					   IEEE80211_TX_PWR_ENV_EXT_COUNT);
+
+			needed += 1 + K;
+			if (len < needed)
+				return false;
+		}
+
+		return true;
+	}
+
+	return false;
+}
+
 /*
  * ieee80211_he_oper_size - calculate 802.11ax HE Operations IE size
  * @he_oper_ie: byte data of the He Operations IE, stating from the byte
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index cafc664ee5318..a4efbfb8d796f 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -550,6 +550,39 @@ struct ieee80211_fils_discovery {
 	u32 max_interval;
 };
 
+#define IEEE80211_TPE_EIRP_ENTRIES_320MHZ	5
+struct ieee80211_parsed_tpe_eirp {
+	bool valid;
+	s8 power[IEEE80211_TPE_EIRP_ENTRIES_320MHZ];
+	u8 count;
+};
+
+#define IEEE80211_TPE_PSD_ENTRIES_320MHZ	16
+struct ieee80211_parsed_tpe_psd {
+	bool valid;
+	s8 power[IEEE80211_TPE_PSD_ENTRIES_320MHZ];
+	u8 count, n;
+};
+
+/**
+ * struct ieee80211_parsed_tpe - parsed transmit power envelope information
+ * @max_local: maximum local EIRP, one value for 20, 40, 80, 160, 320 MHz each
+ *	(indexed by TX power category)
+ * @max_reg_client: maximum regulatory client EIRP, one value for 20, 40, 80,
+ *	160, 320 MHz each
+ *	(indexed by TX power category)
+ * @psd_local: maximum local power spectral density, one value for each 20 MHz
+ *	subchannel per bss_conf's chanreq.oper
+ *	(indexed by TX power category)
+ * @psd_reg_client: maximum regulatory power spectral density, one value for
+ *	each 20 MHz subchannel per bss_conf's chanreq.oper
+ *	(indexed by TX power category)
+ */
+struct ieee80211_parsed_tpe {
+	struct ieee80211_parsed_tpe_eirp max_local[2], max_reg_client[2];
+	struct ieee80211_parsed_tpe_psd psd_local[2], psd_reg_client[2];
+};
+
 /**
  * struct ieee80211_bss_conf - holds the BSS's changing parameters
  *
@@ -662,8 +695,7 @@ struct ieee80211_fils_discovery {
  * @beacon_tx_rate: The configured beacon transmit rate that needs to be passed
  *	to driver when rate control is offloaded to firmware.
  * @power_type: power type of BSS for 6 GHz
- * @tx_pwr_env: transmit power envelope array of BSS.
- * @tx_pwr_env_num: number of @tx_pwr_env.
+ * @tpe: transmit power envelope information
  * @pwr_reduction: power constraint of BSS.
  * @eht_support: does this BSS support EHT
  * @csa_active: marks whether a channel switch is going on.
@@ -766,8 +798,9 @@ struct ieee80211_bss_conf {
 	u32 unsol_bcast_probe_resp_interval;
 	struct cfg80211_bitrate_mask beacon_tx_rate;
 	enum ieee80211_ap_reg_power power_type;
-	struct ieee80211_tx_pwr_env tx_pwr_env[IEEE80211_TPE_MAX_IE_COUNT];
-	u8 tx_pwr_env_num;
+
+	struct ieee80211_parsed_tpe tpe;
+
 	u8 pwr_reduction;
 	bool eht_support;
 
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index eb62b7d4b4f7e..7d541a2355f69 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -26,6 +26,7 @@
 #include <linux/idr.h>
 #include <linux/rhashtable.h>
 #include <linux/rbtree.h>
+#include <kunit/visibility.h>
 #include <net/ieee80211_radiotap.h>
 #include <net/cfg80211.h>
 #include <net/mac80211.h>
@@ -1708,7 +1709,6 @@ struct ieee802_11_elems {
 	const struct ieee80211_he_spr *he_spr;
 	const struct ieee80211_mu_edca_param_set *mu_edca_param_set;
 	const struct ieee80211_he_6ghz_capa *he_6ghz_capa;
-	const struct ieee80211_tx_pwr_env *tx_pwr_env[IEEE80211_TPE_MAX_IE_COUNT];
 	const u8 *uora_element;
 	const u8 *mesh_id;
 	const u8 *peering;
@@ -1746,6 +1746,9 @@ struct ieee802_11_elems {
 	const struct ieee80211_bandwidth_indication *bandwidth_indication;
 	const struct ieee80211_ttlm_elem *ttlm[IEEE80211_TTLM_MAX_CNT];
 
+	/* not the order in the psd values is per element, not per chandef */
+	struct ieee80211_parsed_tpe tpe;
+
 	/* length of them, respectively */
 	u8 ext_capab_len;
 	u8 ssid_len;
@@ -1764,8 +1767,6 @@ struct ieee802_11_elems {
 	u8 perr_len;
 	u8 country_elem_len;
 	u8 bssid_index_len;
-	u8 tx_pwr_env_len[IEEE80211_TPE_MAX_IE_COUNT];
-	u8 tx_pwr_env_num;
 	u8 eht_cap_len;
 
 	/* mult-link element can be de-fragmented and thus u8 is not sufficient */
@@ -2243,6 +2244,7 @@ int ieee80211_frame_duration(enum nl80211_band band, size_t len,
 void ieee80211_regulatory_limit_wmm_params(struct ieee80211_sub_if_data *sdata,
 					   struct ieee80211_tx_queue_params *qparam,
 					   int ac);
+void ieee80211_clear_tpe(struct ieee80211_parsed_tpe *tpe);
 void ieee80211_set_wmm_default(struct ieee80211_link_data *link,
 			       bool bss_notify, bool enable_qos);
 void ieee80211_xmit(struct ieee80211_sub_if_data *sdata,
@@ -2681,6 +2683,11 @@ void ieee80211_remove_wbrf(struct ieee80211_local *local, struct cfg80211_chan_d
 #define VISIBLE_IF_MAC80211_KUNIT
 ieee80211_rx_result
 ieee80211_drop_unencrypted_mgmt(struct ieee80211_rx_data *rx);
+int ieee80211_calc_chandef_subchan_offset(const struct cfg80211_chan_def *ap,
+					  u8 n_partial_subchans);
+void ieee80211_rearrange_tpe_psd(struct ieee80211_parsed_tpe_psd *psd,
+				 const struct cfg80211_chan_def *ap,
+				 const struct cfg80211_chan_def *used);
 #else
 #define EXPORT_SYMBOL_IF_MAC80211_KUNIT(sym)
 #define VISIBLE_IF_MAC80211_KUNIT static
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index e410a43dc681c..ed9851faac058 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -606,11 +606,195 @@ static bool ieee80211_chandef_usable(struct ieee80211_sub_if_data *sdata,
 	return true;
 }
 
+static int ieee80211_chandef_num_subchans(const struct cfg80211_chan_def *c)
+{
+	if (c->width == NL80211_CHAN_WIDTH_80P80)
+		return 4 + 4;
+
+	return nl80211_chan_width_to_mhz(c->width) / 20;
+}
+
+static int ieee80211_chandef_num_widths(const struct cfg80211_chan_def *c)
+{
+	switch (c->width) {
+	case NL80211_CHAN_WIDTH_20:
+	case NL80211_CHAN_WIDTH_20_NOHT:
+		return 1;
+	case NL80211_CHAN_WIDTH_40:
+		return 2;
+	case NL80211_CHAN_WIDTH_80P80:
+	case NL80211_CHAN_WIDTH_80:
+		return 3;
+	case NL80211_CHAN_WIDTH_160:
+		return 4;
+	case NL80211_CHAN_WIDTH_320:
+		return 5;
+	default:
+		WARN_ON(1);
+		return 0;
+	}
+}
+
+VISIBLE_IF_MAC80211_KUNIT int
+ieee80211_calc_chandef_subchan_offset(const struct cfg80211_chan_def *ap,
+				      u8 n_partial_subchans)
+{
+	int n = ieee80211_chandef_num_subchans(ap);
+	struct cfg80211_chan_def tmp = *ap;
+	int offset = 0;
+
+	/*
+	 * Given a chandef (in this context, it's the AP's) and a number
+	 * of subchannels that we want to look at ('n_partial_subchans'),
+	 * calculate the offset in number of subchannels between the full
+	 * and the subset with the desired width.
+	 */
+
+	/* same number of subchannels means no offset, obviously */
+	if (n == n_partial_subchans)
+		return 0;
+
+	/* don't WARN - misconfigured APs could cause this if their N > width */
+	if (n < n_partial_subchans)
+		return 0;
+
+	while (ieee80211_chandef_num_subchans(&tmp) > n_partial_subchans) {
+		u32 prev = tmp.center_freq1;
+
+		ieee80211_chandef_downgrade(&tmp, NULL);
+
+		/*
+		 * if center_freq moved up, half the original channels
+		 * are gone now but were below, so increase offset
+		 */
+		if (prev < tmp.center_freq1)
+			offset += ieee80211_chandef_num_subchans(&tmp);
+	}
+
+	/*
+	 * 80+80 with secondary 80 below primary - four subchannels for it
+	 * (we cannot downgrade *to* 80+80, so no need to consider 'tmp')
+	 */
+	if (ap->width == NL80211_CHAN_WIDTH_80P80 &&
+	    ap->center_freq2 < ap->center_freq1)
+		offset += 4;
+
+	return offset;
+}
+EXPORT_SYMBOL_IF_MAC80211_KUNIT(ieee80211_calc_chandef_subchan_offset);
+
+VISIBLE_IF_MAC80211_KUNIT void
+ieee80211_rearrange_tpe_psd(struct ieee80211_parsed_tpe_psd *psd,
+			    const struct cfg80211_chan_def *ap,
+			    const struct cfg80211_chan_def *used)
+{
+	u8 needed = ieee80211_chandef_num_subchans(used);
+	u8 have = ieee80211_chandef_num_subchans(ap);
+	u8 tmp[IEEE80211_TPE_PSD_ENTRIES_320MHZ];
+	u8 offset;
+
+	if (!psd->valid)
+		return;
+
+	/* if N is zero, all defaults were used, no point in rearranging */
+	if (!psd->n)
+		goto out;
+
+	BUILD_BUG_ON(sizeof(tmp) != sizeof(psd->power));
+
+	/*
+	 * This assumes that 'N' is consistent with the HE channel, as
+	 * it should be (otherwise the AP is broken).
+	 *
+	 * In psd->power we have values in the order 0..N, 0..K, where
+	 * N+K should cover the entire channel per 'ap', but even if it
+	 * doesn't then we've pre-filled 'unlimited' as defaults.
+	 *
+	 * But this is all the wrong order, we want to have them in the
+	 * order of the 'used' channel.
+	 *
+	 * So for example, we could have a 320 MHz EHT AP, which has the
+	 * HE channel as 80 MHz (e.g. due to puncturing, which doesn't
+	 * seem to be considered for the TPE), as follows:
+	 *
+	 * EHT  320:   |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |
+	 * HE    80:                           |  |  |  |  |
+	 * used 160:                           |  |  |  |  |  |  |  |  |
+	 *
+	 * N entries:                          |--|--|--|--|
+	 * K entries:  |--|--|--|--|--|--|--|--|           |--|--|--|--|
+	 * power idx:   4  5  6  7  8  9  10 11 0  1  2  3  12 13 14 15
+	 * full chan:   0  1  2  3  4  5  6  7  8  9  10 11 12 13 14 15
+	 * used chan:                           0  1  2  3  4  5  6  7
+	 *
+	 * The idx in the power array ('power idx') is like this since it
+	 * comes directly from the element's N and K entries in their
+	 * element order, and those are this way for HE compatibility.
+	 *
+	 * Rearrange them as desired here, first by putting them into the
+	 * 'full chan' order, and then selecting the necessary subset for
+	 * the 'used chan'.
+	 */
+
+	/* first reorder according to AP channel */
+	offset = ieee80211_calc_chandef_subchan_offset(ap, psd->n);
+	for (int i = 0; i < have; i++) {
+		if (i < offset)
+			tmp[i] = psd->power[i + psd->n];
+		else if (i < offset + psd->n)
+			tmp[i] = psd->power[i - offset];
+		else
+			tmp[i] = psd->power[i];
+	}
+
+	/*
+	 * and then select the subset for the used channel
+	 * (set everything to defaults first in case a driver is confused)
+	 */
+	memset(psd->power, IEEE80211_TPE_PSD_NO_LIMIT, sizeof(psd->power));
+	offset = ieee80211_calc_chandef_subchan_offset(ap, needed);
+	for (int i = 0; i < needed; i++)
+		psd->power[i] = tmp[offset + i];
+
+out:
+	/* limit, but don't lie if there are defaults in the data */
+	if (needed < psd->count)
+		psd->count = needed;
+}
+EXPORT_SYMBOL_IF_MAC80211_KUNIT(ieee80211_rearrange_tpe_psd);
+
+static void ieee80211_rearrange_tpe(struct ieee80211_parsed_tpe *tpe,
+				    const struct cfg80211_chan_def *ap,
+				    const struct cfg80211_chan_def *used)
+{
+	/* ignore this completely for narrow/invalid channels */
+	if (!ieee80211_chandef_num_subchans(ap) ||
+	    !ieee80211_chandef_num_subchans(used)) {
+		ieee80211_clear_tpe(tpe);
+		return;
+	}
+
+	for (int i = 0; i < 2; i++) {
+		int needed_pwr_count;
+
+		ieee80211_rearrange_tpe_psd(&tpe->psd_local[i], ap, used);
+		ieee80211_rearrange_tpe_psd(&tpe->psd_reg_client[i], ap, used);
+
+		/* limit this to the widths we actually need */
+		needed_pwr_count = ieee80211_chandef_num_widths(used);
+		if (needed_pwr_count < tpe->max_local[i].count)
+			tpe->max_local[i].count = needed_pwr_count;
+		if (needed_pwr_count < tpe->max_reg_client[i].count)
+			tpe->max_reg_client[i].count = needed_pwr_count;
+	}
+}
+
 static struct ieee802_11_elems *
 ieee80211_determine_chan_mode(struct ieee80211_sub_if_data *sdata,
 			      struct ieee80211_conn_settings *conn,
 			      struct cfg80211_bss *cbss, int link_id,
-			      struct ieee80211_chan_req *chanreq)
+			      struct ieee80211_chan_req *chanreq,
+			      struct cfg80211_chan_def *ap_chandef)
 {
 	const struct cfg80211_bss_ies *ies = rcu_dereference(cbss->ies);
 	struct ieee80211_bss *bss = (void *)cbss->priv;
@@ -623,7 +807,6 @@ ieee80211_determine_chan_mode(struct ieee80211_sub_if_data *sdata,
 	};
 	struct ieee802_11_elems *elems;
 	struct ieee80211_supported_band *sband;
-	struct cfg80211_chan_def ap_chandef;
 	enum ieee80211_conn_mode ap_mode;
 	int ret;
 
@@ -634,7 +817,7 @@ again:
 		return ERR_PTR(-ENOMEM);
 
 	ap_mode = ieee80211_determine_ap_chan(sdata, channel, bss->vht_cap_info,
-					      elems, false, conn, &ap_chandef);
+					      elems, false, conn, ap_chandef);
 
 	/* this should be impossible since parsing depends on our mode */
 	if (WARN_ON(ap_mode > conn->mode)) {
@@ -701,12 +884,12 @@ again:
 		break;
 	}
 
-	chanreq->oper = ap_chandef;
+	chanreq->oper = *ap_chandef;
 
 	/* wider-bandwidth OFDMA is only done in EHT */
 	if (conn->mode >= IEEE80211_CONN_MODE_EHT &&
 	    !(sdata->vif.driver_flags & IEEE80211_VIF_IGNORE_OFDMA_WIDER_BW))
-		chanreq->ap = ap_chandef;
+		chanreq->ap = *ap_chandef;
 	else
 		chanreq->ap.chan = NULL;
 
@@ -738,7 +921,7 @@ again:
 				       IEEE80211_CONN_BW_LIMIT_160);
 	}
 
-	if (chanreq->oper.width != ap_chandef.width || ap_mode != conn->mode)
+	if (chanreq->oper.width != ap_chandef->width || ap_mode != conn->mode)
 		sdata_info(sdata,
 			   "regulatory prevented using AP config, downgraded\n");
 
@@ -3275,9 +3458,7 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata,
 
 	sdata->vif.bss_conf.power_type = IEEE80211_REG_UNSET_AP;
 	sdata->vif.bss_conf.pwr_reduction = 0;
-	sdata->vif.bss_conf.tx_pwr_env_num = 0;
-	memset(sdata->vif.bss_conf.tx_pwr_env, 0,
-	       sizeof(sdata->vif.bss_conf.tx_pwr_env));
+	ieee80211_clear_tpe(&sdata->vif.bss_conf.tpe);
 
 	sdata->vif.cfg.eml_cap = 0;
 	sdata->vif.cfg.eml_med_sync_delay = 0;
@@ -5018,15 +5199,15 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata,
 	struct ieee80211_local *local = sdata->local;
 	bool is_6ghz = cbss->channel->band == NL80211_BAND_6GHZ;
 	struct ieee80211_chan_req chanreq = {};
+	struct cfg80211_chan_def ap_chandef;
 	struct ieee802_11_elems *elems;
 	int ret;
-	u32 i;
 
 	lockdep_assert_wiphy(local->hw.wiphy);
 
 	rcu_read_lock();
 	elems = ieee80211_determine_chan_mode(sdata, conn, cbss, link_id,
-					      &chanreq);
+					      &chanreq, &ap_chandef);
 
 	if (IS_ERR(elems)) {
 		rcu_read_unlock();
@@ -5042,35 +5223,22 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata,
 
 	if (link && is_6ghz && conn->mode >= IEEE80211_CONN_MODE_HE) {
 		const struct ieee80211_he_6ghz_oper *he_6ghz_oper;
-		struct ieee80211_bss_conf *bss_conf;
-		u8 j = 0;
-
-		bss_conf = link->conf;
 
 		if (elems->pwr_constr_elem)
-			bss_conf->pwr_reduction = *elems->pwr_constr_elem;
-
-		BUILD_BUG_ON(ARRAY_SIZE(bss_conf->tx_pwr_env) !=
-			     ARRAY_SIZE(elems->tx_pwr_env));
-
-		for (i = 0; i < elems->tx_pwr_env_num; i++) {
-			if (elems->tx_pwr_env_len[i] > sizeof(bss_conf->tx_pwr_env[j]))
-				continue;
-
-			bss_conf->tx_pwr_env_num++;
-			memcpy(&bss_conf->tx_pwr_env[j], elems->tx_pwr_env[i],
-			       elems->tx_pwr_env_len[i]);
-			j++;
-		}
+			link->conf->pwr_reduction = *elems->pwr_constr_elem;
 
 		he_6ghz_oper = ieee80211_he_6ghz_oper(elems->he_operation);
 		if (he_6ghz_oper)
-			bss_conf->power_type =
+			link->conf->power_type =
 				ieee80211_ap_power_type(he_6ghz_oper->control);
 		else
 			link_info(link,
 				  "HE 6 GHz operation missing (on %d MHz), expect issues\n",
 				  cbss->channel->center_freq);
+
+		link->conf->tpe = elems->tpe;
+		ieee80211_rearrange_tpe(&link->conf->tpe, &ap_chandef,
+					&chanreq.oper);
 	}
 	rcu_read_unlock();
 	/* the element data was RCU protected so no longer valid anyway */
@@ -7558,6 +7726,8 @@ void ieee80211_mgd_setup_link(struct ieee80211_link_data *link)
 	wiphy_delayed_work_init(&link->u.mgd.chswitch_work,
 				ieee80211_chswitch_work);
 
+	ieee80211_clear_tpe(&link->conf->tpe);
+
 	if (sdata->u.mgd.assoc_data)
 		ether_addr_copy(link->conf->addr,
 				sdata->u.mgd.assoc_data->link[link_id].addr);
diff --git a/net/mac80211/parse.c b/net/mac80211/parse.c
index 55e5497f89781..6efeb977f8e55 100644
--- a/net/mac80211/parse.c
+++ b/net/mac80211/parse.c
@@ -187,6 +187,84 @@ ieee80211_parse_extension_element(u32 *crc,
 		*crc = crc32_be(*crc, (void *)elem, elem->datalen + 2);
 }
 
+static void ieee80211_parse_tpe(struct ieee80211_parsed_tpe *tpe,
+				const u8 *data, u8 len)
+{
+	const struct ieee80211_tx_pwr_env *env = (const void *)data;
+	u8 count, interpret, category;
+	u8 *out, N, *cnt_out = NULL, *N_out = NULL;
+
+	if (!ieee80211_valid_tpe_element(data, len))
+		return;
+
+	count = u8_get_bits(env->info, IEEE80211_TX_PWR_ENV_INFO_COUNT);
+	interpret = u8_get_bits(env->info, IEEE80211_TX_PWR_ENV_INFO_INTERPRET);
+	category = u8_get_bits(env->info, IEEE80211_TX_PWR_ENV_INFO_CATEGORY);
+
+	switch (interpret) {
+	case IEEE80211_TPE_LOCAL_EIRP:
+		out = tpe->max_local[category].power;
+		cnt_out = &tpe->max_local[category].count;
+		tpe->max_local[category].valid = true;
+		break;
+	case IEEE80211_TPE_REG_CLIENT_EIRP:
+		out = tpe->max_reg_client[category].power;
+		cnt_out = &tpe->max_reg_client[category].count;
+		tpe->max_reg_client[category].valid = true;
+		break;
+	case IEEE80211_TPE_LOCAL_EIRP_PSD:
+		out = tpe->psd_local[category].power;
+		cnt_out = &tpe->psd_local[category].count;
+		N_out = &tpe->psd_local[category].n;
+		tpe->psd_local[category].valid = true;
+		break;
+	case IEEE80211_TPE_REG_CLIENT_EIRP_PSD:
+		out = tpe->psd_reg_client[category].power;
+		cnt_out = &tpe->psd_reg_client[category].count;
+		N_out = &tpe->psd_reg_client[category].n;
+		tpe->psd_reg_client[category].valid = true;
+		break;
+	}
+
+	switch (interpret) {
+	case IEEE80211_TPE_LOCAL_EIRP:
+	case IEEE80211_TPE_REG_CLIENT_EIRP:
+		/* count was validated <= 3, plus 320 MHz */
+		BUILD_BUG_ON(IEEE80211_TPE_EIRP_ENTRIES_320MHZ < 5);
+		memcpy(out, env->variable, count + 1);
+		*cnt_out = count + 1;
+		/* separately take 320 MHz if present */
+		if (count == 3 && len > sizeof(*env) + count + 1) {
+			out[4] = env->variable[count + 2];
+			*cnt_out = 5;
+		}
+		break;
+	case IEEE80211_TPE_LOCAL_EIRP_PSD:
+	case IEEE80211_TPE_REG_CLIENT_EIRP_PSD:
+		if (!count) {
+			memset(out, env->variable[0],
+			       IEEE80211_TPE_PSD_ENTRIES_320MHZ);
+			*cnt_out = IEEE80211_TPE_PSD_ENTRIES_320MHZ;
+			break;
+		}
+
+		N = 1 << (count - 1);
+		memcpy(out, env->variable, N);
+		*cnt_out = N;
+		*N_out = N;
+
+		if (len > sizeof(*env) + N) {
+			int K = u8_get_bits(env->variable[N],
+					    IEEE80211_TX_PWR_ENV_EXT_COUNT);
+
+			K = min(K, IEEE80211_TPE_PSD_ENTRIES_320MHZ - N);
+			memcpy(out + N, env->variable + N + 1, K);
+			(*cnt_out) += K;
+		}
+		break;
+	}
+}
+
 static u32
 _ieee802_11_parse_elems_full(struct ieee80211_elems_parse_params *params,
 			     struct ieee80211_elems_parse *elems_parse,
@@ -593,16 +671,9 @@ _ieee802_11_parse_elems_full(struct ieee80211_elems_parse_params *params,
 			elems->rsnx_len = elen;
 			break;
 		case WLAN_EID_TX_POWER_ENVELOPE:
-			if (elen < 1 ||
-			    elen > sizeof(struct ieee80211_tx_pwr_env))
-				break;
-
-			if (elems->tx_pwr_env_num >= ARRAY_SIZE(elems->tx_pwr_env))
+			if (params->mode < IEEE80211_CONN_MODE_HE)
 				break;
-
-			elems->tx_pwr_env[elems->tx_pwr_env_num] = (void *)pos;
-			elems->tx_pwr_env_len[elems->tx_pwr_env_num] = elen;
-			elems->tx_pwr_env_num++;
+			ieee80211_parse_tpe(&elems->tpe, pos, elen);
 			break;
 		case WLAN_EID_EXTENSION:
 			ieee80211_parse_extension_element(calc_crc ?
@@ -889,6 +960,9 @@ ieee802_11_parse_elems_full(struct ieee80211_elems_parse_params *params)
 	elems->ie_start = params->start;
 	elems->total_len = params->len;
 
+	/* set all TPE entries to unlimited (but invalid) */
+	ieee80211_clear_tpe(&elems->tpe);
+
 	nontransmitted_profile = elems_parse->scratch_pos;
 	nontransmitted_profile_len =
 		ieee802_11_find_bssid_profile(params->start, params->len,
diff --git a/net/mac80211/tests/Makefile b/net/mac80211/tests/Makefile
index 4fdaf3feaca31..511dfa2266994 100644
--- a/net/mac80211/tests/Makefile
+++ b/net/mac80211/tests/Makefile
@@ -1,3 +1,3 @@
-mac80211-tests-y += module.o elems.o mfp.o
+mac80211-tests-y += module.o elems.o mfp.o tpe.o
 
 obj-$(CONFIG_MAC80211_KUNIT_TEST) += mac80211-tests.o
diff --git a/net/mac80211/tests/tpe.c b/net/mac80211/tests/tpe.c
new file mode 100644
index 0000000000000..dd63303a2985b
--- /dev/null
+++ b/net/mac80211/tests/tpe.c
@@ -0,0 +1,284 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * KUnit tests for TPE element handling
+ *
+ * Copyright (C) 2024 Intel Corporation
+ */
+#include <kunit/test.h>
+#include "../ieee80211_i.h"
+
+MODULE_IMPORT_NS(EXPORTED_FOR_KUNIT_TESTING);
+
+static struct ieee80211_channel chan6g_1 = {
+	.band = NL80211_BAND_6GHZ,
+	.center_freq = 5955,
+};
+
+static struct ieee80211_channel chan6g_33 = {
+	.band = NL80211_BAND_6GHZ,
+	.center_freq = 6115,
+};
+
+static struct ieee80211_channel chan6g_61 = {
+	.band = NL80211_BAND_6GHZ,
+	.center_freq = 6255,
+};
+
+static const struct subchan_test_case {
+	const char *desc;
+	struct cfg80211_chan_def c;
+	u8 n;
+	int expect;
+} subchan_offset_cases[] = {
+	{
+		.desc = "identical 20 MHz",
+		.c.width = NL80211_CHAN_WIDTH_20,
+		.c.chan = &chan6g_1,
+		.c.center_freq1 = 5955,
+		.n = 1,
+		.expect = 0,
+	},
+	{
+		.desc = "identical 40 MHz",
+		.c.width = NL80211_CHAN_WIDTH_40,
+		.c.chan = &chan6g_1,
+		.c.center_freq1 = 5965,
+		.n = 2,
+		.expect = 0,
+	},
+	{
+		.desc = "identical 80+80 MHz",
+		/* not really is valid? doesn't matter for the test */
+		.c.width = NL80211_CHAN_WIDTH_80P80,
+		.c.chan = &chan6g_1,
+		.c.center_freq1 = 5985,
+		.c.center_freq2 = 6225,
+		.n = 16,
+		.expect = 0,
+	},
+	{
+		.desc = "identical 320 MHz",
+		.c.width = NL80211_CHAN_WIDTH_320,
+		.c.chan = &chan6g_1,
+		.c.center_freq1 = 6105,
+		.n = 16,
+		.expect = 0,
+	},
+	{
+		.desc = "lower 160 MHz of 320 MHz",
+		.c.width = NL80211_CHAN_WIDTH_320,
+		.c.chan = &chan6g_1,
+		.c.center_freq1 = 6105,
+		.n = 8,
+		.expect = 0,
+	},
+	{
+		.desc = "upper 160 MHz of 320 MHz",
+		.c.width = NL80211_CHAN_WIDTH_320,
+		.c.chan = &chan6g_61,
+		.c.center_freq1 = 6105,
+		.n = 8,
+		.expect = 8,
+	},
+	{
+		.desc = "upper 160 MHz of 320 MHz, go to 40",
+		.c.width = NL80211_CHAN_WIDTH_320,
+		.c.chan = &chan6g_61,
+		.c.center_freq1 = 6105,
+		.n = 2,
+		.expect = 8 + 4 + 2,
+	},
+	{
+		.desc = "secondary 80 above primary in 80+80 MHz",
+		/* not really is valid? doesn't matter for the test */
+		.c.width = NL80211_CHAN_WIDTH_80P80,
+		.c.chan = &chan6g_1,
+		.c.center_freq1 = 5985,
+		.c.center_freq2 = 6225,
+		.n = 4,
+		.expect = 0,
+	},
+	{
+		.desc = "secondary 80 below primary in 80+80 MHz",
+		/* not really is valid? doesn't matter for the test */
+		.c.width = NL80211_CHAN_WIDTH_80P80,
+		.c.chan = &chan6g_61,
+		.c.center_freq1 = 6225,
+		.c.center_freq2 = 5985,
+		.n = 4,
+		.expect = 4,
+	},
+	{
+		.desc = "secondary 80 below primary in 80+80 MHz, go to 20",
+		/* not really is valid? doesn't matter for the test */
+		.c.width = NL80211_CHAN_WIDTH_80P80,
+		.c.chan = &chan6g_61,
+		.c.center_freq1 = 6225,
+		.c.center_freq2 = 5985,
+		.n = 1,
+		.expect = 7,
+	},
+};
+
+KUNIT_ARRAY_PARAM_DESC(subchan_offset, subchan_offset_cases, desc);
+
+static void subchan_offset(struct kunit *test)
+{
+	const struct subchan_test_case *params = test->param_value;
+	int offset;
+
+	KUNIT_ASSERT_EQ(test, cfg80211_chandef_valid(&params->c), true);
+
+	offset = ieee80211_calc_chandef_subchan_offset(&params->c, params->n);
+
+	KUNIT_EXPECT_EQ(test, params->expect, offset);
+}
+
+static const struct psd_reorder_test_case {
+	const char *desc;
+	struct cfg80211_chan_def ap, used;
+	struct ieee80211_parsed_tpe_psd psd, out;
+} psd_reorder_cases[] = {
+	{
+		.desc = "no changes, 320 MHz",
+
+		.ap.width = NL80211_CHAN_WIDTH_320,
+		.ap.chan = &chan6g_1,
+		.ap.center_freq1 = 6105,
+
+		.used.width = NL80211_CHAN_WIDTH_320,
+		.used.chan = &chan6g_1,
+		.used.center_freq1 = 6105,
+
+		.psd.valid = true,
+		.psd.count = 16,
+		.psd.n = 8,
+		.psd.power = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 },
+
+		.out.valid = true,
+		.out.count = 16,
+		.out.n = 8,
+		.out.power = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 },
+	},
+	{
+		.desc = "no changes, 320 MHz, 160 MHz used, n=0",
+
+		.ap.width = NL80211_CHAN_WIDTH_320,
+		.ap.chan = &chan6g_1,
+		.ap.center_freq1 = 6105,
+
+		.used.width = NL80211_CHAN_WIDTH_160,
+		.used.chan = &chan6g_1,
+		.used.center_freq1 = 6025,
+
+		.psd.valid = true,
+		.psd.count = 16,
+		.psd.n = 0,
+		.psd.power = { 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, },
+
+		.out.valid = true,
+		.out.count = 8,
+		.out.n = 0,
+		.out.power = { 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, },
+	},
+	{
+		.desc = "320 MHz, HE is 80, used 160, all lower",
+
+		.ap.width = NL80211_CHAN_WIDTH_320,
+		.ap.chan = &chan6g_1,
+		.ap.center_freq1 = 6105,
+
+		.used.width = NL80211_CHAN_WIDTH_160,
+		.used.chan = &chan6g_1,
+		.used.center_freq1 = 6025,
+
+		.psd.valid = true,
+		.psd.count = 16,
+		.psd.n = 4,
+		.psd.power = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 },
+
+		.out.valid = true,
+		.out.count = 8,
+		.out.n = 4,
+		.out.power = { 0, 1, 2, 3, 4, 5, 6, 7, 127, 127, 127, 127, 127, 127, 127, 127},
+	},
+	{
+		.desc = "320 MHz, HE is 80, used 160, all upper",
+		/*
+		 * EHT: | | | | | | | | | | | | | | | | |
+		 * HE:                          | | | | |
+		 * used:                | | | | | | | | |
+		 */
+
+		.ap.width = NL80211_CHAN_WIDTH_320,
+		.ap.chan = &chan6g_61,
+		.ap.center_freq1 = 6105,
+
+		.used.width = NL80211_CHAN_WIDTH_160,
+		.used.chan = &chan6g_61,
+		.used.center_freq1 = 6185,
+
+		.psd.valid = true,
+		.psd.count = 16,
+		.psd.n = 4,
+		.psd.power = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 },
+
+		.out.valid = true,
+		.out.count = 8,
+		.out.n = 4,
+		.out.power = { 12, 13, 14, 15, 0, 1, 2, 3, 127, 127, 127, 127, 127, 127, 127, 127},
+	},
+	{
+		.desc = "320 MHz, HE is 80, used 160, split",
+		/*
+		 * EHT: | | | | | | | | | | | | | | | | |
+		 * HE:                  | | | | |
+		 * used:                | | | | | | | | |
+		 */
+
+		.ap.width = NL80211_CHAN_WIDTH_320,
+		.ap.chan = &chan6g_33,
+		.ap.center_freq1 = 6105,
+
+		.used.width = NL80211_CHAN_WIDTH_160,
+		.used.chan = &chan6g_33,
+		.used.center_freq1 = 6185,
+
+		.psd.valid = true,
+		.psd.count = 16,
+		.psd.n = 4,
+		.psd.power = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 },
+
+		.out.valid = true,
+		.out.count = 8,
+		.out.n = 4,
+		.out.power = { 0, 1, 2, 3, 12, 13, 14, 15, 127, 127, 127, 127, 127, 127, 127, 127},
+	},
+};
+
+KUNIT_ARRAY_PARAM_DESC(psd_reorder, psd_reorder_cases, desc);
+
+static void psd_reorder(struct kunit *test)
+{
+	const struct psd_reorder_test_case *params = test->param_value;
+	struct ieee80211_parsed_tpe_psd tmp = params->psd;
+
+	KUNIT_ASSERT_EQ(test, cfg80211_chandef_valid(&params->ap), true);
+	KUNIT_ASSERT_EQ(test, cfg80211_chandef_valid(&params->used), true);
+
+	ieee80211_rearrange_tpe_psd(&tmp, &params->ap, &params->used);
+	KUNIT_EXPECT_MEMEQ(test, &tmp, &params->out, sizeof(tmp));
+}
+
+static struct kunit_case tpe_test_cases[] = {
+	KUNIT_CASE_PARAM(subchan_offset, subchan_offset_gen_params),
+	KUNIT_CASE_PARAM(psd_reorder, psd_reorder_gen_params),
+	{}
+};
+
+static struct kunit_suite tpe = {
+	.name = "mac80211-tpe",
+	.test_cases = tpe_test_cases,
+};
+
+kunit_test_suite(tpe);
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 6139c930b572e..183de2075fb99 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -4334,3 +4334,28 @@ ieee80211_min_bw_limit_from_chandef(struct cfg80211_chan_def *chandef)
 		return IEEE80211_CONN_BW_LIMIT_20;
 	}
 }
+
+void ieee80211_clear_tpe(struct ieee80211_parsed_tpe *tpe)
+{
+	for (int i = 0; i < 2; i++) {
+		tpe->max_local[i].valid = false;
+		memset(tpe->max_local[i].power,
+		       IEEE80211_TPE_MAX_TX_PWR_NO_CONSTRAINT,
+		       sizeof(tpe->max_local[i].power));
+
+		tpe->max_reg_client[i].valid = false;
+		memset(tpe->max_reg_client[i].power,
+		       IEEE80211_TPE_MAX_TX_PWR_NO_CONSTRAINT,
+		       sizeof(tpe->max_reg_client[i].power));
+
+		tpe->psd_local[i].valid = false;
+		memset(tpe->psd_local[i].power,
+		       IEEE80211_TPE_PSD_NO_LIMIT,
+		       sizeof(tpe->psd_local[i].power));
+
+		tpe->psd_reg_client[i].valid = false;
+		memset(tpe->psd_reg_client[i].power,
+		       IEEE80211_TPE_PSD_NO_LIMIT,
+		       sizeof(tpe->psd_reg_client[i].power));
+	}
+}
-- 
GitLab


From 5a009b42e0418d30b3ffaff2f46c534cd79b3f23 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 6 May 2024 21:37:57 +0200
Subject: [PATCH 114/950] wifi: mac80211: track changes in AP's TPE

If the TPE (transmit power envelope) is changed, detect and
report that to the driver.

Reviewed-by: Miriam Rachel Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240506214536.103dda923f45.I990877e409ab8eade9ed7c172272e0cae57256cf@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h |  2 ++
 net/mac80211/mlme.c    | 16 ++++++++++++++--
 2 files changed, 16 insertions(+), 2 deletions(-)

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index a4efbfb8d796f..a59eacfe04804 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -362,6 +362,7 @@ struct ieee80211_vif_chanctx_switch {
  *	status changed.
  * @BSS_CHANGED_MLD_VALID_LINKS: MLD valid links status changed.
  * @BSS_CHANGED_MLD_TTLM: negotiated TID to link mapping was changed
+ * @BSS_CHANGED_TPE: transmit power envelope changed
  */
 enum ieee80211_bss_change {
 	BSS_CHANGED_ASSOC		= 1<<0,
@@ -398,6 +399,7 @@ enum ieee80211_bss_change {
 	BSS_CHANGED_UNSOL_BCAST_PROBE_RESP = 1<<31,
 	BSS_CHANGED_MLD_VALID_LINKS	= BIT_ULL(33),
 	BSS_CHANGED_MLD_TTLM		= BIT_ULL(34),
+	BSS_CHANGED_TPE			= BIT_ULL(35),
 
 	/* when adding here, make sure to change ieee80211_reconfig */
 };
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index ed9851faac058..08c0999746fb5 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -973,6 +973,7 @@ static int ieee80211_config_bw(struct ieee80211_link_data *link,
 	struct ieee80211_channel *channel = link->conf->chanreq.oper.chan;
 	struct ieee80211_sub_if_data *sdata = link->sdata;
 	struct ieee80211_chan_req chanreq = {};
+	struct cfg80211_chan_def ap_chandef;
 	enum ieee80211_conn_mode ap_mode;
 	u32 vht_cap_info = 0;
 	u16 ht_opmode;
@@ -988,7 +989,7 @@ static int ieee80211_config_bw(struct ieee80211_link_data *link,
 
 	ap_mode = ieee80211_determine_ap_chan(sdata, channel, vht_cap_info,
 					      elems, true, &link->u.mgd.conn,
-					      &chanreq.ap);
+					      &ap_chandef);
 
 	if (ap_mode != link->u.mgd.conn.mode) {
 		link_info(link,
@@ -998,7 +999,8 @@ static int ieee80211_config_bw(struct ieee80211_link_data *link,
 		return -EINVAL;
 	}
 
-	chanreq.oper = chanreq.ap;
+	chanreq.ap = ap_chandef;
+	chanreq.oper = ap_chandef;
 	if (link->u.mgd.conn.mode < IEEE80211_CONN_MODE_EHT ||
 	    sdata->vif.driver_flags & IEEE80211_VIF_IGNORE_OFDMA_WIDER_BW)
 		chanreq.ap.chan = NULL;
@@ -1026,6 +1028,16 @@ static int ieee80211_config_bw(struct ieee80211_link_data *link,
 			ieee80211_min_bw_limit_from_chandef(&chanreq.oper))
 		ieee80211_chandef_downgrade(&chanreq.oper, NULL);
 
+	if (ap_chandef.chan->band == NL80211_BAND_6GHZ &&
+	    link->u.mgd.conn.mode >= IEEE80211_CONN_MODE_HE) {
+		ieee80211_rearrange_tpe(&elems->tpe, &ap_chandef,
+					&chanreq.oper);
+		if (memcmp(&link->conf->tpe, &elems->tpe, sizeof(elems->tpe))) {
+			link->conf->tpe = elems->tpe;
+			*changed |= BSS_CHANGED_TPE;
+		}
+	}
+
 	if (ieee80211_chanreq_identical(&chanreq, &link->conf->chanreq))
 		return 0;
 
-- 
GitLab


From 32fca7e3820cc915d1d47e33b13da8124208b04c Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 10 May 2024 17:06:28 +0300
Subject: [PATCH 115/950] wifi: iwlwifi: dvm: clean up rs_get_rate() logic

The logic here is rather convoluted - we cannot get here with
lq_sta being NULL as mac80211 will (no longer) call us like
that, and since I removed the rate_control_send_low() call in
this function there's no longer any point in setting priv_sta
to NULL either.

So the only thing that remains to check is if we have actually
initialized our lq_sta->drv pointer, and exit if we didn't in
which case we'll use the data mac80211 already set up for the
low rate usage.

Reviewed-by: Luciano Coelho <luciano.coelho@intel.com>
Link: https://msgid.link/20240510170500.a4cdb41825eb.Id202bcc967c32829f70ab1412f8893b6eb7f78e2@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/dvm/rs.c | 21 ++++++++-------------
 1 file changed, 8 insertions(+), 13 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/rs.c b/drivers/net/wireless/intel/iwlwifi/dvm/rs.c
index f4a6f76cf193a..8879e668ef0da 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/rs.c
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/rs.c
@@ -2673,20 +2673,16 @@ static void rs_get_rate(void *priv_r, struct ieee80211_sta *sta, void *priv_sta,
 	IWL_DEBUG_RATE_LIMIT(priv, "rate scale calculate new rate for skb\n");
 
 	/* Get max rate if user set max rate */
-	if (lq_sta) {
-		lq_sta->max_rate_idx = fls(txrc->rate_idx_mask) - 1;
-		if ((sband->band == NL80211_BAND_5GHZ) &&
-		    (lq_sta->max_rate_idx != -1))
-			lq_sta->max_rate_idx += IWL_FIRST_OFDM_RATE;
-		if ((lq_sta->max_rate_idx < 0) ||
-		    (lq_sta->max_rate_idx >= IWL_RATE_COUNT))
-			lq_sta->max_rate_idx = -1;
-	}
+	lq_sta->max_rate_idx = fls(txrc->rate_idx_mask) - 1;
+	if (sband->band == NL80211_BAND_5GHZ && lq_sta->max_rate_idx != -1)
+		lq_sta->max_rate_idx += IWL_FIRST_OFDM_RATE;
+	if (lq_sta->max_rate_idx < 0 || lq_sta->max_rate_idx >= IWL_RATE_COUNT)
+		lq_sta->max_rate_idx = -1;
 
-	/* Treat uninitialized rate scaling data same as non-existing. */
-	if (lq_sta && !lq_sta->drv) {
+	if (!lq_sta->drv) {
 		IWL_DEBUG_RATE(priv, "Rate scaling not initialized yet.\n");
-		priv_sta = NULL;
+		/* mac80211 already set up the data for using low rates */
+		return;
 	}
 
 	rate_idx  = lq_sta->last_txrate_idx;
@@ -2756,7 +2752,6 @@ void iwl_rs_rate_init(struct iwl_priv *priv, struct ieee80211_sta *sta, u8 sta_i
 	lq_sta = &sta_priv->lq_sta;
 	sband = hw->wiphy->bands[conf->chandef.chan->band];
 
-
 	lq_sta->lq.sta_id = sta_id;
 
 	for (j = 0; j < LQ_SIZE; j++)
-- 
GitLab


From 7aea71803777cddf17bbb1d4e7cd1c45df0dd47a Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Fri, 10 May 2024 17:06:30 +0300
Subject: [PATCH 116/950] wifi: iwlwifi: mvm: simplify the uAPSD coexistence
 limitation code

uAPSD can't be enabled on BSS or P2P Client if there is
another active interface (e.g. associated client). Allow
the code that apply those limitations to run on BSS as well.
Also forbid uAPSD if we have an IBSS or NAN interface in
the system.
Since we are now forbidding uAPSD in any concurrency
scenario, we don't need to check the number of PHY
contexts.

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240510170500.4ac26534adf7.Ib892020177e86603b2be3a105f8717b9a15951d3@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 .../net/wireless/intel/iwlwifi/mvm/power.c    | 55 +++++++++----------
 1 file changed, 27 insertions(+), 28 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/power.c b/drivers/net/wireless/intel/iwlwifi/mvm/power.c
index 568f53c561998..72f4480ae7f5c 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/power.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/power.c
@@ -211,19 +211,29 @@ static void iwl_mvm_power_configure_uapsd(struct iwl_mvm *mvm,
 		IWL_MVM_PS_HEAVY_RX_THLD_PERCENT;
 }
 
-static void iwl_mvm_p2p_standalone_iterator(void *_data, u8 *mac,
-					    struct ieee80211_vif *vif)
+struct iwl_allow_uapsd_iface_iterator_data {
+	struct ieee80211_vif *exclude_vif;
+	bool allow_uapsd;
+};
+
+static void iwl_mvm_allow_uapsd_iterator(void *_data, u8 *mac,
+					 struct ieee80211_vif *vif)
 {
-	bool *is_p2p_standalone = _data;
+	struct iwl_allow_uapsd_iface_iterator_data *data = _data;
 
-	switch (ieee80211_vif_type_p2p(vif)) {
-	case NL80211_IFTYPE_P2P_GO:
+	/* exclude the given vif */
+	if (vif == data->exclude_vif)
+		return;
+
+	switch (vif->type) {
 	case NL80211_IFTYPE_AP:
-		*is_p2p_standalone = false;
+	case NL80211_IFTYPE_ADHOC:
+	case NL80211_IFTYPE_NAN:
+		data->allow_uapsd = false;
 		break;
 	case NL80211_IFTYPE_STATION:
 		if (vif->cfg.assoc)
-			*is_p2p_standalone = false;
+			data->allow_uapsd = false;
 		break;
 
 	default:
@@ -235,6 +245,10 @@ static bool iwl_mvm_power_allow_uapsd(struct iwl_mvm *mvm,
 				       struct ieee80211_vif *vif)
 {
 	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
+	struct iwl_allow_uapsd_iface_iterator_data data = {
+		.exclude_vif = vif,
+		.allow_uapsd = true,
+	};
 
 	if (ether_addr_equal(mvmvif->uapsd_misbehaving_ap_addr,
 			     vif->cfg.ap_addr))
@@ -249,30 +263,15 @@ static bool iwl_mvm_power_allow_uapsd(struct iwl_mvm *mvm,
 	    IEEE80211_P2P_OPPPS_ENABLE_BIT))
 		return false;
 
-	/*
-	 * Avoid using uAPSD if client is in DCM -
-	 * low latency issue in Miracast
-	 */
-	if (iwl_mvm_phy_ctx_count(mvm) >= 2)
+	if (vif->p2p && !iwl_mvm_is_p2p_scm_uapsd_supported(mvm))
 		return false;
 
-	if (vif->p2p) {
-		/* Allow U-APSD only if p2p is stand alone */
-		bool is_p2p_standalone = true;
-
-		if (!iwl_mvm_is_p2p_scm_uapsd_supported(mvm))
-			return false;
-
-		ieee80211_iterate_active_interfaces_atomic(mvm->hw,
-					IEEE80211_IFACE_ITER_NORMAL,
-					iwl_mvm_p2p_standalone_iterator,
-					&is_p2p_standalone);
-
-		if (!is_p2p_standalone)
-			return false;
-	}
+	ieee80211_iterate_active_interfaces_atomic(mvm->hw,
+				IEEE80211_IFACE_ITER_NORMAL,
+				iwl_mvm_allow_uapsd_iterator,
+				&data);
 
-	return true;
+	return data.allow_uapsd;
 }
 
 static bool iwl_mvm_power_is_radar(struct ieee80211_vif *vif)
-- 
GitLab


From 42884d2c2f512d7123962ab0425c782316f3805f Mon Sep 17 00:00:00 2001
From: Avraham Stern <avraham.stern@intel.com>
Date: Fri, 10 May 2024 17:06:31 +0300
Subject: [PATCH 117/950] wifi: iwlwifi: mvm: allow UAPSD when in SCM

Allow UAPSD when P2P and BSS interfaces share the same channel.

Signed-off-by: Avraham Stern <avraham.stern@intel.com>
Reviewed-by: Luciano Coelho <luciano.coelho@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240510170500.1ec19d432497.Id6de5337c878fa70e85bfcf6f4e0e34ce60756fb@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/power.c | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/power.c b/drivers/net/wireless/intel/iwlwifi/mvm/power.c
index 72f4480ae7f5c..cc7176b0be4fc 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/power.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/power.c
@@ -212,7 +212,7 @@ static void iwl_mvm_power_configure_uapsd(struct iwl_mvm *mvm,
 }
 
 struct iwl_allow_uapsd_iface_iterator_data {
-	struct ieee80211_vif *exclude_vif;
+	struct ieee80211_vif *current_vif;
 	bool allow_uapsd;
 };
 
@@ -220,9 +220,12 @@ static void iwl_mvm_allow_uapsd_iterator(void *_data, u8 *mac,
 					 struct ieee80211_vif *vif)
 {
 	struct iwl_allow_uapsd_iface_iterator_data *data = _data;
+	struct iwl_mvm_vif *other_mvmvif = iwl_mvm_vif_from_mac80211(vif);
+	struct iwl_mvm_vif *curr_mvmvif =
+		iwl_mvm_vif_from_mac80211(data->current_vif);
 
 	/* exclude the given vif */
-	if (vif == data->exclude_vif)
+	if (vif == data->current_vif)
 		return;
 
 	switch (vif->type) {
@@ -232,7 +235,12 @@ static void iwl_mvm_allow_uapsd_iterator(void *_data, u8 *mac,
 		data->allow_uapsd = false;
 		break;
 	case NL80211_IFTYPE_STATION:
-		if (vif->cfg.assoc)
+		/* allow UAPSD if P2P interface and BSS station interface share
+		 * the same channel.
+		 */
+		if (vif->cfg.assoc && other_mvmvif->deflink.phy_ctxt &&
+		    curr_mvmvif->deflink.phy_ctxt &&
+		    other_mvmvif->deflink.phy_ctxt->id != curr_mvmvif->deflink.phy_ctxt->id)
 			data->allow_uapsd = false;
 		break;
 
@@ -246,7 +254,7 @@ static bool iwl_mvm_power_allow_uapsd(struct iwl_mvm *mvm,
 {
 	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
 	struct iwl_allow_uapsd_iface_iterator_data data = {
-		.exclude_vif = vif,
+		.current_vif = vif,
 		.allow_uapsd = true,
 	};
 
-- 
GitLab


From 8a29b006dc39484624f841c1e1c30a64a523bbc8 Mon Sep 17 00:00:00 2001
From: Avraham Stern <avraham.stern@intel.com>
Date: Fri, 10 May 2024 17:06:32 +0300
Subject: [PATCH 118/950] wifi: iwlwifi: mvm: debugfs: add entry for setting
 maximum TXOP time

Add an entry for setting the maximum TXOP time in microseconds.
The configured value can be read from the same entry.

Signed-off-by: Avraham Stern <avraham.stern@intel.com>
Reviewed-by: Gregory Greenman <gregory.greenman@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240510170500.b8d17a9c1731.I57c33574a61edd68bd0ec1aa7009f31111fd7efe@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 .../wireless/intel/iwlwifi/mvm/debugfs-vif.c  | 38 +++++++++++++++++++
 drivers/net/wireless/intel/iwlwifi/mvm/mvm.h  |  3 ++
 .../net/wireless/intel/iwlwifi/mvm/rs-fw.c    |  3 ++
 3 files changed, 44 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c
index 17c97dfbc62aa..25f07e00db429 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c
@@ -692,6 +692,42 @@ static ssize_t iwl_dbgfs_quota_min_read(struct file *file,
 	return simple_read_from_buffer(user_buf, count, ppos, buf, len);
 }
 
+static ssize_t iwl_dbgfs_max_tx_op_write(struct ieee80211_vif *vif, char *buf,
+					 size_t count, loff_t *ppos)
+{
+	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
+	struct iwl_mvm *mvm = mvmvif->mvm;
+	u16 value;
+	int ret;
+
+	ret = kstrtou16(buf, 0, &value);
+	if (ret)
+		return ret;
+
+	mutex_lock(&mvm->mutex);
+	mvmvif->max_tx_op = value;
+	mutex_unlock(&mvm->mutex);
+
+	return count;
+}
+
+static ssize_t iwl_dbgfs_max_tx_op_read(struct file *file,
+					char __user *user_buf,
+					size_t count, loff_t *ppos)
+{
+	struct ieee80211_vif *vif = file->private_data;
+	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
+	struct iwl_mvm *mvm = mvmvif->mvm;
+	char buf[10];
+	int len;
+
+	mutex_lock(&mvm->mutex);
+	len = scnprintf(buf, sizeof(buf), "%hu\n", mvmvif->max_tx_op);
+	mutex_unlock(&mvm->mutex);
+
+	return simple_read_from_buffer(user_buf, count, ppos, buf, len);
+}
+
 static ssize_t iwl_dbgfs_int_mlo_scan_write(struct ieee80211_vif *vif,
 					    char *buf, size_t count,
 					    loff_t *ppos)
@@ -801,6 +837,7 @@ MVM_DEBUGFS_READ_WRITE_FILE_OPS(uapsd_misbehaving, 20);
 MVM_DEBUGFS_READ_WRITE_FILE_OPS(rx_phyinfo, 10);
 MVM_DEBUGFS_READ_WRITE_FILE_OPS(quota_min, 32);
 MVM_DEBUGFS_READ_FILE_OPS(os_device_timediff);
+MVM_DEBUGFS_READ_WRITE_FILE_OPS(max_tx_op, 10);
 MVM_DEBUGFS_WRITE_FILE_OPS(int_mlo_scan, 32);
 MVM_DEBUGFS_READ_WRITE_FILE_OPS(esr_disable_reason, 32);
 
@@ -830,6 +867,7 @@ void iwl_mvm_vif_add_debugfs(struct ieee80211_hw *hw, struct ieee80211_vif *vif)
 	MVM_DEBUGFS_ADD_FILE_VIF(rx_phyinfo, mvmvif->dbgfs_dir, 0600);
 	MVM_DEBUGFS_ADD_FILE_VIF(quota_min, mvmvif->dbgfs_dir, 0600);
 	MVM_DEBUGFS_ADD_FILE_VIF(os_device_timediff, mvmvif->dbgfs_dir, 0400);
+	MVM_DEBUGFS_ADD_FILE_VIF(max_tx_op, mvmvif->dbgfs_dir, 0600);
 	debugfs_create_bool("ftm_unprotected", 0200, mvmvif->dbgfs_dir,
 			    &mvmvif->ftm_unprotected);
 	MVM_DEBUGFS_ADD_FILE_VIF(int_mlo_scan, mvmvif->dbgfs_dir, 0200);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index 1f58c727fa632..ca1c5944da670 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -426,6 +426,7 @@ struct iwl_mvm_esr_exit {
  * @csa_bcn_pending: indicates that we are waiting for a beacon on a new channel
  * @csa_blocks_tx: CSA is blocking TX
  * @features: hw features active for this vif
+ * @max_tx_op: max TXOP in usecs for all ACs, zero for no limit.
  * @ap_beacon_time: AP beacon time for synchronisation (on older FW)
  * @bf_enabled: indicates if beacon filtering is enabled
  * @ba_enabled: indicated if beacon abort is enabled
@@ -538,6 +539,8 @@ struct iwl_mvm_vif {
 		struct ieee80211_key_conf __rcu *keys[2];
 	} bcn_prot;
 
+	u16 max_tx_op;
+
 	u16 link_selection_res;
 	u8 link_selection_primary;
 	u8 primary_link;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c
index 3ba62fb2c85e2..884fd56e74263 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c
@@ -609,6 +609,7 @@ void iwl_mvm_rs_fw_rate_init(struct iwl_mvm *mvm,
 				cpu_to_le16(max_amsdu_len) : 0,
 	};
 	unsigned int link_id = link_conf->link_id;
+	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(mvmsta->vif);
 	int cmd_ver;
 	int ret;
 
@@ -654,6 +655,8 @@ void iwl_mvm_rs_fw_rate_init(struct iwl_mvm *mvm,
 	 */
 	sta->deflink.agg.max_amsdu_len = max_amsdu_len;
 
+	cfg_cmd.max_tx_op = cpu_to_le16(mvmvif->max_tx_op);
+
 	cmd_ver = iwl_fw_lookup_cmd_ver(mvm->fw, cmd_id, 0);
 	IWL_DEBUG_RATE(mvm, "TLC CONFIG CMD, sta_id=%d, max_ch_width=%d, mode=%d\n",
 		       cfg_cmd.sta_id, cfg_cmd.max_ch_width, cfg_cmd.mode);
-- 
GitLab


From 7c789b91f538b3a31b1512b46873174fd3960fc3 Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Fri, 10 May 2024 17:06:34 +0300
Subject: [PATCH 119/950] wifi: iwlwifi: mvm: define link_sta in the relevant
 scope

The link_sta pointer is now only used inside this if, so define it inside
its scope.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240510170500.e0a1dd285d9a.Id5ff16fb98af0c5f533aed6b5ec3cc856401e488@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
index d78af29281522..8bbef4454399f 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
@@ -2032,7 +2032,6 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 	u32 len;
 	u32 pkt_len = iwl_rx_packet_payload_len(pkt);
 	struct ieee80211_sta *sta = NULL;
-	struct ieee80211_link_sta *link_sta = NULL;
 	struct sk_buff *skb;
 	u8 crypt_len = 0;
 	u8 sta_id = le32_get_bits(desc->status, IWL_RX_MPDU_STATUS_STA_ID);
@@ -2185,6 +2184,8 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 
 	if (desc->status & cpu_to_le32(IWL_RX_MPDU_STATUS_SRC_STA_FOUND)) {
 		if (!WARN_ON_ONCE(sta_id >= mvm->fw->ucode_capa.num_stations)) {
+			struct ieee80211_link_sta *link_sta;
+
 			sta = rcu_dereference(mvm->fw_id_to_mac_id[sta_id]);
 			if (IS_ERR(sta))
 				sta = NULL;
-- 
GitLab


From bb3261943fd8b4b0d21c9f609eb42b6c948e4578 Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Fri, 10 May 2024 17:06:36 +0300
Subject: [PATCH 120/950] wifi: iwlwifi: mvm: set A-MSDU size on the correct
 link

The existing code sets the max A-MSDU size to the deflink, set it
on the given link instead.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240510170500.4de5c1a031ca.I063bc1508e5068b32e321b0f268bc51dba0c0747@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c
index 884fd56e74263..031b5e70d1811 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c
@@ -653,7 +653,7 @@ void iwl_mvm_rs_fw_rate_init(struct iwl_mvm *mvm,
 	 * since TLC offload works with one mode we can assume
 	 * that only vht/ht is used and also set it as station max amsdu
 	 */
-	sta->deflink.agg.max_amsdu_len = max_amsdu_len;
+	link_sta->agg.max_amsdu_len = max_amsdu_len;
 
 	cfg_cmd.max_tx_op = cpu_to_le16(mvmvif->max_tx_op);
 
-- 
GitLab


From b79b56091d2456491f4471bea202453f9755a42d Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Fri, 10 May 2024 17:06:37 +0300
Subject: [PATCH 121/950] wifi: iwlwifi: mvm: call
 ieee80211_sta_recalc_aggregates on A-MSDU size update

The driver needs to call this function when the A-MSDU size changes.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240510170500.632ee6612a79.Ice3a536a4cbfe60d0edfa231fcb79ee7ab9495dd@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c
index 031b5e70d1811..05715e5af6ab3 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c
@@ -514,6 +514,8 @@ void iwl_mvm_tlc_update_notif(struct iwl_mvm *mvm,
 				link_sta->agg.max_tid_amsdu_len[i] = 1;
 		}
 
+		ieee80211_sta_recalc_aggregates(sta);
+
 		IWL_DEBUG_RATE(mvm,
 			       "AMSDU update. AMSDU size: %d, AMSDU selected size: %d, AMSDU TID bitmap 0x%X\n",
 			       le32_to_cpu(notif->amsdu_size), size,
@@ -654,6 +656,7 @@ void iwl_mvm_rs_fw_rate_init(struct iwl_mvm *mvm,
 	 * that only vht/ht is used and also set it as station max amsdu
 	 */
 	link_sta->agg.max_amsdu_len = max_amsdu_len;
+	ieee80211_sta_recalc_aggregates(sta);
 
 	cfg_cmd.max_tx_op = cpu_to_le16(mvmvif->max_tx_op);
 
-- 
GitLab


From d49c5be9f7fe4864f698c15bf332524f2be3ee69 Mon Sep 17 00:00:00 2001
From: Andrei Otcheretianski <andrei.otcheretianski@intel.com>
Date: Fri, 10 May 2024 17:06:38 +0300
Subject: [PATCH 122/950] wifi: iwlwifi: mvm: Don't set NO_HT40+/- flags on 6
 GHz band

These flags are not needed on 6 GHz channels, and anyway they were set
incorrectly.
This in turn resulted in alternating channel flags, preventing reg domain
rules to be merged together, so cfg80211 couldn't even send them to the
user space, as the regulatory domain was too large.
Fix it.

Signed-off-by: Andrei Otcheretianski <andrei.otcheretianski@intel.com>
Reviewed-by: Luciano Coelho <luciano.coelho@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240510170500.b0d51b2229f8.I092e21cde43320ffc2eff17f5748ff9c87c87fcf@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
index 149903f525673..cf5c9500af8c8 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
@@ -1625,11 +1625,15 @@ static u32 iwl_nvm_get_regdom_bw_flags(const u16 *nvm_chan,
 			flags &= ~NL80211_RRF_NO_HT40PLUS;
 		if (nvm_chan[ch_idx] >= FIRST_2GHZ_HT_MINUS)
 			flags &= ~NL80211_RRF_NO_HT40MINUS;
-	} else if (nvm_flags & NVM_CHANNEL_40MHZ) {
+	} else if (ch_idx < NUM_2GHZ_CHANNELS + NUM_5GHZ_CHANNELS &&
+		   nvm_flags & NVM_CHANNEL_40MHZ) {
 		if ((ch_idx - NUM_2GHZ_CHANNELS) % 2 == 0)
 			flags &= ~NL80211_RRF_NO_HT40PLUS;
 		else
 			flags &= ~NL80211_RRF_NO_HT40MINUS;
+	} else if (nvm_flags & NVM_CHANNEL_40MHZ) {
+		flags &= ~NL80211_RRF_NO_HT40PLUS;
+		flags &= ~NL80211_RRF_NO_HT40MINUS;
 	}
 
 	if (!(nvm_flags & NVM_CHANNEL_80MHZ))
-- 
GitLab


From 37733bffda3285d18bd1d72c14b3a1cf39c56a5e Mon Sep 17 00:00:00 2001
From: Shahar S Matityahu <shahar.s.matityahu@intel.com>
Date: Fri, 10 May 2024 17:06:40 +0300
Subject: [PATCH 123/950] wifi: iwlwifi: remove fw_running op

fw_running assumes that memory can be retrieved only after alive.
This assumption is no longer true as we support dump before alive.
To avoid invalid access to the NIC, check that STATUS_DEVICE_ENABLED
bit in trans status is set before dumping instead of the prior check.

Signed-off-by: Shahar S Matityahu <shahar.s.matityahu@intel.com>
Reviewed-by: Luciano Coelho <luciano.coelho@intel.com>
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240510170500.ca07138cedeb.I090e31d3eaeb4ba19f5f84aba997ccd36927e9ac@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/debugfs.c | 3 +--
 drivers/net/wireless/intel/iwlwifi/fw/runtime.h | 1 -
 drivers/net/wireless/intel/iwlwifi/mvm/ops.c    | 6 ------
 3 files changed, 1 insertion(+), 9 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/debugfs.c b/drivers/net/wireless/intel/iwlwifi/fw/debugfs.c
index 751a125a1566f..893b21fcaf87c 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/debugfs.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/debugfs.c
@@ -230,8 +230,7 @@ static ssize_t iwl_dbgfs_send_hcmd_write(struct iwl_fw_runtime *fwrt, char *buf,
 		.data = { NULL, },
 	};
 
-	if (fwrt->ops && fwrt->ops->fw_running &&
-	    !fwrt->ops->fw_running(fwrt->ops_ctx))
+	if (!iwl_trans_fw_running(fwrt->trans))
 		return -EIO;
 
 	if (count < header_size + 1 || count > 1024 * 4)
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/runtime.h b/drivers/net/wireless/intel/iwlwifi/fw/runtime.h
index 9122f9a1260ae..d201440066ea9 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/runtime.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/runtime.h
@@ -19,7 +19,6 @@
 struct iwl_fw_runtime_ops {
 	void (*dump_start)(void *ctx);
 	void (*dump_end)(void *ctx);
-	bool (*fw_running)(void *ctx);
 	int (*send_hcmd)(void *ctx, struct iwl_host_cmd *host_cmd);
 	bool (*d3_debug_enable)(void *ctx);
 };
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
index 53283d052e189..f19577474f4be 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
@@ -770,11 +770,6 @@ static void iwl_mvm_fwrt_dump_end(void *ctx)
 	mutex_unlock(&mvm->mutex);
 }
 
-static bool iwl_mvm_fwrt_fw_running(void *ctx)
-{
-	return iwl_mvm_firmware_running(ctx);
-}
-
 static int iwl_mvm_fwrt_send_hcmd(void *ctx, struct iwl_host_cmd *host_cmd)
 {
 	struct iwl_mvm *mvm = (struct iwl_mvm *)ctx;
@@ -795,7 +790,6 @@ static bool iwl_mvm_d3_debug_enable(void *ctx)
 static const struct iwl_fw_runtime_ops iwl_mvm_fwrt_ops = {
 	.dump_start = iwl_mvm_fwrt_dump_start,
 	.dump_end = iwl_mvm_fwrt_dump_end,
-	.fw_running = iwl_mvm_fwrt_fw_running,
 	.send_hcmd = iwl_mvm_fwrt_send_hcmd,
 	.d3_debug_enable = iwl_mvm_d3_debug_enable,
 };
-- 
GitLab


From 797af7ac20283d10818e9fc21b405dcaf6902b69 Mon Sep 17 00:00:00 2001
From: Chaya Rachel Ivgi <chaya.rachel.ivgi@intel.com>
Date: Fri, 10 May 2024 17:06:41 +0300
Subject: [PATCH 124/950] wifi: iwlwifi: remove redundant reading from NVM file

The driver reads xtal_calib from NVM file, but actually never uses it.
This is only used in dvm driver.

Signed-off-by: Chaya Rachel Ivgi <chaya.rachel.ivgi@intel.com>
Reviewed-by: Luciano Coelho <luciano.coelho@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240510170500.c4d1a4571049.I7d7b73dccb793e220f023e0d049b082b043ca95e@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c | 8 +-------
 1 file changed, 1 insertion(+), 7 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
index cf5c9500af8c8..5132964661c80 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
@@ -38,16 +38,13 @@ enum nvm_offsets {
 	N_HW_ADDRS = 3,
 	NVM_CHANNELS = 0x1E0 - NVM_SW_SECTION,
 
-	/* NVM calibration section offset (in words) definitions */
-	NVM_CALIB_SECTION = 0x2B8,
-	XTAL_CALIB = 0x316 - NVM_CALIB_SECTION,
-
 	/* NVM REGULATORY -Section offset (in words) definitions */
 	NVM_CHANNELS_SDP = 0,
 };
 
 enum ext_nvm_offsets {
 	/* NVM HW-Section offset (in words) definitions */
+
 	MAC_ADDRESS_OVERRIDE_EXT_NVM = 1,
 
 	/* NVM SW-Section offset (in words) definitions */
@@ -1574,9 +1571,6 @@ iwl_parse_nvm_data(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 			     &regulatory[NVM_CHANNELS_SDP] :
 			     &nvm_sw[NVM_CHANNELS];
 
-		/* in family 8000 Xtal calibration values moved to OTP */
-		data->xtal_calib[0] = *(nvm_calib + XTAL_CALIB);
-		data->xtal_calib[1] = *(nvm_calib + XTAL_CALIB + 1);
 		lar_enabled = true;
 	} else {
 		u16 lar_offset = data->nvm_version < 0xE39 ?
-- 
GitLab


From 6a32ebd534ff31e93d6ef3ee5640b97efff8185d Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Sun, 12 May 2024 07:30:55 +0300
Subject: [PATCH 125/950] wifi: iwlwifi: mvm: don't always set antenna in
 beacon template cmd

This needs to be set only if the FW is not capable of selecting an
antenna on its own.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240512072733.73d790911268.I158dc1dbc9c2e199c69d8213e5496d2de72da28b@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
index 5a06f887769a6..f6baf7135efd9 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
@@ -1010,12 +1010,13 @@ static void iwl_mvm_mac_ctxt_set_tx(struct iwl_mvm *mvm,
 	tx->tx_flags = cpu_to_le32(tx_flags);
 
 	if (!fw_has_capa(&mvm->fw->ucode_capa,
-			 IWL_UCODE_TLV_CAPA_BEACON_ANT_SELECTION))
+			 IWL_UCODE_TLV_CAPA_BEACON_ANT_SELECTION)) {
 		iwl_mvm_toggle_tx_ant(mvm, &mvm->mgmt_last_antenna_idx);
 
-	tx->rate_n_flags =
-		cpu_to_le32(BIT(mvm->mgmt_last_antenna_idx) <<
-			    RATE_MCS_ANT_POS);
+		tx->rate_n_flags =
+			cpu_to_le32(BIT(mvm->mgmt_last_antenna_idx) <<
+				    RATE_MCS_ANT_POS);
+	}
 
 	rate = iwl_mvm_mac_ctxt_get_beacon_rate(mvm, info, vif);
 
-- 
GitLab


From ca88709d10b1c21aca2bf58fa528723a81322b03 Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Sun, 12 May 2024 07:30:56 +0300
Subject: [PATCH 126/950] wifi: iwlwifi: mvm: Use the SMPS cfg of the correct
 link

The exiting code is checking the SMPS mode of deflink.
Use the SMPS mode of the link_sta function parameter.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240512072733.f3e2834e78f5.Ie24b431a6ad0dbf977afbbd4d2116bfe2426a0d5@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c
index b7a461dba41ee..3b2875f2cab74 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c
@@ -470,7 +470,7 @@ static int iwl_mvm_mld_cfg_sta(struct iwl_mvm *mvm, struct ieee80211_sta *sta,
 		break;
 	}
 
-	switch (sta->deflink.smps_mode) {
+	switch (link_sta->smps_mode) {
 	case IEEE80211_SMPS_AUTOMATIC:
 	case IEEE80211_SMPS_NUM_MODES:
 		WARN_ON(1);
-- 
GitLab


From bc4867aabfead3d8eb64827208f59bc1d517e213 Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Sun, 12 May 2024 07:30:57 +0300
Subject: [PATCH 127/950] wifi: iwlwifi: mvm: add a of print of a few commands

This is needed for debugging.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240512072733.65fc46e2ffbc.I19d4ef2cc06bfee7d9644a376d39399f0f6eaa15@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/ops.c | 25 ++++++++++++++++++++
 1 file changed, 25 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
index f19577474f4be..c3cd5ab11aec1 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
@@ -572,6 +572,7 @@ static const struct iwl_hcmd_names iwl_mvm_legacy_names[] = {
 	HCMD_NAME(D0I3_END_CMD),
 	HCMD_NAME(LTR_CONFIG),
 	HCMD_NAME(LDBG_CONFIG_CMD),
+	HCMD_NAME(DEBUG_LOG_MSG),
 };
 
 /* Please keep this array *SORTED* by hex value.
@@ -579,6 +580,7 @@ static const struct iwl_hcmd_names iwl_mvm_legacy_names[] = {
  */
 static const struct iwl_hcmd_names iwl_mvm_system_names[] = {
 	HCMD_NAME(SHARED_MEM_CFG_CMD),
+	HCMD_NAME(SOC_CONFIGURATION_CMD),
 	HCMD_NAME(INIT_EXTENDED_CFG_CMD),
 	HCMD_NAME(FW_ERROR_RECOVERY_CMD),
 	HCMD_NAME(RFI_CONFIG_CMD),
@@ -593,8 +595,10 @@ static const struct iwl_hcmd_names iwl_mvm_system_names[] = {
  * Access is done through binary search
  */
 static const struct iwl_hcmd_names iwl_mvm_mac_conf_names[] = {
+	HCMD_NAME(LOW_LATENCY_CMD),
 	HCMD_NAME(CHANNEL_SWITCH_TIME_EVENT_CMD),
 	HCMD_NAME(SESSION_PROTECTION_CMD),
+	HCMD_NAME(CANCEL_CHANNEL_SWITCH_CMD),
 	HCMD_NAME(MAC_CONFIG_CMD),
 	HCMD_NAME(LINK_CONFIG_CMD),
 	HCMD_NAME(STA_CONFIG_CMD),
@@ -603,7 +607,10 @@ static const struct iwl_hcmd_names iwl_mvm_mac_conf_names[] = {
 	HCMD_NAME(STA_DISABLE_TX_CMD),
 	HCMD_NAME(ROC_CMD),
 	HCMD_NAME(ROC_NOTIF),
+	HCMD_NAME(CHANNEL_SWITCH_ERROR_NOTIF),
+	HCMD_NAME(MISSED_VAP_NOTIF),
 	HCMD_NAME(SESSION_PROTECTION_NOTIF),
+	HCMD_NAME(PROBE_RESPONSE_DATA_NOTIF),
 	HCMD_NAME(CHANNEL_SWITCH_START_NOTIF),
 };
 
@@ -627,6 +634,8 @@ static const struct iwl_hcmd_names iwl_mvm_data_path_names[] = {
 	HCMD_NAME(DQA_ENABLE_CMD),
 	HCMD_NAME(UPDATE_MU_GROUPS_CMD),
 	HCMD_NAME(TRIGGER_RX_QUEUES_NOTIF_CMD),
+	HCMD_NAME(WNM_PLATFORM_PTM_REQUEST_CMD),
+	HCMD_NAME(WNM_80211V_TIMING_MEASUREMENT_CONFIG_CMD),
 	HCMD_NAME(STA_HE_CTXT_CMD),
 	HCMD_NAME(RLC_CONFIG_CMD),
 	HCMD_NAME(RFH_QUEUE_CONFIG_CMD),
@@ -650,6 +659,21 @@ static const struct iwl_hcmd_names iwl_mvm_statistics_names[] = {
 	HCMD_NAME(STATISTICS_OPER_PART1_NOTIF),
 };
 
+/* Please keep this array *SORTED* by hex value.
+ * Access is done through binary search
+ */
+static const struct iwl_hcmd_names iwl_mvm_debug_names[] = {
+	HCMD_NAME(LMAC_RD_WR),
+	HCMD_NAME(UMAC_RD_WR),
+	HCMD_NAME(HOST_EVENT_CFG),
+	HCMD_NAME(DBGC_SUSPEND_RESUME),
+	HCMD_NAME(BUFFER_ALLOCATION),
+	HCMD_NAME(GET_TAS_STATUS),
+	HCMD_NAME(FW_DUMP_COMPLETE_CMD),
+	HCMD_NAME(FW_CLEAR_BUFFER),
+	HCMD_NAME(MFU_ASSERT_DUMP_NTF),
+};
+
 /* Please keep this array *SORTED* by hex value.
  * Access is done through binary search
  */
@@ -705,6 +729,7 @@ static const struct iwl_hcmd_arr iwl_mvm_groups[] = {
 	[PROT_OFFLOAD_GROUP] = HCMD_ARR(iwl_mvm_prot_offload_names),
 	[REGULATORY_AND_NVM_GROUP] =
 		HCMD_ARR(iwl_mvm_regulatory_and_nvm_names),
+	[DEBUG_GROUP] = HCMD_ARR(iwl_mvm_debug_names),
 	[STATISTICS_GROUP] = HCMD_ARR(iwl_mvm_statistics_names),
 };
 
-- 
GitLab


From e213eb95a49724a8168e6ef48a62fa06a785fa41 Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Sun, 12 May 2024 07:30:58 +0300
Subject: [PATCH 128/950] wifi: iwlwifi: bump FW API to 91 for BZ/SC devices

Start supporting API version 91 for new devices.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240512072733.27c00099e8b7.I99b4f24bba073414dd04a6e04a359c7fbba52990@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/cfg/bz.c | 2 +-
 drivers/net/wireless/intel/iwlwifi/cfg/sc.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/bz.c b/drivers/net/wireless/intel/iwlwifi/cfg/bz.c
index bc98b87cf2a13..45905e57e084a 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/bz.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/bz.c
@@ -10,7 +10,7 @@
 #include "fw/api/txq.h"
 
 /* Highest firmware API version supported */
-#define IWL_BZ_UCODE_API_MAX	90
+#define IWL_BZ_UCODE_API_MAX	91
 
 /* Lowest firmware API version supported */
 #define IWL_BZ_UCODE_API_MIN	80
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/sc.c b/drivers/net/wireless/intel/iwlwifi/cfg/sc.c
index 9b79279fd76ca..653279e089273 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/sc.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/sc.c
@@ -10,7 +10,7 @@
 #include "fw/api/txq.h"
 
 /* Highest firmware API version supported */
-#define IWL_SC_UCODE_API_MAX	90
+#define IWL_SC_UCODE_API_MAX	91
 
 /* Lowest firmware API version supported */
 #define IWL_SC_UCODE_API_MIN	82
-- 
GitLab


From 472a15d319b8560da94c7c6e94ead2fea491dd1c Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Sun, 12 May 2024 07:30:59 +0300
Subject: [PATCH 129/950] wifi: iwlwifi: mvm: mark bad no-data RX as having bad
 PLCP

Just like with any other frame, mac80211 will do sanity checks
on no-data RX (representing e.g. sounding PPDUs), and if e.g.
the NSS is wrong, it will warn. This isn't a good idea if we
already know the frame wasn't received well, e.g. has bad PLCP.
Unless the firmware reports "no error", set the bad PLCP flag
to skip checks in mac80211.

Also, since we're now extracting two different values from the
info field, use le32_get_bits() for both.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Reviewed-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240512072733.e6adcb9a6ece.Ic14c2e8ed5e80d48af78b2f04e9f08beeb62d68e@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
index 8bbef4454399f..2f9e2254fb467 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
@@ -2361,7 +2361,6 @@ void iwl_mvm_rx_monitor_no_data(struct iwl_mvm *mvm, struct napi_struct *napi,
 	struct iwl_rx_packet *pkt = rxb_addr(rxb);
 	struct iwl_rx_no_data_ver_3 *desc = (void *)pkt->data;
 	u32 rssi;
-	u32 info_type;
 	struct ieee80211_sta *sta = NULL;
 	struct sk_buff *skb;
 	struct iwl_mvm_rx_phy_data phy_data;
@@ -2374,7 +2373,6 @@ void iwl_mvm_rx_monitor_no_data(struct iwl_mvm *mvm, struct napi_struct *napi,
 		return;
 
 	rssi = le32_to_cpu(desc->rssi);
-	info_type = le32_to_cpu(desc->info) & RX_NO_DATA_INFO_TYPE_MSK;
 	phy_data.d0 = desc->phy_info[0];
 	phy_data.d1 = desc->phy_info[1];
 	phy_data.phy_info = IWL_RX_MPDU_PHY_TSF_OVERLOAD;
@@ -2426,7 +2424,12 @@ void iwl_mvm_rx_monitor_no_data(struct iwl_mvm *mvm, struct napi_struct *napi,
 	/* 0-length PSDU */
 	rx_status->flag |= RX_FLAG_NO_PSDU;
 
-	switch (info_type) {
+	/* mark as failed PLCP on any errors to skip checks in mac80211 */
+	if (le32_get_bits(desc->info, RX_NO_DATA_INFO_ERR_MSK) !=
+	    RX_NO_DATA_INFO_ERR_NONE)
+		rx_status->flag |= RX_FLAG_FAILED_PLCP_CRC;
+
+	switch (le32_get_bits(desc->info, RX_NO_DATA_INFO_TYPE_MSK)) {
 	case RX_NO_DATA_INFO_TYPE_NDP:
 		rx_status->zero_length_psdu_type =
 			IEEE80211_RADIOTAP_ZERO_LEN_PSDU_SOUNDING;
-- 
GitLab


From 9c93c0b44be36fd5267fb79ae33453f989fbe909 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Sun, 12 May 2024 07:31:00 +0300
Subject: [PATCH 130/950] wifi: iwlwifi: mei: unify iwl_mei_set_power_limit()
 prototype

The two versions of iwl_mei_set_power_limit() are a bit different,
and while really the const isn't all that necessary on the inline,
it's still better to have it be the same.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240512072733.854427753c92.I557716085cb1f6a35d1f97640388fa421f42a56a@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mei/iwl-mei.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mei/iwl-mei.h b/drivers/net/wireless/intel/iwlwifi/mei/iwl-mei.h
index 1f3c885aeb654..ee48b86674a6e 100644
--- a/drivers/net/wireless/intel/iwlwifi/mei/iwl-mei.h
+++ b/drivers/net/wireless/intel/iwlwifi/mei/iwl-mei.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * Copyright (C) 2021-2023 Intel Corporation
+ * Copyright (C) 2021-2024 Intel Corporation
  */
 
 #ifndef __iwl_mei_h__
@@ -488,7 +488,7 @@ static inline void iwl_mei_set_nic_info(const u8 *mac_address, const u8 *nvm_add
 static inline void iwl_mei_set_country_code(u16 mcc)
 {}
 
-static inline void iwl_mei_set_power_limit(__le16 *power_limit)
+static inline void iwl_mei_set_power_limit(const __le16 *power_limit)
 {}
 
 static inline int iwl_mei_register(void *priv,
-- 
GitLab


From 8d59995067d9a6024fc63afa1434e0f5196727de Mon Sep 17 00:00:00 2001
From: Mukesh Sisodiya <mukesh.sisodiya@intel.com>
Date: Sun, 12 May 2024 07:31:01 +0300
Subject: [PATCH 131/950] wifi: iwlwifi: fw: api: Add new timepoint for scan
 failure

Add new time point to get the details of scan failure
While on it added other missing enum to match with FW.

Signed-off-by: Mukesh Sisodiya <mukesh.sisodiya@intel.com>
Reviewed-by: Pagadala Yesu Anjaneyulu <pagadala.yesu.anjaneyulu@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240512072733.6781e76990c4.Iadfb3f6dd63a98fc35019772266b5ebddc5b5270@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/api/dbg-tlv.h | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/dbg-tlv.h b/drivers/net/wireless/intel/iwlwifi/fw/api/dbg-tlv.h
index 47c914de29927..6cfe8a779cc73 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/dbg-tlv.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/dbg-tlv.h
@@ -470,6 +470,10 @@ enum iwl_fw_ini_region_device_memory_subtype {
  * @IWL_FW_INI_TIME_POINT_EAPOL_FAILED: EAPOL failed
  * @IWL_FW_INI_TIME_POINT_FAKE_TX: fake Tx
  * @IWL_FW_INI_TIME_POINT_DEASSOC: de association
+ * @IWL_FW_INI_TIME_POINT_PRESET_OVERRIDE_EXT_REQ: request to override preset
+ * @IWL_FW_INI_TIME_POINT_PRESET_OVERRIDE_START: start handling override preset
+ *	request
+ * @IWL_FW_INI_TIME_SCAN_FAILURE: failed scan channel list
  * @IWL_FW_INI_TIME_POINT_NUM: number of time points
  */
 enum iwl_fw_ini_time_point {
@@ -500,6 +504,9 @@ enum iwl_fw_ini_time_point {
 	IWL_FW_INI_TIME_POINT_EAPOL_FAILED,
 	IWL_FW_INI_TIME_POINT_FAKE_TX,
 	IWL_FW_INI_TIME_POINT_DEASSOC,
+	IWL_FW_INI_TIME_POINT_PRESET_OVERRIDE_EXT_REQ,
+	IWL_FW_INI_TIME_POINT_PRESET_OVERRIDE_START,
+	IWL_FW_INI_TIME_SCAN_FAILURE,
 	IWL_FW_INI_TIME_POINT_NUM,
 }; /* FW_TLV_DEBUG_TIME_POINT_API_E */
 
-- 
GitLab


From 6ccfc7c49b6d99e3b857afb064e56a004b0a5e03 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Sun, 12 May 2024 07:31:03 +0300
Subject: [PATCH 132/950] wifi: iwlwifi: fw: avoid bad FW config on RXQ DMA
 failure

In practice, iwl_trans_get_rxq_dma_data() will not fail,
it only can do that if called with the wrong arguments.
But it does have an error value and doesn't initialize
the argument when it fails, so don't use the value then.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240512072733.faf3a1b87589.I77c950173cb914676fbd28483e5ef420bb9f1bc9@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/init.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/init.c b/drivers/net/wireless/intel/iwlwifi/fw/init.c
index 135bd48bfe9fa..d8b083be5b6b5 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/init.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/init.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
  * Copyright (C) 2017 Intel Deutschland GmbH
- * Copyright (C) 2019-2021 Intel Corporation
+ * Copyright (C) 2019-2021, 2024 Intel Corporation
  */
 #include "iwl-drv.h"
 #include "runtime.h"
@@ -135,7 +135,9 @@ int iwl_configure_rxq(struct iwl_fw_runtime *fwrt)
 		struct iwl_trans_rxq_dma_data data;
 
 		cmd->data[i].q_num = i + 1;
-		iwl_trans_get_rxq_dma_data(fwrt->trans, i + 1, &data);
+		ret = iwl_trans_get_rxq_dma_data(fwrt->trans, i + 1, &data);
+		if (ret)
+			goto out;
 
 		cmd->data[i].fr_bd_cb = cpu_to_le64(data.fr_bd_cb);
 		cmd->data[i].urbd_stts_wrptr =
@@ -149,6 +151,7 @@ int iwl_configure_rxq(struct iwl_fw_runtime *fwrt)
 
 	ret = iwl_trans_send_cmd(fwrt->trans, &hcmd);
 
+out:
 	kfree(cmd);
 
 	if (ret)
-- 
GitLab


From 45eeee1f300d2b0b1ad8570b4ef6e2a23932f1a5 Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Sun, 12 May 2024 07:31:05 +0300
Subject: [PATCH 133/950] wifi: iwlwifi: always print the firmware version in
 hex

All our firmware versions should now be printed in hex.

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Reviewed-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240512072733.cae4c562b2c3.I5043383bd0e81f872c55046afd2c6560f482c8e0@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/iwl-drv.c | 14 ++++----------
 1 file changed, 4 insertions(+), 10 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
index 33654f228ee87..a392a5f1847f2 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
@@ -982,16 +982,10 @@ static int iwl_parse_tlv_firmware(struct iwl_drv *drv,
 			minor = le32_to_cpup(ptr++);
 			local_comp = le32_to_cpup(ptr);
 
-			if (major >= 35)
-				snprintf(drv->fw.fw_version,
-					 sizeof(drv->fw.fw_version),
-					"%u.%08x.%u %s", major, minor,
-					local_comp, iwl_reduced_fw_name(drv));
-			else
-				snprintf(drv->fw.fw_version,
-					 sizeof(drv->fw.fw_version),
-					"%u.%u.%u %s", major, minor,
-					local_comp, iwl_reduced_fw_name(drv));
+			snprintf(drv->fw.fw_version,
+				 sizeof(drv->fw.fw_version),
+				 "%u.%08x.%u %s", major, minor,
+				 local_comp, iwl_reduced_fw_name(drv));
 			break;
 			}
 		case IWL_UCODE_TLV_FW_DBG_DEST: {
-- 
GitLab


From ed93faf01797d83b3347168adae93e6eb5fc1d9c Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Sun, 12 May 2024 07:31:07 +0300
Subject: [PATCH 134/950] wifi: iwlwifi: mvm: don't track used links separately

We track which link is using which FW link ID, so there
really isn't a need to separately track which link IDs
are in use. Remove that code and check the table when
looking for a new link ID to use.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240512072733.1a67d8af815f.Ie642c12dce3ab55c688abd9a25918569e83e558a@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/fw.c   |  2 --
 drivers/net/wireless/intel/iwlwifi/mvm/link.c | 22 +++++--------------
 drivers/net/wireless/intel/iwlwifi/mvm/mvm.h  |  1 -
 3 files changed, 5 insertions(+), 20 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
index e7f5978ef2d71..8198451d70a2c 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
@@ -1499,8 +1499,6 @@ int iwl_mvm_up(struct iwl_mvm *mvm)
 	for (i = 0; i < IWL_MVM_FW_MAX_LINK_ID + 1; i++)
 		RCU_INIT_POINTER(mvm->link_id_to_link_conf[i], NULL);
 
-	memset(&mvm->fw_link_ids_map, 0, sizeof(mvm->fw_link_ids_map));
-
 	mvm->tdls_cs.peer.sta_id = IWL_MVM_INVALID_STA;
 
 	/* reset quota debouncing buffer - 0xff will yield invalid data */
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/link.c b/drivers/net/wireless/intel/iwlwifi/mvm/link.c
index 6ec9a8e21a34e..14dab617c0bdf 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/link.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/link.c
@@ -50,26 +50,15 @@ static void iwl_mvm_print_esr_state(struct iwl_mvm *mvm, u32 mask)
 static u32 iwl_mvm_get_free_fw_link_id(struct iwl_mvm *mvm,
 				       struct iwl_mvm_vif *mvm_vif)
 {
-	u32 link_id;
+	u32 i;
 
 	lockdep_assert_held(&mvm->mutex);
 
-	link_id = ffz(mvm->fw_link_ids_map);
+	for (i = 0; i < ARRAY_SIZE(mvm->link_id_to_link_conf); i++)
+		if (!rcu_access_pointer(mvm->link_id_to_link_conf[i]))
+			return i;
 
-	/* this case can happen if there're deactivated but not removed links */
-	if (link_id > IWL_MVM_FW_MAX_LINK_ID)
-		return IWL_MVM_FW_LINK_ID_INVALID;
-
-	mvm->fw_link_ids_map |= BIT(link_id);
-	return link_id;
-}
-
-static void iwl_mvm_release_fw_link_id(struct iwl_mvm *mvm, u32 link_id)
-{
-	lockdep_assert_held(&mvm->mutex);
-
-	if (!WARN_ON(link_id > IWL_MVM_FW_MAX_LINK_ID))
-		mvm->fw_link_ids_map &= ~BIT(link_id);
+	return IWL_MVM_FW_LINK_ID_INVALID;
 }
 
 static int iwl_mvm_link_cmd_send(struct iwl_mvm *mvm,
@@ -380,7 +369,6 @@ int iwl_mvm_unset_link_mapping(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 
 	RCU_INIT_POINTER(mvm->link_id_to_link_conf[link_info->fw_link_id],
 			 NULL);
-	iwl_mvm_release_fw_link_id(mvm, link_info->fw_link_id);
 	return 0;
 }
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index ca1c5944da670..d732780aae5f1 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -1043,7 +1043,6 @@ struct iwl_mvm {
 	struct iwl_rx_phy_info last_phy_info;
 	struct ieee80211_sta __rcu *fw_id_to_mac_id[IWL_MVM_STATION_COUNT_MAX];
 	struct ieee80211_link_sta __rcu *fw_id_to_link_sta[IWL_MVM_STATION_COUNT_MAX];
-	unsigned long fw_link_ids_map;
 	u8 rx_ba_sessions;
 
 	/* configured by mac80211 */
-- 
GitLab


From 157c8a448354518f9a1e8d758094fc80afeb8568 Mon Sep 17 00:00:00 2001
From: Benjamin Berg <benjamin.berg@intel.com>
Date: Sun, 12 May 2024 07:31:08 +0300
Subject: [PATCH 135/950] wifi: iwlwifi: mvm: use vif P2P type helper

Use ieee80211_vif_type_p2p instead of checking for IFTYPE_AP in
combination with vif->p2p.

Signed-off-by: Benjamin Berg <benjamin.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240512072733.15a00a812c1b.I5ffee795d960c9beda46a934f5b4c70acde112f9@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/scan.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
index a7ec172eeade8..695b5ba3d0235 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
@@ -208,7 +208,7 @@ static void iwl_mvm_scan_iterator(void *_data, u8 *mac,
 
 	curr_mvmvif = iwl_mvm_vif_from_mac80211(data->current_vif);
 
-	if (vif->type == NL80211_IFTYPE_AP && vif->p2p &&
+	if (ieee80211_vif_type_p2p(vif) == NL80211_IFTYPE_P2P_GO &&
 	    mvmvif->deflink.phy_ctxt && curr_mvmvif->deflink.phy_ctxt &&
 	    mvmvif->deflink.phy_ctxt->id != curr_mvmvif->deflink.phy_ctxt->id)
 		data->is_dcm_with_p2p_go = true;
@@ -2875,7 +2875,7 @@ static void iwl_mvm_scan_respect_p2p_go_iter(void *_data, u8 *mac,
 	if (vif == data->current_vif)
 		return;
 
-	if (vif->type == NL80211_IFTYPE_AP && vif->p2p) {
+	if (ieee80211_vif_type_p2p(vif) == NL80211_IFTYPE_P2P_GO) {
 		u32 link_id;
 
 		for (link_id = 0;
-- 
GitLab


From 9574c7592c5080a3e1f3fdfe658bd13083a04cb5 Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Sun, 12 May 2024 07:31:10 +0300
Subject: [PATCH 136/950] wifi: iwlwifi: mvm: disable dynamic EMLSR when
 AUTO_EML is false

When AUTO_EML is set to false, this change ignores the exit criteria,
for testing purposes. Currently, if AUTO_EML is disabled, the
driver will not select a link or enter EMLSR, but will still exit if one
of the criteria is not fulfilled.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Reviewed-by: Johannes Berg <johannes.berg@intel.com>
Link: https://msgid.link/20240512072733.10a0b5da6ec2.I46fd578a3ef6cdbf14fdc4dfa97b4be008fe68e3@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/link.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/link.c b/drivers/net/wireless/intel/iwlwifi/mvm/link.c
index 14dab617c0bdf..fd8a21891d262 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/link.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/link.c
@@ -966,6 +966,9 @@ void iwl_mvm_exit_esr(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 
 	lockdep_assert_held(&mvm->mutex);
 
+	if (!IWL_MVM_AUTO_EML_ENABLE)
+		return;
+
 	/* Nothing to do */
 	if (!mvmvif->esr_active)
 		return;
@@ -1013,6 +1016,9 @@ void iwl_mvm_block_esr(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 
 	lockdep_assert_held(&mvm->mutex);
 
+	if (!IWL_MVM_AUTO_EML_ENABLE)
+		return;
+
 	/* This should be called only with disable reasons */
 	if (WARN_ON(!(reason & IWL_MVM_BLOCK_ESR_REASONS)))
 		return;
@@ -1099,6 +1105,9 @@ void iwl_mvm_unblock_esr(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 
 	lockdep_assert_held(&mvm->mutex);
 
+	if (!IWL_MVM_AUTO_EML_ENABLE)
+		return;
+
 	/* This should be called only with disable reasons */
 	if (WARN_ON(!(reason & IWL_MVM_BLOCK_ESR_REASONS)))
 		return;
-- 
GitLab


From f79968eb417574f84a06c22510cbeb414e89a809 Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Sun, 12 May 2024 07:58:57 +0300
Subject: [PATCH 137/950] wifi: iwlwifi: mvm: leave a print in the logs when we
 call fw_nmi()

When we crash the firmware, we need to know why we decided to do so.
Almost all the callsites of iwl_force_nmi() print something in the logs
that explain why the driver decided to crash the firmware.
Debugfs doesn't print anything and it is then hard to understand why the
firmware has crashed.
Add a simple print in the debugfs hook to ease the debug.

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240512075822.e2558de222dc.Idd81777c47264e6f557b086625895c1dc2f667f3@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
index 79f4ac8cbc729..96c9382b98fb5 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
@@ -1396,6 +1396,8 @@ static ssize_t iwl_dbgfs_fw_nmi_write(struct iwl_mvm *mvm, char *buf,
 	if (!iwl_mvm_firmware_running(mvm))
 		return -EIO;
 
+	IWL_ERR(mvm, "Triggering an NMI from debugfs\n");
+
 	if (count == 6 && !strcmp(buf, "nolog\n"))
 		set_bit(IWL_MVM_STATUS_SUPPRESS_ERROR_LOG_ONCE, &mvm->status);
 
-- 
GitLab


From bdaae563e097a40e942d66a15cb3a5537f156dd5 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Sun, 12 May 2024 15:24:56 +0300
Subject: [PATCH 138/950] wifi: iwlwifi: tracing: fix condition to allocate
 buf1

There's no need to allocate buf1 if we're not going to
write anything to it, and the condition for writing is
(correctly) "hdr_len > 0 && !iwl_trace_data()". Also
allocate the event space only under the same condition.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240512152312.a11e6490d053.Ie090beea70d2f271bb22c9b0e287dbd342fb2a96@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/iwl-devtrace-iwlwifi.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-devtrace-iwlwifi.h b/drivers/net/wireless/intel/iwlwifi/iwl-devtrace-iwlwifi.h
index e656bf6bc0033..b9aa04cf1d833 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-devtrace-iwlwifi.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-devtrace-iwlwifi.h
@@ -4,7 +4,7 @@
  * Copyright(c) 2009 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
- * Copyright(c) 2018, 2023  Intel Corporation
+ * Copyright(c) 2018, 2023-2024  Intel Corporation
  *****************************************************************************/
 
 #if !defined(__IWLWIFI_DEVICE_TRACE_IWLWIFI) || defined(TRACE_HEADER_MULTI_READ)
@@ -88,8 +88,8 @@ TRACE_EVENT(iwlwifi_dev_tx,
 		 * for the possible padding).
 		 */
 		__dynamic_array(u8, buf0, buf0_len)
-		__dynamic_array(u8, buf1, hdr_len > 0 && iwl_trace_data(skb) ?
-						0 : skb->len - hdr_len)
+		__dynamic_array(u8, buf1, hdr_len > 0 && !iwl_trace_data(skb) ?
+						skb->len - hdr_len : 0)
 	),
 	TP_fast_assign(
 		DEV_ASSIGN;
-- 
GitLab


From 9d42be9b181b825d7401a8dd10a198b087783e0b Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Sun, 12 May 2024 15:24:57 +0300
Subject: [PATCH 139/950] wifi: iwlwifi: simplify TX tracing

There's no need to calculate again whether data should
be included or be handled externally, just check if any
space for it was already reserved.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240512152312.a3d3b4796460.I85bd3029baee24ebf0be04db7d6bf01834090869@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/iwl-devtrace-data.h    | 4 ++--
 drivers/net/wireless/intel/iwlwifi/iwl-devtrace-iwlwifi.h | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-devtrace-data.h b/drivers/net/wireless/intel/iwlwifi/iwl-devtrace-data.h
index 2c280a2fe3df3..0d4a0896a2c51 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-devtrace-data.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-devtrace-data.h
@@ -3,7 +3,7 @@
  *
  * Copyright(c) 2009 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2015        Intel Deutschland GmbH
- * Copyright(c) 2018 - 2019, 2023 Intel Corporation
+ * Copyright(c) 2018 - 2019, 2023-2024 Intel Corporation
  *****************************************************************************/
 
 #if !defined(__IWLWIFI_DEVICE_TRACE_DATA) || defined(TRACE_HEADER_MULTI_READ)
@@ -28,7 +28,7 @@ TRACE_EVENT(iwlwifi_dev_tx_tb,
 	TP_fast_assign(
 		DEV_ASSIGN;
 		__entry->phys = phys;
-		if (iwl_trace_data(skb))
+		if (__get_dynamic_array_len(data))
 			memcpy(__get_dynamic_array(data), data_src, data_len);
 	),
 	TP_printk("[%s] TX frame data", __get_str(dev))
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-devtrace-iwlwifi.h b/drivers/net/wireless/intel/iwlwifi/iwl-devtrace-iwlwifi.h
index b9aa04cf1d833..ead72c3d33bdf 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-devtrace-iwlwifi.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-devtrace-iwlwifi.h
@@ -99,7 +99,7 @@ TRACE_EVENT(iwlwifi_dev_tx,
 			__entry->framelen += skb->len - hdr_len;
 		memcpy(__get_dynamic_array(tfd), tfd, tfdlen);
 		memcpy(__get_dynamic_array(buf0), buf0, buf0_len);
-		if (hdr_len > 0 && !iwl_trace_data(skb))
+		if (__get_dynamic_array_len(buf1))
 			skb_copy_bits(skb, hdr_len,
 				      __get_dynamic_array(buf1),
 				      skb->len - hdr_len);
-- 
GitLab


From 3f3126515fbee0e364f8218f6171c091d8e2555e Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Sun, 12 May 2024 15:24:58 +0300
Subject: [PATCH 140/950] wifi: iwlwifi: mvm: add mvm-specific guard

Add and use an mvm-specific guard for the mvm mutex.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240512152312.7391425b3af2.I1b109f56753dd3f35602dd2c5cf6e1e35aee313d@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 .../net/wireless/intel/iwlwifi/mvm/mac80211.c | 225 ++++++------------
 .../wireless/intel/iwlwifi/mvm/mld-mac80211.c |  88 +++----
 drivers/net/wireless/intel/iwlwifi/mvm/mvm.h  |   3 +
 drivers/net/wireless/intel/iwlwifi/mvm/ops.c  |  14 +-
 drivers/net/wireless/intel/iwlwifi/mvm/tdls.c |  34 +--
 drivers/net/wireless/intel/iwlwifi/mvm/tt.c   |  60 ++---
 .../net/wireless/intel/iwlwifi/mvm/utils.c    |   7 +-
 7 files changed, 136 insertions(+), 295 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index 486a6b8f3c97f..f2f9e2620ff6f 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -1258,7 +1258,7 @@ static void iwl_mvm_restart_complete(struct iwl_mvm *mvm)
 {
 	int ret;
 
-	mutex_lock(&mvm->mutex);
+	guard(mvm)(mvm);
 
 	clear_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status);
 
@@ -1274,8 +1274,6 @@ static void iwl_mvm_restart_complete(struct iwl_mvm *mvm)
 	 * of packets the FW sent out, so we must reconnect.
 	 */
 	iwl_mvm_teardown_tdls_peers(mvm);
-
-	mutex_unlock(&mvm->mutex);
 }
 
 void iwl_mvm_mac_reconfig_complete(struct ieee80211_hw *hw,
@@ -1621,9 +1619,8 @@ static void iwl_mvm_prevent_esr_done_wk(struct wiphy *wiphy,
 	struct iwl_mvm *mvm = mvmvif->mvm;
 	struct ieee80211_vif *vif = iwl_mvm_get_bss_vif(mvm);
 
-	mutex_lock(&mvm->mutex);
+	guard(mvm)(mvm);
 	iwl_mvm_unblock_esr(mvm, vif, IWL_MVM_ESR_BLOCKED_PREVENTION);
-	mutex_unlock(&mvm->mutex);
 }
 
 static void iwl_mvm_mlo_int_scan_wk(struct wiphy *wiphy, struct wiphy_work *wk)
@@ -1633,11 +1630,8 @@ static void iwl_mvm_mlo_int_scan_wk(struct wiphy *wiphy, struct wiphy_work *wk)
 	struct ieee80211_vif *vif =
 		container_of((void *)mvmvif, struct ieee80211_vif, drv_priv);
 
-	mutex_lock(&mvmvif->mvm->mutex);
-
+	guard(mvm)(mvmvif->mvm);
 	iwl_mvm_int_mlo_scan(mvmvif->mvm, vif);
-
-	mutex_unlock(&mvmvif->mvm->mutex);
 }
 
 static void iwl_mvm_unblock_esr_tpt(struct wiphy *wiphy, struct wiphy_work *wk)
@@ -1647,9 +1641,8 @@ static void iwl_mvm_unblock_esr_tpt(struct wiphy *wiphy, struct wiphy_work *wk)
 	struct iwl_mvm *mvm = mvmvif->mvm;
 	struct ieee80211_vif *vif = iwl_mvm_get_bss_vif(mvm);
 
-	mutex_lock(&mvm->mutex);
+	guard(mvm)(mvm);
 	iwl_mvm_unblock_esr(mvm, vif, IWL_MVM_ESR_BLOCKED_TPT);
-	mutex_unlock(&mvm->mutex);
 }
 
 void iwl_mvm_mac_init_mvmvif(struct iwl_mvm *mvm, struct iwl_mvm_vif *mvmvif)
@@ -2039,7 +2032,7 @@ void iwl_mvm_configure_filter(struct ieee80211_hw *hw,
 	struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
 	struct iwl_mcast_filter_cmd *cmd = (void *)(unsigned long)multicast;
 
-	mutex_lock(&mvm->mutex);
+	guard(mvm)(mvm);
 
 	/* replace previous configuration */
 	kfree(mvm->mcast_filter_cmd);
@@ -2056,7 +2049,6 @@ void iwl_mvm_configure_filter(struct ieee80211_hw *hw,
 
 	iwl_mvm_recalc_multicast(mvm);
 out:
-	mutex_unlock(&mvm->mutex);
 	*total_flags = 0;
 }
 
@@ -2076,9 +2068,8 @@ static void iwl_mvm_config_iface_filter(struct ieee80211_hw *hw,
 	    !vif->p2p)
 		return;
 
-	mutex_lock(&mvm->mutex);
+	guard(mvm)(mvm);
 	iwl_mvm_mac_ctxt_changed(mvm, vif, false, NULL);
-	mutex_unlock(&mvm->mutex);
 }
 
 int iwl_mvm_update_mu_groups(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
@@ -3123,7 +3114,7 @@ static void iwl_mvm_stop_ap_ibss(struct ieee80211_hw *hw,
 {
 	struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
 
-	mutex_lock(&mvm->mutex);
+	guard(mvm)(mvm);
 
 	iwl_mvm_stop_ap_ibss_common(mvm, vif);
 
@@ -3153,8 +3144,6 @@ static void iwl_mvm_stop_ap_ibss(struct ieee80211_hw *hw,
 	iwl_mvm_power_update_mac(mvm);
 
 	iwl_mvm_mac_ctxt_remove(mvm, vif);
-
-	mutex_unlock(&mvm->mutex);
 }
 
 static void iwl_mvm_stop_ap(struct ieee80211_hw *hw,
@@ -3209,7 +3198,7 @@ static void iwl_mvm_bss_info_changed(struct ieee80211_hw *hw,
 {
 	struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
 
-	mutex_lock(&mvm->mutex);
+	guard(mvm)(mvm);
 
 	if (changes & BSS_CHANGED_IDLE && !vif->cfg.idle)
 		iwl_mvm_scan_stop(mvm, IWL_MVM_SCAN_SCHED, true);
@@ -3236,25 +3225,19 @@ static void iwl_mvm_bss_info_changed(struct ieee80211_hw *hw,
 				bss_conf->txpower);
 		iwl_mvm_set_tx_power(mvm, vif, bss_conf->txpower);
 	}
-
-	mutex_unlock(&mvm->mutex);
 }
 
 int iwl_mvm_mac_hw_scan(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 			struct ieee80211_scan_request *hw_req)
 {
 	struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
-	int ret;
 
 	if (hw_req->req.n_channels == 0 ||
 	    hw_req->req.n_channels > mvm->fw->ucode_capa.n_scan_channels)
 		return -EINVAL;
 
-	mutex_lock(&mvm->mutex);
-	ret = iwl_mvm_reg_scan_start(mvm, vif, &hw_req->req, &hw_req->ies);
-	mutex_unlock(&mvm->mutex);
-
-	return ret;
+	guard(mvm)(mvm);
+	return iwl_mvm_reg_scan_start(mvm, vif, &hw_req->req, &hw_req->ies);
 }
 
 void iwl_mvm_mac_cancel_hw_scan(struct ieee80211_hw *hw,
@@ -3262,7 +3245,7 @@ void iwl_mvm_mac_cancel_hw_scan(struct ieee80211_hw *hw,
 {
 	struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
 
-	mutex_lock(&mvm->mutex);
+	guard(mvm)(mvm);
 
 	/* Due to a race condition, it's possible that mac80211 asks
 	 * us to stop a hw_scan when it's already stopped.  This can
@@ -3273,8 +3256,6 @@ void iwl_mvm_mac_cancel_hw_scan(struct ieee80211_hw *hw,
 	*/
 	if (mvm->scan_status & IWL_MVM_SCAN_REGULAR)
 		iwl_mvm_scan_stop(mvm, IWL_MVM_SCAN_REGULAR, true);
-
-	mutex_unlock(&mvm->mutex);
 }
 
 void
@@ -3443,7 +3424,7 @@ void iwl_mvm_sta_pre_rcu_remove(struct ieee80211_hw *hw,
 	 * Since there's mvm->mutex here, no need to have RCU lock for
 	 * mvm_sta->link access.
 	 */
-	mutex_lock(&mvm->mutex);
+	guard(mvm)(mvm);
 	for (link_id = 0; link_id < ARRAY_SIZE(mvm_sta->link); link_id++) {
 		struct iwl_mvm_link_sta *link_sta;
 		u32 sta_id;
@@ -3460,7 +3441,6 @@ void iwl_mvm_sta_pre_rcu_remove(struct ieee80211_hw *hw,
 			RCU_INIT_POINTER(mvm->fw_id_to_link_sta[sta_id], NULL);
 		}
 	}
-	mutex_unlock(&mvm->mutex);
 }
 
 static void iwl_mvm_check_uapsd(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
@@ -4207,12 +4187,8 @@ static int iwl_mvm_mac_conf_tx(struct ieee80211_hw *hw,
 	 * The exception is P2P_DEVICE interface which needs immediate update.
 	 */
 	if (vif->type == NL80211_IFTYPE_P2P_DEVICE) {
-		int ret;
-
-		mutex_lock(&mvm->mutex);
-		ret = iwl_mvm_mac_ctxt_changed(mvm, vif, false, NULL);
-		mutex_unlock(&mvm->mutex);
-		return ret;
+		guard(mvm)(mvm);
+		return iwl_mvm_mac_ctxt_changed(mvm, vif, false, NULL);
 	}
 	return 0;
 }
@@ -4223,9 +4199,8 @@ void iwl_mvm_mac_mgd_prepare_tx(struct ieee80211_hw *hw,
 {
 	struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
 
-	mutex_lock(&mvm->mutex);
+	guard(mvm)(mvm);
 	iwl_mvm_protect_assoc(mvm, vif, info->duration, info->link_id);
-	mutex_unlock(&mvm->mutex);
 }
 
 void iwl_mvm_mac_mgd_complete_tx(struct ieee80211_hw *hw,
@@ -4238,9 +4213,8 @@ void iwl_mvm_mac_mgd_complete_tx(struct ieee80211_hw *hw,
 	if (info->success)
 		return;
 
-	mutex_lock(&mvm->mutex);
+	guard(mvm)(mvm);
 	iwl_mvm_stop_session_protection(mvm, vif);
-	mutex_unlock(&mvm->mutex);
 }
 
 int iwl_mvm_mac_sched_scan_start(struct ieee80211_hw *hw,
@@ -4250,20 +4224,12 @@ int iwl_mvm_mac_sched_scan_start(struct ieee80211_hw *hw,
 {
 	struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
 
-	int ret;
-
-	mutex_lock(&mvm->mutex);
+	guard(mvm)(mvm);
 
-	if (!vif->cfg.idle) {
-		ret = -EBUSY;
-		goto out;
-	}
-
-	ret = iwl_mvm_sched_scan_start(mvm, vif, req, ies, IWL_MVM_SCAN_SCHED);
+	if (!vif->cfg.idle)
+		return -EBUSY;
 
-out:
-	mutex_unlock(&mvm->mutex);
-	return ret;
+	return iwl_mvm_sched_scan_start(mvm, vif, req, ies, IWL_MVM_SCAN_SCHED);
 }
 
 int iwl_mvm_mac_sched_scan_stop(struct ieee80211_hw *hw,
@@ -4541,13 +4507,9 @@ int iwl_mvm_mac_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 			struct ieee80211_key_conf *key)
 {
 	struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
-	int ret;
 
-	mutex_lock(&mvm->mutex);
-	ret = __iwl_mvm_mac_set_key(hw, cmd, vif, sta, key);
-	mutex_unlock(&mvm->mutex);
-
-	return ret;
+	guard(mvm)(mvm);
+	return __iwl_mvm_mac_set_key(hw, cmd, vif, sta, key);
 }
 
 void iwl_mvm_mac_update_tkip_key(struct ieee80211_hw *hw,
@@ -4838,7 +4800,7 @@ int iwl_mvm_roc_common(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	if (ret)
 		return ret;
 
-	mutex_lock(&mvm->mutex);
+	guard(mvm)(mvm);
 
 	switch (vif->type) {
 	case NL80211_IFTYPE_STATION:
@@ -4848,30 +4810,25 @@ int iwl_mvm_roc_common(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 		ret = ops->add_aux_sta_for_hs20(mvm, lmac_id);
 		if (!ret)
 			ret = iwl_mvm_roc_station(mvm, channel, vif, duration);
-		goto out_unlock;
+		return ret;
 	case NL80211_IFTYPE_P2P_DEVICE:
 		/* handle below */
 		break;
 	default:
 		IWL_ERR(mvm, "ROC: Invalid vif type=%u\n", vif->type);
-		ret = -EINVAL;
-		goto out_unlock;
+		return -EINVAL;
 	}
 
 
 	ret = iwl_mvm_p2p_find_phy_ctxt(mvm, vif, channel);
 	if (ret)
-		goto out_unlock;
+		return ret;
 
 	ret = ops->link(mvm, vif);
 	if (ret)
-		goto out_unlock;
+		return ret;
 
-	ret = iwl_mvm_start_p2p_roc(mvm, vif, duration, type);
-out_unlock:
-	mutex_unlock(&mvm->mutex);
-	IWL_DEBUG_MAC80211(mvm, "leave\n");
-	return ret;
+	return iwl_mvm_start_p2p_roc(mvm, vif, duration, type);
 }
 
 int iwl_mvm_cancel_roc(struct ieee80211_hw *hw,
@@ -4952,13 +4909,9 @@ int iwl_mvm_add_chanctx(struct ieee80211_hw *hw,
 			struct ieee80211_chanctx_conf *ctx)
 {
 	struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
-	int ret;
 
-	mutex_lock(&mvm->mutex);
-	ret = __iwl_mvm_add_chanctx(mvm, ctx);
-	mutex_unlock(&mvm->mutex);
-
-	return ret;
+	guard(mvm)(mvm);
+	return __iwl_mvm_add_chanctx(mvm, ctx);
 }
 
 static void __iwl_mvm_remove_chanctx(struct iwl_mvm *mvm,
@@ -4977,9 +4930,8 @@ void iwl_mvm_remove_chanctx(struct ieee80211_hw *hw,
 {
 	struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
 
-	mutex_lock(&mvm->mutex);
+	guard(mvm)(mvm);
 	__iwl_mvm_remove_chanctx(mvm, ctx);
-	mutex_unlock(&mvm->mutex);
 }
 
 void iwl_mvm_change_chanctx(struct ieee80211_hw *hw,
@@ -4999,26 +4951,23 @@ void iwl_mvm_change_chanctx(struct ieee80211_hw *hw,
 		      phy_ctxt->ref, changed))
 		return;
 
-	mutex_lock(&mvm->mutex);
+	guard(mvm)(mvm);
 
 	/* we are only changing the min_width, may be a noop */
 	if (changed == IEEE80211_CHANCTX_CHANGE_MIN_WIDTH) {
 		if (phy_ctxt->width == def->width)
-			goto out_unlock;
+			return;
 
 		/* we are just toggling between 20_NOHT and 20 */
 		if (phy_ctxt->width <= NL80211_CHAN_WIDTH_20 &&
 		    def->width <= NL80211_CHAN_WIDTH_20)
-			goto out_unlock;
+			return;
 	}
 
 	iwl_mvm_bt_coex_vif_change(mvm);
 	iwl_mvm_phy_ctxt_changed(mvm, phy_ctxt, def, &ctx->ap,
 				 ctx->rx_chains_static,
 				 ctx->rx_chains_dynamic);
-
-out_unlock:
-	mutex_unlock(&mvm->mutex);
 }
 
 /*
@@ -5157,13 +5106,9 @@ static int iwl_mvm_assign_vif_chanctx(struct ieee80211_hw *hw,
 				      struct ieee80211_chanctx_conf *ctx)
 {
 	struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
-	int ret;
 
-	mutex_lock(&mvm->mutex);
-	ret = __iwl_mvm_assign_vif_chanctx(mvm, vif, link_conf, ctx, false);
-	mutex_unlock(&mvm->mutex);
-
-	return ret;
+	guard(mvm)(mvm);
+	return __iwl_mvm_assign_vif_chanctx(mvm, vif, link_conf, ctx, false);
 }
 
 /*
@@ -5251,9 +5196,8 @@ static void iwl_mvm_unassign_vif_chanctx(struct ieee80211_hw *hw,
 {
 	struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
 
-	mutex_lock(&mvm->mutex);
+	guard(mvm)(mvm);
 	__iwl_mvm_unassign_vif_chanctx(mvm, vif, link_conf, ctx, false);
-	mutex_unlock(&mvm->mutex);
 }
 
 static int
@@ -5263,7 +5207,7 @@ iwl_mvm_switch_vif_chanctx_swap(struct iwl_mvm *mvm,
 {
 	int ret;
 
-	mutex_lock(&mvm->mutex);
+	guard(mvm)(mvm);
 	ops->__unassign_vif_chanctx(mvm, vifs[0].vif, vifs[0].link_conf,
 				    vifs[0].old_ctx, true);
 	__iwl_mvm_remove_chanctx(mvm, vifs[0].old_ctx);
@@ -5286,7 +5230,7 @@ iwl_mvm_switch_vif_chanctx_swap(struct iwl_mvm *mvm,
 	if (iwl_mvm_phy_ctx_count(mvm) > 1)
 		iwl_mvm_teardown_tdls_peers(mvm);
 
-	goto out;
+	return 0;
 
 out_remove:
 	__iwl_mvm_remove_chanctx(mvm, vifs[0].new_ctx);
@@ -5303,15 +5247,11 @@ out_reassign:
 		goto out_restart;
 	}
 
-	goto out;
+	return ret;
 
 out_restart:
 	/* things keep failing, better restart the hw */
 	iwl_mvm_nic_restart(mvm, false);
-
-out:
-	mutex_unlock(&mvm->mutex);
-
 	return ret;
 }
 
@@ -5322,7 +5262,7 @@ iwl_mvm_switch_vif_chanctx_reassign(struct iwl_mvm *mvm,
 {
 	int ret;
 
-	mutex_lock(&mvm->mutex);
+	guard(mvm)(mvm);
 	ops->__unassign_vif_chanctx(mvm, vifs[0].vif, vifs[0].link_conf,
 				    vifs[0].old_ctx, true);
 
@@ -5334,7 +5274,7 @@ iwl_mvm_switch_vif_chanctx_reassign(struct iwl_mvm *mvm,
 		goto out_reassign;
 	}
 
-	goto out;
+	return 0;
 
 out_reassign:
 	if (ops->__assign_vif_chanctx(mvm, vifs[0].vif, vifs[0].link_conf,
@@ -5343,15 +5283,11 @@ out_reassign:
 		goto out_restart;
 	}
 
-	goto out;
+	return ret;
 
 out_restart:
 	/* things keep failing, better restart the hw */
 	iwl_mvm_nic_restart(mvm, false);
-
-out:
-	mutex_unlock(&mvm->mutex);
-
 	return ret;
 }
 
@@ -5478,13 +5414,9 @@ int iwl_mvm_mac_testmode_cmd(struct ieee80211_hw *hw,
 			     void *data, int len)
 {
 	struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
-	int err;
 
-	mutex_lock(&mvm->mutex);
-	err = __iwl_mvm_mac_testmode_cmd(mvm, vif, data, len);
-	mutex_unlock(&mvm->mutex);
-
-	return err;
+	guard(mvm)(mvm);
+	return __iwl_mvm_mac_testmode_cmd(mvm, vif, data, len);
 }
 #endif
 
@@ -5701,13 +5633,9 @@ static int iwl_mvm_mac_pre_channel_switch(struct ieee80211_hw *hw,
 					  struct ieee80211_channel_switch *chsw)
 {
 	struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
-	int ret;
 
-	mutex_lock(&mvm->mutex);
-	ret = iwl_mvm_pre_channel_switch(mvm, vif, chsw);
-	mutex_unlock(&mvm->mutex);
-
-	return ret;
+	guard(mvm)(mvm);
+	return iwl_mvm_pre_channel_switch(mvm, vif, chsw);
 }
 
 void iwl_mvm_channel_switch_rx_beacon(struct ieee80211_hw *hw,
@@ -5759,16 +5687,14 @@ void iwl_mvm_channel_switch_rx_beacon(struct ieee80211_hw *hw,
 	}
 	mvmvif->csa_count = chsw->count;
 
-	mutex_lock(&mvm->mutex);
+	guard(mvm)(mvm);
 	if (mvmvif->csa_failed)
-		goto out_unlock;
+		return;
 
 	WARN_ON(iwl_mvm_send_cmd_pdu(mvm,
 				     WIDE_ID(MAC_CONF_GROUP,
 					     CHANNEL_SWITCH_TIME_EVENT_CMD),
 				     0, sizeof(cmd), &cmd));
-out_unlock:
-	mutex_unlock(&mvm->mutex);
 }
 
 static void iwl_mvm_flush_no_vif(struct iwl_mvm *mvm, u32 queues, bool drop)
@@ -5777,17 +5703,16 @@ static void iwl_mvm_flush_no_vif(struct iwl_mvm *mvm, u32 queues, bool drop)
 
 	if (!iwl_mvm_has_new_tx_api(mvm)) {
 		if (drop) {
-			mutex_lock(&mvm->mutex);
+			guard(mvm)(mvm);
 			iwl_mvm_flush_tx_path(mvm,
 				iwl_mvm_flushable_queues(mvm) & queues);
-			mutex_unlock(&mvm->mutex);
 		} else {
 			iwl_trans_wait_tx_queues_empty(mvm->trans, queues);
 		}
 		return;
 	}
 
-	mutex_lock(&mvm->mutex);
+	guard(mvm)(mvm);
 	for (i = 0; i < mvm->fw->ucode_capa.num_stations; i++) {
 		struct ieee80211_sta *sta;
 
@@ -5802,7 +5727,6 @@ static void iwl_mvm_flush_no_vif(struct iwl_mvm *mvm, u32 queues, bool drop)
 			iwl_mvm_wait_sta_queues_empty(mvm,
 					iwl_mvm_sta_from_mac80211(sta));
 	}
-	mutex_unlock(&mvm->mutex);
 }
 
 void iwl_mvm_mac_flush(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
@@ -5885,7 +5809,7 @@ void iwl_mvm_mac_flush_sta(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	struct ieee80211_link_sta *link_sta;
 	int link_id;
 
-	mutex_lock(&mvm->mutex);
+	guard(mvm)(mvm);
 	for_each_sta_active_link(vif, sta, link_sta, link_id) {
 		mvm_link_sta = rcu_dereference_protected(mvmsta->link[link_id],
 							 lockdep_is_held(&mvm->mutex));
@@ -5896,7 +5820,6 @@ void iwl_mvm_mac_flush_sta(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 				      mvmsta->tfd_queue_msk))
 			IWL_ERR(mvm, "flush request fail\n");
 	}
-	mutex_unlock(&mvm->mutex);
 }
 
 static int iwl_mvm_mac_get_acs_survey(struct iwl_mvm *mvm, int idx,
@@ -5962,7 +5885,6 @@ int iwl_mvm_mac_get_survey(struct ieee80211_hw *hw, int idx,
 			   struct survey_info *survey)
 {
 	struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
-	int ret = 0;
 	u8 cmd_ver = iwl_fw_lookup_cmd_ver(mvm->fw,
 					   WIDE_ID(SYSTEM_GROUP,
 						   SYSTEM_STATISTICS_CMD),
@@ -5982,12 +5904,13 @@ int iwl_mvm_mac_get_survey(struct ieee80211_hw *hw, int idx,
 	if (idx > 0)
 		return iwl_mvm_mac_get_acs_survey(mvm, idx - 1, survey);
 
-	mutex_lock(&mvm->mutex);
+	guard(mvm)(mvm);
 
 	if (iwl_mvm_firmware_running(mvm)) {
-		ret = iwl_mvm_request_statistics(mvm, false);
+		int ret = iwl_mvm_request_statistics(mvm, false);
+
 		if (ret)
-			goto out;
+			return ret;
 	}
 
 	survey->filled = SURVEY_INFO_TIME_RX |
@@ -6003,7 +5926,7 @@ int iwl_mvm_mac_get_survey(struct ieee80211_hw *hw, int idx,
 
 	/* the new fw api doesn't support the following fields */
 	if (cmd_ver != IWL_FW_CMD_VER_UNKNOWN)
-		goto out;
+		return 0;
 
 	survey->filled |= SURVEY_INFO_TIME |
 			  SURVEY_INFO_TIME_SCAN;
@@ -6015,9 +5938,7 @@ int iwl_mvm_mac_get_survey(struct ieee80211_hw *hw, int idx,
 			    mvm->radio_stats.on_time_scan;
 	do_div(survey->time_scan, USEC_PER_MSEC);
 
- out:
-	mutex_unlock(&mvm->mutex);
-	return ret;
+	return 0;
 }
 
 static void iwl_mvm_set_sta_rate(u32 rate_n_flags, struct rate_info *rinfo)
@@ -6184,13 +6105,13 @@ void iwl_mvm_mac_sta_statistics(struct ieee80211_hw *hw,
 	if (!vif->cfg.assoc)
 		return;
 
-	mutex_lock(&mvm->mutex);
+	guard(mvm)(mvm);
 
 	if (mvmvif->deflink.ap_sta_id != mvmsta->deflink.sta_id)
-		goto unlock;
+		return;
 
 	if (iwl_mvm_request_statistics(mvm, false))
-		goto unlock;
+		return;
 
 	sinfo->rx_beacon = 0;
 	for_each_mvm_vif_valid_link(mvmvif, i)
@@ -6204,8 +6125,6 @@ void iwl_mvm_mac_sta_statistics(struct ieee80211_hw *hw,
 			mvmvif->deflink.beacon_stats.avg_signal;
 		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_BEACON_SIGNAL_AVG);
 	}
- unlock:
-	mutex_unlock(&mvm->mutex);
 }
 
 static void iwl_mvm_event_mlme_callback_ini(struct iwl_mvm *mvm,
@@ -6393,9 +6312,8 @@ void iwl_mvm_sync_rx_queues(struct ieee80211_hw *hw)
 {
 	struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
 
-	mutex_lock(&mvm->mutex);
+	guard(mvm)(mvm);
 	iwl_mvm_sync_rx_queues_internal(mvm, IWL_MVM_RXQ_EMPTY, true, NULL, 0);
-	mutex_unlock(&mvm->mutex);
 }
 
 int
@@ -6431,13 +6349,9 @@ int iwl_mvm_start_pmsr(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 		       struct cfg80211_pmsr_request *request)
 {
 	struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
-	int ret;
 
-	mutex_lock(&mvm->mutex);
-	ret = iwl_mvm_ftm_start(mvm, vif, request);
-	mutex_unlock(&mvm->mutex);
-
-	return ret;
+	guard(mvm)(mvm);
+	return iwl_mvm_ftm_start(mvm, vif, request);
 }
 
 void iwl_mvm_abort_pmsr(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
@@ -6445,9 +6359,8 @@ void iwl_mvm_abort_pmsr(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 {
 	struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
 
-	mutex_lock(&mvm->mutex);
+	guard(mvm)(mvm);
 	iwl_mvm_ftm_abort(mvm, request);
-	mutex_unlock(&mvm->mutex);
 }
 
 static bool iwl_mvm_can_hw_csum(struct sk_buff *skb)
@@ -6482,7 +6395,6 @@ int iwl_mvm_set_hw_timestamp(struct ieee80211_hw *hw,
 {
 	struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
 	u32 protocols = 0;
-	int ret;
 
 	/* HW timestamping is only supported for a specific station */
 	if (!hwts->macaddr)
@@ -6492,11 +6404,8 @@ int iwl_mvm_set_hw_timestamp(struct ieee80211_hw *hw,
 		protocols =
 			IWL_TIME_SYNC_PROTOCOL_TM | IWL_TIME_SYNC_PROTOCOL_FTM;
 
-	mutex_lock(&mvm->mutex);
-	ret = iwl_mvm_time_sync_config(mvm, hwts->macaddr, protocols);
-	mutex_unlock(&mvm->mutex);
-
-	return ret;
+	guard(mvm)(mvm);
+	return iwl_mvm_time_sync_config(mvm, hwts->macaddr, protocols);
 }
 
 const struct ieee80211_ops iwl_mvm_hw_ops = {
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
index 0a3b7284eeddf..f69f7df40a6dd 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
@@ -12,7 +12,7 @@ static int iwl_mvm_mld_mac_add_interface(struct ieee80211_hw *hw,
 	int ret;
 	int i;
 
-	mutex_lock(&mvm->mutex);
+	guard(mvm)(mvm);
 
 	iwl_mvm_mac_init_mvmvif(mvm, mvmvif);
 
@@ -32,7 +32,7 @@ static int iwl_mvm_mld_mac_add_interface(struct ieee80211_hw *hw,
 	/* Allocate resources for the MAC context, and add it to the fw  */
 	ret = iwl_mvm_mac_ctxt_init(mvm, vif);
 	if (ret)
-		goto out_unlock;
+		return ret;
 
 	rcu_assign_pointer(mvm->vif_id_to_mac[mvmvif->id], vif);
 
@@ -46,7 +46,7 @@ static int iwl_mvm_mld_mac_add_interface(struct ieee80211_hw *hw,
 
 	ret = iwl_mvm_mld_mac_ctxt_add(mvm, vif);
 	if (ret)
-		goto out_unlock;
+		return ret;
 
 	/* beacon filtering */
 	ret = iwl_mvm_disable_beacon_filter(mvm, vif);
@@ -97,7 +97,7 @@ static int iwl_mvm_mld_mac_add_interface(struct ieee80211_hw *hw,
 	if (vif->p2p || iwl_fw_lookup_cmd_ver(mvm->fw, PHY_CONTEXT_CMD, 1) < 5)
 		vif->driver_flags |= IEEE80211_VIF_IGNORE_OFDMA_WIDER_BW;
 
-	goto out_unlock;
+	return 0;
 
  out_free_bf:
 	if (mvm->bf_allowed_vif == mvmvif) {
@@ -108,9 +108,6 @@ static int iwl_mvm_mld_mac_add_interface(struct ieee80211_hw *hw,
  out_remove_mac:
 	mvmvif->link[0] = NULL;
 	iwl_mvm_mld_mac_ctxt_remove(mvm, vif);
- out_unlock:
-	mutex_unlock(&mvm->mutex);
-
 	return ret;
 }
 
@@ -127,7 +124,7 @@ static void iwl_mvm_mld_mac_remove_interface(struct ieee80211_hw *hw,
 	      vif->type == NL80211_IFTYPE_ADHOC))
 		iwl_mvm_tcm_rm_vif(mvm, vif);
 
-	mutex_lock(&mvm->mutex);
+	guard(mvm)(mvm);
 
 	if (vif == mvm->csme_vif) {
 		iwl_mei_set_netdev(NULL);
@@ -190,8 +187,6 @@ static void iwl_mvm_mld_mac_remove_interface(struct ieee80211_hw *hw,
 		mvm->monitor_on = false;
 		__clear_bit(IEEE80211_HW_RX_INCLUDES_FCS, mvm->hw->flags);
 	}
-
-	mutex_unlock(&mvm->mutex);
 }
 
 static unsigned int iwl_mvm_mld_count_active_links(struct iwl_mvm_vif *mvmvif)
@@ -389,10 +384,11 @@ static int iwl_mvm_mld_assign_vif_chanctx(struct ieee80211_hw *hw,
 					  struct ieee80211_chanctx_conf *ctx)
 {
 	struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
-	int ret;
 
 	/* update EMLSR mode */
 	if (ieee80211_vif_type_p2p(vif) != NL80211_IFTYPE_STATION) {
+		int ret;
+
 		ret = iwl_mvm_esr_non_bss_link(mvm, vif, link_conf->link_id,
 					       true);
 		/*
@@ -403,11 +399,8 @@ static int iwl_mvm_mld_assign_vif_chanctx(struct ieee80211_hw *hw,
 			return ret;
 	}
 
-	mutex_lock(&mvm->mutex);
-	ret = __iwl_mvm_mld_assign_vif_chanctx(mvm, vif, link_conf, ctx, false);
-	mutex_unlock(&mvm->mutex);
-
-	return ret;
+	guard(mvm)(mvm);
+	return __iwl_mvm_mld_assign_vif_chanctx(mvm, vif, link_conf, ctx, false);
 }
 
 static int iwl_mvm_esr_mode_inactive(struct iwl_mvm *mvm,
@@ -586,7 +579,7 @@ static int iwl_mvm_mld_start_ap_ibss(struct ieee80211_hw *hw,
 	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
 	int ret;
 
-	mutex_lock(&mvm->mutex);
+	guard(mvm)(mvm);
 
 	if (vif->type == NL80211_IFTYPE_AP)
 		iwl_mvm_send_ap_tx_power_constraint_cmd(mvm, vif, link_conf);
@@ -594,7 +587,7 @@ static int iwl_mvm_mld_start_ap_ibss(struct ieee80211_hw *hw,
 	/* Send the beacon template */
 	ret = iwl_mvm_mac_ctxt_beacon_changed(mvm, vif, link_conf);
 	if (ret)
-		goto out_unlock;
+		return ret;
 
 	/* the link should be already activated when assigning chan context */
 	ret = iwl_mvm_link_changed(mvm, vif, link_conf,
@@ -602,11 +595,11 @@ static int iwl_mvm_mld_start_ap_ibss(struct ieee80211_hw *hw,
 				   ~LINK_CONTEXT_MODIFY_ACTIVE,
 				   true);
 	if (ret)
-		goto out_unlock;
+		return ret;
 
 	ret = iwl_mvm_mld_add_mcast_sta(mvm, vif, link_conf);
 	if (ret)
-		goto out_unlock;
+		return ret;
 
 	/* Send the bcast station. At this stage the TBTT and DTIM time
 	 * events are added and applied to the scheduler
@@ -630,7 +623,7 @@ static int iwl_mvm_mld_start_ap_ibss(struct ieee80211_hw *hw,
 
 	iwl_mvm_ftm_restart_responder(mvm, vif, link_conf);
 
-	goto out_unlock;
+	return 0;
 
 out_failed:
 	iwl_mvm_power_update_mac(mvm);
@@ -638,8 +631,6 @@ out_failed:
 	iwl_mvm_mld_rm_bcast_sta(mvm, vif, link_conf);
 out_rm_mcast:
 	iwl_mvm_mld_rm_mcast_sta(mvm, vif, link_conf);
-out_unlock:
-	mutex_unlock(&mvm->mutex);
 	return ret;
 }
 
@@ -662,7 +653,7 @@ static void iwl_mvm_mld_stop_ap_ibss(struct ieee80211_hw *hw,
 {
 	struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
 
-	mutex_lock(&mvm->mutex);
+	guard(mvm)(mvm);
 
 	iwl_mvm_stop_ap_ibss_common(mvm, vif);
 
@@ -676,7 +667,6 @@ static void iwl_mvm_mld_stop_ap_ibss(struct ieee80211_hw *hw,
 	iwl_mvm_mld_rm_mcast_sta(mvm, vif, link_conf);
 
 	iwl_mvm_power_update_mac(mvm);
-	mutex_unlock(&mvm->mutex);
 }
 
 static void iwl_mvm_mld_stop_ap(struct ieee80211_hw *hw,
@@ -979,7 +969,7 @@ static void iwl_mvm_mld_link_info_changed(struct ieee80211_hw *hw,
 {
 	struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
 
-	mutex_lock(&mvm->mutex);
+	guard(mvm)(mvm);
 
 	switch (vif->type) {
 	case NL80211_IFTYPE_STATION:
@@ -1005,8 +995,6 @@ static void iwl_mvm_mld_link_info_changed(struct ieee80211_hw *hw,
 				link_conf->txpower);
 		iwl_mvm_set_tx_power(mvm, vif, link_conf->txpower);
 	}
-
-	mutex_unlock(&mvm->mutex);
 }
 
 static void iwl_mvm_mld_vif_cfg_changed(struct ieee80211_hw *hw,
@@ -1015,15 +1003,13 @@ static void iwl_mvm_mld_vif_cfg_changed(struct ieee80211_hw *hw,
 {
 	struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
 
-	mutex_lock(&mvm->mutex);
+	guard(mvm)(mvm);
 
 	if (changes & BSS_CHANGED_IDLE && !vif->cfg.idle)
 		iwl_mvm_scan_stop(mvm, IWL_MVM_SCAN_SCHED, true);
 
 	if (vif->type == NL80211_IFTYPE_STATION)
 		iwl_mvm_mld_vif_cfg_changed_station(mvm, vif, changes);
-
-	mutex_unlock(&mvm->mutex);
 }
 
 static int
@@ -1056,9 +1042,8 @@ static void iwl_mvm_mld_config_iface_filter(struct ieee80211_hw *hw,
 	    !vif->p2p)
 		return;
 
-	mutex_lock(&mvm->mutex);
+	guard(mvm)(mvm);
 	iwl_mvm_mld_mac_ctxt_changed(mvm, vif, false);
-	mutex_unlock(&mvm->mutex);
 }
 
 static int
@@ -1080,14 +1065,10 @@ iwl_mvm_mld_mac_conf_tx(struct ieee80211_hw *hw,
 	 * The exception is P2P_DEVICE interface which needs immediate update.
 	 */
 	if (vif->type == NL80211_IFTYPE_P2P_DEVICE) {
-		int ret;
-
-		mutex_lock(&mvm->mutex);
-		ret = iwl_mvm_link_changed(mvm, vif, &vif->bss_conf,
-					   LINK_CONTEXT_MODIFY_QOS_PARAMS,
-					   true);
-		mutex_unlock(&mvm->mutex);
-		return ret;
+		guard(mvm)(mvm);
+		return iwl_mvm_link_changed(mvm, vif, &vif->bss_conf,
+					    LINK_CONTEXT_MODIFY_QOS_PARAMS,
+					    true);
 	}
 	return 0;
 }
@@ -1232,13 +1213,9 @@ iwl_mvm_mld_change_sta_links(struct ieee80211_hw *hw,
 			     u16 old_links, u16 new_links)
 {
 	struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
-	int ret;
-
-	mutex_lock(&mvm->mutex);
-	ret = iwl_mvm_mld_update_sta_links(mvm, vif, sta, old_links, new_links);
-	mutex_unlock(&mvm->mutex);
 
-	return ret;
+	guard(mvm)(mvm);
+	return iwl_mvm_mld_update_sta_links(mvm, vif, sta, old_links, new_links);
 }
 
 bool iwl_mvm_vif_has_esr_cap(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
@@ -1266,26 +1243,19 @@ static bool iwl_mvm_mld_can_activate_links(struct ieee80211_hw *hw,
 {
 	struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
 	int n_links = hweight16(desired_links);
-	bool ret = true;
 
 	if (n_links <= 1)
 		return true;
 
-	mutex_lock(&mvm->mutex);
+	guard(mvm)(mvm);
 
 	/* Check if HW supports the wanted number of links */
-	if (n_links > iwl_mvm_max_active_links(mvm, vif)) {
-		ret = false;
-		goto unlock;
-	}
+	if (n_links > iwl_mvm_max_active_links(mvm, vif))
+		return false;
 
 	/* If it is an eSR device, check that we can enter eSR */
-	ret = iwl_mvm_is_esr_supported(mvm->fwrt.trans) &&
-	      iwl_mvm_vif_has_esr_cap(mvm, vif);
-
-unlock:
-	mutex_unlock(&mvm->mutex);
-	return ret;
+	return iwl_mvm_is_esr_supported(mvm->fwrt.trans) &&
+	       iwl_mvm_vif_has_esr_cap(mvm, vif);
 }
 
 static enum ieee80211_neg_ttlm_res
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index d732780aae5f1..dd4599ca1f452 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -9,6 +9,7 @@
 
 #include <linux/list.h>
 #include <linux/spinlock.h>
+#include <linux/cleanup.h>
 #include <linux/leds.h>
 #include <linux/in6.h>
 
@@ -1332,6 +1333,8 @@ struct iwl_mvm {
 #define IWL_MAC80211_GET_MVM(_hw)			\
 	IWL_OP_MODE_GET_MVM((struct iwl_op_mode *)((_hw)->priv))
 
+DEFINE_GUARD(mvm, struct iwl_mvm *, mutex_lock(&_T->mutex), mutex_unlock(&_T->mutex))
+
 /**
  * enum iwl_mvm_status - MVM status bits
  * @IWL_MVM_STATUS_HW_RFKILL: HW RF-kill is asserted
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
index c3cd5ab11aec1..160bb619ba9b8 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
@@ -765,20 +765,18 @@ static void iwl_mvm_tx_unblock_dwork(struct work_struct *work)
 	struct ieee80211_vif *tx_blocked_vif;
 	struct iwl_mvm_vif *mvmvif;
 
-	mutex_lock(&mvm->mutex);
+	guard(mvm)(mvm);
 
 	tx_blocked_vif =
 		rcu_dereference_protected(mvm->csa_tx_blocked_vif,
 					  lockdep_is_held(&mvm->mutex));
 
 	if (!tx_blocked_vif)
-		goto unlock;
+		return;
 
 	mvmvif = iwl_mvm_vif_from_mac80211(tx_blocked_vif);
 	iwl_mvm_modify_all_sta_disable_tx(mvm, mvmvif, false);
 	RCU_INIT_POINTER(mvm->csa_tx_blocked_vif, NULL);
-unlock:
-	mutex_unlock(&mvm->mutex);
 }
 
 static void iwl_mvm_fwrt_dump_start(void *ctx)
@@ -798,13 +796,9 @@ static void iwl_mvm_fwrt_dump_end(void *ctx)
 static int iwl_mvm_fwrt_send_hcmd(void *ctx, struct iwl_host_cmd *host_cmd)
 {
 	struct iwl_mvm *mvm = (struct iwl_mvm *)ctx;
-	int ret;
 
-	mutex_lock(&mvm->mutex);
-	ret = iwl_mvm_send_cmd(mvm, host_cmd);
-	mutex_unlock(&mvm->mutex);
-
-	return ret;
+	guard(mvm)(mvm);
+	return iwl_mvm_send_cmd(mvm, host_cmd);
 }
 
 static bool iwl_mvm_d3_debug_enable(void *ctx)
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tdls.c b/drivers/net/wireless/intel/iwlwifi/mvm/tdls.c
index e7d5f4ebeb259..3d25ff5cd7e8a 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/tdls.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tdls.c
@@ -2,7 +2,7 @@
 /*
  * Copyright (C) 2014 Intel Mobile Communications GmbH
  * Copyright (C) 2017 Intel Deutschland GmbH
- * Copyright (C) 2018-2020, 2022-2023 Intel Corporation
+ * Copyright (C) 2018-2020, 2022-2024 Intel Corporation
  */
 #include <linux/etherdevice.h>
 #include "mvm.h"
@@ -151,7 +151,7 @@ void iwl_mvm_mac_mgd_protect_tdls_discover(struct ieee80211_hw *hw,
 	u32 duration = 2 * vif->bss_conf.dtim_period * vif->bss_conf.beacon_int;
 
 	/* Protect the session to hear the TDLS setup response on the channel */
-	mutex_lock(&mvm->mutex);
+	guard(mvm)(mvm);
 	if (fw_has_capa(&mvm->fw->ucode_capa,
 			IWL_UCODE_TLV_CAPA_SESSION_PROT_CMD))
 		iwl_mvm_schedule_session_protection(mvm, vif, duration,
@@ -159,7 +159,6 @@ void iwl_mvm_mac_mgd_protect_tdls_discover(struct ieee80211_hw *hw,
 	else
 		iwl_mvm_protect_session(mvm, vif, duration,
 					duration, 100, true);
-	mutex_unlock(&mvm->mutex);
 }
 
 static const char *
@@ -460,21 +459,21 @@ void iwl_mvm_tdls_ch_switch_work(struct work_struct *work)
 	int ret;
 
 	mvm = container_of(work, struct iwl_mvm, tdls_cs.dwork.work);
-	mutex_lock(&mvm->mutex);
+	guard(mvm)(mvm);
 
 	/* called after an active channel switch has finished or timed-out */
 	iwl_mvm_tdls_update_cs_state(mvm, IWL_MVM_TDLS_SW_IDLE);
 
 	/* station might be gone, in that case do nothing */
 	if (mvm->tdls_cs.peer.sta_id == IWL_MVM_INVALID_STA)
-		goto out;
+		return;
 
 	sta = rcu_dereference_protected(
 				mvm->fw_id_to_mac_id[mvm->tdls_cs.peer.sta_id],
 				lockdep_is_held(&mvm->mutex));
 	/* the station may not be here, but if it is, it must be a TDLS peer */
 	if (!sta || IS_ERR(sta) || WARN_ON(!sta->tdls))
-		goto out;
+		return;
 
 	mvmsta = iwl_mvm_sta_from_mac80211(sta);
 	vif = mvmsta->vif;
@@ -493,8 +492,6 @@ void iwl_mvm_tdls_ch_switch_work(struct work_struct *work)
 	/* retry after a DTIM if we failed sending now */
 	delay = TU_TO_MS(vif->bss_conf.dtim_period * vif->bss_conf.beacon_int);
 	schedule_delayed_work(&mvm->tdls_cs.dwork, msecs_to_jiffies(delay));
-out:
-	mutex_unlock(&mvm->mutex);
 }
 
 int
@@ -509,7 +506,7 @@ iwl_mvm_tdls_channel_switch(struct ieee80211_hw *hw,
 	unsigned int delay;
 	int ret;
 
-	mutex_lock(&mvm->mutex);
+	guard(mvm)(mvm);
 
 	IWL_DEBUG_TDLS(mvm, "TDLS channel switch with %pM ch %d width %d\n",
 		       sta->addr, chandef->chan->center_freq, chandef->width);
@@ -519,8 +516,7 @@ iwl_mvm_tdls_channel_switch(struct ieee80211_hw *hw,
 		IWL_DEBUG_TDLS(mvm,
 			       "Existing peer. Can't start switch with %pM\n",
 			       sta->addr);
-		ret = -EBUSY;
-		goto out;
+		return -EBUSY;
 	}
 
 	ret = iwl_mvm_tdls_config_channel_switch(mvm, vif,
@@ -529,17 +525,15 @@ iwl_mvm_tdls_channel_switch(struct ieee80211_hw *hw,
 						 oper_class, chandef, 0, 0, 0,
 						 tmpl_skb, ch_sw_tm_ie);
 	if (ret)
-		goto out;
+		return ret;
 
 	/*
 	 * Mark the peer as "in tdls switch" for this vif. We only allow a
 	 * single such peer per vif.
 	 */
 	mvm->tdls_cs.peer.skb = skb_copy(tmpl_skb, GFP_KERNEL);
-	if (!mvm->tdls_cs.peer.skb) {
-		ret = -ENOMEM;
-		goto out;
-	}
+	if (!mvm->tdls_cs.peer.skb)
+		return -ENOMEM;
 
 	mvmsta = iwl_mvm_sta_from_mac80211(sta);
 	mvm->tdls_cs.peer.sta_id = mvmsta->deflink.sta_id;
@@ -556,10 +550,7 @@ iwl_mvm_tdls_channel_switch(struct ieee80211_hw *hw,
 			     vif->bss_conf.beacon_int);
 	mod_delayed_work(system_wq, &mvm->tdls_cs.dwork,
 			 msecs_to_jiffies(delay));
-
-out:
-	mutex_unlock(&mvm->mutex);
-	return ret;
+	return 0;
 }
 
 void iwl_mvm_tdls_cancel_channel_switch(struct ieee80211_hw *hw,
@@ -626,7 +617,7 @@ iwl_mvm_tdls_recv_channel_switch(struct ieee80211_hw *hw,
 		params->action_code == WLAN_TDLS_CHANNEL_SWITCH_REQUEST ?
 		"REQ" : "RESP";
 
-	mutex_lock(&mvm->mutex);
+	guard(mvm)(mvm);
 
 	IWL_DEBUG_TDLS(mvm,
 		       "Received TDLS ch switch action %s from %pM status %d\n",
@@ -670,5 +661,4 @@ retry:
 		1024 / 1000;
 	mod_delayed_work(system_wq, &mvm->tdls_cs.dwork,
 			 msecs_to_jiffies(delay));
-	mutex_unlock(&mvm->mutex);
 }
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tt.c b/drivers/net/wireless/intel/iwlwifi/mvm/tt.c
index 61a4638d1be2f..45b431ffbc977 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/tt.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tt.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2012-2014, 2019-2022 Intel Corporation
+ * Copyright (C) 2012-2014, 2019-2022, 2024 Intel Corporation
  * Copyright (C) 2013-2014 Intel Mobile Communications GmbH
  * Copyright (C) 2015-2016 Intel Deutschland GmbH
  */
@@ -618,48 +618,35 @@ static int iwl_mvm_tzone_get_temp(struct thermal_zone_device *device,
 	int ret;
 	int temp;
 
-	mutex_lock(&mvm->mutex);
+	guard(mvm)(mvm);
 
 	if (!iwl_mvm_firmware_running(mvm) ||
-	    mvm->fwrt.cur_fw_img != IWL_UCODE_REGULAR) {
-		ret = -ENODATA;
-		goto out;
-	}
+	    mvm->fwrt.cur_fw_img != IWL_UCODE_REGULAR)
+		return -ENODATA;
 
 	ret = iwl_mvm_get_temp(mvm, &temp);
 	if (ret)
-		goto out;
+		return ret;
 
 	*temperature = temp * 1000;
-
-out:
-	mutex_unlock(&mvm->mutex);
-	return ret;
+	return 0;
 }
 
 static int iwl_mvm_tzone_set_trip_temp(struct thermal_zone_device *device,
 				       int trip, int temp)
 {
 	struct iwl_mvm *mvm = thermal_zone_device_priv(device);
-	int ret;
 
-	mutex_lock(&mvm->mutex);
+	guard(mvm)(mvm);
 
 	if (!iwl_mvm_firmware_running(mvm) ||
-	    mvm->fwrt.cur_fw_img != IWL_UCODE_REGULAR) {
-		ret = -EIO;
-		goto out;
-	}
+	    mvm->fwrt.cur_fw_img != IWL_UCODE_REGULAR)
+		return -EIO;
 
-	if ((temp / 1000) > S16_MAX) {
-		ret = -EINVAL;
-		goto out;
-	}
+	if ((temp / 1000) > S16_MAX)
+		return -EINVAL;
 
-	ret = iwl_mvm_send_temp_report_ths_cmd(mvm);
-out:
-	mutex_unlock(&mvm->mutex);
-	return ret;
+	return iwl_mvm_send_temp_report_ths_cmd(mvm);
 }
 
 static  struct thermal_zone_device_ops tzone_ops = {
@@ -733,27 +720,18 @@ static int iwl_mvm_tcool_set_cur_state(struct thermal_cooling_device *cdev,
 				       unsigned long new_state)
 {
 	struct iwl_mvm *mvm = (struct iwl_mvm *)(cdev->devdata);
-	int ret;
 
-	mutex_lock(&mvm->mutex);
+	guard(mvm)(mvm);
 
 	if (!iwl_mvm_firmware_running(mvm) ||
-	    mvm->fwrt.cur_fw_img != IWL_UCODE_REGULAR) {
-		ret = -EIO;
-		goto unlock;
-	}
+	    mvm->fwrt.cur_fw_img != IWL_UCODE_REGULAR)
+		return -EIO;
 
-	if (new_state >= ARRAY_SIZE(iwl_mvm_cdev_budgets)) {
-		ret = -EINVAL;
-		goto unlock;
-	}
-
-	ret = iwl_mvm_ctdp_command(mvm, CTDP_CMD_OPERATION_START,
-				   new_state);
+	if (new_state >= ARRAY_SIZE(iwl_mvm_cdev_budgets))
+		return -EINVAL;
 
-unlock:
-	mutex_unlock(&mvm->mutex);
-	return ret;
+	return iwl_mvm_ctdp_command(mvm, CTDP_CMD_OPERATION_START,
+				    new_state);
 }
 
 static const struct thermal_cooling_device_ops tcooling_ops = {
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c
index 47283a358ffdd..0e5fa8374103f 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c
@@ -892,7 +892,7 @@ static void iwl_mvm_tcm_iter(void *_data, u8 *mac, struct ieee80211_vif *vif)
 
 static void iwl_mvm_tcm_results(struct iwl_mvm *mvm)
 {
-	mutex_lock(&mvm->mutex);
+	guard(mvm)(mvm);
 
 	ieee80211_iterate_active_interfaces(
 		mvm->hw, IEEE80211_IFACE_ITER_NORMAL,
@@ -900,8 +900,6 @@ static void iwl_mvm_tcm_results(struct iwl_mvm *mvm)
 
 	if (fw_has_capa(&mvm->fw->ucode_capa, IWL_UCODE_TLV_CAPA_UMAC_SCAN))
 		iwl_mvm_config_scan(mvm);
-
-	mutex_unlock(&mvm->mutex);
 }
 
 static void iwl_mvm_tcm_uapsd_nonagg_detected_wk(struct work_struct *wk)
@@ -1130,10 +1128,9 @@ void iwl_mvm_recalc_tcm(struct iwl_mvm *mvm)
 	spin_unlock(&mvm->tcm.lock);
 
 	if (handle_uapsd && iwl_mvm_has_new_rx_api(mvm)) {
-		mutex_lock(&mvm->mutex);
+		guard(mvm)(mvm);
 		if (iwl_mvm_request_statistics(mvm, true))
 			handle_uapsd = false;
-		mutex_unlock(&mvm->mutex);
 	}
 
 	spin_lock(&mvm->tcm.lock);
-- 
GitLab


From 46144103ace2863e26f4e911aa45200753b7dbca Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Sun, 12 May 2024 15:24:59 +0300
Subject: [PATCH 141/950] wifi: iwlwifi: mvm: don't skip link selection

If we exit EMLSR due to a IWL_MVM_ESR_EXIT*, a MLO scan followed by a
link selection is scheduled with a delay of 30 seconds.
If during that 30 seconds EMLSR was blocked and unblocked
(IWL_MVM_ESR_BLOCKED*), we would still want to get the needed data from
the MLO scan and select link accordingly, and not return immediately to
EMLSR.

Fixes: 2f33561ea8f9 ("wifi: iwlwifi: mvm: trigger link selection after exiting EMLSR")
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Reviewed-by: Johannes Berg <johannes.berg@intel.com>
Link: https://msgid.link/20240512152312.caab27a8dd8f.I63f67e213d5e05416f71513a8d914917d59aa44f@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/link.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/link.c b/drivers/net/wireless/intel/iwlwifi/mvm/link.c
index fd8a21891d262..0745229c8c375 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/link.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/link.c
@@ -1076,6 +1076,13 @@ static void iwl_mvm_esr_unblocked(struct iwl_mvm *mvm,
 
 	IWL_DEBUG_INFO(mvm, "EMLSR is unblocked\n");
 
+	/* We exited due to an EXIT reason, so MLO scan was scheduled already */
+	if (mvmvif->last_esr_exit.reason &&
+	    !(mvmvif->last_esr_exit.reason & IWL_MVM_BLOCK_ESR_REASONS)) {
+		IWL_DEBUG_INFO(mvm, "Wait for MLO scan\n");
+		return;
+	}
+
 	/*
 	 * If EMLSR was blocked for more than 30 seconds, or the last link
 	 * selection decided to not enter EMLSR, trigger a new scan.
-- 
GitLab


From b476564b90668ea957db2411fc946753cdc36d8d Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Sun, 12 May 2024 15:25:02 +0300
Subject: [PATCH 142/950] wifi: iwlwifi: kill iwl-eeprom-read

This is used by dvm only, move to dvm.

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240512152312.72f4bf256c8d.I7433bda9b0fc9eece5210db2cb90c2f03973f5ec@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/Makefile          |  2 +-
 drivers/net/wireless/intel/iwlwifi/dvm/Makefile      |  2 +-
 drivers/net/wireless/intel/iwlwifi/dvm/agn.h         |  4 +++-
 .../iwlwifi/{iwl-eeprom-read.c => dvm/eeprom.c}      |  5 ++---
 drivers/net/wireless/intel/iwlwifi/dvm/main.c        |  4 ++--
 drivers/net/wireless/intel/iwlwifi/iwl-eeprom-read.h | 12 ------------
 drivers/net/wireless/intel/iwlwifi/mvm/nvm.c         |  3 +--
 7 files changed, 10 insertions(+), 22 deletions(-)
 rename drivers/net/wireless/intel/iwlwifi/{iwl-eeprom-read.c => dvm/eeprom.c} (98%)
 delete mode 100644 drivers/net/wireless/intel/iwlwifi/iwl-eeprom-read.h

diff --git a/drivers/net/wireless/intel/iwlwifi/Makefile b/drivers/net/wireless/intel/iwlwifi/Makefile
index 8bb94a4c12cd5..2c2c18cef9ff9 100644
--- a/drivers/net/wireless/intel/iwlwifi/Makefile
+++ b/drivers/net/wireless/intel/iwlwifi/Makefile
@@ -4,7 +4,7 @@ obj-$(CONFIG_IWLWIFI)	+= iwlwifi.o
 iwlwifi-objs		+= iwl-io.o
 iwlwifi-objs		+= iwl-drv.o
 iwlwifi-objs		+= iwl-debug.o
-iwlwifi-objs		+= iwl-eeprom-read.o iwl-eeprom-parse.o
+iwlwifi-objs		+= iwl-eeprom-parse.o
 iwlwifi-objs		+= iwl-phy-db.o iwl-nvm-parse.o
 iwlwifi-objs		+= pcie/drv.o pcie/rx.o pcie/tx.o pcie/trans.o
 iwlwifi-objs		+= pcie/ctxt-info.o pcie/ctxt-info-gen3.o
diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/Makefile b/drivers/net/wireless/intel/iwlwifi/dvm/Makefile
index 0486b17d7c41f..2d0b6d287af41 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/Makefile
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/Makefile
@@ -2,7 +2,7 @@
 # DVM
 obj-$(CONFIG_IWLDVM)	+= iwldvm.o
 iwldvm-objs		+= main.o rs.o mac80211.o ucode.o tx.o
-iwldvm-objs		+= lib.o calib.o tt.o sta.o rx.o
+iwldvm-objs		+= lib.o calib.o tt.o sta.o rx.o eeprom.o
 
 iwldvm-objs		+= power.o
 iwldvm-objs		+= scan.o
diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/agn.h b/drivers/net/wireless/intel/iwlwifi/dvm/agn.h
index fefaa414272b3..47d21413ba596 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/agn.h
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/agn.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2005-2014, 2021 Intel Corporation
+ * Copyright (C) 2005-2014, 2021, 2024 Intel Corporation
  */
 #ifndef __iwl_agn_h__
 #define __iwl_agn_h__
@@ -385,6 +385,8 @@ static inline void iwl_dvm_set_pmi(struct iwl_priv *priv, bool state)
 	iwl_trans_set_pmi(priv->trans, state);
 }
 
+int iwl_read_eeprom(struct iwl_trans *trans, u8 **eeprom, size_t *eeprom_size);
+
 #ifdef CONFIG_IWLWIFI_DEBUGFS
 void iwl_dbgfs_register(struct iwl_priv *priv, struct dentry *dbgfs_dir);
 #else
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-eeprom-read.c b/drivers/net/wireless/intel/iwlwifi/dvm/eeprom.c
similarity index 98%
rename from drivers/net/wireless/intel/iwlwifi/iwl-eeprom-read.c
rename to drivers/net/wireless/intel/iwlwifi/dvm/eeprom.c
index 5f386bb1a3539..3972775fc133b 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-eeprom-read.c
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/eeprom.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2005-2014, 2018-2019, 2021 Intel Corporation
+ * Copyright (C) 2005-2014, 2018-2019, 2021, 2024 Intel Corporation
  */
 #include <linux/types.h>
 #include <linux/slab.h>
@@ -8,10 +8,10 @@
 
 #include "iwl-drv.h"
 #include "iwl-debug.h"
-#include "iwl-eeprom-read.h"
 #include "iwl-io.h"
 #include "iwl-prph.h"
 #include "iwl-csr.h"
+#include "agn.h"
 
 /*
  * EEPROM access time values:
@@ -391,4 +391,3 @@ int iwl_read_eeprom(struct iwl_trans *trans, u8 **eeprom, size_t *eeprom_size)
 
 	return ret;
 }
-IWL_EXPORT_SYMBOL(iwl_read_eeprom);
diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/main.c b/drivers/net/wireless/intel/iwlwifi/dvm/main.c
index 8774dd7b921ef..7bb3011e12e37 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/main.c
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/main.c
@@ -1,7 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /******************************************************************************
  *
- * Copyright(c) 2003 - 2014, 2018 - 2022  Intel Corporation. All rights reserved.
+ * Copyright(c) 2003 - 2014, 2018 - 2022 Intel Corporation. All rights reserved.
+ * Copyright(c) 2024 Intel Corporation. All rights reserved.
  * Copyright(c) 2015 Intel Deutschland GmbH
  *
  * Portions of this file are derived from the ipw3945 project, as well
@@ -25,7 +26,6 @@
 
 #include <asm/div64.h>
 
-#include "iwl-eeprom-read.h"
 #include "iwl-eeprom-parse.h"
 #include "iwl-io.h"
 #include "iwl-trans.h"
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-eeprom-read.h b/drivers/net/wireless/intel/iwlwifi/iwl-eeprom-read.h
deleted file mode 100644
index 63b8e6c6659b6..0000000000000
--- a/drivers/net/wireless/intel/iwlwifi/iwl-eeprom-read.h
+++ /dev/null
@@ -1,12 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
-/*
- * Copyright (C) 2005-2014 Intel Corporation
- */
-#ifndef __iwl_eeprom_h__
-#define __iwl_eeprom_h__
-
-#include "iwl-trans.h"
-
-int iwl_read_eeprom(struct iwl_trans *trans, u8 **eeprom, size_t *eeprom_size);
-
-#endif  /* __iwl_eeprom_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c b/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c
index ae81772228813..1e949b48188e3 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2012-2014, 2018-2019, 2021-2023 Intel Corporation
+ * Copyright (C) 2012-2014, 2018-2019, 2021-2024 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
  */
@@ -10,7 +10,6 @@
 #include "iwl-csr.h"
 #include "mvm.h"
 #include "iwl-eeprom-parse.h"
-#include "iwl-eeprom-read.h"
 #include "iwl-nvm-parse.h"
 #include "iwl-prph.h"
 #include "fw/acpi.h"
-- 
GitLab


From 6584b9d0aa3234bd8af419e46de1a9648cd34116 Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Sun, 12 May 2024 15:25:03 +0300
Subject: [PATCH 143/950] wifi: iwlwifi: move code from iwl-eeprom-parse to dvm

Move code that is DVM only to dvm.

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240512152312.9a1b6ef116e0.I217a513f544d5288a7760d265f51419e81abfd9d@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/Makefile   |   2 +-
 drivers/net/wireless/intel/iwlwifi/dvm/agn.h  |  17 +
 drivers/net/wireless/intel/iwlwifi/dvm/dev.h  |   2 +-
 .../net/wireless/intel/iwlwifi/dvm/devices.c  |   2 +-
 .../net/wireless/intel/iwlwifi/dvm/eeprom.c   | 757 +++++++++++++++
 drivers/net/wireless/intel/iwlwifi/dvm/main.c |   2 +-
 .../net/wireless/intel/iwlwifi/fw/runtime.h   |   2 +-
 .../wireless/intel/iwlwifi/iwl-eeprom-parse.c | 882 ------------------
 .../wireless/intel/iwlwifi/iwl-nvm-parse.h    |   2 +-
 .../wireless/intel/iwlwifi/iwl-nvm-utils.c    | 118 +++
 .../{iwl-eeprom-parse.h => iwl-nvm-utils.h}   |  17 -
 .../net/wireless/intel/iwlwifi/mvm/mac80211.c |   2 +-
 drivers/net/wireless/intel/iwlwifi/mvm/mvm.h  |   2 +-
 drivers/net/wireless/intel/iwlwifi/mvm/nvm.c  |   2 +-
 drivers/net/wireless/intel/iwlwifi/mvm/ops.c  |   2 +-
 drivers/net/wireless/intel/iwlwifi/mvm/tx.c   |   2 +-
 16 files changed, 903 insertions(+), 910 deletions(-)
 delete mode 100644 drivers/net/wireless/intel/iwlwifi/iwl-eeprom-parse.c
 create mode 100644 drivers/net/wireless/intel/iwlwifi/iwl-nvm-utils.c
 rename drivers/net/wireless/intel/iwlwifi/{iwl-eeprom-parse.h => iwl-nvm-utils.h} (73%)

diff --git a/drivers/net/wireless/intel/iwlwifi/Makefile b/drivers/net/wireless/intel/iwlwifi/Makefile
index 2c2c18cef9ff9..93cce88f2e27d 100644
--- a/drivers/net/wireless/intel/iwlwifi/Makefile
+++ b/drivers/net/wireless/intel/iwlwifi/Makefile
@@ -4,7 +4,7 @@ obj-$(CONFIG_IWLWIFI)	+= iwlwifi.o
 iwlwifi-objs		+= iwl-io.o
 iwlwifi-objs		+= iwl-drv.o
 iwlwifi-objs		+= iwl-debug.o
-iwlwifi-objs		+= iwl-eeprom-parse.o
+iwlwifi-objs		+= iwl-nvm-utils.o
 iwlwifi-objs		+= iwl-phy-db.o iwl-nvm-parse.o
 iwlwifi-objs		+= pcie/drv.o pcie/rx.o pcie/tx.o pcie/trans.o
 iwlwifi-objs		+= pcie/ctxt-info.o pcie/ctxt-info-gen3.o
diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/agn.h b/drivers/net/wireless/intel/iwlwifi/dvm/agn.h
index 47d21413ba596..a13add556a7b6 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/agn.h
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/agn.h
@@ -385,6 +385,23 @@ static inline void iwl_dvm_set_pmi(struct iwl_priv *priv, bool state)
 	iwl_trans_set_pmi(priv->trans, state);
 }
 
+/**
+ * iwl_parse_eeprom_data - parse EEPROM data and return values
+ *
+ * @trans: ransport we're parsing for, for debug only
+ * @cfg: device configuration for parsing and overrides
+ * @eeprom: the EEPROM data
+ * @eeprom_size: length of the EEPROM data
+ *
+ * This function parses all EEPROM values we need and then
+ * returns a (newly allocated) struct containing all the
+ * relevant values for driver use. The struct must be freed
+ * later with iwl_free_nvm_data().
+ */
+struct iwl_nvm_data *
+iwl_parse_eeprom_data(struct iwl_trans *trans, const struct iwl_cfg *cfg,
+		      const u8 *eeprom, size_t eeprom_size);
+
 int iwl_read_eeprom(struct iwl_trans *trans, u8 **eeprom, size_t *eeprom_size);
 
 #ifdef CONFIG_IWLWIFI_DEBUGFS
diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/dev.h b/drivers/net/wireless/intel/iwlwifi/dvm/dev.h
index 25283e4b849f2..4ac8b862ad418 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/dev.h
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/dev.h
@@ -19,7 +19,7 @@
 #include <linux/mutex.h>
 
 #include "fw/img.h"
-#include "iwl-eeprom-parse.h"
+#include "iwl-nvm-utils.h"
 #include "iwl-csr.h"
 #include "iwl-debug.h"
 #include "iwl-agn-hw.h"
diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/devices.c b/drivers/net/wireless/intel/iwlwifi/dvm/devices.c
index 39e40901fa464..48a8349680fc3 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/devices.c
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/devices.c
@@ -12,7 +12,7 @@
  */
 #include "iwl-io.h"
 #include "iwl-prph.h"
-#include "iwl-eeprom-parse.h"
+#include "iwl-nvm-utils.h"
 
 #include "agn.h"
 #include "dev.h"
diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/eeprom.c b/drivers/net/wireless/intel/iwlwifi/dvm/eeprom.c
index 3972775fc133b..931aa3f5798d5 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/eeprom.c
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/eeprom.c
@@ -13,6 +13,641 @@
 #include "iwl-csr.h"
 #include "agn.h"
 
+/* EEPROM offset definitions */
+
+/* indirect access definitions */
+#define ADDRESS_MSK                 0x0000FFFF
+#define INDIRECT_TYPE_MSK           0x000F0000
+#define INDIRECT_HOST               0x00010000
+#define INDIRECT_GENERAL            0x00020000
+#define INDIRECT_REGULATORY         0x00030000
+#define INDIRECT_CALIBRATION        0x00040000
+#define INDIRECT_PROCESS_ADJST      0x00050000
+#define INDIRECT_OTHERS             0x00060000
+#define INDIRECT_TXP_LIMIT          0x00070000
+#define INDIRECT_TXP_LIMIT_SIZE     0x00080000
+#define INDIRECT_ADDRESS            0x00100000
+
+/* corresponding link offsets in EEPROM */
+#define EEPROM_LINK_HOST             (2*0x64)
+#define EEPROM_LINK_GENERAL          (2*0x65)
+#define EEPROM_LINK_REGULATORY       (2*0x66)
+#define EEPROM_LINK_CALIBRATION      (2*0x67)
+#define EEPROM_LINK_PROCESS_ADJST    (2*0x68)
+#define EEPROM_LINK_OTHERS           (2*0x69)
+#define EEPROM_LINK_TXP_LIMIT        (2*0x6a)
+#define EEPROM_LINK_TXP_LIMIT_SIZE   (2*0x6b)
+
+/* General */
+#define EEPROM_DEVICE_ID                    (2*0x08)	/* 2 bytes */
+#define EEPROM_SUBSYSTEM_ID		    (2*0x0A)	/* 2 bytes */
+#define EEPROM_MAC_ADDRESS                  (2*0x15)	/* 6  bytes */
+#define EEPROM_BOARD_REVISION               (2*0x35)	/* 2  bytes */
+#define EEPROM_BOARD_PBA_NUMBER             (2*0x3B+1)	/* 9  bytes */
+#define EEPROM_VERSION                      (2*0x44)	/* 2  bytes */
+#define EEPROM_SKU_CAP                      (2*0x45)	/* 2  bytes */
+#define EEPROM_OEM_MODE                     (2*0x46)	/* 2  bytes */
+#define EEPROM_RADIO_CONFIG                 (2*0x48)	/* 2  bytes */
+#define EEPROM_NUM_MAC_ADDRESS              (2*0x4C)	/* 2  bytes */
+
+/* calibration */
+struct iwl_eeprom_calib_hdr {
+	u8 version;
+	u8 pa_type;
+	__le16 voltage;
+} __packed;
+
+#define EEPROM_CALIB_ALL	(INDIRECT_ADDRESS | INDIRECT_CALIBRATION)
+#define EEPROM_XTAL		((2*0x128) | EEPROM_CALIB_ALL)
+
+/* temperature */
+#define EEPROM_KELVIN_TEMPERATURE	((2*0x12A) | EEPROM_CALIB_ALL)
+#define EEPROM_RAW_TEMPERATURE		((2*0x12B) | EEPROM_CALIB_ALL)
+
+/* SKU Capabilities (actual values from EEPROM definition) */
+enum eeprom_sku_bits {
+	EEPROM_SKU_CAP_BAND_24GHZ	= BIT(4),
+	EEPROM_SKU_CAP_BAND_52GHZ	= BIT(5),
+	EEPROM_SKU_CAP_11N_ENABLE	= BIT(6),
+	EEPROM_SKU_CAP_AMT_ENABLE	= BIT(7),
+	EEPROM_SKU_CAP_IPAN_ENABLE	= BIT(8)
+};
+
+/* radio config bits (actual values from EEPROM definition) */
+#define EEPROM_RF_CFG_TYPE_MSK(x)   (x & 0x3)         /* bits 0-1   */
+#define EEPROM_RF_CFG_STEP_MSK(x)   ((x >> 2)  & 0x3) /* bits 2-3   */
+#define EEPROM_RF_CFG_DASH_MSK(x)   ((x >> 4)  & 0x3) /* bits 4-5   */
+#define EEPROM_RF_CFG_PNUM_MSK(x)   ((x >> 6)  & 0x3) /* bits 6-7   */
+#define EEPROM_RF_CFG_TX_ANT_MSK(x) ((x >> 8)  & 0xF) /* bits 8-11  */
+#define EEPROM_RF_CFG_RX_ANT_MSK(x) ((x >> 12) & 0xF) /* bits 12-15 */
+
+/*
+ * EEPROM bands
+ * These are the channel numbers from each band in the order
+ * that they are stored in the EEPROM band information. Note
+ * that EEPROM bands aren't the same as mac80211 bands, and
+ * there are even special "ht40 bands" in the EEPROM.
+ */
+static const u8 iwl_eeprom_band_1[14] = { /* 2.4 GHz */
+	1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14
+};
+
+static const u8 iwl_eeprom_band_2[] = {	/* 4915-5080MHz */
+	183, 184, 185, 187, 188, 189, 192, 196, 7, 8, 11, 12, 16
+};
+
+static const u8 iwl_eeprom_band_3[] = {	/* 5170-5320MHz */
+	34, 36, 38, 40, 42, 44, 46, 48, 52, 56, 60, 64
+};
+
+static const u8 iwl_eeprom_band_4[] = {	/* 5500-5700MHz */
+	100, 104, 108, 112, 116, 120, 124, 128, 132, 136, 140
+};
+
+static const u8 iwl_eeprom_band_5[] = {	/* 5725-5825MHz */
+	145, 149, 153, 157, 161, 165
+};
+
+static const u8 iwl_eeprom_band_6[] = {	/* 2.4 ht40 channel */
+	1, 2, 3, 4, 5, 6, 7
+};
+
+static const u8 iwl_eeprom_band_7[] = {	/* 5.2 ht40 channel */
+	36, 44, 52, 60, 100, 108, 116, 124, 132, 149, 157
+};
+
+#define IWL_NUM_CHANNELS	(ARRAY_SIZE(iwl_eeprom_band_1) + \
+				 ARRAY_SIZE(iwl_eeprom_band_2) + \
+				 ARRAY_SIZE(iwl_eeprom_band_3) + \
+				 ARRAY_SIZE(iwl_eeprom_band_4) + \
+				 ARRAY_SIZE(iwl_eeprom_band_5))
+
+/* rate data (static) */
+static struct ieee80211_rate iwl_cfg80211_rates[] = {
+	{ .bitrate = 1 * 10, .hw_value = 0, .hw_value_short = 0, },
+	{ .bitrate = 2 * 10, .hw_value = 1, .hw_value_short = 1,
+	  .flags = IEEE80211_RATE_SHORT_PREAMBLE, },
+	{ .bitrate = 5.5 * 10, .hw_value = 2, .hw_value_short = 2,
+	  .flags = IEEE80211_RATE_SHORT_PREAMBLE, },
+	{ .bitrate = 11 * 10, .hw_value = 3, .hw_value_short = 3,
+	  .flags = IEEE80211_RATE_SHORT_PREAMBLE, },
+	{ .bitrate = 6 * 10, .hw_value = 4, .hw_value_short = 4, },
+	{ .bitrate = 9 * 10, .hw_value = 5, .hw_value_short = 5, },
+	{ .bitrate = 12 * 10, .hw_value = 6, .hw_value_short = 6, },
+	{ .bitrate = 18 * 10, .hw_value = 7, .hw_value_short = 7, },
+	{ .bitrate = 24 * 10, .hw_value = 8, .hw_value_short = 8, },
+	{ .bitrate = 36 * 10, .hw_value = 9, .hw_value_short = 9, },
+	{ .bitrate = 48 * 10, .hw_value = 10, .hw_value_short = 10, },
+	{ .bitrate = 54 * 10, .hw_value = 11, .hw_value_short = 11, },
+};
+#define RATES_24_OFFS	0
+#define N_RATES_24	ARRAY_SIZE(iwl_cfg80211_rates)
+#define RATES_52_OFFS	4
+#define N_RATES_52	(N_RATES_24 - RATES_52_OFFS)
+
+/* EEPROM reading functions */
+
+static u16 iwl_eeprom_query16(const u8 *eeprom, size_t eeprom_size, int offset)
+{
+	if (WARN_ON(offset + sizeof(u16) > eeprom_size))
+		return 0;
+	return le16_to_cpup((__le16 *)(eeprom + offset));
+}
+
+static u32 eeprom_indirect_address(const u8 *eeprom, size_t eeprom_size,
+				   u32 address)
+{
+	u16 offset = 0;
+
+	if ((address & INDIRECT_ADDRESS) == 0)
+		return address;
+
+	switch (address & INDIRECT_TYPE_MSK) {
+	case INDIRECT_HOST:
+		offset = iwl_eeprom_query16(eeprom, eeprom_size,
+					    EEPROM_LINK_HOST);
+		break;
+	case INDIRECT_GENERAL:
+		offset = iwl_eeprom_query16(eeprom, eeprom_size,
+					    EEPROM_LINK_GENERAL);
+		break;
+	case INDIRECT_REGULATORY:
+		offset = iwl_eeprom_query16(eeprom, eeprom_size,
+					    EEPROM_LINK_REGULATORY);
+		break;
+	case INDIRECT_TXP_LIMIT:
+		offset = iwl_eeprom_query16(eeprom, eeprom_size,
+					    EEPROM_LINK_TXP_LIMIT);
+		break;
+	case INDIRECT_TXP_LIMIT_SIZE:
+		offset = iwl_eeprom_query16(eeprom, eeprom_size,
+					    EEPROM_LINK_TXP_LIMIT_SIZE);
+		break;
+	case INDIRECT_CALIBRATION:
+		offset = iwl_eeprom_query16(eeprom, eeprom_size,
+					    EEPROM_LINK_CALIBRATION);
+		break;
+	case INDIRECT_PROCESS_ADJST:
+		offset = iwl_eeprom_query16(eeprom, eeprom_size,
+					    EEPROM_LINK_PROCESS_ADJST);
+		break;
+	case INDIRECT_OTHERS:
+		offset = iwl_eeprom_query16(eeprom, eeprom_size,
+					    EEPROM_LINK_OTHERS);
+		break;
+	default:
+		WARN_ON(1);
+		break;
+	}
+
+	/* translate the offset from words to byte */
+	return (address & ADDRESS_MSK) + (offset << 1);
+}
+
+static const u8 *iwl_eeprom_query_addr(const u8 *eeprom, size_t eeprom_size,
+				       u32 offset)
+{
+	u32 address = eeprom_indirect_address(eeprom, eeprom_size, offset);
+
+	if (WARN_ON(address >= eeprom_size))
+		return NULL;
+
+	return &eeprom[address];
+}
+
+static int iwl_eeprom_read_calib(const u8 *eeprom, size_t eeprom_size,
+				 struct iwl_nvm_data *data)
+{
+	struct iwl_eeprom_calib_hdr *hdr;
+
+	hdr = (void *)iwl_eeprom_query_addr(eeprom, eeprom_size,
+					    EEPROM_CALIB_ALL);
+	if (!hdr)
+		return -ENODATA;
+	data->calib_version = hdr->version;
+	data->calib_voltage = hdr->voltage;
+
+	return 0;
+}
+
+/**
+ * enum iwl_eeprom_channel_flags - channel flags in EEPROM
+ * @EEPROM_CHANNEL_VALID: channel is usable for this SKU/geo
+ * @EEPROM_CHANNEL_IBSS: usable as an IBSS channel
+ * @EEPROM_CHANNEL_ACTIVE: active scanning allowed
+ * @EEPROM_CHANNEL_RADAR: radar detection required
+ * @EEPROM_CHANNEL_WIDE: 20 MHz channel okay (?)
+ * @EEPROM_CHANNEL_DFS: dynamic freq selection candidate
+ */
+enum iwl_eeprom_channel_flags {
+	EEPROM_CHANNEL_VALID = BIT(0),
+	EEPROM_CHANNEL_IBSS = BIT(1),
+	EEPROM_CHANNEL_ACTIVE = BIT(3),
+	EEPROM_CHANNEL_RADAR = BIT(4),
+	EEPROM_CHANNEL_WIDE = BIT(5),
+	EEPROM_CHANNEL_DFS = BIT(7),
+};
+
+/**
+ * struct iwl_eeprom_channel - EEPROM channel data
+ * @flags: %EEPROM_CHANNEL_* flags
+ * @max_power_avg: max power (in dBm) on this channel, at most 31 dBm
+ */
+struct iwl_eeprom_channel {
+	u8 flags;
+	s8 max_power_avg;
+} __packed;
+
+enum iwl_eeprom_enhanced_txpwr_flags {
+	IWL_EEPROM_ENH_TXP_FL_VALID = BIT(0),
+	IWL_EEPROM_ENH_TXP_FL_BAND_52G = BIT(1),
+	IWL_EEPROM_ENH_TXP_FL_OFDM = BIT(2),
+	IWL_EEPROM_ENH_TXP_FL_40MHZ = BIT(3),
+	IWL_EEPROM_ENH_TXP_FL_HT_AP = BIT(4),
+	IWL_EEPROM_ENH_TXP_FL_RES1 = BIT(5),
+	IWL_EEPROM_ENH_TXP_FL_RES2 = BIT(6),
+	IWL_EEPROM_ENH_TXP_FL_COMMON_TYPE = BIT(7),
+};
+
+/**
+ * struct iwl_eeprom_enhanced_txpwr - enhanced regulatory TX power limits
+ * @flags: entry flags
+ * @channel: channel number
+ * @chain_a_max: chain a max power in 1/2 dBm
+ * @chain_b_max: chain b max power in 1/2 dBm
+ * @chain_c_max: chain c max power in 1/2 dBm
+ * @delta_20_in_40: 20-in-40 deltas (hi/lo)
+ * @mimo2_max: mimo2 max power in 1/2 dBm
+ * @mimo3_max: mimo3 max power in 1/2 dBm
+ *
+ * This structure presents the enhanced regulatory tx power limit layout
+ * in an EEPROM image.
+ */
+struct iwl_eeprom_enhanced_txpwr {
+	u8 flags;
+	u8 channel;
+	s8 chain_a_max;
+	s8 chain_b_max;
+	s8 chain_c_max;
+	u8 delta_20_in_40;
+	s8 mimo2_max;
+	s8 mimo3_max;
+} __packed;
+
+static s8 iwl_get_max_txpwr_half_dbm(const struct iwl_nvm_data *data,
+				     struct iwl_eeprom_enhanced_txpwr *txp)
+{
+	s8 result = 0; /* (.5 dBm) */
+
+	/* Take the highest tx power from any valid chains */
+	if (data->valid_tx_ant & ANT_A && txp->chain_a_max > result)
+		result = txp->chain_a_max;
+
+	if (data->valid_tx_ant & ANT_B && txp->chain_b_max > result)
+		result = txp->chain_b_max;
+
+	if (data->valid_tx_ant & ANT_C && txp->chain_c_max > result)
+		result = txp->chain_c_max;
+
+	if ((data->valid_tx_ant == ANT_AB ||
+	     data->valid_tx_ant == ANT_BC ||
+	     data->valid_tx_ant == ANT_AC) && txp->mimo2_max > result)
+		result = txp->mimo2_max;
+
+	if (data->valid_tx_ant == ANT_ABC && txp->mimo3_max > result)
+		result = txp->mimo3_max;
+
+	return result;
+}
+
+#define EEPROM_TXP_OFFS	(0x00 | INDIRECT_ADDRESS | INDIRECT_TXP_LIMIT)
+#define EEPROM_TXP_ENTRY_LEN sizeof(struct iwl_eeprom_enhanced_txpwr)
+#define EEPROM_TXP_SZ_OFFS (0x00 | INDIRECT_ADDRESS | INDIRECT_TXP_LIMIT_SIZE)
+
+#define TXP_CHECK_AND_PRINT(x) \
+	((txp->flags & IWL_EEPROM_ENH_TXP_FL_##x) ? # x " " : "")
+
+static void
+iwl_eeprom_enh_txp_read_element(struct iwl_nvm_data *data,
+				struct iwl_eeprom_enhanced_txpwr *txp,
+				int n_channels, s8 max_txpower_avg)
+{
+	int ch_idx;
+	enum nl80211_band band;
+
+	band = txp->flags & IWL_EEPROM_ENH_TXP_FL_BAND_52G ?
+		NL80211_BAND_5GHZ : NL80211_BAND_2GHZ;
+
+	for (ch_idx = 0; ch_idx < n_channels; ch_idx++) {
+		struct ieee80211_channel *chan = &data->channels[ch_idx];
+
+		/* update matching channel or from common data only */
+		if (txp->channel != 0 && chan->hw_value != txp->channel)
+			continue;
+
+		/* update matching band only */
+		if (band != chan->band)
+			continue;
+
+		if (chan->max_power < max_txpower_avg &&
+		    !(txp->flags & IWL_EEPROM_ENH_TXP_FL_40MHZ))
+			chan->max_power = max_txpower_avg;
+	}
+}
+
+static void iwl_eeprom_enhanced_txpower(struct device *dev,
+					struct iwl_nvm_data *data,
+					const u8 *eeprom, size_t eeprom_size,
+					int n_channels)
+{
+	struct iwl_eeprom_enhanced_txpwr *txp_array, *txp;
+	int idx, entries;
+	__le16 *txp_len;
+	s8 max_txp_avg_halfdbm;
+
+	BUILD_BUG_ON(sizeof(struct iwl_eeprom_enhanced_txpwr) != 8);
+
+	/* the length is in 16-bit words, but we want entries */
+	txp_len = (__le16 *)iwl_eeprom_query_addr(eeprom, eeprom_size,
+						  EEPROM_TXP_SZ_OFFS);
+	entries = le16_to_cpup(txp_len) * 2 / EEPROM_TXP_ENTRY_LEN;
+
+	txp_array = (void *)iwl_eeprom_query_addr(eeprom, eeprom_size,
+						  EEPROM_TXP_OFFS);
+
+	for (idx = 0; idx < entries; idx++) {
+		txp = &txp_array[idx];
+		/* skip invalid entries */
+		if (!(txp->flags & IWL_EEPROM_ENH_TXP_FL_VALID))
+			continue;
+
+		IWL_DEBUG_EEPROM(dev, "%s %d:\t %s%s%s%s%s%s%s%s (0x%02x)\n",
+				 (txp->channel && (txp->flags &
+					IWL_EEPROM_ENH_TXP_FL_COMMON_TYPE)) ?
+					"Common " : (txp->channel) ?
+					"Channel" : "Common",
+				 (txp->channel),
+				 TXP_CHECK_AND_PRINT(VALID),
+				 TXP_CHECK_AND_PRINT(BAND_52G),
+				 TXP_CHECK_AND_PRINT(OFDM),
+				 TXP_CHECK_AND_PRINT(40MHZ),
+				 TXP_CHECK_AND_PRINT(HT_AP),
+				 TXP_CHECK_AND_PRINT(RES1),
+				 TXP_CHECK_AND_PRINT(RES2),
+				 TXP_CHECK_AND_PRINT(COMMON_TYPE),
+				 txp->flags);
+		IWL_DEBUG_EEPROM(dev,
+				 "\t\t chain_A: %d chain_B: %d chain_C: %d\n",
+				 txp->chain_a_max, txp->chain_b_max,
+				 txp->chain_c_max);
+		IWL_DEBUG_EEPROM(dev,
+				 "\t\t MIMO2: %d MIMO3: %d High 20_on_40: 0x%02x Low 20_on_40: 0x%02x\n",
+				 txp->mimo2_max, txp->mimo3_max,
+				 ((txp->delta_20_in_40 & 0xf0) >> 4),
+				 (txp->delta_20_in_40 & 0x0f));
+
+		max_txp_avg_halfdbm = iwl_get_max_txpwr_half_dbm(data, txp);
+
+		iwl_eeprom_enh_txp_read_element(data, txp, n_channels,
+				DIV_ROUND_UP(max_txp_avg_halfdbm, 2));
+
+		if (max_txp_avg_halfdbm > data->max_tx_pwr_half_dbm)
+			data->max_tx_pwr_half_dbm = max_txp_avg_halfdbm;
+	}
+}
+
+static void iwl_init_band_reference(const struct iwl_cfg *cfg,
+				    const u8 *eeprom, size_t eeprom_size,
+				    int eeprom_band, int *eeprom_ch_count,
+				    const struct iwl_eeprom_channel **ch_info,
+				    const u8 **eeprom_ch_array)
+{
+	u32 offset = cfg->eeprom_params->regulatory_bands[eeprom_band - 1];
+
+	offset |= INDIRECT_ADDRESS | INDIRECT_REGULATORY;
+
+	*ch_info = (void *)iwl_eeprom_query_addr(eeprom, eeprom_size, offset);
+
+	switch (eeprom_band) {
+	case 1:		/* 2.4GHz band */
+		*eeprom_ch_count = ARRAY_SIZE(iwl_eeprom_band_1);
+		*eeprom_ch_array = iwl_eeprom_band_1;
+		break;
+	case 2:		/* 4.9GHz band */
+		*eeprom_ch_count = ARRAY_SIZE(iwl_eeprom_band_2);
+		*eeprom_ch_array = iwl_eeprom_band_2;
+		break;
+	case 3:		/* 5.2GHz band */
+		*eeprom_ch_count = ARRAY_SIZE(iwl_eeprom_band_3);
+		*eeprom_ch_array = iwl_eeprom_band_3;
+		break;
+	case 4:		/* 5.5GHz band */
+		*eeprom_ch_count = ARRAY_SIZE(iwl_eeprom_band_4);
+		*eeprom_ch_array = iwl_eeprom_band_4;
+		break;
+	case 5:		/* 5.7GHz band */
+		*eeprom_ch_count = ARRAY_SIZE(iwl_eeprom_band_5);
+		*eeprom_ch_array = iwl_eeprom_band_5;
+		break;
+	case 6:		/* 2.4GHz ht40 channels */
+		*eeprom_ch_count = ARRAY_SIZE(iwl_eeprom_band_6);
+		*eeprom_ch_array = iwl_eeprom_band_6;
+		break;
+	case 7:		/* 5 GHz ht40 channels */
+		*eeprom_ch_count = ARRAY_SIZE(iwl_eeprom_band_7);
+		*eeprom_ch_array = iwl_eeprom_band_7;
+		break;
+	default:
+		*eeprom_ch_count = 0;
+		*eeprom_ch_array = NULL;
+		WARN_ON(1);
+	}
+}
+
+#define CHECK_AND_PRINT(x) \
+	((eeprom_ch->flags & EEPROM_CHANNEL_##x) ? # x " " : "")
+
+static void iwl_mod_ht40_chan_info(struct device *dev,
+				   struct iwl_nvm_data *data, int n_channels,
+				   enum nl80211_band band, u16 channel,
+				   const struct iwl_eeprom_channel *eeprom_ch,
+				   u8 clear_ht40_extension_channel)
+{
+	struct ieee80211_channel *chan = NULL;
+	int i;
+
+	for (i = 0; i < n_channels; i++) {
+		if (data->channels[i].band != band)
+			continue;
+		if (data->channels[i].hw_value != channel)
+			continue;
+		chan = &data->channels[i];
+		break;
+	}
+
+	if (!chan)
+		return;
+
+	IWL_DEBUG_EEPROM(dev,
+			 "HT40 Ch. %d [%sGHz] %s%s%s%s%s(0x%02x %ddBm): Ad-Hoc %ssupported\n",
+			 channel,
+			 band == NL80211_BAND_5GHZ ? "5.2" : "2.4",
+			 CHECK_AND_PRINT(IBSS),
+			 CHECK_AND_PRINT(ACTIVE),
+			 CHECK_AND_PRINT(RADAR),
+			 CHECK_AND_PRINT(WIDE),
+			 CHECK_AND_PRINT(DFS),
+			 eeprom_ch->flags,
+			 eeprom_ch->max_power_avg,
+			 ((eeprom_ch->flags & EEPROM_CHANNEL_IBSS) &&
+			  !(eeprom_ch->flags & EEPROM_CHANNEL_RADAR)) ? ""
+								      : "not ");
+
+	if (eeprom_ch->flags & EEPROM_CHANNEL_VALID)
+		chan->flags &= ~clear_ht40_extension_channel;
+}
+
+#define CHECK_AND_PRINT_I(x)	\
+	((eeprom_ch_info[ch_idx].flags & EEPROM_CHANNEL_##x) ? # x " " : "")
+
+static int iwl_init_channel_map(struct device *dev, const struct iwl_cfg *cfg,
+				struct iwl_nvm_data *data,
+				const u8 *eeprom, size_t eeprom_size)
+{
+	int band, ch_idx;
+	const struct iwl_eeprom_channel *eeprom_ch_info;
+	const u8 *eeprom_ch_array;
+	int eeprom_ch_count;
+	int n_channels = 0;
+
+	/*
+	 * Loop through the 5 EEPROM bands and add them to the parse list
+	 */
+	for (band = 1; band <= 5; band++) {
+		struct ieee80211_channel *channel;
+
+		iwl_init_band_reference(cfg, eeprom, eeprom_size, band,
+					&eeprom_ch_count, &eeprom_ch_info,
+					&eeprom_ch_array);
+
+		/* Loop through each band adding each of the channels */
+		for (ch_idx = 0; ch_idx < eeprom_ch_count; ch_idx++) {
+			const struct iwl_eeprom_channel *eeprom_ch;
+
+			eeprom_ch = &eeprom_ch_info[ch_idx];
+
+			if (!(eeprom_ch->flags & EEPROM_CHANNEL_VALID)) {
+				IWL_DEBUG_EEPROM(dev,
+						 "Ch. %d Flags %x [%sGHz] - No traffic\n",
+						 eeprom_ch_array[ch_idx],
+						 eeprom_ch_info[ch_idx].flags,
+						 (band != 1) ? "5.2" : "2.4");
+				continue;
+			}
+
+			channel = &data->channels[n_channels];
+			n_channels++;
+
+			channel->hw_value = eeprom_ch_array[ch_idx];
+			channel->band = (band == 1) ? NL80211_BAND_2GHZ
+						    : NL80211_BAND_5GHZ;
+			channel->center_freq =
+				ieee80211_channel_to_frequency(
+					channel->hw_value, channel->band);
+
+			/* set no-HT40, will enable as appropriate later */
+			channel->flags = IEEE80211_CHAN_NO_HT40;
+
+			if (!(eeprom_ch->flags & EEPROM_CHANNEL_IBSS))
+				channel->flags |= IEEE80211_CHAN_NO_IR;
+
+			if (!(eeprom_ch->flags & EEPROM_CHANNEL_ACTIVE))
+				channel->flags |= IEEE80211_CHAN_NO_IR;
+
+			if (eeprom_ch->flags & EEPROM_CHANNEL_RADAR)
+				channel->flags |= IEEE80211_CHAN_RADAR;
+
+			/* Initialize regulatory-based run-time data */
+			channel->max_power =
+				eeprom_ch_info[ch_idx].max_power_avg;
+			IWL_DEBUG_EEPROM(dev,
+					 "Ch. %d [%sGHz] %s%s%s%s%s%s(0x%02x %ddBm): Ad-Hoc %ssupported\n",
+					 channel->hw_value,
+					 (band != 1) ? "5.2" : "2.4",
+					 CHECK_AND_PRINT_I(VALID),
+					 CHECK_AND_PRINT_I(IBSS),
+					 CHECK_AND_PRINT_I(ACTIVE),
+					 CHECK_AND_PRINT_I(RADAR),
+					 CHECK_AND_PRINT_I(WIDE),
+					 CHECK_AND_PRINT_I(DFS),
+					 eeprom_ch_info[ch_idx].flags,
+					 eeprom_ch_info[ch_idx].max_power_avg,
+					 ((eeprom_ch_info[ch_idx].flags &
+							EEPROM_CHANNEL_IBSS) &&
+					  !(eeprom_ch_info[ch_idx].flags &
+							EEPROM_CHANNEL_RADAR))
+						? "" : "not ");
+		}
+	}
+
+	if (cfg->eeprom_params->enhanced_txpower) {
+		/*
+		 * for newer device (6000 series and up)
+		 * EEPROM contain enhanced tx power information
+		 * driver need to process addition information
+		 * to determine the max channel tx power limits
+		 */
+		iwl_eeprom_enhanced_txpower(dev, data, eeprom, eeprom_size,
+					    n_channels);
+	} else {
+		/* All others use data from channel map */
+		int i;
+
+		data->max_tx_pwr_half_dbm = -128;
+
+		for (i = 0; i < n_channels; i++)
+			data->max_tx_pwr_half_dbm =
+				max_t(s8, data->max_tx_pwr_half_dbm,
+				      data->channels[i].max_power * 2);
+	}
+
+	/* Check if we do have HT40 channels */
+	if (cfg->eeprom_params->regulatory_bands[5] ==
+				EEPROM_REGULATORY_BAND_NO_HT40 &&
+	    cfg->eeprom_params->regulatory_bands[6] ==
+				EEPROM_REGULATORY_BAND_NO_HT40)
+		return n_channels;
+
+	/* Two additional EEPROM bands for 2.4 and 5 GHz HT40 channels */
+	for (band = 6; band <= 7; band++) {
+		enum nl80211_band ieeeband;
+
+		iwl_init_band_reference(cfg, eeprom, eeprom_size, band,
+					&eeprom_ch_count, &eeprom_ch_info,
+					&eeprom_ch_array);
+
+		/* EEPROM band 6 is 2.4, band 7 is 5 GHz */
+		ieeeband = (band == 6) ? NL80211_BAND_2GHZ
+				       : NL80211_BAND_5GHZ;
+
+		/* Loop through each band adding each of the channels */
+		for (ch_idx = 0; ch_idx < eeprom_ch_count; ch_idx++) {
+			/* Set up driver's info for lower half */
+			iwl_mod_ht40_chan_info(dev, data, n_channels, ieeeband,
+					       eeprom_ch_array[ch_idx],
+					       &eeprom_ch_info[ch_idx],
+					       IEEE80211_CHAN_NO_HT40PLUS);
+
+			/* Set up driver's info for upper half */
+			iwl_mod_ht40_chan_info(dev, data, n_channels, ieeeband,
+					       eeprom_ch_array[ch_idx] + 4,
+					       &eeprom_ch_info[ch_idx],
+					       IEEE80211_CHAN_NO_HT40MINUS);
+		}
+	}
+
+	return n_channels;
+}
 /*
  * EEPROM access time values:
  *
@@ -391,3 +1026,125 @@ int iwl_read_eeprom(struct iwl_trans *trans, u8 **eeprom, size_t *eeprom_size)
 
 	return ret;
 }
+
+static void iwl_init_sbands(struct iwl_trans *trans, const struct iwl_cfg *cfg,
+			    struct iwl_nvm_data *data,
+			    const u8 *eeprom, size_t eeprom_size)
+{
+	struct device *dev = trans->dev;
+	int n_channels = iwl_init_channel_map(dev, cfg, data,
+					      eeprom, eeprom_size);
+	int n_used = 0;
+	struct ieee80211_supported_band *sband;
+
+	sband = &data->bands[NL80211_BAND_2GHZ];
+	sband->band = NL80211_BAND_2GHZ;
+	sband->bitrates = &iwl_cfg80211_rates[RATES_24_OFFS];
+	sband->n_bitrates = N_RATES_24;
+	n_used += iwl_init_sband_channels(data, sband, n_channels,
+					  NL80211_BAND_2GHZ);
+	iwl_init_ht_hw_capab(trans, data, &sband->ht_cap, NL80211_BAND_2GHZ,
+			     data->valid_tx_ant, data->valid_rx_ant);
+
+	sband = &data->bands[NL80211_BAND_5GHZ];
+	sband->band = NL80211_BAND_5GHZ;
+	sband->bitrates = &iwl_cfg80211_rates[RATES_52_OFFS];
+	sband->n_bitrates = N_RATES_52;
+	n_used += iwl_init_sband_channels(data, sband, n_channels,
+					  NL80211_BAND_5GHZ);
+	iwl_init_ht_hw_capab(trans, data, &sband->ht_cap, NL80211_BAND_5GHZ,
+			     data->valid_tx_ant, data->valid_rx_ant);
+
+	if (n_channels != n_used)
+		IWL_ERR_DEV(dev, "EEPROM: used only %d of %d channels\n",
+			    n_used, n_channels);
+}
+
+/* EEPROM data functions */
+struct iwl_nvm_data *
+iwl_parse_eeprom_data(struct iwl_trans *trans, const struct iwl_cfg *cfg,
+		      const u8 *eeprom, size_t eeprom_size)
+{
+	struct iwl_nvm_data *data;
+	struct device *dev = trans->dev;
+	const void *tmp;
+	u16 radio_cfg, sku;
+
+	if (WARN_ON(!cfg || !cfg->eeprom_params))
+		return NULL;
+
+	data = kzalloc(struct_size(data, channels, IWL_NUM_CHANNELS),
+		       GFP_KERNEL);
+	if (!data)
+		return NULL;
+
+	/* get MAC address(es) */
+	tmp = iwl_eeprom_query_addr(eeprom, eeprom_size, EEPROM_MAC_ADDRESS);
+	if (!tmp)
+		goto err_free;
+	memcpy(data->hw_addr, tmp, ETH_ALEN);
+	data->n_hw_addrs = iwl_eeprom_query16(eeprom, eeprom_size,
+					      EEPROM_NUM_MAC_ADDRESS);
+
+	if (iwl_eeprom_read_calib(eeprom, eeprom_size, data))
+		goto err_free;
+
+	tmp = iwl_eeprom_query_addr(eeprom, eeprom_size, EEPROM_XTAL);
+	if (!tmp)
+		goto err_free;
+	memcpy(data->xtal_calib, tmp, sizeof(data->xtal_calib));
+
+	tmp = iwl_eeprom_query_addr(eeprom, eeprom_size,
+				    EEPROM_RAW_TEMPERATURE);
+	if (!tmp)
+		goto err_free;
+	data->raw_temperature = *(__le16 *)tmp;
+
+	tmp = iwl_eeprom_query_addr(eeprom, eeprom_size,
+				    EEPROM_KELVIN_TEMPERATURE);
+	if (!tmp)
+		goto err_free;
+	data->kelvin_temperature = *(__le16 *)tmp;
+	data->kelvin_voltage = *((__le16 *)tmp + 1);
+
+	radio_cfg =
+		iwl_eeprom_query16(eeprom, eeprom_size, EEPROM_RADIO_CONFIG);
+	data->radio_cfg_dash = EEPROM_RF_CFG_DASH_MSK(radio_cfg);
+	data->radio_cfg_pnum = EEPROM_RF_CFG_PNUM_MSK(radio_cfg);
+	data->radio_cfg_step = EEPROM_RF_CFG_STEP_MSK(radio_cfg);
+	data->radio_cfg_type = EEPROM_RF_CFG_TYPE_MSK(radio_cfg);
+	data->valid_rx_ant = EEPROM_RF_CFG_RX_ANT_MSK(radio_cfg);
+	data->valid_tx_ant = EEPROM_RF_CFG_TX_ANT_MSK(radio_cfg);
+
+	sku = iwl_eeprom_query16(eeprom, eeprom_size,
+				 EEPROM_SKU_CAP);
+	data->sku_cap_11n_enable = sku & EEPROM_SKU_CAP_11N_ENABLE;
+	data->sku_cap_amt_enable = sku & EEPROM_SKU_CAP_AMT_ENABLE;
+	data->sku_cap_band_24ghz_enable = sku & EEPROM_SKU_CAP_BAND_24GHZ;
+	data->sku_cap_band_52ghz_enable = sku & EEPROM_SKU_CAP_BAND_52GHZ;
+	data->sku_cap_ipan_enable = sku & EEPROM_SKU_CAP_IPAN_ENABLE;
+	if (iwlwifi_mod_params.disable_11n & IWL_DISABLE_HT_ALL)
+		data->sku_cap_11n_enable = false;
+
+	data->nvm_version = iwl_eeprom_query16(eeprom, eeprom_size,
+					       EEPROM_VERSION);
+
+	/* check overrides (some devices have wrong EEPROM) */
+	if (cfg->valid_tx_ant)
+		data->valid_tx_ant = cfg->valid_tx_ant;
+	if (cfg->valid_rx_ant)
+		data->valid_rx_ant = cfg->valid_rx_ant;
+
+	if (!data->valid_tx_ant || !data->valid_rx_ant) {
+		IWL_ERR_DEV(dev, "invalid antennas (0x%x, 0x%x)\n",
+			    data->valid_tx_ant, data->valid_rx_ant);
+		goto err_free;
+	}
+
+	iwl_init_sbands(trans, cfg, data, eeprom, eeprom_size);
+
+	return data;
+ err_free:
+	kfree(data);
+	return NULL;
+}
diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/main.c b/drivers/net/wireless/intel/iwlwifi/dvm/main.c
index 7bb3011e12e37..65b7c68e5ca77 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/main.c
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/main.c
@@ -26,7 +26,7 @@
 
 #include <asm/div64.h>
 
-#include "iwl-eeprom-parse.h"
+#include "iwl-nvm-utils.h"
 #include "iwl-io.h"
 #include "iwl-trans.h"
 #include "iwl-op-mode.h"
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/runtime.h b/drivers/net/wireless/intel/iwlwifi/fw/runtime.h
index d201440066ea9..3fcc08b3c0db0 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/runtime.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/runtime.h
@@ -12,7 +12,7 @@
 #include "fw/api/debug.h"
 #include "fw/api/paging.h"
 #include "fw/api/power.h"
-#include "iwl-eeprom-parse.h"
+#include "iwl-nvm-utils.h"
 #include "fw/acpi.h"
 #include "fw/regulatory.h"
 
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-eeprom-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-eeprom-parse.c
deleted file mode 100644
index 2b290fab1ef2b..0000000000000
--- a/drivers/net/wireless/intel/iwlwifi/iwl-eeprom-parse.c
+++ /dev/null
@@ -1,882 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
-/*
- * Copyright (C) 2005-2014, 2018-2021, 2023 Intel Corporation
- * Copyright (C) 2015 Intel Mobile Communications GmbH
- */
-#include <linux/types.h>
-#include <linux/slab.h>
-#include <linux/export.h>
-#include "iwl-drv.h"
-#include "iwl-modparams.h"
-#include "iwl-eeprom-parse.h"
-
-#if IS_ENABLED(CONFIG_IWLDVM)
-/* EEPROM offset definitions */
-
-/* indirect access definitions */
-#define ADDRESS_MSK                 0x0000FFFF
-#define INDIRECT_TYPE_MSK           0x000F0000
-#define INDIRECT_HOST               0x00010000
-#define INDIRECT_GENERAL            0x00020000
-#define INDIRECT_REGULATORY         0x00030000
-#define INDIRECT_CALIBRATION        0x00040000
-#define INDIRECT_PROCESS_ADJST      0x00050000
-#define INDIRECT_OTHERS             0x00060000
-#define INDIRECT_TXP_LIMIT          0x00070000
-#define INDIRECT_TXP_LIMIT_SIZE     0x00080000
-#define INDIRECT_ADDRESS            0x00100000
-
-/* corresponding link offsets in EEPROM */
-#define EEPROM_LINK_HOST             (2*0x64)
-#define EEPROM_LINK_GENERAL          (2*0x65)
-#define EEPROM_LINK_REGULATORY       (2*0x66)
-#define EEPROM_LINK_CALIBRATION      (2*0x67)
-#define EEPROM_LINK_PROCESS_ADJST    (2*0x68)
-#define EEPROM_LINK_OTHERS           (2*0x69)
-#define EEPROM_LINK_TXP_LIMIT        (2*0x6a)
-#define EEPROM_LINK_TXP_LIMIT_SIZE   (2*0x6b)
-
-/* General */
-#define EEPROM_DEVICE_ID                    (2*0x08)	/* 2 bytes */
-#define EEPROM_SUBSYSTEM_ID		    (2*0x0A)	/* 2 bytes */
-#define EEPROM_MAC_ADDRESS                  (2*0x15)	/* 6  bytes */
-#define EEPROM_BOARD_REVISION               (2*0x35)	/* 2  bytes */
-#define EEPROM_BOARD_PBA_NUMBER             (2*0x3B+1)	/* 9  bytes */
-#define EEPROM_VERSION                      (2*0x44)	/* 2  bytes */
-#define EEPROM_SKU_CAP                      (2*0x45)	/* 2  bytes */
-#define EEPROM_OEM_MODE                     (2*0x46)	/* 2  bytes */
-#define EEPROM_RADIO_CONFIG                 (2*0x48)	/* 2  bytes */
-#define EEPROM_NUM_MAC_ADDRESS              (2*0x4C)	/* 2  bytes */
-
-/* calibration */
-struct iwl_eeprom_calib_hdr {
-	u8 version;
-	u8 pa_type;
-	__le16 voltage;
-} __packed;
-
-#define EEPROM_CALIB_ALL	(INDIRECT_ADDRESS | INDIRECT_CALIBRATION)
-#define EEPROM_XTAL		((2*0x128) | EEPROM_CALIB_ALL)
-
-/* temperature */
-#define EEPROM_KELVIN_TEMPERATURE	((2*0x12A) | EEPROM_CALIB_ALL)
-#define EEPROM_RAW_TEMPERATURE		((2*0x12B) | EEPROM_CALIB_ALL)
-
-/* SKU Capabilities (actual values from EEPROM definition) */
-enum eeprom_sku_bits {
-	EEPROM_SKU_CAP_BAND_24GHZ	= BIT(4),
-	EEPROM_SKU_CAP_BAND_52GHZ	= BIT(5),
-	EEPROM_SKU_CAP_11N_ENABLE	= BIT(6),
-	EEPROM_SKU_CAP_AMT_ENABLE	= BIT(7),
-	EEPROM_SKU_CAP_IPAN_ENABLE	= BIT(8)
-};
-
-/* radio config bits (actual values from EEPROM definition) */
-#define EEPROM_RF_CFG_TYPE_MSK(x)   (x & 0x3)         /* bits 0-1   */
-#define EEPROM_RF_CFG_STEP_MSK(x)   ((x >> 2)  & 0x3) /* bits 2-3   */
-#define EEPROM_RF_CFG_DASH_MSK(x)   ((x >> 4)  & 0x3) /* bits 4-5   */
-#define EEPROM_RF_CFG_PNUM_MSK(x)   ((x >> 6)  & 0x3) /* bits 6-7   */
-#define EEPROM_RF_CFG_TX_ANT_MSK(x) ((x >> 8)  & 0xF) /* bits 8-11  */
-#define EEPROM_RF_CFG_RX_ANT_MSK(x) ((x >> 12) & 0xF) /* bits 12-15 */
-
-
-/*
- * EEPROM bands
- * These are the channel numbers from each band in the order
- * that they are stored in the EEPROM band information. Note
- * that EEPROM bands aren't the same as mac80211 bands, and
- * there are even special "ht40 bands" in the EEPROM.
- */
-static const u8 iwl_eeprom_band_1[14] = { /* 2.4 GHz */
-	1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14
-};
-
-static const u8 iwl_eeprom_band_2[] = {	/* 4915-5080MHz */
-	183, 184, 185, 187, 188, 189, 192, 196, 7, 8, 11, 12, 16
-};
-
-static const u8 iwl_eeprom_band_3[] = {	/* 5170-5320MHz */
-	34, 36, 38, 40, 42, 44, 46, 48, 52, 56, 60, 64
-};
-
-static const u8 iwl_eeprom_band_4[] = {	/* 5500-5700MHz */
-	100, 104, 108, 112, 116, 120, 124, 128, 132, 136, 140
-};
-
-static const u8 iwl_eeprom_band_5[] = {	/* 5725-5825MHz */
-	145, 149, 153, 157, 161, 165
-};
-
-static const u8 iwl_eeprom_band_6[] = {	/* 2.4 ht40 channel */
-	1, 2, 3, 4, 5, 6, 7
-};
-
-static const u8 iwl_eeprom_band_7[] = {	/* 5.2 ht40 channel */
-	36, 44, 52, 60, 100, 108, 116, 124, 132, 149, 157
-};
-
-#define IWL_NUM_CHANNELS	(ARRAY_SIZE(iwl_eeprom_band_1) + \
-				 ARRAY_SIZE(iwl_eeprom_band_2) + \
-				 ARRAY_SIZE(iwl_eeprom_band_3) + \
-				 ARRAY_SIZE(iwl_eeprom_band_4) + \
-				 ARRAY_SIZE(iwl_eeprom_band_5))
-
-/* rate data (static) */
-static struct ieee80211_rate iwl_cfg80211_rates[] = {
-	{ .bitrate = 1 * 10, .hw_value = 0, .hw_value_short = 0, },
-	{ .bitrate = 2 * 10, .hw_value = 1, .hw_value_short = 1,
-	  .flags = IEEE80211_RATE_SHORT_PREAMBLE, },
-	{ .bitrate = 5.5 * 10, .hw_value = 2, .hw_value_short = 2,
-	  .flags = IEEE80211_RATE_SHORT_PREAMBLE, },
-	{ .bitrate = 11 * 10, .hw_value = 3, .hw_value_short = 3,
-	  .flags = IEEE80211_RATE_SHORT_PREAMBLE, },
-	{ .bitrate = 6 * 10, .hw_value = 4, .hw_value_short = 4, },
-	{ .bitrate = 9 * 10, .hw_value = 5, .hw_value_short = 5, },
-	{ .bitrate = 12 * 10, .hw_value = 6, .hw_value_short = 6, },
-	{ .bitrate = 18 * 10, .hw_value = 7, .hw_value_short = 7, },
-	{ .bitrate = 24 * 10, .hw_value = 8, .hw_value_short = 8, },
-	{ .bitrate = 36 * 10, .hw_value = 9, .hw_value_short = 9, },
-	{ .bitrate = 48 * 10, .hw_value = 10, .hw_value_short = 10, },
-	{ .bitrate = 54 * 10, .hw_value = 11, .hw_value_short = 11, },
-};
-#define RATES_24_OFFS	0
-#define N_RATES_24	ARRAY_SIZE(iwl_cfg80211_rates)
-#define RATES_52_OFFS	4
-#define N_RATES_52	(N_RATES_24 - RATES_52_OFFS)
-
-/* EEPROM reading functions */
-
-static u16 iwl_eeprom_query16(const u8 *eeprom, size_t eeprom_size, int offset)
-{
-	if (WARN_ON(offset + sizeof(u16) > eeprom_size))
-		return 0;
-	return le16_to_cpup((__le16 *)(eeprom + offset));
-}
-
-static u32 eeprom_indirect_address(const u8 *eeprom, size_t eeprom_size,
-				   u32 address)
-{
-	u16 offset = 0;
-
-	if ((address & INDIRECT_ADDRESS) == 0)
-		return address;
-
-	switch (address & INDIRECT_TYPE_MSK) {
-	case INDIRECT_HOST:
-		offset = iwl_eeprom_query16(eeprom, eeprom_size,
-					    EEPROM_LINK_HOST);
-		break;
-	case INDIRECT_GENERAL:
-		offset = iwl_eeprom_query16(eeprom, eeprom_size,
-					    EEPROM_LINK_GENERAL);
-		break;
-	case INDIRECT_REGULATORY:
-		offset = iwl_eeprom_query16(eeprom, eeprom_size,
-					    EEPROM_LINK_REGULATORY);
-		break;
-	case INDIRECT_TXP_LIMIT:
-		offset = iwl_eeprom_query16(eeprom, eeprom_size,
-					    EEPROM_LINK_TXP_LIMIT);
-		break;
-	case INDIRECT_TXP_LIMIT_SIZE:
-		offset = iwl_eeprom_query16(eeprom, eeprom_size,
-					    EEPROM_LINK_TXP_LIMIT_SIZE);
-		break;
-	case INDIRECT_CALIBRATION:
-		offset = iwl_eeprom_query16(eeprom, eeprom_size,
-					    EEPROM_LINK_CALIBRATION);
-		break;
-	case INDIRECT_PROCESS_ADJST:
-		offset = iwl_eeprom_query16(eeprom, eeprom_size,
-					    EEPROM_LINK_PROCESS_ADJST);
-		break;
-	case INDIRECT_OTHERS:
-		offset = iwl_eeprom_query16(eeprom, eeprom_size,
-					    EEPROM_LINK_OTHERS);
-		break;
-	default:
-		WARN_ON(1);
-		break;
-	}
-
-	/* translate the offset from words to byte */
-	return (address & ADDRESS_MSK) + (offset << 1);
-}
-
-static const u8 *iwl_eeprom_query_addr(const u8 *eeprom, size_t eeprom_size,
-				       u32 offset)
-{
-	u32 address = eeprom_indirect_address(eeprom, eeprom_size, offset);
-
-	if (WARN_ON(address >= eeprom_size))
-		return NULL;
-
-	return &eeprom[address];
-}
-
-static int iwl_eeprom_read_calib(const u8 *eeprom, size_t eeprom_size,
-				 struct iwl_nvm_data *data)
-{
-	struct iwl_eeprom_calib_hdr *hdr;
-
-	hdr = (void *)iwl_eeprom_query_addr(eeprom, eeprom_size,
-					    EEPROM_CALIB_ALL);
-	if (!hdr)
-		return -ENODATA;
-	data->calib_version = hdr->version;
-	data->calib_voltage = hdr->voltage;
-
-	return 0;
-}
-
-/**
- * enum iwl_eeprom_channel_flags - channel flags in EEPROM
- * @EEPROM_CHANNEL_VALID: channel is usable for this SKU/geo
- * @EEPROM_CHANNEL_IBSS: usable as an IBSS channel
- * @EEPROM_CHANNEL_ACTIVE: active scanning allowed
- * @EEPROM_CHANNEL_RADAR: radar detection required
- * @EEPROM_CHANNEL_WIDE: 20 MHz channel okay (?)
- * @EEPROM_CHANNEL_DFS: dynamic freq selection candidate
- */
-enum iwl_eeprom_channel_flags {
-	EEPROM_CHANNEL_VALID = BIT(0),
-	EEPROM_CHANNEL_IBSS = BIT(1),
-	EEPROM_CHANNEL_ACTIVE = BIT(3),
-	EEPROM_CHANNEL_RADAR = BIT(4),
-	EEPROM_CHANNEL_WIDE = BIT(5),
-	EEPROM_CHANNEL_DFS = BIT(7),
-};
-
-/**
- * struct iwl_eeprom_channel - EEPROM channel data
- * @flags: %EEPROM_CHANNEL_* flags
- * @max_power_avg: max power (in dBm) on this channel, at most 31 dBm
- */
-struct iwl_eeprom_channel {
-	u8 flags;
-	s8 max_power_avg;
-} __packed;
-
-
-enum iwl_eeprom_enhanced_txpwr_flags {
-	IWL_EEPROM_ENH_TXP_FL_VALID = BIT(0),
-	IWL_EEPROM_ENH_TXP_FL_BAND_52G = BIT(1),
-	IWL_EEPROM_ENH_TXP_FL_OFDM = BIT(2),
-	IWL_EEPROM_ENH_TXP_FL_40MHZ = BIT(3),
-	IWL_EEPROM_ENH_TXP_FL_HT_AP = BIT(4),
-	IWL_EEPROM_ENH_TXP_FL_RES1 = BIT(5),
-	IWL_EEPROM_ENH_TXP_FL_RES2 = BIT(6),
-	IWL_EEPROM_ENH_TXP_FL_COMMON_TYPE = BIT(7),
-};
-
-/**
- * struct iwl_eeprom_enhanced_txpwr - enhanced regulatory TX power limits
- * @flags: entry flags
- * @channel: channel number
- * @chain_a_max: chain a max power in 1/2 dBm
- * @chain_b_max: chain b max power in 1/2 dBm
- * @chain_c_max: chain c max power in 1/2 dBm
- * @delta_20_in_40: 20-in-40 deltas (hi/lo)
- * @mimo2_max: mimo2 max power in 1/2 dBm
- * @mimo3_max: mimo3 max power in 1/2 dBm
- *
- * This structure presents the enhanced regulatory tx power limit layout
- * in an EEPROM image.
- */
-struct iwl_eeprom_enhanced_txpwr {
-	u8 flags;
-	u8 channel;
-	s8 chain_a_max;
-	s8 chain_b_max;
-	s8 chain_c_max;
-	u8 delta_20_in_40;
-	s8 mimo2_max;
-	s8 mimo3_max;
-} __packed;
-
-static s8 iwl_get_max_txpwr_half_dbm(const struct iwl_nvm_data *data,
-				     struct iwl_eeprom_enhanced_txpwr *txp)
-{
-	s8 result = 0; /* (.5 dBm) */
-
-	/* Take the highest tx power from any valid chains */
-	if (data->valid_tx_ant & ANT_A && txp->chain_a_max > result)
-		result = txp->chain_a_max;
-
-	if (data->valid_tx_ant & ANT_B && txp->chain_b_max > result)
-		result = txp->chain_b_max;
-
-	if (data->valid_tx_ant & ANT_C && txp->chain_c_max > result)
-		result = txp->chain_c_max;
-
-	if ((data->valid_tx_ant == ANT_AB ||
-	     data->valid_tx_ant == ANT_BC ||
-	     data->valid_tx_ant == ANT_AC) && txp->mimo2_max > result)
-		result = txp->mimo2_max;
-
-	if (data->valid_tx_ant == ANT_ABC && txp->mimo3_max > result)
-		result = txp->mimo3_max;
-
-	return result;
-}
-
-#define EEPROM_TXP_OFFS	(0x00 | INDIRECT_ADDRESS | INDIRECT_TXP_LIMIT)
-#define EEPROM_TXP_ENTRY_LEN sizeof(struct iwl_eeprom_enhanced_txpwr)
-#define EEPROM_TXP_SZ_OFFS (0x00 | INDIRECT_ADDRESS | INDIRECT_TXP_LIMIT_SIZE)
-
-#define TXP_CHECK_AND_PRINT(x) \
-	((txp->flags & IWL_EEPROM_ENH_TXP_FL_##x) ? # x " " : "")
-
-static void
-iwl_eeprom_enh_txp_read_element(struct iwl_nvm_data *data,
-				struct iwl_eeprom_enhanced_txpwr *txp,
-				int n_channels, s8 max_txpower_avg)
-{
-	int ch_idx;
-	enum nl80211_band band;
-
-	band = txp->flags & IWL_EEPROM_ENH_TXP_FL_BAND_52G ?
-		NL80211_BAND_5GHZ : NL80211_BAND_2GHZ;
-
-	for (ch_idx = 0; ch_idx < n_channels; ch_idx++) {
-		struct ieee80211_channel *chan = &data->channels[ch_idx];
-
-		/* update matching channel or from common data only */
-		if (txp->channel != 0 && chan->hw_value != txp->channel)
-			continue;
-
-		/* update matching band only */
-		if (band != chan->band)
-			continue;
-
-		if (chan->max_power < max_txpower_avg &&
-		    !(txp->flags & IWL_EEPROM_ENH_TXP_FL_40MHZ))
-			chan->max_power = max_txpower_avg;
-	}
-}
-
-static void iwl_eeprom_enhanced_txpower(struct device *dev,
-					struct iwl_nvm_data *data,
-					const u8 *eeprom, size_t eeprom_size,
-					int n_channels)
-{
-	struct iwl_eeprom_enhanced_txpwr *txp_array, *txp;
-	int idx, entries;
-	__le16 *txp_len;
-	s8 max_txp_avg_halfdbm;
-
-	BUILD_BUG_ON(sizeof(struct iwl_eeprom_enhanced_txpwr) != 8);
-
-	/* the length is in 16-bit words, but we want entries */
-	txp_len = (__le16 *)iwl_eeprom_query_addr(eeprom, eeprom_size,
-						  EEPROM_TXP_SZ_OFFS);
-	entries = le16_to_cpup(txp_len) * 2 / EEPROM_TXP_ENTRY_LEN;
-
-	txp_array = (void *)iwl_eeprom_query_addr(eeprom, eeprom_size,
-						  EEPROM_TXP_OFFS);
-
-	for (idx = 0; idx < entries; idx++) {
-		txp = &txp_array[idx];
-		/* skip invalid entries */
-		if (!(txp->flags & IWL_EEPROM_ENH_TXP_FL_VALID))
-			continue;
-
-		IWL_DEBUG_EEPROM(dev, "%s %d:\t %s%s%s%s%s%s%s%s (0x%02x)\n",
-				 (txp->channel && (txp->flags &
-					IWL_EEPROM_ENH_TXP_FL_COMMON_TYPE)) ?
-					"Common " : (txp->channel) ?
-					"Channel" : "Common",
-				 (txp->channel),
-				 TXP_CHECK_AND_PRINT(VALID),
-				 TXP_CHECK_AND_PRINT(BAND_52G),
-				 TXP_CHECK_AND_PRINT(OFDM),
-				 TXP_CHECK_AND_PRINT(40MHZ),
-				 TXP_CHECK_AND_PRINT(HT_AP),
-				 TXP_CHECK_AND_PRINT(RES1),
-				 TXP_CHECK_AND_PRINT(RES2),
-				 TXP_CHECK_AND_PRINT(COMMON_TYPE),
-				 txp->flags);
-		IWL_DEBUG_EEPROM(dev,
-				 "\t\t chain_A: %d chain_B: %d chain_C: %d\n",
-				 txp->chain_a_max, txp->chain_b_max,
-				 txp->chain_c_max);
-		IWL_DEBUG_EEPROM(dev,
-				 "\t\t MIMO2: %d MIMO3: %d High 20_on_40: 0x%02x Low 20_on_40: 0x%02x\n",
-				 txp->mimo2_max, txp->mimo3_max,
-				 ((txp->delta_20_in_40 & 0xf0) >> 4),
-				 (txp->delta_20_in_40 & 0x0f));
-
-		max_txp_avg_halfdbm = iwl_get_max_txpwr_half_dbm(data, txp);
-
-		iwl_eeprom_enh_txp_read_element(data, txp, n_channels,
-				DIV_ROUND_UP(max_txp_avg_halfdbm, 2));
-
-		if (max_txp_avg_halfdbm > data->max_tx_pwr_half_dbm)
-			data->max_tx_pwr_half_dbm = max_txp_avg_halfdbm;
-	}
-}
-
-static void iwl_init_band_reference(const struct iwl_cfg *cfg,
-				    const u8 *eeprom, size_t eeprom_size,
-				    int eeprom_band, int *eeprom_ch_count,
-				    const struct iwl_eeprom_channel **ch_info,
-				    const u8 **eeprom_ch_array)
-{
-	u32 offset = cfg->eeprom_params->regulatory_bands[eeprom_band - 1];
-
-	offset |= INDIRECT_ADDRESS | INDIRECT_REGULATORY;
-
-	*ch_info = (void *)iwl_eeprom_query_addr(eeprom, eeprom_size, offset);
-
-	switch (eeprom_band) {
-	case 1:		/* 2.4GHz band */
-		*eeprom_ch_count = ARRAY_SIZE(iwl_eeprom_band_1);
-		*eeprom_ch_array = iwl_eeprom_band_1;
-		break;
-	case 2:		/* 4.9GHz band */
-		*eeprom_ch_count = ARRAY_SIZE(iwl_eeprom_band_2);
-		*eeprom_ch_array = iwl_eeprom_band_2;
-		break;
-	case 3:		/* 5.2GHz band */
-		*eeprom_ch_count = ARRAY_SIZE(iwl_eeprom_band_3);
-		*eeprom_ch_array = iwl_eeprom_band_3;
-		break;
-	case 4:		/* 5.5GHz band */
-		*eeprom_ch_count = ARRAY_SIZE(iwl_eeprom_band_4);
-		*eeprom_ch_array = iwl_eeprom_band_4;
-		break;
-	case 5:		/* 5.7GHz band */
-		*eeprom_ch_count = ARRAY_SIZE(iwl_eeprom_band_5);
-		*eeprom_ch_array = iwl_eeprom_band_5;
-		break;
-	case 6:		/* 2.4GHz ht40 channels */
-		*eeprom_ch_count = ARRAY_SIZE(iwl_eeprom_band_6);
-		*eeprom_ch_array = iwl_eeprom_band_6;
-		break;
-	case 7:		/* 5 GHz ht40 channels */
-		*eeprom_ch_count = ARRAY_SIZE(iwl_eeprom_band_7);
-		*eeprom_ch_array = iwl_eeprom_band_7;
-		break;
-	default:
-		*eeprom_ch_count = 0;
-		*eeprom_ch_array = NULL;
-		WARN_ON(1);
-	}
-}
-
-#define CHECK_AND_PRINT(x) \
-	((eeprom_ch->flags & EEPROM_CHANNEL_##x) ? # x " " : "")
-
-static void iwl_mod_ht40_chan_info(struct device *dev,
-				   struct iwl_nvm_data *data, int n_channels,
-				   enum nl80211_band band, u16 channel,
-				   const struct iwl_eeprom_channel *eeprom_ch,
-				   u8 clear_ht40_extension_channel)
-{
-	struct ieee80211_channel *chan = NULL;
-	int i;
-
-	for (i = 0; i < n_channels; i++) {
-		if (data->channels[i].band != band)
-			continue;
-		if (data->channels[i].hw_value != channel)
-			continue;
-		chan = &data->channels[i];
-		break;
-	}
-
-	if (!chan)
-		return;
-
-	IWL_DEBUG_EEPROM(dev,
-			 "HT40 Ch. %d [%sGHz] %s%s%s%s%s(0x%02x %ddBm): Ad-Hoc %ssupported\n",
-			 channel,
-			 band == NL80211_BAND_5GHZ ? "5.2" : "2.4",
-			 CHECK_AND_PRINT(IBSS),
-			 CHECK_AND_PRINT(ACTIVE),
-			 CHECK_AND_PRINT(RADAR),
-			 CHECK_AND_PRINT(WIDE),
-			 CHECK_AND_PRINT(DFS),
-			 eeprom_ch->flags,
-			 eeprom_ch->max_power_avg,
-			 ((eeprom_ch->flags & EEPROM_CHANNEL_IBSS) &&
-			  !(eeprom_ch->flags & EEPROM_CHANNEL_RADAR)) ? ""
-								      : "not ");
-
-	if (eeprom_ch->flags & EEPROM_CHANNEL_VALID)
-		chan->flags &= ~clear_ht40_extension_channel;
-}
-
-#define CHECK_AND_PRINT_I(x)	\
-	((eeprom_ch_info[ch_idx].flags & EEPROM_CHANNEL_##x) ? # x " " : "")
-
-static int iwl_init_channel_map(struct device *dev, const struct iwl_cfg *cfg,
-				struct iwl_nvm_data *data,
-				const u8 *eeprom, size_t eeprom_size)
-{
-	int band, ch_idx;
-	const struct iwl_eeprom_channel *eeprom_ch_info;
-	const u8 *eeprom_ch_array;
-	int eeprom_ch_count;
-	int n_channels = 0;
-
-	/*
-	 * Loop through the 5 EEPROM bands and add them to the parse list
-	 */
-	for (band = 1; band <= 5; band++) {
-		struct ieee80211_channel *channel;
-
-		iwl_init_band_reference(cfg, eeprom, eeprom_size, band,
-					&eeprom_ch_count, &eeprom_ch_info,
-					&eeprom_ch_array);
-
-		/* Loop through each band adding each of the channels */
-		for (ch_idx = 0; ch_idx < eeprom_ch_count; ch_idx++) {
-			const struct iwl_eeprom_channel *eeprom_ch;
-
-			eeprom_ch = &eeprom_ch_info[ch_idx];
-
-			if (!(eeprom_ch->flags & EEPROM_CHANNEL_VALID)) {
-				IWL_DEBUG_EEPROM(dev,
-						 "Ch. %d Flags %x [%sGHz] - No traffic\n",
-						 eeprom_ch_array[ch_idx],
-						 eeprom_ch_info[ch_idx].flags,
-						 (band != 1) ? "5.2" : "2.4");
-				continue;
-			}
-
-			channel = &data->channels[n_channels];
-			n_channels++;
-
-			channel->hw_value = eeprom_ch_array[ch_idx];
-			channel->band = (band == 1) ? NL80211_BAND_2GHZ
-						    : NL80211_BAND_5GHZ;
-			channel->center_freq =
-				ieee80211_channel_to_frequency(
-					channel->hw_value, channel->band);
-
-			/* set no-HT40, will enable as appropriate later */
-			channel->flags = IEEE80211_CHAN_NO_HT40;
-
-			if (!(eeprom_ch->flags & EEPROM_CHANNEL_IBSS))
-				channel->flags |= IEEE80211_CHAN_NO_IR;
-
-			if (!(eeprom_ch->flags & EEPROM_CHANNEL_ACTIVE))
-				channel->flags |= IEEE80211_CHAN_NO_IR;
-
-			if (eeprom_ch->flags & EEPROM_CHANNEL_RADAR)
-				channel->flags |= IEEE80211_CHAN_RADAR;
-
-			/* Initialize regulatory-based run-time data */
-			channel->max_power =
-				eeprom_ch_info[ch_idx].max_power_avg;
-			IWL_DEBUG_EEPROM(dev,
-					 "Ch. %d [%sGHz] %s%s%s%s%s%s(0x%02x %ddBm): Ad-Hoc %ssupported\n",
-					 channel->hw_value,
-					 (band != 1) ? "5.2" : "2.4",
-					 CHECK_AND_PRINT_I(VALID),
-					 CHECK_AND_PRINT_I(IBSS),
-					 CHECK_AND_PRINT_I(ACTIVE),
-					 CHECK_AND_PRINT_I(RADAR),
-					 CHECK_AND_PRINT_I(WIDE),
-					 CHECK_AND_PRINT_I(DFS),
-					 eeprom_ch_info[ch_idx].flags,
-					 eeprom_ch_info[ch_idx].max_power_avg,
-					 ((eeprom_ch_info[ch_idx].flags &
-							EEPROM_CHANNEL_IBSS) &&
-					  !(eeprom_ch_info[ch_idx].flags &
-							EEPROM_CHANNEL_RADAR))
-						? "" : "not ");
-		}
-	}
-
-	if (cfg->eeprom_params->enhanced_txpower) {
-		/*
-		 * for newer device (6000 series and up)
-		 * EEPROM contain enhanced tx power information
-		 * driver need to process addition information
-		 * to determine the max channel tx power limits
-		 */
-		iwl_eeprom_enhanced_txpower(dev, data, eeprom, eeprom_size,
-					    n_channels);
-	} else {
-		/* All others use data from channel map */
-		int i;
-
-		data->max_tx_pwr_half_dbm = -128;
-
-		for (i = 0; i < n_channels; i++)
-			data->max_tx_pwr_half_dbm =
-				max_t(s8, data->max_tx_pwr_half_dbm,
-				      data->channels[i].max_power * 2);
-	}
-
-	/* Check if we do have HT40 channels */
-	if (cfg->eeprom_params->regulatory_bands[5] ==
-				EEPROM_REGULATORY_BAND_NO_HT40 &&
-	    cfg->eeprom_params->regulatory_bands[6] ==
-				EEPROM_REGULATORY_BAND_NO_HT40)
-		return n_channels;
-
-	/* Two additional EEPROM bands for 2.4 and 5 GHz HT40 channels */
-	for (band = 6; band <= 7; band++) {
-		enum nl80211_band ieeeband;
-
-		iwl_init_band_reference(cfg, eeprom, eeprom_size, band,
-					&eeprom_ch_count, &eeprom_ch_info,
-					&eeprom_ch_array);
-
-		/* EEPROM band 6 is 2.4, band 7 is 5 GHz */
-		ieeeband = (band == 6) ? NL80211_BAND_2GHZ
-				       : NL80211_BAND_5GHZ;
-
-		/* Loop through each band adding each of the channels */
-		for (ch_idx = 0; ch_idx < eeprom_ch_count; ch_idx++) {
-			/* Set up driver's info for lower half */
-			iwl_mod_ht40_chan_info(dev, data, n_channels, ieeeband,
-					       eeprom_ch_array[ch_idx],
-					       &eeprom_ch_info[ch_idx],
-					       IEEE80211_CHAN_NO_HT40PLUS);
-
-			/* Set up driver's info for upper half */
-			iwl_mod_ht40_chan_info(dev, data, n_channels, ieeeband,
-					       eeprom_ch_array[ch_idx] + 4,
-					       &eeprom_ch_info[ch_idx],
-					       IEEE80211_CHAN_NO_HT40MINUS);
-		}
-	}
-
-	return n_channels;
-}
-#endif
-
-int iwl_init_sband_channels(struct iwl_nvm_data *data,
-			    struct ieee80211_supported_band *sband,
-			    int n_channels, enum nl80211_band band)
-{
-	struct ieee80211_channel *chan = &data->channels[0];
-	int n = 0, idx = 0;
-
-	while (idx < n_channels && chan->band != band)
-		chan = &data->channels[++idx];
-
-	sband->channels = &data->channels[idx];
-
-	while (idx < n_channels && chan->band == band) {
-		chan = &data->channels[++idx];
-		n++;
-	}
-
-	sband->n_channels = n;
-
-	return n;
-}
-
-#define MAX_BIT_RATE_40_MHZ	150 /* Mbps */
-#define MAX_BIT_RATE_20_MHZ	72 /* Mbps */
-
-void iwl_init_ht_hw_capab(struct iwl_trans *trans,
-			  struct iwl_nvm_data *data,
-			  struct ieee80211_sta_ht_cap *ht_info,
-			  enum nl80211_band band,
-			  u8 tx_chains, u8 rx_chains)
-{
-	const struct iwl_cfg *cfg = trans->cfg;
-	int max_bit_rate = 0;
-
-	tx_chains = hweight8(tx_chains);
-	if (cfg->rx_with_siso_diversity)
-		rx_chains = 1;
-	else
-		rx_chains = hweight8(rx_chains);
-
-	if (!(data->sku_cap_11n_enable) ||
-	    (iwlwifi_mod_params.disable_11n & IWL_DISABLE_HT_ALL) ||
-	    !cfg->ht_params) {
-		ht_info->ht_supported = false;
-		return;
-	}
-
-	if (data->sku_cap_mimo_disabled)
-		rx_chains = 1;
-
-	ht_info->ht_supported = true;
-	ht_info->cap = IEEE80211_HT_CAP_DSSSCCK40;
-
-	if (cfg->ht_params->stbc) {
-		ht_info->cap |= (1 << IEEE80211_HT_CAP_RX_STBC_SHIFT);
-
-		if (tx_chains > 1)
-			ht_info->cap |= IEEE80211_HT_CAP_TX_STBC;
-	}
-
-	if (cfg->ht_params->ldpc)
-		ht_info->cap |= IEEE80211_HT_CAP_LDPC_CODING;
-
-	if (trans->trans_cfg->mq_rx_supported ||
-	    iwlwifi_mod_params.amsdu_size >= IWL_AMSDU_8K)
-		ht_info->cap |= IEEE80211_HT_CAP_MAX_AMSDU;
-
-	ht_info->ampdu_factor = IEEE80211_HT_MAX_AMPDU_64K;
-	ht_info->ampdu_density = IEEE80211_HT_MPDU_DENSITY_4;
-
-	ht_info->mcs.rx_mask[0] = 0xFF;
-	ht_info->mcs.rx_mask[1] = 0x00;
-	ht_info->mcs.rx_mask[2] = 0x00;
-
-	if (rx_chains >= 2)
-		ht_info->mcs.rx_mask[1] = 0xFF;
-	if (rx_chains >= 3)
-		ht_info->mcs.rx_mask[2] = 0xFF;
-
-	if (cfg->ht_params->ht_greenfield_support)
-		ht_info->cap |= IEEE80211_HT_CAP_GRN_FLD;
-	ht_info->cap |= IEEE80211_HT_CAP_SGI_20;
-
-	max_bit_rate = MAX_BIT_RATE_20_MHZ;
-
-	if (cfg->ht_params->ht40_bands & BIT(band)) {
-		ht_info->cap |= IEEE80211_HT_CAP_SUP_WIDTH_20_40;
-		ht_info->cap |= IEEE80211_HT_CAP_SGI_40;
-		max_bit_rate = MAX_BIT_RATE_40_MHZ;
-	}
-
-	/* Highest supported Rx data rate */
-	max_bit_rate *= rx_chains;
-	WARN_ON(max_bit_rate & ~IEEE80211_HT_MCS_RX_HIGHEST_MASK);
-	ht_info->mcs.rx_highest = cpu_to_le16(max_bit_rate);
-
-	/* Tx MCS capabilities */
-	ht_info->mcs.tx_params = IEEE80211_HT_MCS_TX_DEFINED;
-	if (tx_chains != rx_chains) {
-		ht_info->mcs.tx_params |= IEEE80211_HT_MCS_TX_RX_DIFF;
-		ht_info->mcs.tx_params |= ((tx_chains - 1) <<
-				IEEE80211_HT_MCS_TX_MAX_STREAMS_SHIFT);
-	}
-}
-
-#if IS_ENABLED(CONFIG_IWLDVM)
-static void iwl_init_sbands(struct iwl_trans *trans, const struct iwl_cfg *cfg,
-			    struct iwl_nvm_data *data,
-			    const u8 *eeprom, size_t eeprom_size)
-{
-	struct device *dev = trans->dev;
-	int n_channels = iwl_init_channel_map(dev, cfg, data,
-					      eeprom, eeprom_size);
-	int n_used = 0;
-	struct ieee80211_supported_band *sband;
-
-	sband = &data->bands[NL80211_BAND_2GHZ];
-	sband->band = NL80211_BAND_2GHZ;
-	sband->bitrates = &iwl_cfg80211_rates[RATES_24_OFFS];
-	sband->n_bitrates = N_RATES_24;
-	n_used += iwl_init_sband_channels(data, sband, n_channels,
-					  NL80211_BAND_2GHZ);
-	iwl_init_ht_hw_capab(trans, data, &sband->ht_cap, NL80211_BAND_2GHZ,
-			     data->valid_tx_ant, data->valid_rx_ant);
-
-	sband = &data->bands[NL80211_BAND_5GHZ];
-	sband->band = NL80211_BAND_5GHZ;
-	sband->bitrates = &iwl_cfg80211_rates[RATES_52_OFFS];
-	sband->n_bitrates = N_RATES_52;
-	n_used += iwl_init_sband_channels(data, sband, n_channels,
-					  NL80211_BAND_5GHZ);
-	iwl_init_ht_hw_capab(trans, data, &sband->ht_cap, NL80211_BAND_5GHZ,
-			     data->valid_tx_ant, data->valid_rx_ant);
-
-	if (n_channels != n_used)
-		IWL_ERR_DEV(dev, "EEPROM: used only %d of %d channels\n",
-			    n_used, n_channels);
-}
-
-/* EEPROM data functions */
-
-struct iwl_nvm_data *
-iwl_parse_eeprom_data(struct iwl_trans *trans, const struct iwl_cfg *cfg,
-		      const u8 *eeprom, size_t eeprom_size)
-{
-	struct iwl_nvm_data *data;
-	struct device *dev = trans->dev;
-	const void *tmp;
-	u16 radio_cfg, sku;
-
-	if (WARN_ON(!cfg || !cfg->eeprom_params))
-		return NULL;
-
-	data = kzalloc(struct_size(data, channels, IWL_NUM_CHANNELS),
-		       GFP_KERNEL);
-	if (!data)
-		return NULL;
-
-	/* get MAC address(es) */
-	tmp = iwl_eeprom_query_addr(eeprom, eeprom_size, EEPROM_MAC_ADDRESS);
-	if (!tmp)
-		goto err_free;
-	memcpy(data->hw_addr, tmp, ETH_ALEN);
-	data->n_hw_addrs = iwl_eeprom_query16(eeprom, eeprom_size,
-					      EEPROM_NUM_MAC_ADDRESS);
-
-	if (iwl_eeprom_read_calib(eeprom, eeprom_size, data))
-		goto err_free;
-
-	tmp = iwl_eeprom_query_addr(eeprom, eeprom_size, EEPROM_XTAL);
-	if (!tmp)
-		goto err_free;
-	memcpy(data->xtal_calib, tmp, sizeof(data->xtal_calib));
-
-	tmp = iwl_eeprom_query_addr(eeprom, eeprom_size,
-				    EEPROM_RAW_TEMPERATURE);
-	if (!tmp)
-		goto err_free;
-	data->raw_temperature = *(__le16 *)tmp;
-
-	tmp = iwl_eeprom_query_addr(eeprom, eeprom_size,
-				    EEPROM_KELVIN_TEMPERATURE);
-	if (!tmp)
-		goto err_free;
-	data->kelvin_temperature = *(__le16 *)tmp;
-	data->kelvin_voltage = *((__le16 *)tmp + 1);
-
-	radio_cfg = iwl_eeprom_query16(eeprom, eeprom_size,
-					     EEPROM_RADIO_CONFIG);
-	data->radio_cfg_dash = EEPROM_RF_CFG_DASH_MSK(radio_cfg);
-	data->radio_cfg_pnum = EEPROM_RF_CFG_PNUM_MSK(radio_cfg);
-	data->radio_cfg_step = EEPROM_RF_CFG_STEP_MSK(radio_cfg);
-	data->radio_cfg_type = EEPROM_RF_CFG_TYPE_MSK(radio_cfg);
-	data->valid_rx_ant = EEPROM_RF_CFG_RX_ANT_MSK(radio_cfg);
-	data->valid_tx_ant = EEPROM_RF_CFG_TX_ANT_MSK(radio_cfg);
-
-	sku = iwl_eeprom_query16(eeprom, eeprom_size,
-				 EEPROM_SKU_CAP);
-	data->sku_cap_11n_enable = sku & EEPROM_SKU_CAP_11N_ENABLE;
-	data->sku_cap_amt_enable = sku & EEPROM_SKU_CAP_AMT_ENABLE;
-	data->sku_cap_band_24ghz_enable = sku & EEPROM_SKU_CAP_BAND_24GHZ;
-	data->sku_cap_band_52ghz_enable = sku & EEPROM_SKU_CAP_BAND_52GHZ;
-	data->sku_cap_ipan_enable = sku & EEPROM_SKU_CAP_IPAN_ENABLE;
-	if (iwlwifi_mod_params.disable_11n & IWL_DISABLE_HT_ALL)
-		data->sku_cap_11n_enable = false;
-
-	data->nvm_version = iwl_eeprom_query16(eeprom, eeprom_size,
-					       EEPROM_VERSION);
-
-	/* check overrides (some devices have wrong EEPROM) */
-	if (cfg->valid_tx_ant)
-		data->valid_tx_ant = cfg->valid_tx_ant;
-	if (cfg->valid_rx_ant)
-		data->valid_rx_ant = cfg->valid_rx_ant;
-
-	if (!data->valid_tx_ant || !data->valid_rx_ant) {
-		IWL_ERR_DEV(dev, "invalid antennas (0x%x, 0x%x)\n",
-			    data->valid_tx_ant, data->valid_rx_ant);
-		goto err_free;
-	}
-
-	iwl_init_sbands(trans, cfg, data, eeprom, eeprom_size);
-
-	return data;
- err_free:
-	kfree(data);
-	return NULL;
-}
-IWL_EXPORT_SYMBOL(iwl_parse_eeprom_data);
-#endif
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h
index fd9c3bed94079..5a1b5ab62de15 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h
@@ -7,7 +7,7 @@
 #define __iwl_nvm_parse_h__
 
 #include <net/cfg80211.h>
-#include "iwl-eeprom-parse.h"
+#include "iwl-nvm-utils.h"
 #include "mei/iwl-mei.h"
 
 /**
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-utils.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-utils.c
new file mode 100644
index 0000000000000..b3c25acd3691b
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-utils.c
@@ -0,0 +1,118 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * Copyright (C) 2005-2014, 2018-2021, 2023 Intel Corporation
+ * Copyright (C) 2015 Intel Mobile Communications GmbH
+ */
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/export.h>
+#include "iwl-drv.h"
+#include "iwl-modparams.h"
+#include "iwl-nvm-utils.h"
+
+int iwl_init_sband_channels(struct iwl_nvm_data *data,
+			    struct ieee80211_supported_band *sband,
+			    int n_channels, enum nl80211_band band)
+{
+	struct ieee80211_channel *chan = &data->channels[0];
+	int n = 0, idx = 0;
+
+	while (idx < n_channels && chan->band != band)
+		chan = &data->channels[++idx];
+
+	sband->channels = &data->channels[idx];
+
+	while (idx < n_channels && chan->band == band) {
+		chan = &data->channels[++idx];
+		n++;
+	}
+
+	sband->n_channels = n;
+
+	return n;
+}
+IWL_EXPORT_SYMBOL(iwl_init_sband_channels);
+
+#define MAX_BIT_RATE_40_MHZ	150 /* Mbps */
+#define MAX_BIT_RATE_20_MHZ	72 /* Mbps */
+
+void iwl_init_ht_hw_capab(struct iwl_trans *trans,
+			  struct iwl_nvm_data *data,
+			  struct ieee80211_sta_ht_cap *ht_info,
+			  enum nl80211_band band,
+			  u8 tx_chains, u8 rx_chains)
+{
+	const struct iwl_cfg *cfg = trans->cfg;
+	int max_bit_rate = 0;
+
+	tx_chains = hweight8(tx_chains);
+	if (cfg->rx_with_siso_diversity)
+		rx_chains = 1;
+	else
+		rx_chains = hweight8(rx_chains);
+
+	if (!(data->sku_cap_11n_enable) ||
+	    (iwlwifi_mod_params.disable_11n & IWL_DISABLE_HT_ALL) ||
+	    !cfg->ht_params) {
+		ht_info->ht_supported = false;
+		return;
+	}
+
+	if (data->sku_cap_mimo_disabled)
+		rx_chains = 1;
+
+	ht_info->ht_supported = true;
+	ht_info->cap = IEEE80211_HT_CAP_DSSSCCK40;
+
+	if (cfg->ht_params->stbc) {
+		ht_info->cap |= (1 << IEEE80211_HT_CAP_RX_STBC_SHIFT);
+
+		if (tx_chains > 1)
+			ht_info->cap |= IEEE80211_HT_CAP_TX_STBC;
+	}
+
+	if (cfg->ht_params->ldpc)
+		ht_info->cap |= IEEE80211_HT_CAP_LDPC_CODING;
+
+	if (trans->trans_cfg->mq_rx_supported ||
+	    iwlwifi_mod_params.amsdu_size >= IWL_AMSDU_8K)
+		ht_info->cap |= IEEE80211_HT_CAP_MAX_AMSDU;
+
+	ht_info->ampdu_factor = IEEE80211_HT_MAX_AMPDU_64K;
+	ht_info->ampdu_density = IEEE80211_HT_MPDU_DENSITY_4;
+
+	ht_info->mcs.rx_mask[0] = 0xFF;
+	ht_info->mcs.rx_mask[1] = 0x00;
+	ht_info->mcs.rx_mask[2] = 0x00;
+
+	if (rx_chains >= 2)
+		ht_info->mcs.rx_mask[1] = 0xFF;
+	if (rx_chains >= 3)
+		ht_info->mcs.rx_mask[2] = 0xFF;
+
+	if (cfg->ht_params->ht_greenfield_support)
+		ht_info->cap |= IEEE80211_HT_CAP_GRN_FLD;
+	ht_info->cap |= IEEE80211_HT_CAP_SGI_20;
+
+	max_bit_rate = MAX_BIT_RATE_20_MHZ;
+
+	if (cfg->ht_params->ht40_bands & BIT(band)) {
+		ht_info->cap |= IEEE80211_HT_CAP_SUP_WIDTH_20_40;
+		ht_info->cap |= IEEE80211_HT_CAP_SGI_40;
+		max_bit_rate = MAX_BIT_RATE_40_MHZ;
+	}
+
+	/* Highest supported Rx data rate */
+	max_bit_rate *= rx_chains;
+	WARN_ON(max_bit_rate & ~IEEE80211_HT_MCS_RX_HIGHEST_MASK);
+	ht_info->mcs.rx_highest = cpu_to_le16(max_bit_rate);
+
+	/* Tx MCS capabilities */
+	ht_info->mcs.tx_params = IEEE80211_HT_MCS_TX_DEFINED;
+	if (tx_chains != rx_chains) {
+		ht_info->mcs.tx_params |= IEEE80211_HT_MCS_TX_RX_DIFF;
+		ht_info->mcs.tx_params |= ((tx_chains - 1) <<
+				IEEE80211_HT_MCS_TX_MAX_STREAMS_SHIFT);
+	}
+}
+IWL_EXPORT_SYMBOL(iwl_init_ht_hw_capab);
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-eeprom-parse.h b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-utils.h
similarity index 73%
rename from drivers/net/wireless/intel/iwlwifi/iwl-eeprom-parse.h
rename to drivers/net/wireless/intel/iwlwifi/iwl-nvm-utils.h
index 34a178a2eb5d4..ac0a29a1c31f5 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-eeprom-parse.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-utils.h
@@ -58,23 +58,6 @@ struct iwl_nvm_data {
 	struct ieee80211_channel channels[];
 };
 
-/**
- * iwl_parse_eeprom_data - parse EEPROM data and return values
- *
- * @trans: ransport we're parsing for, for debug only
- * @cfg: device configuration for parsing and overrides
- * @eeprom: the EEPROM data
- * @eeprom_size: length of the EEPROM data
- *
- * This function parses all EEPROM values we need and then
- * returns a (newly allocated) struct containing all the
- * relevant values for driver use. The struct must be freed
- * later with iwl_free_nvm_data().
- */
-struct iwl_nvm_data *
-iwl_parse_eeprom_data(struct iwl_trans *trans, const struct iwl_cfg *cfg,
-		      const u8 *eeprom, size_t eeprom_size);
-
 int iwl_init_sband_channels(struct iwl_nvm_data *data,
 			    struct ieee80211_supported_band *sband,
 			    int n_channels, enum nl80211_band band);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index f2f9e2620ff6f..8ec699d9f316a 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -22,7 +22,7 @@
 #include "mvm.h"
 #include "sta.h"
 #include "time-event.h"
-#include "iwl-eeprom-parse.h"
+#include "iwl-nvm-utils.h"
 #include "iwl-phy-db.h"
 #include "testmode.h"
 #include "fw/error-dump.h"
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index dd4599ca1f452..770a7098b0f9b 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -24,7 +24,7 @@
 #include "iwl-op-mode.h"
 #include "iwl-trans.h"
 #include "fw/notif-wait.h"
-#include "iwl-eeprom-parse.h"
+#include "iwl-nvm-utils.h"
 #include "fw/file.h"
 #include "iwl-config.h"
 #include "sta.h"
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c b/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c
index 1e949b48188e3..836ca22597bc1 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c
@@ -9,7 +9,7 @@
 #include "iwl-trans.h"
 #include "iwl-csr.h"
 #include "mvm.h"
-#include "iwl-eeprom-parse.h"
+#include "iwl-nvm-utils.h"
 #include "iwl-nvm-parse.h"
 #include "iwl-prph.h"
 #include "fw/acpi.h"
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
index 160bb619ba9b8..516decc647dda 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
@@ -18,7 +18,7 @@
 #include "iwl-modparams.h"
 #include "mvm.h"
 #include "iwl-phy-db.h"
-#include "iwl-eeprom-parse.h"
+#include "iwl-nvm-utils.h"
 #include "iwl-csr.h"
 #include "iwl-io.h"
 #include "iwl-prph.h"
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
index 1d695ece93e9e..599550f311dea 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
@@ -12,7 +12,7 @@
 #include <net/ipv6.h>
 
 #include "iwl-trans.h"
-#include "iwl-eeprom-parse.h"
+#include "iwl-nvm-utils.h"
 #include "mvm.h"
 #include "sta.h"
 #include "time-sync.h"
-- 
GitLab


From 48443a4a1c97dd8b6614833af928bc15aeff2e47 Mon Sep 17 00:00:00 2001
From: Anjaneyulu <pagadala.yesu.anjaneyulu@intel.com>
Date: Sun, 12 May 2024 15:25:05 +0300
Subject: [PATCH 144/950] wifi: iwlwifi: Add support for LARI_CONFIG_CHANGE_CMD
 v11

Add support for enable/disable 11be for china and South Korea by
reading DSM function 12 from UEFI or ACPI and sending it to the FW.

Signed-off-by: Anjaneyulu <pagadala.yesu.anjaneyulu@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240512152312.037613d03c87.I4e5ee63c0dbdd4bd6c48daee7b0c88462b702423@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/acpi.c  |  1 +
 .../wireless/intel/iwlwifi/fw/api/nvm-reg.h   | 52 +++++++++++++++++--
 .../wireless/intel/iwlwifi/fw/regulatory.c    | 15 +++++-
 .../wireless/intel/iwlwifi/fw/regulatory.h    |  3 +-
 4 files changed, 65 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
index fa339791223b8..79774c8c7ff45 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
@@ -27,6 +27,7 @@ static const size_t acpi_dsm_size[DSM_FUNC_NUM_FUNCS] = {
 	[DSM_FUNC_FORCE_DISABLE_CHANNELS] =	sizeof(u32),
 	[DSM_FUNC_ENERGY_DETECTION_THRESHOLD] =	sizeof(u32),
 	[DSM_FUNC_RFI_CONFIG] =			sizeof(u32),
+	[DSM_FUNC_ENABLE_11BE] =		sizeof(u32),
 };
 
 static int iwl_acpi_get_handle(struct device *dev, acpi_string method,
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/nvm-reg.h b/drivers/net/wireless/intel/iwlwifi/fw/api/nvm-reg.h
index a08497a04733d..644c8df780bc5 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/nvm-reg.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/nvm-reg.h
@@ -23,7 +23,8 @@ enum iwl_regulatory_and_nvm_subcmd_ids {
 	 *	&struct iwl_lari_config_change_cmd_v4,
 	 *	&struct iwl_lari_config_change_cmd_v5,
 	 *	&struct iwl_lari_config_change_cmd_v6,
-	 *	&struct iwl_lari_config_change_cmd_v7 or
+	 *	&struct iwl_lari_config_change_cmd_v7,
+	 *	&struct iwl_lari_config_change_cmd_v10 or
 	 *	&struct iwl_lari_config_change_cmd
 	 */
 	LARI_CONFIG_CHANGE = 0x1,
@@ -648,7 +649,7 @@ struct iwl_lari_config_change_cmd_v7 {
 /* LARI_CHANGE_CONF_CMD_S_VER_9 */
 
 /**
- * struct iwl_lari_config_change_cmd - change LARI configuration
+ * struct iwl_lari_config_change_cmd_v10 - change LARI configuration
  * @config_bitmap: Bitmap of the config commands. Each bit will trigger a
  *	different predefined FW config operation.
  * @oem_uhb_allow_bitmap: Bitmap of UHB enabled MCC sets.
@@ -674,7 +675,7 @@ struct iwl_lari_config_change_cmd_v7 {
  *	bit1: enable 320Mhz in South Korea.
  *	bit 2 - 31: reserved.
  */
-struct iwl_lari_config_change_cmd {
+struct iwl_lari_config_change_cmd_v10 {
 	__le32 config_bitmap;
 	__le32 oem_uhb_allow_bitmap;
 	__le32 oem_11ax_allow_bitmap;
@@ -686,6 +687,51 @@ struct iwl_lari_config_change_cmd {
 } __packed;
 /* LARI_CHANGE_CONF_CMD_S_VER_10 */
 
+/**
+ * struct iwl_lari_config_change_cmd - change LARI configuration
+ * @config_bitmap: Bitmap of the config commands. Each bit will trigger a
+ *	different predefined FW config operation.
+ * @oem_uhb_allow_bitmap: Bitmap of UHB enabled MCC sets.
+ * @oem_11ax_allow_bitmap: Bitmap of 11ax allowed MCCs. There are two bits
+ *	per country, one to indicate whether to override and the other to
+ *	indicate the value to use.
+ * @oem_unii4_allow_bitmap: Bitmap of unii4 allowed MCCs.There are two bits
+ *	per country, one to indicate whether to override and the other to
+ *	indicate allow/disallow unii4 channels.
+ *	For LARI cmd version 11 - bits 0:5 are supported.
+ * @chan_state_active_bitmap: Bitmap to enable different bands per country
+ *	or region.
+ *	Each bit represents a country or region, and a band to activate
+ *	according to the BIOS definitions.
+ *	For LARI cmd version 11 - bits 0:4 are supported.
+ * @force_disable_channels_bitmap: Bitmap of disabled bands/channels.
+ *	Each bit represents a set of channels in a specific band that should be
+ *	disabled
+ * @edt_bitmap: Bitmap of energy detection threshold table.
+ *	Disable/enable the EDT optimization method for different band.
+ * @oem_320mhz_allow_bitmap: 320Mhz bandwidth enablement bitmap per MCC.
+ *	bit0: enable 320Mhz in Japan.
+ *	bit1: enable 320Mhz in South Korea.
+ *	bit 2 - 31: reserved.
+ * @oem_11be_allow_bitmap: Bitmap of 11be allowed MCCs. No need to mask out the
+ *	unsupported bits
+ *	bit0: enable 11be in China(CB/CN).
+ *	bit1: enable 11be in South Korea.
+ *	bit 2 - 31: reserved.
+ */
+struct iwl_lari_config_change_cmd {
+	__le32 config_bitmap;
+	__le32 oem_uhb_allow_bitmap;
+	__le32 oem_11ax_allow_bitmap;
+	__le32 oem_unii4_allow_bitmap;
+	__le32 chan_state_active_bitmap;
+	__le32 force_disable_channels_bitmap;
+	__le32 edt_bitmap;
+	__le32 oem_320mhz_allow_bitmap;
+	__le32 oem_11be_allow_bitmap;
+} __packed;
+/* LARI_CHANGE_CONF_CMD_S_VER_11 */
+
 /* Activate UNII-1 (5.2GHz) for World Wide */
 #define ACTIVATE_5G2_IN_WW_MASK	BIT(4)
 
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/regulatory.c b/drivers/net/wireless/intel/iwlwifi/fw/regulatory.c
index b9bb3636e88f0..5228b837a9ef6 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/regulatory.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/regulatory.c
@@ -497,9 +497,12 @@ static size_t iwl_get_lari_config_cmd_size(u8 cmd_ver)
 	size_t cmd_size;
 
 	switch (cmd_ver) {
-	case 10:
+	case 11:
 		cmd_size = sizeof(struct iwl_lari_config_change_cmd);
 		break;
+	case 10:
+		cmd_size = sizeof(struct iwl_lari_config_change_cmd_v10);
+		break;
 	case 9:
 	case 8:
 	case 7:
@@ -580,6 +583,10 @@ int iwl_fill_lari_config(struct iwl_fw_runtime *fwrt,
 	if (!ret)
 		cmd->oem_320mhz_allow_bitmap = cpu_to_le32(value);
 
+	ret = iwl_bios_get_dsm(fwrt, DSM_FUNC_ENABLE_11BE, &value);
+	if (!ret)
+		cmd->oem_11be_allow_bitmap = cpu_to_le32(value);
+
 	if (cmd->config_bitmap ||
 	    cmd->oem_uhb_allow_bitmap ||
 	    cmd->oem_11ax_allow_bitmap ||
@@ -587,7 +594,8 @@ int iwl_fill_lari_config(struct iwl_fw_runtime *fwrt,
 	    cmd->chan_state_active_bitmap ||
 	    cmd->force_disable_channels_bitmap ||
 	    cmd->edt_bitmap ||
-	    cmd->oem_320mhz_allow_bitmap) {
+	    cmd->oem_320mhz_allow_bitmap ||
+	    cmd->oem_11be_allow_bitmap) {
 		IWL_DEBUG_RADIO(fwrt,
 				"sending LARI_CONFIG_CHANGE, config_bitmap=0x%x, oem_11ax_allow_bitmap=0x%x\n",
 				le32_to_cpu(cmd->config_bitmap),
@@ -605,6 +613,9 @@ int iwl_fill_lari_config(struct iwl_fw_runtime *fwrt,
 				"sending LARI_CONFIG_CHANGE, edt_bitmap=0x%x, oem_320mhz_allow_bitmap=0x%x\n",
 				le32_to_cpu(cmd->edt_bitmap),
 				le32_to_cpu(cmd->oem_320mhz_allow_bitmap));
+		IWL_DEBUG_RADIO(fwrt,
+				"sending LARI_CONFIG_CHANGE, oem_11be_allow_bitmap=0x%x\n",
+				le32_to_cpu(cmd->oem_11be_allow_bitmap));
 	} else {
 		return 1;
 	}
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/regulatory.h b/drivers/net/wireless/intel/iwlwifi/fw/regulatory.h
index 633c9ad9af841..e2c056f483c1c 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/regulatory.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/regulatory.h
@@ -115,7 +115,8 @@ enum iwl_dsm_funcs {
 	DSM_FUNC_FORCE_DISABLE_CHANNELS = 9,
 	DSM_FUNC_ENERGY_DETECTION_THRESHOLD = 10,
 	DSM_FUNC_RFI_CONFIG = 11,
-	DSM_FUNC_NUM_FUNCS = 12,
+	DSM_FUNC_ENABLE_11BE = 12,
+	DSM_FUNC_NUM_FUNCS = 13,
 };
 
 enum iwl_dsm_values_srd {
-- 
GitLab


From ce9e660ef32e87441bf59b04f67a24113e82546a Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 6 May 2024 21:13:12 +0200
Subject: [PATCH 145/950] wifi: mac80211: move radar detect work to sdata

At some point we thought perhaps this could be per link, but
really that didn't happen, and it's confusing. Radar detection
still uses the deflink to allocate the channel, but the work
need not be there. Move it back.

Reviewed-by: Miriam Rachel Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240506211311.43bd82c6da04.Ib39bec3aa198d137385f081e7e1910dcbde3aa1b@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/cfg.c         | 6 +++---
 net/mac80211/ieee80211_i.h | 3 ++-
 net/mac80211/iface.c       | 4 +++-
 net/mac80211/link.c        | 2 --
 net/mac80211/mlme.c        | 9 ++++-----
 net/mac80211/util.c        | 2 +-
 6 files changed, 13 insertions(+), 13 deletions(-)

diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 3673c7f6b21a3..0ed7e8bbf5c08 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -1666,7 +1666,7 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev,
 
 	if (sdata->wdev.cac_started) {
 		chandef = link_conf->chanreq.oper;
-		wiphy_delayed_work_cancel(wiphy, &link->dfs_cac_timer_work);
+		wiphy_delayed_work_cancel(wiphy, &sdata->dfs_cac_timer_work);
 		cfg80211_cac_event(sdata->dev, &chandef,
 				   NL80211_RADAR_CAC_ABORTED,
 				   GFP_KERNEL);
@@ -3466,7 +3466,7 @@ static int ieee80211_start_radar_detection(struct wiphy *wiphy,
 	if (err)
 		goto out_unlock;
 
-	wiphy_delayed_work_queue(wiphy, &sdata->deflink.dfs_cac_timer_work,
+	wiphy_delayed_work_queue(wiphy, &sdata->dfs_cac_timer_work,
 				 msecs_to_jiffies(cac_time_ms));
 
  out_unlock:
@@ -3483,7 +3483,7 @@ static void ieee80211_end_cac(struct wiphy *wiphy,
 
 	list_for_each_entry(sdata, &local->interfaces, list) {
 		wiphy_delayed_work_cancel(wiphy,
-					  &sdata->deflink.dfs_cac_timer_work);
+					  &sdata->dfs_cac_timer_work);
 
 		if (sdata->wdev.cac_started) {
 			ieee80211_link_release_channel(&sdata->deflink);
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 7d541a2355f69..4f4ef6710e8d9 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -1060,7 +1060,6 @@ struct ieee80211_link_data {
 	int ap_power_level; /* in dBm */
 
 	bool radar_required;
-	struct wiphy_delayed_work dfs_cac_timer_work;
 
 	union {
 		struct ieee80211_link_data_managed mgd;
@@ -1159,6 +1158,8 @@ struct ieee80211_sub_if_data {
 	struct ieee80211_link_data deflink;
 	struct ieee80211_link_data __rcu *link[IEEE80211_MLD_MAX_NUM_LINKS];
 
+	struct wiphy_delayed_work dfs_cac_timer_work;
+
 	/* for ieee80211_set_active_links_async() */
 	struct wiphy_work activate_links_work;
 	u16 desired_active_links;
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index dc42902e26935..1ef4b6dc37308 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -554,7 +554,7 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do
 	wiphy_work_cancel(local->hw.wiphy,
 			  &sdata->deflink.color_change_finalize_work);
 	wiphy_delayed_work_cancel(local->hw.wiphy,
-				  &sdata->deflink.dfs_cac_timer_work);
+				  &sdata->dfs_cac_timer_work);
 
 	if (sdata->wdev.cac_started) {
 		chandef = sdata->vif.bss_conf.chanreq.oper;
@@ -1746,6 +1746,8 @@ static void ieee80211_setup_sdata(struct ieee80211_sub_if_data *sdata,
 	wiphy_work_init(&sdata->work, ieee80211_iface_work);
 	wiphy_work_init(&sdata->activate_links_work,
 			ieee80211_activate_links_work);
+	wiphy_delayed_work_init(&sdata->dfs_cac_timer_work,
+				ieee80211_dfs_cac_timer_work);
 
 	switch (type) {
 	case NL80211_IFTYPE_P2P_GO:
diff --git a/net/mac80211/link.c b/net/mac80211/link.c
index af0321408a97a..f57282488222f 100644
--- a/net/mac80211/link.c
+++ b/net/mac80211/link.c
@@ -45,8 +45,6 @@ void ieee80211_link_init(struct ieee80211_sub_if_data *sdata,
 			  ieee80211_color_collision_detection_work);
 	INIT_LIST_HEAD(&link->assigned_chanctx_list);
 	INIT_LIST_HEAD(&link->reserved_chanctx_list);
-	wiphy_delayed_work_init(&link->dfs_cac_timer_work,
-				ieee80211_dfs_cac_timer_work);
 
 	if (!deflink) {
 		switch (sdata->vif.type) {
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 08c0999746fb5..a2b8bfc1fe0e4 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -2797,16 +2797,15 @@ void ieee80211_dynamic_ps_timer(struct timer_list *t)
 
 void ieee80211_dfs_cac_timer_work(struct wiphy *wiphy, struct wiphy_work *work)
 {
-	struct ieee80211_link_data *link =
-		container_of(work, struct ieee80211_link_data,
+	struct ieee80211_sub_if_data *sdata =
+		container_of(work, struct ieee80211_sub_if_data,
 			     dfs_cac_timer_work.work);
-	struct cfg80211_chan_def chandef = link->conf->chanreq.oper;
-	struct ieee80211_sub_if_data *sdata = link->sdata;
+	struct cfg80211_chan_def chandef = sdata->vif.bss_conf.chanreq.oper;
 
 	lockdep_assert_wiphy(sdata->local->hw.wiphy);
 
 	if (sdata->wdev.cac_started) {
-		ieee80211_link_release_channel(link);
+		ieee80211_link_release_channel(&sdata->deflink);
 		cfg80211_cac_event(sdata->dev, &chandef,
 				   NL80211_RADAR_CAC_FINISHED,
 				   GFP_KERNEL);
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 183de2075fb99..43625ca87d5e8 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -3457,7 +3457,7 @@ void ieee80211_dfs_cac_cancel(struct ieee80211_local *local)
 
 	list_for_each_entry(sdata, &local->interfaces, list) {
 		wiphy_delayed_work_cancel(local->hw.wiphy,
-					  &sdata->deflink.dfs_cac_timer_work);
+					  &sdata->dfs_cac_timer_work);
 
 		if (sdata->wdev.cac_started) {
 			chandef = sdata->vif.bss_conf.chanreq.oper;
-- 
GitLab


From 2d33ecf5d0148671c74e68e18755b9411a7ba923 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 6 May 2024 21:11:59 +0200
Subject: [PATCH 146/950] wifi: cfg80211: restrict operation during radar
 detection

Just like it's not currently possible to start radar
detection while already operating, it shouldn't be
possible to start operating while radar detection is
running. Fix that.

Also, improve the check whether operating (carrier
might not be up if e.g. attempting to join IBSS).

Reviewed-by: Miriam Rachel Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240506211158.ae8dca3d0d6c.I7c70a66a5fbdbc63a78fee8a34f31d1995491bc3@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/ibss.c    |  5 ++++-
 net/wireless/mesh.c    |  5 ++++-
 net/wireless/nl80211.c | 21 +++++++++++++++------
 3 files changed, 23 insertions(+), 8 deletions(-)

diff --git a/net/wireless/ibss.c b/net/wireless/ibss.c
index 9f02ee5f08beb..34e5acff39351 100644
--- a/net/wireless/ibss.c
+++ b/net/wireless/ibss.c
@@ -3,7 +3,7 @@
  * Some IBSS support code for cfg80211.
  *
  * Copyright 2009	Johannes Berg <johannes@sipsolutions.net>
- * Copyright (C) 2020-2023 Intel Corporation
+ * Copyright (C) 2020-2024 Intel Corporation
  */
 
 #include <linux/etherdevice.h>
@@ -94,6 +94,9 @@ int __cfg80211_join_ibss(struct cfg80211_registered_device *rdev,
 
 	lockdep_assert_held(&rdev->wiphy.mtx);
 
+	if (wdev->cac_started)
+		return -EBUSY;
+
 	if (wdev->u.ibss.ssid_len)
 		return -EALREADY;
 
diff --git a/net/wireless/mesh.c b/net/wireless/mesh.c
index 83306979fbe21..aaca65b66af48 100644
--- a/net/wireless/mesh.c
+++ b/net/wireless/mesh.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
  * Portions
- * Copyright (C) 2022-2023 Intel Corporation
+ * Copyright (C) 2022-2024 Intel Corporation
  */
 #include <linux/ieee80211.h>
 #include <linux/export.h>
@@ -127,6 +127,9 @@ int __cfg80211_join_mesh(struct cfg80211_registered_device *rdev,
 	if (!rdev->ops->join_mesh)
 		return -EOPNOTSUPP;
 
+	if (wdev->cac_started)
+		return -EBUSY;
+
 	if (!setup->chandef.chan) {
 		/* if no channel explicitly given, use preset channel */
 		setup->chandef = wdev->u.mesh.preset_chandef;
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 93c313149f571..6ba988a6f5a22 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -5964,6 +5964,9 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info)
 	if (!rdev->ops->start_ap)
 		return -EOPNOTSUPP;
 
+	if (wdev->cac_started)
+		return -EBUSY;
+
 	if (wdev->links[link_id].ap.beacon_interval)
 		return -EALREADY;
 
@@ -9956,6 +9959,17 @@ static int nl80211_start_radar_detection(struct sk_buff *skb,
 
 	flush_delayed_work(&rdev->dfs_update_channels_wk);
 
+	switch (wdev->iftype) {
+	case NL80211_IFTYPE_AP:
+	case NL80211_IFTYPE_P2P_GO:
+	case NL80211_IFTYPE_MESH_POINT:
+	case NL80211_IFTYPE_ADHOC:
+		break;
+	default:
+		/* caution - see cfg80211_beaconing_iface_active() below */
+		return -EINVAL;
+	}
+
 	wiphy_lock(wiphy);
 
 	dfs_region = reg_get_dfs_region(wiphy);
@@ -9986,12 +10000,7 @@ static int nl80211_start_radar_detection(struct sk_buff *skb,
 		goto unlock;
 	}
 
-	if (netif_carrier_ok(dev)) {
-		err = -EBUSY;
-		goto unlock;
-	}
-
-	if (wdev->cac_started) {
+	if (cfg80211_beaconing_iface_active(wdev) || wdev->cac_started) {
 		err = -EBUSY;
 		goto unlock;
 	}
-- 
GitLab


From 7ef8f6821d16623a3f6ea279542f9f47ece9ff1e Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 15 Apr 2024 11:27:11 +0300
Subject: [PATCH 147/950] wifi: mac80211: mlme: handle cross-link CSA

If we see a channel switch announcement on one link for
another, handle that case and start the CSA. The driver
can react to this in whatever way it needs. The stack
will have the ability to track it via the RNR/MLE in the
reporting link's beacon if it sees it for inactive links
and adjust everything accordingly.

Note that currently the timings for the CSA aren't set,
the values are only used by the Intel drivers, and they
don't need this for newer devices that support MLO, so
I've left it out for now.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240415112355.4d34b6a31be7.Ie8453979f5805873a8411c99346bcc3810cd6476@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/driver-ops.h  |  12 +
 net/mac80211/ieee80211_i.h |   1 +
 net/mac80211/link.c        |  12 +
 net/mac80211/mlme.c        | 470 +++++++++++++++++++++++++++++--------
 4 files changed, 403 insertions(+), 92 deletions(-)

diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index 5d078c0a23236..d4e73d3630e0b 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -1150,6 +1150,9 @@ drv_pre_channel_switch(struct ieee80211_sub_if_data *sdata,
 	if (!check_sdata_in_driver(sdata))
 		return -EIO;
 
+	if (!ieee80211_vif_link_active(&sdata->vif, ch_switch->link_id))
+		return 0;
+
 	trace_drv_pre_channel_switch(local, sdata, ch_switch);
 	if (local->ops->pre_channel_switch)
 		ret = local->ops->pre_channel_switch(&local->hw, &sdata->vif,
@@ -1171,6 +1174,9 @@ drv_post_channel_switch(struct ieee80211_link_data *link)
 	if (!check_sdata_in_driver(sdata))
 		return -EIO;
 
+	if (!ieee80211_vif_link_active(&sdata->vif, link->link_id))
+		return 0;
+
 	trace_drv_post_channel_switch(local, sdata);
 	if (local->ops->post_channel_switch)
 		ret = local->ops->post_channel_switch(&local->hw, &sdata->vif,
@@ -1191,6 +1197,9 @@ drv_abort_channel_switch(struct ieee80211_link_data *link)
 	if (!check_sdata_in_driver(sdata))
 		return;
 
+	if (!ieee80211_vif_link_active(&sdata->vif, link->link_id))
+		return;
+
 	trace_drv_abort_channel_switch(local, sdata);
 
 	if (local->ops->abort_channel_switch)
@@ -1210,6 +1219,9 @@ drv_channel_switch_rx_beacon(struct ieee80211_sub_if_data *sdata,
 	if (!check_sdata_in_driver(sdata))
 		return;
 
+	if (!ieee80211_vif_link_active(&sdata->vif, ch_switch->link_id))
+		return;
+
 	trace_drv_channel_switch_rx_beacon(local, sdata, ch_switch);
 	if (local->ops->channel_switch_rx_beacon)
 		local->ops->channel_switch_rx_beacon(&local->hw, &sdata->vif,
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 4f4ef6710e8d9..4ce34e95902e1 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -978,6 +978,7 @@ struct ieee80211_link_data_managed {
 	bool csa_waiting_bcn;
 	bool csa_ignored_same_chan;
 	bool csa_blocked_tx;
+	unsigned long csa_time;
 	struct wiphy_delayed_work chswitch_work;
 
 	struct wiphy_work request_smps_work;
diff --git a/net/mac80211/link.c b/net/mac80211/link.c
index f57282488222f..508759cc99794 100644
--- a/net/mac80211/link.c
+++ b/net/mac80211/link.c
@@ -357,6 +357,18 @@ static int _ieee80211_set_active_links(struct ieee80211_sub_if_data *sdata,
 		ieee80211_teardown_tdls_peers(link);
 
 		__ieee80211_link_release_channel(link, true);
+
+		/*
+		 * If CSA is (still) active while the link is deactivated,
+		 * just schedule the channel switch work for the time we
+		 * had previously calculated, and we'll take the process
+		 * from there.
+		 */
+		if (link->conf->csa_active)
+			wiphy_delayed_work_queue(local->hw.wiphy,
+						 &link->u.mgd.chswitch_work,
+						 link->u.mgd.csa_time -
+						 jiffies);
 	}
 
 	list_for_each_entry(sta, &local->sta_list, list) {
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index a2b8bfc1fe0e4..aedd1ce1fb8d0 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -2079,6 +2079,18 @@ static void ieee80211_chswitch_work(struct wiphy *wiphy,
 	if (!link->conf->csa_active)
 		return;
 
+	/*
+	 * If the link isn't active (now), we cannot wait for beacons, won't
+	 * have a reserved chanctx, etc. Just switch over the chandef and
+	 * update cfg80211 directly.
+	 */
+	if (!ieee80211_vif_link_active(&sdata->vif, link->link_id)) {
+		link->conf->chanreq = link->csa_chanreq;
+		cfg80211_ch_switch_notify(sdata->dev, &link->csa_chanreq.oper,
+					  link->link_id);
+		return;
+	}
+
 	/*
 	 * using reservation isn't immediate as it may be deferred until later
 	 * with multi-vif. once reservation is complete it will re-schedule the
@@ -2097,9 +2109,9 @@ static void ieee80211_chswitch_work(struct wiphy *wiphy,
 
 		ret = ieee80211_link_use_reserved_context(link);
 		if (ret) {
-			sdata_info(sdata,
-				   "failed to use reserved channel context, disconnecting (err=%d)\n",
-				   ret);
+			link_info(link,
+				  "failed to use reserved channel context, disconnecting (err=%d)\n",
+				  ret);
 			wiphy_work_queue(sdata->local->hw.wiphy,
 					 &ifmgd->csa_connection_drop_work);
 		}
@@ -2108,8 +2120,8 @@ static void ieee80211_chswitch_work(struct wiphy *wiphy,
 
 	if (!ieee80211_chanreq_identical(&link->conf->chanreq,
 					 &link->csa_chanreq)) {
-		sdata_info(sdata,
-			   "failed to finalize channel switch, disconnecting\n");
+		link_info(link,
+			  "failed to finalize channel switch, disconnecting\n");
 		wiphy_work_queue(sdata->local->hw.wiphy,
 				 &ifmgd->csa_connection_drop_work);
 		return;
@@ -2144,14 +2156,14 @@ static void ieee80211_chswitch_post_beacon(struct ieee80211_link_data *link)
 
 	ret = drv_post_channel_switch(link);
 	if (ret) {
-		sdata_info(sdata,
-			   "driver post channel switch failed, disconnecting\n");
+		link_info(link,
+			  "driver post channel switch failed, disconnecting\n");
 		wiphy_work_queue(sdata->local->hw.wiphy,
 				 &ifmgd->csa_connection_drop_work);
 		return;
 	}
 
-	cfg80211_ch_switch_notify(sdata->dev, &link->reserved.oper,
+	cfg80211_ch_switch_notify(sdata->dev, &link->conf->chanreq.oper,
 				  link->link_id);
 }
 
@@ -2166,7 +2178,8 @@ void ieee80211_chswitch_done(struct ieee80211_vif *vif, bool success,
 
 	if (!success) {
 		sdata_info(sdata,
-			   "driver channel switch failed, disconnecting\n");
+			   "driver channel switch failed (link %d), disconnecting\n",
+			   link_id);
 		wiphy_work_queue(sdata->local->hw.wiphy,
 				 &sdata->u.mgd.csa_connection_drop_work);
 	} else {
@@ -2211,69 +2224,221 @@ ieee80211_sta_abort_chanswitch(struct ieee80211_link_data *link)
 	drv_abort_channel_switch(link);
 }
 
+struct sta_csa_rnr_iter_data {
+	struct ieee80211_link_data *link;
+	struct ieee80211_channel *chan;
+	u8 mld_id;
+};
+
+static enum cfg80211_rnr_iter_ret
+ieee80211_sta_csa_rnr_iter(void *_data, u8 type,
+			   const struct ieee80211_neighbor_ap_info *info,
+			   const u8 *tbtt_info, u8 tbtt_info_len)
+{
+	struct sta_csa_rnr_iter_data *data = _data;
+	struct ieee80211_link_data *link = data->link;
+	struct ieee80211_sub_if_data *sdata = link->sdata;
+	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
+	const struct ieee80211_tbtt_info_ge_11 *ti;
+	enum nl80211_band band;
+	unsigned int center_freq;
+	int link_id;
+
+	if (type != IEEE80211_TBTT_INFO_TYPE_TBTT)
+		return RNR_ITER_CONTINUE;
+
+	if (tbtt_info_len < sizeof(*ti))
+		return RNR_ITER_CONTINUE;
+
+	ti = (const void *)tbtt_info;
+
+	if (ti->mld_params.mld_id != data->mld_id)
+		return RNR_ITER_CONTINUE;
+
+	link_id = le16_get_bits(ti->mld_params.params,
+				IEEE80211_RNR_MLD_PARAMS_LINK_ID);
+	if (link_id != data->link->link_id)
+		return RNR_ITER_CONTINUE;
+
+	/* we found the entry for our link! */
+
+	/* this AP is confused, it had this right before ... just disconnect */
+	if (!ieee80211_operating_class_to_band(info->op_class, &band)) {
+		link_info(link,
+			  "AP now has invalid operating class in RNR, disconnect\n");
+		wiphy_work_queue(sdata->local->hw.wiphy,
+				 &ifmgd->csa_connection_drop_work);
+		return RNR_ITER_BREAK;
+	}
+
+	center_freq = ieee80211_channel_to_frequency(info->channel, band);
+	data->chan = ieee80211_get_channel(sdata->local->hw.wiphy, center_freq);
+
+	return RNR_ITER_BREAK;
+}
+
+static void
+ieee80211_sta_other_link_csa_disappeared(struct ieee80211_link_data *link,
+					 struct ieee802_11_elems *elems)
+{
+	struct ieee80211_sub_if_data *sdata = link->sdata;
+	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
+	struct sta_csa_rnr_iter_data data = {
+		.link = link,
+	};
+
+	/*
+	 * If we get here, we see a beacon from another link without
+	 * CSA still being reported for it, so now we have to check
+	 * if the CSA was aborted or completed. This may not even be
+	 * perfectly possible if the CSA was only done for changing
+	 * the puncturing, but in that case if the link in inactive
+	 * we don't really care, and if it's an active link (or when
+	 * it's activated later) we'll get a beacon and adjust.
+	 */
+
+	if (WARN_ON(!elems->ml_basic))
+		return;
+
+	data.mld_id = ieee80211_mle_get_mld_id((const void *)elems->ml_basic);
+
+	/*
+	 * So in order to do this, iterate the RNR element(s) and see
+	 * what channel is reported now.
+	 */
+	cfg80211_iter_rnr(elems->ie_start, elems->total_len,
+			  ieee80211_sta_csa_rnr_iter, &data);
+
+	if (!data.chan) {
+		link_info(link,
+			  "couldn't find (valid) channel in RNR for CSA, disconnect\n");
+		wiphy_work_queue(sdata->local->hw.wiphy,
+				 &ifmgd->csa_connection_drop_work);
+		return;
+	}
+
+	/*
+	 * If it doesn't match the CSA, then assume it aborted. This
+	 * may erroneously detect that it was _not_ aborted when it
+	 * was in fact aborted, but only changed the bandwidth or the
+	 * puncturing configuration, but we don't have enough data to
+	 * detect that.
+	 */
+	if (data.chan != link->csa_chanreq.oper.chan)
+		ieee80211_sta_abort_chanswitch(link);
+}
+
+enum ieee80211_csa_source {
+	IEEE80211_CSA_SOURCE_BEACON,
+	IEEE80211_CSA_SOURCE_OTHER_LINK,
+	IEEE80211_CSA_SOURCE_ACTION,
+};
+
 static void
 ieee80211_sta_process_chanswitch(struct ieee80211_link_data *link,
 				 u64 timestamp, u32 device_timestamp,
-				 struct ieee802_11_elems *elems,
-				 bool beacon)
+				 struct ieee802_11_elems *full_elems,
+				 struct ieee802_11_elems *csa_elems,
+				 enum ieee80211_csa_source source)
 {
 	struct ieee80211_sub_if_data *sdata = link->sdata;
 	struct ieee80211_local *local = sdata->local;
 	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
-	struct cfg80211_bss *cbss = link->conf->bss;
+	struct ieee80211_chanctx *chanctx = NULL;
 	struct ieee80211_chanctx_conf *conf;
-	struct ieee80211_chanctx *chanctx;
-	enum nl80211_band current_band;
-	struct ieee80211_csa_ie csa_ie;
+	struct ieee80211_csa_ie csa_ie = {};
 	struct ieee80211_channel_switch ch_switch = {
 		.link_id = link->link_id,
+		.timestamp = timestamp,
+		.device_timestamp = device_timestamp,
 	};
-	struct ieee80211_bss *bss;
-	unsigned long timeout;
+	unsigned long now;
 	int res;
 
 	lockdep_assert_wiphy(local->hw.wiphy);
 
-	if (!cbss)
-		return;
+	if (csa_elems) {
+		struct cfg80211_bss *cbss = link->conf->bss;
+		enum nl80211_band current_band;
+		struct ieee80211_bss *bss;
 
-	current_band = cbss->channel->band;
-	bss = (void *)cbss->priv;
-	res = ieee80211_parse_ch_switch_ie(sdata, elems, current_band,
-					   bss->vht_cap_info,
-					   &link->u.mgd.conn,
-					   link->u.mgd.bssid, &csa_ie);
+		if (WARN_ON(!cbss))
+			return;
 
-	if (!res) {
-		ch_switch.timestamp = timestamp;
-		ch_switch.device_timestamp = device_timestamp;
-		ch_switch.block_tx = csa_ie.mode;
-		ch_switch.chandef = csa_ie.chanreq.oper;
-		ch_switch.count = csa_ie.count;
-		ch_switch.delay = csa_ie.max_switch_time;
+		current_band = cbss->channel->band;
+		bss = (void *)cbss->priv;
+
+		res = ieee80211_parse_ch_switch_ie(sdata, csa_elems,
+						   current_band,
+						   bss->vht_cap_info,
+						   &link->u.mgd.conn,
+						   link->u.mgd.bssid, &csa_ie);
+		if (res == 0) {
+			ch_switch.block_tx = csa_ie.mode;
+			ch_switch.chandef = csa_ie.chanreq.oper;
+			ch_switch.count = csa_ie.count;
+			ch_switch.delay = csa_ie.max_switch_time;
+		}
+	} else {
+		/*
+		 * If there was no per-STA profile for this link, we
+		 * get called with csa_elems == NULL. This of course means
+		 * there are no CSA elements, so set res=1 indicating
+		 * no more CSA.
+		 */
+		res = 1;
 	}
 
 	if (res < 0)
 		goto drop_connection;
 
 	if (link->conf->csa_active) {
-		/* already processing - disregard action frames */
-		if (!beacon)
+		switch (source) {
+		case IEEE80211_CSA_SOURCE_ACTION:
+			/* already processing - disregard action frames */
 			return;
+		case IEEE80211_CSA_SOURCE_BEACON:
+			if (link->u.mgd.csa_waiting_bcn) {
+				ieee80211_chswitch_post_beacon(link);
+				/*
+				 * If the CSA is still present after the switch
+				 * we need to consider it as a new CSA (possibly
+				 * to self). This happens by not returning here
+				 * so we'll get to the check below.
+				 */
+			} else if (res) {
+				ieee80211_sta_abort_chanswitch(link);
+				return;
+			} else {
+				drv_channel_switch_rx_beacon(sdata, &ch_switch);
+				return;
+			}
+			break;
+		case IEEE80211_CSA_SOURCE_OTHER_LINK:
+			/* active link: we want to see the beacon to continue */
+			if (ieee80211_vif_link_active(&sdata->vif,
+						      link->link_id))
+				return;
 
-		if (link->u.mgd.csa_waiting_bcn) {
-			ieee80211_chswitch_post_beacon(link);
-			/*
-			 * If the CSA IE is still present in the beacon after
-			 * the switch, we need to consider it as a new CSA
-			 * (possibly to self) - this happens by not returning
-			 * here so we'll get to the check below.
-			 */
-		} else if (res) {
-			ieee80211_sta_abort_chanswitch(link);
-			return;
-		} else {
-			drv_channel_switch_rx_beacon(sdata, &ch_switch);
+			/* switch work ran, so just complete the process */
+			if (link->u.mgd.csa_waiting_bcn) {
+				ieee80211_chswitch_post_beacon(link);
+				/*
+				 * If the CSA is still present after the switch
+				 * we need to consider it as a new CSA (possibly
+				 * to self). This happens by not returning here
+				 * so we'll get to the check below.
+				 */
+				break;
+			}
+
+			/* link still has CSA but we already know, do nothing */
+			if (!res)
+				return;
+
+			/* check in the RNR if the CSA aborted */
+			ieee80211_sta_other_link_csa_disappeared(link,
+								 full_elems);
 			return;
 		}
 	}
@@ -2284,40 +2449,38 @@ ieee80211_sta_process_chanswitch(struct ieee80211_link_data *link,
 
 	if (link->conf->chanreq.oper.chan->band !=
 	    csa_ie.chanreq.oper.chan->band) {
-		sdata_info(sdata,
-			   "AP %pM switches to different band (%d MHz, width:%d, CF1/2: %d/%d MHz), disconnecting\n",
-			   link->u.mgd.bssid,
-			   csa_ie.chanreq.oper.chan->center_freq,
-			   csa_ie.chanreq.oper.width,
-			   csa_ie.chanreq.oper.center_freq1,
-			   csa_ie.chanreq.oper.center_freq2);
+		link_info(link,
+			  "AP %pM switches to different band (%d MHz, width:%d, CF1/2: %d/%d MHz), disconnecting\n",
+			  link->u.mgd.bssid,
+			  csa_ie.chanreq.oper.chan->center_freq,
+			  csa_ie.chanreq.oper.width,
+			  csa_ie.chanreq.oper.center_freq1,
+			  csa_ie.chanreq.oper.center_freq2);
 		goto drop_connection;
 	}
 
 	if (!cfg80211_chandef_usable(local->hw.wiphy, &csa_ie.chanreq.oper,
 				     IEEE80211_CHAN_DISABLED)) {
-		sdata_info(sdata,
-			   "AP %pM switches to unsupported channel "
-			   "(%d.%03d MHz, width:%d, CF1/2: %d.%03d/%d MHz), "
-			   "disconnecting\n",
-			   link->u.mgd.bssid,
-			   csa_ie.chanreq.oper.chan->center_freq,
-			   csa_ie.chanreq.oper.chan->freq_offset,
-			   csa_ie.chanreq.oper.width,
-			   csa_ie.chanreq.oper.center_freq1,
-			   csa_ie.chanreq.oper.freq1_offset,
-			   csa_ie.chanreq.oper.center_freq2);
+		link_info(link,
+			  "AP %pM switches to unsupported channel (%d.%03d MHz, width:%d, CF1/2: %d.%03d/%d MHz), disconnecting\n",
+			  link->u.mgd.bssid,
+			  csa_ie.chanreq.oper.chan->center_freq,
+			  csa_ie.chanreq.oper.chan->freq_offset,
+			  csa_ie.chanreq.oper.width,
+			  csa_ie.chanreq.oper.center_freq1,
+			  csa_ie.chanreq.oper.freq1_offset,
+			  csa_ie.chanreq.oper.center_freq2);
 		goto drop_connection;
 	}
 
 	if (cfg80211_chandef_identical(&csa_ie.chanreq.oper,
 				       &link->conf->chanreq.oper) &&
-	    (!csa_ie.mode || !beacon)) {
+	    (!csa_ie.mode || source != IEEE80211_CSA_SOURCE_BEACON)) {
 		if (link->u.mgd.csa_ignored_same_chan)
 			return;
-		sdata_info(sdata,
-			   "AP %pM tries to chanswitch to same channel, ignore\n",
-			   link->u.mgd.bssid);
+		link_info(link,
+			  "AP %pM tries to chanswitch to same channel, ignore\n",
+			  link->u.mgd.bssid);
 		link->u.mgd.csa_ignored_same_chan = true;
 		return;
 	}
@@ -2333,33 +2496,36 @@ ieee80211_sta_process_chanswitch(struct ieee80211_link_data *link,
 
 	conf = rcu_dereference_protected(link->conf->chanctx_conf,
 					 lockdep_is_held(&local->hw.wiphy->mtx));
-	if (!conf) {
-		sdata_info(sdata,
-			   "no channel context assigned to vif?, disconnecting\n");
+	if (ieee80211_vif_link_active(&sdata->vif, link->link_id) && !conf) {
+		link_info(link,
+			  "no channel context assigned to vif?, disconnecting\n");
 		goto drop_connection;
 	}
 
-	chanctx = container_of(conf, struct ieee80211_chanctx, conf);
+	if (conf)
+		chanctx = container_of(conf, struct ieee80211_chanctx, conf);
 
 	if (!ieee80211_hw_check(&local->hw, CHANCTX_STA_CSA)) {
-		sdata_info(sdata,
-			   "driver doesn't support chan-switch with channel contexts\n");
+		link_info(link,
+			  "driver doesn't support chan-switch with channel contexts\n");
 		goto drop_connection;
 	}
 
 	if (drv_pre_channel_switch(sdata, &ch_switch)) {
-		sdata_info(sdata,
-			   "preparing for channel switch failed, disconnecting\n");
+		link_info(link,
+			  "preparing for channel switch failed, disconnecting\n");
 		goto drop_connection;
 	}
 
-	res = ieee80211_link_reserve_chanctx(link, &csa_ie.chanreq,
-					     chanctx->mode, false);
-	if (res) {
-		sdata_info(sdata,
-			   "failed to reserve channel context for channel switch, disconnecting (err=%d)\n",
-			   res);
-		goto drop_connection;
+	if (chanctx) {
+		res = ieee80211_link_reserve_chanctx(link, &csa_ie.chanreq,
+						     chanctx->mode, false);
+		if (res) {
+			link_info(link,
+				  "failed to reserve channel context for channel switch, disconnecting (err=%d)\n",
+				  res);
+			goto drop_connection;
+		}
 	}
 
 	link->conf->csa_active = true;
@@ -2379,18 +2545,28 @@ ieee80211_sta_process_chanswitch(struct ieee80211_link_data *link,
 					  link->link_id, csa_ie.count,
 					  csa_ie.mode);
 
-	if (local->ops->channel_switch) {
-		/* use driver's channel switch callback */
+	/* we may have to handle timeout for deactivated link in software */
+	now = jiffies;
+	link->u.mgd.csa_time = now +
+			       TU_TO_JIFFIES((max_t(int, csa_ie.count, 1) - 1) *
+					     link->conf->beacon_int);
+
+	if (ieee80211_vif_link_active(&sdata->vif, link->link_id) &&
+	    local->ops->channel_switch) {
+		/*
+		 * Use driver's channel switch callback, the driver will
+		 * later call ieee80211_chswitch_done(). It may deactivate
+		 * the link as well, we handle that elsewhere and queue
+		 * the chswitch_work for the calculated time then.
+		 */
 		drv_channel_switch(local, sdata, &ch_switch);
 		return;
 	}
 
 	/* channel switch handled in software */
-	timeout = TU_TO_JIFFIES((max_t(int, csa_ie.count, 1) - 1) *
-				cbss->beacon_interval);
 	wiphy_delayed_work_queue(local->hw.wiphy,
 				 &link->u.mgd.chswitch_work,
-				 timeout);
+				 link->u.mgd.csa_time - now);
 	return;
  drop_connection:
 	/*
@@ -6328,6 +6504,110 @@ static void ieee80211_process_adv_ttlm(struct ieee80211_sub_if_data *sdata,
 	}
 }
 
+static void
+ieee80211_mgd_check_cross_link_csa(struct ieee80211_sub_if_data *sdata,
+				   int reporting_link_id,
+				   struct ieee802_11_elems *elems)
+{
+	const struct element *sta_profiles[IEEE80211_MLD_MAX_NUM_LINKS] = {};
+	ssize_t sta_profiles_len[IEEE80211_MLD_MAX_NUM_LINKS] = {};
+	const struct element *sub;
+	const u8 *subelems;
+	size_t subelems_len;
+	u8 common_size;
+	int link_id;
+
+	if (!ieee80211_mle_size_ok((u8 *)elems->ml_basic, elems->ml_basic_len))
+		return;
+
+	common_size = ieee80211_mle_common_size((u8 *)elems->ml_basic);
+	subelems = (u8 *)elems->ml_basic + common_size;
+	subelems_len = elems->ml_basic_len - common_size;
+
+	for_each_element_id(sub, IEEE80211_MLE_SUBELEM_PER_STA_PROFILE,
+			    subelems, subelems_len) {
+		struct ieee80211_mle_per_sta_profile *prof = (void *)sub->data;
+		struct ieee80211_link_data *link;
+		ssize_t len;
+
+		if (!ieee80211_mle_basic_sta_prof_size_ok(sub->data,
+							  sub->datalen))
+			continue;
+
+		link_id = le16_get_bits(prof->control,
+					IEEE80211_MLE_STA_CONTROL_LINK_ID);
+		/* need a valid link ID, but also not our own, both AP bugs */
+		if (link_id == reporting_link_id ||
+		    link_id >= IEEE80211_MLD_MAX_NUM_LINKS)
+			continue;
+
+		link = sdata_dereference(sdata->link[link_id], sdata);
+		if (!link)
+			continue;
+
+		len = cfg80211_defragment_element(sub, subelems, subelems_len,
+						  NULL, 0,
+						  IEEE80211_MLE_SUBELEM_FRAGMENT);
+		if (WARN_ON(len < 0))
+			continue;
+
+		sta_profiles[link_id] = sub;
+		sta_profiles_len[link_id] = len;
+	}
+
+	for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; link_id++) {
+		struct ieee80211_mle_per_sta_profile *prof;
+		struct ieee802_11_elems *prof_elems;
+		struct ieee80211_link_data *link;
+		ssize_t len;
+
+		if (link_id == reporting_link_id)
+			continue;
+
+		link = sdata_dereference(sdata->link[link_id], sdata);
+		if (!link)
+			continue;
+
+		if (!sta_profiles[link_id]) {
+			prof_elems = NULL;
+			goto handle;
+		}
+
+		/* we can defragment in-place, won't use the buffer again */
+		len = cfg80211_defragment_element(sta_profiles[link_id],
+						  subelems, subelems_len,
+						  (void *)sta_profiles[link_id],
+						  sta_profiles_len[link_id],
+						  IEEE80211_MLE_SUBELEM_FRAGMENT);
+		if (WARN_ON(len != sta_profiles_len[link_id]))
+			continue;
+
+		prof = (void *)sta_profiles[link_id];
+		prof_elems = ieee802_11_parse_elems(prof->variable +
+						    (prof->sta_info_len - 1),
+						    len -
+						    (prof->sta_info_len - 1),
+						    false, NULL);
+
+		/* memory allocation failed - let's hope that's transient */
+		if (!prof_elems)
+			continue;
+
+handle:
+		/*
+		 * FIXME: the timings here are obviously incorrect,
+		 * but only older Intel drivers seem to care, and
+		 * those don't have MLO. If you really need this,
+		 * the problem is having to calculate it with the
+		 * TSF offset etc. The device_timestamp is still
+		 * correct, of course.
+		 */
+		ieee80211_sta_process_chanswitch(link, 0, 0, elems, prof_elems,
+						 IEEE80211_CSA_SOURCE_OTHER_LINK);
+		kfree(prof_elems);
+	}
+}
+
 static void ieee80211_rx_mgmt_beacon(struct ieee80211_link_data *link,
 				     struct ieee80211_hdr *hdr, size_t len,
 				     struct ieee80211_rx_status *rx_status)
@@ -6552,7 +6832,11 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_link_data *link,
 
 	ieee80211_sta_process_chanswitch(link, rx_status->mactime,
 					 rx_status->device_timestamp,
-					 elems, true);
+					 elems, elems,
+					 IEEE80211_CSA_SOURCE_BEACON);
+
+	/* note that after this elems->ml_basic can no longer be used fully */
+	ieee80211_mgd_check_cross_link_csa(sdata, rx_status->link_id, elems);
 
 	if (!link->u.mgd.disable_wmm_tracking &&
 	    ieee80211_sta_wmm_params(local, link, elems->wmm_param,
@@ -7148,7 +7432,8 @@ void ieee80211_sta_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata,
 				ieee80211_sta_process_chanswitch(link,
 								 rx_status->mactime,
 								 rx_status->device_timestamp,
-								 elems, false);
+								 elems, elems,
+								 IEEE80211_CSA_SOURCE_ACTION);
 			kfree(elems);
 		} else if (mgmt->u.action.category == WLAN_CATEGORY_PUBLIC) {
 			struct ieee802_11_elems *elems;
@@ -7176,7 +7461,8 @@ void ieee80211_sta_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata,
 				ieee80211_sta_process_chanswitch(link,
 								 rx_status->mactime,
 								 rx_status->device_timestamp,
-								 elems, false);
+								 elems, elems,
+								 IEEE80211_CSA_SOURCE_ACTION);
 			}
 
 			kfree(elems);
-- 
GitLab


From 344d18cec23142b3921e068a90f58e8fc5f7637a Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 6 May 2024 21:54:49 +0200
Subject: [PATCH 148/950] wifi: mac80211: collect some CSA data into
 sub-structs

Collect the CSA data in ieee80211_link_data_managed and
ieee80211_link_data into a csa sub-struct to clean up a
bit and make adding new things more obvious.

Reviewed-by: Miriam Rachel Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240506215543.29f954b1f576.I9a683a9647c33d4dd3011aade6677982428c1082@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/cfg.c         | 16 ++++-----
 net/mac80211/chan.c        |  4 +--
 net/mac80211/ibss.c        |  6 ++--
 net/mac80211/ieee80211_i.h | 18 ++++++----
 net/mac80211/iface.c       |  4 +--
 net/mac80211/link.c        |  8 ++---
 net/mac80211/mlme.c        | 70 +++++++++++++++++++-------------------
 7 files changed, 65 insertions(+), 61 deletions(-)

diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 0ed7e8bbf5c08..3319c93605070 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -3633,10 +3633,10 @@ void ieee80211_csa_finish(struct ieee80211_vif *vif, unsigned int link_id)
 				continue;
 
 			wiphy_work_queue(iter->local->hw.wiphy,
-					 &iter->deflink.csa_finalize_work);
+					 &iter->deflink.csa.finalize_work);
 		}
 	}
-	wiphy_work_queue(local->hw.wiphy, &link_data->csa_finalize_work);
+	wiphy_work_queue(local->hw.wiphy, &link_data->csa.finalize_work);
 
 	rcu_read_unlock();
 }
@@ -3723,7 +3723,7 @@ static int __ieee80211_csa_finalize(struct ieee80211_link_data *link_data)
 	}
 
 	if (!cfg80211_chandef_identical(&link_conf->chanreq.oper,
-					&link_data->csa_chanreq.oper))
+					&link_data->csa.chanreq.oper))
 		return -EINVAL;
 
 	link_conf->csa_active = false;
@@ -3744,7 +3744,7 @@ static int __ieee80211_csa_finalize(struct ieee80211_link_data *link_data)
 	if (err)
 		return err;
 
-	cfg80211_ch_switch_notify(sdata->dev, &link_data->csa_chanreq.oper,
+	cfg80211_ch_switch_notify(sdata->dev, &link_data->csa.chanreq.oper,
 				  link_data->link_id);
 
 	return 0;
@@ -3765,7 +3765,7 @@ static void ieee80211_csa_finalize(struct ieee80211_link_data *link_data)
 void ieee80211_csa_finalize_work(struct wiphy *wiphy, struct wiphy_work *work)
 {
 	struct ieee80211_link_data *link =
-		container_of(work, struct ieee80211_link_data, csa_finalize_work);
+		container_of(work, struct ieee80211_link_data, csa.finalize_work);
 	struct ieee80211_sub_if_data *sdata = link->sdata;
 	struct ieee80211_local *local = sdata->local;
 
@@ -4012,7 +4012,7 @@ __ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev,
 		goto out;
 	}
 
-	link_data->csa_chanreq = chanreq; 
+	link_data->csa.chanreq = chanreq;
 	link_conf->csa_active = true;
 
 	if (params->block_tx &&
@@ -4023,12 +4023,12 @@ __ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev,
 	}
 
 	cfg80211_ch_switch_started_notify(sdata->dev,
-					  &link_data->csa_chanreq.oper, 0,
+					  &link_data->csa.chanreq.oper, 0,
 					  params->count, params->block_tx);
 
 	if (changed) {
 		ieee80211_link_info_change_notify(sdata, link_data, changed);
-		drv_channel_switch_beacon(sdata, &link_data->csa_chanreq.oper);
+		drv_channel_switch_beacon(sdata, &link_data->csa.chanreq.oper);
 	} else {
 		/* if the beacon didn't change, we can finalize immediately */
 		ieee80211_csa_finalize(link_data);
diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c
index 380695fdc32fa..ec16d7676088c 100644
--- a/net/mac80211/chan.c
+++ b/net/mac80211/chan.c
@@ -1162,11 +1162,11 @@ ieee80211_link_chanctx_reservation_complete(struct ieee80211_link_data *link)
 	case NL80211_IFTYPE_MESH_POINT:
 	case NL80211_IFTYPE_OCB:
 		wiphy_work_queue(sdata->local->hw.wiphy,
-				 &link->csa_finalize_work);
+				 &link->csa.finalize_work);
 		break;
 	case NL80211_IFTYPE_STATION:
 		wiphy_delayed_work_queue(sdata->local->hw.wiphy,
-					 &link->u.mgd.chswitch_work, 0);
+					 &link->u.mgd.csa.switch_work, 0);
 		break;
 	case NL80211_IFTYPE_UNSPECIFIED:
 	case NL80211_IFTYPE_AP_VLAN:
diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c
index 7ace5cdc6c265..bf338f3d4dd32 100644
--- a/net/mac80211/ibss.c
+++ b/net/mac80211/ibss.c
@@ -9,7 +9,7 @@
  * Copyright 2009, Johannes Berg <johannes@sipsolutions.net>
  * Copyright 2013-2014  Intel Mobile Communications GmbH
  * Copyright(c) 2016 Intel Deutschland GmbH
- * Copyright(c) 2018-2023 Intel Corporation
+ * Copyright(c) 2018-2024 Intel Corporation
  */
 
 #include <linux/delay.h>
@@ -533,12 +533,12 @@ int ieee80211_ibss_finish_csa(struct ieee80211_sub_if_data *sdata, u64 *changed)
 					IEEE80211_PRIVACY(ifibss->privacy));
 		/* XXX: should not really modify cfg80211 data */
 		if (cbss) {
-			cbss->channel = sdata->deflink.csa_chanreq.oper.chan;
+			cbss->channel = sdata->deflink.csa.chanreq.oper.chan;
 			cfg80211_put_bss(sdata->local->hw.wiphy, cbss);
 		}
 	}
 
-	ifibss->chandef = sdata->deflink.csa_chanreq.oper;
+	ifibss->chandef = sdata->deflink.csa.chanreq.oper;
 
 	/* generate the beacon */
 	return ieee80211_ibss_csa_beacon(sdata, NULL, changed);
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 4ce34e95902e1..cba1c2c3d9f1d 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -975,11 +975,13 @@ struct ieee80211_link_data_managed {
 	bool disable_wmm_tracking;
 	bool operating_11g_mode;
 
-	bool csa_waiting_bcn;
-	bool csa_ignored_same_chan;
-	bool csa_blocked_tx;
-	unsigned long csa_time;
-	struct wiphy_delayed_work chswitch_work;
+	struct {
+		struct wiphy_delayed_work switch_work;
+		unsigned long time;
+		bool waiting_bcn;
+		bool ignored_same_chan;
+		bool blocked_tx;
+	} csa;
 
 	struct wiphy_work request_smps_work;
 	/* used to reconfigure hardware SM PS */
@@ -1038,11 +1040,13 @@ struct ieee80211_link_data {
 	struct ieee80211_key __rcu *default_mgmt_key;
 	struct ieee80211_key __rcu *default_beacon_key;
 
-	struct wiphy_work csa_finalize_work;
 
 	bool operating_11g_mode;
 
-	struct ieee80211_chan_req csa_chanreq;
+	struct {
+		struct wiphy_work finalize_work;
+		struct ieee80211_chan_req chanreq;
+	} csa;
 
 	struct wiphy_work color_change_finalize_work;
 	struct delayed_work color_collision_detect_work;
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 1ef4b6dc37308..d1a49ee4a194f 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -543,14 +543,14 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do
 
 	sdata->vif.bss_conf.csa_active = false;
 	if (sdata->vif.type == NL80211_IFTYPE_STATION)
-		sdata->deflink.u.mgd.csa_waiting_bcn = false;
+		sdata->deflink.u.mgd.csa.waiting_bcn = false;
 	if (sdata->csa_blocked_queues) {
 		ieee80211_wake_vif_queues(local, sdata,
 					  IEEE80211_QUEUE_STOP_REASON_CSA);
 		sdata->csa_blocked_queues = false;
 	}
 
-	wiphy_work_cancel(local->hw.wiphy, &sdata->deflink.csa_finalize_work);
+	wiphy_work_cancel(local->hw.wiphy, &sdata->deflink.csa.finalize_work);
 	wiphy_work_cancel(local->hw.wiphy,
 			  &sdata->deflink.color_change_finalize_work);
 	wiphy_delayed_work_cancel(local->hw.wiphy,
diff --git a/net/mac80211/link.c b/net/mac80211/link.c
index 508759cc99794..2e6e92defbca6 100644
--- a/net/mac80211/link.c
+++ b/net/mac80211/link.c
@@ -37,7 +37,7 @@ void ieee80211_link_init(struct ieee80211_sub_if_data *sdata,
 	link_conf->link_id = link_id;
 	link_conf->vif = &sdata->vif;
 
-	wiphy_work_init(&link->csa_finalize_work,
+	wiphy_work_init(&link->csa.finalize_work,
 			ieee80211_csa_finalize_work);
 	wiphy_work_init(&link->color_change_finalize_work,
 			ieee80211_color_change_finalize_work);
@@ -72,7 +72,7 @@ void ieee80211_link_stop(struct ieee80211_link_data *link)
 
 	cancel_delayed_work_sync(&link->color_collision_detect_work);
 	wiphy_work_cancel(link->sdata->local->hw.wiphy,
-			  &link->csa_finalize_work);
+			  &link->csa.finalize_work);
 	ieee80211_link_release_channel(link);
 }
 
@@ -366,8 +366,8 @@ static int _ieee80211_set_active_links(struct ieee80211_sub_if_data *sdata,
 		 */
 		if (link->conf->csa_active)
 			wiphy_delayed_work_queue(local->hw.wiphy,
-						 &link->u.mgd.chswitch_work,
-						 link->u.mgd.csa_time -
+						 &link->u.mgd.csa.switch_work,
+						 link->u.mgd.csa.time -
 						 jiffies);
 	}
 
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index aedd1ce1fb8d0..75d53257dd974 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -2057,12 +2057,12 @@ void ieee80211_send_4addr_nullfunc(struct ieee80211_local *local,
 }
 
 /* spectrum management related things */
-static void ieee80211_chswitch_work(struct wiphy *wiphy,
-				    struct wiphy_work *work)
+static void ieee80211_csa_switch_work(struct wiphy *wiphy,
+				      struct wiphy_work *work)
 {
 	struct ieee80211_link_data *link =
 		container_of(work, struct ieee80211_link_data,
-			     u.mgd.chswitch_work.work);
+			     u.mgd.csa.switch_work.work);
 	struct ieee80211_sub_if_data *sdata = link->sdata;
 	struct ieee80211_local *local = sdata->local;
 	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
@@ -2085,8 +2085,8 @@ static void ieee80211_chswitch_work(struct wiphy *wiphy,
 	 * update cfg80211 directly.
 	 */
 	if (!ieee80211_vif_link_active(&sdata->vif, link->link_id)) {
-		link->conf->chanreq = link->csa_chanreq;
-		cfg80211_ch_switch_notify(sdata->dev, &link->csa_chanreq.oper,
+		link->conf->chanreq = link->csa.chanreq;
+		cfg80211_ch_switch_notify(sdata->dev, &link->csa.chanreq.oper,
 					  link->link_id);
 		return;
 	}
@@ -2119,7 +2119,7 @@ static void ieee80211_chswitch_work(struct wiphy *wiphy,
 	}
 
 	if (!ieee80211_chanreq_identical(&link->conf->chanreq,
-					 &link->csa_chanreq)) {
+					 &link->csa.chanreq)) {
 		link_info(link,
 			  "failed to finalize channel switch, disconnecting\n");
 		wiphy_work_queue(sdata->local->hw.wiphy,
@@ -2127,7 +2127,7 @@ static void ieee80211_chswitch_work(struct wiphy *wiphy,
 		return;
 	}
 
-	link->u.mgd.csa_waiting_bcn = true;
+	link->u.mgd.csa.waiting_bcn = true;
 
 	ieee80211_sta_reset_beacon_monitor(sdata);
 	ieee80211_sta_reset_conn_monitor(sdata);
@@ -2151,8 +2151,8 @@ static void ieee80211_chswitch_post_beacon(struct ieee80211_link_data *link)
 	}
 
 	link->conf->csa_active = false;
-	link->u.mgd.csa_blocked_tx = false;
-	link->u.mgd.csa_waiting_bcn = false;
+	link->u.mgd.csa.blocked_tx = false;
+	link->u.mgd.csa.waiting_bcn = false;
 
 	ret = drv_post_channel_switch(link);
 	if (ret) {
@@ -2192,7 +2192,7 @@ void ieee80211_chswitch_done(struct ieee80211_vif *vif, bool success,
 		}
 
 		wiphy_delayed_work_queue(sdata->local->hw.wiphy,
-					 &link->u.mgd.chswitch_work, 0);
+					 &link->u.mgd.csa.switch_work, 0);
 	}
 
 	rcu_read_unlock();
@@ -2219,7 +2219,7 @@ ieee80211_sta_abort_chanswitch(struct ieee80211_link_data *link)
 	}
 
 	link->conf->csa_active = false;
-	link->u.mgd.csa_blocked_tx = false;
+	link->u.mgd.csa.blocked_tx = false;
 
 	drv_abort_channel_switch(link);
 }
@@ -2324,7 +2324,7 @@ ieee80211_sta_other_link_csa_disappeared(struct ieee80211_link_data *link,
 	 * puncturing configuration, but we don't have enough data to
 	 * detect that.
 	 */
-	if (data.chan != link->csa_chanreq.oper.chan)
+	if (data.chan != link->csa.chanreq.oper.chan)
 		ieee80211_sta_abort_chanswitch(link);
 }
 
@@ -2398,7 +2398,7 @@ ieee80211_sta_process_chanswitch(struct ieee80211_link_data *link,
 			/* already processing - disregard action frames */
 			return;
 		case IEEE80211_CSA_SOURCE_BEACON:
-			if (link->u.mgd.csa_waiting_bcn) {
+			if (link->u.mgd.csa.waiting_bcn) {
 				ieee80211_chswitch_post_beacon(link);
 				/*
 				 * If the CSA is still present after the switch
@@ -2421,7 +2421,7 @@ ieee80211_sta_process_chanswitch(struct ieee80211_link_data *link,
 				return;
 
 			/* switch work ran, so just complete the process */
-			if (link->u.mgd.csa_waiting_bcn) {
+			if (link->u.mgd.csa.waiting_bcn) {
 				ieee80211_chswitch_post_beacon(link);
 				/*
 				 * If the CSA is still present after the switch
@@ -2476,12 +2476,12 @@ ieee80211_sta_process_chanswitch(struct ieee80211_link_data *link,
 	if (cfg80211_chandef_identical(&csa_ie.chanreq.oper,
 				       &link->conf->chanreq.oper) &&
 	    (!csa_ie.mode || source != IEEE80211_CSA_SOURCE_BEACON)) {
-		if (link->u.mgd.csa_ignored_same_chan)
+		if (link->u.mgd.csa.ignored_same_chan)
 			return;
 		link_info(link,
 			  "AP %pM tries to chanswitch to same channel, ignore\n",
 			  link->u.mgd.bssid);
-		link->u.mgd.csa_ignored_same_chan = true;
+		link->u.mgd.csa.ignored_same_chan = true;
 		return;
 	}
 
@@ -2529,10 +2529,10 @@ ieee80211_sta_process_chanswitch(struct ieee80211_link_data *link,
 	}
 
 	link->conf->csa_active = true;
-	link->csa_chanreq = csa_ie.chanreq;
-	link->u.mgd.csa_ignored_same_chan = false;
+	link->csa.chanreq = csa_ie.chanreq;
+	link->u.mgd.csa.ignored_same_chan = false;
 	link->u.mgd.beacon_crc_valid = false;
-	link->u.mgd.csa_blocked_tx = csa_ie.mode;
+	link->u.mgd.csa.blocked_tx = csa_ie.mode;
 
 	if (csa_ie.mode &&
 	    !ieee80211_hw_check(&local->hw, HANDLES_QUIET_CSA)) {
@@ -2547,7 +2547,7 @@ ieee80211_sta_process_chanswitch(struct ieee80211_link_data *link,
 
 	/* we may have to handle timeout for deactivated link in software */
 	now = jiffies;
-	link->u.mgd.csa_time = now +
+	link->u.mgd.csa.time = now +
 			       TU_TO_JIFFIES((max_t(int, csa_ie.count, 1) - 1) *
 					     link->conf->beacon_int);
 
@@ -2557,7 +2557,7 @@ ieee80211_sta_process_chanswitch(struct ieee80211_link_data *link,
 		 * Use driver's channel switch callback, the driver will
 		 * later call ieee80211_chswitch_done(). It may deactivate
 		 * the link as well, we handle that elsewhere and queue
-		 * the chswitch_work for the calculated time then.
+		 * the csa.switch_work for the calculated time then.
 		 */
 		drv_channel_switch(local, sdata, &ch_switch);
 		return;
@@ -2565,8 +2565,8 @@ ieee80211_sta_process_chanswitch(struct ieee80211_link_data *link,
 
 	/* channel switch handled in software */
 	wiphy_delayed_work_queue(local->hw.wiphy,
-				 &link->u.mgd.chswitch_work,
-				 link->u.mgd.csa_time - now);
+				 &link->u.mgd.csa.switch_work,
+				 link->u.mgd.csa.time - now);
 	return;
  drop_connection:
 	/*
@@ -2577,7 +2577,7 @@ ieee80211_sta_process_chanswitch(struct ieee80211_link_data *link,
 	 * reset when the disconnection worker runs.
 	 */
 	link->conf->csa_active = true;
-	link->u.mgd.csa_blocked_tx = csa_ie.mode;
+	link->u.mgd.csa.blocked_tx = csa_ie.mode;
 	sdata->csa_blocked_queues =
 		csa_ie.mode && !ieee80211_hw_check(&local->hw, HANDLES_QUIET_CSA);
 
@@ -3630,9 +3630,9 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata,
 	}
 
 	sdata->vif.bss_conf.csa_active = false;
-	sdata->deflink.u.mgd.csa_blocked_tx = false;
-	sdata->deflink.u.mgd.csa_waiting_bcn = false;
-	sdata->deflink.u.mgd.csa_ignored_same_chan = false;
+	sdata->deflink.u.mgd.csa.blocked_tx = false;
+	sdata->deflink.u.mgd.csa.waiting_bcn = false;
+	sdata->deflink.u.mgd.csa.ignored_same_chan = false;
 	if (sdata->csa_blocked_queues) {
 		ieee80211_wake_vif_queues(local, sdata,
 					  IEEE80211_QUEUE_STOP_REASON_CSA);
@@ -3960,7 +3960,7 @@ static void __ieee80211_disconnect(struct ieee80211_sub_if_data *sdata)
 		if (WARN_ON_ONCE(!link))
 			continue;
 
-		if (link->u.mgd.csa_blocked_tx)
+		if (link->u.mgd.csa.blocked_tx)
 			continue;
 
 		tx = true;
@@ -3997,8 +3997,8 @@ static void __ieee80211_disconnect(struct ieee80211_sub_if_data *sdata)
 			       tx, frame_buf);
 	/* the other links will be destroyed */
 	sdata->vif.bss_conf.csa_active = false;
-	sdata->deflink.u.mgd.csa_waiting_bcn = false;
-	sdata->deflink.u.mgd.csa_blocked_tx = false;
+	sdata->deflink.u.mgd.csa.waiting_bcn = false;
+	sdata->deflink.u.mgd.csa.blocked_tx = false;
 	if (sdata->csa_blocked_queues) {
 		ieee80211_wake_vif_queues(local, sdata,
 					  IEEE80211_QUEUE_STOP_REASON_CSA);
@@ -7785,7 +7785,7 @@ static void ieee80211_sta_bcn_mon_timer(struct timer_list *t)
 		return;
 
 	if (sdata->vif.bss_conf.csa_active &&
-	    !sdata->deflink.u.mgd.csa_waiting_bcn)
+	    !sdata->deflink.u.mgd.csa.waiting_bcn)
 		return;
 
 	if (sdata->vif.driver_flags & IEEE80211_VIF_BEACON_FILTER)
@@ -7809,7 +7809,7 @@ static void ieee80211_sta_conn_mon_timer(struct timer_list *t)
 		return;
 
 	if (sdata->vif.bss_conf.csa_active &&
-	    !sdata->deflink.u.mgd.csa_waiting_bcn)
+	    !sdata->deflink.u.mgd.csa.waiting_bcn)
 		return;
 
 	sta = sta_info_get(sdata, sdata->vif.cfg.ap_addr);
@@ -8020,8 +8020,8 @@ void ieee80211_mgd_setup_link(struct ieee80211_link_data *link)
 	else
 		link->u.mgd.req_smps = IEEE80211_SMPS_OFF;
 
-	wiphy_delayed_work_init(&link->u.mgd.chswitch_work,
-				ieee80211_chswitch_work);
+	wiphy_delayed_work_init(&link->u.mgd.csa.switch_work,
+				ieee80211_csa_switch_work);
 
 	ieee80211_clear_tpe(&link->conf->tpe);
 
@@ -9152,7 +9152,7 @@ void ieee80211_mgd_stop_link(struct ieee80211_link_data *link)
 	wiphy_work_cancel(link->sdata->local->hw.wiphy,
 			  &link->u.mgd.recalc_smps);
 	wiphy_delayed_work_cancel(link->sdata->local->hw.wiphy,
-				  &link->u.mgd.chswitch_work);
+				  &link->u.mgd.csa.switch_work);
 }
 
 void ieee80211_mgd_stop(struct ieee80211_sub_if_data *sdata)
-- 
GitLab


From f81747a9ad2e773ee72d881717e859a9f7a01c76 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 6 May 2024 21:54:50 +0200
Subject: [PATCH 149/950] wifi: mac80211: handle wider bandwidth OFDMA during
 CSA

During channel switch, track the AP configuration in the
chanreq, so that wider bandwidth OFDMA is taken into
account correctly, since multiple channel contexts may
be needed due to sharing not being possible due to
wider bandwidth OFDMA.

Reviewed-by: Miriam Rachel Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240506215543.b2c5a72dac1b.I69f65cb2e75d4a49a174b1aede68bf8ff0a3cab3@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mlme.c      | 8 ++++++--
 net/mac80211/spectmgmt.c | 5 ++++-
 2 files changed, 10 insertions(+), 3 deletions(-)

diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 75d53257dd974..1d0b414619a4b 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -2517,8 +2517,13 @@ ieee80211_sta_process_chanswitch(struct ieee80211_link_data *link,
 		goto drop_connection;
 	}
 
+	link->csa.chanreq = csa_ie.chanreq;
+	if (link->u.mgd.conn.mode < IEEE80211_CONN_MODE_EHT ||
+	    sdata->vif.driver_flags & IEEE80211_VIF_IGNORE_OFDMA_WIDER_BW)
+		link->csa.chanreq.ap.chan = NULL;
+
 	if (chanctx) {
-		res = ieee80211_link_reserve_chanctx(link, &csa_ie.chanreq,
+		res = ieee80211_link_reserve_chanctx(link, &link->csa.chanreq,
 						     chanctx->mode, false);
 		if (res) {
 			link_info(link,
@@ -2529,7 +2534,6 @@ ieee80211_sta_process_chanswitch(struct ieee80211_link_data *link,
 	}
 
 	link->conf->csa_active = true;
-	link->csa.chanreq = csa_ie.chanreq;
 	link->u.mgd.csa.ignored_same_chan = false;
 	link->u.mgd.beacon_crc_valid = false;
 	link->u.mgd.csa.blocked_tx = csa_ie.mode;
diff --git a/net/mac80211/spectmgmt.c b/net/mac80211/spectmgmt.c
index b2de4c6fb8088..df96d3db1c0e6 100644
--- a/net/mac80211/spectmgmt.c
+++ b/net/mac80211/spectmgmt.c
@@ -9,7 +9,7 @@
  * Copyright 2007, Michael Wu <flamingice@sourmilk.net>
  * Copyright 2007-2008, Intel Corporation
  * Copyright 2008, Johannes Berg <johannes@sipsolutions.net>
- * Copyright (C) 2018, 2020, 2022-2023 Intel Corporation
+ * Copyright (C) 2018, 2020, 2022-2024 Intel Corporation
  */
 
 #include <linux/ieee80211.h>
@@ -366,6 +366,9 @@ int ieee80211_parse_ch_switch_ie(struct ieee80211_sub_if_data *sdata,
 		validate_chandef_by_ht_vht_oper(sdata, conn, vht_cap_info,
 						&new_chandef);
 
+	/* capture the AP chandef before (potential) downgrading */
+	csa_ie->chanreq.ap = new_chandef;
+
 	/* if data is there validate the bandwidth & use it */
 	if (new_chandef.chan) {
 		if (conn->bw_limit < IEEE80211_CONN_BW_LIMIT_320 &&
-- 
GitLab


From 4540568136fefe0fcc366ded125cc56b0d9e1724 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 6 May 2024 21:54:51 +0200
Subject: [PATCH 150/950] wifi: mac80211: handle TPE element during CSA

Handle the transmit power envelope (TPE) element during
channel switch, applying it when the channel switch is
done.

Reviewed-by: Miriam Rachel Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240506215543.486c33157d18.Idf971ad801b6961c177bdf42cc323fd1a4ca8165@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/ieee80211_i.h |  3 +++
 net/mac80211/mlme.c        | 18 ++++++++++++++++++
 net/mac80211/parse.c       |  8 ++++++++
 3 files changed, 29 insertions(+)

diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index cba1c2c3d9f1d..76965d64a0fae 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -977,6 +977,8 @@ struct ieee80211_link_data_managed {
 
 	struct {
 		struct wiphy_delayed_work switch_work;
+		struct cfg80211_chan_def ap_chandef;
+		struct ieee80211_parsed_tpe tpe;
 		unsigned long time;
 		bool waiting_bcn;
 		bool ignored_same_chan;
@@ -1754,6 +1756,7 @@ struct ieee802_11_elems {
 
 	/* not the order in the psd values is per element, not per chandef */
 	struct ieee80211_parsed_tpe tpe;
+	struct ieee80211_parsed_tpe csa_tpe;
 
 	/* length of them, respectively */
 	u8 ext_capab_len;
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 1d0b414619a4b..18793f2fb91ce 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -2129,6 +2129,20 @@ static void ieee80211_csa_switch_work(struct wiphy *wiphy,
 
 	link->u.mgd.csa.waiting_bcn = true;
 
+	/* apply new TPE restrictions immediately on the new channel */
+	if (link->u.mgd.csa.ap_chandef.chan->band == NL80211_BAND_6GHZ &&
+	    link->u.mgd.conn.mode >= IEEE80211_CONN_MODE_HE) {
+		ieee80211_rearrange_tpe(&link->u.mgd.csa.tpe,
+					&link->u.mgd.csa.ap_chandef,
+					&link->conf->chanreq.oper);
+		if (memcmp(&link->conf->tpe, &link->u.mgd.csa.tpe,
+			   sizeof(link->u.mgd.csa.tpe))) {
+			link->conf->tpe = link->u.mgd.csa.tpe;
+			ieee80211_link_info_change_notify(sdata, link,
+							  BSS_CHANGED_TPE);
+		}
+	}
+
 	ieee80211_sta_reset_beacon_monitor(sdata);
 	ieee80211_sta_reset_conn_monitor(sdata);
 }
@@ -2379,6 +2393,8 @@ ieee80211_sta_process_chanswitch(struct ieee80211_link_data *link,
 			ch_switch.count = csa_ie.count;
 			ch_switch.delay = csa_ie.max_switch_time;
 		}
+
+		link->u.mgd.csa.tpe = csa_elems->csa_tpe;
 	} else {
 		/*
 		 * If there was no per-STA profile for this link, we
@@ -2517,6 +2533,8 @@ ieee80211_sta_process_chanswitch(struct ieee80211_link_data *link,
 		goto drop_connection;
 	}
 
+	link->u.mgd.csa.ap_chandef = csa_ie.chanreq.ap;
+
 	link->csa.chanreq = csa_ie.chanreq;
 	if (link->u.mgd.conn.mode < IEEE80211_CONN_MODE_EHT ||
 	    sdata->vif.driver_flags & IEEE80211_VIF_IGNORE_OFDMA_WIDER_BW)
diff --git a/net/mac80211/parse.c b/net/mac80211/parse.c
index 6efeb977f8e55..5c5c21ecb2b77 100644
--- a/net/mac80211/parse.c
+++ b/net/mac80211/parse.c
@@ -607,6 +607,13 @@ _ieee802_11_parse_elems_full(struct ieee80211_elems_parse_params *params,
 					elem_parse_failed =
 						IEEE80211_PARSE_ERR_BAD_ELEM_SIZE;
 			}
+
+			subelem = cfg80211_find_ext_elem(WLAN_EID_TX_POWER_ENVELOPE,
+							 pos, elen);
+			if (subelem)
+				ieee80211_parse_tpe(&elems->csa_tpe,
+						    subelem->data + 1,
+						    subelem->datalen - 1);
 			break;
 		case WLAN_EID_COUNTRY:
 			elems->country_elem = pos;
@@ -962,6 +969,7 @@ ieee802_11_parse_elems_full(struct ieee80211_elems_parse_params *params)
 
 	/* set all TPE entries to unlimited (but invalid) */
 	ieee80211_clear_tpe(&elems->tpe);
+	ieee80211_clear_tpe(&elems->csa_tpe);
 
 	nontransmitted_profile = elems_parse->scratch_pos;
 	nontransmitted_profile_len =
-- 
GitLab


From 9f472520f6f7b8ed3cf82d800b75c91c4c3d4ef1 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 6 May 2024 21:54:52 +0200
Subject: [PATCH 151/950] wifi: mac80211: refactor chanreq.ap setting

There are now three places setting up chanreq.ap which always
depends on the mode (EHT being used or not) and override flag.
Refactor that code into a common function with a comment, to
make that clearer.

Reviewed-by: Miriam Rachel Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240506215543.5cd6a209e58a.I3be318959d9e2df5dccd2d0938c3d2fcc6688030@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mlme.c | 43 +++++++++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 14 deletions(-)

diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 18793f2fb91ce..a974a75df2664 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -789,6 +789,29 @@ static void ieee80211_rearrange_tpe(struct ieee80211_parsed_tpe *tpe,
 	}
 }
 
+/*
+ * The AP part of the channel request is used to distinguish settings
+ * to the device used for wider bandwidth OFDMA. This is used in the
+ * channel context code to assign two channel contexts even if they're
+ * both for the same channel, if the AP bandwidths are incompatible.
+ * If not EHT (or driver override) then ap.chan == NULL indicates that
+ * there's no wider BW OFDMA used.
+ */
+static void ieee80211_set_chanreq_ap(struct ieee80211_sub_if_data *sdata,
+				     struct ieee80211_chan_req *chanreq,
+				     struct ieee80211_conn_settings *conn,
+				     struct cfg80211_chan_def *ap_chandef)
+{
+	chanreq->ap.chan = NULL;
+
+	if (conn->mode < IEEE80211_CONN_MODE_EHT)
+		return;
+	if (sdata->vif.driver_flags & IEEE80211_VIF_IGNORE_OFDMA_WIDER_BW)
+		return;
+
+	chanreq->ap = *ap_chandef;
+}
+
 static struct ieee802_11_elems *
 ieee80211_determine_chan_mode(struct ieee80211_sub_if_data *sdata,
 			      struct ieee80211_conn_settings *conn,
@@ -886,12 +909,7 @@ again:
 
 	chanreq->oper = *ap_chandef;
 
-	/* wider-bandwidth OFDMA is only done in EHT */
-	if (conn->mode >= IEEE80211_CONN_MODE_EHT &&
-	    !(sdata->vif.driver_flags & IEEE80211_VIF_IGNORE_OFDMA_WIDER_BW))
-		chanreq->ap = *ap_chandef;
-	else
-		chanreq->ap.chan = NULL;
+	ieee80211_set_chanreq_ap(sdata, chanreq, conn, ap_chandef);
 
 	while (!ieee80211_chandef_usable(sdata, &chanreq->oper,
 					 IEEE80211_CHAN_DISABLED)) {
@@ -999,11 +1017,9 @@ static int ieee80211_config_bw(struct ieee80211_link_data *link,
 		return -EINVAL;
 	}
 
-	chanreq.ap = ap_chandef;
 	chanreq.oper = ap_chandef;
-	if (link->u.mgd.conn.mode < IEEE80211_CONN_MODE_EHT ||
-	    sdata->vif.driver_flags & IEEE80211_VIF_IGNORE_OFDMA_WIDER_BW)
-		chanreq.ap.chan = NULL;
+	ieee80211_set_chanreq_ap(sdata, &chanreq, &link->u.mgd.conn,
+				 &ap_chandef);
 
 	/*
 	 * if HT operation mode changed store the new one -
@@ -2535,10 +2551,9 @@ ieee80211_sta_process_chanswitch(struct ieee80211_link_data *link,
 
 	link->u.mgd.csa.ap_chandef = csa_ie.chanreq.ap;
 
-	link->csa.chanreq = csa_ie.chanreq;
-	if (link->u.mgd.conn.mode < IEEE80211_CONN_MODE_EHT ||
-	    sdata->vif.driver_flags & IEEE80211_VIF_IGNORE_OFDMA_WIDER_BW)
-		link->csa.chanreq.ap.chan = NULL;
+	link->csa.chanreq.oper = csa_ie.chanreq.oper;
+	ieee80211_set_chanreq_ap(sdata, &link->csa.chanreq, &link->u.mgd.conn,
+				 &csa_ie.chanreq.ap);
 
 	if (chanctx) {
 		res = ieee80211_link_reserve_chanctx(link, &link->csa.chanreq,
-- 
GitLab


From f9a0757a4b2f5df4376963c25a3d7d7aeba78444 Mon Sep 17 00:00:00 2001
From: Pradeep Kumar Chitrapu <quic_pradeepc@quicinc.com>
Date: Wed, 15 May 2024 11:13:18 -0700
Subject: [PATCH 152/950] wifi: mac80211: Add EHT UL MU-MIMO flag in
 ieee80211_bss_conf

Add flag for Full Bandwidth UL MU-MIMO for EHT. This is utilized
to pass EHT MU-MIMO configurations from user space to driver
in AP mode.

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

Signed-off-by: Pradeep Kumar Chitrapu <quic_pradeepc@quicinc.com>
Link: https://msgid.link/20240515181327.12855-2-quic_pradeepc@quicinc.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h | 4 ++++
 net/mac80211/cfg.c     | 5 +++++
 2 files changed, 9 insertions(+)

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index a59eacfe04804..ecfa65ade2262 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -735,6 +735,9 @@ struct ieee80211_parsed_tpe {
  *	beamformee
  * @eht_mu_beamformer: in AP-mode, does this BSS enable operation as an EHT MU
  *	beamformer
+ * @eht_80mhz_full_bw_ul_mumimo: in AP-mode, does this BSS support the
+ *	reception of an EHT TB PPDU on an RU that spans the entire PPDU
+ *	bandwidth
  */
 struct ieee80211_bss_conf {
 	struct ieee80211_vif *vif;
@@ -828,6 +831,7 @@ struct ieee80211_bss_conf {
 	bool eht_su_beamformer;
 	bool eht_su_beamformee;
 	bool eht_mu_beamformer;
+	bool eht_80mhz_full_bw_ul_mumimo;
 };
 
 /**
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 3319c93605070..62119e957cd84 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -1379,6 +1379,11 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev,
 				(IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_80MHZ |
 				 IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_160MHZ |
 				 IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_320MHZ);
+		link_conf->eht_80mhz_full_bw_ul_mumimo =
+			params->eht_cap->fixed.phy_cap_info[7] &
+				(IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_80MHZ |
+				 IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_160MHZ |
+				 IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_320MHZ);
 	} else {
 		link_conf->eht_su_beamformer = false;
 		link_conf->eht_su_beamformee = false;
-- 
GitLab


From aa4ec06c455d0200eea0a4361cc58eb5b8bf68c4 Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Fri, 17 May 2024 18:33:31 +0300
Subject: [PATCH 153/950] wifi: cfg80211: use __counted_by where appropriate

Annotate 'sub_specs' of 'struct cfg80211_sar_specs', 'channels'
of 'struct cfg80211_sched_scan_request', 'channels' of 'struct
cfg80211_wowlan_nd_match', and 'matches' of 'struct
cfg80211_wowlan_nd_info' with '__counted_by' attribute. Briefly
tested with clang 18.1.1 and CONFIG_UBSAN_BOUNDS running iwlwifi.

Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Link: https://msgid.link/20240517153332.18271-1-dmantipov@yandex.ru
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index cbf1664dc569c..d79180bec7a1f 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -2200,7 +2200,7 @@ struct cfg80211_sar_sub_specs {
 struct cfg80211_sar_specs {
 	enum nl80211_sar_type type;
 	u32 num_sub_specs;
-	struct cfg80211_sar_sub_specs sub_specs[];
+	struct cfg80211_sar_sub_specs sub_specs[] __counted_by(num_sub_specs);
 };
 
 
@@ -2838,7 +2838,7 @@ struct cfg80211_sched_scan_request {
 	struct list_head list;
 
 	/* keep last */
-	struct ieee80211_channel *channels[];
+	struct ieee80211_channel *channels[] __counted_by(n_channels);
 };
 
 /**
@@ -3582,7 +3582,7 @@ struct cfg80211_coalesce {
 struct cfg80211_wowlan_nd_match {
 	struct cfg80211_ssid ssid;
 	int n_channels;
-	u32 channels[];
+	u32 channels[] __counted_by(n_channels);
 };
 
 /**
@@ -3596,7 +3596,7 @@ struct cfg80211_wowlan_nd_match {
  */
 struct cfg80211_wowlan_nd_info {
 	int n_matches;
-	struct cfg80211_wowlan_nd_match *matches[];
+	struct cfg80211_wowlan_nd_match *matches[] __counted_by(n_matches);
 };
 
 /**
-- 
GitLab


From 2fe0a605d083b884490ee4de02be071b5b4291b1 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 6 May 2024 21:18:52 +0200
Subject: [PATCH 154/950] wifi: mac80211: fix TTLM teardown work

The worker calculates the wrong sdata pointer, so if it ever
runs, it'll crash. Fix that.

Fixes: a17a58ad2ff2 ("wifi: mac80211: add support for tearing down negotiated TTLM")
Reviewed-by: Miriam Rachel Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240506211853.e6471800c76d.I8b7c2d6984c89a11cd33d1a610e9645fa965f6e1@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mlme.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index a974a75df2664..a29c4a4deb0b5 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -7333,7 +7333,7 @@ static void ieee80211_teardown_ttlm_work(struct wiphy *wiphy,
 	u16 new_dormant_links;
 	struct ieee80211_sub_if_data *sdata =
 		container_of(work, struct ieee80211_sub_if_data,
-			     u.mgd.neg_ttlm_timeout_work.work);
+			     u.mgd.teardown_ttlm_work);
 
 	if (!sdata->vif.neg_ttlm.valid)
 		return;
-- 
GitLab


From 53b739fd46462dc40fd18390d76f2ee05c18ea3a Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 6 May 2024 21:10:33 +0200
Subject: [PATCH 155/950] wifi: mac80211: cancel multi-link reconf work on
 disconnect

This work shouldn't run after we're disconnecting. Cancel it earlier
(and then don't cancel it in stop later.)

Fixes: 8eb8dd2ffbbb ("wifi: mac80211: Support link removal using Reconfiguration ML element")
Reviewed-by: Ilan Peer <ilan.peer@intel.com>
Reviewed-by: Miriam Rachel Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240506211034.ac754794279f.Ib9fbb1dab50c6b67f6de9be09a6c452ce89bbd50@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mlme.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index a29c4a4deb0b5..ab6b379d522b3 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -3694,6 +3694,11 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata,
 
 	wiphy_delayed_work_cancel(sdata->local->hw.wiphy,
 				  &ifmgd->neg_ttlm_timeout_work);
+
+	sdata->u.mgd.removed_links = 0;
+	wiphy_delayed_work_cancel(sdata->local->hw.wiphy,
+				  &sdata->u.mgd.ml_reconf_work);
+
 	ieee80211_vif_set_links(sdata, 0, 0);
 
 	ifmgd->mcast_seq_last = IEEE80211_SN_MODULO;
@@ -9211,8 +9216,6 @@ void ieee80211_mgd_stop(struct ieee80211_sub_if_data *sdata)
 			  &ifmgd->teardown_ttlm_work);
 	wiphy_delayed_work_cancel(sdata->local->hw.wiphy,
 				  &ifmgd->tdls_peer_del_work);
-	wiphy_delayed_work_cancel(sdata->local->hw.wiphy,
-				  &ifmgd->ml_reconf_work);
 	wiphy_delayed_work_cancel(sdata->local->hw.wiphy, &ifmgd->ttlm_work);
 	wiphy_delayed_work_cancel(sdata->local->hw.wiphy,
 				  &ifmgd->neg_ttlm_timeout_work);
-- 
GitLab


From 3567bd6dcd1467d2ad0f597be94114c6f9c62680 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 6 May 2024 21:10:34 +0200
Subject: [PATCH 156/950] wifi: mac80211: cancel TTLM teardown work earlier

It shouldn't be possible to run this after disconnecting, so
cancel the work earlier.

Fixes: a17a58ad2ff2 ("wifi: mac80211: add support for tearing down negotiated TTLM")
Reviewed-by: Miriam Rachel Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240506211034.096a10ccebec.I5584a21c27eb9b3e87b9e26380b627114b32ccba@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mlme.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index ab6b379d522b3..e0b44f47747be 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -3699,6 +3699,9 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata,
 	wiphy_delayed_work_cancel(sdata->local->hw.wiphy,
 				  &sdata->u.mgd.ml_reconf_work);
 
+	wiphy_work_cancel(sdata->local->hw.wiphy,
+			  &ifmgd->teardown_ttlm_work);
+
 	ieee80211_vif_set_links(sdata, 0, 0);
 
 	ifmgd->mcast_seq_last = IEEE80211_SN_MODULO;
@@ -9212,8 +9215,6 @@ void ieee80211_mgd_stop(struct ieee80211_sub_if_data *sdata)
 			  &ifmgd->beacon_connection_loss_work);
 	wiphy_work_cancel(sdata->local->hw.wiphy,
 			  &ifmgd->csa_connection_drop_work);
-	wiphy_work_cancel(sdata->local->hw.wiphy,
-			  &ifmgd->teardown_ttlm_work);
 	wiphy_delayed_work_cancel(sdata->local->hw.wiphy,
 				  &ifmgd->tdls_peer_del_work);
 	wiphy_delayed_work_cancel(sdata->local->hw.wiphy, &ifmgd->ttlm_work);
-- 
GitLab


From 0d22026f3287ef5af80d983db150ff260e7117e8 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 6 May 2024 21:10:35 +0200
Subject: [PATCH 157/950] wifi: mac80211: don't stop TTLM works again

There's no need to stop works that have already been
stopped during disconnect, so don't.

Reviewed-by: Miriam Rachel Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240506211034.f8434be19f56.I021afadc538508da3bc8f95c89f424ca62b94bef@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mlme.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index e0b44f47747be..09451a6f74b8d 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -9217,9 +9217,6 @@ void ieee80211_mgd_stop(struct ieee80211_sub_if_data *sdata)
 			  &ifmgd->csa_connection_drop_work);
 	wiphy_delayed_work_cancel(sdata->local->hw.wiphy,
 				  &ifmgd->tdls_peer_del_work);
-	wiphy_delayed_work_cancel(sdata->local->hw.wiphy, &ifmgd->ttlm_work);
-	wiphy_delayed_work_cancel(sdata->local->hw.wiphy,
-				  &ifmgd->neg_ttlm_timeout_work);
 
 	if (ifmgd->assoc_data)
 		ieee80211_destroy_assoc_data(sdata, ASSOC_TIMEOUT);
-- 
GitLab


From 609c12a2af046c3674af2d5c7978b025718de5e8 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 6 May 2024 21:18:59 +0200
Subject: [PATCH 158/950] wifi: mac80211: reset negotiated TTLM on disconnect

The negotiated TTLM data must be reset on disconnect, otherwise
it may end up getting reused on another connection. Fix that.

Fixes: 8f500fbc6c65 ("wifi: mac80211: process and save negotiated TID to Link mapping request")
Reviewed-by: Miriam Rachel Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240506211858.04142e8fe01c.Ia144457e086ebd8ddcfa31bdf5ff210b4b351c22@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mlme.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 09451a6f74b8d..ef3280fafbe99 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -3692,6 +3692,7 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata,
 	       sizeof(sdata->u.mgd.ttlm_info));
 	wiphy_delayed_work_cancel(sdata->local->hw.wiphy, &ifmgd->ttlm_work);
 
+	memset(&sdata->vif.neg_ttlm, 0, sizeof(sdata->vif.neg_ttlm));
 	wiphy_delayed_work_cancel(sdata->local->hw.wiphy,
 				  &ifmgd->neg_ttlm_timeout_work);
 
-- 
GitLab


From a92fd2d9327ba877f29753eec15b93072ac300b0 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 10 May 2024 11:26:02 +0200
Subject: [PATCH 159/950] wifi: mac80211: send DelBA with correct BSSID

In MLO, the deflink BSSID is clearly invalid. Since we fill
the addresses as MLD addresses and translate later, use the
AP address here instead.

This fixes an issue that happens with HW restart, where the
DelBA frame is transmitted, but not processed correctly due
to the wrong BSSID (or even just discarded entirely).  As a
result, the BA sessions are kept alive; however, as other
state is reset during HW restart, this then fails (reorder,
etc.) and data doesn't go through until new BA sessions are
established.

Reviewed-by: Miriam Rachel Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240510112601.f4e1effdea29.I98e81f22166b68d4b6211191bcaaf8531b324a77@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/ht.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c
index d7e8cf8e48b78..79caeb485fd5d 100644
--- a/net/mac80211/ht.c
+++ b/net/mac80211/ht.c
@@ -475,7 +475,7 @@ void ieee80211_send_delba(struct ieee80211_sub_if_data *sdata,
 	    sdata->vif.type == NL80211_IFTYPE_MESH_POINT)
 		memcpy(mgmt->bssid, sdata->vif.addr, ETH_ALEN);
 	else if (sdata->vif.type == NL80211_IFTYPE_STATION)
-		memcpy(mgmt->bssid, sdata->deflink.u.mgd.bssid, ETH_ALEN);
+		memcpy(mgmt->bssid, sdata->vif.cfg.ap_addr, ETH_ALEN);
 	else if (sdata->vif.type == NL80211_IFTYPE_ADHOC)
 		memcpy(mgmt->bssid, sdata->u.ibss.bssid, ETH_ALEN);
 
-- 
GitLab


From c898afdc15645efb555acb6d85b484eb40a45409 Mon Sep 17 00:00:00 2001
From: Dominique Martinet <asmadeus@codewreck.org>
Date: Tue, 21 May 2024 21:13:36 +0900
Subject: [PATCH 160/950] 9p: add missing locking around taking dentry fid list

Fix a use-after-free on dentry's d_fsdata fid list when a thread
looks up a fid through dentry while another thread unlinks it:

UAF thread:
refcount_t: addition on 0; use-after-free.
 p9_fid_get linux/./include/net/9p/client.h:262
 v9fs_fid_find+0x236/0x280 linux/fs/9p/fid.c:129
 v9fs_fid_lookup_with_uid linux/fs/9p/fid.c:181
 v9fs_fid_lookup+0xbf/0xc20 linux/fs/9p/fid.c:314
 v9fs_vfs_getattr_dotl+0xf9/0x360 linux/fs/9p/vfs_inode_dotl.c:400
 vfs_statx+0xdd/0x4d0 linux/fs/stat.c:248

Freed by:
 p9_fid_destroy (inlined)
 p9_client_clunk+0xb0/0xe0 linux/net/9p/client.c:1456
 p9_fid_put linux/./include/net/9p/client.h:278
 v9fs_dentry_release+0xb5/0x140 linux/fs/9p/vfs_dentry.c:55
 v9fs_remove+0x38f/0x620 linux/fs/9p/vfs_inode.c:518
 vfs_unlink+0x29a/0x810 linux/fs/namei.c:4335

The problem is that d_fsdata was not accessed under d_lock, because
d_release() normally is only called once the dentry is otherwise no
longer accessible but since we also call it explicitly in v9fs_remove
that lock is required:
move the hlist out of the dentry under lock then unref its fids once
they are no longer accessible.

Fixes: 154372e67d40 ("fs/9p: fix create-unlink-getattr idiom")
Cc: stable@vger.kernel.org
Reported-by: Meysam Firouzi
Reported-by: Amirmohammad Eftekhar
Reviewed-by: Christian Schoenebeck <linux_oss@crudebyte.com>
Message-ID: <20240521122947.1080227-1-asmadeus@codewreck.org>
Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
---
 fs/9p/vfs_dentry.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/fs/9p/vfs_dentry.c b/fs/9p/vfs_dentry.c
index f16f735816349..01338d4c2d9e6 100644
--- a/fs/9p/vfs_dentry.c
+++ b/fs/9p/vfs_dentry.c
@@ -48,12 +48,17 @@ static int v9fs_cached_dentry_delete(const struct dentry *dentry)
 static void v9fs_dentry_release(struct dentry *dentry)
 {
 	struct hlist_node *p, *n;
+	struct hlist_head head;
 
 	p9_debug(P9_DEBUG_VFS, " dentry: %pd (%p)\n",
 		 dentry, dentry);
-	hlist_for_each_safe(p, n, (struct hlist_head *)&dentry->d_fsdata)
+
+	spin_lock(&dentry->d_lock);
+	hlist_move_list((struct hlist_head *)&dentry->d_fsdata, &head);
+	spin_unlock(&dentry->d_lock);
+
+	hlist_for_each_safe(p, n, &head)
 		p9_fid_put(hlist_entry(p, struct p9_fid, dlist));
-	dentry->d_fsdata = NULL;
 }
 
 static int v9fs_lookup_revalidate(struct dentry *dentry, unsigned int flags)
-- 
GitLab


From 9f788ba457b45b0ce422943fcec9fa35c4587764 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Wed, 22 May 2024 20:09:49 +0300
Subject: [PATCH 161/950] spi: Don't mark message DMA mapped when no transfer
 in it is

There is no need to set the DMA mapped flag of the message if it has
no mapped transfers. Moreover, it may give the code a chance to take
the wrong paths, i.e. to exercise DMA related APIs on unmapped data.
Make __spi_map_msg() to bail earlier on the above mentioned cases.

Fixes: 99adef310f68 ("spi: Provide core support for DMA mapping transfers")
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://msgid.link/r/20240522171018.3362521-2-andriy.shevchenko@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index a8966caed8414..d40ce0fdb1a81 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -1243,6 +1243,7 @@ static int __spi_map_msg(struct spi_controller *ctlr, struct spi_message *msg)
 	else
 		rx_dev = ctlr->dev.parent;
 
+	ret = -ENOMSG;
 	list_for_each_entry(xfer, &msg->transfers, transfer_list) {
 		/* The sync is done before each transfer. */
 		unsigned long attrs = DMA_ATTR_SKIP_CPU_SYNC;
@@ -1272,6 +1273,9 @@ static int __spi_map_msg(struct spi_controller *ctlr, struct spi_message *msg)
 			}
 		}
 	}
+	/* No transfer has been mapped, bail out with success */
+	if (ret)
+		return 0;
 
 	ctlr->cur_rx_dma_dev = rx_dev;
 	ctlr->cur_tx_dma_dev = tx_dev;
-- 
GitLab


From da560097c05612f8d360f86528f6213629b9c395 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Wed, 22 May 2024 20:09:50 +0300
Subject: [PATCH 162/950] spi: Check if transfer is mapped before calling DMA
 sync APIs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The resent update to remove the orig_nents checks revealed
that not all DMA sync backends can cope with the unallocated
SG list, while supplying orig_nents == 0 (the commit 861370f49ce4
("iommu/dma: force bouncing if the size is not cacheline-aligned"),
for example, makes that happen for the IOMMU case). It means
we have to check if the buffers are DMA mapped before trying
to sync them. Re-introduce that check in a form of calling
->can_dma() in the same way as it's done in the DMA mapping loop
for the SPI transfers.

Reported-by: Nícolas F. R. A. Prado <nfraprado@collabora.com>
Reported-by: Neil Armstrong <neil.armstrong@linaro.org>
Closes: https://lore.kernel.org/r/8ae675b5-fcf9-4c9b-b06a-4462f70e1322@linaro.org
Closes: https://lore.kernel.org/all/d3679496-2e4e-4a7c-97ed-f193bd53af1d@notapiano
Fixes: 8cc3bad9d9d6 ("spi: Remove unneded check for orig_nents")
Suggested-by: Nícolas F. R. A. Prado <nfraprado@collabora.com>
Tested-by: Nícolas F. R. A. Prado <nfraprado@collabora.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://msgid.link/r/20240522171018.3362521-3-andriy.shevchenko@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi.c | 18 +++++++++++++-----
 1 file changed, 13 insertions(+), 5 deletions(-)

diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index d40ce0fdb1a81..b18a4c871e217 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -1311,7 +1311,7 @@ static int __spi_unmap_msg(struct spi_controller *ctlr, struct spi_message *msg)
 	return 0;
 }
 
-static void spi_dma_sync_for_device(struct spi_controller *ctlr,
+static void spi_dma_sync_for_device(struct spi_controller *ctlr, struct spi_message *msg,
 				    struct spi_transfer *xfer)
 {
 	struct device *rx_dev = ctlr->cur_rx_dma_dev;
@@ -1320,11 +1320,14 @@ static void spi_dma_sync_for_device(struct spi_controller *ctlr,
 	if (!ctlr->cur_msg_mapped)
 		return;
 
+	if (!ctlr->can_dma(ctlr, msg->spi, xfer))
+		return;
+
 	dma_sync_sgtable_for_device(tx_dev, &xfer->tx_sg, DMA_TO_DEVICE);
 	dma_sync_sgtable_for_device(rx_dev, &xfer->rx_sg, DMA_FROM_DEVICE);
 }
 
-static void spi_dma_sync_for_cpu(struct spi_controller *ctlr,
+static void spi_dma_sync_for_cpu(struct spi_controller *ctlr, struct spi_message *msg,
 				 struct spi_transfer *xfer)
 {
 	struct device *rx_dev = ctlr->cur_rx_dma_dev;
@@ -1333,6 +1336,9 @@ static void spi_dma_sync_for_cpu(struct spi_controller *ctlr,
 	if (!ctlr->cur_msg_mapped)
 		return;
 
+	if (!ctlr->can_dma(ctlr, msg->spi, xfer))
+		return;
+
 	dma_sync_sgtable_for_cpu(rx_dev, &xfer->rx_sg, DMA_FROM_DEVICE);
 	dma_sync_sgtable_for_cpu(tx_dev, &xfer->tx_sg, DMA_TO_DEVICE);
 }
@@ -1350,11 +1356,13 @@ static inline int __spi_unmap_msg(struct spi_controller *ctlr,
 }
 
 static void spi_dma_sync_for_device(struct spi_controller *ctrl,
+				    struct spi_message *msg,
 				    struct spi_transfer *xfer)
 {
 }
 
 static void spi_dma_sync_for_cpu(struct spi_controller *ctrl,
+				 struct spi_message *msg,
 				 struct spi_transfer *xfer)
 {
 }
@@ -1626,10 +1634,10 @@ static int spi_transfer_one_message(struct spi_controller *ctlr,
 			reinit_completion(&ctlr->xfer_completion);
 
 fallback_pio:
-			spi_dma_sync_for_device(ctlr, xfer);
+			spi_dma_sync_for_device(ctlr, msg, xfer);
 			ret = ctlr->transfer_one(ctlr, msg->spi, xfer);
 			if (ret < 0) {
-				spi_dma_sync_for_cpu(ctlr, xfer);
+				spi_dma_sync_for_cpu(ctlr, msg, xfer);
 
 				if (ctlr->cur_msg_mapped &&
 				   (xfer->error & SPI_TRANS_FAIL_NO_START)) {
@@ -1654,7 +1662,7 @@ fallback_pio:
 					msg->status = ret;
 			}
 
-			spi_dma_sync_for_cpu(ctlr, xfer);
+			spi_dma_sync_for_cpu(ctlr, msg, xfer);
 		} else {
 			if (xfer->len)
 				dev_err(&msg->spi->dev,
-- 
GitLab


From a827ad9b3c2fc243e058595533f91ce41a312527 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Thu, 23 May 2024 12:33:25 +0200
Subject: [PATCH 163/950] spi: stm32: Revert change that enabled controller
 before asserting CS
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

On stm32mp157 enabling the controller before asserting CS makes the
hardware trigger spurious interrupts in a tight loop and the transfers
fail. Revert the commit that swapped the order of enable and CS. This
reintroduces the problem that swapping was supposed to fix, which
however is less grave.

Reported-by: Leonard Göhrs <l.goehrs@pengutronix.de>
Link: https://lore.kernel.org/all/39033ed7-3e57-4339-80b4-fc8919e26aa7@pengutronix.de/
Fixes: 52b62e7a5d4f ("spi: stm32: enable controller before asserting CS")
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://msgid.link/r/20240523103326.792907-2-u.kleine-koenig@pengutronix.de
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-stm32.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/drivers/spi/spi-stm32.c b/drivers/spi/spi-stm32.c
index 4a68abcdcc353..e4e7ddb7524a9 100644
--- a/drivers/spi/spi-stm32.c
+++ b/drivers/spi/spi-stm32.c
@@ -1016,8 +1016,10 @@ end_irq:
 static irqreturn_t stm32fx_spi_irq_thread(int irq, void *dev_id)
 {
 	struct spi_controller *ctrl = dev_id;
+	struct stm32_spi *spi = spi_controller_get_devdata(ctrl);
 
 	spi_finalize_current_transfer(ctrl);
+	stm32fx_spi_disable(spi);
 
 	return IRQ_HANDLED;
 }
@@ -1185,8 +1187,6 @@ static int stm32_spi_prepare_msg(struct spi_controller *ctrl,
 			 ~clrb) | setb,
 			spi->base + spi->cfg->regs->cpol.reg);
 
-	stm32_spi_enable(spi);
-
 	spin_unlock_irqrestore(&spi->lock, flags);
 
 	return 0;
@@ -1204,6 +1204,7 @@ static void stm32fx_spi_dma_tx_cb(void *data)
 
 	if (spi->cur_comm == SPI_SIMPLEX_TX || spi->cur_comm == SPI_3WIRE_TX) {
 		spi_finalize_current_transfer(spi->ctrl);
+		stm32fx_spi_disable(spi);
 	}
 }
 
@@ -1218,6 +1219,7 @@ static void stm32_spi_dma_rx_cb(void *data)
 	struct stm32_spi *spi = data;
 
 	spi_finalize_current_transfer(spi->ctrl);
+	spi->cfg->disable(spi);
 }
 
 /**
@@ -1305,6 +1307,8 @@ static int stm32fx_spi_transfer_one_irq(struct stm32_spi *spi)
 
 	stm32_spi_set_bits(spi, STM32FX_SPI_CR2, cr2);
 
+	stm32_spi_enable(spi);
+
 	/* starting data transfer when buffer is loaded */
 	if (spi->tx_buf)
 		spi->cfg->write_tx(spi);
@@ -1341,6 +1345,8 @@ static int stm32h7_spi_transfer_one_irq(struct stm32_spi *spi)
 
 	spin_lock_irqsave(&spi->lock, flags);
 
+	stm32_spi_enable(spi);
+
 	/* Be sure to have data in fifo before starting data transfer */
 	if (spi->tx_buf)
 		stm32h7_spi_write_txfifo(spi);
@@ -1372,6 +1378,8 @@ static void stm32fx_spi_transfer_one_dma_start(struct stm32_spi *spi)
 		 */
 		stm32_spi_set_bits(spi, STM32FX_SPI_CR2, STM32FX_SPI_CR2_ERRIE);
 	}
+
+	stm32_spi_enable(spi);
 }
 
 /**
@@ -1405,6 +1413,8 @@ static void stm32h7_spi_transfer_one_dma_start(struct stm32_spi *spi)
 
 	stm32_spi_set_bits(spi, STM32H7_SPI_IER, ier);
 
+	stm32_spi_enable(spi);
+
 	if (STM32_SPI_HOST_MODE(spi))
 		stm32_spi_set_bits(spi, STM32H7_SPI_CR1, STM32H7_SPI_CR1_CSTART);
 }
-- 
GitLab


From e6722ea6b9ed731f7392277d76ca912dfffca7ee Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sat, 6 Jan 2024 13:48:25 +0100
Subject: [PATCH 164/950] i2c: synquacer: Remove a clk reference from struct
 synquacer_i2c

'pclk' is only used locally in the probe. Remove it from the
'synquacer_i2c' structure.

Also remove a useless debug message.

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
---
 drivers/i2c/busses/i2c-synquacer.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/drivers/i2c/busses/i2c-synquacer.c b/drivers/i2c/busses/i2c-synquacer.c
index 31ecb2c7e9783..4eccbcd0fbfc0 100644
--- a/drivers/i2c/busses/i2c-synquacer.c
+++ b/drivers/i2c/busses/i2c-synquacer.c
@@ -138,7 +138,6 @@ struct synquacer_i2c {
 	int			irq;
 	struct device		*dev;
 	void __iomem		*base;
-	struct clk		*pclk;
 	u32			pclkrate;
 	u32			speed_khz;
 	u32			timeout_ms;
@@ -535,6 +534,7 @@ static const struct i2c_adapter synquacer_i2c_ops = {
 static int synquacer_i2c_probe(struct platform_device *pdev)
 {
 	struct synquacer_i2c *i2c;
+	struct clk *pclk;
 	u32 bus_speed;
 	int ret;
 
@@ -550,13 +550,12 @@ static int synquacer_i2c_probe(struct platform_device *pdev)
 	device_property_read_u32(&pdev->dev, "socionext,pclk-rate",
 				 &i2c->pclkrate);
 
-	i2c->pclk = devm_clk_get_enabled(&pdev->dev, "pclk");
-	if (IS_ERR(i2c->pclk))
-		return dev_err_probe(&pdev->dev, PTR_ERR(i2c->pclk),
+	pclk = devm_clk_get_enabled(&pdev->dev, "pclk");
+	if (IS_ERR(pclk))
+		return dev_err_probe(&pdev->dev, PTR_ERR(pclk),
 				     "failed to get and enable clock\n");
 
-	dev_dbg(&pdev->dev, "clock source %p\n", i2c->pclk);
-	i2c->pclkrate = clk_get_rate(i2c->pclk);
+	i2c->pclkrate = clk_get_rate(pclk);
 
 	if (i2c->pclkrate < SYNQUACER_I2C_MIN_CLK_RATE ||
 	    i2c->pclkrate > SYNQUACER_I2C_MAX_CLK_RATE)
-- 
GitLab


From e61bcf42d290e73025bab38e0e55a5586c2d8ad5 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 15 Apr 2024 22:50:27 +0200
Subject: [PATCH 165/950] i2c: Remove I2C_CLASS_SPD

Remove this class after all users have been gone.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
---
 include/linux/i2c.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index 5e6cd43a6dbdd..9709537370ee9 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -852,7 +852,6 @@ static inline void i2c_mark_adapter_resumed(struct i2c_adapter *adap)
 
 /* i2c adapter classes (bitmask) */
 #define I2C_CLASS_HWMON		(1<<0)	/* lm_sensors, ... */
-#define I2C_CLASS_SPD		(1<<7)	/* Memory modules */
 /* Warn users that the adapter doesn't support classes anymore */
 #define I2C_CLASS_DEPRECATED	(1<<8)
 
-- 
GitLab


From ed281c6ab6eb8a914f06c74dfeaebde15b34a3f4 Mon Sep 17 00:00:00 2001
From: Carl Huang <quic_cjhuang@quicinc.com>
Date: Tue, 21 May 2024 11:08:10 +0300
Subject: [PATCH 166/950] wifi: ath11k: fix WCN6750 firmware crash caused by 17
 num_vdevs

WCN6750 firmware crashes because of num_vdevs changed from 4 to 17
in ath11k_init_wmi_config_qca6390() as the ab->hw_params.num_vdevs
is 17. This is caused by commit f019f4dff2e4 ("wifi: ath11k: support
2 station interfaces") which assigns ab->hw_params.num_vdevs directly
to config->num_vdevs in ath11k_init_wmi_config_qca6390(), therefore
WCN6750 firmware crashes as it can't support such a big num_vdevs.

Fix it by assign 3 to num_vdevs in hw_params for WCN6750 as 3 is
sufficient too.

Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-03125-QCAHSPSWPL_V1_V2_SILICONZ_LITE-3
Tested-on: WCN6750 hw1.0 AHB WLAN.MSL.1.0.1-01371-QCAMSLSWPLZ-1

Fixes: f019f4dff2e4 ("wifi: ath11k: support 2 station interfaces")
Reported-by: Luca Weiss <luca.weiss@fairphone.com>
Tested-by: Luca Weiss <luca.weiss@fairphone.com>
Closes: https://lore.kernel.org/r/D15TIIDIIESY.D1EKKJLZINMA@fairphone.com/
Signed-off-by: Carl Huang <quic_cjhuang@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240520030757.2209395-1-quic_cjhuang@quicinc.com
---
 drivers/net/wireless/ath/ath11k/core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath11k/core.c b/drivers/net/wireless/ath/ath11k/core.c
index 3cc817a3b4a40..b82e8fb285413 100644
--- a/drivers/net/wireless/ath/ath11k/core.c
+++ b/drivers/net/wireless/ath/ath11k/core.c
@@ -604,7 +604,7 @@ static const struct ath11k_hw_params ath11k_hw_params[] = {
 		.coldboot_cal_ftm = true,
 		.cbcal_restart_fw = false,
 		.fw_mem_mode = 0,
-		.num_vdevs = 16 + 1,
+		.num_vdevs = 3,
 		.num_peers = 512,
 		.supports_suspend = false,
 		.hal_desc_sz = sizeof(struct hal_rx_desc_qcn9074),
-- 
GitLab


From 6e16782d6b4a724f9c9dcd49471219643593b60c Mon Sep 17 00:00:00 2001
From: Baochen Qiang <quic_bqiang@quicinc.com>
Date: Tue, 21 May 2024 11:08:11 +0300
Subject: [PATCH 167/950] wifi: ath11k: move power type check to ASSOC stage
 when connecting to 6 GHz AP

With commit bc8a0fac8677 ("wifi: mac80211: don't set bss_conf in parsing")
ath11k fails to connect to 6 GHz AP.

This is because currently ath11k checks AP's power type in
ath11k_mac_op_assign_vif_chanctx() which would be called in AUTH stage.
However with above commit power type is not available until ASSOC stage.
As a result power type check fails and therefore connection fails.

Fix this by moving power type check to ASSOC stage, also move regulatory
rules update there because it depends on power type.

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

Fixes: bc8a0fac8677 ("wifi: mac80211: don't set bss_conf in parsing")
Signed-off-by: Baochen Qiang <quic_bqiang@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240424064019.4847-1-quic_bqiang@quicinc.com
---
 drivers/net/wireless/ath/ath11k/mac.c | 38 ++++++++++++++++++---------
 1 file changed, 25 insertions(+), 13 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c
index 4f62e38ba48b3..9b96dbb21d833 100644
--- a/drivers/net/wireless/ath/ath11k/mac.c
+++ b/drivers/net/wireless/ath/ath11k/mac.c
@@ -7988,8 +7988,6 @@ ath11k_mac_op_assign_vif_chanctx(struct ieee80211_hw *hw,
 	struct ath11k_base *ab = ar->ab;
 	struct ath11k_vif *arvif = ath11k_vif_to_arvif(vif);
 	int ret;
-	struct cur_regulatory_info *reg_info;
-	enum ieee80211_ap_reg_power power_type;
 
 	mutex_lock(&ar->conf_mutex);
 
@@ -8000,17 +7998,6 @@ ath11k_mac_op_assign_vif_chanctx(struct ieee80211_hw *hw,
 	if (ath11k_wmi_supports_6ghz_cc_ext(ar) &&
 	    ctx->def.chan->band == NL80211_BAND_6GHZ &&
 	    arvif->vdev_type == WMI_VDEV_TYPE_STA) {
-		reg_info = &ab->reg_info_store[ar->pdev_idx];
-		power_type = vif->bss_conf.power_type;
-
-		ath11k_dbg(ab, ATH11K_DBG_MAC, "chanctx power type %d\n", power_type);
-
-		if (power_type == IEEE80211_REG_UNSET_AP) {
-			ret = -EINVAL;
-			goto out;
-		}
-
-		ath11k_reg_handle_chan_list(ab, reg_info, power_type);
 		arvif->chanctx = *ctx;
 		ath11k_mac_parse_tx_pwr_env(ar, vif, ctx);
 	}
@@ -9626,6 +9613,8 @@ static int ath11k_mac_op_sta_state(struct ieee80211_hw *hw,
 	struct ath11k *ar = hw->priv;
 	struct ath11k_vif *arvif = ath11k_vif_to_arvif(vif);
 	struct ath11k_sta *arsta = ath11k_sta_to_arsta(sta);
+	enum ieee80211_ap_reg_power power_type;
+	struct cur_regulatory_info *reg_info;
 	struct ath11k_peer *peer;
 	int ret = 0;
 
@@ -9705,6 +9694,29 @@ static int ath11k_mac_op_sta_state(struct ieee80211_hw *hw,
 				ath11k_warn(ar->ab, "Unable to authorize peer %pM vdev %d: %d\n",
 					    sta->addr, arvif->vdev_id, ret);
 		}
+
+		if (!ret &&
+		    ath11k_wmi_supports_6ghz_cc_ext(ar) &&
+		    arvif->vdev_type == WMI_VDEV_TYPE_STA &&
+		    arvif->chanctx.def.chan &&
+		    arvif->chanctx.def.chan->band == NL80211_BAND_6GHZ) {
+			reg_info = &ar->ab->reg_info_store[ar->pdev_idx];
+			power_type = vif->bss_conf.power_type;
+
+			if (power_type == IEEE80211_REG_UNSET_AP) {
+				ath11k_warn(ar->ab, "invalid power type %d\n",
+					    power_type);
+				ret = -EINVAL;
+			} else {
+				ret = ath11k_reg_handle_chan_list(ar->ab,
+								  reg_info,
+								  power_type);
+				if (ret)
+					ath11k_warn(ar->ab,
+						    "failed to handle chan list with power type %d\n",
+						    power_type);
+			}
+		}
 	} else if (old_state == IEEE80211_STA_AUTHORIZED &&
 		   new_state == IEEE80211_STA_ASSOC) {
 		spin_lock_bh(&ar->ab->base_lock);
-- 
GitLab


From bb9025f4432f8c158322cf2c04c2b492f23eb511 Mon Sep 17 00:00:00 2001
From: Fedor Pchelkin <pchelkin@ispras.ru>
Date: Sat, 4 May 2024 14:47:01 +0300
Subject: [PATCH 168/950] dma-mapping: benchmark: fix up kthread-related error
 handling

kthread creation failure is invalidly handled inside do_map_benchmark().
The put_task_struct() calls on the error path are supposed to balance the
get_task_struct() calls which only happen after all the kthreads are
successfully created. Rollback using kthread_stop() for already created
kthreads in case of such failure.

In normal situation call kthread_stop_put() to gracefully stop kthreads
and put their task refcounts. This should be done for all started
kthreads.

Found by Linux Verification Center (linuxtesting.org).

Fixes: 65789daa8087 ("dma-mapping: add benchmark support for streaming DMA APIs")
Suggested-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Fedor Pchelkin <pchelkin@ispras.ru>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 kernel/dma/map_benchmark.c | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

diff --git a/kernel/dma/map_benchmark.c b/kernel/dma/map_benchmark.c
index 02205ab53b7e9..2478957cf9f83 100644
--- a/kernel/dma/map_benchmark.c
+++ b/kernel/dma/map_benchmark.c
@@ -118,6 +118,8 @@ static int do_map_benchmark(struct map_benchmark_data *map)
 		if (IS_ERR(tsk[i])) {
 			pr_err("create dma_map thread failed\n");
 			ret = PTR_ERR(tsk[i]);
+			while (--i >= 0)
+				kthread_stop(tsk[i]);
 			goto out;
 		}
 
@@ -139,13 +141,17 @@ static int do_map_benchmark(struct map_benchmark_data *map)
 
 	msleep_interruptible(map->bparam.seconds * 1000);
 
-	/* wait for the completion of benchmark threads */
+	/* wait for the completion of all started benchmark threads */
 	for (i = 0; i < threads; i++) {
-		ret = kthread_stop(tsk[i]);
-		if (ret)
-			goto out;
+		int kthread_ret = kthread_stop_put(tsk[i]);
+
+		if (kthread_ret)
+			ret = kthread_ret;
 	}
 
+	if (ret)
+		goto out;
+
 	loops = atomic64_read(&map->loops);
 	if (likely(loops > 0)) {
 		u64 map_variance, unmap_variance;
@@ -170,8 +176,6 @@ static int do_map_benchmark(struct map_benchmark_data *map)
 	}
 
 out:
-	for (i = 0; i < threads; i++)
-		put_task_struct(tsk[i]);
 	put_device(map->dev);
 	kfree(tsk);
 	return ret;
-- 
GitLab


From f7c9ccaadffd13066353332c13d7e9bf73b8f92d Mon Sep 17 00:00:00 2001
From: Fedor Pchelkin <pchelkin@ispras.ru>
Date: Sat, 4 May 2024 14:47:02 +0300
Subject: [PATCH 169/950] dma-mapping: benchmark: avoid needless copy_to_user
 if benchmark fails

If do_map_benchmark() has failed, there is nothing useful to copy back
to userspace.

Suggested-by: Barry Song <21cnbao@gmail.com>
Signed-off-by: Fedor Pchelkin <pchelkin@ispras.ru>
Acked-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 kernel/dma/map_benchmark.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/kernel/dma/map_benchmark.c b/kernel/dma/map_benchmark.c
index 2478957cf9f83..a6edb1ef98c8a 100644
--- a/kernel/dma/map_benchmark.c
+++ b/kernel/dma/map_benchmark.c
@@ -256,6 +256,9 @@ static long map_benchmark_ioctl(struct file *file, unsigned int cmd,
 		 * dma_mask changed by benchmark
 		 */
 		dma_set_mask(map->dev, old_dma_mask);
+
+		if (ret)
+			return ret;
 		break;
 	default:
 		return -EINVAL;
-- 
GitLab


From 1ff05e723f7ca30644b8ec3fb093f16312e408ad Mon Sep 17 00:00:00 2001
From: Fedor Pchelkin <pchelkin@ispras.ru>
Date: Sat, 4 May 2024 14:47:03 +0300
Subject: [PATCH 170/950] dma-mapping: benchmark: fix node id validation

While validating node ids in map_benchmark_ioctl(), node_possible() may
be provided with invalid argument outside of [0,MAX_NUMNODES-1] range
leading to:

BUG: KASAN: wild-memory-access in map_benchmark_ioctl (kernel/dma/map_benchmark.c:214)
Read of size 8 at addr 1fffffff8ccb6398 by task dma_map_benchma/971
CPU: 7 PID: 971 Comm: dma_map_benchma Not tainted 6.9.0-rc6 #37
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996)
Call Trace:
 <TASK>
dump_stack_lvl (lib/dump_stack.c:117)
kasan_report (mm/kasan/report.c:603)
kasan_check_range (mm/kasan/generic.c:189)
variable_test_bit (arch/x86/include/asm/bitops.h:227) [inline]
arch_test_bit (arch/x86/include/asm/bitops.h:239) [inline]
_test_bit at (include/asm-generic/bitops/instrumented-non-atomic.h:142) [inline]
node_state (include/linux/nodemask.h:423) [inline]
map_benchmark_ioctl (kernel/dma/map_benchmark.c:214)
full_proxy_unlocked_ioctl (fs/debugfs/file.c:333)
__x64_sys_ioctl (fs/ioctl.c:890)
do_syscall_64 (arch/x86/entry/common.c:83)
entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130)

Compare node ids with sane bounds first. NUMA_NO_NODE is considered a
special valid case meaning that benchmarking kthreads won't be bound to a
cpuset of a given node.

Found by Linux Verification Center (linuxtesting.org).

Fixes: 65789daa8087 ("dma-mapping: add benchmark support for streaming DMA APIs")
Signed-off-by: Fedor Pchelkin <pchelkin@ispras.ru>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 kernel/dma/map_benchmark.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/kernel/dma/map_benchmark.c b/kernel/dma/map_benchmark.c
index a6edb1ef98c8a..9f6c15f3f1681 100644
--- a/kernel/dma/map_benchmark.c
+++ b/kernel/dma/map_benchmark.c
@@ -212,7 +212,8 @@ static long map_benchmark_ioctl(struct file *file, unsigned int cmd,
 		}
 
 		if (map->bparam.node != NUMA_NO_NODE &&
-		    !node_possible(map->bparam.node)) {
+		    (map->bparam.node < 0 || map->bparam.node >= MAX_NUMNODES ||
+		     !node_possible(map->bparam.node))) {
 			pr_err("invalid numa node\n");
 			return -EINVAL;
 		}
-- 
GitLab


From e64746e74f717961250a155e14c156616fcd981f Mon Sep 17 00:00:00 2001
From: Fedor Pchelkin <pchelkin@ispras.ru>
Date: Sat, 4 May 2024 14:47:04 +0300
Subject: [PATCH 171/950] dma-mapping: benchmark: handle NUMA_NO_NODE correctly

cpumask_of_node() can be called for NUMA_NO_NODE inside do_map_benchmark()
resulting in the following sanitizer report:

UBSAN: array-index-out-of-bounds in ./arch/x86/include/asm/topology.h:72:28
index -1 is out of range for type 'cpumask [64][1]'
CPU: 1 PID: 990 Comm: dma_map_benchma Not tainted 6.9.0-rc6 #29
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996)
Call Trace:
 <TASK>
dump_stack_lvl (lib/dump_stack.c:117)
ubsan_epilogue (lib/ubsan.c:232)
__ubsan_handle_out_of_bounds (lib/ubsan.c:429)
cpumask_of_node (arch/x86/include/asm/topology.h:72) [inline]
do_map_benchmark (kernel/dma/map_benchmark.c:104)
map_benchmark_ioctl (kernel/dma/map_benchmark.c:246)
full_proxy_unlocked_ioctl (fs/debugfs/file.c:333)
__x64_sys_ioctl (fs/ioctl.c:890)
do_syscall_64 (arch/x86/entry/common.c:83)
entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130)

Use cpumask_of_node() in place when binding a kernel thread to a cpuset
of a particular node.

Note that the provided node id is checked inside map_benchmark_ioctl().
It's just a NUMA_NO_NODE case which is not handled properly later.

Found by Linux Verification Center (linuxtesting.org).

Fixes: 65789daa8087 ("dma-mapping: add benchmark support for streaming DMA APIs")
Signed-off-by: Fedor Pchelkin <pchelkin@ispras.ru>
Acked-by: Barry Song <baohua@kernel.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 kernel/dma/map_benchmark.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/kernel/dma/map_benchmark.c b/kernel/dma/map_benchmark.c
index 9f6c15f3f1681..4950e0b622b1f 100644
--- a/kernel/dma/map_benchmark.c
+++ b/kernel/dma/map_benchmark.c
@@ -101,7 +101,6 @@ static int do_map_benchmark(struct map_benchmark_data *map)
 	struct task_struct **tsk;
 	int threads = map->bparam.threads;
 	int node = map->bparam.node;
-	const cpumask_t *cpu_mask = cpumask_of_node(node);
 	u64 loops;
 	int ret = 0;
 	int i;
@@ -124,7 +123,7 @@ static int do_map_benchmark(struct map_benchmark_data *map)
 		}
 
 		if (node != NUMA_NO_NODE)
-			kthread_bind_mask(tsk[i], cpu_mask);
+			kthread_bind_mask(tsk[i], cpumask_of_node(node));
 	}
 
 	/* clear the old value in the previous benchmark */
-- 
GitLab


From 803482f472ccc9576c0e606143725d1d8c61019d Mon Sep 17 00:00:00 2001
From: Isaku Yamahata <isaku.yamahata@intel.com>
Date: Fri, 17 May 2024 17:04:22 -0700
Subject: [PATCH 172/950] KVM: x86/mmu: Use SHADOW_NONPRESENT_VALUE for atomic
 zap in TDP MMU

Use SHADOW_NONPRESENT_VALUE when zapping TDP MMU SPTEs with mmu_lock held
for read, tdp_mmu_zap_spte_atomic() was simply missed during the initial
development.

Fixes: 7f01cab84928 ("KVM: x86/mmu: Allow non-zero value for non-present SPTE and removed SPTE")
Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com>
[sean: write changelog]
Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Kai Huang <kai.huang@intel.com>
Message-ID: <20240518000430.1118488-2-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/tdp_mmu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 1259dd63defc8..36539c1b36cd6 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -626,7 +626,7 @@ static inline int tdp_mmu_zap_spte_atomic(struct kvm *kvm,
 	 * SPTEs.
 	 */
 	handle_changed_spte(kvm, iter->as_id, iter->gfn, iter->old_spte,
-			    0, iter->level, true);
+			    SHADOW_NONPRESENT_VALUE, iter->level, true);
 
 	return 0;
 }
-- 
GitLab


From 40e8a6901a2c983e3e541a363865e02cf591d458 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 17 May 2024 17:04:28 -0700
Subject: [PATCH 173/950] KVM: VMX: Don't kill the VM on an unexpected #VE

Don't terminate the VM on an unexpected #VE, as it's extremely unlikely
the #VE is fatal to the guest, and even less likely that it presents a
danger to the host.  Simply resume the guest on "failure", as the #VE info
page's BUSY field will prevent converting any more EPT Violations to #VEs
for the vCPU (at least, that's what the BUSY field is supposed to do).

Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-ID: <20240518000430.1118488-8-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/vmx/vmx.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 51b2cd13250a2..069fbbc1e04a0 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -5217,8 +5217,8 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu)
 	if (is_invalid_opcode(intr_info))
 		return handle_ud(vcpu);
 
-	if (KVM_BUG_ON(is_ve_fault(intr_info), vcpu->kvm))
-		return -EIO;
+	if (WARN_ON_ONCE(is_ve_fault(intr_info)))
+		return 1;
 
 	error_code = 0;
 	if (intr_info & INTR_INFO_DELIVER_CODE_MASK)
-- 
GitLab


From d1b32ecdc8ad0346ac551866d9f6831995fd70de Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 17 May 2024 17:04:23 -0700
Subject: [PATCH 174/950] KVM: nVMX: Initialize #VE info page for vmcs02 when
 proving #VE support

Point vmcs02.VE_INFORMATION_ADDRESS at the vCPU's #VE info page when
initializing vmcs02, otherwise KVM will run L2 with EPT Violation #VE
enabled and a VE info address pointing at pfn 0.

Fixes: 8131cf5b4fd8 ("KVM: VMX: Introduce test mode related to EPT violation VE")
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-ID: <20240518000430.1118488-3-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/vmx/nested.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index d5b832126e345..6798fadaa3350 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -2242,6 +2242,9 @@ static void prepare_vmcs02_constant_state(struct vcpu_vmx *vmx)
 		vmcs_write64(EPT_POINTER,
 			     construct_eptp(&vmx->vcpu, 0, PT64_ROOT_4LEVEL));
 
+	if (vmx->ve_info)
+		vmcs_write64(VE_INFORMATION_ADDRESS, __pa(vmx->ve_info));
+
 	/* All VMFUNCs are currently emulated through L0 vmexits.  */
 	if (cpu_has_vmx_vmfunc())
 		vmcs_write64(VM_FUNCTION_CONTROL, 0);
-- 
GitLab


From 9031b42139b9d45ef806c9a7fee166c1b6443c3c Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 17 May 2024 17:04:24 -0700
Subject: [PATCH 175/950] KVM: nVMX: Always handle #VEs in L0 (never forward
 #VEs from L2 to L1)

Always handle #VEs, e.g. due to prove EPT Violation #VE failures, in L0,
as KVM does not expose any #VE capabilities to L1, i.e. any and all #VEs
are KVM's responsibility.

Fixes: 8131cf5b4fd8 ("KVM: VMX: Introduce test mode related to EPT violation VE")
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-ID: <20240518000430.1118488-4-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/vmx/nested.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 6798fadaa3350..643935a0f70ab 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -6233,6 +6233,8 @@ static bool nested_vmx_l0_wants_exit(struct kvm_vcpu *vcpu,
 		else if (is_alignment_check(intr_info) &&
 			 !vmx_guest_inject_ac(vcpu))
 			return true;
+		else if (is_ve_fault(intr_info))
+			return true;
 		return false;
 	case EXIT_REASON_EXTERNAL_INTERRUPT:
 		return true;
-- 
GitLab


From 837d557aba6b816985141ddbeb7649444ed26d3b Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 17 May 2024 17:04:25 -0700
Subject: [PATCH 176/950] KVM: x86/mmu: Add sanity checks that KVM doesn't
 create EPT #VE SPTEs

Assert that KVM doesn't set a SPTE to a value that could trigger an EPT
Violation #VE on a non-MMIO SPTE, e.g. to help detect bugs even without
KVM_INTEL_PROVE_VE enabled, and to help debug actual #VE failures.

Note, this will run afoul of TDX support, which needs to reflect emulated
MMIO accesses into the guest as #VEs (which was the whole point of adding
EPT Violation #VE support in KVM).  The obvious fix for that is to exempt
MMIO SPTEs, but that's annoyingly difficult now that is_mmio_spte() relies
on a per-VM value.  However, resolving that conundrum is a future problem,
whereas getting KVM_INTEL_PROVE_VE healthy is a current problem.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-ID: <20240518000430.1118488-5-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/mmu.c      | 3 +++
 arch/x86/kvm/mmu/spte.h     | 9 +++++++++
 arch/x86/kvm/mmu/tdp_iter.h | 2 ++
 3 files changed, 14 insertions(+)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 662f62dfb2aa9..1ae1c1328268b 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -336,16 +336,19 @@ static int is_cpuid_PSE36(void)
 #ifdef CONFIG_X86_64
 static void __set_spte(u64 *sptep, u64 spte)
 {
+	KVM_MMU_WARN_ON(is_ept_ve_possible(spte));
 	WRITE_ONCE(*sptep, spte);
 }
 
 static void __update_clear_spte_fast(u64 *sptep, u64 spte)
 {
+	KVM_MMU_WARN_ON(is_ept_ve_possible(spte));
 	WRITE_ONCE(*sptep, spte);
 }
 
 static u64 __update_clear_spte_slow(u64 *sptep, u64 spte)
 {
+	KVM_MMU_WARN_ON(is_ept_ve_possible(spte));
 	return xchg(sptep, spte);
 }
 
diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h
index 5dd5405fa07ac..52fa004a1fbc9 100644
--- a/arch/x86/kvm/mmu/spte.h
+++ b/arch/x86/kvm/mmu/spte.h
@@ -3,6 +3,8 @@
 #ifndef KVM_X86_MMU_SPTE_H
 #define KVM_X86_MMU_SPTE_H
 
+#include <asm/vmx.h>
+
 #include "mmu.h"
 #include "mmu_internal.h"
 
@@ -276,6 +278,13 @@ static inline bool is_shadow_present_pte(u64 pte)
 	return !!(pte & SPTE_MMU_PRESENT_MASK);
 }
 
+static inline bool is_ept_ve_possible(u64 spte)
+{
+	return (shadow_present_mask & VMX_EPT_SUPPRESS_VE_BIT) &&
+	       !(spte & VMX_EPT_SUPPRESS_VE_BIT) &&
+	       (spte & VMX_EPT_RWX_MASK) != VMX_EPT_MISCONFIG_WX_VALUE;
+}
+
 /*
  * Returns true if A/D bits are supported in hardware and are enabled by KVM.
  * When enabled, KVM uses A/D bits for all non-nested MMUs.  Because L1 can
diff --git a/arch/x86/kvm/mmu/tdp_iter.h b/arch/x86/kvm/mmu/tdp_iter.h
index fae559559a806..2880fd392e0cb 100644
--- a/arch/x86/kvm/mmu/tdp_iter.h
+++ b/arch/x86/kvm/mmu/tdp_iter.h
@@ -21,11 +21,13 @@ static inline u64 kvm_tdp_mmu_read_spte(tdp_ptep_t sptep)
 
 static inline u64 kvm_tdp_mmu_write_spte_atomic(tdp_ptep_t sptep, u64 new_spte)
 {
+	KVM_MMU_WARN_ON(is_ept_ve_possible(new_spte));
 	return xchg(rcu_dereference(sptep), new_spte);
 }
 
 static inline void __kvm_tdp_mmu_write_spte(tdp_ptep_t sptep, u64 new_spte)
 {
+	KVM_MMU_WARN_ON(is_ept_ve_possible(new_spte));
 	WRITE_ONCE(*rcu_dereference(sptep), new_spte);
 }
 
-- 
GitLab


From 743f1773366461cb44de297b1caf0a4292eb8fda Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 17 May 2024 17:04:26 -0700
Subject: [PATCH 177/950] KVM: VMX: Dump VMCS on unexpected #VE

Dump the VMCS on an unexpected #VE, otherwise it's practically impossible
to figure out why the #VE occurred.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-ID: <20240518000430.1118488-6-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/vmx/vmx.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 069fbbc1e04a0..a02b2720023a3 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -5217,8 +5217,10 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu)
 	if (is_invalid_opcode(intr_info))
 		return handle_ud(vcpu);
 
-	if (WARN_ON_ONCE(is_ve_fault(intr_info)))
+	if (WARN_ON_ONCE(is_ve_fault(intr_info))) {
+		dump_vmcs(vcpu);
 		return 1;
+	}
 
 	error_code = 0;
 	if (intr_info & INTR_INFO_DELIVER_CODE_MASK)
-- 
GitLab


From bca99c0356524a620126b789edbaf25934415467 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 17 May 2024 17:04:27 -0700
Subject: [PATCH 178/950] KVM: x86/mmu: Print SPTEs on unexpected #VE

Print the SPTEs that correspond to the faulting GPA on an unexpected EPT
Violation #VE to help the user debug failures, e.g. to pinpoint which SPTE
didn't have SUPPRESS_VE set.

Opportunistically assert that the underlying exit reason was indeed an EPT
Violation, as the CPU has *really* gone off the rails if a #VE occurs due
to a completely unexpected exit reason.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-ID: <20240518000430.1118488-7-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/include/asm/kvm_host.h |  1 +
 arch/x86/kvm/mmu/mmu.c          | 40 ++++++++++++++++++++++++++-------
 arch/x86/kvm/vmx/vmx.c          |  5 +++++
 3 files changed, 38 insertions(+), 8 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index ece45b3f6f207..f8ca74e7678f3 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -2154,6 +2154,7 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu);
 
 int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code,
 		       void *insn, int insn_len);
+void kvm_mmu_print_sptes(struct kvm_vcpu *vcpu, gpa_t gpa, const char *msg);
 void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva);
 void kvm_mmu_invalidate_addr(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 			     u64 addr, unsigned long roots);
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 1ae1c1328268b..b7b4426a7221d 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -4104,23 +4104,31 @@ static int get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, int *root_level
 	return leaf;
 }
 
-/* return true if reserved bit(s) are detected on a valid, non-MMIO SPTE. */
-static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep)
+static int get_sptes_lockless(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes,
+			      int *root_level)
 {
-	u64 sptes[PT64_ROOT_MAX_LEVEL + 1];
-	struct rsvd_bits_validate *rsvd_check;
-	int root, leaf, level;
-	bool reserved = false;
+	int leaf;
 
 	walk_shadow_page_lockless_begin(vcpu);
 
 	if (is_tdp_mmu_active(vcpu))
-		leaf = kvm_tdp_mmu_get_walk(vcpu, addr, sptes, &root);
+		leaf = kvm_tdp_mmu_get_walk(vcpu, addr, sptes, root_level);
 	else
-		leaf = get_walk(vcpu, addr, sptes, &root);
+		leaf = get_walk(vcpu, addr, sptes, root_level);
 
 	walk_shadow_page_lockless_end(vcpu);
+	return leaf;
+}
 
+/* return true if reserved bit(s) are detected on a valid, non-MMIO SPTE. */
+static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep)
+{
+	u64 sptes[PT64_ROOT_MAX_LEVEL + 1];
+	struct rsvd_bits_validate *rsvd_check;
+	int root, leaf, level;
+	bool reserved = false;
+
+	leaf = get_sptes_lockless(vcpu, addr, sptes, &root);
 	if (unlikely(leaf < 0)) {
 		*sptep = 0ull;
 		return reserved;
@@ -5924,6 +5932,22 @@ emulate:
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_page_fault);
 
+void kvm_mmu_print_sptes(struct kvm_vcpu *vcpu, gpa_t gpa, const char *msg)
+{
+	u64 sptes[PT64_ROOT_MAX_LEVEL + 1];
+	int root_level, leaf, level;
+
+	leaf = get_sptes_lockless(vcpu, gpa, sptes, &root_level);
+	if (unlikely(leaf < 0))
+		return;
+
+	pr_err("%s %llx", msg, gpa);
+	for (level = root_level; level >= leaf; level--)
+		pr_cont(", spte[%d] = 0x%llx", level, sptes[level]);
+	pr_cont("\n");
+}
+EXPORT_SYMBOL_GPL(kvm_mmu_print_sptes);
+
 static void __kvm_mmu_invalidate_addr(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 				      u64 addr, hpa_t root_hpa)
 {
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index a02b2720023a3..58832aae22487 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -5218,7 +5218,12 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu)
 		return handle_ud(vcpu);
 
 	if (WARN_ON_ONCE(is_ve_fault(intr_info))) {
+		struct vmx_ve_information *ve_info = vmx->ve_info;
+
+		WARN_ONCE(ve_info->exit_reason != EXIT_REASON_EPT_VIOLATION,
+			  "Unexpected #VE on VM-Exit reason 0x%x", ve_info->exit_reason);
 		dump_vmcs(vcpu);
+		kvm_mmu_print_sptes(vcpu, ve_info->guest_physical_address, "#VE");
 		return 1;
 	}
 
-- 
GitLab


From a5dc0c9b557573315633bc78bacf8f548352f95b Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 17 May 2024 17:04:29 -0700
Subject: [PATCH 179/950] KVM: VMX: Enumerate EPT Violation #VE support in
 /proc/cpuinfo

Don't suppress printing EPT_VIOLATION_VE in /proc/cpuinfo, knowing whether
or not KVM_INTEL_PROVE_VE actually does anything is extremely valuable.
A privileged user can get at the information by reading the raw MSR, but
the whole point of the VMX flags is to avoid needing to glean information
from raw MSR reads.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-ID: <20240518000430.1118488-9-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/include/asm/vmxfeatures.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/vmxfeatures.h b/arch/x86/include/asm/vmxfeatures.h
index 266daf5b5b842..695f366648899 100644
--- a/arch/x86/include/asm/vmxfeatures.h
+++ b/arch/x86/include/asm/vmxfeatures.h
@@ -77,7 +77,7 @@
 #define VMX_FEATURE_ENCLS_EXITING	( 2*32+ 15) /* "" VM-Exit on ENCLS (leaf dependent) */
 #define VMX_FEATURE_RDSEED_EXITING	( 2*32+ 16) /* "" VM-Exit on RDSEED */
 #define VMX_FEATURE_PAGE_MOD_LOGGING	( 2*32+ 17) /* "pml" Log dirty pages into buffer */
-#define VMX_FEATURE_EPT_VIOLATION_VE	( 2*32+ 18) /* "" Conditionally reflect EPT violations as #VE exceptions */
+#define VMX_FEATURE_EPT_VIOLATION_VE	( 2*32+ 18) /* Conditionally reflect EPT violations as #VE exceptions */
 #define VMX_FEATURE_PT_CONCEAL_VMX	( 2*32+ 19) /* "" Suppress VMX indicators in Processor Trace */
 #define VMX_FEATURE_XSAVES		( 2*32+ 20) /* "" Enable XSAVES and XRSTORS in guest */
 #define VMX_FEATURE_MODE_BASED_EPT_EXEC	( 2*32+ 22) /* "ept_mode_based_exec" Enable separate EPT EXEC bits for supervisor vs. user */
-- 
GitLab


From 6af6142e3a62efd6074905e4a94d64956a3f4b7c Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 17 May 2024 17:04:30 -0700
Subject: [PATCH 180/950] KVM: x86: Disable KVM_INTEL_PROVE_VE by default

Disable KVM's "prove #VE" support by default, as it provides no functional
value, and even its sanity checking benefits are relatively limited.  I.e.
it should be fully opt-in even on debug kernels, especially since EPT
Violation #VE suppression appears to be buggy on some CPUs.

Opportunistically add a line in the help text to make it abundantly clear
that KVM_INTEL_PROVE_VE should never be enabled in a production
environment.

Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-ID: <20240518000430.1118488-10-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/Kconfig | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index d64fb2b3eb69e..7f47233ddf46c 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -97,15 +97,17 @@ config KVM_INTEL
 
 config KVM_INTEL_PROVE_VE
         bool "Check that guests do not receive #VE exceptions"
-        default KVM_PROVE_MMU || DEBUG_KERNEL
-        depends on KVM_INTEL
+        depends on KVM_INTEL && EXPERT
         help
-
           Checks that KVM's page table management code will not incorrectly
           let guests receive a virtualization exception.  Virtualization
           exceptions will be trapped by the hypervisor rather than injected
           in the guest.
 
+          Note: some CPUs appear to generate spurious EPT Violations #VEs
+          that trigger KVM's WARN, in particular with eptad=0 and/or nested
+          virtualization.
+
           If unsure, say N.
 
 config X86_SGX_KVM
-- 
GitLab


From 76d5363c20eeeb937b56c0ac6c61e697bd1bf154 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 17 May 2024 11:03:41 -0700
Subject: [PATCH 181/950] KVM: x86: Force KVM_WERROR if the global WERROR is
 enabled

Force KVM_WERROR if the global WERROR is enabled to avoid pestering the
user about a Kconfig that will ultimately be ignored.  Force KVM_WERROR
instead of making it mutually exclusive with WERROR to avoid generating a
.config builds KVM with -Werror, but has KVM_WERROR=n.

Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-ID: <20240517180341.974251-1-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/Kconfig | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 7f47233ddf46c..fec95a7702703 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -44,6 +44,7 @@ config KVM
 	select KVM_VFIO
 	select HAVE_KVM_PM_NOTIFIER if PM
 	select KVM_GENERIC_HARDWARE_ENABLING
+	select KVM_WERROR if WERROR
 	help
 	  Support hosting fully virtualized guest machines using hardware
 	  virtualization extensions.  You will need a fairly recent
@@ -66,7 +67,7 @@ config KVM_WERROR
 	# FRAME_WARN, i.e. KVM_WERROR=y with KASAN=y requires special tuning.
 	# Building KVM with -Werror and KASAN is still doable via enabling
 	# the kernel-wide WERROR=y.
-	depends on KVM && EXPERT && !KASAN
+	depends on KVM && ((EXPERT && !KASAN) || WERROR)
 	help
 	  Add -Werror to the build flags for KVM.
 
-- 
GitLab


From b4bd556467477420ee3a91fbcba73c579669edc6 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 21 May 2024 19:14:35 -0700
Subject: [PATCH 182/950] KVM: SVM: WARN on vNMI + NMI window iff NMIs are
 outright masked

When requesting an NMI window, WARN on vNMI support being enabled if and
only if NMIs are actually masked, i.e. if the vCPU is already handling an
NMI.  KVM's ABI for NMIs that arrive simultanesouly (from KVM's point of
view) is to inject one NMI and pend the other.  When using vNMI, KVM pends
the second NMI simply by setting V_NMI_PENDING, and lets the CPU do the
rest (hardware automatically sets V_NMI_BLOCKING when an NMI is injected).

However, if KVM can't immediately inject an NMI, e.g. because the vCPU is
in an STI shadow or is running with GIF=0, then KVM will request an NMI
window and trigger the WARN (but still function correctly).

Whether or not the GIF=0 case makes sense is debatable, as the intent of
KVM's behavior is to provide functionality that is as close to real
hardware as possible.  E.g. if two NMIs are sent in quick succession, the
probability of both NMIs arriving in an STI shadow is infinitesimally low
on real hardware, but significantly larger in a virtual environment, e.g.
if the vCPU is preempted in the STI shadow.  For GIF=0, the argument isn't
as clear cut, because the window where two NMIs can collide is much larger
in bare metal (though still small).

That said, KVM should not have divergent behavior for the GIF=0 case based
on whether or not vNMI support is enabled.  And KVM has allowed
simultaneous NMIs with GIF=0 for over a decade, since commit 7460fb4a3400
("KVM: Fix simultaneous NMIs").  I.e. KVM's GIF=0 handling shouldn't be
modified without a *really* good reason to do so, and if KVM's behavior
were to be modified, it should be done irrespective of vNMI support.

Fixes: fa4c027a7956 ("KVM: x86: Add support for SVM's Virtual NMI")
Cc: stable@vger.kernel.org
Cc: Santosh Shukla <Santosh.Shukla@amd.com>
Cc: Maxim Levitsky <mlevitsk@redhat.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-ID: <20240522021435.1684366-1-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/svm/svm.c | 27 +++++++++++++++++++--------
 1 file changed, 19 insertions(+), 8 deletions(-)

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index c8dc25886c165..1d3c8be39479b 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -3846,16 +3846,27 @@ static void svm_enable_nmi_window(struct kvm_vcpu *vcpu)
 	struct vcpu_svm *svm = to_svm(vcpu);
 
 	/*
-	 * KVM should never request an NMI window when vNMI is enabled, as KVM
-	 * allows at most one to-be-injected NMI and one pending NMI, i.e. if
-	 * two NMIs arrive simultaneously, KVM will inject one and set
-	 * V_NMI_PENDING for the other.  WARN, but continue with the standard
-	 * single-step approach to try and salvage the pending NMI.
+	 * If NMIs are outright masked, i.e. the vCPU is already handling an
+	 * NMI, and KVM has not yet intercepted an IRET, then there is nothing
+	 * more to do at this time as KVM has already enabled IRET intercepts.
+	 * If KVM has already intercepted IRET, then single-step over the IRET,
+	 * as NMIs aren't architecturally unmasked until the IRET completes.
+	 *
+	 * If vNMI is enabled, KVM should never request an NMI window if NMIs
+	 * are masked, as KVM allows at most one to-be-injected NMI and one
+	 * pending NMI.  If two NMIs arrive simultaneously, KVM will inject one
+	 * NMI and set V_NMI_PENDING for the other, but if and only if NMIs are
+	 * unmasked.  KVM _will_ request an NMI window in some situations, e.g.
+	 * if the vCPU is in an STI shadow or if GIF=0, KVM can't immediately
+	 * inject the NMI.  In those situations, KVM needs to single-step over
+	 * the STI shadow or intercept STGI.
 	 */
-	WARN_ON_ONCE(is_vnmi_enabled(svm));
+	if (svm_get_nmi_mask(vcpu)) {
+		WARN_ON_ONCE(is_vnmi_enabled(svm));
 
-	if (svm_get_nmi_mask(vcpu) && !svm->awaiting_iret_completion)
-		return; /* IRET will cause a vm exit */
+		if (!svm->awaiting_iret_completion)
+			return; /* IRET will cause a vm exit */
+	}
 
 	/*
 	 * SEV-ES guests are responsible for signaling when a vCPU is ready to
-- 
GitLab


From 2fe7b422460d14b33027d8770f7be8d26bcb2639 Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Tue, 21 May 2024 09:50:47 -0700
Subject: [PATCH 183/950] nvme: fix multipath batched completion accounting

Batched completions were missing the io stats accounting and bio trace
events. Move the common code to a helper and call it from the batched
and non-batched functions.

Fixes: d4d957b53d91ee ("nvme-multipath: support io stats on the mpath device")
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/core.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 954f850f113a1..79cdd34dfa18e 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -414,6 +414,14 @@ static inline void nvme_end_req_zoned(struct request *req)
 	}
 }
 
+static inline void __nvme_end_req(struct request *req)
+{
+	nvme_end_req_zoned(req);
+	nvme_trace_bio_complete(req);
+	if (req->cmd_flags & REQ_NVME_MPATH)
+		nvme_mpath_end_request(req);
+}
+
 static inline void nvme_end_req(struct request *req)
 {
 	blk_status_t status = nvme_error_status(nvme_req(req)->status);
@@ -424,10 +432,7 @@ static inline void nvme_end_req(struct request *req)
 		else
 			nvme_log_error(req);
 	}
-	nvme_end_req_zoned(req);
-	nvme_trace_bio_complete(req);
-	if (req->cmd_flags & REQ_NVME_MPATH)
-		nvme_mpath_end_request(req);
+	__nvme_end_req(req);
 	blk_mq_end_request(req, status);
 }
 
@@ -476,7 +481,7 @@ void nvme_complete_batch_req(struct request *req)
 {
 	trace_nvme_complete_rq(req);
 	nvme_cleanup_cmd(req);
-	nvme_end_req_zoned(req);
+	__nvme_end_req(req);
 }
 EXPORT_SYMBOL_GPL(nvme_complete_batch_req);
 
-- 
GitLab


From a2e4c5f5f68dbd206f132bc709b98dea64afc3b8 Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Tue, 21 May 2024 11:02:28 -0700
Subject: [PATCH 184/950] nvme-multipath: fix io accounting on failover

There are io stats accounting that needs to be handled, so don't call
blk_mq_end_request() directly. Use the existing nvme_end_req() helper
that already handles everything.

Fixes: d4d957b53d91ee ("nvme-multipath: support io stats on the mpath device")
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/core.c      | 2 +-
 drivers/nvme/host/multipath.c | 3 ++-
 drivers/nvme/host/nvme.h      | 1 +
 3 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 79cdd34dfa18e..7706df2373494 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -422,7 +422,7 @@ static inline void __nvme_end_req(struct request *req)
 		nvme_mpath_end_request(req);
 }
 
-static inline void nvme_end_req(struct request *req)
+void nvme_end_req(struct request *req)
 {
 	blk_status_t status = nvme_error_status(nvme_req(req)->status);
 
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 9c1e135b8df3b..1bee176fd850e 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -118,7 +118,8 @@ void nvme_failover_req(struct request *req)
 	blk_steal_bios(&ns->head->requeue_list, req);
 	spin_unlock_irqrestore(&ns->head->requeue_lock, flags);
 
-	blk_mq_end_request(req, 0);
+	nvme_req(req)->status = 0;
+	nvme_end_req(req);
 	kblockd_schedule_work(&ns->head->requeue_work);
 }
 
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index cacc56f4bbf44..fc31bd340a63a 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -767,6 +767,7 @@ static inline bool nvme_state_terminal(struct nvme_ctrl *ctrl)
 	}
 }
 
+void nvme_end_req(struct request *req);
 void nvme_complete_rq(struct request *req);
 void nvme_complete_batch_req(struct request *req);
 
-- 
GitLab


From f97914e35fd98b2b18fb8a092e0a0799f73afdfe Mon Sep 17 00:00:00 2001
From: Sagi Grimberg <sagi@grimberg.me>
Date: Tue, 21 May 2024 23:20:28 +0300
Subject: [PATCH 185/950] nvmet: fix ns enable/disable possible hang

When disabling an nvmet namespace, there is a period where the
subsys->lock is released, as the ns disable waits for backend IO to
complete, and the ns percpu ref to be properly killed. The original
intent was to avoid taking the subsystem lock for a prolong period as
other processes may need to acquire it (for example new incoming
connections).

However, it opens up a window where another process may come in and
enable the ns, (re)intiailizing the ns percpu_ref, causing the disable
sequence to hang.

Solve this by taking the global nvmet_config_sem over the entire configfs
enable/disable sequence.

Fixes: a07b4970f464 ("nvmet: add a generic NVMe target")
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/target/configfs.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c
index 7c43a0ad68771..bd87dfd173a4c 100644
--- a/drivers/nvme/target/configfs.c
+++ b/drivers/nvme/target/configfs.c
@@ -676,10 +676,18 @@ static ssize_t nvmet_ns_enable_store(struct config_item *item,
 	if (kstrtobool(page, &enable))
 		return -EINVAL;
 
+	/*
+	 * take a global nvmet_config_sem because the disable routine has a
+	 * window where it releases the subsys-lock, giving a chance to
+	 * a parallel enable to concurrently execute causing the disable to
+	 * have a misaccounting of the ns percpu_ref.
+	 */
+	down_write(&nvmet_config_sem);
 	if (enable)
 		ret = nvmet_ns_enable(ns);
 	else
 		nvmet_ns_disable(ns);
+	up_write(&nvmet_config_sem);
 
 	return ret ? ret : count;
 }
-- 
GitLab


From 4d25ca2d6801cfcf26f7f39c561611ba5be99bf8 Mon Sep 17 00:00:00 2001
From: Abhishek Chauhan <quic_abchauha@quicinc.com>
Date: Thu, 9 May 2024 14:18:32 -0700
Subject: [PATCH 186/950] net: Rename mono_delivery_time to tstamp_type for
 scalabilty

mono_delivery_time was added to check if skb->tstamp has delivery
time in mono clock base (i.e. EDT) otherwise skb->tstamp has
timestamp in ingress and delivery_time at egress.

Renaming the bitfield from mono_delivery_time to tstamp_type is for
extensibilty for other timestamps such as userspace timestamp
(i.e. SO_TXTIME) set via sock opts.

As we are renaming the mono_delivery_time to tstamp_type, it makes
sense to start assigning tstamp_type based on enum defined
in this commit.

Earlier we used bool arg flag to check if the tstamp is mono in
function skb_set_delivery_time, Now the signature of the functions
accepts tstamp_type to distinguish between mono and real time.

Also skb_set_delivery_type_by_clockid is a new function which accepts
clockid to determine the tstamp_type.

In future tstamp_type:1 can be extended to support userspace timestamp
by increasing the bitfield.

Signed-off-by: Abhishek Chauhan <quic_abchauha@quicinc.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://lore.kernel.org/r/20240509211834.3235191-2-quic_abchauha@quicinc.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 include/linux/skbuff.h                     | 52 ++++++++++++++++------
 include/net/inet_frag.h                    |  4 +-
 net/bridge/netfilter/nf_conntrack_bridge.c |  6 +--
 net/core/dev.c                             |  2 +-
 net/core/filter.c                          | 10 ++---
 net/ieee802154/6lowpan/reassembly.c        |  2 +-
 net/ipv4/inet_fragment.c                   |  2 +-
 net/ipv4/ip_fragment.c                     |  2 +-
 net/ipv4/ip_output.c                       |  9 ++--
 net/ipv4/tcp_output.c                      | 14 +++---
 net/ipv6/ip6_output.c                      |  6 +--
 net/ipv6/netfilter.c                       |  6 +--
 net/ipv6/netfilter/nf_conntrack_reasm.c    |  2 +-
 net/ipv6/reassembly.c                      |  2 +-
 net/ipv6/tcp_ipv6.c                        |  2 +-
 net/sched/act_bpf.c                        |  4 +-
 net/sched/cls_bpf.c                        |  4 +-
 17 files changed, 78 insertions(+), 51 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index c0b97c93a6de0..3a721cc3b6441 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -706,6 +706,11 @@ typedef unsigned int sk_buff_data_t;
 typedef unsigned char *sk_buff_data_t;
 #endif
 
+enum skb_tstamp_type {
+	SKB_CLOCK_REALTIME,
+	SKB_CLOCK_MONOTONIC,
+};
+
 /**
  * DOC: Basic sk_buff geometry
  *
@@ -823,10 +828,8 @@ typedef unsigned char *sk_buff_data_t;
  *	@dst_pending_confirm: need to confirm neighbour
  *	@decrypted: Decrypted SKB
  *	@slow_gro: state present at GRO time, slower prepare step required
- *	@mono_delivery_time: When set, skb->tstamp has the
- *		delivery_time in mono clock base (i.e. EDT).  Otherwise, the
- *		skb->tstamp has the (rcv) timestamp at ingress and
- *		delivery_time at egress.
+ *	@tstamp_type: When set, skb->tstamp has the
+ *		delivery_time clock base of skb->tstamp.
  *	@napi_id: id of the NAPI struct this skb came from
  *	@sender_cpu: (aka @napi_id) source CPU in XPS
  *	@alloc_cpu: CPU which did the skb allocation.
@@ -954,7 +957,7 @@ struct sk_buff {
 	/* private: */
 	__u8			__mono_tc_offset[0];
 	/* public: */
-	__u8			mono_delivery_time:1;	/* See SKB_MONO_DELIVERY_TIME_MASK */
+	__u8			tstamp_type:1;	/* See skb_tstamp_type */
 #ifdef CONFIG_NET_XGRESS
 	__u8			tc_at_ingress:1;	/* See TC_AT_INGRESS_MASK */
 	__u8			tc_skip_classify:1;
@@ -4183,7 +4186,7 @@ static inline void skb_get_new_timestampns(const struct sk_buff *skb,
 static inline void __net_timestamp(struct sk_buff *skb)
 {
 	skb->tstamp = ktime_get_real();
-	skb->mono_delivery_time = 0;
+	skb->tstamp_type = SKB_CLOCK_REALTIME;
 }
 
 static inline ktime_t net_timedelta(ktime_t t)
@@ -4192,10 +4195,33 @@ static inline ktime_t net_timedelta(ktime_t t)
 }
 
 static inline void skb_set_delivery_time(struct sk_buff *skb, ktime_t kt,
-					 bool mono)
+					 u8 tstamp_type)
 {
 	skb->tstamp = kt;
-	skb->mono_delivery_time = kt && mono;
+
+	if (kt)
+		skb->tstamp_type = tstamp_type;
+	else
+		skb->tstamp_type = SKB_CLOCK_REALTIME;
+}
+
+static inline void skb_set_delivery_type_by_clockid(struct sk_buff *skb,
+						    ktime_t kt, clockid_t clockid)
+{
+	u8 tstamp_type = SKB_CLOCK_REALTIME;
+
+	switch (clockid) {
+	case CLOCK_REALTIME:
+		break;
+	case CLOCK_MONOTONIC:
+		tstamp_type = SKB_CLOCK_MONOTONIC;
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		kt = 0;
+	}
+
+	skb_set_delivery_time(skb, kt, tstamp_type);
 }
 
 DECLARE_STATIC_KEY_FALSE(netstamp_needed_key);
@@ -4205,8 +4231,8 @@ DECLARE_STATIC_KEY_FALSE(netstamp_needed_key);
  */
 static inline void skb_clear_delivery_time(struct sk_buff *skb)
 {
-	if (skb->mono_delivery_time) {
-		skb->mono_delivery_time = 0;
+	if (skb->tstamp_type) {
+		skb->tstamp_type = SKB_CLOCK_REALTIME;
 		if (static_branch_unlikely(&netstamp_needed_key))
 			skb->tstamp = ktime_get_real();
 		else
@@ -4216,7 +4242,7 @@ static inline void skb_clear_delivery_time(struct sk_buff *skb)
 
 static inline void skb_clear_tstamp(struct sk_buff *skb)
 {
-	if (skb->mono_delivery_time)
+	if (skb->tstamp_type)
 		return;
 
 	skb->tstamp = 0;
@@ -4224,7 +4250,7 @@ static inline void skb_clear_tstamp(struct sk_buff *skb)
 
 static inline ktime_t skb_tstamp(const struct sk_buff *skb)
 {
-	if (skb->mono_delivery_time)
+	if (skb->tstamp_type)
 		return 0;
 
 	return skb->tstamp;
@@ -4232,7 +4258,7 @@ static inline ktime_t skb_tstamp(const struct sk_buff *skb)
 
 static inline ktime_t skb_tstamp_cond(const struct sk_buff *skb, bool cond)
 {
-	if (!skb->mono_delivery_time && skb->tstamp)
+	if (skb->tstamp_type != SKB_CLOCK_MONOTONIC && skb->tstamp)
 		return skb->tstamp;
 
 	if (static_branch_unlikely(&netstamp_needed_key) || cond)
diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index 153960663ce4c..5af6eb14c5db1 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -76,7 +76,7 @@ struct frag_v6_compare_key {
  * @stamp: timestamp of the last received fragment
  * @len: total length of the original datagram
  * @meat: length of received fragments so far
- * @mono_delivery_time: stamp has a mono delivery time (EDT)
+ * @tstamp_type: stamp has a mono delivery time (EDT)
  * @flags: fragment queue flags
  * @max_size: maximum received fragment size
  * @fqdir: pointer to struct fqdir
@@ -97,7 +97,7 @@ struct inet_frag_queue {
 	ktime_t			stamp;
 	int			len;
 	int			meat;
-	u8			mono_delivery_time;
+	u8			tstamp_type;
 	__u8			flags;
 	u16			max_size;
 	struct fqdir		*fqdir;
diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c
index c3c51b9a68265..816bb0fde718e 100644
--- a/net/bridge/netfilter/nf_conntrack_bridge.c
+++ b/net/bridge/netfilter/nf_conntrack_bridge.c
@@ -32,7 +32,7 @@ static int nf_br_ip_fragment(struct net *net, struct sock *sk,
 					   struct sk_buff *))
 {
 	int frag_max_size = BR_INPUT_SKB_CB(skb)->frag_max_size;
-	bool mono_delivery_time = skb->mono_delivery_time;
+	u8 tstamp_type = skb->tstamp_type;
 	unsigned int hlen, ll_rs, mtu;
 	ktime_t tstamp = skb->tstamp;
 	struct ip_frag_state state;
@@ -82,7 +82,7 @@ static int nf_br_ip_fragment(struct net *net, struct sock *sk,
 			if (iter.frag)
 				ip_fraglist_prepare(skb, &iter);
 
-			skb_set_delivery_time(skb, tstamp, mono_delivery_time);
+			skb_set_delivery_time(skb, tstamp, tstamp_type);
 			err = output(net, sk, data, skb);
 			if (err || !iter.frag)
 				break;
@@ -113,7 +113,7 @@ slow_path:
 			goto blackhole;
 		}
 
-		skb_set_delivery_time(skb2, tstamp, mono_delivery_time);
+		skb_set_delivery_time(skb2, tstamp, tstamp_type);
 		err = output(net, sk, data, skb2);
 		if (err)
 			goto blackhole;
diff --git a/net/core/dev.c b/net/core/dev.c
index e1bb6d7856d92..85fe8138f3e4e 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2160,7 +2160,7 @@ EXPORT_SYMBOL(net_disable_timestamp);
 static inline void net_timestamp_set(struct sk_buff *skb)
 {
 	skb->tstamp = 0;
-	skb->mono_delivery_time = 0;
+	skb->tstamp_type = SKB_CLOCK_REALTIME;
 	if (static_branch_unlikely(&netstamp_needed_key))
 		skb->tstamp = ktime_get_real();
 }
diff --git a/net/core/filter.c b/net/core/filter.c
index 2510464692af0..a3781a796da4d 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -7730,13 +7730,13 @@ BPF_CALL_3(bpf_skb_set_tstamp, struct sk_buff *, skb,
 		if (!tstamp)
 			return -EINVAL;
 		skb->tstamp = tstamp;
-		skb->mono_delivery_time = 1;
+		skb->tstamp_type = SKB_CLOCK_MONOTONIC;
 		break;
 	case BPF_SKB_TSTAMP_UNSPEC:
 		if (tstamp)
 			return -EINVAL;
 		skb->tstamp = 0;
-		skb->mono_delivery_time = 0;
+		skb->tstamp_type = SKB_CLOCK_REALTIME;
 		break;
 	default:
 		return -EINVAL;
@@ -9443,7 +9443,7 @@ static struct bpf_insn *bpf_convert_tstamp_read(const struct bpf_prog *prog,
 					TC_AT_INGRESS_MASK | SKB_MONO_DELIVERY_TIME_MASK);
 		*insn++ = BPF_JMP32_IMM(BPF_JNE, tmp_reg,
 					TC_AT_INGRESS_MASK | SKB_MONO_DELIVERY_TIME_MASK, 2);
-		/* skb->tc_at_ingress && skb->mono_delivery_time,
+		/* skb->tc_at_ingress && skb->tstamp_type,
 		 * read 0 as the (rcv) timestamp.
 		 */
 		*insn++ = BPF_MOV64_IMM(value_reg, 0);
@@ -9468,7 +9468,7 @@ static struct bpf_insn *bpf_convert_tstamp_write(const struct bpf_prog *prog,
 	 * the bpf prog is aware the tstamp could have delivery time.
 	 * Thus, write skb->tstamp as is if tstamp_type_access is true.
 	 * Otherwise, writing at ingress will have to clear the
-	 * mono_delivery_time bit also.
+	 * skb->tstamp_type bit also.
 	 */
 	if (!prog->tstamp_type_access) {
 		__u8 tmp_reg = BPF_REG_AX;
@@ -9478,7 +9478,7 @@ static struct bpf_insn *bpf_convert_tstamp_write(const struct bpf_prog *prog,
 		*insn++ = BPF_JMP32_IMM(BPF_JSET, tmp_reg, TC_AT_INGRESS_MASK, 1);
 		/* goto <store> */
 		*insn++ = BPF_JMP_A(2);
-		/* <clear>: mono_delivery_time */
+		/* <clear>: skb->tstamp_type */
 		*insn++ = BPF_ALU32_IMM(BPF_AND, tmp_reg, ~SKB_MONO_DELIVERY_TIME_MASK);
 		*insn++ = BPF_STX_MEM(BPF_B, skb_reg, tmp_reg, SKB_BF_MONO_TC_OFFSET);
 	}
diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c
index 56ef873828f40..867d637d86f08 100644
--- a/net/ieee802154/6lowpan/reassembly.c
+++ b/net/ieee802154/6lowpan/reassembly.c
@@ -130,7 +130,7 @@ static int lowpan_frag_queue(struct lowpan_frag_queue *fq,
 		goto err;
 
 	fq->q.stamp = skb->tstamp;
-	fq->q.mono_delivery_time = skb->mono_delivery_time;
+	fq->q.tstamp_type = skb->tstamp_type;
 	if (frag_type == LOWPAN_DISPATCH_FRAG1)
 		fq->q.flags |= INET_FRAG_FIRST_IN;
 
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index faaec92a46ac0..d179a2c842227 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -619,7 +619,7 @@ void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head,
 	skb_mark_not_on_list(head);
 	head->prev = NULL;
 	head->tstamp = q->stamp;
-	head->mono_delivery_time = q->mono_delivery_time;
+	head->tstamp_type = q->tstamp_type;
 
 	if (sk)
 		refcount_add(sum_truesize - head_truesize, &sk->sk_wmem_alloc);
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 08e2c92e25ab5..a92664a5ef2ef 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -355,7 +355,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
 		qp->iif = dev->ifindex;
 
 	qp->q.stamp = skb->tstamp;
-	qp->q.mono_delivery_time = skb->mono_delivery_time;
+	qp->q.tstamp_type = skb->tstamp_type;
 	qp->q.meat += skb->len;
 	qp->ecn |= ecn;
 	add_frag_mem_limit(qp->q.fqdir, skb->truesize);
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 9500031a1f55b..fe86cadfa85b6 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -764,7 +764,7 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 {
 	struct iphdr *iph;
 	struct sk_buff *skb2;
-	bool mono_delivery_time = skb->mono_delivery_time;
+	u8 tstamp_type = skb->tstamp_type;
 	struct rtable *rt = skb_rtable(skb);
 	unsigned int mtu, hlen, ll_rs;
 	struct ip_fraglist_iter iter;
@@ -856,7 +856,7 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 				}
 			}
 
-			skb_set_delivery_time(skb, tstamp, mono_delivery_time);
+			skb_set_delivery_time(skb, tstamp, tstamp_type);
 			err = output(net, sk, skb);
 
 			if (!err)
@@ -912,7 +912,7 @@ slow_path:
 		/*
 		 *	Put this fragment into the sending queue.
 		 */
-		skb_set_delivery_time(skb2, tstamp, mono_delivery_time);
+		skb_set_delivery_time(skb2, tstamp, tstamp_type);
 		err = output(net, sk, skb2);
 		if (err)
 			goto fail;
@@ -1649,7 +1649,8 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
 			  arg->csumoffset) = csum_fold(csum_add(nskb->csum,
 								arg->csum));
 		nskb->ip_summed = CHECKSUM_NONE;
-		nskb->mono_delivery_time = !!transmit_time;
+		if (transmit_time)
+			nskb->tstamp_type = SKB_CLOCK_MONOTONIC;
 		if (txhash)
 			skb_set_hash(nskb, txhash, PKT_HASH_TYPE_L4);
 		ip_push_pending_frames(sk, &fl4);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 95caf8aaa8bea..d44371cfa6ecb 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1301,7 +1301,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
 	tp = tcp_sk(sk);
 	prior_wstamp = tp->tcp_wstamp_ns;
 	tp->tcp_wstamp_ns = max(tp->tcp_wstamp_ns, tp->tcp_clock_cache);
-	skb_set_delivery_time(skb, tp->tcp_wstamp_ns, true);
+	skb_set_delivery_time(skb, tp->tcp_wstamp_ns, SKB_CLOCK_MONOTONIC);
 	if (clone_it) {
 		oskb = skb;
 
@@ -1655,7 +1655,7 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue,
 
 	skb_split(skb, buff, len);
 
-	skb_set_delivery_time(buff, skb->tstamp, true);
+	skb_set_delivery_time(buff, skb->tstamp, SKB_CLOCK_MONOTONIC);
 	tcp_fragment_tstamp(skb, buff);
 
 	old_factor = tcp_skb_pcount(skb);
@@ -2764,7 +2764,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 		if (unlikely(tp->repair) && tp->repair_queue == TCP_SEND_QUEUE) {
 			/* "skb_mstamp_ns" is used as a start point for the retransmit timer */
 			tp->tcp_wstamp_ns = tp->tcp_clock_cache;
-			skb_set_delivery_time(skb, tp->tcp_wstamp_ns, true);
+			skb_set_delivery_time(skb, tp->tcp_wstamp_ns, SKB_CLOCK_MONOTONIC);
 			list_move_tail(&skb->tcp_tsorted_anchor, &tp->tsorted_sent_queue);
 			tcp_init_tso_segs(skb, mss_now);
 			goto repair; /* Skip network transmission */
@@ -3752,11 +3752,11 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 #ifdef CONFIG_SYN_COOKIES
 	if (unlikely(synack_type == TCP_SYNACK_COOKIE && ireq->tstamp_ok))
 		skb_set_delivery_time(skb, cookie_init_timestamp(req, now),
-				      true);
+				      SKB_CLOCK_MONOTONIC);
 	else
 #endif
 	{
-		skb_set_delivery_time(skb, now, true);
+		skb_set_delivery_time(skb, now, SKB_CLOCK_MONOTONIC);
 		if (!tcp_rsk(req)->snt_synack) /* Timestamp first SYNACK */
 			tcp_rsk(req)->snt_synack = tcp_skb_timestamp_us(skb);
 	}
@@ -3843,7 +3843,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 	bpf_skops_write_hdr_opt((struct sock *)sk, skb, req, syn_skb,
 				synack_type, &opts);
 
-	skb_set_delivery_time(skb, now, true);
+	skb_set_delivery_time(skb, now, SKB_CLOCK_MONOTONIC);
 	tcp_add_tx_delay(skb, tp);
 
 	return skb;
@@ -4027,7 +4027,7 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 
 	err = tcp_transmit_skb(sk, syn_data, 1, sk->sk_allocation);
 
-	skb_set_delivery_time(syn, syn_data->skb_mstamp_ns, true);
+	skb_set_delivery_time(syn, syn_data->skb_mstamp_ns, SKB_CLOCK_MONOTONIC);
 
 	/* Now full SYN+DATA was cloned and sent (or not),
 	 * remove the SYN from the original skb (syn_data)
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 27d8725445e35..1ab0f23d37bfb 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -859,7 +859,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 	struct rt6_info *rt = dst_rt6_info(skb_dst(skb));
 	struct ipv6_pinfo *np = skb->sk && !dev_recursion_level() ?
 				inet6_sk(skb->sk) : NULL;
-	bool mono_delivery_time = skb->mono_delivery_time;
+	u8 tstamp_type = skb->tstamp_type;
 	struct ip6_frag_state state;
 	unsigned int mtu, hlen, nexthdr_offset;
 	ktime_t tstamp = skb->tstamp;
@@ -955,7 +955,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 			if (iter.frag)
 				ip6_fraglist_prepare(skb, &iter);
 
-			skb_set_delivery_time(skb, tstamp, mono_delivery_time);
+			skb_set_delivery_time(skb, tstamp, tstamp_type);
 			err = output(net, sk, skb);
 			if (!err)
 				IP6_INC_STATS(net, ip6_dst_idev(&rt->dst),
@@ -1016,7 +1016,7 @@ slow_path:
 		/*
 		 *	Put this fragment into the sending queue.
 		 */
-		skb_set_delivery_time(frag, tstamp, mono_delivery_time);
+		skb_set_delivery_time(frag, tstamp, tstamp_type);
 		err = output(net, sk, frag);
 		if (err)
 			goto fail;
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index 53d255838e6ab..e0c2347b4dc68 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -126,7 +126,7 @@ int br_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 				  struct sk_buff *))
 {
 	int frag_max_size = BR_INPUT_SKB_CB(skb)->frag_max_size;
-	bool mono_delivery_time = skb->mono_delivery_time;
+	u8 tstamp_type = skb->tstamp_type;
 	ktime_t tstamp = skb->tstamp;
 	struct ip6_frag_state state;
 	u8 *prevhdr, nexthdr = 0;
@@ -192,7 +192,7 @@ int br_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 			if (iter.frag)
 				ip6_fraglist_prepare(skb, &iter);
 
-			skb_set_delivery_time(skb, tstamp, mono_delivery_time);
+			skb_set_delivery_time(skb, tstamp, tstamp_type);
 			err = output(net, sk, data, skb);
 			if (err || !iter.frag)
 				break;
@@ -225,7 +225,7 @@ slow_path:
 			goto blackhole;
 		}
 
-		skb_set_delivery_time(skb2, tstamp, mono_delivery_time);
+		skb_set_delivery_time(skb2, tstamp, tstamp_type);
 		err = output(net, sk, data, skb2);
 		if (err)
 			goto blackhole;
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 5e1b50c6a44d2..6f0844c9315d1 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -263,7 +263,7 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb,
 		fq->iif = dev->ifindex;
 
 	fq->q.stamp = skb->tstamp;
-	fq->q.mono_delivery_time = skb->mono_delivery_time;
+	fq->q.tstamp_type = skb->tstamp_type;
 	fq->q.meat += skb->len;
 	fq->ecn |= ecn;
 	if (payload_len > fq->q.max_size)
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 327caca642576..a48be617a8ab5 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -198,7 +198,7 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
 		fq->iif = dev->ifindex;
 
 	fq->q.stamp = skb->tstamp;
-	fq->q.mono_delivery_time = skb->mono_delivery_time;
+	fq->q.tstamp_type = skb->tstamp_type;
 	fq->q.meat += skb->len;
 	fq->ecn |= ecn;
 	add_frag_mem_limit(fq->q.fqdir, skb->truesize);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 4c3605485b68e..8333005c5c2ea 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -975,7 +975,7 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32
 			mark = inet_twsk(sk)->tw_mark;
 		else
 			mark = READ_ONCE(sk->sk_mark);
-		skb_set_delivery_time(buff, tcp_transmit_time(sk), true);
+		skb_set_delivery_time(buff, tcp_transmit_time(sk), SKB_CLOCK_MONOTONIC);
 	}
 	if (txhash) {
 		/* autoflowlabel/skb_get_hash_flowi6 rely on buff->hash */
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index 0e3cf11ae5fc0..396b576390d00 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -54,8 +54,8 @@ TC_INDIRECT_SCOPE int tcf_bpf_act(struct sk_buff *skb,
 		bpf_compute_data_pointers(skb);
 		filter_res = bpf_prog_run(filter, skb);
 	}
-	if (unlikely(!skb->tstamp && skb->mono_delivery_time))
-		skb->mono_delivery_time = 0;
+	if (unlikely(!skb->tstamp && skb->tstamp_type))
+		skb->tstamp_type = SKB_CLOCK_REALTIME;
 	if (skb_sk_is_prefetched(skb) && filter_res != TC_ACT_OK)
 		skb_orphan(skb);
 
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index 5e83e890f6a4b..1941ebec23ff9 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -104,8 +104,8 @@ TC_INDIRECT_SCOPE int cls_bpf_classify(struct sk_buff *skb,
 			bpf_compute_data_pointers(skb);
 			filter_res = bpf_prog_run(prog->filter, skb);
 		}
-		if (unlikely(!skb->tstamp && skb->mono_delivery_time))
-			skb->mono_delivery_time = 0;
+		if (unlikely(!skb->tstamp && skb->tstamp_type))
+			skb->tstamp_type = SKB_CLOCK_REALTIME;
 
 		if (prog->exts_integrated) {
 			res->class   = 0;
-- 
GitLab


From 1693c5db6ab8262e6f5263f9d211855959aa5acd Mon Sep 17 00:00:00 2001
From: Abhishek Chauhan <quic_abchauha@quicinc.com>
Date: Thu, 9 May 2024 14:18:33 -0700
Subject: [PATCH 187/950] net: Add additional bit to support clockid_t
 timestamp type

tstamp_type is now set based on actual clockid_t compressed
into 2 bits.

To make the design scalable for future needs this commit bring in
the change to extend the tstamp_type:1 to tstamp_type:2 to support
other clockid_t timestamp.

We now support CLOCK_TAI as part of tstamp_type as part of this
commit with existing support CLOCK_MONOTONIC and CLOCK_REALTIME.

Signed-off-by: Abhishek Chauhan <quic_abchauha@quicinc.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://lore.kernel.org/r/20240509211834.3235191-3-quic_abchauha@quicinc.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 include/linux/skbuff.h         | 18 ++++++++-----
 include/uapi/linux/bpf.h       | 15 +++++++----
 net/core/filter.c              | 46 +++++++++++++++++++---------------
 net/ipv4/ip_output.c           |  5 +++-
 net/ipv4/raw.c                 |  2 +-
 net/ipv4/tcp_ipv4.c            |  2 ++
 net/ipv6/ip6_output.c          |  5 +++-
 net/ipv6/raw.c                 |  2 +-
 net/ipv6/tcp_ipv6.c            | 10 ++++++--
 net/packet/af_packet.c         |  7 +++---
 tools/include/uapi/linux/bpf.h | 15 +++++++----
 11 files changed, 81 insertions(+), 46 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 3a721cc3b6441..1e5c97daaa374 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -709,6 +709,8 @@ typedef unsigned char *sk_buff_data_t;
 enum skb_tstamp_type {
 	SKB_CLOCK_REALTIME,
 	SKB_CLOCK_MONOTONIC,
+	SKB_CLOCK_TAI,
+	__SKB_CLOCK_MAX = SKB_CLOCK_TAI,
 };
 
 /**
@@ -957,7 +959,7 @@ struct sk_buff {
 	/* private: */
 	__u8			__mono_tc_offset[0];
 	/* public: */
-	__u8			tstamp_type:1;	/* See skb_tstamp_type */
+	__u8			tstamp_type:2;	/* See skb_tstamp_type */
 #ifdef CONFIG_NET_XGRESS
 	__u8			tc_at_ingress:1;	/* See TC_AT_INGRESS_MASK */
 	__u8			tc_skip_classify:1;
@@ -1087,15 +1089,16 @@ struct sk_buff {
 #endif
 #define PKT_TYPE_OFFSET		offsetof(struct sk_buff, __pkt_type_offset)
 
-/* if you move tc_at_ingress or mono_delivery_time
+/* if you move tc_at_ingress or tstamp_type
  * around, you also must adapt these constants.
  */
 #ifdef __BIG_ENDIAN_BITFIELD
-#define SKB_MONO_DELIVERY_TIME_MASK	(1 << 7)
-#define TC_AT_INGRESS_MASK		(1 << 6)
+#define SKB_TSTAMP_TYPE_MASK		(3 << 6)
+#define SKB_TSTAMP_TYPE_RSHIFT		(6)
+#define TC_AT_INGRESS_MASK		(1 << 5)
 #else
-#define SKB_MONO_DELIVERY_TIME_MASK	(1 << 0)
-#define TC_AT_INGRESS_MASK		(1 << 1)
+#define SKB_TSTAMP_TYPE_MASK		(3)
+#define TC_AT_INGRESS_MASK		(1 << 2)
 #endif
 #define SKB_BF_MONO_TC_OFFSET		offsetof(struct sk_buff, __mono_tc_offset)
 
@@ -4216,6 +4219,9 @@ static inline void skb_set_delivery_type_by_clockid(struct sk_buff *skb,
 	case CLOCK_MONOTONIC:
 		tstamp_type = SKB_CLOCK_MONOTONIC;
 		break;
+	case CLOCK_TAI:
+		tstamp_type = SKB_CLOCK_TAI;
+		break;
 	default:
 		WARN_ON_ONCE(1);
 		kt = 0;
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 90706a47f6ffe..25ea393cf084b 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -6207,12 +6207,17 @@ union {					\
 	__u64 :64;			\
 } __attribute__((aligned(8)))
 
+/* The enum used in skb->tstamp_type. It specifies the clock type
+ * of the time stored in the skb->tstamp.
+ */
 enum {
-	BPF_SKB_TSTAMP_UNSPEC,
-	BPF_SKB_TSTAMP_DELIVERY_MONO,	/* tstamp has mono delivery time */
-	/* For any BPF_SKB_TSTAMP_* that the bpf prog cannot handle,
-	 * the bpf prog should handle it like BPF_SKB_TSTAMP_UNSPEC
-	 * and try to deduce it by ingress, egress or skb->sk->sk_clockid.
+	BPF_SKB_TSTAMP_UNSPEC = 0,		/* DEPRECATED */
+	BPF_SKB_TSTAMP_DELIVERY_MONO = 1,	/* DEPRECATED */
+	BPF_SKB_CLOCK_REALTIME = 0,
+	BPF_SKB_CLOCK_MONOTONIC = 1,
+	BPF_SKB_CLOCK_TAI = 2,
+	/* For any future BPF_SKB_CLOCK_* that the bpf prog cannot handle,
+	 * the bpf prog can try to deduce it by ingress/egress/skb->sk->sk_clockid.
 	 */
 };
 
diff --git a/net/core/filter.c b/net/core/filter.c
index a3781a796da4d..c6edfe9f41bcc 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -7726,17 +7726,21 @@ BPF_CALL_3(bpf_skb_set_tstamp, struct sk_buff *, skb,
 		return -EOPNOTSUPP;
 
 	switch (tstamp_type) {
-	case BPF_SKB_TSTAMP_DELIVERY_MONO:
+	case BPF_SKB_CLOCK_REALTIME:
+		skb->tstamp = tstamp;
+		skb->tstamp_type = SKB_CLOCK_REALTIME;
+		break;
+	case BPF_SKB_CLOCK_MONOTONIC:
 		if (!tstamp)
 			return -EINVAL;
 		skb->tstamp = tstamp;
 		skb->tstamp_type = SKB_CLOCK_MONOTONIC;
 		break;
-	case BPF_SKB_TSTAMP_UNSPEC:
-		if (tstamp)
+	case BPF_SKB_CLOCK_TAI:
+		if (!tstamp)
 			return -EINVAL;
-		skb->tstamp = 0;
-		skb->tstamp_type = SKB_CLOCK_REALTIME;
+		skb->tstamp = tstamp;
+		skb->tstamp_type = SKB_CLOCK_TAI;
 		break;
 	default:
 		return -EINVAL;
@@ -9387,16 +9391,17 @@ static struct bpf_insn *bpf_convert_tstamp_type_read(const struct bpf_insn *si,
 {
 	__u8 value_reg = si->dst_reg;
 	__u8 skb_reg = si->src_reg;
-	/* AX is needed because src_reg and dst_reg could be the same */
-	__u8 tmp_reg = BPF_REG_AX;
-
-	*insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg,
-			      SKB_BF_MONO_TC_OFFSET);
-	*insn++ = BPF_JMP32_IMM(BPF_JSET, tmp_reg,
-				SKB_MONO_DELIVERY_TIME_MASK, 2);
-	*insn++ = BPF_MOV32_IMM(value_reg, BPF_SKB_TSTAMP_UNSPEC);
-	*insn++ = BPF_JMP_A(1);
-	*insn++ = BPF_MOV32_IMM(value_reg, BPF_SKB_TSTAMP_DELIVERY_MONO);
+	BUILD_BUG_ON(__SKB_CLOCK_MAX != (int)BPF_SKB_CLOCK_TAI);
+	BUILD_BUG_ON(SKB_CLOCK_REALTIME != (int)BPF_SKB_CLOCK_REALTIME);
+	BUILD_BUG_ON(SKB_CLOCK_MONOTONIC != (int)BPF_SKB_CLOCK_MONOTONIC);
+	BUILD_BUG_ON(SKB_CLOCK_TAI != (int)BPF_SKB_CLOCK_TAI);
+	*insn++ = BPF_LDX_MEM(BPF_B, value_reg, skb_reg, SKB_BF_MONO_TC_OFFSET);
+	*insn++ = BPF_ALU32_IMM(BPF_AND, value_reg, SKB_TSTAMP_TYPE_MASK);
+#ifdef __BIG_ENDIAN_BITFIELD
+	*insn++ = BPF_ALU32_IMM(BPF_RSH, value_reg, SKB_TSTAMP_TYPE_RSHIFT);
+#else
+	BUILD_BUG_ON(!(SKB_TSTAMP_TYPE_MASK & 0x1));
+#endif
 
 	return insn;
 }
@@ -9439,10 +9444,11 @@ static struct bpf_insn *bpf_convert_tstamp_read(const struct bpf_prog *prog,
 		__u8 tmp_reg = BPF_REG_AX;
 
 		*insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg, SKB_BF_MONO_TC_OFFSET);
-		*insn++ = BPF_ALU32_IMM(BPF_AND, tmp_reg,
-					TC_AT_INGRESS_MASK | SKB_MONO_DELIVERY_TIME_MASK);
-		*insn++ = BPF_JMP32_IMM(BPF_JNE, tmp_reg,
-					TC_AT_INGRESS_MASK | SKB_MONO_DELIVERY_TIME_MASK, 2);
+		/* check if ingress mask bits is set */
+		*insn++ = BPF_JMP32_IMM(BPF_JSET, tmp_reg, TC_AT_INGRESS_MASK, 1);
+		*insn++ = BPF_JMP_A(4);
+		*insn++ = BPF_JMP32_IMM(BPF_JSET, tmp_reg, SKB_TSTAMP_TYPE_MASK, 1);
+		*insn++ = BPF_JMP_A(2);
 		/* skb->tc_at_ingress && skb->tstamp_type,
 		 * read 0 as the (rcv) timestamp.
 		 */
@@ -9479,7 +9485,7 @@ static struct bpf_insn *bpf_convert_tstamp_write(const struct bpf_prog *prog,
 		/* goto <store> */
 		*insn++ = BPF_JMP_A(2);
 		/* <clear>: skb->tstamp_type */
-		*insn++ = BPF_ALU32_IMM(BPF_AND, tmp_reg, ~SKB_MONO_DELIVERY_TIME_MASK);
+		*insn++ = BPF_ALU32_IMM(BPF_AND, tmp_reg, ~SKB_TSTAMP_TYPE_MASK);
 		*insn++ = BPF_STX_MEM(BPF_B, skb_reg, tmp_reg, SKB_BF_MONO_TC_OFFSET);
 	}
 #endif
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index fe86cadfa85b6..b90d0f78ac808 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1457,7 +1457,10 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
 
 	skb->priority = (cork->tos != -1) ? cork->priority: READ_ONCE(sk->sk_priority);
 	skb->mark = cork->mark;
-	skb->tstamp = cork->transmit_time;
+	if (sk_is_tcp(sk))
+		skb_set_delivery_time(skb, cork->transmit_time, SKB_CLOCK_MONOTONIC);
+	else
+		skb_set_delivery_type_by_clockid(skb, cork->transmit_time, sk->sk_clockid);
 	/*
 	 * Steal rt from cork.dst to avoid a pair of atomic_inc/atomic_dec
 	 * on dst refcount
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 4cb43401e0e06..1a09536503564 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -360,7 +360,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
 	skb->protocol = htons(ETH_P_IP);
 	skb->priority = READ_ONCE(sk->sk_priority);
 	skb->mark = sockc->mark;
-	skb->tstamp = sockc->transmit_time;
+	skb_set_delivery_type_by_clockid(skb, sockc->transmit_time, sk->sk_clockid);
 	skb_dst_set(skb, &rt->dst);
 	*rtp = NULL;
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 30ef0c8f5e92d..8f70b8d1d1e56 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -3625,6 +3625,8 @@ void __init tcp_v4_init(void)
 		 */
 		inet_sk(sk)->pmtudisc = IP_PMTUDISC_DO;
 
+		sk->sk_clockid = CLOCK_MONOTONIC;
+
 		per_cpu(ipv4_tcp_sk, cpu) = sk;
 	}
 	if (register_pernet_subsys(&tcp_sk_ops))
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 1ab0f23d37bfb..e7a19df3125e4 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1924,7 +1924,10 @@ struct sk_buff *__ip6_make_skb(struct sock *sk,
 
 	skb->priority = READ_ONCE(sk->sk_priority);
 	skb->mark = cork->base.mark;
-	skb->tstamp = cork->base.transmit_time;
+	if (sk_is_tcp(sk))
+		skb_set_delivery_time(skb, cork->base.transmit_time, SKB_CLOCK_MONOTONIC);
+	else
+		skb_set_delivery_type_by_clockid(skb, cork->base.transmit_time, sk->sk_clockid);
 
 	ip6_cork_steal_dst(skb, cork);
 	IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTREQUESTS);
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 2eedf255600b9..f838366e82567 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -621,7 +621,7 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length,
 	skb->protocol = htons(ETH_P_IPV6);
 	skb->priority = READ_ONCE(sk->sk_priority);
 	skb->mark = sockc->mark;
-	skb->tstamp = sockc->transmit_time;
+	skb_set_delivery_type_by_clockid(skb, sockc->transmit_time, sk->sk_clockid);
 
 	skb_put(skb, length);
 	skb_reset_network_header(skb);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 8333005c5c2ea..750aa681779ca 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -2387,8 +2387,14 @@ static struct inet_protosw tcpv6_protosw = {
 
 static int __net_init tcpv6_net_init(struct net *net)
 {
-	return inet_ctl_sock_create(&net->ipv6.tcp_sk, PF_INET6,
-				    SOCK_RAW, IPPROTO_TCP, net);
+	int res;
+
+	res = inet_ctl_sock_create(&net->ipv6.tcp_sk, PF_INET6,
+				   SOCK_RAW, IPPROTO_TCP, net);
+	if (!res)
+		net->ipv6.tcp_sk->sk_clockid = CLOCK_MONOTONIC;
+
+	return res;
 }
 
 static void __net_exit tcpv6_net_exit(struct net *net)
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index ea3ebc160e25c..fce3908875912 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2056,8 +2056,7 @@ retry:
 	skb->dev = dev;
 	skb->priority = READ_ONCE(sk->sk_priority);
 	skb->mark = READ_ONCE(sk->sk_mark);
-	skb->tstamp = sockc.transmit_time;
-
+	skb_set_delivery_type_by_clockid(skb, sockc.transmit_time, sk->sk_clockid);
 	skb_setup_tx_timestamp(skb, sockc.tsflags);
 
 	if (unlikely(extra_len == 4))
@@ -2584,7 +2583,7 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 	skb->dev = dev;
 	skb->priority = READ_ONCE(po->sk.sk_priority);
 	skb->mark = READ_ONCE(po->sk.sk_mark);
-	skb->tstamp = sockc->transmit_time;
+	skb_set_delivery_type_by_clockid(skb, sockc->transmit_time, po->sk.sk_clockid);
 	skb_setup_tx_timestamp(skb, sockc->tsflags);
 	skb_zcopy_set_nouarg(skb, ph.raw);
 
@@ -3062,7 +3061,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	skb->dev = dev;
 	skb->priority = READ_ONCE(sk->sk_priority);
 	skb->mark = sockc.mark;
-	skb->tstamp = sockc.transmit_time;
+	skb_set_delivery_type_by_clockid(skb, sockc.transmit_time, sk->sk_clockid);
 
 	if (unlikely(extra_len == 4))
 		skb->no_fcs = 1;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 90706a47f6ffe..25ea393cf084b 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -6207,12 +6207,17 @@ union {					\
 	__u64 :64;			\
 } __attribute__((aligned(8)))
 
+/* The enum used in skb->tstamp_type. It specifies the clock type
+ * of the time stored in the skb->tstamp.
+ */
 enum {
-	BPF_SKB_TSTAMP_UNSPEC,
-	BPF_SKB_TSTAMP_DELIVERY_MONO,	/* tstamp has mono delivery time */
-	/* For any BPF_SKB_TSTAMP_* that the bpf prog cannot handle,
-	 * the bpf prog should handle it like BPF_SKB_TSTAMP_UNSPEC
-	 * and try to deduce it by ingress, egress or skb->sk->sk_clockid.
+	BPF_SKB_TSTAMP_UNSPEC = 0,		/* DEPRECATED */
+	BPF_SKB_TSTAMP_DELIVERY_MONO = 1,	/* DEPRECATED */
+	BPF_SKB_CLOCK_REALTIME = 0,
+	BPF_SKB_CLOCK_MONOTONIC = 1,
+	BPF_SKB_CLOCK_TAI = 2,
+	/* For any future BPF_SKB_CLOCK_* that the bpf prog cannot handle,
+	 * the bpf prog can try to deduce it by ingress/egress/skb->sk->sk_clockid.
 	 */
 };
 
-- 
GitLab


From c34e3ab2a76e6a55a64e0d56acc5607062c2bad9 Mon Sep 17 00:00:00 2001
From: Abhishek Chauhan <quic_abchauha@quicinc.com>
Date: Thu, 9 May 2024 14:18:34 -0700
Subject: [PATCH 188/950] selftests/bpf: Handle forwarding of UDP CLOCK_TAI
 packets

With changes in the design to forward CLOCK_TAI in the skbuff
framework,  existing selftest framework needs modification
to handle forwarding of UDP packets with CLOCK_TAI as clockid.

Signed-off-by: Abhishek Chauhan <quic_abchauha@quicinc.com>
Reviewed-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://lore.kernel.org/r/20240509211834.3235191-4-quic_abchauha@quicinc.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 .../selftests/bpf/prog_tests/ctx_rewrite.c    | 10 +++--
 .../selftests/bpf/prog_tests/tc_redirect.c    |  3 --
 .../selftests/bpf/progs/test_tc_dtime.c       | 39 ++++++++-----------
 3 files changed, 23 insertions(+), 29 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/ctx_rewrite.c b/tools/testing/selftests/bpf/prog_tests/ctx_rewrite.c
index 3b7c57fe55a59..08b6391f2f56c 100644
--- a/tools/testing/selftests/bpf/prog_tests/ctx_rewrite.c
+++ b/tools/testing/selftests/bpf/prog_tests/ctx_rewrite.c
@@ -69,15 +69,17 @@ static struct test_case test_cases[] = {
 	{
 		N(SCHED_CLS, struct __sk_buff, tstamp),
 		.read  = "r11 = *(u8 *)($ctx + sk_buff::__mono_tc_offset);"
-			 "w11 &= 3;"
-			 "if w11 != 0x3 goto pc+2;"
+			 "if w11 & 0x4 goto pc+1;"
+			 "goto pc+4;"
+			 "if w11 & 0x3 goto pc+1;"
+			 "goto pc+2;"
 			 "$dst = 0;"
 			 "goto pc+1;"
 			 "$dst = *(u64 *)($ctx + sk_buff::tstamp);",
 		.write = "r11 = *(u8 *)($ctx + sk_buff::__mono_tc_offset);"
-			 "if w11 & 0x2 goto pc+1;"
+			 "if w11 & 0x4 goto pc+1;"
 			 "goto pc+2;"
-			 "w11 &= -2;"
+			 "w11 &= -4;"
 			 "*(u8 *)($ctx + sk_buff::__mono_tc_offset) = r11;"
 			 "*(u64 *)($ctx + sk_buff::tstamp) = $src;",
 	},
diff --git a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
index b1073d36d77ac..327d51f591427 100644
--- a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
+++ b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
@@ -890,9 +890,6 @@ static void test_udp_dtime(struct test_tc_dtime *skel, int family, bool bpf_fwd)
 
 	ASSERT_EQ(dtimes[INGRESS_FWDNS_P100], 0,
 		  dtime_cnt_str(t, INGRESS_FWDNS_P100));
-	/* non mono delivery time is not forwarded */
-	ASSERT_EQ(dtimes[INGRESS_FWDNS_P101], 0,
-		  dtime_cnt_str(t, INGRESS_FWDNS_P101));
 	for (i = EGRESS_FWDNS_P100; i < SET_DTIME; i++)
 		ASSERT_GT(dtimes[i], 0, dtime_cnt_str(t, i));
 
diff --git a/tools/testing/selftests/bpf/progs/test_tc_dtime.c b/tools/testing/selftests/bpf/progs/test_tc_dtime.c
index 74ec09f040b7a..ca8e8734d901a 100644
--- a/tools/testing/selftests/bpf/progs/test_tc_dtime.c
+++ b/tools/testing/selftests/bpf/progs/test_tc_dtime.c
@@ -222,17 +222,21 @@ int egress_host(struct __sk_buff *skb)
 		return TC_ACT_OK;
 
 	if (skb_proto(skb_type) == IPPROTO_TCP) {
-		if (skb->tstamp_type == BPF_SKB_TSTAMP_DELIVERY_MONO &&
+		if (skb->tstamp_type == BPF_SKB_CLOCK_MONOTONIC &&
 		    skb->tstamp)
 			inc_dtimes(EGRESS_ENDHOST);
 		else
 			inc_errs(EGRESS_ENDHOST);
-	} else {
-		if (skb->tstamp_type == BPF_SKB_TSTAMP_UNSPEC &&
+	} else if (skb_proto(skb_type) == IPPROTO_UDP) {
+		if (skb->tstamp_type == BPF_SKB_CLOCK_TAI &&
 		    skb->tstamp)
 			inc_dtimes(EGRESS_ENDHOST);
 		else
 			inc_errs(EGRESS_ENDHOST);
+	} else {
+		if (skb->tstamp_type == BPF_SKB_CLOCK_REALTIME &&
+		    skb->tstamp)
+			inc_errs(EGRESS_ENDHOST);
 	}
 
 	skb->tstamp = EGRESS_ENDHOST_MAGIC;
@@ -252,7 +256,7 @@ int ingress_host(struct __sk_buff *skb)
 	if (!skb_type)
 		return TC_ACT_OK;
 
-	if (skb->tstamp_type == BPF_SKB_TSTAMP_DELIVERY_MONO &&
+	if (skb->tstamp_type == BPF_SKB_CLOCK_MONOTONIC &&
 	    skb->tstamp == EGRESS_FWDNS_MAGIC)
 		inc_dtimes(INGRESS_ENDHOST);
 	else
@@ -315,7 +319,6 @@ int egress_fwdns_prio100(struct __sk_buff *skb)
 SEC("tc")
 int ingress_fwdns_prio101(struct __sk_buff *skb)
 {
-	__u64 expected_dtime = EGRESS_ENDHOST_MAGIC;
 	int skb_type;
 
 	skb_type = skb_get_type(skb);
@@ -323,29 +326,24 @@ int ingress_fwdns_prio101(struct __sk_buff *skb)
 		/* Should have handled in prio100 */
 		return TC_ACT_SHOT;
 
-	if (skb_proto(skb_type) == IPPROTO_UDP)
-		expected_dtime = 0;
-
 	if (skb->tstamp_type) {
 		if (fwdns_clear_dtime() ||
-		    skb->tstamp_type != BPF_SKB_TSTAMP_DELIVERY_MONO ||
-		    skb->tstamp != expected_dtime)
+		    (skb->tstamp_type != BPF_SKB_CLOCK_MONOTONIC &&
+		    skb->tstamp_type != BPF_SKB_CLOCK_TAI) ||
+		    skb->tstamp != EGRESS_ENDHOST_MAGIC)
 			inc_errs(INGRESS_FWDNS_P101);
 		else
 			inc_dtimes(INGRESS_FWDNS_P101);
 	} else {
-		if (!fwdns_clear_dtime() && expected_dtime)
+		if (!fwdns_clear_dtime())
 			inc_errs(INGRESS_FWDNS_P101);
 	}
 
-	if (skb->tstamp_type == BPF_SKB_TSTAMP_DELIVERY_MONO) {
+	if (skb->tstamp_type == BPF_SKB_CLOCK_MONOTONIC) {
 		skb->tstamp = INGRESS_FWDNS_MAGIC;
 	} else {
 		if (bpf_skb_set_tstamp(skb, INGRESS_FWDNS_MAGIC,
-				       BPF_SKB_TSTAMP_DELIVERY_MONO))
-			inc_errs(SET_DTIME);
-		if (!bpf_skb_set_tstamp(skb, INGRESS_FWDNS_MAGIC,
-					BPF_SKB_TSTAMP_UNSPEC))
+				       BPF_SKB_CLOCK_MONOTONIC))
 			inc_errs(SET_DTIME);
 	}
 
@@ -370,7 +368,7 @@ int egress_fwdns_prio101(struct __sk_buff *skb)
 
 	if (skb->tstamp_type) {
 		if (fwdns_clear_dtime() ||
-		    skb->tstamp_type != BPF_SKB_TSTAMP_DELIVERY_MONO ||
+		    skb->tstamp_type != BPF_SKB_CLOCK_MONOTONIC ||
 		    skb->tstamp != INGRESS_FWDNS_MAGIC)
 			inc_errs(EGRESS_FWDNS_P101);
 		else
@@ -380,14 +378,11 @@ int egress_fwdns_prio101(struct __sk_buff *skb)
 			inc_errs(EGRESS_FWDNS_P101);
 	}
 
-	if (skb->tstamp_type == BPF_SKB_TSTAMP_DELIVERY_MONO) {
+	if (skb->tstamp_type == BPF_SKB_CLOCK_MONOTONIC) {
 		skb->tstamp = EGRESS_FWDNS_MAGIC;
 	} else {
 		if (bpf_skb_set_tstamp(skb, EGRESS_FWDNS_MAGIC,
-				       BPF_SKB_TSTAMP_DELIVERY_MONO))
-			inc_errs(SET_DTIME);
-		if (!bpf_skb_set_tstamp(skb, INGRESS_FWDNS_MAGIC,
-					BPF_SKB_TSTAMP_UNSPEC))
+				       BPF_SKB_CLOCK_MONOTONIC))
 			inc_errs(SET_DTIME);
 	}
 
-- 
GitLab


From ec58991054e899c9d86f7e3c8a96cb602d4b5938 Mon Sep 17 00:00:00 2001
From: Hawking Zhang <Hawking.Zhang@amd.com>
Date: Tue, 21 May 2024 15:03:02 +0800
Subject: [PATCH 189/950] drm/amdgpu: correct hbm field in boot status

hbm filed takes bit 13 and bit 14 in boot status.

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
index c8980d5f6540a..7021c4a66fb5e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
@@ -46,7 +46,7 @@ struct amdgpu_iv_entry;
 #define AMDGPU_RAS_GPU_ERR_HBM_BIST_TEST(x)		AMDGPU_GET_REG_FIELD(x, 7, 7)
 #define AMDGPU_RAS_GPU_ERR_SOCKET_ID(x)			AMDGPU_GET_REG_FIELD(x, 10, 8)
 #define AMDGPU_RAS_GPU_ERR_AID_ID(x)			AMDGPU_GET_REG_FIELD(x, 12, 11)
-#define AMDGPU_RAS_GPU_ERR_HBM_ID(x)			AMDGPU_GET_REG_FIELD(x, 13, 13)
+#define AMDGPU_RAS_GPU_ERR_HBM_ID(x)			AMDGPU_GET_REG_FIELD(x, 14, 13)
 #define AMDGPU_RAS_GPU_ERR_BOOT_STATUS(x)		AMDGPU_GET_REG_FIELD(x, 31, 31)
 
 #define AMDGPU_RAS_BOOT_STATUS_POLLING_LIMIT	1000
-- 
GitLab


From 8195979d2dd995d60c2663adf54c69c1bf4eadd1 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Wed, 8 May 2024 16:45:35 -0500
Subject: [PATCH 190/950] drm/amd/display: Enable colorspace property for MST
 connectors
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

MST colorspace property support was disabled due to a series of warnings
that came up when the device was plugged in since the properties weren't
made at device creation. Create the properties in advance instead.

Suggested-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Fixes: 69a959610229 ("drm/amd/display: Temporary Disable MST DP Colorspace Property").
Reported-and-tested-by: Tyler Schneider <tyler.schneider@amd.com>
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/3353
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index 0b03e659fdf3f..8b0e997ebdaeb 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -613,6 +613,9 @@ dm_dp_add_mst_connector(struct drm_dp_mst_topology_mgr *mgr,
 		&connector->base,
 		dev->mode_config.tile_property,
 		0);
+	connector->colorspace_property = master->base.colorspace_property;
+	if (connector->colorspace_property)
+		drm_connector_attach_colorspace_property(connector);
 
 	drm_connector_set_path_property(connector, pathprop);
 
-- 
GitLab


From 699646734ab51bf5b1cd4a7a30c20074f6e74f6e Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Mon, 20 May 2024 22:30:17 -0700
Subject: [PATCH 191/950] uprobes: prevent mutex_lock() under rcu_read_lock()

Recent changes made uprobe_cpu_buffer preparation lazy, and moved it
deeper into __uprobe_trace_func(). This is problematic because
__uprobe_trace_func() is called inside rcu_read_lock()/rcu_read_unlock()
block, which then calls prepare_uprobe_buffer() -> uprobe_buffer_get() ->
mutex_lock(&ucb->mutex), leading to a splat about using mutex under
non-sleepable RCU:

  BUG: sleeping function called from invalid context at kernel/locking/mutex.c:585
   in_atomic(): 0, irqs_disabled(): 0, non_block: 0, pid: 98231, name: stress-ng-sigq
   preempt_count: 0, expected: 0
   RCU nest depth: 1, expected: 0
   ...
   Call Trace:
    <TASK>
    dump_stack_lvl+0x3d/0xe0
    __might_resched+0x24c/0x270
    ? prepare_uprobe_buffer+0xd5/0x1d0
    __mutex_lock+0x41/0x820
    ? ___perf_sw_event+0x206/0x290
    ? __perf_event_task_sched_in+0x54/0x660
    ? __perf_event_task_sched_in+0x54/0x660
    prepare_uprobe_buffer+0xd5/0x1d0
    __uprobe_trace_func+0x4a/0x140
    uprobe_dispatcher+0x135/0x280
    ? uprobe_dispatcher+0x94/0x280
    uprobe_notify_resume+0x650/0xec0
    ? atomic_notifier_call_chain+0x21/0x110
    ? atomic_notifier_call_chain+0xf8/0x110
    irqentry_exit_to_user_mode+0xe2/0x1e0
    asm_exc_int3+0x35/0x40
   RIP: 0033:0x7f7e1d4da390
   Code: 33 04 00 0f 1f 80 00 00 00 00 f3 0f 1e fa b9 01 00 00 00 e9 b2 fc ff ff 66 90 f3 0f 1e fa 31 c9 e9 a5 fc ff ff 0f 1f 44 00 00 <cc> 0f 1e fa b8 27 00 00 00 0f 05 c3 0f 1f 40 00 f3 0f 1e fa b8 6e
   RSP: 002b:00007ffd2abc3608 EFLAGS: 00000246
   RAX: 0000000000000000 RBX: 0000000076d325f1 RCX: 0000000000000000
   RDX: 0000000076d325f1 RSI: 000000000000000a RDI: 00007ffd2abc3690
   RBP: 000000000000000a R08: 00017fb700000000 R09: 00017fb700000000
   R10: 00017fb700000000 R11: 0000000000000246 R12: 0000000000017ff2
   R13: 00007ffd2abc3610 R14: 0000000000000000 R15: 00007ffd2abc3780
    </TASK>

Luckily, it's easy to fix by moving prepare_uprobe_buffer() to be called
slightly earlier: into uprobe_trace_func() and uretprobe_trace_func(), outside
of RCU locked section. This still keeps this buffer preparation lazy and helps
avoid the overhead when it's not needed. E.g., if there is only BPF uprobe
handler installed on a given uprobe, buffer won't be initialized.

Note, the other user of prepare_uprobe_buffer(), __uprobe_perf_func(), is not
affected, as it doesn't prepare buffer under RCU read lock.

Link: https://lore.kernel.org/all/20240521053017.3708530-1-andrii@kernel.org/

Fixes: 1b8f85defbc8 ("uprobes: prepare uprobe args buffer lazily")
Reported-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
 kernel/trace/trace_uprobe.c | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 8541fa1494ae3..c98e3b3386bad 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -970,19 +970,17 @@ static struct uprobe_cpu_buffer *prepare_uprobe_buffer(struct trace_uprobe *tu,
 
 static void __uprobe_trace_func(struct trace_uprobe *tu,
 				unsigned long func, struct pt_regs *regs,
-				struct uprobe_cpu_buffer **ucbp,
+				struct uprobe_cpu_buffer *ucb,
 				struct trace_event_file *trace_file)
 {
 	struct uprobe_trace_entry_head *entry;
 	struct trace_event_buffer fbuffer;
-	struct uprobe_cpu_buffer *ucb;
 	void *data;
 	int size, esize;
 	struct trace_event_call *call = trace_probe_event_call(&tu->tp);
 
 	WARN_ON(call != trace_file->event_call);
 
-	ucb = prepare_uprobe_buffer(tu, regs, ucbp);
 	if (WARN_ON_ONCE(ucb->dsize > PAGE_SIZE))
 		return;
 
@@ -1014,13 +1012,16 @@ static int uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs,
 			     struct uprobe_cpu_buffer **ucbp)
 {
 	struct event_file_link *link;
+	struct uprobe_cpu_buffer *ucb;
 
 	if (is_ret_probe(tu))
 		return 0;
 
+	ucb = prepare_uprobe_buffer(tu, regs, ucbp);
+
 	rcu_read_lock();
 	trace_probe_for_each_link_rcu(link, &tu->tp)
-		__uprobe_trace_func(tu, 0, regs, ucbp, link->file);
+		__uprobe_trace_func(tu, 0, regs, ucb, link->file);
 	rcu_read_unlock();
 
 	return 0;
@@ -1031,10 +1032,13 @@ static void uretprobe_trace_func(struct trace_uprobe *tu, unsigned long func,
 				 struct uprobe_cpu_buffer **ucbp)
 {
 	struct event_file_link *link;
+	struct uprobe_cpu_buffer *ucb;
+
+	ucb = prepare_uprobe_buffer(tu, regs, ucbp);
 
 	rcu_read_lock();
 	trace_probe_for_each_link_rcu(link, &tu->tp)
-		__uprobe_trace_func(tu, func, regs, ucbp, link->file);
+		__uprobe_trace_func(tu, func, regs, ucb, link->file);
 	rcu_read_unlock();
 }
 
-- 
GitLab


From 06e785aeb9ea8a43d0a3967c1ba6e69d758e82d4 Mon Sep 17 00:00:00 2001
From: Matt Jan <zoo868e@gmail.com>
Date: Tue, 14 May 2024 12:10:46 +0800
Subject: [PATCH 192/950] connector: Fix invalid conversion in cn_proc.h

The implicit conversion from unsigned int to enum
proc_cn_event is invalid, so explicitly cast it
for compilation in a C++ compiler.
/usr/include/linux/cn_proc.h: In function 'proc_cn_event valid_event(proc_cn_event)':
/usr/include/linux/cn_proc.h:72:17: error: invalid conversion from 'unsigned int' to 'proc_cn_event' [-fpermissive]
   72 |         ev_type &= PROC_EVENT_ALL;
      |                 ^
      |                 |
      |                 unsigned int

Signed-off-by: Matt Jan <zoo868e@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/cn_proc.h | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/include/uapi/linux/cn_proc.h b/include/uapi/linux/cn_proc.h
index f2afb7cc4926c..18e3745b86cd4 100644
--- a/include/uapi/linux/cn_proc.h
+++ b/include/uapi/linux/cn_proc.h
@@ -69,8 +69,7 @@ struct proc_input {
 
 static inline enum proc_cn_event valid_event(enum proc_cn_event ev_type)
 {
-	ev_type &= PROC_EVENT_ALL;
-	return ev_type;
+	return (enum proc_cn_event)(ev_type & PROC_EVENT_ALL);
 }
 
 /*
-- 
GitLab


From 128d54fbcb14b8717ecf596d3dbded327b9980b3 Mon Sep 17 00:00:00 2001
From: Mathieu Othacehe <othacehe@gnu.org>
Date: Tue, 21 May 2024 08:54:06 +0200
Subject: [PATCH 193/950] net: phy: micrel: set soft_reset callback to
 genphy_soft_reset for KSZ8061

Following a similar reinstate for the KSZ8081 and KSZ9031.

Older kernels would use the genphy_soft_reset if the PHY did not implement
a .soft_reset.

The KSZ8061 errata described here:
https://ww1.microchip.com/downloads/en/DeviceDoc/KSZ8061-Errata-DS80000688B.pdf
and worked around with 232ba3a51c ("net: phy: Micrel KSZ8061: link failure after cable connect")
is back again without this soft reset.

Fixes: 6e2d85ec0559 ("net: phy: Stop with excessive soft reset")
Tested-by: Karim Ben Houcine <karim.benhoucine@landisgyr.com>
Signed-off-by: Mathieu Othacehe <othacehe@gnu.org>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/micrel.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index 13e30ea7eec5d..1d769322b0593 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -5327,6 +5327,7 @@ static struct phy_driver ksphy_driver[] = {
 	/* PHY_BASIC_FEATURES */
 	.probe		= kszphy_probe,
 	.config_init	= ksz8061_config_init,
+	.soft_reset	= genphy_soft_reset,
 	.config_intr	= kszphy_config_intr,
 	.handle_interrupt = kszphy_handle_interrupt,
 	.suspend	= kszphy_suspend,
-- 
GitLab


From 9b038d004ce95551cb35381c49fe896c5bc11ffe Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 21 May 2024 14:37:43 +0100
Subject: [PATCH 194/950] netfs: Fix io_uring based write-through

This can be triggered by mounting a cifs filesystem with a cache=strict
mount option and then, using the fsx program from xfstests, doing:

        ltp/fsx -A -d -N 1000 -S 11463 -P /tmp /cifs-mount/foo \
          --replay-ops=gen112-fsxops

Where gen112-fsxops holds:

        fallocate 0x6be7 0x8fc5 0x377d3
        copy_range 0x9c71 0x77e8 0x2edaf 0x377d3
        write 0x2776d 0x8f65 0x377d3

The problem is that netfs_io_request::len is being used for two purposes
and ends up getting set to the amount of data we transferred, not the
amount of data the caller asked to be transferred (for various reasons,
such as mmap'd writes, we might end up rounding out the data written to the
server to include the entire folio at each end).

Fix this by keeping the amount we were asked to write in ->len and using
->submitted to track what we issued ops for.  Then, when we come to calling
->ki_complete(), ->len is the right size.

This also required netfs_cleanup_dio_write() to change since we're no
longer advancing wreq->len.  Use wreq->transferred instead as we might have
done a short read.

With this, the generic/112 xfstest passes if cifs is forced to put all
non-DIO opens into write-through mode.

Fixes: 288ace2f57c9 ("netfs: New writeback implementation")
Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://lore.kernel.org/r/295086.1716298663@warthog.procyon.org.uk
cc: Jeff Layton <jlayton@kernel.org>
cc: Steve French <stfrench@microsoft.com>
cc: Enzo Matsumiya <ematsumiya@suse.de>
cc: netfs@lists.linux.dev
cc: v9fs@lists.linux.dev
cc: linux-afs@lists.infradead.org
cc: linux-cifs@vger.kernel.org
cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/netfs/direct_write.c  | 2 +-
 fs/netfs/write_collect.c | 7 ++++---
 fs/netfs/write_issue.c   | 2 +-
 3 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c
index 608ba6416919a..28163516bf037 100644
--- a/fs/netfs/direct_write.c
+++ b/fs/netfs/direct_write.c
@@ -12,7 +12,7 @@
 static void netfs_cleanup_dio_write(struct netfs_io_request *wreq)
 {
 	struct inode *inode = wreq->inode;
-	unsigned long long end = wreq->start + wreq->len;
+	unsigned long long end = wreq->start + wreq->transferred;
 
 	if (!wreq->error &&
 	    i_size_read(inode) < end) {
diff --git a/fs/netfs/write_collect.c b/fs/netfs/write_collect.c
index 60112e4b2c5eb..426cf87aaf2ec 100644
--- a/fs/netfs/write_collect.c
+++ b/fs/netfs/write_collect.c
@@ -510,7 +510,7 @@ reassess_streams:
 	 * stream has a gap that can be jumped.
 	 */
 	if (notes & SOME_EMPTY) {
-		unsigned long long jump_to = wreq->start + wreq->len;
+		unsigned long long jump_to = wreq->start + READ_ONCE(wreq->submitted);
 
 		for (s = 0; s < NR_IO_STREAMS; s++) {
 			stream = &wreq->io_streams[s];
@@ -690,10 +690,11 @@ void netfs_write_collection_worker(struct work_struct *work)
 	wake_up_bit(&wreq->flags, NETFS_RREQ_IN_PROGRESS);
 
 	if (wreq->iocb) {
-		wreq->iocb->ki_pos += wreq->transferred;
+		size_t written = min(wreq->transferred, wreq->len);
+		wreq->iocb->ki_pos += written;
 		if (wreq->iocb->ki_complete)
 			wreq->iocb->ki_complete(
-				wreq->iocb, wreq->error ? wreq->error : wreq->transferred);
+				wreq->iocb, wreq->error ? wreq->error : written);
 		wreq->iocb = VFS_PTR_POISON;
 	}
 
diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c
index e190043bc0daa..86dad7e4202b5 100644
--- a/fs/netfs/write_issue.c
+++ b/fs/netfs/write_issue.c
@@ -254,7 +254,7 @@ static void netfs_issue_write(struct netfs_io_request *wreq,
 	stream->construct = NULL;
 
 	if (subreq->start + subreq->len > wreq->start + wreq->submitted)
-		wreq->len = wreq->submitted = subreq->start + subreq->len - wreq->start;
+		WRITE_ONCE(wreq->submitted, subreq->start + subreq->len - wreq->start);
 	netfs_do_issue_write(stream, subreq);
 }
 
-- 
GitLab


From 2c6b531020f0590db3b6b4950a41c692e9aa4f4a Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 21 May 2024 14:36:27 +0100
Subject: [PATCH 195/950] netfs: Fix AIO error handling when doing
 write-through

If an error occurs whilst we're doing an AIO write in write-through mode,
we may end up calling ->ki_complete() *and* returning an error from
->write_iter().  This can result in either a UAF (the ->ki_complete() func
pointer may get overwritten, for example) or a refcount underflow in
io_submit() as ->ki_complete is called twice.

Fix this by making netfs_end_writethrough() - and thus
netfs_perform_write() - unconditionally return -EIOCBQUEUED if we're doing
an AIO write and wait for completion if we're not.

Fixes: 288ace2f57c9 ("netfs: New writeback implementation")
Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://lore.kernel.org/r/295052.1716298587@warthog.procyon.org.uk
cc: Jeff Layton <jlayton@kernel.org>
cc: Enzo Matsumiya <ematsumiya@suse.de>
cc: netfs@lists.linux.dev
cc: v9fs@lists.linux.dev
cc: linux-afs@lists.infradead.org
cc: linux-cifs@vger.kernel.org
cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/netfs/write_issue.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c
index 86dad7e4202b5..3aa86e268f40d 100644
--- a/fs/netfs/write_issue.c
+++ b/fs/netfs/write_issue.c
@@ -636,7 +636,12 @@ int netfs_end_writethrough(struct netfs_io_request *wreq, struct writeback_contr
 
 	mutex_unlock(&ictx->wb_lock);
 
-	ret = wreq->error;
+	if (wreq->iocb) {
+		ret = -EIOCBQUEUED;
+	} else {
+		wait_on_bit(&wreq->flags, NETFS_RREQ_IN_PROGRESS, TASK_UNINTERRUPTIBLE);
+		ret = wreq->error;
+	}
 	netfs_put_request(wreq, false, netfs_rreq_trace_put_return);
 	return ret;
 }
-- 
GitLab


From 79c137454815ba5554caa8eeb4ad5c94e96e45ce Mon Sep 17 00:00:00 2001
From: Xu Yang <xu.yang_2@nxp.com>
Date: Tue, 21 May 2024 19:49:38 +0800
Subject: [PATCH 196/950] filemap: add helper mapping_max_folio_size()

Add mapping_max_folio_size() to get the maximum folio size for this
pagecache mapping.

Fixes: 5d8edfb900d5 ("iomap: Copy larger chunks from userspace")
Cc: stable@vger.kernel.org
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Xu Yang <xu.yang_2@nxp.com>
Link: https://lore.kernel.org/r/20240521114939.2541461-1-xu.yang_2@nxp.com
Reviewed-by: Ritesh Harjani (IBM) <ritesh.list@gmail.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 include/linux/pagemap.h | 34 +++++++++++++++++++++-------------
 1 file changed, 21 insertions(+), 13 deletions(-)

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 3d69589c00a4b..ee633712bba0b 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -346,6 +346,19 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask)
 	m->gfp_mask = mask;
 }
 
+/*
+ * There are some parts of the kernel which assume that PMD entries
+ * are exactly HPAGE_PMD_ORDER.  Those should be fixed, but until then,
+ * limit the maximum allocation order to PMD size.  I'm not aware of any
+ * assumptions about maximum order if THP are disabled, but 8 seems like
+ * a good order (that's 1MB if you're using 4kB pages)
+ */
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define MAX_PAGECACHE_ORDER	HPAGE_PMD_ORDER
+#else
+#define MAX_PAGECACHE_ORDER	8
+#endif
+
 /**
  * mapping_set_large_folios() - Indicate the file supports large folios.
  * @mapping: The file.
@@ -372,6 +385,14 @@ static inline bool mapping_large_folio_support(struct address_space *mapping)
 		test_bit(AS_LARGE_FOLIO_SUPPORT, &mapping->flags);
 }
 
+/* Return the maximum folio size for this pagecache mapping, in bytes. */
+static inline size_t mapping_max_folio_size(struct address_space *mapping)
+{
+	if (mapping_large_folio_support(mapping))
+		return PAGE_SIZE << MAX_PAGECACHE_ORDER;
+	return PAGE_SIZE;
+}
+
 static inline int filemap_nr_thps(struct address_space *mapping)
 {
 #ifdef CONFIG_READ_ONLY_THP_FOR_FS
@@ -530,19 +551,6 @@ static inline void *detach_page_private(struct page *page)
 	return folio_detach_private(page_folio(page));
 }
 
-/*
- * There are some parts of the kernel which assume that PMD entries
- * are exactly HPAGE_PMD_ORDER.  Those should be fixed, but until then,
- * limit the maximum allocation order to PMD size.  I'm not aware of any
- * assumptions about maximum order if THP are disabled, but 8 seems like
- * a good order (that's 1MB if you're using 4kB pages)
- */
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-#define MAX_PAGECACHE_ORDER	HPAGE_PMD_ORDER
-#else
-#define MAX_PAGECACHE_ORDER	8
-#endif
-
 #ifdef CONFIG_NUMA
 struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order);
 #else
-- 
GitLab


From 4e527d5841e24623181edc7fd6f6598ffa810e10 Mon Sep 17 00:00:00 2001
From: Xu Yang <xu.yang_2@nxp.com>
Date: Tue, 21 May 2024 19:49:39 +0800
Subject: [PATCH 197/950] iomap: fault in smaller chunks for non-large folio
 mappings

Since commit (5d8edfb900d5 "iomap: Copy larger chunks from userspace"),
iomap will try to copy in larger chunks than PAGE_SIZE. However, if the
mapping doesn't support large folio, only one page of maximum 4KB will
be created and 4KB data will be writen to pagecache each time. Then,
next 4KB will be handled in next iteration. This will cause potential
write performance problem.

If chunk is 2MB, total 512 pages need to be handled finally. During this
period, fault_in_iov_iter_readable() is called to check iov_iter readable
validity. Since only 4KB will be handled each time, below address space
will be checked over and over again:

start         	end
-
buf,    	buf+2MB
buf+4KB, 	buf+2MB
buf+8KB, 	buf+2MB
...
buf+2044KB 	buf+2MB

Obviously the checking size is wrong since only 4KB will be handled each
time. So this will get a correct chunk to let iomap work well in non-large
folio case.

With this change, the write speed will be stable. Tested on ARM64 device.

Before:

 - dd if=/dev/zero of=/dev/sda bs=400K  count=10485  (334 MB/s)
 - dd if=/dev/zero of=/dev/sda bs=800K  count=5242   (278 MB/s)
 - dd if=/dev/zero of=/dev/sda bs=1600K count=2621   (204 MB/s)
 - dd if=/dev/zero of=/dev/sda bs=2200K count=1906   (170 MB/s)
 - dd if=/dev/zero of=/dev/sda bs=3000K count=1398   (150 MB/s)
 - dd if=/dev/zero of=/dev/sda bs=4500K count=932    (139 MB/s)

After:

 - dd if=/dev/zero of=/dev/sda bs=400K  count=10485  (339 MB/s)
 - dd if=/dev/zero of=/dev/sda bs=800K  count=5242   (330 MB/s)
 - dd if=/dev/zero of=/dev/sda bs=1600K count=2621   (332 MB/s)
 - dd if=/dev/zero of=/dev/sda bs=2200K count=1906   (333 MB/s)
 - dd if=/dev/zero of=/dev/sda bs=3000K count=1398   (333 MB/s)
 - dd if=/dev/zero of=/dev/sda bs=4500K count=932    (333 MB/s)

Fixes: 5d8edfb900d5 ("iomap: Copy larger chunks from userspace")
Cc: stable@vger.kernel.org
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Xu Yang <xu.yang_2@nxp.com>
Link: https://lore.kernel.org/r/20240521114939.2541461-2-xu.yang_2@nxp.com
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/iomap/buffered-io.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 41c8f0c68ef56..c5802a4593345 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -898,11 +898,11 @@ static bool iomap_write_end(struct iomap_iter *iter, loff_t pos, size_t len,
 static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)
 {
 	loff_t length = iomap_length(iter);
-	size_t chunk = PAGE_SIZE << MAX_PAGECACHE_ORDER;
 	loff_t pos = iter->pos;
 	ssize_t total_written = 0;
 	long status = 0;
 	struct address_space *mapping = iter->inode->i_mapping;
+	size_t chunk = mapping_max_folio_size(mapping);
 	unsigned int bdp_flags = (iter->flags & IOMAP_NOWAIT) ? BDP_ASYNC : 0;
 
 	do {
-- 
GitLab


From f826bc9d6fc2f0e089fb8d104415d72e4d2e204c Mon Sep 17 00:00:00 2001
From: Fedor Pchelkin <pchelkin@ispras.ru>
Date: Mon, 20 May 2024 12:08:18 +0300
Subject: [PATCH 198/950] signalfd: fix error return code

If anon_inode_getfile() fails, return appropriate error code. This looks
like a single typo: the similar code changes in timerfd and userfaultfd
are okay.

Found by Linux Verification Center (linuxtesting.org).

Fixes: fbe38120eb1d ("signalfd: convert to ->read_iter()")
Signed-off-by: Fedor Pchelkin <pchelkin@ispras.ru>
Link: https://lore.kernel.org/r/20240520090819.76342-1-pchelkin@ispras.ru
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/signalfd.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/signalfd.c b/fs/signalfd.c
index 4a5614442dbfa..65fe5eed0be4c 100644
--- a/fs/signalfd.c
+++ b/fs/signalfd.c
@@ -282,7 +282,7 @@ static int do_signalfd4(int ufd, sigset_t *mask, int flags)
 		if (IS_ERR(file)) {
 			put_unused_fd(ufd);
 			kfree(ctx);
-			return ufd;
+			return PTR_ERR(file);
 		}
 		file->f_mode |= FMODE_NOWAIT;
 
-- 
GitLab


From 65bea9953715b19371164a8bec4f74fdd22c9e5a Mon Sep 17 00:00:00 2001
From: Fedor Pchelkin <pchelkin@ispras.ru>
Date: Mon, 20 May 2024 12:08:19 +0300
Subject: [PATCH 199/950] signalfd: drop an obsolete comment

Commit fbe38120eb1d ("signalfd: convert to ->read_iter()") removed the
call to anon_inode_getfd() by splitting fd setup into two parts. Drop the
comment referencing the internal details of that function.

Signed-off-by: Fedor Pchelkin <pchelkin@ispras.ru>
Link: https://lore.kernel.org/r/20240520090819.76342-2-pchelkin@ispras.ru
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/signalfd.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/fs/signalfd.c b/fs/signalfd.c
index 65fe5eed0be4c..ec7b2da2477a4 100644
--- a/fs/signalfd.c
+++ b/fs/signalfd.c
@@ -286,10 +286,6 @@ static int do_signalfd4(int ufd, sigset_t *mask, int flags)
 		}
 		file->f_mode |= FMODE_NOWAIT;
 
-		/*
-		 * When we call this, the initialization must be complete, since
-		 * anon_inode_getfd() will install the fd.
-		 */
 		fd_install(ufd, file);
 	} else {
 		struct fd f = fdget(ufd);
-- 
GitLab


From c596bea1452ddf172ec9b588e4597228e9a1f4d5 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 21 May 2024 16:49:46 +0100
Subject: [PATCH 200/950] netfs: Fix setting of BDP_ASYNC from iocb flags

Fix netfs_perform_write() to set BDP_ASYNC if IOCB_NOWAIT is set rather
than if IOCB_SYNC is not set.  It reflects asynchronicity in the sense of
not waiting rather than synchronicity in the sense of not returning until
the op is complete.

Without this, generic/590 fails on cifs in strict caching mode with a
complaint that one of the writes fails with EAGAIN.  The test can be
distilled down to:

        mount -t cifs /my/share /mnt -ostuff
        xfs_io -i -c 'falloc 0 8191M -c fsync -f /mnt/file
        xfs_io -i -c 'pwrite -b 1M -W 0 8191M' /mnt/file

Fixes: c38f4e96e605 ("netfs: Provide func to copy data to pagecache for buffered write")
Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://lore.kernel.org/r/316306.1716306586@warthog.procyon.org.uk
Reviewed-by: Jens Axboe <axboe@kernel.dk>
cc: Jeff Layton <jlayton@kernel.org>
cc: Enzo Matsumiya <ematsumiya@suse.de>
cc: Jens Axboe <axboe@kernel.dk>
cc: Matthew Wilcox <willy@infradead.org>
cc: netfs@lists.linux.dev
cc: v9fs@lists.linux.dev
cc: linux-afs@lists.infradead.org
cc: linux-cifs@vger.kernel.org
cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/netfs/buffered_write.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c
index 1121601536d18..07bc1fd435309 100644
--- a/fs/netfs/buffered_write.c
+++ b/fs/netfs/buffered_write.c
@@ -181,7 +181,7 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
 	struct folio *folio, *writethrough = NULL;
 	enum netfs_how_to_modify howto;
 	enum netfs_folio_trace trace;
-	unsigned int bdp_flags = (iocb->ki_flags & IOCB_SYNC) ? 0: BDP_ASYNC;
+	unsigned int bdp_flags = (iocb->ki_flags & IOCB_NOWAIT) ? BDP_ASYNC : 0;
 	ssize_t written = 0, ret, ret2;
 	loff_t i_size, pos = iocb->ki_pos, from, to;
 	size_t max_chunk = PAGE_SIZE << MAX_PAGECACHE_ORDER;
-- 
GitLab


From 712182b67e831912f90259102ae334089e7bccd1 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Tue, 21 May 2024 21:00:44 +0200
Subject: [PATCH 201/950] swap: yield device immediately

Otherwise we can cause spurious EBUSY issues when trying to mount the
rootfs later on.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=218845
Reported-by: Petri Kaukasoina <petri.kaukasoina@tuni.fi>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 kernel/power/swap.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index 5bc04bfe2db1d..c6f24d17866d8 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -1600,7 +1600,7 @@ int swsusp_check(bool exclusive)
 
 put:
 		if (error)
-			fput(hib_resume_bdev_file);
+			bdev_fput(hib_resume_bdev_file);
 		else
 			pr_debug("Image signature found, resuming\n");
 	} else {
-- 
GitLab


From 51ef9305b8f40946d65c40368ffb4c14636d369a Mon Sep 17 00:00:00 2001
From: Maher Sanalla <msanalla@nvidia.com>
Date: Wed, 22 May 2024 22:26:52 +0300
Subject: [PATCH 202/950] net/mlx5: Lag, do bond only if slaves agree on roce
 state
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently, the driver does not enforce that lag bond slaves must have
matching roce capabilities. Yet, in mlx5_do_bond(), the driver attempts
to enable roce on all vports of the bond slaves, causing the following
syndrome when one slave has no roce fw support:

mlx5_cmd_out_err:809:(pid 25427): MODIFY_NIC_VPORT_CONTEXT(0×755) op_mod(0×0)
failed, status bad parameter(0×3), syndrome (0xc1f678), err(-22)

Thus, create HW lag only if bond's slaves agree on roce state,
either all slaves have roce support resulting in a roce lag bond,
or none do, resulting in a raw eth bond.

Fixes: 7907f23adc18 ("net/mlx5: Implement RoCE LAG feature")
Signed-off-by: Maher Sanalla <msanalla@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
index f7f0476a4a58d..d0871c46b8c54 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
@@ -719,6 +719,7 @@ bool mlx5_lag_check_prereq(struct mlx5_lag *ldev)
 	struct mlx5_core_dev *dev;
 	u8 mode;
 #endif
+	bool roce_support;
 	int i;
 
 	for (i = 0; i < ldev->ports; i++)
@@ -743,6 +744,11 @@ bool mlx5_lag_check_prereq(struct mlx5_lag *ldev)
 		if (mlx5_sriov_is_enabled(ldev->pf[i].dev))
 			return false;
 #endif
+	roce_support = mlx5_get_roce_state(ldev->pf[MLX5_LAG_P1].dev);
+	for (i = 1; i < ldev->ports; i++)
+		if (mlx5_get_roce_state(ldev->pf[i].dev) != roce_support)
+			return false;
+
 	return true;
 }
 
@@ -910,8 +916,10 @@ static void mlx5_do_bond(struct mlx5_lag *ldev)
 		} else if (roce_lag) {
 			dev0->priv.flags &= ~MLX5_PRIV_FLAGS_DISABLE_IB_ADEV;
 			mlx5_rescan_drivers_locked(dev0);
-			for (i = 1; i < ldev->ports; i++)
-				mlx5_nic_vport_enable_roce(ldev->pf[i].dev);
+			for (i = 1; i < ldev->ports; i++) {
+				if (mlx5_get_roce_state(ldev->pf[i].dev))
+					mlx5_nic_vport_enable_roce(ldev->pf[i].dev);
+			}
 		} else if (shared_fdb) {
 			int i;
 
-- 
GitLab


From fca3b4791850b7e2181f0b3195b66d53df83151b Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@nvidia.com>
Date: Wed, 22 May 2024 22:26:53 +0300
Subject: [PATCH 203/950] net/mlx5: Do not query MPIR on embedded CPU function

A proper query to MPIR needs to set the correct value in the depth field.
On embedded CPU this value is not necessarily zero. As there is no real
use case for multi-PF netdev on the embedded CPU of the smart NIC, block
this option.

This fixes the following failure:
ACCESS_REG(0x805) op_mod(0x1) failed, status bad system state(0x4), syndrome (0x685f19), err(-5)

Fixes: 678eb448055a ("net/mlx5: SD, Implement basic query and instantiation")
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c
index dd5d186dc6148..f6deb5a3f8202 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c
@@ -100,10 +100,6 @@ static bool ft_create_alias_supported(struct mlx5_core_dev *dev)
 
 static bool mlx5_sd_is_supported(struct mlx5_core_dev *dev, u8 host_buses)
 {
-	/* Feature is currently implemented for PFs only */
-	if (!mlx5_core_is_pf(dev))
-		return false;
-
 	/* Honor the SW implementation limit */
 	if (host_buses > MLX5_SD_MAX_GROUP_SZ)
 		return false;
@@ -162,6 +158,14 @@ static int sd_init(struct mlx5_core_dev *dev)
 	bool sdm;
 	int err;
 
+	/* Feature is currently implemented for PFs only */
+	if (!mlx5_core_is_pf(dev))
+		return 0;
+
+	/* Block on embedded CPU PFs */
+	if (mlx5_core_is_ecpf(dev))
+		return 0;
+
 	if (!MLX5_CAP_MCAM_REG(dev, mpir))
 		return 0;
 
-- 
GitLab


From 1b9f86c6d53245dab087f1b2c05727b5982142ff Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Wed, 22 May 2024 22:26:54 +0300
Subject: [PATCH 204/950] net/mlx5: Fix MTMP register capability offset in MCAM
 register

The MTMP register (0x900a) capability offset is off-by-one, move it to
the right place.

Fixes: 1f507e80c700 ("net/mlx5: Expose NIC temperature via hardware monitoring kernel API")
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Cosmin Ratiu <cratiu@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/mlx5/mlx5_ifc.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index f468763478ae6..5df52e15f7d6c 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -10308,9 +10308,9 @@ struct mlx5_ifc_mcam_access_reg_bits {
 	u8         mfrl[0x1];
 	u8         regs_39_to_32[0x8];
 
-	u8         regs_31_to_10[0x16];
+	u8         regs_31_to_11[0x15];
 	u8         mtmp[0x1];
-	u8         regs_8_to_0[0x9];
+	u8         regs_9_to_0[0xa];
 };
 
 struct mlx5_ifc_mcam_access_reg_bits1 {
-- 
GitLab


From 16d66a4fa81da07bc4ed19f4e53b87263c2f8d38 Mon Sep 17 00:00:00 2001
From: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Date: Wed, 22 May 2024 22:26:55 +0300
Subject: [PATCH 205/950] net/mlx5: Use mlx5_ipsec_rx_status_destroy to
 correctly delete status rules

rx_create no longer allocates a modify_hdr instance that needs to be
cleaned up. The mlx5_modify_header_dealloc call will lead to a NULL pointer
dereference. A leak in the rules also previously occurred since there are
now two rules populated related to status.

  BUG: kernel NULL pointer dereference, address: 0000000000000000
  #PF: supervisor read access in kernel mode
  #PF: error_code(0x0000) - not-present page
  PGD 109907067 P4D 109907067 PUD 116890067 PMD 0
  Oops: 0000 [#1] SMP
  CPU: 1 PID: 484 Comm: ip Not tainted 6.9.0-rc2-rrameshbabu+ #254
  Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS Arch Linux 1.16.3-1-1 04/01/2014
  RIP: 0010:mlx5_modify_header_dealloc+0xd/0x70
  <snip>
  Call Trace:
   <TASK>
   ? show_regs+0x60/0x70
   ? __die+0x24/0x70
   ? page_fault_oops+0x15f/0x430
   ? free_to_partial_list.constprop.0+0x79/0x150
   ? do_user_addr_fault+0x2c9/0x5c0
   ? exc_page_fault+0x63/0x110
   ? asm_exc_page_fault+0x27/0x30
   ? mlx5_modify_header_dealloc+0xd/0x70
   rx_create+0x374/0x590
   rx_add_rule+0x3ad/0x500
   ? rx_add_rule+0x3ad/0x500
   ? mlx5_cmd_exec+0x2c/0x40
   ? mlx5_create_ipsec_obj+0xd6/0x200
   mlx5e_accel_ipsec_fs_add_rule+0x31/0xf0
   mlx5e_xfrm_add_state+0x426/0xc00
  <snip>

Fixes: 94af50c0a9bb ("net/mlx5e: Unify esw and normal IPsec status table creation/destruction")
Signed-off-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
index 41a2543a52cda..e51b03d4c717f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
@@ -750,8 +750,7 @@ err_fs:
 err_fs_ft:
 	if (rx->allow_tunnel_mode)
 		mlx5_eswitch_unblock_encap(mdev);
-	mlx5_del_flow_rules(rx->status.rule);
-	mlx5_modify_header_dealloc(mdev, rx->status.modify_hdr);
+	mlx5_ipsec_rx_status_destroy(ipsec, rx);
 err_add:
 	mlx5_destroy_flow_table(rx->ft.status);
 err_fs_ft_status:
-- 
GitLab


From 9a52f6d44f4521773b4699b4ed34b8e21d5a175c Mon Sep 17 00:00:00 2001
From: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Date: Wed, 22 May 2024 22:26:56 +0300
Subject: [PATCH 206/950] net/mlx5e: Fix IPsec tunnel mode offload feature
 check

Remove faulty check disabling checksum offload and GSO for offload of
simple IPsec tunnel L4 traffic. Comment previously describing the deleted
code incorrectly claimed the check prevented double tunnel (or three layers
of ip headers).

Fixes: f1267798c980 ("net/mlx5: Fix checksum issue of VXLAN and IPsec crypto offload")
Signed-off-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../mellanox/mlx5/core/en_accel/ipsec_rxtx.h    | 17 +++++------------
 1 file changed, 5 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h
index 82064614846f5..359050f0b54dd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h
@@ -97,18 +97,11 @@ mlx5e_ipsec_feature_check(struct sk_buff *skb, netdev_features_t features)
 		if (!x || !x->xso.offload_handle)
 			goto out_disable;
 
-		if (xo->inner_ipproto) {
-			/* Cannot support tunnel packet over IPsec tunnel mode
-			 * because we cannot offload three IP header csum
-			 */
-			if (x->props.mode == XFRM_MODE_TUNNEL)
-				goto out_disable;
-
-			/* Only support UDP or TCP L4 checksum */
-			if (xo->inner_ipproto != IPPROTO_UDP &&
-			    xo->inner_ipproto != IPPROTO_TCP)
-				goto out_disable;
-		}
+		/* Only support UDP or TCP L4 checksum */
+		if (xo->inner_ipproto &&
+		    xo->inner_ipproto != IPPROTO_UDP &&
+		    xo->inner_ipproto != IPPROTO_TCP)
+			goto out_disable;
 
 		return features;
 
-- 
GitLab


From f55cd31287e5f77f226c91d2f7756bafa0d583ed Mon Sep 17 00:00:00 2001
From: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Date: Wed, 22 May 2024 22:26:57 +0300
Subject: [PATCH 207/950] net/mlx5e: Do not use ptp structure for tx ts stats
 when not initialized

The ptp channel instance is only initialized when ptp traffic is first
processed by the driver. This means that there is a window in between when
port timestamping is enabled and ptp traffic is sent where the ptp channel
instance is not initialized. Accessing statistics during this window will
lead to an access violation (NULL + member offset). Check the validity of
the instance before attempting to query statistics.

  BUG: unable to handle page fault for address: 0000000000003524
  #PF: supervisor read access in kernel mode
  #PF: error_code(0x0000) - not-present page
  PGD 109dfc067 P4D 109dfc067 PUD 1064ef067 PMD 0
  Oops: 0000 [#1] SMP
  CPU: 0 PID: 420 Comm: ethtool Not tainted 6.9.0-rc2-rrameshbabu+ #245
  Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS Arch Linux 1.16.3-1-1 04/01/204
  RIP: 0010:mlx5e_stats_ts_get+0x4c/0x130
  <snip>
  Call Trace:
   <TASK>
   ? show_regs+0x60/0x70
   ? __die+0x24/0x70
   ? page_fault_oops+0x15f/0x430
   ? do_user_addr_fault+0x2c9/0x5c0
   ? exc_page_fault+0x63/0x110
   ? asm_exc_page_fault+0x27/0x30
   ? mlx5e_stats_ts_get+0x4c/0x130
   ? mlx5e_stats_ts_get+0x20/0x130
   mlx5e_get_ts_stats+0x15/0x20
  <snip>

Fixes: 3579032c08c1 ("net/mlx5e: Implement ethtool hardware timestamping statistics")
Signed-off-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index e211c41cec06a..e1ed214e86517 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -1186,6 +1186,9 @@ void mlx5e_stats_ts_get(struct mlx5e_priv *priv,
 		ts_stats->err = 0;
 		ts_stats->lost = 0;
 
+		if (!ptp)
+			goto out;
+
 		/* Aggregate stats across all TCs */
 		for (i = 0; i < ptp->num_tc; i++) {
 			struct mlx5e_ptp_cq_stats *stats =
@@ -1214,6 +1217,7 @@ void mlx5e_stats_ts_get(struct mlx5e_priv *priv,
 		}
 	}
 
+out:
 	mutex_unlock(&priv->state_lock);
 }
 
-- 
GitLab


From 5c74195d5dd977e97556e6fa76909b831c241230 Mon Sep 17 00:00:00 2001
From: Carolina Jubran <cjubran@nvidia.com>
Date: Wed, 22 May 2024 22:26:58 +0300
Subject: [PATCH 208/950] net/mlx5e: Use rx_missed_errors instead of rx_dropped
 for reporting buffer exhaustion

Previously, the driver incorrectly used rx_dropped to report device
buffer exhaustion.

According to the documentation, rx_dropped should not be used to count
packets dropped due to buffer exhaustion, which is the purpose of
rx_missed_errors.

Use rx_missed_errors as intended for counting packets dropped due to
buffer exhaustion.

Fixes: 269e6b3af3bf ("net/mlx5e: Report additional error statistics in get stats ndo")
Signed-off-by: Carolina Jubran <cjubran@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index b758bc72ac36b..c53c99dde5587 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3886,7 +3886,7 @@ mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
 		mlx5e_fold_sw_stats64(priv, stats);
 	}
 
-	stats->rx_dropped = priv->stats.qcnt.rx_out_of_buffer;
+	stats->rx_missed_errors = priv->stats.qcnt.rx_out_of_buffer;
 
 	stats->rx_length_errors =
 		PPORT_802_3_GET(pstats, a_in_range_length_errors) +
-- 
GitLab


From 83fea49f2711fc90c0d115b0ed04046b45155b65 Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Wed, 22 May 2024 22:26:59 +0300
Subject: [PATCH 209/950] net/mlx5e: Fix UDP GSO for encapsulated packets

When the skb is encapsulated, adjust the inner UDP header instead of the
outer one, and account for UDP header (instead of TCP) in the inline
header size calculation.

Fixes: 689adf0d4892 ("net/mlx5e: Add UDP GSO support")
Reported-by: Jason Baron <jbaron@akamai.com>
Closes: https://lore.kernel.org/netdev/c42961cb-50b9-4a9a-bd43-87fe48d88d29@akamai.com/
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Reviewed-by: Boris Pismenny <borisp@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h   | 8 +++++++-
 drivers/net/ethernet/mellanox/mlx5/core/en_tx.c           | 6 +++++-
 2 files changed, 12 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
index caa34b9c161e5..33e32584b07f5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
@@ -102,8 +102,14 @@ static inline void
 mlx5e_udp_gso_handle_tx_skb(struct sk_buff *skb)
 {
 	int payload_len = skb_shinfo(skb)->gso_size + sizeof(struct udphdr);
+	struct udphdr *udphdr;
 
-	udp_hdr(skb)->len = htons(payload_len);
+	if (skb->encapsulation)
+		udphdr = (struct udphdr *)skb_inner_transport_header(skb);
+	else
+		udphdr = udp_hdr(skb);
+
+	udphdr->len = htons(payload_len);
 }
 
 struct mlx5e_accel_tx_state {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index 099bf10788899..b09e9abd39f37 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -153,7 +153,11 @@ mlx5e_tx_get_gso_ihs(struct mlx5e_txqsq *sq, struct sk_buff *skb, int *hopbyhop)
 
 	*hopbyhop = 0;
 	if (skb->encapsulation) {
-		ihs = skb_inner_tcp_all_headers(skb);
+		if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4)
+			ihs = skb_inner_transport_offset(skb) +
+			      sizeof(struct udphdr);
+		else
+			ihs = skb_inner_tcp_all_headers(skb);
 		stats->tso_inner_packets++;
 		stats->tso_inner_bytes += skb->len - ihs;
 	} else {
-- 
GitLab


From b794918961516f667b0c745aebdfebbb8a98df39 Mon Sep 17 00:00:00 2001
From: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Date: Sun, 5 May 2024 23:08:31 +0900
Subject: [PATCH 210/950] dma-buf/sw-sync: don't enable IRQ from
 sync_print_obj()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Since commit a6aa8fca4d79 ("dma-buf/sw-sync: Reduce irqsave/irqrestore from
known context") by error replaced spin_unlock_irqrestore() with
spin_unlock_irq() for both sync_debugfs_show() and sync_print_obj() despite
sync_print_obj() is called from sync_debugfs_show(), lockdep complains
inconsistent lock state warning.

Use plain spin_{lock,unlock}() for sync_print_obj(), for
sync_debugfs_show() is already using spin_{lock,unlock}_irq().

Reported-by: syzbot <syzbot+a225ee3df7e7f9372dbe@syzkaller.appspotmail.com>
Closes: https://syzkaller.appspot.com/bug?extid=a225ee3df7e7f9372dbe
Fixes: a6aa8fca4d79 ("dma-buf/sw-sync: Reduce irqsave/irqrestore from known context")
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Reviewed-by: Christian König <christian.koenig@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/c2e46020-aaa6-4e06-bf73-f05823f913f0@I-love.SAKURA.ne.jp
Signed-off-by: Christian König <christian.koenig@amd.com>
---
 drivers/dma-buf/sync_debug.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/dma-buf/sync_debug.c b/drivers/dma-buf/sync_debug.c
index 101394f16930f..237bce21d1e72 100644
--- a/drivers/dma-buf/sync_debug.c
+++ b/drivers/dma-buf/sync_debug.c
@@ -110,12 +110,12 @@ static void sync_print_obj(struct seq_file *s, struct sync_timeline *obj)
 
 	seq_printf(s, "%s: %d\n", obj->name, obj->value);
 
-	spin_lock_irq(&obj->lock);
+	spin_lock(&obj->lock); /* Caller already disabled IRQ. */
 	list_for_each(pos, &obj->pt_list) {
 		struct sync_pt *pt = container_of(pos, struct sync_pt, link);
 		sync_print_fence(s, &pt->base, false);
 	}
-	spin_unlock_irq(&obj->lock);
+	spin_unlock(&obj->lock);
 }
 
 static void sync_print_sync_file(struct seq_file *s,
-- 
GitLab


From c12603e76ef666ce5c51a9d6faf155c9e3de7601 Mon Sep 17 00:00:00 2001
From: Xiao Wang <xiao.w.wang@intel.com>
Date: Thu, 16 May 2024 17:04:30 +0800
Subject: [PATCH 211/950] riscv, bpf: Optimize zextw insn with Zba extension

The Zba extension provides add.uw insn which can be used to implement
zext.w with rs2 set as ZERO.

Signed-off-by: Xiao Wang <xiao.w.wang@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: Pu Lehui <pulehui@huawei.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Pu Lehui <pulehui@huawei.com>
Link: https://lore.kernel.org/bpf/20240516090430.493122-1-xiao.w.wang@intel.com
---
 arch/riscv/Kconfig       | 12 ++++++++++++
 arch/riscv/net/bpf_jit.h | 18 ++++++++++++++++++
 2 files changed, 30 insertions(+)

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 9e87287942dca..6b8f1059594d8 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -595,6 +595,18 @@ config TOOLCHAIN_HAS_VECTOR_CRYPTO
 	def_bool $(as-instr, .option arch$(comma) +v$(comma) +zvkb)
 	depends on AS_HAS_OPTION_ARCH
 
+config RISCV_ISA_ZBA
+	bool "Zba extension support for bit manipulation instructions"
+	default y
+	help
+	   Add support for enabling optimisations in the kernel when the Zba
+	   extension is detected at boot.
+
+	   The Zba extension provides instructions to accelerate the generation
+	   of addresses that index into arrays of basic data types.
+
+	   If you don't know what to do here, say Y.
+
 config RISCV_ISA_ZBB
 	bool "Zbb extension support for bit manipulation instructions"
 	depends on TOOLCHAIN_HAS_ZBB
diff --git a/arch/riscv/net/bpf_jit.h b/arch/riscv/net/bpf_jit.h
index fdbf88ca8b700..97041b58237a8 100644
--- a/arch/riscv/net/bpf_jit.h
+++ b/arch/riscv/net/bpf_jit.h
@@ -18,6 +18,11 @@ static inline bool rvc_enabled(void)
 	return IS_ENABLED(CONFIG_RISCV_ISA_C);
 }
 
+static inline bool rvzba_enabled(void)
+{
+	return IS_ENABLED(CONFIG_RISCV_ISA_ZBA) && riscv_has_extension_likely(RISCV_ISA_EXT_ZBA);
+}
+
 static inline bool rvzbb_enabled(void)
 {
 	return IS_ENABLED(CONFIG_RISCV_ISA_ZBB) && riscv_has_extension_likely(RISCV_ISA_EXT_ZBB);
@@ -939,6 +944,14 @@ static inline u16 rvc_sdsp(u32 imm9, u8 rs2)
 	return rv_css_insn(0x7, imm, rs2, 0x2);
 }
 
+/* RV64-only ZBA instructions. */
+
+static inline u32 rvzba_zextw(u8 rd, u8 rs1)
+{
+	/* add.uw rd, rs1, ZERO */
+	return rv_r_insn(0x04, RV_REG_ZERO, rs1, 0, rd, 0x3b);
+}
+
 #endif /* __riscv_xlen == 64 */
 
 /* Helper functions that emit RVC instructions when possible. */
@@ -1161,6 +1174,11 @@ static inline void emit_zexth(u8 rd, u8 rs, struct rv_jit_context *ctx)
 
 static inline void emit_zextw(u8 rd, u8 rs, struct rv_jit_context *ctx)
 {
+	if (rvzba_enabled()) {
+		emit(rvzba_zextw(rd, rs), ctx);
+		return;
+	}
+
 	emit_slli(rd, rs, 32, ctx);
 	emit_srli(rd, rd, 32, ctx);
 }
-- 
GitLab


From 44382b3ed6b2787710c8ade06c0e97f5970a47c8 Mon Sep 17 00:00:00 2001
From: Friedrich Vock <friedrich.vock@gmx.de>
Date: Tue, 14 May 2024 09:09:31 +0200
Subject: [PATCH 212/950] bpf: Fix potential integer overflow in resolve_btfids

err is a 32-bit integer, but elf_update returns an off_t, which is 64-bit
at least on 64-bit platforms. If symbols_patch is called on a binary between
2-4GB in size, the result will be negative when cast to a 32-bit integer,
which the code assumes means an error occurred. This can wrongly trigger
build failures when building very large kernel images.

Fixes: fbbb68de80a4 ("bpf: Add resolve_btfids tool to resolve BTF IDs in ELF object")
Signed-off-by: Friedrich Vock <friedrich.vock@gmx.de>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20240514070931.199694-1-friedrich.vock@gmx.de
---
 tools/bpf/resolve_btfids/main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/bpf/resolve_btfids/main.c b/tools/bpf/resolve_btfids/main.c
index d9520cb826b31..af393c7dee1f1 100644
--- a/tools/bpf/resolve_btfids/main.c
+++ b/tools/bpf/resolve_btfids/main.c
@@ -728,7 +728,7 @@ static int sets_patch(struct object *obj)
 
 static int symbols_patch(struct object *obj)
 {
-	int err;
+	off_t err;
 
 	if (__symbols_patch(obj, &obj->structs)  ||
 	    __symbols_patch(obj, &obj->unions)   ||
-- 
GitLab


From e944fc8152744a41dc62e720995538e48b053bb9 Mon Sep 17 00:00:00 2001
From: Xiao Wang <xiao.w.wang@intel.com>
Date: Thu, 23 May 2024 11:18:35 +0800
Subject: [PATCH 213/950] riscv, bpf: Use STACK_ALIGN macro for size rounding
 up

Use the macro STACK_ALIGN that is defined in asm/processor.h for stack size
rounding up, just like bpf_jit_comp32.c does.

Signed-off-by: Xiao Wang <xiao.w.wang@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Pu Lehui <pulehui@huawei.com>
Link: https://lore.kernel.org/bpf/20240523031835.3977713-1-xiao.w.wang@intel.com
---
 arch/riscv/net/bpf_jit_comp64.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index 79a001d5533ea..c21a0ff234158 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -868,7 +868,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
 	stack_size += 8;
 	sreg_off = stack_size;
 
-	stack_size = round_up(stack_size, 16);
+	stack_size = round_up(stack_size, STACK_ALIGN);
 
 	if (!is_struct_ops) {
 		/* For the trampoline called from function entry,
@@ -1960,7 +1960,7 @@ void bpf_jit_build_prologue(struct rv_jit_context *ctx, bool is_subprog)
 {
 	int i, stack_adjust = 0, store_offset, bpf_stack_adjust;
 
-	bpf_stack_adjust = round_up(ctx->prog->aux->stack_depth, 16);
+	bpf_stack_adjust = round_up(ctx->prog->aux->stack_depth, STACK_ALIGN);
 	if (bpf_stack_adjust)
 		mark_fp(ctx);
 
@@ -1982,7 +1982,7 @@ void bpf_jit_build_prologue(struct rv_jit_context *ctx, bool is_subprog)
 	if (ctx->arena_vm_start)
 		stack_adjust += 8;
 
-	stack_adjust = round_up(stack_adjust, 16);
+	stack_adjust = round_up(stack_adjust, STACK_ALIGN);
 	stack_adjust += bpf_stack_adjust;
 
 	store_offset = stack_adjust - 8;
-- 
GitLab


From 99fa63d9ca60c4c1cc843fde205e4bc6e86b218f Mon Sep 17 00:00:00 2001
From: Xiao Wang <xiao.w.wang@intel.com>
Date: Sun, 19 May 2024 13:05:07 +0800
Subject: [PATCH 214/950] riscv, bpf: Try RVC for reg move within BPF_CMPXCHG
 JIT
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We could try to emit compressed insn for reg move operation during CMPXCHG
JIT, the instruction compression has no impact on the jump offsets of
following forward and backward jump instructions.

Signed-off-by: Xiao Wang <xiao.w.wang@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Björn Töpel <bjorn@kernel.org>
Link: https://lore.kernel.org/bpf/20240519050507.2217791-1-xiao.w.wang@intel.com
---
 arch/riscv/net/bpf_jit_comp64.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index c21a0ff234158..2bc4c14ea59a5 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -537,8 +537,10 @@ static void emit_atomic(u8 rd, u8 rs, s16 off, s32 imm, bool is64,
 	/* r0 = atomic_cmpxchg(dst_reg + off16, r0, src_reg); */
 	case BPF_CMPXCHG:
 		r0 = bpf_to_rv_reg(BPF_REG_0, ctx);
-		emit(is64 ? rv_addi(RV_REG_T2, r0, 0) :
-		     rv_addiw(RV_REG_T2, r0, 0), ctx);
+		if (is64)
+			emit_mv(RV_REG_T2, r0, ctx);
+		else
+			emit_addiw(RV_REG_T2, r0, 0, ctx);
 		emit(is64 ? rv_lr_d(r0, 0, rd, 0, 0) :
 		     rv_lr_w(r0, 0, rd, 0, 0), ctx);
 		jmp_offset = ninsns_rvoff(8);
-- 
GitLab


From 2c1713a8f1c94033a6e00aae4693ab03e8a3b9f1 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <linux@weissschuh.net>
Date: Sat, 18 May 2024 16:58:47 +0200
Subject: [PATCH 215/950] bpf: constify member bpf_sysctl_kern:: Table
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The sysctl core is preparing to only expose instances of struct ctl_table
as "const". This will also affect the ctl_table argument of sysctl handlers,
for which bpf_sysctl_kern::table is also used.

As the function prototype of all sysctl handlers throughout the tree
needs to stay consistent that change will be done in one commit.

To reduce the size of that final commit, switch this utility type which
is not bound by "typedef proc_handler" to "const struct ctl_table".

No functional change.

Signed-off-by: Thomas Weißschuh <linux@weissschuh.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Joel Granados <j.granados@samsung.com>
Link: https://lore.kernel.org/bpf/20240518-sysctl-const-handler-bpf-v1-1-f0d7186743c1@weissschuh.net
---
 include/linux/filter.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/filter.h b/include/linux/filter.h
index 0f12cf01070e3..b02aea291b7e8 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1406,7 +1406,7 @@ struct bpf_sock_ops_kern {
 
 struct bpf_sysctl_kern {
 	struct ctl_table_header *head;
-	struct ctl_table *table;
+	const struct ctl_table *table;
 	void *cur_val;
 	size_t cur_len;
 	void *new_val;
-- 
GitLab


From 64e3d02b43b17390f0fa9af6708a4eafdf20ba01 Mon Sep 17 00:00:00 2001
From: Kanchan Joshi <joshi.k@samsung.com>
Date: Fri, 24 May 2024 16:04:48 +0530
Subject: [PATCH 216/950] nvme: remove sgs and sws

sgs/sws are unused, so remove these from nvme_ns_head structure.

Signed-off-by: Kanchan Joshi <joshi.k@samsung.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/nvme.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index fc31bd340a63a..c43a30753d87a 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -471,8 +471,6 @@ struct nvme_ns_head {
 	u8			pi_type;
 	u8			pi_offset;
 	u8			guard_type;
-	u16			sgs;
-	u32			sws;
 #ifdef CONFIG_BLK_DEV_ZONED
 	u64			zsze;
 #endif
-- 
GitLab


From 1bd293fcf3af84674e82ed022c049491f3768840 Mon Sep 17 00:00:00 2001
From: Kundan Kumar <kundan.kumar@samsung.com>
Date: Thu, 23 May 2024 17:01:49 +0530
Subject: [PATCH 217/950] nvme: adjust multiples of NVME_CTRL_PAGE_SIZE in
 offset

bio_vec start offset may be relatively large particularly when large
folio gets added to the bio. A bigger offset will result in avoiding the
single-segment mapping optimization and end up using expensive
mempool_alloc further.

Rather than using absolute value, adjust bv_offset by
NVME_CTRL_PAGE_SIZE while checking if segment can be fitted into one/two
PRP entries.

Suggested-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Kundan Kumar <kundan.kumar@samsung.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/pci.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 710043086dffa..102a9fb0c65ff 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -778,7 +778,8 @@ static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req,
 		struct bio_vec bv = req_bvec(req);
 
 		if (!is_pci_p2pdma_page(bv.bv_page)) {
-			if (bv.bv_offset + bv.bv_len <= NVME_CTRL_PAGE_SIZE * 2)
+			if ((bv.bv_offset & (NVME_CTRL_PAGE_SIZE - 1)) +
+			     bv.bv_len <= NVME_CTRL_PAGE_SIZE * 2)
 				return nvme_setup_prp_simple(dev, req,
 							     &cmnd->rw, &bv);
 
-- 
GitLab


From 4f82a8d5c27748a3b4318af99627f4df248133e8 Mon Sep 17 00:00:00 2001
From: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Date: Tue, 21 May 2024 11:08:10 +0300
Subject: [PATCH 218/950] wifi: ath12k: refactor rx descriptor CMEM
 configuration

Currently, data path Rx descriptor placed in the CMEM memory respective
to the Rx offset. This Rx descriptor CMEM placement is not meeting the
requirements to support inter device MLO. In inter device MLO, multiple
devices participate in a group. The device specific Rx descriptor buffers
transmit to multiple device REO rings. To distinguish between device
specific Rx descriptor buffers, the CMEM setup configuration need to
choose a different placement based on the unique identifier (device index).

Below are the CMEM configuration placement representation:

Intra-Device MLO scenario:

        Device 0                                Device 1

     +-------------+                         +-------------+
     |             |                         |             |
     |     Tx      |                         |     Tx      |
     |             |                         |             |
     +-------------+                         +-------------+
     |             |                         |             |
     |     Rx      |                         |     Rx      |
     |             |                         |             |
     +-------------+                         +-------------+

Inter-Device MLO scenario:

        Device 0                                Device 1

     +-------------+                         +-------------+
     |             |                         |             |
     |     Tx      |                         |     Tx      |
     |             |                         |             |
     +-------------+                         +-------------+
     |             |                         |             |
     |     Rx      |                         |   Reserved  |
     |  Device 0   |                         |             |
     |             |                         |             |
     +-------------+                         +-------------+
     |             |                         |     Rx      |
     |   Reserved  |                         |   Device 1  |
     |             |                         |             |
     +-------------+                         +-------------+

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.0.1-00029-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 HW2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Signed-off-by: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240516000807.1704913-2-quic_periyasa@quicinc.com
---
 drivers/net/wireless/ath/ath12k/dp.c | 12 +++++++++---
 drivers/net/wireless/ath/ath12k/dp.h |  1 +
 2 files changed, 10 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/dp.c b/drivers/net/wireless/ath/ath12k/dp.c
index c04fa3eb57d69..61aa78d8bd8c8 100644
--- a/drivers/net/wireless/ath/ath12k/dp.c
+++ b/drivers/net/wireless/ath/ath12k/dp.c
@@ -1349,13 +1349,14 @@ static inline void *ath12k_dp_cc_get_desc_addr_ptr(struct ath12k_base *ab,
 struct ath12k_rx_desc_info *ath12k_dp_get_rx_desc(struct ath12k_base *ab,
 						  u32 cookie)
 {
+	struct ath12k_dp *dp = &ab->dp;
 	struct ath12k_rx_desc_info **desc_addr_ptr;
 	u16 start_ppt_idx, end_ppt_idx, ppt_idx, spt_idx;
 
 	ppt_idx = u32_get_bits(cookie, ATH12K_DP_CC_COOKIE_PPT);
 	spt_idx = u32_get_bits(cookie, ATH12K_DP_CC_COOKIE_SPT);
 
-	start_ppt_idx = ATH12K_RX_SPT_PAGE_OFFSET;
+	start_ppt_idx = dp->rx_ppt_base + ATH12K_RX_SPT_PAGE_OFFSET;
 	end_ppt_idx = start_ppt_idx + ATH12K_NUM_RX_SPT_PAGES;
 
 	if (ppt_idx < start_ppt_idx ||
@@ -1363,6 +1364,7 @@ struct ath12k_rx_desc_info *ath12k_dp_get_rx_desc(struct ath12k_base *ab,
 	    spt_idx > ATH12K_MAX_SPT_ENTRIES)
 		return NULL;
 
+	ppt_idx = ppt_idx - dp->rx_ppt_base;
 	desc_addr_ptr = ath12k_dp_cc_get_desc_addr_ptr(ab, ppt_idx, spt_idx);
 
 	return *desc_addr_ptr;
@@ -1397,7 +1399,7 @@ static int ath12k_dp_cc_desc_init(struct ath12k_base *ab)
 	struct ath12k_rx_desc_info *rx_descs, **rx_desc_addr;
 	struct ath12k_tx_desc_info *tx_descs, **tx_desc_addr;
 	u32 i, j, pool_id, tx_spt_page;
-	u32 ppt_idx;
+	u32 ppt_idx, cookie_ppt_idx;
 
 	spin_lock_bh(&dp->rx_desc_lock);
 
@@ -1412,10 +1414,11 @@ static int ath12k_dp_cc_desc_init(struct ath12k_base *ab)
 		}
 
 		ppt_idx = ATH12K_RX_SPT_PAGE_OFFSET + i;
+		cookie_ppt_idx = dp->rx_ppt_base + ppt_idx;
 		dp->spt_info->rxbaddr[i] = &rx_descs[0];
 
 		for (j = 0; j < ATH12K_MAX_SPT_ENTRIES; j++) {
-			rx_descs[j].cookie = ath12k_dp_cc_cookie_gen(ppt_idx, j);
+			rx_descs[j].cookie = ath12k_dp_cc_cookie_gen(cookie_ppt_idx, j);
 			rx_descs[j].magic = ATH12K_DP_RX_DESC_MAGIC;
 			list_add_tail(&rx_descs[j].list, &dp->rx_desc_free_list);
 
@@ -1476,6 +1479,7 @@ static int ath12k_dp_cmem_init(struct ath12k_base *ab,
 		end = start + ATH12K_NUM_TX_SPT_PAGES;
 		break;
 	case ATH12K_DP_RX_DESC:
+		cmem_base += ATH12K_PPT_ADDR_OFFSET(dp->rx_ppt_base);
 		start = ATH12K_RX_SPT_PAGE_OFFSET;
 		end = start + ATH12K_NUM_RX_SPT_PAGES;
 		break;
@@ -1518,6 +1522,8 @@ static int ath12k_dp_cc_init(struct ath12k_base *ab)
 		return -ENOMEM;
 	}
 
+	dp->rx_ppt_base = ab->device_id * ATH12K_NUM_RX_SPT_PAGES;
+
 	for (i = 0; i < dp->num_spt_pages; i++) {
 		dp->spt_info[i].vaddr = dma_alloc_coherent(ab->dev,
 							   ATH12K_PAGE_SIZE,
diff --git a/drivers/net/wireless/ath/ath12k/dp.h b/drivers/net/wireless/ath/ath12k/dp.h
index 43589c3dd4bc1..742094545089f 100644
--- a/drivers/net/wireless/ath/ath12k/dp.h
+++ b/drivers/net/wireless/ath/ath12k/dp.h
@@ -350,6 +350,7 @@ struct ath12k_dp {
 	struct ath12k_hp_update_timer tx_ring_timer[DP_TCL_NUM_RING_MAX];
 	struct ath12k_spt_info *spt_info;
 	u32 num_spt_pages;
+	u32 rx_ppt_base;
 	struct list_head rx_desc_free_list;
 	/* protects the free desc list */
 	spinlock_t rx_desc_lock;
-- 
GitLab


From 35864b62fa129196af4641b8bef50ac4226a22ed Mon Sep 17 00:00:00 2001
From: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Date: Tue, 21 May 2024 11:08:10 +0300
Subject: [PATCH 219/950] wifi: ath12k: improve the rx descriptor error
 information

The ath12k_dp_get_rx_desc() failure log currently contains the same
information across multiple Rx data paths and lacks sufficient detail for
debugging purposes. To address this, change the ath12k_dp_get_rx_desc()
failure log to include cookie information along with Rx path details.
This will provide more specific data for debugging purposes.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.0.1-00029-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 HW2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Signed-off-by: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240516000807.1704913-3-quic_periyasa@quicinc.com
---
 drivers/net/wireless/ath/ath12k/dp_rx.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/dp_rx.c b/drivers/net/wireless/ath/ath12k/dp_rx.c
index d8998ac3a482d..000df6edf6b4e 100644
--- a/drivers/net/wireless/ath/ath12k/dp_rx.c
+++ b/drivers/net/wireless/ath/ath12k/dp_rx.c
@@ -2628,7 +2628,8 @@ try_again:
 		if (!desc_info) {
 			desc_info = ath12k_dp_get_rx_desc(ab, cookie);
 			if (!desc_info) {
-				ath12k_warn(ab, "Invalid cookie in manual desc retrieval");
+				ath12k_warn(ab, "Invalid cookie in manual descriptor retrieval: 0x%x\n",
+					    cookie);
 				continue;
 			}
 		}
@@ -3326,7 +3327,8 @@ ath12k_dp_process_rx_err_buf(struct ath12k *ar, struct hal_reo_dest_ring *desc,
 	if (!desc_info) {
 		desc_info = ath12k_dp_get_rx_desc(ab, cookie);
 		if (!desc_info) {
-			ath12k_warn(ab, "Invalid cookie in manual desc retrieval");
+			ath12k_warn(ab, "Invalid cookie in DP rx error descriptor retrieval: 0x%x\n",
+				    cookie);
 			return -EINVAL;
 		}
 	}
@@ -3745,7 +3747,8 @@ int ath12k_dp_rx_process_wbm_err(struct ath12k_base *ab,
 		if (!desc_info) {
 			desc_info = ath12k_dp_get_rx_desc(ab, err_info.cookie);
 			if (!desc_info) {
-				ath12k_warn(ab, "Invalid cookie in manual desc retrieval");
+				ath12k_warn(ab, "Invalid cookie in DP WBM rx error descriptor retrieval: 0x%x\n",
+					    err_info.cookie);
 				continue;
 			}
 		}
-- 
GitLab


From b363614c0c80f9e2f3ffe8e77270e783a0fb8ab5 Mon Sep 17 00:00:00 2001
From: Baochen Qiang <quic_bqiang@quicinc.com>
Date: Tue, 21 May 2024 11:08:10 +0300
Subject: [PATCH 220/950] wifi: ath11k: refactor setting country code logic

ath11k_wmi_send_set_current_country_cmd() is called in several places
and all of them are just simply repeating the same logic.

Refactor to make code clean.

Compile tested only.

Signed-off-by: Baochen Qiang <quic_bqiang@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240520024148.5472-2-quic_bqiang@quicinc.com
---
 drivers/net/wireless/ath/ath11k/core.c | 19 ++++++++-----------
 drivers/net/wireless/ath/ath11k/mac.c  | 13 +++----------
 drivers/net/wireless/ath/ath11k/reg.c  | 14 ++++++++++----
 drivers/net/wireless/ath/ath11k/reg.h  |  4 ++--
 4 files changed, 23 insertions(+), 27 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/core.c b/drivers/net/wireless/ath/ath11k/core.c
index d4ef556852c2c..748e3ad2bec37 100644
--- a/drivers/net/wireless/ath/ath11k/core.c
+++ b/drivers/net/wireless/ath/ath11k/core.c
@@ -1978,23 +1978,20 @@ static void ath11k_update_11d(struct work_struct *work)
 	struct ath11k_base *ab = container_of(work, struct ath11k_base, update_11d_work);
 	struct ath11k *ar;
 	struct ath11k_pdev *pdev;
-	struct wmi_set_current_country_params set_current_param = {};
 	int ret, i;
 
-	spin_lock_bh(&ab->base_lock);
-	memcpy(&set_current_param.alpha2, &ab->new_alpha2, 2);
-	spin_unlock_bh(&ab->base_lock);
-
-	ath11k_dbg(ab, ATH11K_DBG_WMI, "update 11d new cc %c%c\n",
-		   set_current_param.alpha2[0],
-		   set_current_param.alpha2[1]);
-
 	for (i = 0; i < ab->num_radios; i++) {
 		pdev = &ab->pdevs[i];
 		ar = pdev->ar;
 
-		memcpy(&ar->alpha2, &set_current_param.alpha2, 2);
-		ret = ath11k_wmi_send_set_current_country_cmd(ar, &set_current_param);
+		spin_lock_bh(&ab->base_lock);
+		memcpy(&ar->alpha2, &ab->new_alpha2, 2);
+		spin_unlock_bh(&ab->base_lock);
+
+		ath11k_dbg(ab, ATH11K_DBG_WMI, "update 11d new cc %c%c for pdev %d\n",
+			   ar->alpha2[0], ar->alpha2[1], i);
+
+		ret = ath11k_reg_set_cc(ar);
 		if (ret)
 			ath11k_warn(ar->ab,
 				    "pdev id %d failed set current country code: %d\n",
diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c
index 17b06c0cd0628..84415187416d2 100644
--- a/drivers/net/wireless/ath/ath11k/mac.c
+++ b/drivers/net/wireless/ath/ath11k/mac.c
@@ -8864,12 +8864,8 @@ ath11k_mac_op_reconfig_complete(struct ieee80211_hw *hw,
 		ieee80211_wake_queues(ar->hw);
 
 		if (ar->ab->hw_params.current_cc_support &&
-		    ar->alpha2[0] != 0 && ar->alpha2[1] != 0) {
-			struct wmi_set_current_country_params set_current_param = {};
-
-			memcpy(&set_current_param.alpha2, ar->alpha2, 2);
-			ath11k_wmi_send_set_current_country_cmd(ar, &set_current_param);
-		}
+		    ar->alpha2[0] != 0 && ar->alpha2[1] != 0)
+			ath11k_reg_set_cc(ar);
 
 		if (ab->is_reset) {
 			recovery_count = atomic_inc_return(&ab->recovery_count);
@@ -10311,11 +10307,8 @@ static int __ath11k_mac_register(struct ath11k *ar)
 	}
 
 	if (ab->hw_params.current_cc_support && ab->new_alpha2[0]) {
-		struct wmi_set_current_country_params set_current_param = {};
-
-		memcpy(&set_current_param.alpha2, ab->new_alpha2, 2);
 		memcpy(&ar->alpha2, ab->new_alpha2, 2);
-		ret = ath11k_wmi_send_set_current_country_cmd(ar, &set_current_param);
+		ret = ath11k_reg_set_cc(ar);
 		if (ret)
 			ath11k_warn(ar->ab,
 				    "failed set cc code for mac register: %d\n", ret);
diff --git a/drivers/net/wireless/ath/ath11k/reg.c b/drivers/net/wireless/ath/ath11k/reg.c
index 4c3aefbbabbe7..b0f289784dd3a 100644
--- a/drivers/net/wireless/ath/ath11k/reg.c
+++ b/drivers/net/wireless/ath/ath11k/reg.c
@@ -49,7 +49,6 @@ ath11k_reg_notifier(struct wiphy *wiphy, struct regulatory_request *request)
 {
 	struct ieee80211_hw *hw = wiphy_to_ieee80211_hw(wiphy);
 	struct wmi_init_country_params init_country_param;
-	struct wmi_set_current_country_params set_current_param = {};
 	struct ath11k *ar = hw->priv;
 	int ret;
 
@@ -83,9 +82,8 @@ ath11k_reg_notifier(struct wiphy *wiphy, struct regulatory_request *request)
 	 * reg info
 	 */
 	if (ar->ab->hw_params.current_cc_support) {
-		memcpy(&set_current_param.alpha2, request->alpha2, 2);
-		memcpy(&ar->alpha2, &set_current_param.alpha2, 2);
-		ret = ath11k_wmi_send_set_current_country_cmd(ar, &set_current_param);
+		memcpy(&ar->alpha2, request->alpha2, 2);
+		ret = ath11k_reg_set_cc(ar);
 		if (ret)
 			ath11k_warn(ar->ab,
 				    "failed set current country code: %d\n", ret);
@@ -1017,3 +1015,11 @@ void ath11k_reg_free(struct ath11k_base *ab)
 		kfree(ab->new_regd[i]);
 	}
 }
+
+int ath11k_reg_set_cc(struct ath11k *ar)
+{
+	struct wmi_set_current_country_params set_current_param = {};
+
+	memcpy(&set_current_param.alpha2, ar->alpha2, 2);
+	return ath11k_wmi_send_set_current_country_cmd(ar, &set_current_param);
+}
diff --git a/drivers/net/wireless/ath/ath11k/reg.h b/drivers/net/wireless/ath/ath11k/reg.h
index 64edb794260ab..263ea90619483 100644
--- a/drivers/net/wireless/ath/ath11k/reg.h
+++ b/drivers/net/wireless/ath/ath11k/reg.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2019 The Linux Foundation. All rights reserved.
- * Copyright (c) 2022-2023 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2022-2024 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH11K_REG_H
@@ -45,5 +45,5 @@ ath11k_reg_ap_pwr_convert(enum ieee80211_ap_reg_power power_type);
 int ath11k_reg_handle_chan_list(struct ath11k_base *ab,
 				struct cur_regulatory_info *reg_info,
 				enum ieee80211_ap_reg_power power_type);
-
+int ath11k_reg_set_cc(struct ath11k *ar);
 #endif
-- 
GitLab


From 7f0343b7b8710436c1e6355c71782d32ada47e0c Mon Sep 17 00:00:00 2001
From: Baochen Qiang <quic_bqiang@quicinc.com>
Date: Tue, 21 May 2024 11:08:11 +0300
Subject: [PATCH 221/950] wifi: ath11k: restore country code during resume

We got report that regdomain is not correct after
return from hibernation:

Before hibernation:
% iw reg get
[...]
phy#0 (self-managed)
country CH: DFS-ETSI
        (2402 - 2482 @ 40), (N/A, 20), (N/A)
        (5170 - 5250 @ 80), (N/A, 23), (N/A), NO-OUTDOOR, AUTO-BW
        (5250 - 5330 @ 80), (N/A, 23), (0 ms), NO-OUTDOOR, DFS, AUTO-BW
        (5490 - 5590 @ 80), (N/A, 30), (0 ms), DFS, AUTO-BW
        (5590 - 5650 @ 40), (N/A, 30), (600000 ms), DFS, AUTO-BW
        (5650 - 5730 @ 80), (N/A, 30), (0 ms), DFS, AUTO-BW
        (5735 - 5875 @ 80), (N/A, 14), (N/A), AUTO-BW

After hibernation:
% iw reg get
[...]
phy#0 (self-managed)
country na: DFS-UNSET
        (2402 - 2472 @ 40), (N/A, 20), (N/A)
        (2457 - 2482 @ 20), (N/A, 20), (N/A), PASSIVE-SCAN
        (5170 - 5330 @ 160), (N/A, 20), (N/A), AUTO-BW, PASSIVE-SCAN
        (5490 - 5730 @ 160), (N/A, 20), (N/A), AUTO-BW, PASSIVE-SCAN
        (5735 - 5895 @ 160), (N/A, 20), (N/A), AUTO-BW, PASSIVE-SCAN
        (5945 - 7125 @ 160), (N/A, 30), (N/A), AUTO-BW, PASSIVE-SCAN

The reason is, during resume, firmware is reinitialized but host does
not send current country code to firmware. So default reg rules with
country code set to 'na' is uploaded to host, as shown above.

Fix it by restoring country code to firmware during resume.

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

Fixes: 166a490f59ac ("wifi: ath11k: support hibernation")
Signed-off-by: Baochen Qiang <quic_bqiang@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240520024148.5472-3-quic_bqiang@quicinc.com
---
 drivers/net/wireless/ath/ath11k/core.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/net/wireless/ath/ath11k/core.c b/drivers/net/wireless/ath/ath11k/core.c
index 748e3ad2bec37..3772e64d4976b 100644
--- a/drivers/net/wireless/ath/ath11k/core.c
+++ b/drivers/net/wireless/ath/ath11k/core.c
@@ -1009,6 +1009,16 @@ int ath11k_core_resume(struct ath11k_base *ab)
 		return -ETIMEDOUT;
 	}
 
+	if (ab->hw_params.current_cc_support &&
+	    ar->alpha2[0] != 0 && ar->alpha2[1] != 0) {
+		ret = ath11k_reg_set_cc(ar);
+		if (ret) {
+			ath11k_warn(ab, "failed to set country code during resume: %d\n",
+				    ret);
+			return ret;
+		}
+	}
+
 	ret = ath11k_dp_rx_pktlog_start(ab);
 	if (ret)
 		ath11k_warn(ab, "failed to start rx pktlog during resume: %d\n",
-- 
GitLab


From 33322e3ef07409278a18c6919c448e369d66a18e Mon Sep 17 00:00:00 2001
From: P Praneesh <quic_ppranees@quicinc.com>
Date: Mon, 20 May 2024 12:30:43 +0530
Subject: [PATCH 222/950] wifi: ath12k: change DMA direction while mapping
 reinjected packets
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

For fragmented packets, ath12k reassembles each fragment as a normal
packet and then reinjects it into HW ring. In this case, the DMA
direction should be DMA_TO_DEVICE, not DMA_FROM_DEVICE. Otherwise,
an invalid payload may be reinjected into the HW and
subsequently delivered to the host.

Given that arbitrary memory can be allocated to the skb buffer,
knowledge about the data contained in the reinjected buffer is lacking.
Consequently, there’s a risk of private information being leaked.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.1.1-00209-QCAHKSWPL_SILICONZ-1

Fixes: d889913205cf ("wifi: ath12k: driver for Qualcomm Wi-Fi 7 devices")
Co-developed-by: Baochen Qiang <quic_bqiang@quicinc.com>
Signed-off-by: Baochen Qiang <quic_bqiang@quicinc.com>
Signed-off-by: P Praneesh <quic_ppranees@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240520070045.631029-2-quic_ppranees@quicinc.com
---
 drivers/net/wireless/ath/ath12k/dp_rx.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/dp_rx.c b/drivers/net/wireless/ath/ath12k/dp_rx.c
index 000df6edf6b4e..ffd3f003d0037 100644
--- a/drivers/net/wireless/ath/ath12k/dp_rx.c
+++ b/drivers/net/wireless/ath/ath12k/dp_rx.c
@@ -3008,7 +3008,7 @@ static int ath12k_dp_rx_h_defrag_reo_reinject(struct ath12k *ar,
 
 	buf_paddr = dma_map_single(ab->dev, defrag_skb->data,
 				   defrag_skb->len + skb_tailroom(defrag_skb),
-				   DMA_FROM_DEVICE);
+				   DMA_TO_DEVICE);
 	if (dma_mapping_error(ab->dev, buf_paddr))
 		return -ENOMEM;
 
@@ -3094,7 +3094,7 @@ err_free_desc:
 	spin_unlock_bh(&dp->rx_desc_lock);
 err_unmap_dma:
 	dma_unmap_single(ab->dev, buf_paddr, defrag_skb->len + skb_tailroom(defrag_skb),
-			 DMA_FROM_DEVICE);
+			 DMA_TO_DEVICE);
 	return ret;
 }
 
-- 
GitLab


From 073f9f249eecd64ab9d59c91c4a23cfdcc02afe4 Mon Sep 17 00:00:00 2001
From: P Praneesh <quic_ppranees@quicinc.com>
Date: Mon, 20 May 2024 12:30:44 +0530
Subject: [PATCH 223/950] wifi: ath12k: fix invalid memory access while
 processing fragmented packets

The monitor ring and the reo reinject ring share the same ring mask index.
When the driver receives an interrupt for the reo reinject ring, the
monitor ring is also processed, leading to invalid memory access. Since
monitor support is not yet enabled in ath12k, the ring mask for the monitor
ring should be removed.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.1.1-00209-QCAHKSWPL_SILICONZ-1

Fixes: d889913205cf ("wifi: ath12k: driver for Qualcomm Wi-Fi 7 devices")
Signed-off-by: P Praneesh <quic_ppranees@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240520070045.631029-3-quic_ppranees@quicinc.com
---
 drivers/net/wireless/ath/ath12k/hw.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/hw.c b/drivers/net/wireless/ath/ath12k/hw.c
index b45f929a02045..2e11ea7635740 100644
--- a/drivers/net/wireless/ath/ath12k/hw.c
+++ b/drivers/net/wireless/ath/ath12k/hw.c
@@ -544,9 +544,6 @@ static const struct ath12k_hw_ring_mask ath12k_hw_ring_mask_qcn9274 = {
 	},
 	.rx_mon_dest = {
 		0, 0, 0,
-		ATH12K_RX_MON_RING_MASK_0,
-		ATH12K_RX_MON_RING_MASK_1,
-		ATH12K_RX_MON_RING_MASK_2,
 	},
 	.rx = {
 		0, 0, 0, 0,
@@ -572,8 +569,7 @@ static const struct ath12k_hw_ring_mask ath12k_hw_ring_mask_qcn9274 = {
 		ATH12K_HOST2RXDMA_RING_MASK_0,
 	},
 	.tx_mon_dest = {
-		ATH12K_TX_MON_RING_MASK_0,
-		ATH12K_TX_MON_RING_MASK_1,
+		0, 0, 0,
 	},
 };
 
-- 
GitLab


From a57ab7cced454f69b8ee8aa5f5019ea8de4674da Mon Sep 17 00:00:00 2001
From: P Praneesh <quic_ppranees@quicinc.com>
Date: Mon, 20 May 2024 12:30:45 +0530
Subject: [PATCH 224/950] wifi: ath12k: fix firmware crash during reo reinject
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When handling fragmented packets, the ath12k driver reassembles each
fragment into a normal packet and then reinjects it into the HW ring.
However, a firmware crash occurs during this reinjection process.
The issue arises because the driver populates peer metadata in
reo_ent_ring->queue_addr_lo, while the firmware expects the physical
address obtained from the corresponding peer’s queue descriptor. Fix it
by filling peer's queue descriptor's physical address in queue_addr_lo.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.1.1-00209-QCAHKSWPL_SILICONZ-1

Fixes: d889913205cf ("wifi: ath12k: driver for Qualcomm Wi-Fi 7 devices")
Signed-off-by: P Praneesh <quic_ppranees@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240520070045.631029-4-quic_ppranees@quicinc.com
---
 drivers/net/wireless/ath/ath12k/dp_rx.c | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/dp_rx.c b/drivers/net/wireless/ath/ath12k/dp_rx.c
index ffd3f003d0037..a52b7b273540f 100644
--- a/drivers/net/wireless/ath/ath12k/dp_rx.c
+++ b/drivers/net/wireless/ath/ath12k/dp_rx.c
@@ -2971,7 +2971,7 @@ static int ath12k_dp_rx_h_defrag_reo_reinject(struct ath12k *ar,
 	struct hal_srng *srng;
 	dma_addr_t link_paddr, buf_paddr;
 	u32 desc_bank, msdu_info, msdu_ext_info, mpdu_info;
-	u32 cookie, hal_rx_desc_sz, dest_ring_info0;
+	u32 cookie, hal_rx_desc_sz, dest_ring_info0, queue_addr_hi;
 	int ret;
 	struct ath12k_rx_desc_info *desc_info;
 	enum hal_rx_buf_return_buf_manager idle_link_rbm = dp->idle_link_rbm;
@@ -3064,13 +3064,11 @@ static int ath12k_dp_rx_h_defrag_reo_reinject(struct ath12k *ar,
 	reo_ent_ring->rx_mpdu_info.peer_meta_data =
 		reo_dest_ring->rx_mpdu_info.peer_meta_data;
 
-	/* Firmware expects physical address to be filled in queue_addr_lo in
-	 * the MLO scenario and in case of non MLO peer meta data needs to be
-	 * filled.
-	 * TODO: Need to handle for MLO scenario.
-	 */
-	reo_ent_ring->queue_addr_lo = reo_dest_ring->rx_mpdu_info.peer_meta_data;
-	reo_ent_ring->info0 = le32_encode_bits(dst_ind,
+	reo_ent_ring->queue_addr_lo = cpu_to_le32(lower_32_bits(rx_tid->paddr));
+	queue_addr_hi = upper_32_bits(rx_tid->paddr);
+	reo_ent_ring->info0 = le32_encode_bits(queue_addr_hi,
+					       HAL_REO_ENTR_RING_INFO0_QUEUE_ADDR_HI) |
+			      le32_encode_bits(dst_ind,
 					       HAL_REO_ENTR_RING_INFO0_DEST_IND);
 
 	reo_ent_ring->info1 = le32_encode_bits(rx_tid->cur_sn,
-- 
GitLab


From 29be9100aca2915fab54b5693309bc42956542e5 Mon Sep 17 00:00:00 2001
From: Marc Dionne <marc.dionne@auristor.com>
Date: Fri, 24 May 2024 17:17:55 +0100
Subject: [PATCH 225/950] afs: Don't cross .backup mountpoint from backup
 volume

Don't cross a mountpoint that explicitly specifies a backup volume
(target is <vol>.backup) when starting from a backup volume.

It it not uncommon to mount a volume's backup directly in the volume
itself.  This can cause tools that are not paying attention to get
into a loop mounting the volume onto itself as they attempt to
traverse the tree, leading to a variety of problems.

This doesn't prevent the general case of loops in a sequence of
mountpoints, but addresses a common special case in the same way
as other afs clients.

Reported-by: Jan Henrik Sylvester <jan.henrik.sylvester@uni-hamburg.de>
Link: http://lists.infradead.org/pipermail/linux-afs/2024-May/008454.html
Reported-by: Markus Suvanto <markus.suvanto@gmail.com>
Link: http://lists.infradead.org/pipermail/linux-afs/2024-February/008074.html
Signed-off-by: Marc Dionne <marc.dionne@auristor.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://lore.kernel.org/r/768760.1716567475@warthog.procyon.org.uk
Reviewed-by: Jeffrey Altman <jaltman@auristor.com>
cc: linux-afs@lists.infradead.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/afs/mntpt.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c
index 97f50e9fd9eb0..297487ee83231 100644
--- a/fs/afs/mntpt.c
+++ b/fs/afs/mntpt.c
@@ -140,6 +140,11 @@ static int afs_mntpt_set_params(struct fs_context *fc, struct dentry *mntpt)
 		put_page(page);
 		if (ret < 0)
 			return ret;
+
+		/* Don't cross a backup volume mountpoint from a backup volume */
+		if (src_as->volume && src_as->volume->type == AFSVL_BACKVOL &&
+		    ctx->type == AFSVL_BACKVOL)
+			return -ENODEV;
 	}
 
 	return 0;
-- 
GitLab


From 4652072e7b9d643edc9ebb04e3e2c021461b7af0 Mon Sep 17 00:00:00 2001
From: Dave Thaler <dthaler1968@googlemail.com>
Date: Fri, 17 May 2024 08:34:45 -0700
Subject: [PATCH 226/950] bpf, docs: Move sentence about returning R0 to
 abi.rst

As discussed at LSF/MM/BPF, the sentence about using R0 for returning
values from calls is part of the calling convention and belongs in
abi.rst.  Any further additions or clarifications to this text are left
for future patches on abi.rst.  The current patch is simply to unblock
progression of instruction-set.rst to a standard.

In contrast, the restriction of register numbers to the range 0-10
is untouched, left in the instruction-set.rst definition of the
src_reg and dst_reg fields.

Signed-off-by: Dave Thaler <dthaler1968@googlemail.com>
Link: https://lore.kernel.org/r/20240517153445.3914-1-dthaler1968@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 Documentation/bpf/standardization/abi.rst             | 3 +++
 Documentation/bpf/standardization/instruction-set.rst | 3 ---
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/Documentation/bpf/standardization/abi.rst b/Documentation/bpf/standardization/abi.rst
index 0c2e10eeb89a0..41514137cb7b8 100644
--- a/Documentation/bpf/standardization/abi.rst
+++ b/Documentation/bpf/standardization/abi.rst
@@ -23,3 +23,6 @@ The BPF calling convention is defined as:
 
 R0 - R5 are scratch registers and BPF programs needs to spill/fill them if
 necessary across calls.
+
+The BPF program needs to store the return value into register R0 before doing an
+``EXIT``.
diff --git a/Documentation/bpf/standardization/instruction-set.rst b/Documentation/bpf/standardization/instruction-set.rst
index 00c93eb42613e..e2f6c0a4a559b 100644
--- a/Documentation/bpf/standardization/instruction-set.rst
+++ b/Documentation/bpf/standardization/instruction-set.rst
@@ -476,9 +476,6 @@ the jump instruction.  Thus 'PC += 1' skips execution of the next
 instruction if it's a basic instruction or results in undefined behavior
 if the next instruction is a 128-bit wide instruction.
 
-The BPF program needs to store the return value into register R0 before doing an
-``EXIT``.
-
 Example:
 
 ``{JSGE, X, JMP32}`` means::
-- 
GitLab


From a985fdca5e7e665d58dc40c92a67c8b67b6291db Mon Sep 17 00:00:00 2001
From: Dave Thaler <dthaler1968@googlemail.com>
Date: Fri, 17 May 2024 09:58:55 -0700
Subject: [PATCH 227/950] bpf, docs: Use RFC 2119 language for ISA requirements

Per IETF convention and discussion at LSF/MM/BPF, use MUST etc.
keywords as requested by IETF Area Director review.  Also as
requested, indicate that documenting BTF is out of scope of this
document and will be covered by a separate IETF specification.

Added paragraph about the terminology that is required IETF boilerplate
and must be worded exactly as such.

Signed-off-by: Dave Thaler <dthaler1968@googlemail.com>
Acked-by: David Vernet <void@manifault.com>
Link: https://lore.kernel.org/r/20240517165855.4688-1-dthaler1968@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../bpf/standardization/instruction-set.rst   | 24 ++++++++++++-------
 1 file changed, 16 insertions(+), 8 deletions(-)

diff --git a/Documentation/bpf/standardization/instruction-set.rst b/Documentation/bpf/standardization/instruction-set.rst
index e2f6c0a4a559b..02e2490433c64 100644
--- a/Documentation/bpf/standardization/instruction-set.rst
+++ b/Documentation/bpf/standardization/instruction-set.rst
@@ -14,6 +14,13 @@ set architecture (ISA).
 Documentation conventions
 =========================
 
+The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT",
+"SHOULD", "SHOULD NOT", "RECOMMENDED", "NOT RECOMMENDED", "MAY", and
+"OPTIONAL" in this document are to be interpreted as described in
+BCP 14 `<https://www.rfc-editor.org/info/rfc2119>`_
+`RFC8174 <https://www.rfc-editor.org/info/rfc8174>`_
+when, and only when, they appear in all capitals, as shown here.
+
 For brevity and consistency, this document refers to families
 of types using a shorthand syntax and refers to several expository,
 mnemonic functions when describing the semantics of instructions.
@@ -106,9 +113,9 @@ Conformance groups
 
 An implementation does not need to support all instructions specified in this
 document (e.g., deprecated instructions).  Instead, a number of conformance
-groups are specified.  An implementation must support the base32 conformance
-group and may support additional conformance groups, where supporting a
-conformance group means it must support all instructions in that conformance
+groups are specified.  An implementation MUST support the base32 conformance
+group and MAY support additional conformance groups, where supporting a
+conformance group means it MUST support all instructions in that conformance
 group.
 
 The use of named conformance groups enables interoperability between a runtime
@@ -209,7 +216,7 @@ For example::
   07     1       0        00 00  11 22 33 44  r1 += 0x11223344 // big
 
 Note that most instructions do not use all of the fields.
-Unused fields shall be cleared to zero.
+Unused fields SHALL be cleared to zero.
 
 Wide instruction encoding
 --------------------------
@@ -374,7 +381,7 @@ interpreted as a 64-bit signed value.
 Note that there are varying definitions of the signed modulo operation
 when the dividend or divisor are negative, where implementations often
 vary by language such that Python, Ruby, etc.  differ from C, Go, Java,
-etc. This specification requires that signed modulo use truncated division
+etc. This specification requires that signed modulo MUST use truncated division
 (where -13 % 3 == -1) as implemented in C, Go, etc.::
 
    a % n = a - n * trunc(a / n)
@@ -404,7 +411,7 @@ only and do not use a separate source register or immediate value.
 For ``ALU``, the 1-bit source operand field in the opcode is used to
 select what byte order the operation converts from or to. For
 ``ALU64``, the 1-bit source operand field in the opcode is reserved
-and must be set to 0.
+and MUST be set to 0.
 
 =====  ========  =====  =================================================
 class  source    value  description
@@ -512,7 +519,8 @@ for each program type, but static IDs are unique across all program types.
 
 Platforms that support the BPF Type Format (BTF) support identifying
 a helper function by a BTF ID encoded in the 'imm' field, where the BTF ID
-identifies the helper name and type.
+identifies the helper name and type.  Further documentation of BTF
+is outside the scope of this document and is left for future work.
 
 Program-local functions
 ~~~~~~~~~~~~~~~~~~~~~~~
@@ -722,5 +730,5 @@ carried over from classic BPF. These instructions used an instruction
 class of ``LD``, a size modifier of ``W``, ``H``, or ``B``, and a
 mode modifier of ``ABS`` or ``IND``.  The 'dst_reg' and 'offset' fields were
 set to zero, and 'src_reg' was set to zero for ``ABS``.  However, these
-instructions are deprecated and should no longer be used.  All legacy packet
+instructions are deprecated and SHOULD no longer be used.  All legacy packet
 access instructions belong to the "packet" conformance group.
-- 
GitLab


From 4e1215d9a1903fc9e976aa8903674d050c7af5ff Mon Sep 17 00:00:00 2001
From: Dave Thaler <dthaler1968@googlemail.com>
Date: Mon, 20 May 2024 14:52:55 -0700
Subject: [PATCH 228/950] bpf, docs: clarify sign extension of 64-bit use of
 32-bit imm

imm is defined as a 32-bit signed integer.

{MOV, K, ALU64} says it does "dst = src" (where src is 'imm') and it
does do dst = (s64)imm, which in that sense does sign extend imm. The MOVSX
instruction is explained as sign extending, so added the example of
{MOV, K, ALU64} to make this more clear.

{JLE, K, JMP} says it does "PC += offset if dst <= src" (where src is 'imm',
and the comparison is unsigned). This was apparently ambiguous to some
readers as to whether the comparison was "dst <= (u64)(u32)imm" or
"dst <= (u64)(s64)imm" so added an example to make this more clear.

v1 -> v2: Address comments from Yonghong

Signed-off-by: Dave Thaler <dthaler1968@googlemail.com>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Acked-by: David Vernet <void@manifault.com>
Link: https://lore.kernel.org/r/20240520215255.10595-1-dthaler1968@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../bpf/standardization/instruction-set.rst     | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/Documentation/bpf/standardization/instruction-set.rst b/Documentation/bpf/standardization/instruction-set.rst
index 02e2490433c64..6b11d1109f12a 100644
--- a/Documentation/bpf/standardization/instruction-set.rst
+++ b/Documentation/bpf/standardization/instruction-set.rst
@@ -393,6 +393,19 @@ The ``MOVSX`` instruction does a move operation with sign extension.
 operands into 64-bit operands.  Unlike other arithmetic instructions,
 ``MOVSX`` is only defined for register source operands (``X``).
 
+``{MOV, K, ALU64}`` means::
+
+  dst = (s64)imm
+
+``{MOV, X, ALU}`` means::
+
+  dst = (u32)src
+
+``{MOVSX, X, ALU}`` with 'offset' 8 means::
+
+  dst = (u32)(s32)(s8)src
+
+
 The ``NEG`` instruction is only defined when the source bit is clear
 (``K``).
 
@@ -491,6 +504,10 @@ Example:
 
 where 's>=' indicates a signed '>=' comparison.
 
+``{JLE, K, JMP}`` means::
+
+  if dst <= (u64)(s64)imm goto +offset
+
 ``{JA, K, JMP32}`` means::
 
   gotol +imm
-- 
GitLab


From 6a6d8b6f00ade597e0030669fae3fdf57cfba33b Mon Sep 17 00:00:00 2001
From: Dave Thaler <dthaler1968@googlemail.com>
Date: Fri, 24 May 2024 09:46:18 -0700
Subject: [PATCH 229/950] bpf, docs: Add table captions

As suggested by Ines Robles in his IETF GENART review at
https://datatracker.ietf.org/doc/review-ietf-bpf-isa-02-genart-lc-robles-2024-05-16/

Signed-off-by: Dave Thaler <dthaler1968@gmail.com>
Link: https://lore.kernel.org/r/20240524164618.18894-1-dthaler1968@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../bpf/standardization/instruction-set.rst   | 184 ++++++++++--------
 1 file changed, 102 insertions(+), 82 deletions(-)

diff --git a/Documentation/bpf/standardization/instruction-set.rst b/Documentation/bpf/standardization/instruction-set.rst
index 6b11d1109f12a..1602454fe7cfc 100644
--- a/Documentation/bpf/standardization/instruction-set.rst
+++ b/Documentation/bpf/standardization/instruction-set.rst
@@ -32,7 +32,7 @@ Types
 This document refers to integer types with the notation `SN` to specify
 a type's signedness (`S`) and bit width (`N`), respectively.
 
-.. table:: Meaning of signedness notation.
+.. table:: Meaning of signedness notation
 
   ==== =========
   S    Meaning
@@ -41,7 +41,7 @@ a type's signedness (`S`) and bit width (`N`), respectively.
   s    signed
   ==== =========
 
-.. table:: Meaning of bit-width notation.
+.. table:: Meaning of bit-width notation
 
   ===== =========
   N     Bit width
@@ -263,18 +263,20 @@ Instruction classes
 
 The three least significant bits of the 'opcode' field store the instruction class:
 
-=====  =====  ===============================  ===================================
-class  value  description                      reference
-=====  =====  ===============================  ===================================
-LD     0x0    non-standard load operations     `Load and store instructions`_
-LDX    0x1    load into register operations    `Load and store instructions`_
-ST     0x2    store from immediate operations  `Load and store instructions`_
-STX    0x3    store from register operations   `Load and store instructions`_
-ALU    0x4    32-bit arithmetic operations     `Arithmetic and jump instructions`_
-JMP    0x5    64-bit jump operations           `Arithmetic and jump instructions`_
-JMP32  0x6    32-bit jump operations           `Arithmetic and jump instructions`_
-ALU64  0x7    64-bit arithmetic operations     `Arithmetic and jump instructions`_
-=====  =====  ===============================  ===================================
+.. table:: Instruction class
+
+  =====  =====  ===============================  ===================================
+  class  value  description                      reference
+  =====  =====  ===============================  ===================================
+  LD     0x0    non-standard load operations     `Load and store instructions`_
+  LDX    0x1    load into register operations    `Load and store instructions`_
+  ST     0x2    store from immediate operations  `Load and store instructions`_
+  STX    0x3    store from register operations   `Load and store instructions`_
+  ALU    0x4    32-bit arithmetic operations     `Arithmetic and jump instructions`_
+  JMP    0x5    64-bit jump operations           `Arithmetic and jump instructions`_
+  JMP32  0x6    32-bit jump operations           `Arithmetic and jump instructions`_
+  ALU64  0x7    64-bit arithmetic operations     `Arithmetic and jump instructions`_
+  =====  =====  ===============================  ===================================
 
 Arithmetic and jump instructions
 ================================
@@ -292,6 +294,8 @@ For arithmetic and jump instructions (``ALU``, ``ALU64``, ``JMP`` and
 **s (source)**
   the source operand location, which unless otherwise specified is one of:
 
+  .. table:: Source operand location
+
   ======  =====  ==============================================
   source  value  description
   ======  =====  ==============================================
@@ -312,27 +316,29 @@ The 'code' field encodes the operation as below, where 'src' refers to the
 the source operand and 'dst' refers to the value of the destination
 register.
 
-=====  =====  =======  ==========================================================
-name   code   offset   description
-=====  =====  =======  ==========================================================
-ADD    0x0    0        dst += src
-SUB    0x1    0        dst -= src
-MUL    0x2    0        dst \*= src
-DIV    0x3    0        dst = (src != 0) ? (dst / src) : 0
-SDIV   0x3    1        dst = (src != 0) ? (dst s/ src) : 0
-OR     0x4    0        dst \|= src
-AND    0x5    0        dst &= src
-LSH    0x6    0        dst <<= (src & mask)
-RSH    0x7    0        dst >>= (src & mask)
-NEG    0x8    0        dst = -dst
-MOD    0x9    0        dst = (src != 0) ? (dst % src) : dst
-SMOD   0x9    1        dst = (src != 0) ? (dst s% src) : dst
-XOR    0xa    0        dst ^= src
-MOV    0xb    0        dst = src
-MOVSX  0xb    8/16/32  dst = (s8,s16,s32)src
-ARSH   0xc    0        :term:`sign extending<Sign Extend>` dst >>= (src & mask)
-END    0xd    0        byte swap operations (see `Byte swap instructions`_ below)
-=====  =====  =======  ==========================================================
+.. table:: Arithmetic instructions
+
+  =====  =====  =======  ==========================================================
+  name   code   offset   description
+  =====  =====  =======  ==========================================================
+  ADD    0x0    0        dst += src
+  SUB    0x1    0        dst -= src
+  MUL    0x2    0        dst \*= src
+  DIV    0x3    0        dst = (src != 0) ? (dst / src) : 0
+  SDIV   0x3    1        dst = (src != 0) ? (dst s/ src) : 0
+  OR     0x4    0        dst \|= src
+  AND    0x5    0        dst &= src
+  LSH    0x6    0        dst <<= (src & mask)
+  RSH    0x7    0        dst >>= (src & mask)
+  NEG    0x8    0        dst = -dst
+  MOD    0x9    0        dst = (src != 0) ? (dst % src) : dst
+  SMOD   0x9    1        dst = (src != 0) ? (dst s% src) : dst
+  XOR    0xa    0        dst ^= src
+  MOV    0xb    0        dst = src
+  MOVSX  0xb    8/16/32  dst = (s8,s16,s32)src
+  ARSH   0xc    0        :term:`sign extending<Sign Extend>` dst >>= (src & mask)
+  END    0xd    0        byte swap operations (see `Byte swap instructions`_ below)
+  =====  =====  =======  ==========================================================
 
 Underflow and overflow are allowed during arithmetic operations, meaning
 the 64-bit or 32-bit value will wrap. If BPF program execution would
@@ -426,13 +432,15 @@ select what byte order the operation converts from or to. For
 ``ALU64``, the 1-bit source operand field in the opcode is reserved
 and MUST be set to 0.
 
-=====  ========  =====  =================================================
-class  source    value  description
-=====  ========  =====  =================================================
-ALU    TO_LE     0      convert between host byte order and little endian
-ALU    TO_BE     1      convert between host byte order and big endian
-ALU64  Reserved  0      do byte swap unconditionally
-=====  ========  =====  =================================================
+.. table:: Byte swap instructions
+
+  =====  ========  =====  =================================================
+  class  source    value  description
+  =====  ========  =====  =================================================
+  ALU    TO_LE     0      convert between host byte order and little endian
+  ALU    TO_BE     1      convert between host byte order and big endian
+  ALU64  Reserved  0      do byte swap unconditionally
+  =====  ========  =====  =================================================
 
 The 'imm' field encodes the width of the swap operations.  The following widths
 are supported: 16, 32 and 64.  Width 64 operations belong to the base64
@@ -468,27 +476,29 @@ otherwise identical operations, and indicates the base64 conformance
 group unless otherwise specified.
 The 'code' field encodes the operation as below:
 
-========  =====  =======  =================================  ===================================================
-code      value  src_reg  description                        notes
-========  =====  =======  =================================  ===================================================
-JA        0x0    0x0      PC += offset                       {JA, K, JMP} only
-JA        0x0    0x0      PC += imm                          {JA, K, JMP32} only
-JEQ       0x1    any      PC += offset if dst == src
-JGT       0x2    any      PC += offset if dst > src          unsigned
-JGE       0x3    any      PC += offset if dst >= src         unsigned
-JSET      0x4    any      PC += offset if dst & src
-JNE       0x5    any      PC += offset if dst != src
-JSGT      0x6    any      PC += offset if dst > src          signed
-JSGE      0x7    any      PC += offset if dst >= src         signed
-CALL      0x8    0x0      call helper function by static ID  {CALL, K, JMP} only, see `Helper functions`_
-CALL      0x8    0x1      call PC += imm                     {CALL, K, JMP} only, see `Program-local functions`_
-CALL      0x8    0x2      call helper function by BTF ID     {CALL, K, JMP} only, see `Helper functions`_
-EXIT      0x9    0x0      return                             {CALL, K, JMP} only
-JLT       0xa    any      PC += offset if dst < src          unsigned
-JLE       0xb    any      PC += offset if dst <= src         unsigned
-JSLT      0xc    any      PC += offset if dst < src          signed
-JSLE      0xd    any      PC += offset if dst <= src         signed
-========  =====  =======  =================================  ===================================================
+.. table:: Jump instructions
+
+  ========  =====  =======  =================================  ===================================================
+  code      value  src_reg  description                        notes
+  ========  =====  =======  =================================  ===================================================
+  JA        0x0    0x0      PC += offset                       {JA, K, JMP} only
+  JA        0x0    0x0      PC += imm                          {JA, K, JMP32} only
+  JEQ       0x1    any      PC += offset if dst == src
+  JGT       0x2    any      PC += offset if dst > src          unsigned
+  JGE       0x3    any      PC += offset if dst >= src         unsigned
+  JSET      0x4    any      PC += offset if dst & src
+  JNE       0x5    any      PC += offset if dst != src
+  JSGT      0x6    any      PC += offset if dst > src          signed
+  JSGE      0x7    any      PC += offset if dst >= src         signed
+  CALL      0x8    0x0      call helper function by static ID  {CALL, K, JMP} only, see `Helper functions`_
+  CALL      0x8    0x1      call PC += imm                     {CALL, K, JMP} only, see `Program-local functions`_
+  CALL      0x8    0x2      call helper function by BTF ID     {CALL, K, JMP} only, see `Helper functions`_
+  EXIT      0x9    0x0      return                             {CALL, K, JMP} only
+  JLT       0xa    any      PC += offset if dst < src          unsigned
+  JLE       0xb    any      PC += offset if dst <= src         unsigned
+  JSLT      0xc    any      PC += offset if dst < src          signed
+  JSLE      0xd    any      PC += offset if dst <= src         signed
+  ========  =====  =======  =================================  ===================================================
 
 where 'PC' denotes the program counter, and the offset to increment by
 is in units of 64-bit instructions relative to the instruction following
@@ -559,6 +569,8 @@ For load and store instructions (``LD``, ``LDX``, ``ST``, and ``STX``), the
 **mode**
   The mode modifier is one of:
 
+  .. table:: Mode modifier
+
     =============  =====  ====================================  =============
     mode modifier  value  description                           reference
     =============  =====  ====================================  =============
@@ -573,6 +585,8 @@ For load and store instructions (``LD``, ``LDX``, ``ST``, and ``STX``), the
 **sz (size)**
   The size modifier is one of:
 
+  .. table:: Size modifier
+
     ====  =====  =====================
     size  value  description
     ====  =====  =====================
@@ -641,14 +655,16 @@ The 'imm' field is used to encode the actual atomic operation.
 Simple atomic operation use a subset of the values defined to encode
 arithmetic operations in the 'imm' field to encode the atomic operation:
 
-========  =====  ===========
-imm       value  description
-========  =====  ===========
-ADD       0x00   atomic add
-OR        0x40   atomic or
-AND       0x50   atomic and
-XOR       0xa0   atomic xor
-========  =====  ===========
+.. table:: Simple atomic operations
+
+  ========  =====  ===========
+  imm       value  description
+  ========  =====  ===========
+  ADD       0x00   atomic add
+  OR        0x40   atomic or
+  AND       0x50   atomic and
+  XOR       0xa0   atomic xor
+  ========  =====  ===========
 
 
 ``{ATOMIC, W, STX}`` with 'imm' = ADD means::
@@ -662,6 +678,8 @@ XOR       0xa0   atomic xor
 In addition to the simple atomic operations, there also is a modifier and
 two complex atomic operations:
 
+.. table:: Complex atomic operations
+
 ===========  ================  ===========================
 imm          value             description
 ===========  ================  ===========================
@@ -695,17 +713,19 @@ The following table defines a set of ``{IMM, DW, LD}`` instructions
 with opcode subtypes in the 'src_reg' field, using new terms such as "map"
 defined further below:
 
-=======  =========================================  ===========  ==============
-src_reg  pseudocode                                 imm type     dst type
-=======  =========================================  ===========  ==============
-0x0      dst = (next_imm << 32) | imm               integer      integer
-0x1      dst = map_by_fd(imm)                       map fd       map
-0x2      dst = map_val(map_by_fd(imm)) + next_imm   map fd       data address
-0x3      dst = var_addr(imm)                        variable id  data address
-0x4      dst = code_addr(imm)                       integer      code address
-0x5      dst = map_by_idx(imm)                      map index    map
-0x6      dst = map_val(map_by_idx(imm)) + next_imm  map index    data address
-=======  =========================================  ===========  ==============
+.. table:: 64-bit immediate instructions
+
+  =======  =========================================  ===========  ==============
+  src_reg  pseudocode                                 imm type     dst type
+  =======  =========================================  ===========  ==============
+  0x0      dst = (next_imm << 32) | imm               integer      integer
+  0x1      dst = map_by_fd(imm)                       map fd       map
+  0x2      dst = map_val(map_by_fd(imm)) + next_imm   map fd       data address
+  0x3      dst = var_addr(imm)                        variable id  data address
+  0x4      dst = code_addr(imm)                       integer      code address
+  0x5      dst = map_by_idx(imm)                      map index    map
+  0x6      dst = map_val(map_by_idx(imm)) + next_imm  map index    data address
+  =======  =========================================  ===========  ==============
 
 where
 
-- 
GitLab


From f980f13e4eb299abba6692365315196e1ba6fd2c Mon Sep 17 00:00:00 2001
From: Dave Thaler <dthaler1968@googlemail.com>
Date: Sat, 25 May 2024 08:33:32 -0700
Subject: [PATCH 230/950] bpf, docs: Clarify call local offset

In the Jump instructions section it explains that the offset is
"relative to the instruction following the jump instruction".
But the program-local section confusingly said "referenced by
offset from the call instruction, similar to JA".

This patch updates that sentence with consistent wording, saying
it's relative to the instruction following the call instruction.

Signed-off-by: Dave Thaler <dthaler1968@gmail.com>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20240525153332.21355-1-dthaler1968@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 Documentation/bpf/standardization/instruction-set.rst | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/Documentation/bpf/standardization/instruction-set.rst b/Documentation/bpf/standardization/instruction-set.rst
index 1602454fe7cfc..08f614b10a56b 100644
--- a/Documentation/bpf/standardization/instruction-set.rst
+++ b/Documentation/bpf/standardization/instruction-set.rst
@@ -552,9 +552,10 @@ is outside the scope of this document and is left for future work.
 Program-local functions
 ~~~~~~~~~~~~~~~~~~~~~~~
 Program-local functions are functions exposed by the same BPF program as the
-caller, and are referenced by offset from the call instruction, similar to
-``JA``.  The offset is encoded in the 'imm' field of the call instruction.
-An ``EXIT`` within the program-local function will return to the caller.
+caller, and are referenced by offset from the instruction following the call
+instruction, similar to ``JA``.  The offset is encoded in the 'imm' field of
+the call instruction. An ``EXIT`` within the program-local function will
+return to the caller.
 
 Load and store instructions
 ===========================
-- 
GitLab


From 46ba0e49b64232adac35a2bc892f1710c5b0fb7f Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Tue, 21 May 2024 09:33:57 -0700
Subject: [PATCH 231/950] bpf: fix multi-uprobe PID filtering logic

Current implementation of PID filtering logic for multi-uprobes in
uprobe_prog_run() is filtering down to exact *thread*, while the intent
for PID filtering it to filter by *process* instead. The check in
uprobe_prog_run() also differs from the analogous one in
uprobe_multi_link_filter() for some reason. The latter is correct,
checking task->mm, not the task itself.

Fix the check in uprobe_prog_run() to perform the same task->mm check.

While doing this, we also update get_pid_task() use to use PIDTYPE_TGID
type of lookup, given the intent is to get a representative task of an
entire process. This doesn't change behavior, but seems more logical. It
would hold task group leader task now, not any random thread task.

Last but not least, given multi-uprobe support is half-broken due to
this PID filtering logic (depending on whether PID filtering is
important or not), we need to make it easy for user space consumers
(including libbpf) to easily detect whether PID filtering logic was
already fixed.

We do it here by adding an early check on passed pid parameter. If it's
negative (and so has no chance of being a valid PID), we return -EINVAL.
Previous behavior would eventually return -ESRCH ("No process found"),
given there can't be any process with negative PID. This subtle change
won't make any practical change in behavior, but will allow applications
to detect PID filtering fixes easily. Libbpf fixes take advantage of
this in the next patch.

Cc: stable@vger.kernel.org
Acked-by: Jiri Olsa <jolsa@kernel.org>
Fixes: b733eeade420 ("bpf: Add pid filter support for uprobe_multi link")
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20240521163401.3005045-2-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/trace/bpf_trace.c                                  | 8 ++++----
 .../testing/selftests/bpf/prog_tests/uprobe_multi_test.c  | 2 +-
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index f5154c051d2c1..1baaeb9ca2055 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -3295,7 +3295,7 @@ static int uprobe_prog_run(struct bpf_uprobe *uprobe,
 	struct bpf_run_ctx *old_run_ctx;
 	int err = 0;
 
-	if (link->task && current != link->task)
+	if (link->task && current->mm != link->task->mm)
 		return 0;
 
 	if (sleepable)
@@ -3396,8 +3396,9 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
 	upath = u64_to_user_ptr(attr->link_create.uprobe_multi.path);
 	uoffsets = u64_to_user_ptr(attr->link_create.uprobe_multi.offsets);
 	cnt = attr->link_create.uprobe_multi.cnt;
+	pid = attr->link_create.uprobe_multi.pid;
 
-	if (!upath || !uoffsets || !cnt)
+	if (!upath || !uoffsets || !cnt || pid < 0)
 		return -EINVAL;
 	if (cnt > MAX_UPROBE_MULTI_CNT)
 		return -E2BIG;
@@ -3421,10 +3422,9 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
 		goto error_path_put;
 	}
 
-	pid = attr->link_create.uprobe_multi.pid;
 	if (pid) {
 		rcu_read_lock();
-		task = get_pid_task(find_vpid(pid), PIDTYPE_PID);
+		task = get_pid_task(find_vpid(pid), PIDTYPE_TGID);
 		rcu_read_unlock();
 		if (!task) {
 			err = -ESRCH;
diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
index 8269cdee33ae9..38fda42fd70f9 100644
--- a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
@@ -397,7 +397,7 @@ static void test_attach_api_fails(void)
 	link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts);
 	if (!ASSERT_ERR(link_fd, "link_fd"))
 		goto cleanup;
-	ASSERT_EQ(link_fd, -ESRCH, "pid_is_wrong");
+	ASSERT_EQ(link_fd, -EINVAL, "pid_is_wrong");
 
 cleanup:
 	if (link_fd >= 0)
-- 
GitLab


From 4a8f635a60540888dab3804992e86410360339c8 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Tue, 21 May 2024 09:33:58 -0700
Subject: [PATCH 232/950] bpf: remove unnecessary rcu_read_{lock,unlock}() in
 multi-uprobe attach logic

get_pid_task() internally already calls rcu_read_lock() and
rcu_read_unlock(), so there is no point to do this one extra time.

This is a drive-by improvement and has no correctness implications.

Acked-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20240521163401.3005045-3-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/trace/bpf_trace.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 1baaeb9ca2055..6249dac617018 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -3423,9 +3423,7 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
 	}
 
 	if (pid) {
-		rcu_read_lock();
 		task = get_pid_task(find_vpid(pid), PIDTYPE_TGID);
-		rcu_read_unlock();
 		if (!task) {
 			err = -ESRCH;
 			goto error_path_put;
-- 
GitLab


From 04d939a2ab229a3821f04fc81f7c027842f501f1 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Tue, 21 May 2024 09:33:59 -0700
Subject: [PATCH 233/950] libbpf: detect broken PID filtering logic for
 multi-uprobe

Libbpf is automatically (and transparently to user) detecting
multi-uprobe support in the kernel, and, if supported, uses
multi-uprobes to improve USDT attachment speed.

USDTs can be attached system-wide or for the specific process by PID. In
the latter case, we rely on correct kernel logic of not triggering USDT
for unrelated processes.

As such, on older kernels that do support multi-uprobes, but still have
broken PID filtering logic, we need to fall back to singular uprobes.

Unfortunately, whether user is using PID filtering or not is known at
the attachment time, which happens after relevant BPF programs were
loaded into the kernel. Also unfortunately, we need to make a call
whether to use multi-uprobes or singular uprobe for SEC("usdt") programs
during BPF object load time, at which point we have no information about
possible PID filtering.

The distinction between single and multi-uprobes is small, but important
for the kernel. Multi-uprobes get BPF_TRACE_UPROBE_MULTI attach type,
and kernel internally substitiute different implementation of some of
BPF helpers (e.g., bpf_get_attach_cookie()) depending on whether uprobe
is multi or singular. So, multi-uprobes and singular uprobes cannot be
intermixed.

All the above implies that we have to make an early and conservative
call about the use of multi-uprobes. And so this patch modifies libbpf's
existing feature detector for multi-uprobe support to also check correct
PID filtering. If PID filtering is not yet fixed, we fall back to
singular uprobes for USDTs.

This extension to feature detection is simple thanks to kernel's -EINVAL
addition for pid < 0.

Acked-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20240521163401.3005045-4-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/features.c | 31 ++++++++++++++++++++++++++++++-
 1 file changed, 30 insertions(+), 1 deletion(-)

diff --git a/tools/lib/bpf/features.c b/tools/lib/bpf/features.c
index a336786a22a38..3df0125ed5fa7 100644
--- a/tools/lib/bpf/features.c
+++ b/tools/lib/bpf/features.c
@@ -392,11 +392,40 @@ static int probe_uprobe_multi_link(int token_fd)
 	link_fd = bpf_link_create(prog_fd, -1, BPF_TRACE_UPROBE_MULTI, &link_opts);
 	err = -errno; /* close() can clobber errno */
 
+	if (link_fd >= 0 || err != -EBADF) {
+		close(link_fd);
+		close(prog_fd);
+		return 0;
+	}
+
+	/* Initial multi-uprobe support in kernel didn't handle PID filtering
+	 * correctly (it was doing thread filtering, not process filtering).
+	 * So now we'll detect if PID filtering logic was fixed, and, if not,
+	 * we'll pretend multi-uprobes are not supported, if not.
+	 * Multi-uprobes are used in USDT attachment logic, and we need to be
+	 * conservative here, because multi-uprobe selection happens early at
+	 * load time, while the use of PID filtering is known late at
+	 * attachment time, at which point it's too late to undo multi-uprobe
+	 * selection.
+	 *
+	 * Creating uprobe with pid == -1 for (invalid) '/' binary will fail
+	 * early with -EINVAL on kernels with fixed PID filtering logic;
+	 * otherwise -ESRCH would be returned if passed correct binary path
+	 * (but we'll just get -BADF, of course).
+	 */
+	link_opts.uprobe_multi.pid = -1; /* invalid PID */
+	link_opts.uprobe_multi.path = "/"; /* invalid path */
+	link_opts.uprobe_multi.offsets = &offset;
+	link_opts.uprobe_multi.cnt = 1;
+
+	link_fd = bpf_link_create(prog_fd, -1, BPF_TRACE_UPROBE_MULTI, &link_opts);
+	err = -errno; /* close() can clobber errno */
+
 	if (link_fd >= 0)
 		close(link_fd);
 	close(prog_fd);
 
-	return link_fd < 0 && err == -EBADF;
+	return link_fd < 0 && err == -EINVAL;
 }
 
 static int probe_kern_bpf_cookie(int token_fd)
-- 
GitLab


From 70342420a1cf1173bdec456e5fa574a804e422db Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Tue, 21 May 2024 09:34:00 -0700
Subject: [PATCH 234/950] selftests/bpf: extend multi-uprobe tests with child
 thread case

Extend existing multi-uprobe tests to test that PID filtering works
correctly. We already have child *process* tests, but we need also child
*thread* tests. This patch adds spawn_thread() helper to start child
thread, wait for it to be ready, and then instruct it to trigger desired
uprobes.

Additionally, we extend BPF-side code to track thread ID, not just
process ID. Also we detect whether extraneous triggerings with
unexpected process IDs happened, and validate that none of that happened
in practice.

These changes prove that fixed PID filtering logic for multi-uprobe
works as expected. These tests fail on old kernels.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20240521163401.3005045-5-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../bpf/prog_tests/uprobe_multi_test.c        | 107 ++++++++++++++++--
 .../selftests/bpf/progs/uprobe_multi.c        |  17 ++-
 2 files changed, 115 insertions(+), 9 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
index 38fda42fd70f9..677232d314322 100644
--- a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 
 #include <unistd.h>
+#include <pthread.h>
 #include <test_progs.h>
 #include "uprobe_multi.skel.h"
 #include "uprobe_multi_bench.skel.h"
@@ -27,7 +28,10 @@ noinline void uprobe_multi_func_3(void)
 
 struct child {
 	int go[2];
+	int c2p[2]; /* child -> parent channel */
 	int pid;
+	int tid;
+	pthread_t thread;
 };
 
 static void release_child(struct child *child)
@@ -38,6 +42,10 @@ static void release_child(struct child *child)
 		return;
 	close(child->go[1]);
 	close(child->go[0]);
+	if (child->thread)
+		pthread_join(child->thread, NULL);
+	close(child->c2p[0]);
+	close(child->c2p[1]);
 	if (child->pid > 0)
 		waitpid(child->pid, &child_status, 0);
 }
@@ -63,7 +71,7 @@ static struct child *spawn_child(void)
 	if (pipe(child.go))
 		return NULL;
 
-	child.pid = fork();
+	child.pid = child.tid = fork();
 	if (child.pid < 0) {
 		release_child(&child);
 		errno = EINVAL;
@@ -89,6 +97,66 @@ static struct child *spawn_child(void)
 	return &child;
 }
 
+static void *child_thread(void *ctx)
+{
+	struct child *child = ctx;
+	int c = 0, err;
+
+	child->tid = syscall(SYS_gettid);
+
+	/* let parent know we are ready */
+	err = write(child->c2p[1], &c, 1);
+	if (err != 1)
+		pthread_exit(&err);
+
+	/* wait for parent's kick */
+	err = read(child->go[0], &c, 1);
+	if (err != 1)
+		pthread_exit(&err);
+
+	uprobe_multi_func_1();
+	uprobe_multi_func_2();
+	uprobe_multi_func_3();
+
+	err = 0;
+	pthread_exit(&err);
+}
+
+static struct child *spawn_thread(void)
+{
+	static struct child child;
+	int c, err;
+
+	/* pipe to notify child to execute the trigger functions */
+	if (pipe(child.go))
+		return NULL;
+	/* pipe to notify parent that child thread is ready */
+	if (pipe(child.c2p)) {
+		close(child.go[0]);
+		close(child.go[1]);
+		return NULL;
+	}
+
+	child.pid = getpid();
+
+	err = pthread_create(&child.thread, NULL, child_thread, &child);
+	if (err) {
+		err = -errno;
+		close(child.go[0]);
+		close(child.go[1]);
+		close(child.c2p[0]);
+		close(child.c2p[1]);
+		errno = -err;
+		return NULL;
+	}
+
+	err = read(child.c2p[0], &c, 1);
+	if (!ASSERT_EQ(err, 1, "child_thread_ready"))
+		return NULL;
+
+	return &child;
+}
+
 static void uprobe_multi_test_run(struct uprobe_multi *skel, struct child *child)
 {
 	skel->bss->uprobe_multi_func_1_addr = (__u64) uprobe_multi_func_1;
@@ -103,15 +171,22 @@ static void uprobe_multi_test_run(struct uprobe_multi *skel, struct child *child
 	 * passed at the probe attach.
 	 */
 	skel->bss->pid = child ? 0 : getpid();
+	skel->bss->expect_pid = child ? child->pid : 0;
+
+	/* trigger all probes, if we are testing child *process*, just to make
+	 * sure that PID filtering doesn't let through activations from wrong
+	 * PIDs; when we test child *thread*, we don't want to do this to
+	 * avoid double counting number of triggering events
+	 */
+	if (!child || !child->thread) {
+		uprobe_multi_func_1();
+		uprobe_multi_func_2();
+		uprobe_multi_func_3();
+	}
 
 	if (child)
 		kick_child(child);
 
-	/* trigger all probes */
-	uprobe_multi_func_1();
-	uprobe_multi_func_2();
-	uprobe_multi_func_3();
-
 	/*
 	 * There are 2 entry and 2 exit probe called for each uprobe_multi_func_[123]
 	 * function and each slepable probe (6) increments uprobe_multi_sleep_result.
@@ -126,8 +201,12 @@ static void uprobe_multi_test_run(struct uprobe_multi *skel, struct child *child
 
 	ASSERT_EQ(skel->bss->uprobe_multi_sleep_result, 6, "uprobe_multi_sleep_result");
 
-	if (child)
+	ASSERT_FALSE(skel->bss->bad_pid_seen, "bad_pid_seen");
+
+	if (child) {
 		ASSERT_EQ(skel->bss->child_pid, child->pid, "uprobe_multi_child_pid");
+		ASSERT_EQ(skel->bss->child_tid, child->tid, "uprobe_multi_child_tid");
+	}
 }
 
 static void test_skel_api(void)
@@ -210,6 +289,13 @@ test_attach_api(const char *binary, const char *pattern, struct bpf_uprobe_multi
 		return;
 
 	__test_attach_api(binary, pattern, opts, child);
+
+	/* pid filter (thread) */
+	child = spawn_thread();
+	if (!ASSERT_OK_PTR(child, "spawn_thread"))
+		return;
+
+	__test_attach_api(binary, pattern, opts, child);
 }
 
 static void test_attach_api_pattern(void)
@@ -495,6 +581,13 @@ static void test_link_api(void)
 		return;
 
 	__test_link_api(child);
+
+	/* pid filter (thread) */
+	child = spawn_thread();
+	if (!ASSERT_OK_PTR(child, "spawn_thread"))
+		return;
+
+	__test_link_api(child);
 }
 
 static void test_bench_attach_uprobe(void)
diff --git a/tools/testing/selftests/bpf/progs/uprobe_multi.c b/tools/testing/selftests/bpf/progs/uprobe_multi.c
index 419d9aa28fce5..86a7ff5d3726d 100644
--- a/tools/testing/selftests/bpf/progs/uprobe_multi.c
+++ b/tools/testing/selftests/bpf/progs/uprobe_multi.c
@@ -22,6 +22,10 @@ __u64 uprobe_multi_sleep_result = 0;
 
 int pid = 0;
 int child_pid = 0;
+int child_tid = 0;
+
+int expect_pid = 0;
+bool bad_pid_seen = false;
 
 bool test_cookie = false;
 void *user_ptr = 0;
@@ -36,11 +40,19 @@ static __always_inline bool verify_sleepable_user_copy(void)
 
 static void uprobe_multi_check(void *ctx, bool is_return, bool is_sleep)
 {
-	child_pid = bpf_get_current_pid_tgid() >> 32;
+	__u64 cur_pid_tgid = bpf_get_current_pid_tgid();
+	__u32 cur_pid;
 
-	if (pid && child_pid != pid)
+	cur_pid = cur_pid_tgid >> 32;
+	if (pid && cur_pid != pid)
 		return;
 
+	if (expect_pid && cur_pid != expect_pid)
+		bad_pid_seen = true;
+
+	child_pid = cur_pid_tgid >> 32;
+	child_tid = (__u32)cur_pid_tgid;
+
 	__u64 cookie = test_cookie ? bpf_get_attach_cookie(ctx) : 0;
 	__u64 addr = bpf_get_func_ip(ctx);
 
@@ -97,5 +109,6 @@ int uretprobe_sleep(struct pt_regs *ctx)
 SEC("uprobe.multi//proc/self/exe:uprobe_multi_func_*")
 int uprobe_extra(struct pt_regs *ctx)
 {
+	/* we need this one just to mix PID-filtered and global uprobes */
 	return 0;
 }
-- 
GitLab


From 198034a87dfeb64d5a8359a5089022c6b923646e Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Tue, 21 May 2024 09:34:01 -0700
Subject: [PATCH 235/950] selftests/bpf: extend multi-uprobe tests with USDTs

Validate libbpf's USDT-over-multi-uprobe logic by adding USDTs to
existing multi-uprobe tests. This checks correct libbpf fallback to
singular uprobes (when run on older kernels with buggy PID filtering).
We reuse already established child process and child thread testing
infrastructure, so additions are minimal. These test fail on either
older kernels or older version of libbpf that doesn't detect PID
filtering problems.

Acked-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20240521163401.3005045-6-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../bpf/prog_tests/uprobe_multi_test.c        | 25 ++++++++++++++
 .../selftests/bpf/progs/uprobe_multi.c        | 33 +++++++++++++++++--
 2 files changed, 56 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
index 677232d314322..bf6ca8e3eb131 100644
--- a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
@@ -8,6 +8,7 @@
 #include "uprobe_multi_usdt.skel.h"
 #include "bpf/libbpf_internal.h"
 #include "testing_helpers.h"
+#include "../sdt.h"
 
 static char test_data[] = "test_data";
 
@@ -26,6 +27,11 @@ noinline void uprobe_multi_func_3(void)
 	asm volatile ("");
 }
 
+noinline void usdt_trigger(void)
+{
+	STAP_PROBE(test, pid_filter_usdt);
+}
+
 struct child {
 	int go[2];
 	int c2p[2]; /* child -> parent channel */
@@ -90,6 +96,7 @@ static struct child *spawn_child(void)
 		uprobe_multi_func_1();
 		uprobe_multi_func_2();
 		uprobe_multi_func_3();
+		usdt_trigger();
 
 		exit(errno);
 	}
@@ -117,6 +124,7 @@ static void *child_thread(void *ctx)
 	uprobe_multi_func_1();
 	uprobe_multi_func_2();
 	uprobe_multi_func_3();
+	usdt_trigger();
 
 	err = 0;
 	pthread_exit(&err);
@@ -182,6 +190,7 @@ static void uprobe_multi_test_run(struct uprobe_multi *skel, struct child *child
 		uprobe_multi_func_1();
 		uprobe_multi_func_2();
 		uprobe_multi_func_3();
+		usdt_trigger();
 	}
 
 	if (child)
@@ -269,8 +278,24 @@ __test_attach_api(const char *binary, const char *pattern, struct bpf_uprobe_mul
 	if (!ASSERT_OK_PTR(skel->links.uprobe_extra, "bpf_program__attach_uprobe_multi"))
 		goto cleanup;
 
+	/* Attach (uprobe-backed) USDTs */
+	skel->links.usdt_pid = bpf_program__attach_usdt(skel->progs.usdt_pid, pid, binary,
+							"test", "pid_filter_usdt", NULL);
+	if (!ASSERT_OK_PTR(skel->links.usdt_pid, "attach_usdt_pid"))
+		goto cleanup;
+
+	skel->links.usdt_extra = bpf_program__attach_usdt(skel->progs.usdt_extra, -1, binary,
+							  "test", "pid_filter_usdt", NULL);
+	if (!ASSERT_OK_PTR(skel->links.usdt_extra, "attach_usdt_extra"))
+		goto cleanup;
+
 	uprobe_multi_test_run(skel, child);
 
+	ASSERT_FALSE(skel->bss->bad_pid_seen_usdt, "bad_pid_seen_usdt");
+	if (child) {
+		ASSERT_EQ(skel->bss->child_pid_usdt, child->pid, "usdt_multi_child_pid");
+		ASSERT_EQ(skel->bss->child_tid_usdt, child->tid, "usdt_multi_child_tid");
+	}
 cleanup:
 	uprobe_multi__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/progs/uprobe_multi.c b/tools/testing/selftests/bpf/progs/uprobe_multi.c
index 86a7ff5d3726d..44190efcdba21 100644
--- a/tools/testing/selftests/bpf/progs/uprobe_multi.c
+++ b/tools/testing/selftests/bpf/progs/uprobe_multi.c
@@ -1,8 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <linux/bpf.h>
+#include "vmlinux.h"
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
-#include <stdbool.h>
+#include <bpf/usdt.bpf.h>
 
 char _license[] SEC("license") = "GPL";
 
@@ -23,9 +23,12 @@ __u64 uprobe_multi_sleep_result = 0;
 int pid = 0;
 int child_pid = 0;
 int child_tid = 0;
+int child_pid_usdt = 0;
+int child_tid_usdt = 0;
 
 int expect_pid = 0;
 bool bad_pid_seen = false;
+bool bad_pid_seen_usdt = false;
 
 bool test_cookie = false;
 void *user_ptr = 0;
@@ -112,3 +115,29 @@ int uprobe_extra(struct pt_regs *ctx)
 	/* we need this one just to mix PID-filtered and global uprobes */
 	return 0;
 }
+
+SEC("usdt")
+int usdt_pid(struct pt_regs *ctx)
+{
+	__u64 cur_pid_tgid = bpf_get_current_pid_tgid();
+	__u32 cur_pid;
+
+	cur_pid = cur_pid_tgid >> 32;
+	if (pid && cur_pid != pid)
+		return 0;
+
+	if (expect_pid && cur_pid != expect_pid)
+		bad_pid_seen_usdt = true;
+
+	child_pid_usdt = cur_pid_tgid >> 32;
+	child_tid_usdt = (__u32)cur_pid_tgid;
+
+	return 0;
+}
+
+SEC("usdt")
+int usdt_extra(struct pt_regs *ctx)
+{
+	/* we need this one just to mix PID-filtered and global USDT probes */
+	return 0;
+}
-- 
GitLab


From dd6a403795f0c7b5c566f86f2ee6b687278d3c1c Mon Sep 17 00:00:00 2001
From: Shahab Vahedi <shahab@synopsys.com>
Date: Sat, 25 May 2024 05:56:28 +0200
Subject: [PATCH 236/950] ARC, bpf: Fix issues reported by the static analyzers

Also updated couple of comments along the way.

One of the issues reported was indeed a bug in the code:

  memset(ctx, 0, sizeof(ctx))      // original line
  memset(ctx, 0, sizeof(*ctx))     // fixed line

That was a nice catch.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202405222314.UG5F2NHn-lkp@intel.com/
Closes: https://lore.kernel.org/oe-kbuild-all/202405232036.Xqoc3b0J-lkp@intel.com/
Signed-off-by: Shahab Vahedi <shahab@synopsys.com>
Link: https://lore.kernel.org/r/20240525035628.1026-1-list+bpf@vahedi.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/arc/net/bpf_jit.h       |  2 +-
 arch/arc/net/bpf_jit_arcv2.c | 10 ++++++----
 arch/arc/net/bpf_jit_core.c  | 22 +++++++++++-----------
 3 files changed, 18 insertions(+), 16 deletions(-)

diff --git a/arch/arc/net/bpf_jit.h b/arch/arc/net/bpf_jit.h
index ec44873c42d15..495f3023e4c18 100644
--- a/arch/arc/net/bpf_jit.h
+++ b/arch/arc/net/bpf_jit.h
@@ -39,7 +39,7 @@
 
 /************** Functions that the back-end must provide **************/
 /* Extension for 32-bit operations. */
-inline u8 zext(u8 *buf, u8 rd);
+u8 zext(u8 *buf, u8 rd);
 /***** Moves *****/
 u8 mov_r32(u8 *buf, u8 rd, u8 rs, u8 sign_ext);
 u8 mov_r32_i32(u8 *buf, u8 reg, s32 imm);
diff --git a/arch/arc/net/bpf_jit_arcv2.c b/arch/arc/net/bpf_jit_arcv2.c
index 31bfb6e9ce00f..4458e409ca0a8 100644
--- a/arch/arc/net/bpf_jit_arcv2.c
+++ b/arch/arc/net/bpf_jit_arcv2.c
@@ -62,7 +62,7 @@ enum {
  *   If/when we decide to add ARCv2 instructions that do use register pairs,
  *   the mapping, hopefully, doesn't need to be revisited.
  */
-const u8 bpf2arc[][2] = {
+static const u8 bpf2arc[][2] = {
 	/* Return value from in-kernel function, and exit value from eBPF */
 	[BPF_REG_0] = {ARC_R_8, ARC_R_9},
 	/* Arguments from eBPF program to in-kernel function */
@@ -1302,7 +1302,7 @@ static u8 arc_b(u8 *buf, s32 offset)
 
 /************* Packers (Deal with BPF_REGs) **************/
 
-inline u8 zext(u8 *buf, u8 rd)
+u8 zext(u8 *buf, u8 rd)
 {
 	if (rd != BPF_REG_FP)
 		return arc_movi_r(buf, REG_HI(rd), 0);
@@ -2235,6 +2235,7 @@ u8 gen_swap(u8 *buf, u8 rd, u8 size, u8 endian, bool force, bool do_zext)
 			break;
 		default:
 			/* The caller must have handled this. */
+			break;
 		}
 	} else {
 		/*
@@ -2253,6 +2254,7 @@ u8 gen_swap(u8 *buf, u8 rd, u8 size, u8 endian, bool force, bool do_zext)
 			break;
 		default:
 			/* The caller must have handled this. */
+			break;
 		}
 	}
 
@@ -2517,7 +2519,7 @@ u8 arc_epilogue(u8 *buf, u32 usage, u16 frame_size)
 #define JCC64_NR_OF_JMPS 3	/* Number of jumps in jcc64 template. */
 #define JCC64_INSNS_TO_END 3	/* Number of insn. inclusive the 2nd jmp to end. */
 #define JCC64_SKIP_JMP 1	/* Index of the "skip" jump to "end". */
-const struct {
+static const struct {
 	/*
 	 * "jit_off" is common between all "jmp[]" and is coupled with
 	 * "cond" of each "jmp[]" instance. e.g.:
@@ -2883,7 +2885,7 @@ u8 gen_jmp_64(u8 *buf, u8 rd, u8 rs, u8 cond, u32 curr_off, u32 targ_off)
  * The "ARC_CC_SET" becomes "CC_unequal" because of the "tst"
  * instruction that precedes the conditional branch.
  */
-const u8 arcv2_32_jmps[ARC_CC_LAST] = {
+static const u8 arcv2_32_jmps[ARC_CC_LAST] = {
 	[ARC_CC_UGT] = CC_great_u,
 	[ARC_CC_UGE] = CC_great_eq_u,
 	[ARC_CC_ULT] = CC_less_u,
diff --git a/arch/arc/net/bpf_jit_core.c b/arch/arc/net/bpf_jit_core.c
index 6f6b4ffccf2c2..e3628922c24a0 100644
--- a/arch/arc/net/bpf_jit_core.c
+++ b/arch/arc/net/bpf_jit_core.c
@@ -159,7 +159,7 @@ static void jit_dump(const struct jit_context *ctx)
 /* Initialise the context so there's no garbage. */
 static int jit_ctx_init(struct jit_context *ctx, struct bpf_prog *prog)
 {
-	memset(ctx, 0, sizeof(ctx));
+	memset(ctx, 0, sizeof(*ctx));
 
 	ctx->orig_prog = prog;
 
@@ -167,7 +167,7 @@ static int jit_ctx_init(struct jit_context *ctx, struct bpf_prog *prog)
 	ctx->prog = bpf_jit_blind_constants(prog);
 	if (IS_ERR(ctx->prog))
 		return PTR_ERR(ctx->prog);
-	ctx->blinded = (ctx->prog == ctx->orig_prog ? false : true);
+	ctx->blinded = (ctx->prog != ctx->orig_prog);
 
 	/* If the verifier doesn't zero-extend, then we have to do it. */
 	ctx->do_zext = !ctx->prog->aux->verifier_zext;
@@ -1182,12 +1182,12 @@ static int jit_prepare(struct jit_context *ctx)
 }
 
 /*
- * All the "handle_*()" functions have been called before by the
- * "jit_prepare()". If there was an error, we would know by now.
- * Therefore, no extra error checking at this point, other than
- * a sanity check at the end that expects the calculated length
- * (jit.len) to be equal to the length of generated instructions
- * (jit.index).
+ * jit_compile() is the real compilation phase. jit_prepare() is
+ * invoked before jit_compile() as a dry-run to make sure everything
+ * will go OK and allocate the necessary memory.
+ *
+ * In the end, jit_compile() checks if it has produced the same number
+ * of instructions as jit_prepare() would.
  */
 static int jit_compile(struct jit_context *ctx)
 {
@@ -1407,9 +1407,9 @@ static struct bpf_prog *do_extra_pass(struct bpf_prog *prog)
 
 /*
  * This function may be invoked twice for the same stream of BPF
- * instructions. The "extra pass" happens, when there are "call"s
- * involved that their addresses are not known during the first
- * invocation.
+ * instructions. The "extra pass" happens, when there are
+ * (re)locations involved that their addresses are not known
+ * during the first run.
  */
 struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 {
-- 
GitLab


From d6fe532b7499e4575f9647879b7a34625817fe7f Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 24 May 2024 18:36:16 +0200
Subject: [PATCH 237/950] netkit: Fix setting mac address in l2 mode

When running Cilium connectivity test suite with netkit in L2 mode, we
found that it is expected to be able to specify a custom MAC address for
the devices, in particular, cilium-cni obtains the specified MAC address
by querying the endpoint and sets the MAC address of the interface inside
the Pod. Thus, fix the missing support in netkit for L2 mode.

Fixes: 35dfaad7188c ("netkit, bpf: Add bpf programmable net device")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Acked-by: Stanislav Fomichev <sdf@google.com>
Link: https://lore.kernel.org/r/20240524163619.26001-1-daniel@iogearbox.net
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 drivers/net/netkit.c | 26 +++++++++++++++++++++-----
 1 file changed, 21 insertions(+), 5 deletions(-)

diff --git a/drivers/net/netkit.c b/drivers/net/netkit.c
index a4d2e76a8d587..272894053e2c4 100644
--- a/drivers/net/netkit.c
+++ b/drivers/net/netkit.c
@@ -155,6 +155,16 @@ static void netkit_set_multicast(struct net_device *dev)
 	/* Nothing to do, we receive whatever gets pushed to us! */
 }
 
+static int netkit_set_macaddr(struct net_device *dev, void *sa)
+{
+	struct netkit *nk = netkit_priv(dev);
+
+	if (nk->mode != NETKIT_L2)
+		return -EOPNOTSUPP;
+
+	return eth_mac_addr(dev, sa);
+}
+
 static void netkit_set_headroom(struct net_device *dev, int headroom)
 {
 	struct netkit *nk = netkit_priv(dev), *nk2;
@@ -198,6 +208,7 @@ static const struct net_device_ops netkit_netdev_ops = {
 	.ndo_start_xmit		= netkit_xmit,
 	.ndo_set_rx_mode	= netkit_set_multicast,
 	.ndo_set_rx_headroom	= netkit_set_headroom,
+	.ndo_set_mac_address	= netkit_set_macaddr,
 	.ndo_get_iflink		= netkit_get_iflink,
 	.ndo_get_peer_dev	= netkit_peer_dev,
 	.ndo_get_stats64	= netkit_get_stats,
@@ -300,9 +311,11 @@ static int netkit_validate(struct nlattr *tb[], struct nlattr *data[],
 
 	if (!attr)
 		return 0;
-	NL_SET_ERR_MSG_ATTR(extack, attr,
-			    "Setting Ethernet address is not supported");
-	return -EOPNOTSUPP;
+	if (nla_len(attr) != ETH_ALEN)
+		return -EINVAL;
+	if (!is_valid_ether_addr(nla_data(attr)))
+		return -EADDRNOTAVAIL;
+	return 0;
 }
 
 static struct rtnl_link_ops netkit_link_ops;
@@ -365,6 +378,9 @@ static int netkit_new_link(struct net *src_net, struct net_device *dev,
 		strscpy(ifname, "nk%d", IFNAMSIZ);
 		ifname_assign_type = NET_NAME_ENUM;
 	}
+	if (mode != NETKIT_L2 &&
+	    (tb[IFLA_ADDRESS] || tbp[IFLA_ADDRESS]))
+		return -EOPNOTSUPP;
 
 	net = rtnl_link_get_net(src_net, tbp);
 	if (IS_ERR(net))
@@ -379,7 +395,7 @@ static int netkit_new_link(struct net *src_net, struct net_device *dev,
 
 	netif_inherit_tso_max(peer, dev);
 
-	if (mode == NETKIT_L2)
+	if (mode == NETKIT_L2 && !(ifmp && tbp[IFLA_ADDRESS]))
 		eth_hw_addr_random(peer);
 	if (ifmp && dev->ifindex)
 		peer->ifindex = ifmp->ifi_index;
@@ -402,7 +418,7 @@ static int netkit_new_link(struct net *src_net, struct net_device *dev,
 	if (err < 0)
 		goto err_configure_peer;
 
-	if (mode == NETKIT_L2)
+	if (mode == NETKIT_L2 && !tb[IFLA_ADDRESS])
 		eth_hw_addr_random(dev);
 	if (tb[IFLA_IFNAME])
 		nla_strscpy(dev->name, tb[IFLA_IFNAME], IFNAMSIZ);
-- 
GitLab


From 3998d184267dfcff858aaa84d3de17429253629d Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 24 May 2024 18:36:17 +0200
Subject: [PATCH 238/950] netkit: Fix pkt_type override upon netkit pass
 verdict

When running Cilium connectivity test suite with netkit in L2 mode, we
found that compared to tcx a few tests were failing which pushed traffic
into an L7 proxy sitting in host namespace. The problem in particular is
around the invocation of eth_type_trans() in netkit.

In case of tcx, this is run before the tcx ingress is triggered inside
host namespace and thus if the BPF program uses the bpf_skb_change_type()
helper the newly set type is retained. However, in case of netkit, the
late eth_type_trans() invocation overrides the earlier decision from the
BPF program which eventually leads to the test failure.

Instead of eth_type_trans(), split out the relevant parts, meaning, reset
of mac header and call to eth_skb_pkt_type() before the BPF program is run
in order to have the same behavior as with tcx, and refactor a small helper
called eth_skb_pull_mac() which is run in case it's passed up the stack
where the mac header must be pulled. With this all connectivity tests pass.

Fixes: 35dfaad7188c ("netkit, bpf: Add bpf programmable net device")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://lore.kernel.org/r/20240524163619.26001-2-daniel@iogearbox.net
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 drivers/net/netkit.c        | 4 +++-
 include/linux/etherdevice.h | 8 ++++++++
 net/ethernet/eth.c          | 4 +---
 3 files changed, 12 insertions(+), 4 deletions(-)

diff --git a/drivers/net/netkit.c b/drivers/net/netkit.c
index 272894053e2c4..16789cd446e9e 100644
--- a/drivers/net/netkit.c
+++ b/drivers/net/netkit.c
@@ -55,6 +55,7 @@ static void netkit_prep_forward(struct sk_buff *skb, bool xnet)
 	skb_scrub_packet(skb, xnet);
 	skb->priority = 0;
 	nf_skip_egress(skb, true);
+	skb_reset_mac_header(skb);
 }
 
 static struct netkit *netkit_priv(const struct net_device *dev)
@@ -78,6 +79,7 @@ static netdev_tx_t netkit_xmit(struct sk_buff *skb, struct net_device *dev)
 		     skb_orphan_frags(skb, GFP_ATOMIC)))
 		goto drop;
 	netkit_prep_forward(skb, !net_eq(dev_net(dev), dev_net(peer)));
+	eth_skb_pkt_type(skb, peer);
 	skb->dev = peer;
 	entry = rcu_dereference(nk->active);
 	if (entry)
@@ -85,7 +87,7 @@ static netdev_tx_t netkit_xmit(struct sk_buff *skb, struct net_device *dev)
 	switch (ret) {
 	case NETKIT_NEXT:
 	case NETKIT_PASS:
-		skb->protocol = eth_type_trans(skb, skb->dev);
+		eth_skb_pull_mac(skb);
 		skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
 		if (likely(__netif_rx(skb) == NET_RX_SUCCESS)) {
 			dev_sw_netstats_tx_add(dev, 1, len);
diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h
index 2ad1ffa4ccb9f..0ed47d00549ba 100644
--- a/include/linux/etherdevice.h
+++ b/include/linux/etherdevice.h
@@ -636,6 +636,14 @@ static inline void eth_skb_pkt_type(struct sk_buff *skb,
 	}
 }
 
+static inline struct ethhdr *eth_skb_pull_mac(struct sk_buff *skb)
+{
+	struct ethhdr *eth = (struct ethhdr *)skb->data;
+
+	skb_pull_inline(skb, ETH_HLEN);
+	return eth;
+}
+
 /**
  * eth_skb_pad - Pad buffer to mininum number of octets for Ethernet frame
  * @skb: Buffer to pad
diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c
index 049c3adeb8504..4e3651101b866 100644
--- a/net/ethernet/eth.c
+++ b/net/ethernet/eth.c
@@ -161,9 +161,7 @@ __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev)
 	skb->dev = dev;
 	skb_reset_mac_header(skb);
 
-	eth = (struct ethhdr *)skb->data;
-	skb_pull_inline(skb, ETH_HLEN);
-
+	eth = eth_skb_pull_mac(skb);
 	eth_skb_pkt_type(skb, dev);
 
 	/*
-- 
GitLab


From 998ffeb2738e26f134dc8e63b5dcaece22573957 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 24 May 2024 18:36:18 +0200
Subject: [PATCH 239/950] selftests/bpf: Add netkit tests for mac address

This adds simple tests around setting MAC addresses in the different
netkit modes.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/r/20240524163619.26001-3-daniel@iogearbox.net
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/prog_tests/tc_netkit.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/tools/testing/selftests/bpf/prog_tests/tc_netkit.c b/tools/testing/selftests/bpf/prog_tests/tc_netkit.c
index 15ee7b2fc4106..18b2e969a4567 100644
--- a/tools/testing/selftests/bpf/prog_tests/tc_netkit.c
+++ b/tools/testing/selftests/bpf/prog_tests/tc_netkit.c
@@ -73,6 +73,16 @@ static int create_netkit(int mode, int policy, int peer_policy, int *ifindex,
 			 "up primary");
 	ASSERT_OK(system("ip addr add dev " netkit_name " 10.0.0.1/24"),
 			 "addr primary");
+
+	if (mode == NETKIT_L3) {
+		ASSERT_EQ(system("ip link set dev " netkit_name
+				 " addr ee:ff:bb:cc:aa:dd 2> /dev/null"), 512,
+				 "set hwaddress");
+	} else {
+		ASSERT_OK(system("ip link set dev " netkit_name
+				 " addr ee:ff:bb:cc:aa:dd"),
+				 "set hwaddress");
+	}
 	if (same_netns) {
 		ASSERT_OK(system("ip link set dev " netkit_peer " up"),
 				 "up peer");
-- 
GitLab


From 95348e463eabc803341c67d562f9e0a5f0a48fe6 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 24 May 2024 18:36:19 +0200
Subject: [PATCH 240/950] selftests/bpf: Add netkit test for pkt_type

Add a test case to assert that the skb->pkt_type which was set from the BPF
program is retained from the netkit xmit side to the peer's device at tcx
ingress location.

  # ./vmtest.sh -- ./test_progs -t netkit
  [...]
  ./test_progs -t netkit
  [    1.140780] bpf_testmod: loading out-of-tree module taints kernel.
  [    1.141127] bpf_testmod: module verification failed: signature and/or required key missing - tainting kernel
  [    1.284601] tsc: Refined TSC clocksource calibration: 3408.006 MHz
  [    1.286672] clocksource: tsc: mask: 0xffffffffffffffff max_cycles: 0x311fd9b189d, max_idle_ns: 440795225691 ns
  [    1.290384] clocksource: Switched to clocksource tsc
  #345     tc_netkit_basic:OK
  #346     tc_netkit_device:OK
  #347     tc_netkit_multi_links:OK
  #348     tc_netkit_multi_opts:OK
  #349     tc_netkit_neigh_links:OK
  #350     tc_netkit_pkt_type:OK
  Summary: 6/0 PASSED, 0 SKIPPED, 0 FAILED

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/r/20240524163619.26001-4-daniel@iogearbox.net
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../selftests/bpf/prog_tests/tc_netkit.c      | 84 +++++++++++++++++++
 .../selftests/bpf/progs/test_tc_link.c        | 35 +++++++-
 2 files changed, 118 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/tc_netkit.c b/tools/testing/selftests/bpf/prog_tests/tc_netkit.c
index 18b2e969a4567..b9135720024cc 100644
--- a/tools/testing/selftests/bpf/prog_tests/tc_netkit.c
+++ b/tools/testing/selftests/bpf/prog_tests/tc_netkit.c
@@ -99,6 +99,16 @@ static int create_netkit(int mode, int policy, int peer_policy, int *ifindex,
 	return err;
 }
 
+static void move_netkit(void)
+{
+	ASSERT_OK(system("ip link set " netkit_peer " netns foo"),
+			 "move peer");
+	ASSERT_OK(system("ip netns exec foo ip link set dev "
+			 netkit_peer " up"), "up peer");
+	ASSERT_OK(system("ip netns exec foo ip addr add dev "
+			 netkit_peer " 10.0.0.2/24"), "addr peer");
+}
+
 static void destroy_netkit(void)
 {
 	ASSERT_OK(system("ip link del dev " netkit_name), "del primary");
@@ -695,3 +705,77 @@ void serial_test_tc_netkit_neigh_links(void)
 	serial_test_tc_netkit_neigh_links_target(NETKIT_L2, BPF_NETKIT_PRIMARY);
 	serial_test_tc_netkit_neigh_links_target(NETKIT_L3, BPF_NETKIT_PRIMARY);
 }
+
+static void serial_test_tc_netkit_pkt_type_mode(int mode)
+{
+	LIBBPF_OPTS(bpf_netkit_opts, optl_nk);
+	LIBBPF_OPTS(bpf_tcx_opts, optl_tcx);
+	int err, ifindex, ifindex2;
+	struct test_tc_link *skel;
+	struct bpf_link *link;
+
+	err = create_netkit(mode, NETKIT_PASS, NETKIT_PASS,
+			    &ifindex, true);
+	if (err)
+		return;
+
+	ifindex2 = if_nametoindex(netkit_peer);
+	ASSERT_NEQ(ifindex, ifindex2, "ifindex_1_2");
+
+	skel = test_tc_link__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1,
+		  BPF_NETKIT_PRIMARY), 0, "tc1_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc7,
+		  BPF_TCX_INGRESS), 0, "tc7_attach_type");
+
+	err = test_tc_link__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	assert_mprog_count_ifindex(ifindex,  BPF_NETKIT_PRIMARY, 0);
+	assert_mprog_count_ifindex(ifindex2, BPF_TCX_INGRESS, 0);
+
+	link = bpf_program__attach_netkit(skel->progs.tc1, ifindex, &optl_nk);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc1 = link;
+
+	assert_mprog_count_ifindex(ifindex,  BPF_NETKIT_PRIMARY, 1);
+	assert_mprog_count_ifindex(ifindex2, BPF_TCX_INGRESS, 0);
+
+	link = bpf_program__attach_tcx(skel->progs.tc7, ifindex2, &optl_tcx);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc7 = link;
+
+	assert_mprog_count_ifindex(ifindex,  BPF_NETKIT_PRIMARY, 1);
+	assert_mprog_count_ifindex(ifindex2, BPF_TCX_INGRESS, 1);
+
+	move_netkit();
+
+	tc_skel_reset_all_seen(skel);
+	skel->bss->set_type = true;
+	ASSERT_EQ(send_icmp(), 0, "icmp_pkt");
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc7, true, "seen_tc7");
+
+	ASSERT_EQ(skel->bss->seen_host,  true, "seen_host");
+	ASSERT_EQ(skel->bss->seen_mcast, true, "seen_mcast");
+cleanup:
+	test_tc_link__destroy(skel);
+
+	assert_mprog_count_ifindex(ifindex,  BPF_NETKIT_PRIMARY, 0);
+	destroy_netkit();
+}
+
+void serial_test_tc_netkit_pkt_type(void)
+{
+	serial_test_tc_netkit_pkt_type_mode(NETKIT_L2);
+	serial_test_tc_netkit_pkt_type_mode(NETKIT_L3);
+}
diff --git a/tools/testing/selftests/bpf/progs/test_tc_link.c b/tools/testing/selftests/bpf/progs/test_tc_link.c
index 992400acb9572..ab3eae3d6af87 100644
--- a/tools/testing/selftests/bpf/progs/test_tc_link.c
+++ b/tools/testing/selftests/bpf/progs/test_tc_link.c
@@ -4,7 +4,8 @@
 
 #include <linux/bpf.h>
 #include <linux/if_ether.h>
-
+#include <linux/stddef.h>
+#include <linux/if_packet.h>
 #include <bpf/bpf_endian.h>
 #include <bpf/bpf_helpers.h>
 
@@ -16,7 +17,13 @@ bool seen_tc3;
 bool seen_tc4;
 bool seen_tc5;
 bool seen_tc6;
+bool seen_tc7;
+
+bool set_type;
+
 bool seen_eth;
+bool seen_host;
+bool seen_mcast;
 
 SEC("tc/ingress")
 int tc1(struct __sk_buff *skb)
@@ -28,8 +35,16 @@ int tc1(struct __sk_buff *skb)
 	if (bpf_skb_load_bytes(skb, 0, &eth, sizeof(eth)))
 		goto out;
 	seen_eth = eth.h_proto == bpf_htons(ETH_P_IP);
+	seen_host = skb->pkt_type == PACKET_HOST;
+	if (seen_host && set_type) {
+		eth.h_dest[0] = 4;
+		if (bpf_skb_store_bytes(skb, 0, &eth, sizeof(eth), 0))
+			goto fail;
+		bpf_skb_change_type(skb, PACKET_MULTICAST);
+	}
 out:
 	seen_tc1 = true;
+fail:
 	return TCX_NEXT;
 }
 
@@ -67,3 +82,21 @@ int tc6(struct __sk_buff *skb)
 	seen_tc6 = true;
 	return TCX_PASS;
 }
+
+SEC("tc/ingress")
+int tc7(struct __sk_buff *skb)
+{
+	struct ethhdr eth = {};
+
+	if (skb->protocol != __bpf_constant_htons(ETH_P_IP))
+		goto out;
+	if (bpf_skb_load_bytes(skb, 0, &eth, sizeof(eth)))
+		goto out;
+	if (eth.h_dest[0] == 4 && set_type) {
+		seen_mcast = skb->pkt_type == PACKET_MULTICAST;
+		bpf_skb_change_type(skb, PACKET_HOST);
+	}
+out:
+	seen_tc7 = true;
+	return TCX_PASS;
+}
-- 
GitLab


From 67ec8cdf29971677b2fb4b6d92871eb5d5e95597 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Wed, 22 May 2024 13:37:54 +0800
Subject: [PATCH 241/950] hwrng: core - Remove add_early_randomness
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

A potential deadlock was reported with the config file at

https://web.archive.org/web/20240522052129/https://0x0.st/XPN_.txt

In this particular configuration, the deadlock doesn't exist because
the warning triggered at a point before modules were even available.
However, the deadlock can be real because any module loaded would
invoke async_synchronize_full.

The issue is spurious for software crypto algorithms which aren't
themselves involved in async probing.  However, it would be hard to
avoid for a PCI crypto driver using async probing.

In this particular call trace, the problem is easily avoided because
the only reason the module is being requested during probing is the
add_early_randomness call in the hwrng core.  This feature is
vestigial since there is now a kernel thread dedicated to doing
exactly this.

So remove add_early_randomness as it is no longer needed.

Reported-by: Nícolas F. R. A. Prado <nfraprado@collabora.com>
Reported-by: Eric Biggers <ebiggers@kernel.org>
Fixes: 1b6d7f9eb150 ("tpm: add session encryption protection to tpm2_get_random()")
Link: https://lore.kernel.org/r/119dc5ed-f159-41be-9dda-1a056f29888d@notapiano/
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Reviewed-by: Jarkko Sakkinen <jarkko@kernel.org>
Tested-by: Nícolas F. R. A. Prado <nfraprado@collabora.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/char/hw_random/core.c | 47 +++--------------------------------
 1 file changed, 4 insertions(+), 43 deletions(-)

diff --git a/drivers/char/hw_random/core.c b/drivers/char/hw_random/core.c
index f5c71a617a993..4084df65c9fa3 100644
--- a/drivers/char/hw_random/core.c
+++ b/drivers/char/hw_random/core.c
@@ -64,19 +64,6 @@ static size_t rng_buffer_size(void)
 	return RNG_BUFFER_SIZE;
 }
 
-static void add_early_randomness(struct hwrng *rng)
-{
-	int bytes_read;
-
-	mutex_lock(&reading_mutex);
-	bytes_read = rng_get_data(rng, rng_fillbuf, 32, 0);
-	mutex_unlock(&reading_mutex);
-	if (bytes_read > 0) {
-		size_t entropy = bytes_read * 8 * rng->quality / 1024;
-		add_hwgenerator_randomness(rng_fillbuf, bytes_read, entropy, false);
-	}
-}
-
 static inline void cleanup_rng(struct kref *kref)
 {
 	struct hwrng *rng = container_of(kref, struct hwrng, ref);
@@ -340,13 +327,12 @@ static ssize_t rng_current_store(struct device *dev,
 				 const char *buf, size_t len)
 {
 	int err;
-	struct hwrng *rng, *old_rng, *new_rng;
+	struct hwrng *rng, *new_rng;
 
 	err = mutex_lock_interruptible(&rng_mutex);
 	if (err)
 		return -ERESTARTSYS;
 
-	old_rng = current_rng;
 	if (sysfs_streq(buf, "")) {
 		err = enable_best_rng();
 	} else {
@@ -362,11 +348,8 @@ static ssize_t rng_current_store(struct device *dev,
 	new_rng = get_current_rng_nolock();
 	mutex_unlock(&rng_mutex);
 
-	if (new_rng) {
-		if (new_rng != old_rng)
-			add_early_randomness(new_rng);
+	if (new_rng)
 		put_rng(new_rng);
-	}
 
 	return err ? : len;
 }
@@ -544,7 +527,6 @@ int hwrng_register(struct hwrng *rng)
 {
 	int err = -EINVAL;
 	struct hwrng *tmp;
-	bool is_new_current = false;
 
 	if (!rng->name || (!rng->data_read && !rng->read))
 		goto out;
@@ -573,25 +555,8 @@ int hwrng_register(struct hwrng *rng)
 		err = set_current_rng(rng);
 		if (err)
 			goto out_unlock;
-		/* to use current_rng in add_early_randomness() we need
-		 * to take a ref
-		 */
-		is_new_current = true;
-		kref_get(&rng->ref);
 	}
 	mutex_unlock(&rng_mutex);
-	if (is_new_current || !rng->init) {
-		/*
-		 * Use a new device's input to add some randomness to
-		 * the system.  If this rng device isn't going to be
-		 * used right away, its init function hasn't been
-		 * called yet by set_current_rng(); so only use the
-		 * randomness from devices that don't need an init callback
-		 */
-		add_early_randomness(rng);
-	}
-	if (is_new_current)
-		put_rng(rng);
 	return 0;
 out_unlock:
 	mutex_unlock(&rng_mutex);
@@ -602,12 +567,11 @@ EXPORT_SYMBOL_GPL(hwrng_register);
 
 void hwrng_unregister(struct hwrng *rng)
 {
-	struct hwrng *old_rng, *new_rng;
+	struct hwrng *new_rng;
 	int err;
 
 	mutex_lock(&rng_mutex);
 
-	old_rng = current_rng;
 	list_del(&rng->list);
 	complete_all(&rng->dying);
 	if (current_rng == rng) {
@@ -626,11 +590,8 @@ void hwrng_unregister(struct hwrng *rng)
 	} else
 		mutex_unlock(&rng_mutex);
 
-	if (new_rng) {
-		if (old_rng != new_rng)
-			add_early_randomness(new_rng);
+	if (new_rng)
 		put_rng(new_rng);
-	}
 
 	wait_for_completion(&rng->cleanup_done);
 }
-- 
GitLab


From d509cadc3a48fee394d68757e4b685f7c143ed64 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sat, 25 May 2024 00:53:25 -0400
Subject: [PATCH 242/950] bcachefs: Fix debug assert

Reported-by: syzbot+a8074a75b8d73328751e@syzkaller.appspotmail.com
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/super.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/bcachefs/super.c b/fs/bcachefs/super.c
index 2206a8dee693a..df2bea38e83f0 100644
--- a/fs/bcachefs/super.c
+++ b/fs/bcachefs/super.c
@@ -564,7 +564,7 @@ static void __bch2_fs_free(struct bch_fs *c)
 	BUG_ON(atomic_read(&c->journal_keys.ref));
 	bch2_fs_btree_write_buffer_exit(c);
 	percpu_free_rwsem(&c->mark_lock);
-	EBUG_ON(percpu_u64_get(c->online_reserved));
+	EBUG_ON(c->online_reserved && percpu_u64_get(c->online_reserved));
 	free_percpu(c->online_reserved);
 
 	darray_exit(&c->btree_roots_extra);
-- 
GitLab


From 9242a34b760648b722f4958749ad83ef7d0f7525 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sat, 25 May 2024 12:38:53 -0400
Subject: [PATCH 243/950] bcachefs: Fix sb-downgrade validation

Superblock downgrade entries are only two byte aligned, but section
sizes are 8 byte aligned, which means we have to be careful about
overrun checks; an entry that crosses the end of the section is allowed
(and ignored) as long as it has zero errors.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/sb-downgrade.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/fs/bcachefs/sb-downgrade.c b/fs/bcachefs/sb-downgrade.c
index 390a1bbd2567a..3fb23e399ffb3 100644
--- a/fs/bcachefs/sb-downgrade.c
+++ b/fs/bcachefs/sb-downgrade.c
@@ -146,10 +146,17 @@ static int bch2_sb_downgrade_validate(struct bch_sb *sb, struct bch_sb_field *f,
 	for (const struct bch_sb_field_downgrade_entry *i = e->entries;
 	     (void *) i	< vstruct_end(&e->field);
 	     i = downgrade_entry_next_c(i)) {
+		/*
+		 * Careful: sb_field_downgrade_entry is only 2 byte aligned, but
+		 * section sizes are 8 byte aligned - an empty entry spanning
+		 * the end of the section is allowed (and ignored):
+		 */
+		if ((void *) &i->errors[0] > vstruct_end(&e->field))
+			break;
+
 		if (flags & BCH_VALIDATE_write &&
-		    ((void *) &i->errors[0] > vstruct_end(&e->field) ||
-		     (void *) downgrade_entry_next_c(i) > vstruct_end(&e->field))) {
-			prt_printf(err, "downgrade entry overruns end of superblock section)");
+		    (void *) downgrade_entry_next_c(i) > vstruct_end(&e->field)) {
+			prt_printf(err, "downgrade entry overruns end of superblock section");
 			return -BCH_ERR_invalid_sb_downgrade;
 		}
 
-- 
GitLab


From e245ef8a0b06fa5a18ca3bdcf82430166419283e Mon Sep 17 00:00:00 2001
From: Dave Thaler <dthaler1968@googlemail.com>
Date: Sat, 25 May 2024 23:18:15 -0700
Subject: [PATCH 244/950] bpf, docs: Fix instruction.rst indentation

The table captions patch corrected indented most tables to work with
the table directive for adding a caption but missed two of them.

Signed-off-by: Dave Thaler <dthaler1968@gmail.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20240526061815.22497-1-dthaler1968@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../bpf/standardization/instruction-set.rst   | 26 +++++++++----------
 1 file changed, 13 insertions(+), 13 deletions(-)

diff --git a/Documentation/bpf/standardization/instruction-set.rst b/Documentation/bpf/standardization/instruction-set.rst
index 08f614b10a56b..8d19810504b8d 100644
--- a/Documentation/bpf/standardization/instruction-set.rst
+++ b/Documentation/bpf/standardization/instruction-set.rst
@@ -296,12 +296,12 @@ For arithmetic and jump instructions (``ALU``, ``ALU64``, ``JMP`` and
 
   .. table:: Source operand location
 
-  ======  =====  ==============================================
-  source  value  description
-  ======  =====  ==============================================
-  K       0      use 32-bit 'imm' value as source operand
-  X       1      use 'src_reg' register value as source operand
-  ======  =====  ==============================================
+    ======  =====  ==============================================
+    source  value  description
+    ======  =====  ==============================================
+    K       0      use 32-bit 'imm' value as source operand
+    X       1      use 'src_reg' register value as source operand
+    ======  =====  ==============================================
 
 **instruction class**
   the instruction class (see `Instruction classes`_)
@@ -681,13 +681,13 @@ two complex atomic operations:
 
 .. table:: Complex atomic operations
 
-===========  ================  ===========================
-imm          value             description
-===========  ================  ===========================
-FETCH        0x01              modifier: return old value
-XCHG         0xe0 | FETCH      atomic exchange
-CMPXCHG      0xf0 | FETCH      atomic compare and exchange
-===========  ================  ===========================
+  ===========  ================  ===========================
+  imm          value             description
+  ===========  ================  ===========================
+  FETCH        0x01              modifier: return old value
+  XCHG         0xe0 | FETCH      atomic exchange
+  CMPXCHG      0xf0 | FETCH      atomic compare and exchange
+  ===========  ================  ===========================
 
 The ``FETCH`` modifier is optional for simple atomic operations, and
 always set for the complex atomic operations.  If the ``FETCH`` flag
-- 
GitLab


From f94b77709e82242c1101e59a90a7807455c4ab2a Mon Sep 17 00:00:00 2001
From: Jeff Johnson <quic_jjohnson@quicinc.com>
Date: Thu, 23 May 2024 16:22:34 -0700
Subject: [PATCH 245/950] firewire: add missing MODULE_DESCRIPTION() to test
 modules

Fix the 'make W=1' warnings:
WARNING: modpost: missing MODULE_DESCRIPTION() in drivers/firewire/uapi-test.o
WARNING: modpost: missing MODULE_DESCRIPTION() in drivers/firewire/packet-serdes-test.o

Signed-off-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Link: https://lore.kernel.org/r/20240523-md-firewire-uapi-test-v1-1-6be5adcc3aed@quicinc.com
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
---
 drivers/firewire/packet-serdes-test.c | 1 +
 drivers/firewire/uapi-test.c          | 1 +
 2 files changed, 2 insertions(+)

diff --git a/drivers/firewire/packet-serdes-test.c b/drivers/firewire/packet-serdes-test.c
index f93c966e794d9..e83b1fece780e 100644
--- a/drivers/firewire/packet-serdes-test.c
+++ b/drivers/firewire/packet-serdes-test.c
@@ -579,4 +579,5 @@ static struct kunit_suite packet_serdes_test_suite = {
 };
 kunit_test_suite(packet_serdes_test_suite);
 
+MODULE_DESCRIPTION("FireWire packet serialization/deserialization unit test suite");
 MODULE_LICENSE("GPL");
diff --git a/drivers/firewire/uapi-test.c b/drivers/firewire/uapi-test.c
index 2fcbede4fab1f..bc3f10a2e516e 100644
--- a/drivers/firewire/uapi-test.c
+++ b/drivers/firewire/uapi-test.c
@@ -86,4 +86,5 @@ static struct kunit_suite structure_layout_test_suite = {
 };
 kunit_test_suite(structure_layout_test_suite);
 
+MODULE_DESCRIPTION("FireWire UAPI unit test suite");
 MODULE_LICENSE("GPL");
-- 
GitLab


From 611b7eb19d0a305d4de00280e4a71a1b15c507fc Mon Sep 17 00:00:00 2001
From: Jim Wylder <jwylder@google.com>
Date: Thu, 23 May 2024 16:14:36 -0500
Subject: [PATCH 246/950] regmap-i2c: Subtract reg size from max_write

Currently, when an adapter defines a max_write_len quirk,
the data will be chunked into data sizes equal to the
max_write_len quirk value.  But the payload will be increased by
the size of the register address before transmission.  The
resulting value always ends up larger than the limit set
by the quirk.

Avoid this error by setting regmap's max_write to the quirk's
max_write_len minus the number of bytes for the register and
padding.  This allows the chunking to work correctly for this
limited case without impacting other use-cases.

Signed-off-by: Jim Wylder <jwylder@google.com>
Link: https://msgid.link/r/20240523211437.2839942-1-jwylder@google.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/base/regmap/regmap-i2c.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/base/regmap/regmap-i2c.c b/drivers/base/regmap/regmap-i2c.c
index 3ec611dc0c09f..a905e955bbfc7 100644
--- a/drivers/base/regmap/regmap-i2c.c
+++ b/drivers/base/regmap/regmap-i2c.c
@@ -350,7 +350,8 @@ static const struct regmap_bus *regmap_get_i2c_bus(struct i2c_client *i2c,
 
 		if (quirks->max_write_len &&
 		    (bus->max_raw_write == 0 || bus->max_raw_write > quirks->max_write_len))
-			max_write = quirks->max_write_len;
+			max_write = quirks->max_write_len -
+				(config->reg_bits + config->pad_bits) / BITS_PER_BYTE;
 
 		if (max_read || max_write) {
 			ret_bus = kmemdup(bus, sizeof(*bus), GFP_KERNEL);
-- 
GitLab


From b82b6eeefd30f1ff049bff54da419a30ad9354c0 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Fri, 24 May 2024 20:46:25 +0100
Subject: [PATCH 247/950] bcachefs: Use copy_folio_from_iter_atomic()

copy_page_from_iter_atomic() will be removed at some point.
Also fixup a comment for folios.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/fs-io-buffered.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/bcachefs/fs-io-buffered.c b/fs/bcachefs/fs-io-buffered.c
index 6b69e5cd68dd5..54873ecc635cb 100644
--- a/fs/bcachefs/fs-io-buffered.c
+++ b/fs/bcachefs/fs-io-buffered.c
@@ -437,8 +437,8 @@ static void bch2_writepage_io_done(struct bch_write_op *op)
 	 */
 
 	/*
-	 * PageWriteback is effectively our ref on the inode - fixup i_blocks
-	 * before calling end_page_writeback:
+	 * The writeback flag is effectively our ref on the inode -
+	 * fixup i_blocks before calling folio_end_writeback:
 	 */
 	bch2_i_sectors_acct(c, io->inode, NULL, io->op.i_sectors_delta);
 
@@ -898,7 +898,7 @@ static int __bch2_buffered_write(struct bch_inode_info *inode,
 	darray_for_each(fs, fi) {
 		f = *fi;
 		f_len = min(end, folio_end_pos(f)) - f_pos;
-		f_copied = copy_page_from_iter_atomic(&f->page, f_offset, f_len, iter);
+		f_copied = copy_folio_from_iter_atomic(f, f_offset, f_len, iter);
 		if (!f_copied) {
 			folios_trunc(&fs, fi);
 			break;
-- 
GitLab


From 9ee267a29309233b9ef8f58ee61e0b1c9b5879e8 Mon Sep 17 00:00:00 2001
From: Jeff Johnson <quic_jjohnson@quicinc.com>
Date: Sun, 26 May 2024 09:52:48 -0700
Subject: [PATCH 248/950] fs: smb: common: add missing MODULE_DESCRIPTION()
 macros

Fix the 'make W=1' warnings:
WARNING: modpost: missing MODULE_DESCRIPTION() in fs/smb/common/cifs_arc4.o
WARNING: modpost: missing MODULE_DESCRIPTION() in fs/smb/common/cifs_md4.o

Signed-off-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/common/cifs_arc4.c | 1 +
 fs/smb/common/cifs_md4.c  | 1 +
 2 files changed, 2 insertions(+)

diff --git a/fs/smb/common/cifs_arc4.c b/fs/smb/common/cifs_arc4.c
index 043e4cb839fa2..df360ca47826a 100644
--- a/fs/smb/common/cifs_arc4.c
+++ b/fs/smb/common/cifs_arc4.c
@@ -10,6 +10,7 @@
 #include <linux/module.h>
 #include "arc4.h"
 
+MODULE_DESCRIPTION("ARC4 Cipher Algorithm");
 MODULE_LICENSE("GPL");
 
 int cifs_arc4_setkey(struct arc4_ctx *ctx, const u8 *in_key, unsigned int key_len)
diff --git a/fs/smb/common/cifs_md4.c b/fs/smb/common/cifs_md4.c
index 50f78cfc6ce92..7ee7f4dad90c0 100644
--- a/fs/smb/common/cifs_md4.c
+++ b/fs/smb/common/cifs_md4.c
@@ -24,6 +24,7 @@
 #include <asm/byteorder.h>
 #include "md4.h"
 
+MODULE_DESCRIPTION("MD4 Message Digest Algorithm (RFC1320)");
 MODULE_LICENSE("GPL");
 
 static inline u32 lshift(u32 x, unsigned int s)
-- 
GitLab


From 495000a38634e640e2fd02f7e4f1512ccc92d770 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Fri, 24 May 2024 17:11:46 +0200
Subject: [PATCH 249/950] ALSA: core: Remove debugfs at disconnection

The card-specific debugfs entries are removed at the last stage of
card free phase, and it's performed after synchronization of the
closes of all opened fds.  This works fine for most cases, but it can
be potentially problematic for a hotplug device like USB-audio.  Due
to the nature of snd_card_free_when_closed(), the card free isn't
called immediately after the driver removal for a hotplug device, but
it's left until the last fd is closed.  It implies that the card
debugfs entries also remain.  Meanwhile, when a new device is inserted
before the last close and the very same card slot is assigned, the
driver tries to create the card debugfs root again on the very same
path.  This conflicts with the remaining entry, and results in the
kernel warning such as:
  debugfs: Directory 'card0' with parent 'sound' already present!
with the missing debugfs entry afterwards.

For avoiding such conflicts, remove debugfs entries at the device
disconnection phase instead.  The jack kctl debugfs entries get
removed in snd_jack_dev_disconnect() instead of each kctl
private_free.

Fixes: 2d670ea2bd53 ("ALSA: jack: implement software jack injection via debugfs")
Link: https://lore.kernel.org/r/20240524151256.32521-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/core/init.c |  9 +++++----
 sound/core/jack.c | 21 ++++++++++++++-------
 2 files changed, 19 insertions(+), 11 deletions(-)

diff --git a/sound/core/init.c b/sound/core/init.c
index 4e52bbe32786b..b9b708cf980d6 100644
--- a/sound/core/init.c
+++ b/sound/core/init.c
@@ -537,6 +537,11 @@ void snd_card_disconnect(struct snd_card *card)
 		synchronize_irq(card->sync_irq);
 
 	snd_info_card_disconnect(card);
+#ifdef CONFIG_SND_DEBUG
+	debugfs_remove(card->debugfs_root);
+	card->debugfs_root = NULL;
+#endif
+
 	if (card->registered) {
 		device_del(&card->card_dev);
 		card->registered = false;
@@ -586,10 +591,6 @@ static int snd_card_do_free(struct snd_card *card)
 		dev_warn(card->dev, "unable to free card info\n");
 		/* Not fatal error */
 	}
-#ifdef CONFIG_SND_DEBUG
-	debugfs_remove(card->debugfs_root);
-	card->debugfs_root = NULL;
-#endif
 	if (card->release_completion)
 		complete(card->release_completion);
 	if (!card->managed)
diff --git a/sound/core/jack.c b/sound/core/jack.c
index e08b2c4fbd1a5..e4bcecdf89b7e 100644
--- a/sound/core/jack.c
+++ b/sound/core/jack.c
@@ -37,11 +37,15 @@ static const int jack_switch_types[SND_JACK_SWITCH_TYPES] = {
 };
 #endif /* CONFIG_SND_JACK_INPUT_DEV */
 
+static void snd_jack_remove_debugfs(struct snd_jack *jack);
+
 static int snd_jack_dev_disconnect(struct snd_device *device)
 {
-#ifdef CONFIG_SND_JACK_INPUT_DEV
 	struct snd_jack *jack = device->device_data;
 
+	snd_jack_remove_debugfs(jack);
+
+#ifdef CONFIG_SND_JACK_INPUT_DEV
 	guard(mutex)(&jack->input_dev_lock);
 	if (!jack->input_dev)
 		return 0;
@@ -381,10 +385,14 @@ static int snd_jack_debugfs_add_inject_node(struct snd_jack *jack,
 	return 0;
 }
 
-static void snd_jack_debugfs_clear_inject_node(struct snd_jack_kctl *jack_kctl)
+static void snd_jack_remove_debugfs(struct snd_jack *jack)
 {
-	debugfs_remove(jack_kctl->jack_debugfs_root);
-	jack_kctl->jack_debugfs_root = NULL;
+	struct snd_jack_kctl *jack_kctl;
+
+	list_for_each_entry(jack_kctl, &jack->kctl_list, list) {
+		debugfs_remove(jack_kctl->jack_debugfs_root);
+		jack_kctl->jack_debugfs_root = NULL;
+	}
 }
 #else /* CONFIG_SND_JACK_INJECTION_DEBUG */
 static int snd_jack_debugfs_add_inject_node(struct snd_jack *jack,
@@ -393,7 +401,7 @@ static int snd_jack_debugfs_add_inject_node(struct snd_jack *jack,
 	return 0;
 }
 
-static void snd_jack_debugfs_clear_inject_node(struct snd_jack_kctl *jack_kctl)
+static void snd_jack_remove_debugfs(struct snd_jack *jack)
 {
 }
 #endif /* CONFIG_SND_JACK_INJECTION_DEBUG */
@@ -404,7 +412,6 @@ static void snd_jack_kctl_private_free(struct snd_kcontrol *kctl)
 
 	jack_kctl = kctl->private_data;
 	if (jack_kctl) {
-		snd_jack_debugfs_clear_inject_node(jack_kctl);
 		list_del(&jack_kctl->list);
 		kfree(jack_kctl);
 	}
@@ -497,8 +504,8 @@ int snd_jack_new(struct snd_card *card, const char *id, int type,
 		.dev_free = snd_jack_dev_free,
 #ifdef CONFIG_SND_JACK_INPUT_DEV
 		.dev_register = snd_jack_dev_register,
-		.dev_disconnect = snd_jack_dev_disconnect,
 #endif /* CONFIG_SND_JACK_INPUT_DEV */
+		.dev_disconnect = snd_jack_dev_disconnect,
 	};
 
 	if (initial_kctl) {
-- 
GitLab


From 2be46155d792d629e8fe3188c2cde176833afe36 Mon Sep 17 00:00:00 2001
From: "Luke D. Jones" <luke@ljones.dev>
Date: Sun, 26 May 2024 21:10:32 +1200
Subject: [PATCH 250/950] ALSA: hda/realtek: Adjust G814JZR to use SPI init for
 amp

The 2024 ASUS ROG G814J model is much the same as the 2023 model
and the 2023 16" version. We can use the same Cirrus Amp quirk.

Fixes: 811dd426a9b1 ("ALSA: hda/realtek: Add quirks for Asus ROG 2024 laptops using CS35L41")
Signed-off-by: Luke D. Jones <luke@ljones.dev>
Link: https://lore.kernel.org/r/20240526091032.114545-1-luke@ljones.dev
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index e3c0b9d5552d9..aa76d1c885895 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -10310,7 +10310,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x3030, "ASUS ZN270IE", ALC256_FIXUP_ASUS_AIO_GPIO2),
 	SND_PCI_QUIRK(0x1043, 0x3a20, "ASUS G614JZR", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x3a30, "ASUS G814JVR/JIR", ALC245_FIXUP_CS35L41_SPI_2),
-	SND_PCI_QUIRK(0x1043, 0x3a40, "ASUS G814JZR", ALC245_FIXUP_CS35L41_SPI_2),
+	SND_PCI_QUIRK(0x1043, 0x3a40, "ASUS G814JZR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),
 	SND_PCI_QUIRK(0x1043, 0x3a50, "ASUS G834JYR/JZR", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x3a60, "ASUS G634JYR/JZR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),
 	SND_PCI_QUIRK(0x1043, 0x831a, "ASUS P901", ALC269_FIXUP_STEREO_DMIC),
-- 
GitLab


From 9e2f46cd87473c70d01fcaf8a559809e6d18dd50 Mon Sep 17 00:00:00 2001
From: Jason Nader <dev@kayoway.com>
Date: Tue, 21 May 2024 22:36:24 +0900
Subject: [PATCH 251/950] ata: ahci: Do not apply Intel PCS quirk on Intel
 Alder Lake

Commit b8b8b4e0c052 ("ata: ahci: Add Intel Alder Lake-P AHCI controller
to low power chipsets list") added Intel Alder Lake to the ahci_pci_tbl.

Because of the way that the Intel PCS quirk was implemented, having
an explicit entry in the ahci_pci_tbl caused the Intel PCS quirk to
be applied. (The quirk was not being applied if there was no explict
entry.)

Thus, entries that were added to the ahci_pci_tbl also got the Intel
PCS quirk applied.

The quirk was cleaned up in commit 7edbb6059274 ("ahci: clean up
intel_pcs_quirk"), such that it is clear which entries that actually
applies the Intel PCS quirk.

Newer Intel AHCI controllers do not need the Intel PCS quirk,
and applying it when not needed actually breaks some platforms.

Do not apply the Intel PCS quirk for Intel Alder Lake.
This is in line with how things worked before commit b8b8b4e0c052 ("ata:
ahci: Add Intel Alder Lake-P AHCI controller to low power chipsets list"),
such that certain platforms using Intel Alder Lake will work once again.

Cc: stable@vger.kernel.org # 6.7
Fixes: b8b8b4e0c052 ("ata: ahci: Add Intel Alder Lake-P AHCI controller to low power chipsets list")
Signed-off-by: Jason Nader <dev@kayoway.com>
Signed-off-by: Niklas Cassel <cassel@kernel.org>
---
 drivers/ata/ahci.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index 6548f10e61d9c..07d66d2c5f0dd 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -429,7 +429,6 @@ static const struct pci_device_id ahci_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, 0x02d7), board_ahci_pcs_quirk }, /* Comet Lake PCH RAID */
 	/* Elkhart Lake IDs 0x4b60 & 0x4b62 https://sata-io.org/product/8803 not tested yet */
 	{ PCI_VDEVICE(INTEL, 0x4b63), board_ahci_pcs_quirk }, /* Elkhart Lake AHCI */
-	{ PCI_VDEVICE(INTEL, 0x7ae2), board_ahci_pcs_quirk }, /* Alder Lake-P AHCI */
 
 	/* JMicron 360/1/3/5/6, match class to avoid IDE function */
 	{ PCI_VENDOR_ID_JMICRON, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID,
-- 
GitLab


From 9e305a6f01ad539dc134b8017521495378d8e00e Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Tue, 21 May 2024 12:01:39 +0800
Subject: [PATCH 252/950] wifi: rtw89: 8852c: correct logic and restore PCI PHY
 EQ after device resume

PCI PHY EQ value is missing after card off/on, so update the value after
device resume. The original commit only updates once at probe stage, which
could lead problem after suspend/resume.

The logic should be read a value from one register and write to another
register with a mask to avoid affecting unrelated bits.

Fixes: a78d33a1286c ("wifi: rtw89: 8852c: disable PCI PHY EQ to improve compatibility")
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://msgid.link/20240521040139.20311-1-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/pci.c | 23 ++++++++++++-----------
 1 file changed, 12 insertions(+), 11 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/pci.c b/drivers/net/wireless/realtek/rtw89/pci.c
index f93385cc20cd3..dbbb2f6500e29 100644
--- a/drivers/net/wireless/realtek/rtw89/pci.c
+++ b/drivers/net/wireless/realtek/rtw89/pci.c
@@ -2330,21 +2330,20 @@ static void rtw89_pci_disable_eq(struct rtw89_dev *rtwdev)
 	u32 backup_aspm;
 	u32 phy_offset;
 	u16 oobs_val;
-	u16 val16;
 	int ret;
 
 	if (rtwdev->chip->chip_id != RTL8852C)
 		return;
 
-	backup_aspm = rtw89_read32(rtwdev, R_AX_PCIE_MIX_CFG_V1);
-	rtw89_write32_clr(rtwdev, R_AX_PCIE_MIX_CFG_V1, B_AX_ASPM_CTRL_MASK);
-
 	g1_oobs = rtw89_read16_mask(rtwdev, R_RAC_DIRECT_OFFSET_G1 +
 					    RAC_ANA09 * RAC_MULT, BAC_OOBS_SEL);
 	g2_oobs = rtw89_read16_mask(rtwdev, R_RAC_DIRECT_OFFSET_G2 +
 					    RAC_ANA09 * RAC_MULT, BAC_OOBS_SEL);
 	if (g1_oobs && g2_oobs)
-		goto out;
+		return;
+
+	backup_aspm = rtw89_read32(rtwdev, R_AX_PCIE_MIX_CFG_V1);
+	rtw89_write32_clr(rtwdev, R_AX_PCIE_MIX_CFG_V1, B_AX_ASPM_CTRL_MASK);
 
 	ret = rtw89_pci_get_phy_offset_by_link_speed(rtwdev, &phy_offset);
 	if (ret)
@@ -2354,15 +2353,16 @@ static void rtw89_pci_disable_eq(struct rtw89_dev *rtwdev)
 	rtw89_write16(rtwdev, phy_offset + RAC_ANA10 * RAC_MULT, ADDR_SEL_PINOUT_DIS_VAL);
 	rtw89_write16_set(rtwdev, phy_offset + RAC_ANA19 * RAC_MULT, B_PCIE_BIT_RD_SEL);
 
-	val16 = rtw89_read16_mask(rtwdev, phy_offset + RAC_ANA1F * RAC_MULT,
-				  OOBS_LEVEL_MASK);
-	oobs_val = u16_encode_bits(val16, OOBS_SEN_MASK);
+	oobs_val = rtw89_read16_mask(rtwdev, phy_offset + RAC_ANA1F * RAC_MULT,
+				     OOBS_LEVEL_MASK);
 
-	rtw89_write16(rtwdev, R_RAC_DIRECT_OFFSET_G1 + RAC_ANA03 * RAC_MULT, oobs_val);
+	rtw89_write16_mask(rtwdev, R_RAC_DIRECT_OFFSET_G1 + RAC_ANA03 * RAC_MULT,
+			   OOBS_SEN_MASK, oobs_val);
 	rtw89_write16_set(rtwdev, R_RAC_DIRECT_OFFSET_G1 + RAC_ANA09 * RAC_MULT,
 			  BAC_OOBS_SEL);
 
-	rtw89_write16(rtwdev, R_RAC_DIRECT_OFFSET_G2 + RAC_ANA03 * RAC_MULT, oobs_val);
+	rtw89_write16_mask(rtwdev, R_RAC_DIRECT_OFFSET_G2 + RAC_ANA03 * RAC_MULT,
+			   OOBS_SEN_MASK, oobs_val);
 	rtw89_write16_set(rtwdev, R_RAC_DIRECT_OFFSET_G2 + RAC_ANA09 * RAC_MULT,
 			  BAC_OOBS_SEL);
 
@@ -2783,7 +2783,6 @@ static int rtw89_pci_ops_mac_pre_init_ax(struct rtw89_dev *rtwdev)
 	const struct rtw89_pci_info *info = rtwdev->pci_info;
 	int ret;
 
-	rtw89_pci_disable_eq(rtwdev);
 	rtw89_pci_ber(rtwdev);
 	rtw89_pci_rxdma_prefth(rtwdev);
 	rtw89_pci_l1off_pwroff(rtwdev);
@@ -4155,6 +4154,7 @@ static int __maybe_unused rtw89_pci_resume(struct device *dev)
 				  B_AX_SEL_REQ_ENTR_L1);
 	}
 	rtw89_pci_l2_hci_ldo(rtwdev);
+	rtw89_pci_disable_eq(rtwdev);
 	rtw89_pci_filter_out(rtwdev);
 	rtw89_pci_link_cfg(rtwdev);
 	rtw89_pci_l1ss_cfg(rtwdev);
@@ -4289,6 +4289,7 @@ int rtw89_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto err_clear_resource;
 	}
 
+	rtw89_pci_disable_eq(rtwdev);
 	rtw89_pci_filter_out(rtwdev);
 	rtw89_pci_link_cfg(rtwdev);
 	rtw89_pci_l1ss_cfg(rtwdev);
-- 
GitLab


From f12fc2065647f8032fef2b43ad17843fc82ef456 Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Wed, 22 May 2024 10:38:29 +0800
Subject: [PATCH 253/950] wifi: rtw89: fill STBC and LDPC capabilities to TX
 descriptor

Fill STBC and LDPC fields to get better performance when transmitting under
noisy environment. Old chips like 8852AE use firmware command to enable
these two capabilities, but newer chips must use TX descriptor.

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://msgid.link/20240522023830.9798-1-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.c | 12 ++++++++++--
 drivers/net/wireless/realtek/rtw89/core.h |  2 ++
 drivers/net/wireless/realtek/rtw89/txrx.h |  2 ++
 3 files changed, 14 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c
index 8b6cb310eabac..36d31608157f1 100644
--- a/drivers/net/wireless/realtek/rtw89/core.c
+++ b/drivers/net/wireless/realtek/rtw89/core.c
@@ -813,6 +813,8 @@ rtw89_core_tx_update_data_info(struct rtw89_dev *rtwdev,
 	desc_info->mac_id = rtw89_core_tx_get_mac_id(rtwdev, tx_req);
 	desc_info->port = desc_info->hiq ? rtwvif->port : 0;
 	desc_info->er_cap = rtwsta ? rtwsta->er_cap : false;
+	desc_info->stbc = rtwsta ? rtwsta->ra.stbc_cap : false;
+	desc_info->ldpc = rtwsta ? rtwsta->ra.ldpc_cap : false;
 
 	/* enable wd_info for AMPDU */
 	desc_info->en_wd_info = true;
@@ -1127,6 +1129,8 @@ static __le32 rtw89_build_txwd_info0(struct rtw89_tx_desc_info *desc_info)
 {
 	u32 dword = FIELD_PREP(RTW89_TXWD_INFO0_USE_RATE, desc_info->use_rate) |
 		    FIELD_PREP(RTW89_TXWD_INFO0_DATA_RATE, desc_info->data_rate) |
+		    FIELD_PREP(RTW89_TXWD_INFO0_DATA_STBC, desc_info->stbc) |
+		    FIELD_PREP(RTW89_TXWD_INFO0_DATA_LDPC, desc_info->ldpc) |
 		    FIELD_PREP(RTW89_TXWD_INFO0_DISDATAFB, desc_info->dis_data_fb) |
 		    FIELD_PREP(RTW89_TXWD_INFO0_MULTIPORT_ID, desc_info->port);
 
@@ -1135,7 +1139,9 @@ static __le32 rtw89_build_txwd_info0(struct rtw89_tx_desc_info *desc_info)
 
 static __le32 rtw89_build_txwd_info0_v1(struct rtw89_tx_desc_info *desc_info)
 {
-	u32 dword = FIELD_PREP(RTW89_TXWD_INFO0_DISDATAFB, desc_info->dis_data_fb) |
+	u32 dword = FIELD_PREP(RTW89_TXWD_INFO0_DATA_STBC, desc_info->stbc) |
+		    FIELD_PREP(RTW89_TXWD_INFO0_DATA_LDPC, desc_info->ldpc) |
+		    FIELD_PREP(RTW89_TXWD_INFO0_DISDATAFB, desc_info->dis_data_fb) |
 		    FIELD_PREP(RTW89_TXWD_INFO0_MULTIPORT_ID, desc_info->port) |
 		    FIELD_PREP(RTW89_TXWD_INFO0_DATA_ER, desc_info->er_cap) |
 		    FIELD_PREP(RTW89_TXWD_INFO0_DATA_BW_ER, 0);
@@ -1301,7 +1307,9 @@ static __le32 rtw89_build_txwd_body7_v2(struct rtw89_tx_desc_info *desc_info)
 
 static __le32 rtw89_build_txwd_info0_v2(struct rtw89_tx_desc_info *desc_info)
 {
-	u32 dword = FIELD_PREP(BE_TXD_INFO0_DISDATAFB, desc_info->dis_data_fb) |
+	u32 dword = FIELD_PREP(BE_TXD_INFO0_DATA_STBC, desc_info->stbc) |
+		    FIELD_PREP(BE_TXD_INFO0_DATA_LDPC, desc_info->ldpc) |
+		    FIELD_PREP(BE_TXD_INFO0_DISDATAFB, desc_info->dis_data_fb) |
 		    FIELD_PREP(BE_TXD_INFO0_MULTIPORT_ID, desc_info->port);
 
 	return cpu_to_le32(dword);
diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index 523ea9f5e6b19..e953c99b9a471 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -1136,6 +1136,8 @@ struct rtw89_tx_desc_info {
 	bool hiq;
 	u8 port;
 	bool er_cap;
+	bool stbc;
+	bool ldpc;
 };
 
 struct rtw89_core_tx_request {
diff --git a/drivers/net/wireless/realtek/rtw89/txrx.h b/drivers/net/wireless/realtek/rtw89/txrx.h
index c467a80ffa88d..11049a50de2c9 100644
--- a/drivers/net/wireless/realtek/rtw89/txrx.h
+++ b/drivers/net/wireless/realtek/rtw89/txrx.h
@@ -113,6 +113,8 @@ static inline u8 rtw89_get_data_nss(struct rtw89_dev *rtwdev, u16 hw_rate)
 #define RTW89_TXWD_INFO0_GI_LTF GENMASK(27, 25)
 #define RTW89_TXWD_INFO0_DATA_RATE GENMASK(24, 16)
 #define RTW89_TXWD_INFO0_DATA_ER BIT(15)
+#define RTW89_TXWD_INFO0_DATA_STBC BIT(12)
+#define RTW89_TXWD_INFO0_DATA_LDPC BIT(11)
 #define RTW89_TXWD_INFO0_DISDATAFB BIT(10)
 #define RTW89_TXWD_INFO0_DATA_BW_ER BIT(8)
 #define RTW89_TXWD_INFO0_MULTIPORT_ID GENMASK(6, 4)
-- 
GitLab


From 85e02a0aee586d031c3804de488e67daf8e16f9f Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Wed, 22 May 2024 10:38:30 +0800
Subject: [PATCH 254/950] wifi: rtw89: add LDPC and STBC to rx_status and
 radiotap known fields for monitor mode

Add LDPC and STBC to rx_status by hardware PPDU status, and set them as
known fields of radiotap, so we can check these capabilities in monitor
mode.

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://msgid.link/20240522023830.9798-2-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.c | 36 ++++++++++++++++++++++-
 drivers/net/wireless/realtek/rtw89/core.h |  2 ++
 drivers/net/wireless/realtek/rtw89/txrx.h |  2 ++
 3 files changed, 39 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c
index 36d31608157f1..3e99b63a79959 100644
--- a/drivers/net/wireless/realtek/rtw89/core.c
+++ b/drivers/net/wireless/realtek/rtw89/core.c
@@ -1557,6 +1557,12 @@ static void rtw89_core_parse_phy_status_ie01(struct rtw89_dev *rtwdev,
 	u32 t;
 
 	phy_ppdu->chan_idx = le32_get_bits(ie->w0, RTW89_PHY_STS_IE01_W0_CH_IDX);
+
+	if (rtwdev->hw->conf.flags & IEEE80211_CONF_MONITOR) {
+		phy_ppdu->ldpc = le32_get_bits(ie->w2, RTW89_PHY_STS_IE01_W2_LDPC);
+		phy_ppdu->stbc = le32_get_bits(ie->w2, RTW89_PHY_STS_IE01_W2_STBC);
+	}
+
 	if (phy_ppdu->rate < RTW89_HW_RATE_OFDM6)
 		return;
 
@@ -1982,6 +1988,23 @@ static void rtw89_core_hw_to_sband_rate(struct ieee80211_rx_status *rx_status)
 	rx_status->rate_idx -= 4;
 }
 
+static
+void rtw89_core_update_rx_status_by_ppdu(struct rtw89_dev *rtwdev,
+					 struct ieee80211_rx_status *rx_status,
+					 struct rtw89_rx_phy_ppdu *phy_ppdu)
+{
+	if (!(rtwdev->hw->conf.flags & IEEE80211_CONF_MONITOR))
+		return;
+
+	if (!phy_ppdu)
+		return;
+
+	if (phy_ppdu->ldpc)
+		rx_status->enc_flags |= RX_ENC_FLAG_LDPC;
+	if (phy_ppdu->stbc)
+		rx_status->enc_flags |= u8_encode_bits(1, RX_ENC_FLAG_STBC_MASK);
+}
+
 static const u8 rx_status_bw_to_radiotap_eht_usig[] = {
 	[RATE_INFO_BW_20] = IEEE80211_RADIOTAP_EHT_USIG_COMMON_BW_20MHZ,
 	[RATE_INFO_BW_5] = U8_MAX,
@@ -2025,10 +2048,14 @@ static void rtw89_core_update_radiotap_eht(struct rtw89_dev *rtwdev,
 
 	eht->user_info[0] =
 		cpu_to_le32(IEEE80211_RADIOTAP_EHT_USER_INFO_MCS_KNOWN |
-			    IEEE80211_RADIOTAP_EHT_USER_INFO_NSS_KNOWN_O);
+			    IEEE80211_RADIOTAP_EHT_USER_INFO_NSS_KNOWN_O |
+			    IEEE80211_RADIOTAP_EHT_USER_INFO_CODING_KNOWN);
 	eht->user_info[0] |=
 		le32_encode_bits(rx_status->rate_idx, IEEE80211_RADIOTAP_EHT_USER_INFO_MCS) |
 		le32_encode_bits(rx_status->nss, IEEE80211_RADIOTAP_EHT_USER_INFO_NSS_O);
+	if (rx_status->enc_flags & RX_ENC_FLAG_LDPC)
+		eht->user_info[0] |=
+			cpu_to_le32(IEEE80211_RADIOTAP_EHT_USER_INFO_CODING);
 
 	/* U-SIG */
 	tlv = (void *)tlv + sizeof(*tlv) + ALIGN(eht_len, 4);
@@ -2054,6 +2081,8 @@ static void rtw89_core_update_radiotap(struct rtw89_dev *rtwdev,
 {
 	static const struct ieee80211_radiotap_he known_he = {
 		.data1 = cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA1_DATA_MCS_KNOWN |
+				     IEEE80211_RADIOTAP_HE_DATA1_CODING_KNOWN |
+				     IEEE80211_RADIOTAP_HE_DATA1_STBC_KNOWN |
 				     IEEE80211_RADIOTAP_HE_DATA1_BW_RU_ALLOC_KNOWN),
 		.data2 = cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA2_GI_KNOWN),
 	};
@@ -2085,6 +2114,7 @@ static void rtw89_core_rx_to_mac80211(struct rtw89_dev *rtwdev,
 
 	rtw89_core_hw_to_sband_rate(rx_status);
 	rtw89_core_rx_stats(rtwdev, phy_ppdu, desc_info, skb_ppdu);
+	rtw89_core_update_rx_status_by_ppdu(rtwdev, rx_status, phy_ppdu);
 	rtw89_core_update_radiotap(rtwdev, skb_ppdu, rx_status);
 	/* In low power mode, it does RX in thread context. */
 	local_bh_disable();
@@ -4496,6 +4526,10 @@ static int rtw89_core_register_hw(struct rtw89_dev *rtwdev)
 	hw->max_tx_aggregation_subframes = RTW89_MAX_TX_AGG_NUM;
 	hw->uapsd_max_sp_len = IEEE80211_WMM_IE_STA_QOSINFO_SP_ALL;
 
+	hw->radiotap_mcs_details |= IEEE80211_RADIOTAP_MCS_HAVE_FEC |
+				    IEEE80211_RADIOTAP_MCS_HAVE_STBC;
+	hw->radiotap_vht_details |= IEEE80211_RADIOTAP_VHT_KNOWN_STBC;
+
 	ieee80211_hw_set(hw, SIGNAL_DBM);
 	ieee80211_hw_set(hw, HAS_RATE_CONTROL);
 	ieee80211_hw_set(hw, MFP_CAPABLE);
diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index e953c99b9a471..68221f0b156e2 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -793,6 +793,8 @@ struct rtw89_rx_phy_ppdu {
 		u8 evm_max;
 		u8 evm_min;
 	} ofdm;
+	bool ldpc;
+	bool stbc;
 	bool to_self;
 	bool valid;
 };
diff --git a/drivers/net/wireless/realtek/rtw89/txrx.h b/drivers/net/wireless/realtek/rtw89/txrx.h
index 11049a50de2c9..3882938c08931 100644
--- a/drivers/net/wireless/realtek/rtw89/txrx.h
+++ b/drivers/net/wireless/realtek/rtw89/txrx.h
@@ -558,6 +558,8 @@ struct rtw89_phy_sts_ie0 {
 #define RTW89_PHY_STS_IE01_W2_AVG_SNR GENMASK(5, 0)
 #define RTW89_PHY_STS_IE01_W2_EVM_MAX GENMASK(15, 8)
 #define RTW89_PHY_STS_IE01_W2_EVM_MIN GENMASK(23, 16)
+#define RTW89_PHY_STS_IE01_W2_LDPC BIT(28)
+#define RTW89_PHY_STS_IE01_W2_STBC BIT(30)
 
 enum rtw89_tx_channel {
 	RTW89_TXCH_ACH0	= 0,
-- 
GitLab


From e88c1714b2c7b230c799a00973bdeb374c765c06 Mon Sep 17 00:00:00 2001
From: Po-Hao Huang <phhuang@realtek.com>
Date: Wed, 22 May 2024 10:45:31 +0800
Subject: [PATCH 255/950] wifi: rtw89: Fix P2P behavior for WiFi 7 chips

Previously we used CCK rate when scanning for P2P on WiFi 7 chips.
Fix this by explicitly setting the rate to OFDM 6Mbps.

Signed-off-by: Po-Hao Huang <phhuang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://msgid.link/20240522024531.11401-1-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/fw.c | 10 ++++++++++
 drivers/net/wireless/realtek/rtw89/fw.h |  4 ++++
 2 files changed, 14 insertions(+)

diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index 1ea2b662fc89c..be39a8468d32b 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -4850,6 +4850,7 @@ int rtw89_fw_h2c_scan_offload_be(struct rtw89_dev *rtwdev,
 {
 	struct rtw89_hw_scan_info *scan_info = &rtwdev->scan_info;
 	struct rtw89_wait_info *wait = &rtwdev->mac.fw_ofld_wait;
+	struct cfg80211_scan_request *req = rtwvif->scan_req;
 	struct rtw89_h2c_scanofld_be_macc_role *macc_role;
 	struct rtw89_chan *op = &scan_info->op_chan;
 	struct rtw89_h2c_scanofld_be_opch *opch;
@@ -4923,6 +4924,15 @@ int rtw89_fw_h2c_scan_offload_be(struct rtw89_dev *rtwdev,
 				   RTW89_H2C_SCANOFLD_BE_W6_CHAN_PROHIB_LOW);
 	h2c->w7 = le32_encode_bits(option->prohib_chan >> 32,
 				   RTW89_H2C_SCANOFLD_BE_W7_CHAN_PROHIB_HIGH);
+	if (req->no_cck) {
+		h2c->w0 |= le32_encode_bits(true, RTW89_H2C_SCANOFLD_BE_W0_PROBE_WITH_RATE);
+		h2c->w8 = le32_encode_bits(RTW89_HW_RATE_OFDM6,
+					   RTW89_H2C_SCANOFLD_BE_W8_PROBE_RATE_2GHZ) |
+			  le32_encode_bits(RTW89_HW_RATE_OFDM6,
+					   RTW89_H2C_SCANOFLD_BE_W8_PROBE_RATE_5GHZ) |
+			  le32_encode_bits(RTW89_HW_RATE_OFDM6,
+					   RTW89_H2C_SCANOFLD_BE_W8_PROBE_RATE_6GHZ);
+	}
 	ptr += sizeof(*h2c);
 
 	for (i = 0; i < option->num_macc_role; i++) {
diff --git a/drivers/net/wireless/realtek/rtw89/fw.h b/drivers/net/wireless/realtek/rtw89/fw.h
index 4151c9d566bd6..01fea0b004d35 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.h
+++ b/drivers/net/wireless/realtek/rtw89/fw.h
@@ -2722,6 +2722,7 @@ struct rtw89_h2c_scanofld_be {
 #define RTW89_H2C_SCANOFLD_BE_W0_MACID GENMASK(23, 8)
 #define RTW89_H2C_SCANOFLD_BE_W0_PORT GENMASK(26, 24)
 #define RTW89_H2C_SCANOFLD_BE_W0_BAND GENMASK(28, 27)
+#define RTW89_H2C_SCANOFLD_BE_W0_PROBE_WITH_RATE BIT(29)
 #define RTW89_H2C_SCANOFLD_BE_W1_NUM_MACC_ROLE GENMASK(7, 0)
 #define RTW89_H2C_SCANOFLD_BE_W1_NUM_OP GENMASK(15, 8)
 #define RTW89_H2C_SCANOFLD_BE_W1_NORM_PD GENMASK(31, 16)
@@ -2738,6 +2739,9 @@ struct rtw89_h2c_scanofld_be {
 #define RTW89_H2C_SCANOFLD_BE_W5_MLO_MODE GENMASK(31, 0)
 #define RTW89_H2C_SCANOFLD_BE_W6_CHAN_PROHIB_LOW GENMASK(31, 0)
 #define RTW89_H2C_SCANOFLD_BE_W7_CHAN_PROHIB_HIGH GENMASK(31, 0)
+#define RTW89_H2C_SCANOFLD_BE_W8_PROBE_RATE_2GHZ GENMASK(7, 0)
+#define RTW89_H2C_SCANOFLD_BE_W8_PROBE_RATE_5GHZ GENMASK(15, 8)
+#define RTW89_H2C_SCANOFLD_BE_W8_PROBE_RATE_6GHZ GENMASK(23, 16)
 
 static inline void RTW89_SET_FWCMD_P2P_MACID(void *cmd, u32 val)
 {
-- 
GitLab


From e8021b94b0412c37bcc79027c2e382086b6ce449 Mon Sep 17 00:00:00 2001
From: Roded Zats <rzats@paloaltonetworks.com>
Date: Wed, 22 May 2024 10:30:44 +0300
Subject: [PATCH 256/950] enic: Validate length of nl attributes in
 enic_set_vf_port

enic_set_vf_port assumes that the nl attribute IFLA_PORT_PROFILE
is of length PORT_PROFILE_MAX and that the nl attributes
IFLA_PORT_INSTANCE_UUID, IFLA_PORT_HOST_UUID are of length PORT_UUID_MAX.
These attributes are validated (in the function do_setlink in rtnetlink.c)
using the nla_policy ifla_port_policy. The policy defines IFLA_PORT_PROFILE
as NLA_STRING, IFLA_PORT_INSTANCE_UUID as NLA_BINARY and
IFLA_PORT_HOST_UUID as NLA_STRING. That means that the length validation
using the policy is for the max size of the attributes and not on exact
size so the length of these attributes might be less than the sizes that
enic_set_vf_port expects. This might cause an out of bands
read access in the memcpys of the data of these
attributes in enic_set_vf_port.

Fixes: f8bd909183ac ("net: Add ndo_{set|get}_vf_port support for enic dynamic vnics")
Signed-off-by: Roded Zats <rzats@paloaltonetworks.com>
Link: https://lore.kernel.org/r/20240522073044.33519-1-rzats@paloaltonetworks.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/cisco/enic/enic_main.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index f604119efc809..5f26fc3ad6555 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -1117,18 +1117,30 @@ static int enic_set_vf_port(struct net_device *netdev, int vf,
 	pp->request = nla_get_u8(port[IFLA_PORT_REQUEST]);
 
 	if (port[IFLA_PORT_PROFILE]) {
+		if (nla_len(port[IFLA_PORT_PROFILE]) != PORT_PROFILE_MAX) {
+			memcpy(pp, &prev_pp, sizeof(*pp));
+			return -EINVAL;
+		}
 		pp->set |= ENIC_SET_NAME;
 		memcpy(pp->name, nla_data(port[IFLA_PORT_PROFILE]),
 			PORT_PROFILE_MAX);
 	}
 
 	if (port[IFLA_PORT_INSTANCE_UUID]) {
+		if (nla_len(port[IFLA_PORT_INSTANCE_UUID]) != PORT_UUID_MAX) {
+			memcpy(pp, &prev_pp, sizeof(*pp));
+			return -EINVAL;
+		}
 		pp->set |= ENIC_SET_INSTANCE;
 		memcpy(pp->instance_uuid,
 			nla_data(port[IFLA_PORT_INSTANCE_UUID]), PORT_UUID_MAX);
 	}
 
 	if (port[IFLA_PORT_HOST_UUID]) {
+		if (nla_len(port[IFLA_PORT_HOST_UUID]) != PORT_UUID_MAX) {
+			memcpy(pp, &prev_pp, sizeof(*pp));
+			return -EINVAL;
+		}
 		pp->set |= ENIC_SET_HOST;
 		memcpy(pp->host_uuid,
 			nla_data(port[IFLA_PORT_HOST_UUID]), PORT_UUID_MAX);
-- 
GitLab


From a4edf675ba3357f60e2ee310acc15eb9cd5a8ae0 Mon Sep 17 00:00:00 2001
From: Harshit Mogalapalli <harshit.m.mogalapalli@oracle.com>
Date: Fri, 17 May 2024 07:49:46 -0700
Subject: [PATCH 257/950] platform/x86: ISST: fix use-after-free in
 tpmi_sst_dev_remove()

In tpmi_sst_dev_remove(), tpmi_sst is dereferenced after being freed.
Fix this by reordering the kfree() post the dereference.

Fixes: 9d1d36268f3d ("platform/x86: ISST: Support partitioned systems")
Signed-off-by: Harshit Mogalapalli <harshit.m.mogalapalli@oracle.com>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Acked-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Link: https://lore.kernel.org/r/20240517144946.289615-1-harshit.m.mogalapalli@oracle.com
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
 drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c b/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c
index 7bac7841ff0ab..7fa360073f6ef 100644
--- a/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c
+++ b/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c
@@ -1610,8 +1610,8 @@ void tpmi_sst_dev_remove(struct auxiliary_device *auxdev)
 	tpmi_sst->partition_mask_current &= ~BIT(plat_info->partition);
 	/* Free the package instance when the all partitions are removed */
 	if (!tpmi_sst->partition_mask_current) {
-		kfree(tpmi_sst);
 		isst_common.sst_inst[tpmi_sst->package_id] = NULL;
+		kfree(tpmi_sst);
 	}
 	mutex_unlock(&isst_tpmi_dev_lock);
 }
-- 
GitLab


From 4d6ef1be2492a6789ba2b711933625cd72ced39d Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Tue, 21 May 2024 11:47:41 +0200
Subject: [PATCH 258/950] platform/x86: x86-android-tablets: Add "select
 LEDS_CLASS"

Since the x86-android-tablets now calls devm_led_classdev_register_ext()
it needs to select LEDS_CLASS as well as LEDS_CLASS' NEW_LEDS dependency.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202405182256.FsKBjIzG-lkp@intel.com/
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20240521094741.273397-1-hdegoede@redhat.com
---
 drivers/platform/x86/x86-android-tablets/Kconfig | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/platform/x86/x86-android-tablets/Kconfig b/drivers/platform/x86/x86-android-tablets/Kconfig
index 6603461d42730..b591419de80c3 100644
--- a/drivers/platform/x86/x86-android-tablets/Kconfig
+++ b/drivers/platform/x86/x86-android-tablets/Kconfig
@@ -6,6 +6,8 @@
 config X86_ANDROID_TABLETS
 	tristate "X86 Android tablet support"
 	depends on I2C && SPI && SERIAL_DEV_BUS && ACPI && EFI && GPIOLIB && PMIC_OPREGION
+	select NEW_LEDS
+	select LEDS_CLASS
 	help
 	  X86 tablets which ship with Android as (part of) the factory image
 	  typically have various problems with their DSDTs. The factory kernels
-- 
GitLab


From 5d059bf2b1c4d5779a4c09ec418e40eded44a187 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Google)" <rostedt@goodmis.org>
Date: Wed, 22 May 2024 07:48:13 -0400
Subject: [PATCH 259/950] platform/x86: thinkpad_acpi: Select INPUT_SPARSEKMAP
 in Kconfig

Now that drivers/platform/x86/thinkpad_acpi.c uses
sparse_keymap_report_event(), it must select INPUT_SPARSEKMAP in its
Kconfig option otherwise the build fails with:

  ld: vmlinux.o: in function `tpacpi_input_send_key':
  thinkpad_acpi.c:(.text+0xd4d27f): undefined reference to `sparse_keymap_report_event'
  ld: vmlinux.o: in function `hotkey_init':
  thinkpad_acpi.c:(.init.text+0x66cb6): undefined reference to `sparse_keymap_setup'

Fixes: 42f7b965de9d ("platform/x86: thinkpad_acpi: Switch to using sparse-keymap helpers")
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20240522074813.379b9fc2@gandalf.local.home
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
 drivers/platform/x86/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig
index 0ec952b5d03e7..1953317541eab 100644
--- a/drivers/platform/x86/Kconfig
+++ b/drivers/platform/x86/Kconfig
@@ -515,6 +515,7 @@ config THINKPAD_ACPI
 	select NVRAM
 	select NEW_LEDS
 	select LEDS_CLASS
+	select INPUT_SPARSEKMAP
 	help
 	  This is a driver for the IBM and Lenovo ThinkPad laptops. It adds
 	  support for Fn-Fx key combinations, Bluetooth control, video
-- 
GitLab


From 0b178b02673998f5acca5a0365a8858ca45beedb Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Thu, 23 May 2024 16:36:01 +0200
Subject: [PATCH 260/950] platform/x86: touchscreen_dmi: Add support for
 setting touchscreen properties from cmdline

On x86/ACPI platforms touchscreens mostly just work without needing any
device/model specific configuration. But in some cases (mostly with Silead
and Goodix touchscreens) it is still necessary to manually specify various
touchscreen-properties on a per model basis.

touchscreen_dmi is a special place for DMI quirks for this, but it can be
challenging for users to figure out the right property values, especially
for Silead touchscreens where non of these can be read back from
the touchscreen-controller.

ATM users can only test touchscreen properties by editing touchscreen_dmi.c
and then building a completely new kernel which makes it unnecessary
difficult for users to test and submit properties when necessary for their
laptop / tablet model.

Add support for specifying properties on the kernel commandline to allow
users to easily figure out the right settings. See the added documentation
in kernel-parameters.txt for the commandline syntax.

Cc: Gregor Riepl <onitake@gmail.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20240523143601.47555-1-hdegoede@redhat.com
---
 .../admin-guide/kernel-parameters.txt         | 22 ++++++
 drivers/platform/x86/touchscreen_dmi.c        | 79 ++++++++++++++++++-
 2 files changed, 98 insertions(+), 3 deletions(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 500cfa7762257..b600df82669db 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1921,6 +1921,28 @@
 				Format:
 				<bus_id>,<clkrate>
 
+	i2c_touchscreen_props= [HW,ACPI,X86]
+			Set device-properties for ACPI-enumerated I2C-attached
+			touchscreen, to e.g. fix coordinates of upside-down
+			mounted touchscreens. If you need this option please
+			submit a drivers/platform/x86/touchscreen_dmi.c patch
+			adding a DMI quirk for this.
+
+			Format:
+			<ACPI_HW_ID>:<prop_name>=<val>[:prop_name=val][:...]
+			Where <val> is one of:
+			Omit "=<val>" entirely	Set a boolean device-property
+			Unsigned number		Set a u32 device-property
+			Anything else		Set a string device-property
+
+			Examples (split over multiple lines):
+			i2c_touchscreen_props=GDIX1001:touchscreen-inverted-x:
+			touchscreen-inverted-y
+
+			i2c_touchscreen_props=MSSL1680:touchscreen-size-x=1920:
+			touchscreen-size-y=1080:touchscreen-inverted-y:
+			firmware-name=gsl1680-vendor-model.fw:silead,home-button
+
 	i8042.debug	[HW] Toggle i8042 debug mode
 	i8042.unmask_kbd_data
 			[HW] Enable printing of interrupt data from the KBD port
diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c
index c6a10ec2c83f6..b021fb9e579e8 100644
--- a/drivers/platform/x86/touchscreen_dmi.c
+++ b/drivers/platform/x86/touchscreen_dmi.c
@@ -9,10 +9,13 @@
  */
 
 #include <linux/acpi.h>
+#include <linux/ctype.h>
 #include <linux/device.h>
 #include <linux/dmi.h>
 #include <linux/efi_embedded_fw.h>
 #include <linux/i2c.h>
+#include <linux/init.h>
+#include <linux/kstrtox.h>
 #include <linux/notifier.h>
 #include <linux/property.h>
 #include <linux/string.h>
@@ -1817,7 +1820,7 @@ const struct dmi_system_id touchscreen_dmi_table[] = {
 	{ }
 };
 
-static const struct ts_dmi_data *ts_data;
+static struct ts_dmi_data *ts_data;
 
 static void ts_dmi_add_props(struct i2c_client *client)
 {
@@ -1852,6 +1855,64 @@ static int ts_dmi_notifier_call(struct notifier_block *nb,
 	return 0;
 }
 
+#define MAX_CMDLINE_PROPS 16
+
+static struct property_entry ts_cmdline_props[MAX_CMDLINE_PROPS + 1];
+
+static struct ts_dmi_data ts_cmdline_data = {
+	.properties = ts_cmdline_props,
+};
+
+static int __init ts_parse_props(char *str)
+{
+	/* Save the original str to show it on syntax errors */
+	char orig_str[256];
+	char *name, *value;
+	u32 u32val;
+	int i, ret;
+
+	strscpy(orig_str, str, sizeof(orig_str));
+
+	/*
+	 * str is part of the static_command_line from init/main.c and poking
+	 * holes in that by writing 0 to it is allowed, as is taking long
+	 * lasting references to it.
+	 */
+	ts_cmdline_data.acpi_name = strsep(&str, ":");
+
+	for (i = 0; i < MAX_CMDLINE_PROPS; i++) {
+		name = strsep(&str, ":");
+		if (!name || !name[0])
+			break;
+
+		/* Replace '=' with 0 and make value point past '=' or NULL */
+		value = name;
+		strsep(&value, "=");
+		if (!value) {
+			ts_cmdline_props[i] = PROPERTY_ENTRY_BOOL(name);
+		} else if (isdigit(value[0])) {
+			ret = kstrtou32(value, 0, &u32val);
+			if (ret)
+				goto syntax_error;
+
+			ts_cmdline_props[i] = PROPERTY_ENTRY_U32(name, u32val);
+		} else {
+			ts_cmdline_props[i] = PROPERTY_ENTRY_STRING(name, value);
+		}
+	}
+
+	if (!i || str)
+		goto syntax_error;
+
+	ts_data = &ts_cmdline_data;
+	return 1;
+
+syntax_error:
+	pr_err("Invalid '%s' value for 'i2c_touchscreen_props='\n", orig_str);
+	return 1; /* "i2c_touchscreen_props=" is still a known parameter */
+}
+__setup("i2c_touchscreen_props=", ts_parse_props);
+
 static struct notifier_block ts_dmi_notifier = {
 	.notifier_call = ts_dmi_notifier_call,
 };
@@ -1859,13 +1920,25 @@ static struct notifier_block ts_dmi_notifier = {
 static int __init ts_dmi_init(void)
 {
 	const struct dmi_system_id *dmi_id;
+	struct ts_dmi_data *ts_data_dmi;
 	int error;
 
 	dmi_id = dmi_first_match(touchscreen_dmi_table);
-	if (!dmi_id)
+	ts_data_dmi = dmi_id ? dmi_id->driver_data : NULL;
+
+	if (ts_data) {
+		/*
+		 * Kernel cmdline provided data takes precedence, copy over
+		 * DMI efi_embedded_fw info if available.
+		 */
+		if (ts_data_dmi)
+			ts_data->embedded_fw = ts_data_dmi->embedded_fw;
+	} else if (ts_data_dmi) {
+		ts_data = ts_data_dmi;
+	} else {
 		return 0; /* Not an error */
+	}
 
-	ts_data = dmi_id->driver_data;
 	/* Some dmi table entries only provide an efi_embedded_fw_desc */
 	if (!ts_data->properties)
 		return 0;
-- 
GitLab


From 7c8639aa41343fd7b3dbe09baf6b0791fcc407a1 Mon Sep 17 00:00:00 2001
From: hmtheboy154 <buingoc67@gmail.com>
Date: Mon, 27 May 2024 11:14:46 +0200
Subject: [PATCH 261/950] platform/x86: touchscreen_dmi: Add info for
 GlobalSpace SolT IVW 11.6" tablet

This is a tablet created by GlobalSpace Technologies Limited
which uses an Intel Atom x5-Z8300, 4GB of RAM & 64GB of storage.

Link: https://web.archive.org/web/20171102141952/http://globalspace.in/11.6-device.html
Signed-off-by: hmtheboy154 <buingoc67@gmail.com>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20240527091447.248849-2-hdegoede@redhat.com
---
 drivers/platform/x86/touchscreen_dmi.c | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c
index b021fb9e579e8..6c03e7daadd4d 100644
--- a/drivers/platform/x86/touchscreen_dmi.c
+++ b/drivers/platform/x86/touchscreen_dmi.c
@@ -900,6 +900,22 @@ static const struct ts_dmi_data schneider_sct101ctm_data = {
 	.properties	= schneider_sct101ctm_props,
 };
 
+static const struct property_entry globalspace_solt_ivw116_props[] = {
+	PROPERTY_ENTRY_U32("touchscreen-min-x", 7),
+	PROPERTY_ENTRY_U32("touchscreen-min-y", 22),
+	PROPERTY_ENTRY_U32("touchscreen-size-x", 1723),
+	PROPERTY_ENTRY_U32("touchscreen-size-y", 1077),
+	PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-globalspace-solt-ivw116.fw"),
+	PROPERTY_ENTRY_U32("silead,max-fingers", 10),
+	PROPERTY_ENTRY_BOOL("silead,home-button"),
+	{ }
+};
+
+static const struct ts_dmi_data globalspace_solt_ivw116_data = {
+	.acpi_name	= "MSSL1680:00",
+	.properties	= globalspace_solt_ivw116_props,
+};
+
 static const struct property_entry techbite_arc_11_6_props[] = {
 	PROPERTY_ENTRY_U32("touchscreen-min-x", 5),
 	PROPERTY_ENTRY_U32("touchscreen-min-y", 7),
@@ -1627,6 +1643,15 @@ const struct dmi_system_id touchscreen_dmi_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "SCT101CTM"),
 		},
 	},
+	{
+		/* GlobalSpace SoLT IVW 11.6" */
+		.driver_data = (void *)&globalspace_solt_ivw116_data,
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Globalspace Tech Pvt Ltd"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "SolTIVW"),
+			DMI_MATCH(DMI_PRODUCT_SKU, "PN20170413488"),
+		},
+	},
 	{
 		/* Techbite Arc 11.6 */
 		.driver_data = (void *)&techbite_arc_11_6_data,
-- 
GitLab


From 3050052613790e75b5e4a8536930426b0a8b0774 Mon Sep 17 00:00:00 2001
From: hmtheboy154 <buingoc67@gmail.com>
Date: Mon, 27 May 2024 11:14:47 +0200
Subject: [PATCH 262/950] platform/x86: touchscreen_dmi: Add info for the EZpad
 6s Pro

The "EZpad 6s Pro" uses the same touchscreen as the "EZpad 6 Pro B",
unlike the "Ezpad 6 Pro" which has its own touchscreen.

Signed-off-by: hmtheboy154 <buingoc67@gmail.com>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20240527091447.248849-3-hdegoede@redhat.com
---
 drivers/platform/x86/touchscreen_dmi.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c
index 6c03e7daadd4d..2d9ca2292ea19 100644
--- a/drivers/platform/x86/touchscreen_dmi.c
+++ b/drivers/platform/x86/touchscreen_dmi.c
@@ -1404,6 +1404,17 @@ const struct dmi_system_id touchscreen_dmi_table[] = {
 			DMI_MATCH(DMI_BIOS_DATE, "04/24/2018"),
 		},
 	},
+	{
+		/* Jumper EZpad 6s Pro */
+		.driver_data = (void *)&jumper_ezpad_6_pro_b_data,
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Jumper"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Ezpad"),
+			/* Above matches are too generic, add bios match */
+			DMI_MATCH(DMI_BIOS_VERSION, "E.WSA116_8.E1.042.bin"),
+			DMI_MATCH(DMI_BIOS_DATE, "01/08/2020"),
+		},
+	},
 	{
 		/* Jumper EZpad 6 m4 */
 		.driver_data = (void *)&jumper_ezpad_6_m4_data,
-- 
GitLab


From 21a22ed618d072a47597e63ee591973c18524880 Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Wed, 22 May 2024 18:45:04 +0800
Subject: [PATCH 263/950] selftests: hsr: Fix "File exists" errors for hsr_ping

The hsr_ping test reports the following errors:

 INFO: preparing interfaces for HSRv0.
 INFO: Initial validation ping.
 INFO: Longer ping test.
 INFO: Cutting one link.
 INFO: Delay the link and drop a few packages.
 INFO: All good.
 INFO: preparing interfaces for HSRv1.
 RTNETLINK answers: File exists
 RTNETLINK answers: File exists
 RTNETLINK answers: File exists
 RTNETLINK answers: File exists
 RTNETLINK answers: File exists
 RTNETLINK answers: File exists
 Error: ipv4: Address already assigned.
 Error: ipv6: address already assigned.
 Error: ipv4: Address already assigned.
 Error: ipv6: address already assigned.
 Error: ipv4: Address already assigned.
 Error: ipv6: address already assigned.
 INFO: Initial validation ping.

That is because the cleanup code for the 2nd round test before
"setup_hsr_interfaces 1" is removed incorrectly in commit 680fda4f6714
("test: hsr: Remove script code already implemented in lib.sh").

This patch fixes it by re-setup the namespaces using

	setup_ns ns1 ns2 ns3

command before "setup_hsr_interfaces 1". It deletes previous namespaces
and create new ones.

Fixes: 680fda4f6714 ("test: hsr: Remove script code already implemented in lib.sh")
Reviewed-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Link: https://lore.kernel.org/r/6485d3005f467758d49f0f313c8c009759ba6b05.1716374462.git.tanggeliang@kylinos.cn
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 tools/testing/selftests/net/hsr/hsr_ping.sh | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/testing/selftests/net/hsr/hsr_ping.sh b/tools/testing/selftests/net/hsr/hsr_ping.sh
index 790294c8af832..3684b813b0f67 100755
--- a/tools/testing/selftests/net/hsr/hsr_ping.sh
+++ b/tools/testing/selftests/net/hsr/hsr_ping.sh
@@ -174,6 +174,8 @@ trap cleanup_all_ns EXIT
 setup_hsr_interfaces 0
 do_complete_ping_test
 
+setup_ns ns1 ns2 ns3
+
 setup_hsr_interfaces 1
 do_complete_ping_test
 
-- 
GitLab


From 97e1db06c7bb948da10ba85acad8030b56886593 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Thu, 23 May 2024 00:40:02 +0900
Subject: [PATCH 264/950] af_unix: Annotate data-race around unix_sk(sk)->addr.

Once unix_sk(sk)->addr is assigned under net->unx.table.locks and
unix_sk(sk)->bindlock, *(unix_sk(sk)->addr) and unix_sk(sk)->path are
fully set up, and unix_sk(sk)->addr is never changed.

unix_getname() and unix_copy_addr() access the two fields locklessly,
and commit ae3b564179bf ("missing barriers in some of unix_sock ->addr
and ->path accesses") added smp_store_release() and smp_load_acquire()
pairs.

In other functions, we still read unix_sk(sk)->addr locklessly to check
if the socket is bound, and KCSAN complains about it.  [0]

Given these functions have no dependency for *(unix_sk(sk)->addr) and
unix_sk(sk)->path, READ_ONCE() is enough to annotate the data-race.

Note that it is safe to access unix_sk(sk)->addr locklessly if the socket
is found in the hash table.  For example, the lockless read of otheru->addr
in unix_stream_connect() is safe.

Note also that newu->addr there is of the child socket that is still not
accessible from userspace, and smp_store_release() publishes the address
in case the socket is accept()ed and unix_getname() / unix_copy_addr()
is called.

[0]:
BUG: KCSAN: data-race in unix_bind / unix_listen

write (marked) to 0xffff88805f8d1840 of 8 bytes by task 13723 on cpu 0:
 __unix_set_addr_hash net/unix/af_unix.c:329 [inline]
 unix_bind_bsd net/unix/af_unix.c:1241 [inline]
 unix_bind+0x881/0x1000 net/unix/af_unix.c:1319
 __sys_bind+0x194/0x1e0 net/socket.c:1847
 __do_sys_bind net/socket.c:1858 [inline]
 __se_sys_bind net/socket.c:1856 [inline]
 __x64_sys_bind+0x40/0x50 net/socket.c:1856
 do_syscall_x64 arch/x86/entry/common.c:52 [inline]
 do_syscall_64+0x4f/0x110 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x46/0x4e

read to 0xffff88805f8d1840 of 8 bytes by task 13724 on cpu 1:
 unix_listen+0x72/0x180 net/unix/af_unix.c:734
 __sys_listen+0xdc/0x160 net/socket.c:1881
 __do_sys_listen net/socket.c:1890 [inline]
 __se_sys_listen net/socket.c:1888 [inline]
 __x64_sys_listen+0x2e/0x40 net/socket.c:1888
 do_syscall_x64 arch/x86/entry/common.c:52 [inline]
 do_syscall_64+0x4f/0x110 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x46/0x4e

value changed: 0x0000000000000000 -> 0xffff88807b5b1b40

Reported by Kernel Concurrency Sanitizer on:
CPU: 1 PID: 13724 Comm: syz-executor.4 Not tainted 6.8.0-12822-gcd51db110a7e #12
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: syzkaller <syzkaller@googlegroups.com>
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://lore.kernel.org/r/20240522154002.77857-1-kuniyu@amazon.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/unix/af_unix.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index e4af6616e1dff..fe631212a345a 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -731,7 +731,7 @@ static int unix_listen(struct socket *sock, int backlog)
 	if (sock->type != SOCK_STREAM && sock->type != SOCK_SEQPACKET)
 		goto out;	/* Only stream/seqpacket sockets accept */
 	err = -EINVAL;
-	if (!u->addr)
+	if (!READ_ONCE(u->addr))
 		goto out;	/* No listens on an unbound socket */
 	unix_state_lock(sk);
 	if (sk->sk_state != TCP_CLOSE && sk->sk_state != TCP_LISTEN)
@@ -1369,7 +1369,7 @@ static int unix_dgram_connect(struct socket *sock, struct sockaddr *addr,
 
 		if ((test_bit(SOCK_PASSCRED, &sock->flags) ||
 		     test_bit(SOCK_PASSPIDFD, &sock->flags)) &&
-		    !unix_sk(sk)->addr) {
+		    !READ_ONCE(unix_sk(sk)->addr)) {
 			err = unix_autobind(sk);
 			if (err)
 				goto out;
@@ -1481,7 +1481,8 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr,
 		goto out;
 
 	if ((test_bit(SOCK_PASSCRED, &sock->flags) ||
-	     test_bit(SOCK_PASSPIDFD, &sock->flags)) && !u->addr) {
+	     test_bit(SOCK_PASSPIDFD, &sock->flags)) &&
+	    !READ_ONCE(u->addr)) {
 		err = unix_autobind(sk);
 		if (err)
 			goto out;
@@ -1950,7 +1951,8 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
 	}
 
 	if ((test_bit(SOCK_PASSCRED, &sock->flags) ||
-	     test_bit(SOCK_PASSPIDFD, &sock->flags)) && !u->addr) {
+	     test_bit(SOCK_PASSPIDFD, &sock->flags)) &&
+	    !READ_ONCE(u->addr)) {
 		err = unix_autobind(sk);
 		if (err)
 			goto out;
-- 
GitLab


From 51d1b25a720982324871338b1a36b197ec9bd6f0 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Thu, 23 May 2024 00:42:18 +0900
Subject: [PATCH 265/950] af_unix: Read sk->sk_hash under bindlock during
 bind().

syzkaller reported data-race of sk->sk_hash in unix_autobind() [0],
and the same ones exist in unix_bind_bsd() and unix_bind_abstract().

The three bind() functions prefetch sk->sk_hash locklessly and
use it later after validating that unix_sk(sk)->addr is NULL under
unix_sk(sk)->bindlock.

The prefetched sk->sk_hash is the hash value of unbound socket set
in unix_create1() and does not change until bind() completes.

There could be a chance that sk->sk_hash changes after the lockless
read.  However, in such a case, non-NULL unix_sk(sk)->addr is visible
under unix_sk(sk)->bindlock, and bind() returns -EINVAL without using
the prefetched value.

The KCSAN splat is false-positive, but let's silence it by reading
sk->sk_hash under unix_sk(sk)->bindlock.

[0]:
BUG: KCSAN: data-race in unix_autobind / unix_autobind

write to 0xffff888034a9fb88 of 4 bytes by task 4468 on cpu 0:
 __unix_set_addr_hash net/unix/af_unix.c:331 [inline]
 unix_autobind+0x47a/0x7d0 net/unix/af_unix.c:1185
 unix_dgram_connect+0x7e3/0x890 net/unix/af_unix.c:1373
 __sys_connect_file+0xd7/0xe0 net/socket.c:2048
 __sys_connect+0x114/0x140 net/socket.c:2065
 __do_sys_connect net/socket.c:2075 [inline]
 __se_sys_connect net/socket.c:2072 [inline]
 __x64_sys_connect+0x40/0x50 net/socket.c:2072
 do_syscall_x64 arch/x86/entry/common.c:52 [inline]
 do_syscall_64+0x4f/0x110 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x46/0x4e

read to 0xffff888034a9fb88 of 4 bytes by task 4465 on cpu 1:
 unix_autobind+0x28/0x7d0 net/unix/af_unix.c:1134
 unix_dgram_connect+0x7e3/0x890 net/unix/af_unix.c:1373
 __sys_connect_file+0xd7/0xe0 net/socket.c:2048
 __sys_connect+0x114/0x140 net/socket.c:2065
 __do_sys_connect net/socket.c:2075 [inline]
 __se_sys_connect net/socket.c:2072 [inline]
 __x64_sys_connect+0x40/0x50 net/socket.c:2072
 do_syscall_x64 arch/x86/entry/common.c:52 [inline]
 do_syscall_64+0x4f/0x110 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x46/0x4e

value changed: 0x000000e4 -> 0x000001e3

Reported by Kernel Concurrency Sanitizer on:
CPU: 1 PID: 4465 Comm: syz-executor.0 Not tainted 6.8.0-12822-gcd51db110a7e #12
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014

Fixes: afd20b9290e1 ("af_unix: Replace the big lock with small locks.")
Reported-by: syzkaller <syzkaller@googlegroups.com>
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://lore.kernel.org/r/20240522154218.78088-1-kuniyu@amazon.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/unix/af_unix.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index fe631212a345a..25b49efc0926b 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1131,8 +1131,8 @@ static struct sock *unix_find_other(struct net *net,
 
 static int unix_autobind(struct sock *sk)
 {
-	unsigned int new_hash, old_hash = sk->sk_hash;
 	struct unix_sock *u = unix_sk(sk);
+	unsigned int new_hash, old_hash;
 	struct net *net = sock_net(sk);
 	struct unix_address *addr;
 	u32 lastnum, ordernum;
@@ -1155,6 +1155,7 @@ static int unix_autobind(struct sock *sk)
 	addr->name->sun_family = AF_UNIX;
 	refcount_set(&addr->refcnt, 1);
 
+	old_hash = sk->sk_hash;
 	ordernum = get_random_u32();
 	lastnum = ordernum & 0xFFFFF;
 retry:
@@ -1195,8 +1196,8 @@ static int unix_bind_bsd(struct sock *sk, struct sockaddr_un *sunaddr,
 {
 	umode_t mode = S_IFSOCK |
 	       (SOCK_INODE(sk->sk_socket)->i_mode & ~current_umask());
-	unsigned int new_hash, old_hash = sk->sk_hash;
 	struct unix_sock *u = unix_sk(sk);
+	unsigned int new_hash, old_hash;
 	struct net *net = sock_net(sk);
 	struct mnt_idmap *idmap;
 	struct unix_address *addr;
@@ -1234,6 +1235,7 @@ static int unix_bind_bsd(struct sock *sk, struct sockaddr_un *sunaddr,
 	if (u->addr)
 		goto out_unlock;
 
+	old_hash = sk->sk_hash;
 	new_hash = unix_bsd_hash(d_backing_inode(dentry));
 	unix_table_double_lock(net, old_hash, new_hash);
 	u->path.mnt = mntget(parent.mnt);
@@ -1261,8 +1263,8 @@ out:
 static int unix_bind_abstract(struct sock *sk, struct sockaddr_un *sunaddr,
 			      int addr_len)
 {
-	unsigned int new_hash, old_hash = sk->sk_hash;
 	struct unix_sock *u = unix_sk(sk);
+	unsigned int new_hash, old_hash;
 	struct net *net = sock_net(sk);
 	struct unix_address *addr;
 	int err;
@@ -1280,6 +1282,7 @@ static int unix_bind_abstract(struct sock *sk, struct sockaddr_un *sunaddr,
 		goto out_mutex;
 	}
 
+	old_hash = sk->sk_hash;
 	new_hash = unix_abstract_hash(addr->name, addr->len, sk->sk_type);
 	unix_table_double_lock(net, old_hash, new_hash);
 
-- 
GitLab


From 1684842147677a1279bcff95f8adb6de9a656e30 Mon Sep 17 00:00:00 2001
From: Hariprasad Kelam <hkelam@marvell.com>
Date: Thu, 23 May 2024 13:06:26 +0530
Subject: [PATCH 266/950] Octeontx2-pf: Free send queue buffers incase of leaf
 to inner

There are two type of classes. "Leaf classes" that are  the
bottom of the class hierarchy. "Inner classes" that are neither
the root class nor leaf classes. QoS rules can only specify leaf
classes as targets for traffic.

			 Root
		        /  \
		       /    \
                      1      2
                             /\
                            /  \
                           4    5
               classes 1,4 and 5 are leaf classes.
               class 2 is a inner class.

When a leaf class made as inner, or vice versa, resources associated
with send queue (send queue buffers and transmit schedulers) are not
getting freed.

Fixes: 5e6808b4c68d ("octeontx2-pf: Add support for HTB offload")
Signed-off-by: Hariprasad Kelam <hkelam@marvell.com>
Link: https://lore.kernel.org/r/20240523073626.4114-1-hkelam@marvell.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/marvell/octeontx2/nic/qos.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/qos.c b/drivers/net/ethernet/marvell/octeontx2/nic/qos.c
index 070711df612ec..edac008099c0c 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/qos.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/qos.c
@@ -1422,7 +1422,10 @@ static int otx2_qos_leaf_to_inner(struct otx2_nic *pfvf, u16 classid,
 	otx2_qos_read_txschq_cfg(pfvf, node, old_cfg);
 
 	/* delete the txschq nodes allocated for this node */
+	otx2_qos_disable_sq(pfvf, qid);
+	otx2_qos_free_hw_node_schq(pfvf, node);
 	otx2_qos_free_sw_node_schq(pfvf, node);
+	pfvf->qos.qid_to_sqmap[qid] = OTX2_QOS_INVALID_SQ;
 
 	/* mark this node as htb inner node */
 	WRITE_ONCE(node->qid, OTX2_QOS_QID_INNER);
@@ -1632,6 +1635,7 @@ static int otx2_qos_leaf_del_last(struct otx2_nic *pfvf, u16 classid, bool force
 		dwrr_del_node = true;
 
 	/* destroy the leaf node */
+	otx2_qos_disable_sq(pfvf, qid);
 	otx2_qos_destroy_node(pfvf, node);
 	pfvf->qos.qid_to_sqmap[qid] = OTX2_QOS_INVALID_SQ;
 
-- 
GitLab


From d7ba701da636afae17d8e1243b3d12eed149abcb Mon Sep 17 00:00:00 2001
From: John Garry <john.g.garry@oracle.com>
Date: Thu, 2 May 2024 10:08:25 +0000
Subject: [PATCH 267/950] xfs: Clear W=1 warning in xfs_iwalk_run_callbacks()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

For CONFIG_XFS_DEBUG unset, xfs_iwalk_run_callbacks() generates the
following warning for when building with W=1:

fs/xfs/xfs_iwalk.c: In function ‘xfs_iwalk_run_callbacks’:
fs/xfs/xfs_iwalk.c:354:42: error: variable ‘irec’ set but not used [-Werror=unused-but-set-variable]
  354 |         struct xfs_inobt_rec_incore     *irec;
      |                                          ^~~~
cc1: all warnings being treated as errors

Drop @irec, as it is only an intermediate variable.

Suggested-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: John Garry <john.g.garry@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
---
 fs/xfs/xfs_iwalk.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/fs/xfs/xfs_iwalk.c b/fs/xfs/xfs_iwalk.c
index 730c8d48da282..86f14ec7c31fe 100644
--- a/fs/xfs/xfs_iwalk.c
+++ b/fs/xfs/xfs_iwalk.c
@@ -351,7 +351,6 @@ xfs_iwalk_run_callbacks(
 	int				*has_more)
 {
 	struct xfs_mount		*mp = iwag->mp;
-	struct xfs_inobt_rec_incore	*irec;
 	xfs_agino_t			next_agino;
 	int				error;
 
@@ -361,8 +360,8 @@ xfs_iwalk_run_callbacks(
 
 	/* Delete cursor but remember the last record we cached... */
 	xfs_iwalk_del_inobt(iwag->tp, curpp, agi_bpp, 0);
-	irec = &iwag->recs[iwag->nr_recs - 1];
-	ASSERT(next_agino >= irec->ir_startino + XFS_INODES_PER_CHUNK);
+	ASSERT(next_agino >= iwag->recs[iwag->nr_recs - 1].ir_startino +
+			XFS_INODES_PER_CHUNK);
 
 	if (iwag->drop_trans) {
 		xfs_trans_cancel(iwag->tp);
-- 
GitLab


From b33874fb7f28326380562f208d948bab785fbd6f Mon Sep 17 00:00:00 2001
From: John Garry <john.g.garry@oracle.com>
Date: Thu, 2 May 2024 10:08:26 +0000
Subject: [PATCH 268/950] xfs: Stop using __maybe_unused in xfs_alloc.c

In both xfs_alloc_cur_finish() and xfs_alloc_ag_vextent_exact(), local
variable @afg is tagged as __maybe_unused. Otherwise an unused variable
warning would be generated for when building with W=1 and CONFIG_XFS_DEBUG
unset. In both cases, the variable is unused as it is only referenced in
an ASSERT() call, which is compiled out (in this config).

It is generally a poor programming style to use __maybe_unused for
variables.

The ASSERT() call is to verify that agbno of the end of the extent is
within bounds for both functions. @afg is used as an intermediate variable
to find the AG length.

However xfs_verify_agbext() already exists to verify a valid extent range.
The arguments for calling xfs_verify_agbext() are already available, so use
that instead.

An advantage of using xfs_verify_agbext() is that it verifies that both the
start and the end of the extent are within the bounds of the AG and
catches overflows.

Suggested-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: John Garry <john.g.garry@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
---
 fs/xfs/libxfs/xfs_alloc.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 6cb8b2ddc541b..6c55a6e88eba3 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -1008,13 +1008,12 @@ xfs_alloc_cur_finish(
 	struct xfs_alloc_arg	*args,
 	struct xfs_alloc_cur	*acur)
 {
-	struct xfs_agf __maybe_unused *agf = args->agbp->b_addr;
 	int			error;
 
 	ASSERT(acur->cnt && acur->bnolt);
 	ASSERT(acur->bno >= acur->rec_bno);
 	ASSERT(acur->bno + acur->len <= acur->rec_bno + acur->rec_len);
-	ASSERT(acur->rec_bno + acur->rec_len <= be32_to_cpu(agf->agf_length));
+	ASSERT(xfs_verify_agbext(args->pag, acur->rec_bno, acur->rec_len));
 
 	error = xfs_alloc_fixup_trees(acur->cnt, acur->bnolt, acur->rec_bno,
 				      acur->rec_len, acur->bno, acur->len, 0);
@@ -1217,7 +1216,6 @@ STATIC int			/* error */
 xfs_alloc_ag_vextent_exact(
 	xfs_alloc_arg_t	*args)	/* allocation argument structure */
 {
-	struct xfs_agf __maybe_unused *agf = args->agbp->b_addr;
 	struct xfs_btree_cur *bno_cur;/* by block-number btree cursor */
 	struct xfs_btree_cur *cnt_cur;/* by count btree cursor */
 	int		error;
@@ -1297,7 +1295,7 @@ xfs_alloc_ag_vextent_exact(
 	 */
 	cnt_cur = xfs_cntbt_init_cursor(args->mp, args->tp, args->agbp,
 					args->pag);
-	ASSERT(args->agbno + args->len <= be32_to_cpu(agf->agf_length));
+	ASSERT(xfs_verify_agbext(args->pag, args->agbno, args->len));
 	error = xfs_alloc_fixup_trees(cnt_cur, bno_cur, fbno, flen, args->agbno,
 				      args->len, XFSA_FIXUP_BNO_OK);
 	if (error) {
-- 
GitLab


From 2b3f004d3d518ec7a392066d935fd85c81412e33 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Tue, 21 May 2024 23:01:45 -0700
Subject: [PATCH 269/950] xfs: drop xfarray sortinfo folio on error

Chandan Babu reports the following livelock in xfs/708:

 run fstests xfs/708 at 2024-05-04 15:35:29
 XFS (loop16): EXPERIMENTAL online scrub feature in use. Use at your own risk!
 XFS (loop5): Mounting V5 Filesystem e96086f0-a2f9-4424-a1d5-c75d53d823be
 XFS (loop5): Ending clean mount
 XFS (loop5): Quotacheck needed: Please wait.
 XFS (loop5): Quotacheck: Done.
 XFS (loop5): EXPERIMENTAL online scrub feature in use. Use at your own risk!
 INFO: task xfs_io:143725 blocked for more than 122 seconds.
       Not tainted 6.9.0-rc4+ #1
 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
 task:xfs_io          state:D stack:0     pid:143725 tgid:143725 ppid:117661 flags:0x00004006
 Call Trace:
  <TASK>
  __schedule+0x69c/0x17a0
  schedule+0x74/0x1b0
  io_schedule+0xc4/0x140
  folio_wait_bit_common+0x254/0x650
  shmem_undo_range+0x9d5/0xb40
  shmem_evict_inode+0x322/0x8f0
  evict+0x24e/0x560
  __dentry_kill+0x17d/0x4d0
  dput+0x263/0x430
  __fput+0x2fc/0xaa0
  task_work_run+0x132/0x210
  get_signal+0x1a8/0x1910
  arch_do_signal_or_restart+0x7b/0x2f0
  syscall_exit_to_user_mode+0x1c2/0x200
  do_syscall_64+0x72/0x170
  entry_SYSCALL_64_after_hwframe+0x76/0x7e

The shmem code is trying to drop all the folios attached to a shmem
file and gets stuck on a locked folio after a bnobt repair.  It looks
like the process has a signal pending, so I started looking for places
where we lock an xfile folio and then deal with a fatal signal.

I found a bug in xfarray_sort_scan via code inspection.  This function
is called to set up the scanning phase of a quicksort operation, which
may involve grabbing a locked xfile folio.  If we exit the function with
an error code, the caller does not call xfarray_sort_scan_done to put
the xfile folio.  If _sort_scan returns an error code while si->folio is
set, we leak the reference and never unlock the folio.

Therefore, change xfarray_sort to call _scan_done on exit.  This is safe
to call multiple times because it sets si->folio to NULL and ignores a
NULL si->folio.  Also change _sort_scan to use an intermediate variable
so that we never pollute si->folio with an errptr.

Fixes: 232ea052775f9 ("xfs: enable sorting of xfile-backed arrays")
Reported-by: Chandan Babu R <chandanbabu@kernel.org>
Signed-off-by: "Darrick J. Wong" <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
---
 fs/xfs/scrub/xfarray.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/fs/xfs/scrub/xfarray.c b/fs/xfs/scrub/xfarray.c
index 9185ae7088d49..cdd13ed9c569a 100644
--- a/fs/xfs/scrub/xfarray.c
+++ b/fs/xfs/scrub/xfarray.c
@@ -822,12 +822,14 @@ xfarray_sort_scan(
 
 	/* Grab the first folio that backs this array element. */
 	if (!si->folio) {
+		struct folio	*folio;
 		loff_t		next_pos;
 
-		si->folio = xfile_get_folio(si->array->xfile, idx_pos,
+		folio = xfile_get_folio(si->array->xfile, idx_pos,
 				si->array->obj_size, XFILE_ALLOC);
-		if (IS_ERR(si->folio))
-			return PTR_ERR(si->folio);
+		if (IS_ERR(folio))
+			return PTR_ERR(folio);
+		si->folio = folio;
 
 		si->first_folio_idx = xfarray_idx(si->array,
 				folio_pos(si->folio) + si->array->obj_size - 1);
@@ -1048,6 +1050,7 @@ xfarray_sort(
 
 out_free:
 	trace_xfarray_sort_stats(si, error);
+	xfarray_sort_scan_done(si);
 	kvfree(si);
 	return error;
 }
-- 
GitLab


From 97835e6866796874571646a1a8ff44f24c0b39f7 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Tue, 21 May 2024 23:02:01 -0700
Subject: [PATCH 270/950] xfs: fix xfs_init_attr_trans not handling explicit
 operation codes

When we were converting the attr code to use an explicit operation code
instead of keying off of attr->value being null, we forgot to change the
code that initializes the transaction reservation.  Split the function
into two helpers that handle the !remove and remove cases, then fix both
callsites to handle this correctly.

Fixes: c27411d4c640 ("xfs: make attr removal an explicit operation")
Signed-off-by: "Darrick J. Wong" <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
---
 fs/xfs/libxfs/xfs_attr.c | 40 +++++++++++++++++++---------------------
 fs/xfs/libxfs/xfs_attr.h |  3 +--
 fs/xfs/xfs_attr_item.c   | 17 +++++++++++++++--
 3 files changed, 35 insertions(+), 25 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
index 430cd3244c143..f30bcc64100d5 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -329,26 +329,20 @@ xfs_attr_calc_size(
 	return nblks;
 }
 
-/* Initialize transaction reservation for attr operations */
-void
-xfs_init_attr_trans(
-	struct xfs_da_args	*args,
-	struct xfs_trans_res	*tres,
-	unsigned int		*total)
+/* Initialize transaction reservation for an xattr set/replace/upsert */
+inline struct xfs_trans_res
+xfs_attr_set_resv(
+	const struct xfs_da_args	*args)
 {
-	struct xfs_mount	*mp = args->dp->i_mount;
-
-	if (args->value) {
-		tres->tr_logres = M_RES(mp)->tr_attrsetm.tr_logres +
-				 M_RES(mp)->tr_attrsetrt.tr_logres *
-				 args->total;
-		tres->tr_logcount = XFS_ATTRSET_LOG_COUNT;
-		tres->tr_logflags = XFS_TRANS_PERM_LOG_RES;
-		*total = args->total;
-	} else {
-		*tres = M_RES(mp)->tr_attrrm;
-		*total = XFS_ATTRRM_SPACE_RES(mp);
-	}
+	struct xfs_mount		*mp = args->dp->i_mount;
+	struct xfs_trans_res		ret = {
+		.tr_logres = M_RES(mp)->tr_attrsetm.tr_logres +
+			    M_RES(mp)->tr_attrsetrt.tr_logres * args->total,
+		.tr_logcount		= XFS_ATTRSET_LOG_COUNT,
+		.tr_logflags		= XFS_TRANS_PERM_LOG_RES,
+	};
+
+	return ret;
 }
 
 /*
@@ -1006,7 +1000,7 @@ xfs_attr_set(
 	struct xfs_trans_res	tres;
 	int			error, local;
 	int			rmt_blks = 0;
-	unsigned int		total;
+	unsigned int		total = 0;
 
 	ASSERT(!args->trans);
 
@@ -1033,10 +1027,15 @@ xfs_attr_set(
 
 		if (!local)
 			rmt_blks = xfs_attr3_rmt_blocks(mp, args->valuelen);
+
+		tres = xfs_attr_set_resv(args);
+		total = args->total;
 		break;
 	case XFS_ATTRUPDATE_REMOVE:
 		XFS_STATS_INC(mp, xs_attr_remove);
 		rmt_blks = xfs_attr3_max_rmt_blocks(mp);
+		tres = M_RES(mp)->tr_attrrm;
+		total = XFS_ATTRRM_SPACE_RES(mp);
 		break;
 	}
 
@@ -1044,7 +1043,6 @@ xfs_attr_set(
 	 * Root fork attributes can use reserved data blocks for this
 	 * operation if necessary
 	 */
-	xfs_init_attr_trans(args, &tres, &total);
 	error = xfs_trans_alloc_inode(dp, &tres, total, 0, rsvd, &args->trans);
 	if (error)
 		return error;
diff --git a/fs/xfs/libxfs/xfs_attr.h b/fs/xfs/libxfs/xfs_attr.h
index 088cb7b301680..0e51d0723f9aa 100644
--- a/fs/xfs/libxfs/xfs_attr.h
+++ b/fs/xfs/libxfs/xfs_attr.h
@@ -565,8 +565,7 @@ bool xfs_attr_check_namespace(unsigned int attr_flags);
 bool xfs_attr_namecheck(unsigned int attr_flags, const void *name,
 		size_t length);
 int xfs_attr_calc_size(struct xfs_da_args *args, int *local);
-void xfs_init_attr_trans(struct xfs_da_args *args, struct xfs_trans_res *tres,
-			 unsigned int *total);
+struct xfs_trans_res xfs_attr_set_resv(const struct xfs_da_args *args);
 
 /*
  * Check to see if the attr should be upgraded from non-existent or shortform to
diff --git a/fs/xfs/xfs_attr_item.c b/fs/xfs/xfs_attr_item.c
index 2b10ac4c5fce2..f683b7a9323f1 100644
--- a/fs/xfs/xfs_attr_item.c
+++ b/fs/xfs/xfs_attr_item.c
@@ -746,7 +746,7 @@ xfs_attr_recover_work(
 	struct xfs_attri_log_format	*attrp;
 	struct xfs_attri_log_nameval	*nv = attrip->attri_nameval;
 	int				error;
-	int				total;
+	unsigned int			total = 0;
 
 	/*
 	 * First check the validity of the attr described by the ATTRI.  If any
@@ -763,7 +763,20 @@ xfs_attr_recover_work(
 		return PTR_ERR(attr);
 	args = attr->xattri_da_args;
 
-	xfs_init_attr_trans(args, &resv, &total);
+	switch (xfs_attr_intent_op(attr)) {
+	case XFS_ATTRI_OP_FLAGS_PPTR_SET:
+	case XFS_ATTRI_OP_FLAGS_PPTR_REPLACE:
+	case XFS_ATTRI_OP_FLAGS_SET:
+	case XFS_ATTRI_OP_FLAGS_REPLACE:
+		resv = xfs_attr_set_resv(args);
+		total = args->total;
+		break;
+	case XFS_ATTRI_OP_FLAGS_PPTR_REMOVE:
+	case XFS_ATTRI_OP_FLAGS_REMOVE:
+		resv = M_RES(mp)->tr_attrrm;
+		total = XFS_ATTRRM_SPACE_RES(mp);
+		break;
+	}
 	resv = xlog_recover_resv(&resv);
 	error = xfs_trans_alloc(mp, &resv, total, 0, XFS_TRANS_RESERVE, &tp);
 	if (error)
-- 
GitLab


From 38de567906d95c397d87f292b892686b7ec6fbc3 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Tue, 21 May 2024 23:02:16 -0700
Subject: [PATCH 271/950] xfs: allow symlinks with short remote targets

An internal user complained about log recovery failing on a symlink
("Bad dinode after recovery") with the following (excerpted) format:

core.magic = 0x494e
core.mode = 0120777
core.version = 3
core.format = 2 (extents)
core.nlinkv2 = 1
core.nextents = 1
core.size = 297
core.nblocks = 1
core.naextents = 0
core.forkoff = 0
core.aformat = 2 (extents)
u3.bmx[0] = [startoff,startblock,blockcount,extentflag]
0:[0,12,1,0]

This is a symbolic link with a 297-byte target stored in a disk block,
which is to say this is a symlink with a remote target.  The forkoff is
0, which is to say that there's 512 - 176 == 336 bytes in the inode core
to store the data fork.

Eventually, testing of generic/388 failed with the same inode corruption
message during inode recovery.  In writing a debugging patch to call
xfs_dinode_verify on dirty inode log items when we're committing
transactions, I observed that xfs/298 can reproduce the problem quite
quickly.

xfs/298 creates a symbolic link, adds some extended attributes, then
deletes them all.  The test failure occurs when the final removexattr
also deletes the attr fork because that does not convert the remote
symlink back into a shortform symlink.  That is how we trip this test.
The only reason why xfs/298 only triggers with the debug patch added is
that it deletes the symlink, so the final iflush shows the inode as
free.

I wrote a quick fstest to emulate the behavior of xfs/298, except that
it leaves the symlinks on the filesystem after inducing the "corrupt"
state.  Kernels going back at least as far as 4.18 have written out
symlink inodes in this manner and prior to 1eb70f54c445f they did not
object to reading them back in.

Because we've been writing out inodes this way for quite some time, the
only way to fix this is to relax the check for symbolic links.
Directories don't have this problem because di_size is bumped to
blocksize during the sf->data conversion.

Fixes: 1eb70f54c445f ("xfs: validate inode fork size against fork format")
Signed-off-by: "Darrick J. Wong" <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
---
 fs/xfs/libxfs/xfs_inode_buf.c | 28 ++++++++++++++++++++++++----
 1 file changed, 24 insertions(+), 4 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index d79002343d0b6..e7a7bfbe75b46 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -374,17 +374,37 @@ xfs_dinode_verify_fork(
 	/*
 	 * For fork types that can contain local data, check that the fork
 	 * format matches the size of local data contained within the fork.
-	 *
-	 * For all types, check that when the size says the should be in extent
-	 * or btree format, the inode isn't claiming it is in local format.
 	 */
 	if (whichfork == XFS_DATA_FORK) {
-		if (S_ISDIR(mode) || S_ISLNK(mode)) {
+		/*
+		 * A directory small enough to fit in the inode must be stored
+		 * in local format.  The directory sf <-> extents conversion
+		 * code updates the directory size accordingly.
+		 */
+		if (S_ISDIR(mode)) {
+			if (be64_to_cpu(dip->di_size) <= fork_size &&
+			    fork_format != XFS_DINODE_FMT_LOCAL)
+				return __this_address;
+		}
+
+		/*
+		 * A symlink with a target small enough to fit in the inode can
+		 * be stored in extents format if xattrs were added (thus
+		 * converting the data fork from shortform to remote format)
+		 * and then removed.
+		 */
+		if (S_ISLNK(mode)) {
 			if (be64_to_cpu(dip->di_size) <= fork_size &&
+			    fork_format != XFS_DINODE_FMT_EXTENTS &&
 			    fork_format != XFS_DINODE_FMT_LOCAL)
 				return __this_address;
 		}
 
+		/*
+		 * For all types, check that when the size says the fork should
+		 * be in extent or btree format, the inode isn't claiming to be
+		 * in local format.
+		 */
 		if (be64_to_cpu(dip->di_size) > fork_size &&
 		    fork_format == XFS_DINODE_FMT_LOCAL)
 			return __this_address;
-- 
GitLab


From 95b19e2f4e0f730c83910e7f5e4d62ec68c6d862 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Tue, 21 May 2024 23:02:32 -0700
Subject: [PATCH 272/950] xfs: don't open-code u64_to_user_ptr

Don't open-code what the kernel already provides.

Signed-off-by: "Darrick J. Wong" <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
---
 fs/xfs/scrub/scrub.c | 2 +-
 fs/xfs/xfs_handle.c  | 7 +------
 2 files changed, 2 insertions(+), 7 deletions(-)

diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index c013f0ba4f36b..4cbcf7a86dbec 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -856,7 +856,7 @@ xfs_ioc_scrubv_metadata(
 	if (vec_bytes > PAGE_SIZE)
 		return -ENOMEM;
 
-	uvectors = (void __user *)(uintptr_t)head.svh_vectors;
+	uvectors = u64_to_user_ptr(head.svh_vectors);
 	vectors = memdup_user(uvectors, vec_bytes);
 	if (IS_ERR(vectors))
 		return PTR_ERR(vectors);
diff --git a/fs/xfs/xfs_handle.c b/fs/xfs/xfs_handle.c
index c8785ed595434..a3f16e9b6fe5b 100644
--- a/fs/xfs/xfs_handle.c
+++ b/fs/xfs/xfs_handle.c
@@ -773,11 +773,6 @@ xfs_getparents_expand_lastrec(
 	trace_xfs_getparents_expand_lastrec(gpx->ip, gp, &gpx->context, gpr);
 }
 
-static inline void __user *u64_to_uptr(u64 val)
-{
-	return (void __user *)(uintptr_t)val;
-}
-
 /* Retrieve the parent pointers for a given inode. */
 STATIC int
 xfs_getparents(
@@ -862,7 +857,7 @@ xfs_getparents(
 	ASSERT(gpx->context.firstu <= gpx->gph.gph_request.gp_bufsize);
 
 	/* Copy the records to userspace. */
-	if (copy_to_user(u64_to_uptr(gpx->gph.gph_request.gp_buffer),
+	if (copy_to_user(u64_to_user_ptr(gpx->gph.gph_request.gp_buffer),
 				gpx->krecords, gpx->context.firstu))
 		error = -EFAULT;
 
-- 
GitLab


From 7ff6c798eca05e4a9dcb80163cb454d7787a4bc3 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Tue, 21 May 2024 15:46:32 -0700
Subject: [PATCH 273/950] ACPI: APEI: EINJ: Fix einj_dev release leak

The platform driver conversion of EINJ mistakenly used
platform_device_del() to unwind platform_device_register_full() at
module exit. This leads to a small leak of one 'struct platform_device'
instance per module load/unload cycle. Switch to
platform_device_unregister() which performs both device_del() and final
put_device().

Fixes: 5621fafaac00 ("EINJ: Migrate to a platform driver")
Cc: 6.9+ <stable@vger.kernel.org> # 6.9+
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Ben Cheatham <Benjamin.Cheatham@amd.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/apei/einj-core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/acpi/apei/einj-core.c b/drivers/acpi/apei/einj-core.c
index 9515bcfe5e973..73903a497d73f 100644
--- a/drivers/acpi/apei/einj-core.c
+++ b/drivers/acpi/apei/einj-core.c
@@ -909,7 +909,7 @@ static void __exit einj_exit(void)
 	if (einj_initialized)
 		platform_driver_unregister(&einj_driver);
 
-	platform_device_del(einj_dev);
+	platform_device_unregister(einj_dev);
 }
 
 module_init(einj_init);
-- 
GitLab


From f6f172dc6a6d7775b2df6adfd1350700e9a847ec Mon Sep 17 00:00:00 2001
From: Armin Wolf <W_Armin@gmx.de>
Date: Wed, 22 May 2024 23:36:48 +0200
Subject: [PATCH 274/950] ACPI: EC: Abort address space access upon error

When a multi-byte address space access is requested, acpi_ec_read()/
acpi_ec_write() is being called multiple times.

Abort such operations if a single call to acpi_ec_read() /
acpi_ec_write() fails, as the data read from / written to the EC
might be incomplete.

Signed-off-by: Armin Wolf <W_Armin@gmx.de>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/ec.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index e7793ee9e6498..a68dce2147a4d 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -1333,10 +1333,13 @@ acpi_ec_space_handler(u32 function, acpi_physical_address address,
 	if (ec->busy_polling || bits > 8)
 		acpi_ec_burst_enable(ec);
 
-	for (i = 0; i < bytes; ++i, ++address, ++value)
+	for (i = 0; i < bytes; ++i, ++address, ++value) {
 		result = (function == ACPI_READ) ?
 			acpi_ec_read(ec, address, value) :
 			acpi_ec_write(ec, address, *value);
+		if (result < 0)
+			break;
+	}
 
 	if (ec->busy_polling || bits > 8)
 		acpi_ec_burst_disable(ec);
-- 
GitLab


From c4bd7f1d78340e63de4d073fd3dbe5391e2996e5 Mon Sep 17 00:00:00 2001
From: Armin Wolf <W_Armin@gmx.de>
Date: Wed, 22 May 2024 23:36:49 +0200
Subject: [PATCH 275/950] ACPI: EC: Avoid returning AE_OK on errors in address
 space handler

If an error code other than EINVAL, ENODEV or ETIME is returned
by acpi_ec_read() / acpi_ec_write(), then AE_OK is incorrectly
returned by acpi_ec_space_handler().

Fix this by only returning AE_OK on success, and return AE_ERROR
otherwise.

Signed-off-by: Armin Wolf <W_Armin@gmx.de>
[ rjw: Subject and changelog edits ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/ec.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index a68dce2147a4d..68dd17f96f636 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -1351,8 +1351,10 @@ acpi_ec_space_handler(u32 function, acpi_physical_address address,
 		return AE_NOT_FOUND;
 	case -ETIME:
 		return AE_TIME;
-	default:
+	case 0:
 		return AE_OK;
+	default:
+		return AE_ERROR;
 	}
 }
 
-- 
GitLab


From 52a2f0608366a629d43dacd3191039c95fef74ba Mon Sep 17 00:00:00 2001
From: Parthiban Veerasooran <Parthiban.Veerasooran@microchip.com>
Date: Thu, 23 May 2024 14:23:14 +0530
Subject: [PATCH 276/950] net: usb: smsc95xx: fix changing LED_SEL bit value
 updated from EEPROM

LED Select (LED_SEL) bit in the LED General Purpose IO Configuration
register is used to determine the functionality of external LED pins
(Speed Indicator, Link and Activity Indicator, Full Duplex Link
Indicator). The default value for this bit is 0 when no EEPROM is
present. If a EEPROM is present, the default value is the value of the
LED Select bit in the Configuration Flags of the EEPROM. A USB Reset or
Lite Reset (LRST) will cause this bit to be restored to the image value
last loaded from EEPROM, or to be set to 0 if no EEPROM is present.

While configuring the dual purpose GPIO/LED pins to LED outputs in the
LED General Purpose IO Configuration register, the LED_SEL bit is changed
as 0 and resulting the configured value from the EEPROM is cleared. The
issue is fixed by using read-modify-write approach.

Fixes: f293501c61c5 ("smsc95xx: configure LED outputs")
Signed-off-by: Parthiban Veerasooran <Parthiban.Veerasooran@microchip.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Woojung Huh <woojung.huh@microchip.com>
Link: https://lore.kernel.org/r/20240523085314.167650-1-Parthiban.Veerasooran@microchip.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/usb/smsc95xx.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c
index cbea246664795..8e82184be5e7d 100644
--- a/drivers/net/usb/smsc95xx.c
+++ b/drivers/net/usb/smsc95xx.c
@@ -879,7 +879,7 @@ static int smsc95xx_start_rx_path(struct usbnet *dev)
 static int smsc95xx_reset(struct usbnet *dev)
 {
 	struct smsc95xx_priv *pdata = dev->driver_priv;
-	u32 read_buf, write_buf, burst_cap;
+	u32 read_buf, burst_cap;
 	int ret = 0, timeout;
 
 	netif_dbg(dev, ifup, dev->net, "entering smsc95xx_reset\n");
@@ -1003,10 +1003,13 @@ static int smsc95xx_reset(struct usbnet *dev)
 		return ret;
 	netif_dbg(dev, ifup, dev->net, "ID_REV = 0x%08x\n", read_buf);
 
+	ret = smsc95xx_read_reg(dev, LED_GPIO_CFG, &read_buf);
+	if (ret < 0)
+		return ret;
 	/* Configure GPIO pins as LED outputs */
-	write_buf = LED_GPIO_CFG_SPD_LED | LED_GPIO_CFG_LNK_LED |
-		LED_GPIO_CFG_FDX_LED;
-	ret = smsc95xx_write_reg(dev, LED_GPIO_CFG, write_buf);
+	read_buf |= LED_GPIO_CFG_SPD_LED | LED_GPIO_CFG_LNK_LED |
+		    LED_GPIO_CFG_FDX_LED;
+	ret = smsc95xx_write_reg(dev, LED_GPIO_CFG, read_buf);
 	if (ret < 0)
 		return ret;
 
-- 
GitLab


From 9e69acc1de306b5243ca2ef8a54242e56d01b8e5 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Thu, 23 May 2024 17:57:21 +0200
Subject: [PATCH 277/950] thermal/debugfs: Print initial trip temperature and
 hysteresis in tze_seq_show()

The temperature and hysteresis of a trip point may change during a
mitigation episode it is involved in (it may even become invalid
altogether), so in order to avoid possible confusion related to that,
store the temperature and hysteresis of trip points at the time they
are crossed on the way up and print those values instead of their
current temperature and hysteresis.

Fixes: 7ef01f228c9f ("thermal/debugfs: Add thermal debugfs information for mitigation episodes")
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/thermal/thermal_debugfs.c | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/drivers/thermal/thermal_debugfs.c b/drivers/thermal/thermal_debugfs.c
index 91f9c21235a8a..e0e4eb6fad397 100644
--- a/drivers/thermal/thermal_debugfs.c
+++ b/drivers/thermal/thermal_debugfs.c
@@ -91,6 +91,8 @@ struct cdev_record {
  *
  * @timestamp: the trip crossing timestamp
  * @duration: total time when the zone temperature was above the trip point
+ * @trip_temp: trip temperature at mitigation start
+ * @trip_hyst: trip hysteresis at mitigation start
  * @count: the number of times the zone temperature was above the trip point
  * @max: maximum recorded temperature above the trip point
  * @min: minimum recorded temperature above the trip point
@@ -99,6 +101,8 @@ struct cdev_record {
 struct trip_stats {
 	ktime_t timestamp;
 	ktime_t duration;
+	int trip_temp;
+	int trip_hyst;
 	int count;
 	int max;
 	int min;
@@ -574,6 +578,7 @@ void thermal_debug_tz_trip_up(struct thermal_zone_device *tz,
 	struct thermal_debugfs *thermal_dbg = tz->debugfs;
 	int trip_id = thermal_zone_trip_id(tz, trip);
 	ktime_t now = ktime_get();
+	struct trip_stats *trip_stats;
 
 	if (!thermal_dbg)
 		return;
@@ -639,7 +644,10 @@ void thermal_debug_tz_trip_up(struct thermal_zone_device *tz,
 	tz_dbg->trips_crossed[tz_dbg->nr_trips++] = trip_id;
 
 	tze = list_first_entry(&tz_dbg->tz_episodes, struct tz_episode, node);
-	tze->trip_stats[trip_id].timestamp = now;
+	trip_stats = &tze->trip_stats[trip_id];
+	trip_stats->trip_temp = trip->temperature;
+	trip_stats->trip_hyst = trip->hysteresis;
+	trip_stats->timestamp = now;
 
 unlock:
 	mutex_unlock(&thermal_dbg->lock);
@@ -836,8 +844,8 @@ static int tze_seq_show(struct seq_file *s, void *v)
 		seq_printf(s, "| %*d | %*s | %*d | %*d | %c%*lld | %*d | %*d | %*d |\n",
 			   4 , trip_id,
 			   8, type,
-			   9, trip->temperature,
-			   9, trip->hysteresis,
+			   9, trip_stats->trip_temp,
+			   9, trip_stats->trip_hyst,
 			   c, 10, duration_ms,
 			   9, trip_stats->avg,
 			   9, trip_stats->min,
-- 
GitLab


From 5a599e10e53d1914adf0032c730bc0f604a5d947 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Thu, 23 May 2024 17:58:42 +0200
Subject: [PATCH 278/950] thermal/debugfs: Allow tze_seq_show() to print
 statistics for invalid trips

Commit a6258fde8de3 ("thermal/debugfs: Make tze_seq_show() skip invalid
trips and trips with no stats") modified tze_seq_show() to skip invalid
trips, but it overlooked the fact that a trip may become invalid during
a mitigation eposide involving it, in which case its statistics should
still be reported.

For this reason, remove the invalid trip temperature check from the
main loop in tze_seq_show().

The trips that have never been valid will still be skipped after this
change because there are no statistics to report for them.

Fixes: a6258fde8de3 ("thermal/debugfs: Make tze_seq_show() skip invalid trips and trips with no stats")
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/thermal/thermal_debugfs.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/thermal/thermal_debugfs.c b/drivers/thermal/thermal_debugfs.c
index e0e4eb6fad397..9424472291570 100644
--- a/drivers/thermal/thermal_debugfs.c
+++ b/drivers/thermal/thermal_debugfs.c
@@ -802,10 +802,6 @@ static int tze_seq_show(struct seq_file *s, void *v)
 		const struct thermal_trip *trip = &td->trip;
 		struct trip_stats *trip_stats;
 
-		/* Skip invalid trips. */
-		if (trip->temperature == THERMAL_TEMP_INVALID)
-			continue;
-
 		/*
 		 * There is no possible mitigation happening at the
 		 * critical trip point, so the stats will be always
-- 
GitLab


From cb573eec609c44f44b27c2fa07afd926eddc9f89 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Thu, 23 May 2024 18:00:14 +0200
Subject: [PATCH 279/950] thermal: core: Introduce thermal_trip_crossed()

Add a helper function called thermal_trip_crossed() to be invoked by
__thermal_zone_device_update() in order to notify user space, the
thermal debug code and the zone governor about trip crossing.

Subsequently, this will also be used in the case when a trip point
becomes invalid after being crossed on the way up.

No intentional functional impact.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/thermal/thermal_core.c | 29 +++++++++++++++++++----------
 1 file changed, 19 insertions(+), 10 deletions(-)

diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 54cce4e523bc5..c119ef920793d 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -467,6 +467,21 @@ static void thermal_governor_trip_crossed(struct thermal_governor *governor,
 		governor->trip_crossed(tz, trip, crossed_up);
 }
 
+static void thermal_trip_crossed(struct thermal_zone_device *tz,
+				 const struct thermal_trip *trip,
+				 struct thermal_governor *governor,
+				 bool crossed_up)
+{
+	if (crossed_up) {
+		thermal_notify_tz_trip_up(tz, trip);
+		thermal_debug_tz_trip_up(tz, trip);
+	} else {
+		thermal_notify_tz_trip_down(tz, trip);
+		thermal_debug_tz_trip_down(tz, trip);
+	}
+	thermal_governor_trip_crossed(governor, tz, trip, crossed_up);
+}
+
 static int thermal_trip_notify_cmp(void *ascending, const struct list_head *a,
 				   const struct list_head *b)
 {
@@ -506,18 +521,12 @@ void __thermal_zone_device_update(struct thermal_zone_device *tz,
 		handle_thermal_trip(tz, td, &way_up_list, &way_down_list);
 
 	list_sort(&way_up_list, &way_up_list, thermal_trip_notify_cmp);
-	list_for_each_entry(td, &way_up_list, notify_list_node) {
-		thermal_notify_tz_trip_up(tz, &td->trip);
-		thermal_debug_tz_trip_up(tz, &td->trip);
-		thermal_governor_trip_crossed(governor, tz, &td->trip, true);
-	}
+	list_for_each_entry(td, &way_up_list, notify_list_node)
+		thermal_trip_crossed(tz, &td->trip, governor, true);
 
 	list_sort(NULL, &way_down_list, thermal_trip_notify_cmp);
-	list_for_each_entry(td, &way_down_list, notify_list_node) {
-		thermal_notify_tz_trip_down(tz, &td->trip);
-		thermal_debug_tz_trip_down(tz, &td->trip);
-		thermal_governor_trip_crossed(governor, tz, &td->trip, false);
-	}
+	list_for_each_entry(td, &way_down_list, notify_list_node)
+		thermal_trip_crossed(tz, &td->trip, governor, false);
 
 	if (governor->manage)
 		governor->manage(tz);
-- 
GitLab


From ae2170d6ea96e652c7fb5689f1980986bf48b7b8 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Thu, 23 May 2024 18:05:03 +0200
Subject: [PATCH 280/950] thermal: trip: Trigger trip down notifications when
 trips involved in mitigation become invalid

When a trip point becomes invalid after being crossed on the way up,
it is involved in a mitigation episode that needs to be adjusted to
compensate for the trip going away.

For this reason, introduce thermal_zone_trip_down() as a wrapper
around thermal_trip_crossed() and make thermal_zone_set_trip_temp()
call it if the new temperature of the trip at hand is equal to
THERMAL_TEMP_INVALID and it has been crossed on the way up to trigger
all of the necessary adjustments in user space, the thermal debug
code and the zone governor.

Fixes: 8c69a777e480 ("thermal: core: Fix the handling of invalid trip points")
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/thermal/thermal_core.c |  6 ++++++
 drivers/thermal/thermal_core.h |  2 ++
 drivers/thermal/thermal_trip.c | 20 ++++++++++++--------
 3 files changed, 20 insertions(+), 8 deletions(-)

diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index c119ef920793d..30567b4994551 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -602,6 +602,12 @@ void thermal_zone_device_update(struct thermal_zone_device *tz,
 }
 EXPORT_SYMBOL_GPL(thermal_zone_device_update);
 
+void thermal_zone_trip_down(struct thermal_zone_device *tz,
+			    const struct thermal_trip *trip)
+{
+	thermal_trip_crossed(tz, trip, thermal_get_tz_governor(tz), false);
+}
+
 int for_each_thermal_governor(int (*cb)(struct thermal_governor *, void *),
 			      void *data)
 {
diff --git a/drivers/thermal/thermal_core.h b/drivers/thermal/thermal_core.h
index d9785e5bbb08c..20e7b45673d68 100644
--- a/drivers/thermal/thermal_core.h
+++ b/drivers/thermal/thermal_core.h
@@ -246,6 +246,8 @@ int thermal_zone_trip_id(const struct thermal_zone_device *tz,
 void thermal_zone_trip_updated(struct thermal_zone_device *tz,
 			       const struct thermal_trip *trip);
 int __thermal_zone_get_temp(struct thermal_zone_device *tz, int *temp);
+void thermal_zone_trip_down(struct thermal_zone_device *tz,
+			    const struct thermal_trip *trip);
 
 /* sysfs I/F */
 int thermal_zone_create_device_groups(struct thermal_zone_device *tz);
diff --git a/drivers/thermal/thermal_trip.c b/drivers/thermal/thermal_trip.c
index d6a6acc78ddb6..49e63db685172 100644
--- a/drivers/thermal/thermal_trip.c
+++ b/drivers/thermal/thermal_trip.c
@@ -152,17 +152,23 @@ void thermal_zone_set_trip_temp(struct thermal_zone_device *tz,
 	if (trip->temperature == temp)
 		return;
 
+	trip->temperature = temp;
+	thermal_notify_tz_trip_change(tz, trip);
+
 	if (temp == THERMAL_TEMP_INVALID) {
 		struct thermal_trip_desc *td = trip_to_trip_desc(trip);
 
-		if (trip->type == THERMAL_TRIP_PASSIVE &&
-		    tz->temperature >= td->threshold) {
+		if (tz->temperature >= td->threshold) {
 			/*
-			 * The trip has been crossed, so the thermal zone's
-			 * passive count needs to be adjusted.
+			 * The trip has been crossed on the way up, so some
+			 * adjustments are needed to compensate for the lack
+			 * of it going forward.
 			 */
-			tz->passive--;
-			WARN_ON_ONCE(tz->passive < 0);
+			if (trip->type == THERMAL_TRIP_PASSIVE) {
+				tz->passive--;
+				WARN_ON_ONCE(tz->passive < 0);
+			}
+			thermal_zone_trip_down(tz, trip);
 		}
 		/*
 		 * Invalidate the threshold to avoid triggering a spurious
@@ -170,7 +176,5 @@ void thermal_zone_set_trip_temp(struct thermal_zone_device *tz,
 		 */
 		td->threshold = INT_MAX;
 	}
-	trip->temperature = temp;
-	thermal_notify_tz_trip_change(tz, trip);
 }
 EXPORT_SYMBOL_GPL(thermal_zone_set_trip_temp);
-- 
GitLab


From 779aa4d74785078575ee20d05d49e6942d1f2844 Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Fri, 24 May 2024 06:48:17 -0700
Subject: [PATCH 281/950] drm/nouveau/nvif: Avoid build error due to potential
 integer overflows

Trying to build parisc:allmodconfig with gcc 12.x or later results
in the following build error.

drivers/gpu/drm/nouveau/nvif/object.c: In function 'nvif_object_mthd':
drivers/gpu/drm/nouveau/nvif/object.c:161:9: error:
	'memcpy' accessing 4294967264 or more bytes at offsets 0 and 32 overlaps 6442450881 bytes at offset -2147483617 [-Werror=restrict]
  161 |         memcpy(data, args->mthd.data, size);
      |         ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
drivers/gpu/drm/nouveau/nvif/object.c: In function 'nvif_object_ctor':
drivers/gpu/drm/nouveau/nvif/object.c:298:17: error:
	'memcpy' accessing 4294967240 or more bytes at offsets 0 and 56 overlaps 6442450833 bytes at offset -2147483593 [-Werror=restrict]
  298 |                 memcpy(data, args->new.data, size);

gcc assumes that 'sizeof(*args) + size' can overflow, which would result
in the problem.

The problem is not new, only it is now no longer a warning but an error
since W=1 has been enabled for the drm subsystem and since Werror is
enabled for test builds.

Rearrange arithmetic and use check_add_overflow() for validating the
allocation size to avoid the overflow. While at it, split assignments
out of if conditions.

Fixes: a61ddb4393ad ("drm: enable (most) W=1 warnings by default across the subsystem")
Cc: Javier Martinez Canillas <javierm@redhat.com>
Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Thomas Zimmermann <tzimmermann@suse.de>
Cc: Danilo Krummrich <dakr@redhat.com>
Cc: Maxime Ripard <mripard@kernel.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Cc: Joe Perches <joe@perches.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Danilo Krummrich <dakr@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240524134817.1369993-1-linux@roeck-us.net
---
 drivers/gpu/drm/nouveau/nvif/object.c | 24 ++++++++++++++++++------
 1 file changed, 18 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/nouveau/nvif/object.c b/drivers/gpu/drm/nouveau/nvif/object.c
index 4d1aaee8fe15f..1d19c87eaec18 100644
--- a/drivers/gpu/drm/nouveau/nvif/object.c
+++ b/drivers/gpu/drm/nouveau/nvif/object.c
@@ -142,11 +142,16 @@ nvif_object_mthd(struct nvif_object *object, u32 mthd, void *data, u32 size)
 		struct nvif_ioctl_v0 ioctl;
 		struct nvif_ioctl_mthd_v0 mthd;
 	} *args;
+	u32 args_size;
 	u8 stack[128];
 	int ret;
 
-	if (sizeof(*args) + size > sizeof(stack)) {
-		if (!(args = kmalloc(sizeof(*args) + size, GFP_KERNEL)))
+	if (check_add_overflow(sizeof(*args), size, &args_size))
+		return -ENOMEM;
+
+	if (args_size > sizeof(stack)) {
+		args = kmalloc(args_size, GFP_KERNEL);
+		if (!args)
 			return -ENOMEM;
 	} else {
 		args = (void *)stack;
@@ -157,7 +162,7 @@ nvif_object_mthd(struct nvif_object *object, u32 mthd, void *data, u32 size)
 	args->mthd.method = mthd;
 
 	memcpy(args->mthd.data, data, size);
-	ret = nvif_object_ioctl(object, args, sizeof(*args) + size, NULL);
+	ret = nvif_object_ioctl(object, args, args_size, NULL);
 	memcpy(data, args->mthd.data, size);
 	if (args != (void *)stack)
 		kfree(args);
@@ -276,7 +281,15 @@ nvif_object_ctor(struct nvif_object *parent, const char *name, u32 handle,
 	object->map.size = 0;
 
 	if (parent) {
-		if (!(args = kmalloc(sizeof(*args) + size, GFP_KERNEL))) {
+		u32 args_size;
+
+		if (check_add_overflow(sizeof(*args), size, &args_size)) {
+			nvif_object_dtor(object);
+			return -ENOMEM;
+		}
+
+		args = kmalloc(args_size, GFP_KERNEL);
+		if (!args) {
 			nvif_object_dtor(object);
 			return -ENOMEM;
 		}
@@ -293,8 +306,7 @@ nvif_object_ctor(struct nvif_object *parent, const char *name, u32 handle,
 		args->new.oclass = oclass;
 
 		memcpy(args->new.data, data, size);
-		ret = nvif_object_ioctl(parent, args, sizeof(*args) + size,
-					&object->priv);
+		ret = nvif_object_ioctl(parent, args, args_size, &object->priv);
 		memcpy(data, args->new.data, size);
 		kfree(args);
 		if (ret == 0)
-- 
GitLab


From f89ea63f1c65d3e93b255f14f9d9e05df87955fa Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 24 May 2024 15:26:11 +0100
Subject: [PATCH 282/950] netfs, 9p: Fix race between umount and async request
 completion

There's a problem in 9p's interaction with netfslib whereby a crash occurs
because the 9p_fid structs get forcibly destroyed during client teardown
(without paying attention to their refcounts) before netfslib has finished
with them.  However, it's not a simple case of deferring the clunking that
p9_fid_put() does as that requires the p9_client record to still be
present.

The problem is that netfslib has to unlock pages and clear the IN_PROGRESS
flag before destroying the objects involved - including the fid - and, in
any case, nothing checks to see if writeback completed barring looking at
the page flags.

Fix this by keeping a count of outstanding I/O requests (of any type) and
waiting for it to quiesce during inode eviction.

Reported-by: syzbot+df038d463cca332e8414@syzkaller.appspotmail.com
Link: https://lore.kernel.org/all/0000000000005be0aa061846f8d6@google.com/
Reported-by: syzbot+d7c7a495a5e466c031b6@syzkaller.appspotmail.com
Link: https://lore.kernel.org/all/000000000000b86c5e06130da9c6@google.com/
Reported-by: syzbot+1527696d41a634cc1819@syzkaller.appspotmail.com
Link: https://lore.kernel.org/all/000000000000041f960618206d7e@google.com/
Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://lore.kernel.org/r/755891.1716560771@warthog.procyon.org.uk
Tested-by: syzbot+d7c7a495a5e466c031b6@syzkaller.appspotmail.com
Reviewed-by: Dominique Martinet <asmadeus@codewreck.org>
cc: Eric Van Hensbergen <ericvh@kernel.org>
cc: Latchesar Ionkov <lucho@ionkov.net>
cc: Christian Schoenebeck <linux_oss@crudebyte.com>
cc: Jeff Layton <jlayton@kernel.org>
cc: Steve French <sfrench@samba.org>
cc: Hillf Danton <hdanton@sina.com>
cc: v9fs@lists.linux.dev
cc: linux-afs@lists.infradead.org
cc: linux-cifs@vger.kernel.org
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
Reported-and-tested-by: syzbot+d7c7a495a5e466c031b6@syzkaller.appspotmail.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/9p/vfs_inode.c      |  1 +
 fs/afs/inode.c         |  1 +
 fs/netfs/objects.c     |  5 +++++
 fs/smb/client/cifsfs.c |  1 +
 include/linux/netfs.h  | 18 ++++++++++++++++++
 5 files changed, 26 insertions(+)

diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 7a3308d776060..fd72fc38c8f5b 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -348,6 +348,7 @@ void v9fs_evict_inode(struct inode *inode)
 	__le32 __maybe_unused version;
 
 	if (!is_bad_inode(inode)) {
+		netfs_wait_for_outstanding_io(inode);
 		truncate_inode_pages_final(&inode->i_data);
 
 		version = cpu_to_le32(v9inode->qid.version);
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index 94fc049aff584..15bb7989c387a 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -648,6 +648,7 @@ void afs_evict_inode(struct inode *inode)
 
 	ASSERTCMP(inode->i_ino, ==, vnode->fid.vnode);
 
+	netfs_wait_for_outstanding_io(inode);
 	truncate_inode_pages_final(&inode->i_data);
 
 	afs_set_cache_aux(vnode, &aux);
diff --git a/fs/netfs/objects.c b/fs/netfs/objects.c
index c90d482b16505..f4a6427274792 100644
--- a/fs/netfs/objects.c
+++ b/fs/netfs/objects.c
@@ -72,6 +72,7 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping,
 		}
 	}
 
+	atomic_inc(&ctx->io_count);
 	trace_netfs_rreq_ref(rreq->debug_id, 1, netfs_rreq_trace_new);
 	netfs_proc_add_rreq(rreq);
 	netfs_stat(&netfs_n_rh_rreq);
@@ -124,6 +125,7 @@ static void netfs_free_request(struct work_struct *work)
 {
 	struct netfs_io_request *rreq =
 		container_of(work, struct netfs_io_request, work);
+	struct netfs_inode *ictx = netfs_inode(rreq->inode);
 	unsigned int i;
 
 	trace_netfs_rreq(rreq, netfs_rreq_trace_free);
@@ -142,6 +144,9 @@ static void netfs_free_request(struct work_struct *work)
 		}
 		kvfree(rreq->direct_bv);
 	}
+
+	if (atomic_dec_and_test(&ictx->io_count))
+		wake_up_var(&ictx->io_count);
 	call_rcu(&rreq->rcu, netfs_free_request_rcu);
 }
 
diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c
index ec5b639f421a2..14810ffd15c89 100644
--- a/fs/smb/client/cifsfs.c
+++ b/fs/smb/client/cifsfs.c
@@ -431,6 +431,7 @@ cifs_free_inode(struct inode *inode)
 static void
 cifs_evict_inode(struct inode *inode)
 {
+	netfs_wait_for_outstanding_io(inode);
 	truncate_inode_pages_final(&inode->i_data);
 	if (inode->i_state & I_PINNING_NETFS_WB)
 		cifs_fscache_unuse_inode_cookie(inode, true);
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index ca56a4428043d..3b22ce0d064cc 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -68,6 +68,7 @@ struct netfs_inode {
 	loff_t			remote_i_size;	/* Size of the remote file */
 	loff_t			zero_point;	/* Size after which we assume there's no data
 						 * on the server */
+	atomic_t		io_count;	/* Number of outstanding reqs */
 	unsigned long		flags;
 #define NETFS_ICTX_ODIRECT	0		/* The file has DIO in progress */
 #define NETFS_ICTX_UNBUFFERED	1		/* I/O should not use the pagecache */
@@ -472,6 +473,7 @@ static inline void netfs_inode_init(struct netfs_inode *ctx,
 	ctx->remote_i_size = i_size_read(&ctx->inode);
 	ctx->zero_point = LLONG_MAX;
 	ctx->flags = 0;
+	atomic_set(&ctx->io_count, 0);
 #if IS_ENABLED(CONFIG_FSCACHE)
 	ctx->cache = NULL;
 #endif
@@ -515,4 +517,20 @@ static inline struct fscache_cookie *netfs_i_cookie(struct netfs_inode *ctx)
 #endif
 }
 
+/**
+ * netfs_wait_for_outstanding_io - Wait for outstanding I/O to complete
+ * @ctx: The netfs inode to wait on
+ *
+ * Wait for outstanding I/O requests of any type to complete.  This is intended
+ * to be called from inode eviction routines.  This makes sure that any
+ * resources held by those requests are cleaned up before we let the inode get
+ * cleaned up.
+ */
+static inline void netfs_wait_for_outstanding_io(struct inode *inode)
+{
+	struct netfs_inode *ictx = netfs_inode(inode);
+
+	wait_var_event(&ictx->io_count, atomic_read(&ictx->io_count) == 0);
+}
+
 #endif /* _LINUX_NETFS_H */
-- 
GitLab


From e569eb34970281438e2b48a3ef11c87459fcfbcb Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Carlos=20L=C3=B3pez?= <clopez@suse.de>
Date: Mon, 27 May 2024 11:43:52 +0200
Subject: [PATCH 283/950] tracing/probes: fix error check in parse_btf_field()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

btf_find_struct_member() might return NULL or an error via the
ERR_PTR() macro. However, its caller in parse_btf_field() only checks
for the NULL condition. Fix this by using IS_ERR() and returning the
error up the stack.

Link: https://lore.kernel.org/all/20240527094351.15687-1-clopez@suse.de/

Fixes: c440adfbe3025 ("tracing/probes: Support BTF based data structure field access")
Signed-off-by: Carlos López <clopez@suse.de>
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
 kernel/trace/trace_probe.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index 5e263c1415740..39877c80d6cb9 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -554,6 +554,10 @@ static int parse_btf_field(char *fieldname, const struct btf_type *type,
 			anon_offs = 0;
 			field = btf_find_struct_member(ctx->btf, type, fieldname,
 						       &anon_offs);
+			if (IS_ERR(field)) {
+				trace_probe_log_err(ctx->offset, BAD_BTF_TID);
+				return PTR_ERR(field);
+			}
 			if (!field) {
 				trace_probe_log_err(ctx->offset, NO_BTF_FIELD);
 				return -ENOENT;
-- 
GitLab


From 797c525e85d1e44cf0e6f338890e8e0c661f524a Mon Sep 17 00:00:00 2001
From: Charles Keepax <ckeepax@opensource.cirrus.com>
Date: Mon, 27 May 2024 11:08:40 +0100
Subject: [PATCH 284/950] ASoC: cs42l43: Only restrict 44.1kHz for the ASP

The SoundWire interface can always support 44.1kHz using flow controlled
mode, and whether the ASP is in master mode should obviously only affect
the ASP. Update cs42l43_startup() to only restrict the rates for the ASP
DAI.

Fixes: fc918cbe874e ("ASoC: cs42l43: Add support for the cs42l43")
Signed-off-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Link: https://msgid.link/r/20240527100840.439832-1-ckeepax@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/cs42l43.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/sound/soc/codecs/cs42l43.c b/sound/soc/codecs/cs42l43.c
index 94685449f0f48..92674314227c4 100644
--- a/sound/soc/codecs/cs42l43.c
+++ b/sound/soc/codecs/cs42l43.c
@@ -310,8 +310,9 @@ static int cs42l43_startup(struct snd_pcm_substream *substream, struct snd_soc_d
 	struct snd_soc_component *component = dai->component;
 	struct cs42l43_codec *priv = snd_soc_component_get_drvdata(component);
 	struct cs42l43 *cs42l43 = priv->core;
-	int provider = !!regmap_test_bits(cs42l43->regmap, CS42L43_ASP_CLK_CONFIG2,
-					  CS42L43_ASP_MASTER_MODE_MASK);
+	int provider = !dai->id || !!regmap_test_bits(cs42l43->regmap,
+						      CS42L43_ASP_CLK_CONFIG2,
+						      CS42L43_ASP_MASTER_MODE_MASK);
 
 	if (provider)
 		priv->constraint.mask = CS42L43_PROVIDER_RATE_MASK;
-- 
GitLab


From 8d34c12e8751fe180157fbb34a758ed4eede3806 Mon Sep 17 00:00:00 2001
From: Charles Keepax <ckeepax@opensource.cirrus.com>
Date: Mon, 27 May 2024 11:02:37 +0100
Subject: [PATCH 285/950] ASoC: wm_adsp: Add missing MODULE_DESCRIPTION()

wm_adsp is built as a separate module and as such should include a
MODULE_DESCRIPTION() macro.

Signed-off-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Link: https://msgid.link/r/20240527100237.430240-1-ckeepax@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/wm_adsp.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c
index c9d9a7b28efb0..68d2d6444533f 100644
--- a/sound/soc/codecs/wm_adsp.c
+++ b/sound/soc/codecs/wm_adsp.c
@@ -2085,5 +2085,6 @@ static const struct cs_dsp_client_ops wm_adsp2_client_ops = {
 	.watchdog_expired = wm_adsp_fatal_error,
 };
 
+MODULE_DESCRIPTION("Cirrus Logic ASoC DSP Support");
 MODULE_LICENSE("GPL v2");
 MODULE_IMPORT_NS(FW_CS_DSP);
-- 
GitLab


From d5d2a5dacbc8ea4386071ce243c43ea0dac23cb8 Mon Sep 17 00:00:00 2001
From: Charles Keepax <ckeepax@opensource.cirrus.com>
Date: Mon, 27 May 2024 11:13:26 +0100
Subject: [PATCH 286/950] MAINTAINERS: Remove James Schulman from Cirrus audio
 maintainers

James no longer works for Cirrus Logic, remove him from the list of
maintainers for the Cirrus audio CODEC drivers.

Signed-off-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Link: https://msgid.link/r/20240527101326.440345-1-ckeepax@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 MAINTAINERS | 1 -
 1 file changed, 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index d6c90161c7bfe..a6a011792167f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -5187,7 +5187,6 @@ F:	Documentation/devicetree/bindings/media/i2c/chrontel,ch7322.yaml
 F:	drivers/media/cec/i2c/ch7322.c
 
 CIRRUS LOGIC AUDIO CODEC DRIVERS
-M:	James Schulman <james.schulman@cirrus.com>
 M:	David Rhodes <david.rhodes@cirrus.com>
 M:	Richard Fitzgerald <rf@opensource.cirrus.com>
 L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
-- 
GitLab


From 6cb05d89fd62a76a9b74bd16211fb0930e89fea8 Mon Sep 17 00:00:00 2001
From: Fedor Pchelkin <pchelkin@ispras.ru>
Date: Wed, 22 May 2024 21:13:08 +0300
Subject: [PATCH 287/950] dma-buf: handle testing kthreads creation failure
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

kthread creation may possibly fail inside race_signal_callback(). In
such a case stop the already started threads, put the already taken
references to them and return with error code.

Found by Linux Verification Center (linuxtesting.org).

Fixes: 2989f6451084 ("dma-buf: Add selftests for dma-fence")
Cc: stable@vger.kernel.org
Signed-off-by: Fedor Pchelkin <pchelkin@ispras.ru>
Reviewed-by: T.J. Mercier <tjmercier@google.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240522181308.841686-1-pchelkin@ispras.ru
Signed-off-by: Christian König <christian.koenig@amd.com>
---
 drivers/dma-buf/st-dma-fence.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/dma-buf/st-dma-fence.c b/drivers/dma-buf/st-dma-fence.c
index b7c6f7ea9e0c8..6a1bfcd0cc210 100644
--- a/drivers/dma-buf/st-dma-fence.c
+++ b/drivers/dma-buf/st-dma-fence.c
@@ -540,6 +540,12 @@ static int race_signal_callback(void *arg)
 			t[i].before = pass;
 			t[i].task = kthread_run(thread_signal_callback, &t[i],
 						"dma-fence:%d", i);
+			if (IS_ERR(t[i].task)) {
+				ret = PTR_ERR(t[i].task);
+				while (--i >= 0)
+					kthread_stop_put(t[i].task);
+				return ret;
+			}
 			get_task_struct(t[i].task);
 		}
 
-- 
GitLab


From 82d71b53d7e732ede6028591342bdc80fabfa29f Mon Sep 17 00:00:00 2001
From: Lukas Bulwahn <lukas.bulwahn@redhat.com>
Date: Mon, 27 May 2024 15:13:14 +0200
Subject: [PATCH 288/950] Documentation/core-api: correct reference to
 SWIOTLB_DYNAMIC

Commit c93f261dfc39 ("Documentation/core-api: add swiotlb documentation")
accidentally refers to CONFIG_DYNAMIC_SWIOTLB in one place, while the
config is actually called CONFIG_SWIOTLB_DYNAMIC.

Correct the reference to the intended config option.

Signed-off-by: Lukas Bulwahn <lukas.bulwahn@redhat.com>
Reviewed-by: Petr Tesarik <petr@tesarici.cz>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 Documentation/core-api/swiotlb.rst | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/core-api/swiotlb.rst b/Documentation/core-api/swiotlb.rst
index 5ad2c9ca85bcb..cf06bae44ff85 100644
--- a/Documentation/core-api/swiotlb.rst
+++ b/Documentation/core-api/swiotlb.rst
@@ -192,7 +192,7 @@ alignment larger than PAGE_SIZE.
 
 Dynamic swiotlb
 ---------------
-When CONFIG_DYNAMIC_SWIOTLB is enabled, swiotlb can do on-demand expansion of
+When CONFIG_SWIOTLB_DYNAMIC is enabled, swiotlb can do on-demand expansion of
 the amount of memory available for allocation as bounce buffers. If a bounce
 buffer request fails due to lack of available space, an asynchronous background
 task is kicked off to allocate memory from general system memory and turn it
-- 
GitLab


From 80e4e17ac9e05adba3f1f0e1793398086e6d4007 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 21 May 2024 15:16:06 -0700
Subject: [PATCH 289/950] block: remove blk_queue_max_integrity_segments

This is unused now that all the atomic queue limit conversions are
merged.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20240521221606.393040-1-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/blk-integrity.h | 10 ----------
 1 file changed, 10 deletions(-)

diff --git a/include/linux/blk-integrity.h b/include/linux/blk-integrity.h
index e253e7bd0d179..7428cb43952da 100644
--- a/include/linux/blk-integrity.h
+++ b/include/linux/blk-integrity.h
@@ -66,12 +66,6 @@ blk_integrity_queue_supports_integrity(struct request_queue *q)
 	return q->integrity.profile;
 }
 
-static inline void blk_queue_max_integrity_segments(struct request_queue *q,
-						    unsigned int segs)
-{
-	q->limits.max_integrity_segments = segs;
-}
-
 static inline unsigned short
 queue_max_integrity_segments(const struct request_queue *q)
 {
@@ -151,10 +145,6 @@ static inline void blk_integrity_register(struct gendisk *d,
 static inline void blk_integrity_unregister(struct gendisk *d)
 {
 }
-static inline void blk_queue_max_integrity_segments(struct request_queue *q,
-						    unsigned int segs)
-{
-}
 static inline unsigned short
 queue_max_integrity_segments(const struct request_queue *q)
 {
-- 
GitLab


From d9780064b163b91c28e4d44ec3115599db65b7fa Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 27 May 2024 14:36:18 +0200
Subject: [PATCH 290/950] dm: move setting zoned_enabled to
 dm_table_set_restrictions

Keep it together with the rest of the zoned code.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Link: https://lore.kernel.org/r/20240527123634.1116952-2-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/md/dm-table.c | 3 ---
 drivers/md/dm-zone.c  | 8 +++++++-
 2 files changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index cc66a27c363a6..e291b78b307b1 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -2040,9 +2040,6 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 		r = dm_set_zones_restrictions(t, q);
 		if (r)
 			return r;
-		if (blk_queue_is_zoned(q) &&
-		    !static_key_enabled(&zoned_enabled.key))
-			static_branch_enable(&zoned_enabled);
 	}
 
 	dm_update_crypto_profile(q, t);
diff --git a/drivers/md/dm-zone.c b/drivers/md/dm-zone.c
index 8e6bcb0d786a1..3103360ce7f04 100644
--- a/drivers/md/dm-zone.c
+++ b/drivers/md/dm-zone.c
@@ -287,7 +287,13 @@ int dm_set_zones_restrictions(struct dm_table *t, struct request_queue *q)
 		       queue_emulates_zone_append(q) ? "emulated" : "native");
 	}
 
-	return dm_revalidate_zones(md, t);
+	ret = dm_revalidate_zones(md, t);
+	if (ret < 0)
+		return ret;
+
+	if (!static_key_enabled(&zoned_enabled.key))
+		static_branch_enable(&zoned_enabled);
+	return 0;
 }
 
 /*
-- 
GitLab


From 5e7a4bbcc33d7df6bcc8565a8938c196285e5423 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 27 May 2024 14:36:19 +0200
Subject: [PATCH 291/950] dm: remove dm_check_zoned

Fold it into the only caller in preparation to changes in the
queue limits setup.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Mike Snitzer <snitzer@kernel.org>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Link: https://lore.kernel.org/r/20240527123634.1116952-3-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/md/dm-zone.c | 59 +++++++++++++++++---------------------------
 1 file changed, 23 insertions(+), 36 deletions(-)

diff --git a/drivers/md/dm-zone.c b/drivers/md/dm-zone.c
index 3103360ce7f04..0ee22494857d0 100644
--- a/drivers/md/dm-zone.c
+++ b/drivers/md/dm-zone.c
@@ -160,37 +160,6 @@ static int dm_check_zoned_cb(struct blk_zone *zone, unsigned int idx,
 	return 0;
 }
 
-static int dm_check_zoned(struct mapped_device *md, struct dm_table *t)
-{
-	struct gendisk *disk = md->disk;
-	unsigned int nr_conv_zones = 0;
-	int ret;
-
-	/* Count conventional zones */
-	md->zone_revalidate_map = t;
-	ret = dm_blk_report_zones(disk, 0, UINT_MAX,
-				  dm_check_zoned_cb, &nr_conv_zones);
-	md->zone_revalidate_map = NULL;
-	if (ret < 0) {
-		DMERR("Check zoned failed %d", ret);
-		return ret;
-	}
-
-	/*
-	 * If we only have conventional zones, expose the mapped device as
-	 * a regular device.
-	 */
-	if (nr_conv_zones >= ret) {
-		disk->queue->limits.max_open_zones = 0;
-		disk->queue->limits.max_active_zones = 0;
-		disk->queue->limits.zoned = false;
-		clear_bit(DMF_EMULATE_ZONE_APPEND, &md->flags);
-		disk->nr_zones = 0;
-	}
-
-	return 0;
-}
-
 /*
  * Revalidate the zones of a mapped device to initialize resource necessary
  * for zone append emulation. Note that we cannot simply use the block layer
@@ -254,6 +223,8 @@ static bool dm_table_supports_zone_append(struct dm_table *t)
 int dm_set_zones_restrictions(struct dm_table *t, struct request_queue *q)
 {
 	struct mapped_device *md = t->md;
+	struct gendisk *disk = md->disk;
+	unsigned int nr_conv_zones = 0;
 	int ret;
 
 	/*
@@ -272,14 +243,30 @@ int dm_set_zones_restrictions(struct dm_table *t, struct request_queue *q)
 		return 0;
 
 	/*
-	 * Check that the mapped device will indeed be zoned, that is, that it
-	 * has sequential write required zones.
+	 * Count conventional zones to check that the mapped device will indeed 
+	 * have sequential write required zones.
 	 */
-	ret = dm_check_zoned(md, t);
-	if (ret)
+	md->zone_revalidate_map = t;
+	ret = dm_blk_report_zones(disk, 0, UINT_MAX,
+				  dm_check_zoned_cb, &nr_conv_zones);
+	md->zone_revalidate_map = NULL;
+	if (ret < 0) {
+		DMERR("Check zoned failed %d", ret);
 		return ret;
-	if (!blk_queue_is_zoned(q))
+	}
+
+	/*
+	 * If we only have conventional zones, expose the mapped device as
+	 * a regular device.
+	 */
+	if (nr_conv_zones >= ret) {
+		disk->queue->limits.max_open_zones = 0;
+		disk->queue->limits.max_active_zones = 0;
+		disk->queue->limits.zoned = false;
+		clear_bit(DMF_EMULATE_ZONE_APPEND, &md->flags);
+		disk->nr_zones = 0;
 		return 0;
+	}
 
 	if (!md->disk->nr_zones) {
 		DMINFO("%s using %s zone append",
-- 
GitLab


From c8c1f7012b807ca4da0136eacab96961b56f25d5 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 27 May 2024 14:36:20 +0200
Subject: [PATCH 292/950] dm: make dm_set_zones_restrictions work on the queue
 limits

Don't stuff the values directly into the queue without any
synchronization, but instead delay applying the queue limits in
the caller and let dm_set_zones_restrictions work on the limit
structure.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Link: https://lore.kernel.org/r/20240527123634.1116952-4-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/md/dm-table.c | 12 ++++++------
 drivers/md/dm-zone.c  | 11 ++++++-----
 drivers/md/dm.h       |  3 ++-
 3 files changed, 14 insertions(+), 12 deletions(-)

diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index e291b78b307b1..b2d5246cff210 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -1981,10 +1981,6 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 	if (!dm_table_supports_secure_erase(t))
 		limits->max_secure_erase_sectors = 0;
 
-	r = queue_limits_set(q, limits);
-	if (r)
-		return r;
-
 	if (dm_table_supports_flush(t, (1UL << QUEUE_FLAG_WC))) {
 		wc = true;
 		if (dm_table_supports_flush(t, (1UL << QUEUE_FLAG_FUA)))
@@ -2036,12 +2032,16 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 	 * For a zoned target, setup the zones related queue attributes
 	 * and resources necessary for zone append emulation if necessary.
 	 */
-	if (blk_queue_is_zoned(q)) {
-		r = dm_set_zones_restrictions(t, q);
+	if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) && limits->zoned) {
+		r = dm_set_zones_restrictions(t, q, limits);
 		if (r)
 			return r;
 	}
 
+	r = queue_limits_set(q, limits);
+	if (r)
+		return r;
+
 	dm_update_crypto_profile(q, t);
 
 	/*
diff --git a/drivers/md/dm-zone.c b/drivers/md/dm-zone.c
index 0ee22494857d0..5d66d916730ef 100644
--- a/drivers/md/dm-zone.c
+++ b/drivers/md/dm-zone.c
@@ -220,7 +220,8 @@ static bool dm_table_supports_zone_append(struct dm_table *t)
 	return true;
 }
 
-int dm_set_zones_restrictions(struct dm_table *t, struct request_queue *q)
+int dm_set_zones_restrictions(struct dm_table *t, struct request_queue *q,
+		struct queue_limits *lim)
 {
 	struct mapped_device *md = t->md;
 	struct gendisk *disk = md->disk;
@@ -236,7 +237,7 @@ int dm_set_zones_restrictions(struct dm_table *t, struct request_queue *q)
 		clear_bit(DMF_EMULATE_ZONE_APPEND, &md->flags);
 	} else {
 		set_bit(DMF_EMULATE_ZONE_APPEND, &md->flags);
-		blk_queue_max_zone_append_sectors(q, 0);
+		lim->max_zone_append_sectors = 0;
 	}
 
 	if (!get_capacity(md->disk))
@@ -260,9 +261,9 @@ int dm_set_zones_restrictions(struct dm_table *t, struct request_queue *q)
 	 * a regular device.
 	 */
 	if (nr_conv_zones >= ret) {
-		disk->queue->limits.max_open_zones = 0;
-		disk->queue->limits.max_active_zones = 0;
-		disk->queue->limits.zoned = false;
+		lim->max_open_zones = 0;
+		lim->max_active_zones = 0;
+		lim->zoned = false;
 		clear_bit(DMF_EMULATE_ZONE_APPEND, &md->flags);
 		disk->nr_zones = 0;
 		return 0;
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index e0c57f19839b2..53ef8207fe2c1 100644
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -101,7 +101,8 @@ int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t);
 /*
  * Zoned targets related functions.
  */
-int dm_set_zones_restrictions(struct dm_table *t, struct request_queue *q);
+int dm_set_zones_restrictions(struct dm_table *t, struct request_queue *q,
+		struct queue_limits *lim);
 void dm_zone_endio(struct dm_io *io, struct bio *clone);
 #ifdef CONFIG_BLK_DEV_ZONED
 int dm_blk_report_zones(struct gendisk *disk, sector_t sector,
-- 
GitLab


From b0c6bcd58d44b1b843d1b7218db5a1efe917d27e Mon Sep 17 00:00:00 2001
From: "Ritesh Harjani (IBM)" <ritesh.list@gmail.com>
Date: Tue, 7 May 2024 15:06:55 +0530
Subject: [PATCH 293/950] xfs: Add cond_resched to block unmap range and
 reflink remap path

An async dio write to a sparse file can generate a lot of extents
and when we unlink this file (using rm), the kernel can be busy in umapping
and freeing those extents as part of transaction processing.

Similarly xfs reflink remapping path can also iterate over a million
extent entries in xfs_reflink_remap_blocks().

Since we can busy loop in these two functions, so let's add cond_resched()
to avoid softlockup messages like these.

watchdog: BUG: soft lockup - CPU#1 stuck for 22s! [kworker/1:0:82435]
CPU: 1 PID: 82435 Comm: kworker/1:0 Tainted: G S  L   6.9.0-rc5-0-default #1
Workqueue: xfs-inodegc/sda2 xfs_inodegc_worker
NIP [c000000000beea10] xfs_extent_busy_trim+0x100/0x290
LR [c000000000bee958] xfs_extent_busy_trim+0x48/0x290
Call Trace:
  xfs_alloc_get_rec+0x54/0x1b0 (unreliable)
  xfs_alloc_compute_aligned+0x5c/0x144
  xfs_alloc_ag_vextent_size+0x238/0x8d4
  xfs_alloc_fix_freelist+0x540/0x694
  xfs_free_extent_fix_freelist+0x84/0xe0
  __xfs_free_extent+0x74/0x1ec
  xfs_extent_free_finish_item+0xcc/0x214
  xfs_defer_finish_one+0x194/0x388
  xfs_defer_finish_noroll+0x1b4/0x5c8
  xfs_defer_finish+0x2c/0xc4
  xfs_bunmapi_range+0xa4/0x100
  xfs_itruncate_extents_flags+0x1b8/0x2f4
  xfs_inactive_truncate+0xe0/0x124
  xfs_inactive+0x30c/0x3e0
  xfs_inodegc_worker+0x140/0x234
  process_scheduled_works+0x240/0x57c
  worker_thread+0x198/0x468
  kthread+0x138/0x140
  start_kernel_thread+0x14/0x18

run fstests generic/175 at 2024-02-02 04:40:21
[   C17] watchdog: BUG: soft lockup - CPU#17 stuck for 23s! [xfs_io:7679]
 watchdog: BUG: soft lockup - CPU#17 stuck for 23s! [xfs_io:7679]
 CPU: 17 PID: 7679 Comm: xfs_io Kdump: loaded Tainted: G X 6.4.0
 NIP [c008000005e3ec94] xfs_rmapbt_diff_two_keys+0x54/0xe0 [xfs]
 LR [c008000005e08798] xfs_btree_get_leaf_keys+0x110/0x1e0 [xfs]
 Call Trace:
  0xc000000014107c00 (unreliable)
  __xfs_btree_updkeys+0x8c/0x2c0 [xfs]
  xfs_btree_update_keys+0x150/0x170 [xfs]
  xfs_btree_lshift+0x534/0x660 [xfs]
  xfs_btree_make_block_unfull+0x19c/0x240 [xfs]
  xfs_btree_insrec+0x4e4/0x630 [xfs]
  xfs_btree_insert+0x104/0x2d0 [xfs]
  xfs_rmap_insert+0xc4/0x260 [xfs]
  xfs_rmap_map_shared+0x228/0x630 [xfs]
  xfs_rmap_finish_one+0x2d4/0x350 [xfs]
  xfs_rmap_update_finish_item+0x44/0xc0 [xfs]
  xfs_defer_finish_noroll+0x2e4/0x740 [xfs]
  __xfs_trans_commit+0x1f4/0x400 [xfs]
  xfs_reflink_remap_extent+0x2d8/0x650 [xfs]
  xfs_reflink_remap_blocks+0x154/0x320 [xfs]
  xfs_file_remap_range+0x138/0x3a0 [xfs]
  do_clone_file_range+0x11c/0x2f0
  vfs_clone_file_range+0x60/0x1c0
  ioctl_file_clone+0x78/0x140
  sys_ioctl+0x934/0x1270
  system_call_exception+0x158/0x320
  system_call_vectored_common+0x15c/0x2ec

Cc: Ojaswin Mujoo <ojaswin@linux.ibm.com>
Signed-off-by: Ritesh Harjani (IBM) <ritesh.list@gmail.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Tested-by: Disha Goel<disgoel@linux.ibm.com>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
---
 fs/xfs/libxfs/xfs_bmap.c | 1 +
 fs/xfs/xfs_reflink.c     | 1 +
 2 files changed, 2 insertions(+)

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 3b3206d312d6f..c101cf266bc4d 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -6383,6 +6383,7 @@ xfs_bunmapi_range(
 		error = xfs_defer_finish(tpp);
 		if (error)
 			goto out;
+		cond_resched();
 	}
 out:
 	return error;
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 063a2e00d1691..265a2a418bc7b 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -1387,6 +1387,7 @@ xfs_reflink_remap_blocks(
 		destoff += imap.br_blockcount;
 		len -= imap.br_blockcount;
 		remapped_len += imap.br_blockcount;
+		cond_resched();
 	}
 
 	if (error)
-- 
GitLab


From 947051e361d551e0590777080ffc4926190f62f2 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Fri, 24 May 2024 15:19:54 +0100
Subject: [PATCH 294/950] KVM: arm64: Fix AArch32 register narrowing on
 userspace write

When userspace writes to one of the core registers, we make
sure to narrow the corresponding GPRs if PSTATE indicates
an AArch32 context.

The code tries to check whether the context is EL0 or EL1 so
that it narrows the correct registers. But it does so by checking
the full PSTATE instead of PSTATE.M.

As a consequence, and if we are restoring an AArch32 EL0 context
in a 64bit guest, and that PSTATE has *any* bit set outside of
PSTATE.M, we narrow *all* registers instead of only the first 15,
destroying the 64bit state.

Obviously, this is not something the guest is likely to enjoy.

Correctly masking PSTATE to only evaluate PSTATE.M fixes it.

Fixes: 90c1f934ed71 ("KVM: arm64: Get rid of the AArch32 register mapping code")
Reported-by: Nina Schoetterl-Glausch <nsg@linux.ibm.com>
Cc: stable@vger.kernel.org
Reviewed-by: Nina Schoetterl-Glausch <nsg@linux.ibm.com>
Acked-by: Oliver Upton <oliver.upton@linux.dev>
Link: https://lore.kernel.org/r/20240524141956.1450304-2-maz@kernel.org
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/guest.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index e2f762d959bb3..d9617b11f7a87 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -276,7 +276,7 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	if (*vcpu_cpsr(vcpu) & PSR_MODE32_BIT) {
 		int i, nr_reg;
 
-		switch (*vcpu_cpsr(vcpu)) {
+		switch (*vcpu_cpsr(vcpu) & PSR_AA32_MODE_MASK) {
 		/*
 		 * Either we are dealing with user mode, and only the
 		 * first 15 registers (+ PC) must be narrowed to 32bit.
-- 
GitLab


From dfe6d190f38fc5df5ff2614b463a5195a399c885 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Fri, 24 May 2024 15:19:55 +0100
Subject: [PATCH 295/950] KVM: arm64: Allow AArch32 PSTATE.M to be restored as
 System mode

It appears that we don't allow a vcpu to be restored in AArch32
System mode, as we *never* included it in the list of valid modes.

Just add it to the list of allowed modes.

Fixes: 0d854a60b1d7 ("arm64: KVM: enable initialization of a 32bit vcpu")
Cc: stable@vger.kernel.org
Acked-by: Oliver Upton <oliver.upton@linux.dev>
Link: https://lore.kernel.org/r/20240524141956.1450304-3-maz@kernel.org
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/guest.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index d9617b11f7a87..11098eb7eb44a 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -251,6 +251,7 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 		case PSR_AA32_MODE_SVC:
 		case PSR_AA32_MODE_ABT:
 		case PSR_AA32_MODE_UND:
+		case PSR_AA32_MODE_SYS:
 			if (!vcpu_el1_is_32bit(vcpu))
 				return -EINVAL;
 			break;
-- 
GitLab


From c92e8b9eacebb4060634ebd9395bba1b29aadc68 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Fri, 24 May 2024 15:19:56 +0100
Subject: [PATCH 296/950] KVM: arm64: AArch32: Fix spurious trapping of
 conditional instructions

We recently upgraded the view of ESR_EL2 to 64bit, in keeping with
the requirements of the architecture.

However, the AArch32 emulation code was left unaudited, and the
(already dodgy) code that triages whether a trap is spurious or not
(because the condition code failed) broke in a subtle way:

If ESR_EL2.ISS2 is ever non-zero (unlikely, but hey, this is the ARM
architecture we're talking about), the hack that tests the top bits
of ESR_EL2.EC will break in an interesting way.

Instead, use kvm_vcpu_trap_get_class() to obtain the EC, and list
all the possible ECs that can fail a condition code check.

While we're at it, add SMC32 to the list, as it is explicitly listed
as being allowed to trap despite failing a condition code check (as
described in the HCR_EL2.TSC documentation).

Fixes: 0b12620fddb8 ("KVM: arm64: Treat ESR_EL2 as a 64-bit register")
Cc: stable@vger.kernel.org
Acked-by: Oliver Upton <oliver.upton@linux.dev>
Link: https://lore.kernel.org/r/20240524141956.1450304-4-maz@kernel.org
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/hyp/aarch32.c | 18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/kvm/hyp/aarch32.c b/arch/arm64/kvm/hyp/aarch32.c
index 8d9670e6615dc..449fa58cf3b63 100644
--- a/arch/arm64/kvm/hyp/aarch32.c
+++ b/arch/arm64/kvm/hyp/aarch32.c
@@ -50,9 +50,23 @@ bool kvm_condition_valid32(const struct kvm_vcpu *vcpu)
 	u32 cpsr_cond;
 	int cond;
 
-	/* Top two bits non-zero?  Unconditional. */
-	if (kvm_vcpu_get_esr(vcpu) >> 30)
+	/*
+	 * These are the exception classes that could fire with a
+	 * conditional instruction.
+	 */
+	switch (kvm_vcpu_trap_get_class(vcpu)) {
+	case ESR_ELx_EC_CP15_32:
+	case ESR_ELx_EC_CP15_64:
+	case ESR_ELx_EC_CP14_MR:
+	case ESR_ELx_EC_CP14_LS:
+	case ESR_ELx_EC_FP_ASIMD:
+	case ESR_ELx_EC_CP10_ID:
+	case ESR_ELx_EC_CP14_64:
+	case ESR_ELx_EC_SVC32:
+		break;
+	default:
 		return true;
+	}
 
 	/* Is condition field valid? */
 	cond = kvm_vcpu_get_condition(vcpu);
-- 
GitLab


From 98e948fb60d41447fd8d2d0c3b8637fc6b6dc26d Mon Sep 17 00:00:00 2001
From: Jakub Sitnicki <jakub@cloudflare.com>
Date: Mon, 27 May 2024 13:20:07 +0200
Subject: [PATCH 297/950] bpf: Allow delete from sockmap/sockhash only if
 update is allowed

We have seen an influx of syzkaller reports where a BPF program attached to
a tracepoint triggers a locking rule violation by performing a map_delete
on a sockmap/sockhash.

We don't intend to support this artificial use scenario. Extend the
existing verifier allowed-program-type check for updating sockmap/sockhash
to also cover deleting from a map.

From now on only BPF programs which were previously allowed to update
sockmap/sockhash can delete from these map types.

Fixes: ff9105993240 ("bpf, sockmap: Prevent lock inversion deadlock in map delete elem")
Reported-by: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp>
Reported-by: syzbot+ec941d6e24f633a59172@syzkaller.appspotmail.com
Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: syzbot+ec941d6e24f633a59172@syzkaller.appspotmail.com
Acked-by: John Fastabend <john.fastabend@gmail.com>
Closes: https://syzkaller.appspot.com/bug?extid=ec941d6e24f633a59172
Link: https://lore.kernel.org/bpf/20240527-sockmap-verify-deletes-v1-1-944b372f2101@cloudflare.com
---
 kernel/bpf/verifier.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 77da1f438becc..48f3a9acdef3d 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -8882,7 +8882,8 @@ static bool may_update_sockmap(struct bpf_verifier_env *env, int func_id)
 	enum bpf_attach_type eatype = env->prog->expected_attach_type;
 	enum bpf_prog_type type = resolve_prog_type(env->prog);
 
-	if (func_id != BPF_FUNC_map_update_elem)
+	if (func_id != BPF_FUNC_map_update_elem &&
+	    func_id != BPF_FUNC_map_delete_elem)
 		return false;
 
 	/* It's not possible to get access to a locked struct sock in these
@@ -8893,6 +8894,11 @@ static bool may_update_sockmap(struct bpf_verifier_env *env, int func_id)
 		if (eatype == BPF_TRACE_ITER)
 			return true;
 		break;
+	case BPF_PROG_TYPE_SOCK_OPS:
+		/* map_update allowed only via dedicated helpers with event type checks */
+		if (func_id == BPF_FUNC_map_delete_elem)
+			return true;
+		break;
 	case BPF_PROG_TYPE_SOCKET_FILTER:
 	case BPF_PROG_TYPE_SCHED_CLS:
 	case BPF_PROG_TYPE_SCHED_ACT:
@@ -8988,7 +8994,6 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 	case BPF_MAP_TYPE_SOCKMAP:
 		if (func_id != BPF_FUNC_sk_redirect_map &&
 		    func_id != BPF_FUNC_sock_map_update &&
-		    func_id != BPF_FUNC_map_delete_elem &&
 		    func_id != BPF_FUNC_msg_redirect_map &&
 		    func_id != BPF_FUNC_sk_select_reuseport &&
 		    func_id != BPF_FUNC_map_lookup_elem &&
@@ -8998,7 +9003,6 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 	case BPF_MAP_TYPE_SOCKHASH:
 		if (func_id != BPF_FUNC_sk_redirect_hash &&
 		    func_id != BPF_FUNC_sock_hash_update &&
-		    func_id != BPF_FUNC_map_delete_elem &&
 		    func_id != BPF_FUNC_msg_redirect_hash &&
 		    func_id != BPF_FUNC_sk_select_reuseport &&
 		    func_id != BPF_FUNC_map_lookup_elem &&
-- 
GitLab


From 3b9ce0491a43e9af7f108b2f1bced7cd35931660 Mon Sep 17 00:00:00 2001
From: Jakub Sitnicki <jakub@cloudflare.com>
Date: Mon, 27 May 2024 13:20:08 +0200
Subject: [PATCH 298/950] Revert "bpf, sockmap: Prevent lock inversion deadlock
 in map delete elem"

This reverts commit ff91059932401894e6c86341915615c5eb0eca48.

This check is no longer needed. BPF programs attached to tracepoints are
now rejected by the verifier when they attempt to delete from a
sockmap/sockhash maps.

Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20240527-sockmap-verify-deletes-v1-2-944b372f2101@cloudflare.com
---
 net/core/sock_map.c | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 9402889840bf7..63c016b4c1696 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -423,9 +423,6 @@ static int __sock_map_delete(struct bpf_stab *stab, struct sock *sk_test,
 	struct sock *sk;
 	int err = 0;
 
-	if (irqs_disabled())
-		return -EOPNOTSUPP; /* locks here are hardirq-unsafe */
-
 	spin_lock_bh(&stab->lock);
 	sk = *psk;
 	if (!sk_test || sk_test == sk)
@@ -948,9 +945,6 @@ static long sock_hash_delete_elem(struct bpf_map *map, void *key)
 	struct bpf_shtab_elem *elem;
 	int ret = -ENOENT;
 
-	if (irqs_disabled())
-		return -EOPNOTSUPP; /* locks here are hardirq-unsafe */
-
 	hash = sock_hash_bucket_hash(key, key_size);
 	bucket = sock_hash_select_bucket(htab, hash);
 
-- 
GitLab


From a63bf556160fb19591183383da6757f52119981d Mon Sep 17 00:00:00 2001
From: Jakub Sitnicki <jakub@cloudflare.com>
Date: Mon, 27 May 2024 13:20:09 +0200
Subject: [PATCH 299/950] selftests/bpf: Cover verifier checks for mutating
 sockmap/sockhash

Verifier enforces that only certain program types can mutate sock{map,hash}
maps, that is update it or delete from it. Add test coverage for these
checks so we don't regress.

Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20240527-sockmap-verify-deletes-v1-3-944b372f2101@cloudflare.com
---
 .../selftests/bpf/prog_tests/verifier.c       |   2 +
 .../bpf/progs/verifier_sockmap_mutate.c       | 187 ++++++++++++++++++
 2 files changed, 189 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/progs/verifier_sockmap_mutate.c

diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c
index c60db8beeb734..1c9c4ec1be11e 100644
--- a/tools/testing/selftests/bpf/prog_tests/verifier.c
+++ b/tools/testing/selftests/bpf/prog_tests/verifier.c
@@ -67,6 +67,7 @@
 #include "verifier_search_pruning.skel.h"
 #include "verifier_sock.skel.h"
 #include "verifier_sock_addr.skel.h"
+#include "verifier_sockmap_mutate.skel.h"
 #include "verifier_spill_fill.skel.h"
 #include "verifier_spin_lock.skel.h"
 #include "verifier_stack_ptr.skel.h"
@@ -183,6 +184,7 @@ void test_verifier_sdiv(void)                 { RUN(verifier_sdiv); }
 void test_verifier_search_pruning(void)       { RUN(verifier_search_pruning); }
 void test_verifier_sock(void)                 { RUN(verifier_sock); }
 void test_verifier_sock_addr(void)            { RUN(verifier_sock_addr); }
+void test_verifier_sockmap_mutate(void)       { RUN(verifier_sockmap_mutate); }
 void test_verifier_spill_fill(void)           { RUN(verifier_spill_fill); }
 void test_verifier_spin_lock(void)            { RUN(verifier_spin_lock); }
 void test_verifier_stack_ptr(void)            { RUN(verifier_stack_ptr); }
diff --git a/tools/testing/selftests/bpf/progs/verifier_sockmap_mutate.c b/tools/testing/selftests/bpf/progs/verifier_sockmap_mutate.c
new file mode 100644
index 0000000000000..fe4b123187b86
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_sockmap_mutate.c
@@ -0,0 +1,187 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+#include "bpf_misc.h"
+
+#define __always_unused __attribute__((unused))
+
+char _license[] SEC("license") = "GPL";
+
+struct sock {
+} __attribute__((preserve_access_index));
+
+struct bpf_iter__sockmap {
+	union {
+		struct sock *sk;
+	};
+} __attribute__((preserve_access_index));
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SOCKHASH);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, int);
+} sockhash SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SOCKMAP);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, int);
+} sockmap SEC(".maps");
+
+enum { CG_OK = 1 };
+
+int zero = 0;
+
+static __always_inline void test_sockmap_delete(void)
+{
+	bpf_map_delete_elem(&sockmap, &zero);
+	bpf_map_delete_elem(&sockhash, &zero);
+}
+
+static __always_inline void test_sockmap_update(void *sk)
+{
+	if (sk) {
+		bpf_map_update_elem(&sockmap, &zero, sk, BPF_ANY);
+		bpf_map_update_elem(&sockhash, &zero, sk, BPF_ANY);
+	}
+}
+
+static __always_inline void test_sockmap_lookup_and_update(void)
+{
+	struct bpf_sock *sk = bpf_map_lookup_elem(&sockmap, &zero);
+
+	if (sk) {
+		test_sockmap_update(sk);
+		bpf_sk_release(sk);
+	}
+}
+
+static __always_inline void test_sockmap_mutate(void *sk)
+{
+	test_sockmap_delete();
+	test_sockmap_update(sk);
+}
+
+static __always_inline void test_sockmap_lookup_and_mutate(void)
+{
+	test_sockmap_delete();
+	test_sockmap_lookup_and_update();
+}
+
+SEC("action")
+__success
+int test_sched_act(struct __sk_buff *skb)
+{
+	test_sockmap_mutate(skb->sk);
+	return 0;
+}
+
+SEC("classifier")
+__success
+int test_sched_cls(struct __sk_buff *skb)
+{
+	test_sockmap_mutate(skb->sk);
+	return 0;
+}
+
+SEC("flow_dissector")
+__success
+int test_flow_dissector_delete(struct __sk_buff *skb __always_unused)
+{
+	test_sockmap_delete();
+	return 0;
+}
+
+SEC("flow_dissector")
+__failure __msg("program of this type cannot use helper bpf_sk_release")
+int test_flow_dissector_update(struct __sk_buff *skb __always_unused)
+{
+	test_sockmap_lookup_and_update(); /* no access to skb->sk */
+	return 0;
+}
+
+SEC("iter/sockmap")
+__success
+int test_trace_iter(struct bpf_iter__sockmap *ctx)
+{
+	test_sockmap_mutate(ctx->sk);
+	return 0;
+}
+
+SEC("raw_tp/kfree")
+__failure __msg("cannot update sockmap in this context")
+int test_raw_tp_delete(const void *ctx __always_unused)
+{
+	test_sockmap_delete();
+	return 0;
+}
+
+SEC("raw_tp/kfree")
+__failure __msg("cannot update sockmap in this context")
+int test_raw_tp_update(const void *ctx __always_unused)
+{
+	test_sockmap_lookup_and_update();
+	return 0;
+}
+
+SEC("sk_lookup")
+__success
+int test_sk_lookup(struct bpf_sk_lookup *ctx)
+{
+	test_sockmap_mutate(ctx->sk);
+	return 0;
+}
+
+SEC("sk_reuseport")
+__success
+int test_sk_reuseport(struct sk_reuseport_md *ctx)
+{
+	test_sockmap_mutate(ctx->sk);
+	return 0;
+}
+
+SEC("socket")
+__success
+int test_socket_filter(struct __sk_buff *skb)
+{
+	test_sockmap_mutate(skb->sk);
+	return 0;
+}
+
+SEC("sockops")
+__success
+int test_sockops_delete(struct bpf_sock_ops *ctx __always_unused)
+{
+	test_sockmap_delete();
+	return CG_OK;
+}
+
+SEC("sockops")
+__failure __msg("cannot update sockmap in this context")
+int test_sockops_update(struct bpf_sock_ops *ctx)
+{
+	test_sockmap_update(ctx->sk);
+	return CG_OK;
+}
+
+SEC("sockops")
+__success
+int test_sockops_update_dedicated(struct bpf_sock_ops *ctx)
+{
+	bpf_sock_map_update(ctx, &sockmap, &zero, BPF_ANY);
+	bpf_sock_hash_update(ctx, &sockhash, &zero, BPF_ANY);
+	return CG_OK;
+}
+
+SEC("xdp")
+__success
+int test_xdp(struct xdp_md *ctx __always_unused)
+{
+	test_sockmap_lookup_and_mutate();
+	return XDP_PASS;
+}
-- 
GitLab


From d9ff882b54f99f96787fa3df7cd938966843c418 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Mon, 27 May 2024 13:34:45 +0900
Subject: [PATCH 300/950] null_blk: Fix return value of
 nullb_device_power_store()

When powering on a null_blk device that is not already on, the return
value ret that is initialized to be count is reused to check the return
value of null_add_dev(), leading to nullb_device_power_store() to return
null_add_dev() return value (0 on success) instead of "count".
So make sure to set ret to be equal to count when there are no errors.

Fixes: a2db328b0839 ("null_blk: fix null-ptr-dereference while configuring 'power' and 'submit_queues'")
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Yu Kuai <yukuai3@huawei.com>
Reviewed-by: Kanchan Joshi <joshi.k@samsung.com>
Link: https://lore.kernel.org/r/20240527043445.235267-1-dlemoal@kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/null_blk/main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c
index eb023d2673693..631dca2e4e844 100644
--- a/drivers/block/null_blk/main.c
+++ b/drivers/block/null_blk/main.c
@@ -494,6 +494,7 @@ static ssize_t nullb_device_power_store(struct config_item *item,
 
 		set_bit(NULLB_DEV_FL_CONFIGURED, &dev->flags);
 		dev->power = newp;
+		ret = count;
 	} else if (dev->power && !newp) {
 		if (test_and_clear_bit(NULLB_DEV_FL_UP, &dev->flags)) {
 			dev->power = newp;
-- 
GitLab


From 30a0e3135f9aa14ba745f767375183b3112d7440 Mon Sep 17 00:00:00 2001
From: hexue <xue01.he@samsung.com>
Date: Mon, 27 May 2024 16:45:33 +0800
Subject: [PATCH 301/950] block: delete redundant function declaration

blk_stats_alloc_enable was used for block hybrid poll, the related
function definition was removed by patch:
commit 54bdd67d0f88 ("blk-mq: remove hybrid polling")
but the function declaration was not deleted.

Signed-off-by: hexue <xue01.he@samsung.com>
Link: https://lore.kernel.org/r/20240527084533.1485210-1-xue01.he@samsung.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-stat.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/block/blk-stat.h b/block/blk-stat.h
index 17e1eb4ec7e25..5d7f18ba436d0 100644
--- a/block/blk-stat.h
+++ b/block/blk-stat.h
@@ -64,7 +64,6 @@ struct blk_stat_callback {
 
 struct blk_queue_stats *blk_alloc_queue_stats(void);
 void blk_free_queue_stats(struct blk_queue_stats *);
-bool blk_stats_alloc_enable(struct request_queue *q);
 
 void blk_stat_add(struct request *rq, u64 now);
 
-- 
GitLab


From e30a942861b540e056425a8e31ba801de1ed4f25 Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Mon, 27 May 2024 14:44:11 -0500
Subject: [PATCH 302/950] ASoC: SOF: stream-ipc: remove unnecessary
 MODULE_LICENSE
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This file is part of the snd-sof module, there's no reason to re-add the
MODULE_LICENSE here.

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Reviewed-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Reviewed-by: Daniel Baluta <daniel.baluta@nxp.com>
Reviewed-by: Péter Ujfalusi <peter.ujfalusi@linux.intel.com>
Link: https://msgid.link/r/20240527194414.166156-2-pierre-louis.bossart@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sof/stream-ipc.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/sound/soc/sof/stream-ipc.c b/sound/soc/sof/stream-ipc.c
index eb71303aa24c6..794c7bbccbaf9 100644
--- a/sound/soc/sof/stream-ipc.c
+++ b/sound/soc/sof/stream-ipc.c
@@ -125,5 +125,3 @@ int sof_stream_pcm_close(struct snd_sof_dev *sdev,
 	return 0;
 }
 EXPORT_SYMBOL(sof_stream_pcm_close);
-
-MODULE_LICENSE("Dual BSD/GPL");
-- 
GitLab


From b88056df4fcb7b5930d6ee3fef494e8729dcf2b2 Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Mon, 27 May 2024 14:44:12 -0500
Subject: [PATCH 303/950] ASoC: SOF: AMD: group all module related information
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The module information is spread across files, group in a single
location.  For maintenability and alignment, the arbitrary Intel
convention is used with the following order:

MODULE_LICENSE
MODULE_DESCRIPTION
MODULE_IMPORT

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Reviewed-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Reviewed-by: Daniel Baluta <daniel.baluta@nxp.com>
Reviewed-by: Péter Ujfalusi <peter.ujfalusi@linux.intel.com>
Link: https://msgid.link/r/20240527194414.166156-3-pierre-louis.bossart@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sof/amd/acp63.c       | 4 ----
 sound/soc/sof/amd/pci-acp63.c   | 1 +
 sound/soc/sof/amd/pci-rmb.c     | 1 +
 sound/soc/sof/amd/pci-rn.c      | 1 +
 sound/soc/sof/amd/pci-vangogh.c | 1 +
 sound/soc/sof/amd/rembrandt.c   | 4 ----
 sound/soc/sof/amd/renoir.c      | 4 ----
 sound/soc/sof/amd/vangogh.c     | 4 ----
 8 files changed, 4 insertions(+), 16 deletions(-)

diff --git a/sound/soc/sof/amd/acp63.c b/sound/soc/sof/amd/acp63.c
index 9fb645079c3ad..9e6eb4bfc805b 100644
--- a/sound/soc/sof/amd/acp63.c
+++ b/sound/soc/sof/amd/acp63.c
@@ -140,7 +140,3 @@ int sof_acp63_ops_init(struct snd_sof_dev *sdev)
 
 	return 0;
 }
-
-MODULE_IMPORT_NS(SND_SOC_SOF_AMD_COMMON);
-MODULE_DESCRIPTION("ACP63 SOF Driver");
-MODULE_LICENSE("Dual BSD/GPL");
diff --git a/sound/soc/sof/amd/pci-acp63.c b/sound/soc/sof/amd/pci-acp63.c
index eeaa12cceb233..fc89844473657 100644
--- a/sound/soc/sof/amd/pci-acp63.c
+++ b/sound/soc/sof/amd/pci-acp63.c
@@ -109,5 +109,6 @@ static struct pci_driver snd_sof_pci_amd_acp63_driver = {
 module_pci_driver(snd_sof_pci_amd_acp63_driver);
 
 MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("ACP63 SOF Driver");
 MODULE_IMPORT_NS(SND_SOC_SOF_AMD_COMMON);
 MODULE_IMPORT_NS(SND_SOC_SOF_PCI_DEV);
diff --git a/sound/soc/sof/amd/pci-rmb.c b/sound/soc/sof/amd/pci-rmb.c
index 2f288545c4260..4bc30951f8b0d 100644
--- a/sound/soc/sof/amd/pci-rmb.c
+++ b/sound/soc/sof/amd/pci-rmb.c
@@ -99,5 +99,6 @@ static struct pci_driver snd_sof_pci_amd_rmb_driver = {
 module_pci_driver(snd_sof_pci_amd_rmb_driver);
 
 MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("REMBRANDT SOF Driver");
 MODULE_IMPORT_NS(SND_SOC_SOF_AMD_COMMON);
 MODULE_IMPORT_NS(SND_SOC_SOF_PCI_DEV);
diff --git a/sound/soc/sof/amd/pci-rn.c b/sound/soc/sof/amd/pci-rn.c
index a0195e9b400c8..e08875bdfa8b1 100644
--- a/sound/soc/sof/amd/pci-rn.c
+++ b/sound/soc/sof/amd/pci-rn.c
@@ -103,5 +103,6 @@ static struct pci_driver snd_sof_pci_amd_rn_driver = {
 module_pci_driver(snd_sof_pci_amd_rn_driver);
 
 MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("RENOIR SOF Driver");
 MODULE_IMPORT_NS(SND_SOC_SOF_AMD_COMMON);
 MODULE_IMPORT_NS(SND_SOC_SOF_PCI_DEV);
diff --git a/sound/soc/sof/amd/pci-vangogh.c b/sound/soc/sof/amd/pci-vangogh.c
index 5cd3ac84752fb..16eb2994fbab9 100644
--- a/sound/soc/sof/amd/pci-vangogh.c
+++ b/sound/soc/sof/amd/pci-vangogh.c
@@ -101,5 +101,6 @@ static struct pci_driver snd_sof_pci_amd_vgh_driver = {
 module_pci_driver(snd_sof_pci_amd_vgh_driver);
 
 MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("VANGOGH SOF Driver");
 MODULE_IMPORT_NS(SND_SOC_SOF_AMD_COMMON);
 MODULE_IMPORT_NS(SND_SOC_SOF_PCI_DEV);
diff --git a/sound/soc/sof/amd/rembrandt.c b/sound/soc/sof/amd/rembrandt.c
index f1d1ba57ab3a0..076f2f05a95c2 100644
--- a/sound/soc/sof/amd/rembrandt.c
+++ b/sound/soc/sof/amd/rembrandt.c
@@ -140,7 +140,3 @@ int sof_rembrandt_ops_init(struct snd_sof_dev *sdev)
 
 	return 0;
 }
-
-MODULE_IMPORT_NS(SND_SOC_SOF_AMD_COMMON);
-MODULE_DESCRIPTION("REMBRANDT SOF Driver");
-MODULE_LICENSE("Dual BSD/GPL");
diff --git a/sound/soc/sof/amd/renoir.c b/sound/soc/sof/amd/renoir.c
index 47b863f6258c6..aa2d24dac6f5d 100644
--- a/sound/soc/sof/amd/renoir.c
+++ b/sound/soc/sof/amd/renoir.c
@@ -115,7 +115,3 @@ int sof_renoir_ops_init(struct snd_sof_dev *sdev)
 
 	return 0;
 }
-
-MODULE_IMPORT_NS(SND_SOC_SOF_AMD_COMMON);
-MODULE_DESCRIPTION("RENOIR SOF Driver");
-MODULE_LICENSE("Dual BSD/GPL");
diff --git a/sound/soc/sof/amd/vangogh.c b/sound/soc/sof/amd/vangogh.c
index bc6ffdb5471a5..61372958c09dc 100644
--- a/sound/soc/sof/amd/vangogh.c
+++ b/sound/soc/sof/amd/vangogh.c
@@ -161,7 +161,3 @@ int sof_vangogh_ops_init(struct snd_sof_dev *sdev)
 
 	return 0;
 }
-
-MODULE_IMPORT_NS(SND_SOC_SOF_AMD_COMMON);
-MODULE_DESCRIPTION("VANGOGH SOF Driver");
-MODULE_LICENSE("Dual BSD/GPL");
-- 
GitLab


From 06a2315da0b02db4f2115bc9253daa270571e389 Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Mon, 27 May 2024 14:44:13 -0500
Subject: [PATCH 304/950] ASoC: SOF: reorder MODULE_ definitions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Follow the arbitrary Intel convention order to allow for easier grep.

MODULE_LICENSE
MODULE_DESCRIPTION
MODULE_IMPORT

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Reviewed-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Reviewed-by: Daniel Baluta <daniel.baluta@nxp.com>
Reviewed-by: Péter Ujfalusi <peter.ujfalusi@linux.intel.com>
Link: https://msgid.link/r/20240527194414.166156-4-pierre-louis.bossart@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sof/amd/acp-common.c                 | 4 ++--
 sound/soc/sof/amd/acp.c                        | 2 +-
 sound/soc/sof/core.c                           | 2 +-
 sound/soc/sof/nocodec.c                        | 2 +-
 sound/soc/sof/sof-client-ipc-flood-test.c      | 2 +-
 sound/soc/sof/sof-client-ipc-kernel-injector.c | 2 +-
 sound/soc/sof/sof-client-ipc-msg-injector.c    | 2 +-
 sound/soc/sof/sof-client-probes.c              | 2 +-
 sound/soc/sof/xtensa/core.c                    | 2 +-
 9 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/sound/soc/sof/amd/acp-common.c b/sound/soc/sof/amd/acp-common.c
index b26fa471b431f..81bb93e983586 100644
--- a/sound/soc/sof/amd/acp-common.c
+++ b/sound/soc/sof/amd/acp-common.c
@@ -258,8 +258,8 @@ const struct snd_sof_dsp_ops sof_acp_common_ops = {
 };
 EXPORT_SYMBOL_NS(sof_acp_common_ops, SND_SOC_SOF_AMD_COMMON);
 
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("ACP SOF COMMON Driver");
 MODULE_IMPORT_NS(SND_SOC_SOF_AMD_COMMON);
 MODULE_IMPORT_NS(SND_SOC_SOF_XTENSA);
 MODULE_IMPORT_NS(SOUNDWIRE_AMD_INIT);
-MODULE_DESCRIPTION("ACP SOF COMMON Driver");
-MODULE_LICENSE("Dual BSD/GPL");
diff --git a/sound/soc/sof/amd/acp.c b/sound/soc/sof/amd/acp.c
index c12c7f8205294..74fd5f2b148b8 100644
--- a/sound/soc/sof/amd/acp.c
+++ b/sound/soc/sof/amd/acp.c
@@ -801,7 +801,7 @@ void amd_sof_acp_remove(struct snd_sof_dev *sdev)
 }
 EXPORT_SYMBOL_NS(amd_sof_acp_remove, SND_SOC_SOF_AMD_COMMON);
 
+MODULE_LICENSE("Dual BSD/GPL");
 MODULE_DESCRIPTION("AMD ACP sof driver");
 MODULE_IMPORT_NS(SOUNDWIRE_AMD_INIT);
 MODULE_IMPORT_NS(SND_AMD_SOUNDWIRE_ACPI);
-MODULE_LICENSE("Dual BSD/GPL");
diff --git a/sound/soc/sof/core.c b/sound/soc/sof/core.c
index 0a4917136ff97..83fe0401baf86 100644
--- a/sound/soc/sof/core.c
+++ b/sound/soc/sof/core.c
@@ -769,7 +769,7 @@ void sof_machine_unregister(struct snd_sof_dev *sdev, void *pdata)
 EXPORT_SYMBOL(sof_machine_unregister);
 
 MODULE_AUTHOR("Liam Girdwood");
-MODULE_DESCRIPTION("Sound Open Firmware (SOF) Core");
 MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("Sound Open Firmware (SOF) Core");
 MODULE_ALIAS("platform:sof-audio");
 MODULE_IMPORT_NS(SND_SOC_SOF_CLIENT);
diff --git a/sound/soc/sof/nocodec.c b/sound/soc/sof/nocodec.c
index fdcbe33d3dcfb..b12b3d865ae30 100644
--- a/sound/soc/sof/nocodec.c
+++ b/sound/soc/sof/nocodec.c
@@ -110,7 +110,7 @@ static struct platform_driver sof_nocodec_audio = {
 };
 module_platform_driver(sof_nocodec_audio)
 
+MODULE_LICENSE("Dual BSD/GPL");
 MODULE_DESCRIPTION("ASoC sof nocodec");
 MODULE_AUTHOR("Liam Girdwood");
-MODULE_LICENSE("Dual BSD/GPL");
 MODULE_ALIAS("platform:sof-nocodec");
diff --git a/sound/soc/sof/sof-client-ipc-flood-test.c b/sound/soc/sof/sof-client-ipc-flood-test.c
index 4356149260925..e7d2001140e81 100644
--- a/sound/soc/sof/sof-client-ipc-flood-test.c
+++ b/sound/soc/sof/sof-client-ipc-flood-test.c
@@ -394,6 +394,6 @@ static struct auxiliary_driver sof_ipc_flood_client_drv = {
 
 module_auxiliary_driver(sof_ipc_flood_client_drv);
 
-MODULE_DESCRIPTION("SOF IPC Flood Test Client Driver");
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("SOF IPC Flood Test Client Driver");
 MODULE_IMPORT_NS(SND_SOC_SOF_CLIENT);
diff --git a/sound/soc/sof/sof-client-ipc-kernel-injector.c b/sound/soc/sof/sof-client-ipc-kernel-injector.c
index 6973b6690df4b..d3f541069b24b 100644
--- a/sound/soc/sof/sof-client-ipc-kernel-injector.c
+++ b/sound/soc/sof/sof-client-ipc-kernel-injector.c
@@ -157,6 +157,6 @@ static struct auxiliary_driver sof_msg_inject_client_drv = {
 
 module_auxiliary_driver(sof_msg_inject_client_drv);
 
-MODULE_DESCRIPTION("SOF IPC Kernel Injector Client Driver");
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("SOF IPC Kernel Injector Client Driver");
 MODULE_IMPORT_NS(SND_SOC_SOF_CLIENT);
diff --git a/sound/soc/sof/sof-client-ipc-msg-injector.c b/sound/soc/sof/sof-client-ipc-msg-injector.c
index af22e6421029c..d0f8beb9d0008 100644
--- a/sound/soc/sof/sof-client-ipc-msg-injector.c
+++ b/sound/soc/sof/sof-client-ipc-msg-injector.c
@@ -335,6 +335,6 @@ static struct auxiliary_driver sof_msg_inject_client_drv = {
 
 module_auxiliary_driver(sof_msg_inject_client_drv);
 
-MODULE_DESCRIPTION("SOF IPC Message Injector Client Driver");
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("SOF IPC Message Injector Client Driver");
 MODULE_IMPORT_NS(SND_SOC_SOF_CLIENT);
diff --git a/sound/soc/sof/sof-client-probes.c b/sound/soc/sof/sof-client-probes.c
index b8f297307565c..ccc7d38ddc383 100644
--- a/sound/soc/sof/sof-client-probes.c
+++ b/sound/soc/sof/sof-client-probes.c
@@ -540,6 +540,6 @@ static struct auxiliary_driver sof_probes_client_drv = {
 
 module_auxiliary_driver(sof_probes_client_drv);
 
-MODULE_DESCRIPTION("SOF Probes Client Driver");
 MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("SOF Probes Client Driver");
 MODULE_IMPORT_NS(SND_SOC_SOF_CLIENT);
diff --git a/sound/soc/sof/xtensa/core.c b/sound/soc/sof/xtensa/core.c
index ccbc3fcdadd5e..3cf8c84beff95 100644
--- a/sound/soc/sof/xtensa/core.c
+++ b/sound/soc/sof/xtensa/core.c
@@ -151,5 +151,5 @@ const struct dsp_arch_ops sof_xtensa_arch_ops = {
 };
 EXPORT_SYMBOL_NS(sof_xtensa_arch_ops, SND_SOC_SOF_XTENSA);
 
-MODULE_DESCRIPTION("SOF Xtensa DSP support");
 MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("SOF Xtensa DSP support");
-- 
GitLab


From 3ff78451b8e446e9a548b98a0d4dd8d24dc5780b Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Mon, 27 May 2024 14:44:14 -0500
Subject: [PATCH 305/950] ASoC: SOF: add missing MODULE_DESCRIPTION()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

MODULE_DESCRIPTION() was optional until it became mandatory and
flagged as an error by 'make W=1'.

Reported-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Reviewed-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Reviewed-by: Daniel Baluta <daniel.baluta@nxp.com>
Reviewed-by: Péter Ujfalusi <peter.ujfalusi@linux.intel.com>
Link: https://msgid.link/r/20240527194414.166156-5-pierre-louis.bossart@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sof/imx/imx-common.c           | 1 +
 sound/soc/sof/imx/imx8.c                 | 3 ++-
 sound/soc/sof/imx/imx8m.c                | 3 ++-
 sound/soc/sof/imx/imx8ulp.c              | 3 ++-
 sound/soc/sof/intel/atom.c               | 1 +
 sound/soc/sof/intel/bdw.c                | 1 +
 sound/soc/sof/intel/byt.c                | 1 +
 sound/soc/sof/intel/hda-codec.c          | 1 +
 sound/soc/sof/intel/hda-ctrl.c           | 1 +
 sound/soc/sof/intel/hda-mlink.c          | 1 +
 sound/soc/sof/intel/hda.c                | 1 +
 sound/soc/sof/intel/pci-apl.c            | 1 +
 sound/soc/sof/intel/pci-cnl.c            | 1 +
 sound/soc/sof/intel/pci-icl.c            | 1 +
 sound/soc/sof/intel/pci-lnl.c            | 1 +
 sound/soc/sof/intel/pci-mtl.c            | 1 +
 sound/soc/sof/intel/pci-skl.c            | 1 +
 sound/soc/sof/intel/pci-tgl.c            | 1 +
 sound/soc/sof/intel/pci-tng.c            | 1 +
 sound/soc/sof/mediatek/mt8186/mt8186.c   | 3 ++-
 sound/soc/sof/mediatek/mt8195/mt8195.c   | 3 ++-
 sound/soc/sof/mediatek/mtk-adsp-common.c | 1 +
 sound/soc/sof/sof-acpi-dev.c             | 1 +
 sound/soc/sof/sof-of-dev.c               | 1 +
 sound/soc/sof/sof-pci-dev.c              | 1 +
 sound/soc/sof/sof-utils.c                | 1 +
 26 files changed, 31 insertions(+), 5 deletions(-)

diff --git a/sound/soc/sof/imx/imx-common.c b/sound/soc/sof/imx/imx-common.c
index 2981aea123d97..fce6d9cf6a6be 100644
--- a/sound/soc/sof/imx/imx-common.c
+++ b/sound/soc/sof/imx/imx-common.c
@@ -75,3 +75,4 @@ void imx8_dump(struct snd_sof_dev *sdev, u32 flags)
 EXPORT_SYMBOL(imx8_dump);
 
 MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("SOF helpers for IMX platforms");
diff --git a/sound/soc/sof/imx/imx8.c b/sound/soc/sof/imx/imx8.c
index 3021dc87ab5a2..9f24e3c283dd4 100644
--- a/sound/soc/sof/imx/imx8.c
+++ b/sound/soc/sof/imx/imx8.c
@@ -667,5 +667,6 @@ static struct platform_driver snd_sof_of_imx8_driver = {
 };
 module_platform_driver(snd_sof_of_imx8_driver);
 
-MODULE_IMPORT_NS(SND_SOC_SOF_XTENSA);
 MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("SOF support for IMX8 platforms");
+MODULE_IMPORT_NS(SND_SOC_SOF_XTENSA);
diff --git a/sound/soc/sof/imx/imx8m.c b/sound/soc/sof/imx/imx8m.c
index 4ed415f043454..1c7019c3cbd38 100644
--- a/sound/soc/sof/imx/imx8m.c
+++ b/sound/soc/sof/imx/imx8m.c
@@ -514,5 +514,6 @@ static struct platform_driver snd_sof_of_imx8m_driver = {
 };
 module_platform_driver(snd_sof_of_imx8m_driver);
 
-MODULE_IMPORT_NS(SND_SOC_SOF_XTENSA);
 MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("SOF support for IMX8M platforms");
+MODULE_IMPORT_NS(SND_SOC_SOF_XTENSA);
diff --git a/sound/soc/sof/imx/imx8ulp.c b/sound/soc/sof/imx/imx8ulp.c
index 8adfdd00413aa..2585b1beef23f 100644
--- a/sound/soc/sof/imx/imx8ulp.c
+++ b/sound/soc/sof/imx/imx8ulp.c
@@ -516,5 +516,6 @@ static struct platform_driver snd_sof_of_imx8ulp_driver = {
 };
 module_platform_driver(snd_sof_of_imx8ulp_driver);
 
-MODULE_IMPORT_NS(SND_SOC_SOF_XTENSA);
 MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("SOF support for IMX8ULP platforms");
+MODULE_IMPORT_NS(SND_SOC_SOF_XTENSA);
diff --git a/sound/soc/sof/intel/atom.c b/sound/soc/sof/intel/atom.c
index 86af4e9a716ef..3505ac3a1b143 100644
--- a/sound/soc/sof/intel/atom.c
+++ b/sound/soc/sof/intel/atom.c
@@ -418,3 +418,4 @@ void atom_set_mach_params(struct snd_soc_acpi_mach *mach,
 EXPORT_SYMBOL_NS(atom_set_mach_params, SND_SOC_SOF_INTEL_ATOM_HIFI_EP);
 
 MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("SOF support for Atom platforms");
diff --git a/sound/soc/sof/intel/bdw.c b/sound/soc/sof/intel/bdw.c
index 3262286a9a9d7..7f18080e4e191 100644
--- a/sound/soc/sof/intel/bdw.c
+++ b/sound/soc/sof/intel/bdw.c
@@ -694,6 +694,7 @@ static struct platform_driver snd_sof_acpi_intel_bdw_driver = {
 module_platform_driver(snd_sof_acpi_intel_bdw_driver);
 
 MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("SOF support for Broadwell platforms");
 MODULE_IMPORT_NS(SND_SOC_SOF_INTEL_HIFI_EP_IPC);
 MODULE_IMPORT_NS(SND_SOC_SOF_XTENSA);
 MODULE_IMPORT_NS(SND_SOC_SOF_ACPI_DEV);
diff --git a/sound/soc/sof/intel/byt.c b/sound/soc/sof/intel/byt.c
index d78d11d4cfbf6..7a57e162fb1c2 100644
--- a/sound/soc/sof/intel/byt.c
+++ b/sound/soc/sof/intel/byt.c
@@ -475,6 +475,7 @@ static struct platform_driver snd_sof_acpi_intel_byt_driver = {
 module_platform_driver(snd_sof_acpi_intel_byt_driver);
 
 MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("SOF support for Baytrail/Cherrytrail");
 MODULE_IMPORT_NS(SND_SOC_SOF_INTEL_HIFI_EP_IPC);
 MODULE_IMPORT_NS(SND_SOC_SOF_XTENSA);
 MODULE_IMPORT_NS(SND_SOC_SOF_ACPI_DEV);
diff --git a/sound/soc/sof/intel/hda-codec.c b/sound/soc/sof/intel/hda-codec.c
index da3db3ed379ec..dc46888faa0dc 100644
--- a/sound/soc/sof/intel/hda-codec.c
+++ b/sound/soc/sof/intel/hda-codec.c
@@ -457,3 +457,4 @@ EXPORT_SYMBOL_NS_GPL(hda_codec_i915_exit, SND_SOC_SOF_HDA_AUDIO_CODEC_I915);
 #endif
 
 MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("SOF support for HDaudio codecs");
diff --git a/sound/soc/sof/intel/hda-ctrl.c b/sound/soc/sof/intel/hda-ctrl.c
index 262b482dc0a80..b9a02750ce613 100644
--- a/sound/soc/sof/intel/hda-ctrl.c
+++ b/sound/soc/sof/intel/hda-ctrl.c
@@ -328,6 +328,7 @@ void hda_dsp_ctrl_stop_chip(struct snd_sof_dev *sdev)
 }
 
 MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("SOF helpers for HDaudio platforms");
 MODULE_IMPORT_NS(SND_SOC_SOF_HDA_MLINK);
 MODULE_IMPORT_NS(SND_SOC_SOF_HDA_AUDIO_CODEC);
 MODULE_IMPORT_NS(SND_SOC_SOF_HDA_AUDIO_CODEC_I915);
diff --git a/sound/soc/sof/intel/hda-mlink.c b/sound/soc/sof/intel/hda-mlink.c
index 04bbc5c9904ce..9a3559c78b627 100644
--- a/sound/soc/sof/intel/hda-mlink.c
+++ b/sound/soc/sof/intel/hda-mlink.c
@@ -972,3 +972,4 @@ EXPORT_SYMBOL_NS(hdac_bus_eml_enable_offload, SND_SOC_SOF_HDA_MLINK);
 #endif
 
 MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("SOF support for HDaudio multi-link");
diff --git a/sound/soc/sof/intel/hda.c b/sound/soc/sof/intel/hda.c
index e6a38de0a0aa1..dead1c19558bb 100644
--- a/sound/soc/sof/intel/hda.c
+++ b/sound/soc/sof/intel/hda.c
@@ -1522,6 +1522,7 @@ void hda_unregister_clients(struct snd_sof_dev *sdev)
 }
 
 MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("SOF support for HDaudio platforms");
 MODULE_IMPORT_NS(SND_SOC_SOF_PCI_DEV);
 MODULE_IMPORT_NS(SND_SOC_SOF_HDA_AUDIO_CODEC);
 MODULE_IMPORT_NS(SND_SOC_SOF_HDA_AUDIO_CODEC_I915);
diff --git a/sound/soc/sof/intel/pci-apl.c b/sound/soc/sof/intel/pci-apl.c
index df6d897da290b..f006dcf5458ae 100644
--- a/sound/soc/sof/intel/pci-apl.c
+++ b/sound/soc/sof/intel/pci-apl.c
@@ -105,6 +105,7 @@ static struct pci_driver snd_sof_pci_intel_apl_driver = {
 module_pci_driver(snd_sof_pci_intel_apl_driver);
 
 MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("SOF support for ApolloLake platforms");
 MODULE_IMPORT_NS(SND_SOC_SOF_INTEL_HDA_GENERIC);
 MODULE_IMPORT_NS(SND_SOC_SOF_INTEL_HDA_COMMON);
 MODULE_IMPORT_NS(SND_SOC_SOF_PCI_DEV);
diff --git a/sound/soc/sof/intel/pci-cnl.c b/sound/soc/sof/intel/pci-cnl.c
index a39fa3657d555..a8406342f08bd 100644
--- a/sound/soc/sof/intel/pci-cnl.c
+++ b/sound/soc/sof/intel/pci-cnl.c
@@ -143,6 +143,7 @@ static struct pci_driver snd_sof_pci_intel_cnl_driver = {
 module_pci_driver(snd_sof_pci_intel_cnl_driver);
 
 MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("SOF support for CannonLake platforms");
 MODULE_IMPORT_NS(SND_SOC_SOF_INTEL_HDA_GENERIC);
 MODULE_IMPORT_NS(SND_SOC_SOF_INTEL_HDA_COMMON);
 MODULE_IMPORT_NS(SND_SOC_SOF_PCI_DEV);
diff --git a/sound/soc/sof/intel/pci-icl.c b/sound/soc/sof/intel/pci-icl.c
index 9f1fe47475fb1..25effca50d9fe 100644
--- a/sound/soc/sof/intel/pci-icl.c
+++ b/sound/soc/sof/intel/pci-icl.c
@@ -108,6 +108,7 @@ static struct pci_driver snd_sof_pci_intel_icl_driver = {
 module_pci_driver(snd_sof_pci_intel_icl_driver);
 
 MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("SOF support for IceLake platforms");
 MODULE_IMPORT_NS(SND_SOC_SOF_INTEL_HDA_GENERIC);
 MODULE_IMPORT_NS(SND_SOC_SOF_INTEL_HDA_COMMON);
 MODULE_IMPORT_NS(SND_SOC_SOF_INTEL_CNL);
diff --git a/sound/soc/sof/intel/pci-lnl.c b/sound/soc/sof/intel/pci-lnl.c
index 68e5c90151b27..602c574064eb5 100644
--- a/sound/soc/sof/intel/pci-lnl.c
+++ b/sound/soc/sof/intel/pci-lnl.c
@@ -70,6 +70,7 @@ static struct pci_driver snd_sof_pci_intel_lnl_driver = {
 module_pci_driver(snd_sof_pci_intel_lnl_driver);
 
 MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("SOF support for LunarLake platforms");
 MODULE_IMPORT_NS(SND_SOC_SOF_INTEL_HDA_GENERIC);
 MODULE_IMPORT_NS(SND_SOC_SOF_INTEL_HDA_COMMON);
 MODULE_IMPORT_NS(SND_SOC_SOF_INTEL_MTL);
diff --git a/sound/soc/sof/intel/pci-mtl.c b/sound/soc/sof/intel/pci-mtl.c
index c685cb8d61712..8cb0333c033ef 100644
--- a/sound/soc/sof/intel/pci-mtl.c
+++ b/sound/soc/sof/intel/pci-mtl.c
@@ -133,6 +133,7 @@ static struct pci_driver snd_sof_pci_intel_mtl_driver = {
 module_pci_driver(snd_sof_pci_intel_mtl_driver);
 
 MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("SOF support for MeteorLake platforms");
 MODULE_IMPORT_NS(SND_SOC_SOF_INTEL_HDA_GENERIC);
 MODULE_IMPORT_NS(SND_SOC_SOF_INTEL_HDA_COMMON);
 MODULE_IMPORT_NS(SND_SOC_SOF_PCI_DEV);
diff --git a/sound/soc/sof/intel/pci-skl.c b/sound/soc/sof/intel/pci-skl.c
index 862da8009543b..8ca0231d7e4f6 100644
--- a/sound/soc/sof/intel/pci-skl.c
+++ b/sound/soc/sof/intel/pci-skl.c
@@ -89,6 +89,7 @@ static struct pci_driver snd_sof_pci_intel_skl_driver = {
 module_pci_driver(snd_sof_pci_intel_skl_driver);
 
 MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("SOF support for SkyLake platforms");
 MODULE_IMPORT_NS(SND_SOC_SOF_INTEL_HDA_GENERIC);
 MODULE_IMPORT_NS(SND_SOC_SOF_INTEL_HDA_COMMON);
 MODULE_IMPORT_NS(SND_SOC_SOF_PCI_DEV);
diff --git a/sound/soc/sof/intel/pci-tgl.c b/sound/soc/sof/intel/pci-tgl.c
index f73bb47cd79e7..ebe1a7d166894 100644
--- a/sound/soc/sof/intel/pci-tgl.c
+++ b/sound/soc/sof/intel/pci-tgl.c
@@ -317,6 +317,7 @@ static struct pci_driver snd_sof_pci_intel_tgl_driver = {
 module_pci_driver(snd_sof_pci_intel_tgl_driver);
 
 MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("SOF support for TigerLake platforms");
 MODULE_IMPORT_NS(SND_SOC_SOF_INTEL_HDA_GENERIC);
 MODULE_IMPORT_NS(SND_SOC_SOF_INTEL_HDA_COMMON);
 MODULE_IMPORT_NS(SND_SOC_SOF_INTEL_CNL);
diff --git a/sound/soc/sof/intel/pci-tng.c b/sound/soc/sof/intel/pci-tng.c
index 5c3069588bb77..1375c393827e1 100644
--- a/sound/soc/sof/intel/pci-tng.c
+++ b/sound/soc/sof/intel/pci-tng.c
@@ -244,6 +244,7 @@ static struct pci_driver snd_sof_pci_intel_tng_driver = {
 module_pci_driver(snd_sof_pci_intel_tng_driver);
 
 MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("SOF support for Tangier platforms");
 MODULE_IMPORT_NS(SND_SOC_SOF_INTEL_HIFI_EP_IPC);
 MODULE_IMPORT_NS(SND_SOC_SOF_XTENSA);
 MODULE_IMPORT_NS(SND_SOC_SOF_PCI_DEV);
diff --git a/sound/soc/sof/mediatek/mt8186/mt8186.c b/sound/soc/sof/mediatek/mt8186/mt8186.c
index c63e0d2f4b968..bea1b9d9ca288 100644
--- a/sound/soc/sof/mediatek/mt8186/mt8186.c
+++ b/sound/soc/sof/mediatek/mt8186/mt8186.c
@@ -666,6 +666,7 @@ static struct platform_driver snd_sof_of_mt8186_driver = {
 };
 module_platform_driver(snd_sof_of_mt8186_driver);
 
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("SOF support for MT8186/MT8188 platforms");
 MODULE_IMPORT_NS(SND_SOC_SOF_XTENSA);
 MODULE_IMPORT_NS(SND_SOC_SOF_MTK_COMMON);
-MODULE_LICENSE("Dual BSD/GPL");
diff --git a/sound/soc/sof/mediatek/mt8195/mt8195.c b/sound/soc/sof/mediatek/mt8195/mt8195.c
index fc1c016104aee..31dc98d1b1d8b 100644
--- a/sound/soc/sof/mediatek/mt8195/mt8195.c
+++ b/sound/soc/sof/mediatek/mt8195/mt8195.c
@@ -619,6 +619,7 @@ static struct platform_driver snd_sof_of_mt8195_driver = {
 };
 module_platform_driver(snd_sof_of_mt8195_driver);
 
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("SOF support for MTL 8195 platforms");
 MODULE_IMPORT_NS(SND_SOC_SOF_XTENSA);
 MODULE_IMPORT_NS(SND_SOC_SOF_MTK_COMMON);
-MODULE_LICENSE("Dual BSD/GPL");
diff --git a/sound/soc/sof/mediatek/mtk-adsp-common.c b/sound/soc/sof/mediatek/mtk-adsp-common.c
index de8dbe27cd0de..20bcf5590eb88 100644
--- a/sound/soc/sof/mediatek/mtk-adsp-common.c
+++ b/sound/soc/sof/mediatek/mtk-adsp-common.c
@@ -82,3 +82,4 @@ void mtk_adsp_dump(struct snd_sof_dev *sdev, u32 flags)
 EXPORT_SYMBOL(mtk_adsp_dump);
 
 MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("SOF helpers for MTK ADSP platforms");
diff --git a/sound/soc/sof/sof-acpi-dev.c b/sound/soc/sof/sof-acpi-dev.c
index 2d96d00f1c449..b196b2b74c264 100644
--- a/sound/soc/sof/sof-acpi-dev.c
+++ b/sound/soc/sof/sof-acpi-dev.c
@@ -100,3 +100,4 @@ void sof_acpi_remove(struct platform_device *pdev)
 EXPORT_SYMBOL_NS(sof_acpi_remove, SND_SOC_SOF_ACPI_DEV);
 
 MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("SOF support for ACPI platforms");
diff --git a/sound/soc/sof/sof-of-dev.c b/sound/soc/sof/sof-of-dev.c
index b9a499e92b9a5..71f7153cf79c6 100644
--- a/sound/soc/sof/sof-of-dev.c
+++ b/sound/soc/sof/sof-of-dev.c
@@ -93,3 +93,4 @@ void sof_of_shutdown(struct platform_device *pdev)
 EXPORT_SYMBOL(sof_of_shutdown);
 
 MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("SOF support for OF/DT platforms");
diff --git a/sound/soc/sof/sof-pci-dev.c b/sound/soc/sof/sof-pci-dev.c
index 4365405783e61..38f2187da5de1 100644
--- a/sound/soc/sof/sof-pci-dev.c
+++ b/sound/soc/sof/sof-pci-dev.c
@@ -304,3 +304,4 @@ void sof_pci_shutdown(struct pci_dev *pci)
 EXPORT_SYMBOL_NS(sof_pci_shutdown, SND_SOC_SOF_PCI_DEV);
 
 MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("SOF support for PCI platforms");
diff --git a/sound/soc/sof/sof-utils.c b/sound/soc/sof/sof-utils.c
index cad041bf56ccf..44608682e9f8f 100644
--- a/sound/soc/sof/sof-utils.c
+++ b/sound/soc/sof/sof-utils.c
@@ -73,3 +73,4 @@ int snd_sof_create_page_table(struct device *dev,
 EXPORT_SYMBOL(snd_sof_create_page_table);
 
 MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("SOF utils");
-- 
GitLab


From 7b05ab85e28f615e70520d24c075249b4512044e Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 23 May 2024 14:02:57 +0300
Subject: [PATCH 306/950] ipv4: Fix address dump when IPv4 is disabled on an
 interface

Cited commit started returning an error when user space requests to dump
the interface's IPv4 addresses and IPv4 is disabled on the interface.
Restore the previous behavior and do not return an error.

Before cited commit:

 # ip address show dev dummy1
 10: dummy1: <BROADCAST,NOARP,UP,LOWER_UP> mtu 1500 qdisc noqueue state UNKNOWN group default qlen 1000
     link/ether e2:40:68:98:d0:18 brd ff:ff:ff:ff:ff:ff
     inet6 fe80::e040:68ff:fe98:d018/64 scope link proto kernel_ll
        valid_lft forever preferred_lft forever
 # ip link set dev dummy1 mtu 67
 # ip address show dev dummy1
 10: dummy1: <BROADCAST,NOARP,UP,LOWER_UP> mtu 67 qdisc noqueue state UNKNOWN group default qlen 1000
     link/ether e2:40:68:98:d0:18 brd ff:ff:ff:ff:ff:ff

After cited commit:

 # ip address show dev dummy1
 10: dummy1: <BROADCAST,NOARP,UP,LOWER_UP> mtu 1500 qdisc noqueue state UNKNOWN group default qlen 1000
     link/ether 32:2d:69:f2:9c:99 brd ff:ff:ff:ff:ff:ff
     inet6 fe80::302d:69ff:fef2:9c99/64 scope link proto kernel_ll
        valid_lft forever preferred_lft forever
 # ip link set dev dummy1 mtu 67
 # ip address show dev dummy1
 RTNETLINK answers: No such device
 Dump terminated

With this patch:

 # ip address show dev dummy1
 10: dummy1: <BROADCAST,NOARP,UP,LOWER_UP> mtu 1500 qdisc noqueue state UNKNOWN group default qlen 1000
     link/ether de:17:56:bb:57:c0 brd ff:ff:ff:ff:ff:ff
     inet6 fe80::dc17:56ff:febb:57c0/64 scope link proto kernel_ll
        valid_lft forever preferred_lft forever
 # ip link set dev dummy1 mtu 67
 # ip address show dev dummy1
 10: dummy1: <BROADCAST,NOARP,UP,LOWER_UP> mtu 67 qdisc noqueue state UNKNOWN group default qlen 1000
     link/ether de:17:56:bb:57:c0 brd ff:ff:ff:ff:ff:ff

I fixed the exact same issue for IPv6 in commit c04f7dfe6ec2 ("ipv6: Fix
address dump when IPv6 is disabled on an interface"), but noted [1] that
I am not doing the change for IPv4 because I am not aware of a way to
disable IPv4 on an interface other than unregistering it. I clearly
missed the above case.

[1] https://lore.kernel.org/netdev/20240321173042.2151756-1-idosch@nvidia.com/

Fixes: cdb2f80f1c10 ("inet: use xa_array iterator to implement inet_dump_ifaddr()")
Reported-by: Carolina Jubran <cjubran@nvidia.com>
Reported-by: Yamen Safadi <ysafadi@nvidia.com>
Tested-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20240523110257.334315-1-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/devinet.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 96accde527da2..e827da128c5f5 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1887,10 +1887,11 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb)
 			goto done;
 
 		if (fillargs.ifindex) {
-			err = -ENODEV;
 			dev = dev_get_by_index_rcu(tgt_net, fillargs.ifindex);
-			if (!dev)
+			if (!dev) {
+				err = -ENODEV;
 				goto done;
+			}
 			in_dev = __in_dev_get_rcu(dev);
 			if (!in_dev)
 				goto done;
-- 
GitLab


From be008726d0ac338a6bb19c2da2853e3e2112b055 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Thu, 23 May 2024 10:13:45 -0400
Subject: [PATCH 307/950] net: gro: initialize network_offset in network layer

Syzkaller was able to trigger

    kernel BUG at net/core/gro.c:424 !
    RIP: 0010:gro_pull_from_frag0 net/core/gro.c:424 [inline]
    RIP: 0010:gro_try_pull_from_frag0 net/core/gro.c:446 [inline]
    RIP: 0010:dev_gro_receive+0x242f/0x24b0 net/core/gro.c:571

Due to using an incorrect NAPI_GRO_CB(skb)->network_offset.

The referenced commit sets this offset to 0 in skb_gro_reset_offset.
That matches the expected case in dev_gro_receive:

        pp = INDIRECT_CALL_INET(ptype->callbacks.gro_receive,
                                ipv6_gro_receive, inet_gro_receive,
                                &gro_list->list, skb);

But syzkaller injected an skb with protocol ETH_P_TEB into an ip6gre
device (by writing the IP6GRE encapsulated version to a TAP device).
The result was a first call to eth_gro_receive, and thus an extra
ETH_HLEN in network_offset that should not be there. First issue hit
is when computing offset from network header in ipv6_gro_pull_exthdrs.

Initialize both offsets in the network layer gro_receive.

This pairs with all reads in gro_receive, which use
skb_gro_receive_network_offset().

Fixes: 186b1ea73ad8 ("net: gro: use cb instead of skb->network_header")
Reported-by: syzkaller <syzkaller@googlegroups.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
CC: Richard Gobert <richardbgobert@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20240523141434.1752483-1-willemdebruijn.kernel@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/af_inet.c     | 2 +-
 net/ipv6/ip6_offload.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index e03ba4a21c390..b24d74616637a 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1532,7 +1532,7 @@ struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb)
 	}
 
 	NAPI_GRO_CB(skb)->flush |= flush;
-	NAPI_GRO_CB(skb)->inner_network_offset = off;
+	NAPI_GRO_CB(skb)->network_offsets[NAPI_GRO_CB(skb)->encap_mark] = off;
 
 	/* Note : No need to call skb_gro_postpull_rcsum() here,
 	 * as we already checked checksum over ipv4 header was 0
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index bd5aff97d8b1d..9822163428b02 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -236,7 +236,7 @@ INDIRECT_CALLABLE_SCOPE struct sk_buff *ipv6_gro_receive(struct list_head *head,
 	if (unlikely(!iph))
 		goto out;
 
-	NAPI_GRO_CB(skb)->inner_network_offset = off;
+	NAPI_GRO_CB(skb)->network_offsets[NAPI_GRO_CB(skb)->encap_mark] = off;
 
 	flush += ntohs(iph->payload_len) != skb->len - hlen;
 
-- 
GitLab


From f4dca95fc0f6350918f2e6727e35b41f7f86fcce Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 23 May 2024 13:05:27 +0000
Subject: [PATCH 308/950] tcp: reduce accepted window in NEW_SYN_RECV state

Jason commit made checks against ACK sequence less strict
and can be exploited by attackers to establish spoofed flows
with less probes.

Innocent users might use tcp_rmem[1] == 1,000,000,000,
or something more reasonable.

An attacker can use a regular TCP connection to learn the server
initial tp->rcv_wnd, and use it to optimize the attack.

If we make sure that only the announced window (smaller than 65535)
is used for ACK validation, we force an attacker to use
65537 packets to complete the 3WHS (assuming server ISN is unknown)

Fixes: 378979e94e95 ("tcp: remove 64 KByte limit for initial tp->rcv_wnd value")
Link: https://datatracker.ietf.org/meeting/119/materials/slides-119-tcpm-ghost-acks-00
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Link: https://lore.kernel.org/r/20240523130528.60376-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/request_sock.h | 12 ++++++++++++
 net/ipv4/tcp_ipv4.c        |  7 +------
 net/ipv4/tcp_minisocks.c   |  7 +++++--
 net/ipv6/tcp_ipv6.c        |  7 +------
 4 files changed, 19 insertions(+), 14 deletions(-)

diff --git a/include/net/request_sock.h b/include/net/request_sock.h
index d88c0dfc2d468..ebcb8896bffc1 100644
--- a/include/net/request_sock.h
+++ b/include/net/request_sock.h
@@ -285,4 +285,16 @@ static inline int reqsk_queue_len_young(const struct request_sock_queue *queue)
 	return atomic_read(&queue->young);
 }
 
+/* RFC 7323 2.3 Using the Window Scale Option
+ *  The window field (SEG.WND) of every outgoing segment, with the
+ *  exception of <SYN> segments, MUST be right-shifted by
+ *  Rcv.Wind.Shift bits.
+ *
+ * This means the SEG.WND carried in SYNACK can not exceed 65535.
+ * We use this property to harden TCP stack while in NEW_SYN_RECV state.
+ */
+static inline u32 tcp_synack_window(const struct request_sock *req)
+{
+	return min(req->rsk_rcv_wnd, 65535U);
+}
 #endif /* _REQUEST_SOCK_H */
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 30ef0c8f5e92d..b710958393e64 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1144,14 +1144,9 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
 #endif
 	}
 
-	/* RFC 7323 2.3
-	 * The window field (SEG.WND) of every outgoing segment, with the
-	 * exception of <SYN> segments, MUST be right-shifted by
-	 * Rcv.Wind.Shift bits:
-	 */
 	tcp_v4_send_ack(sk, skb, seq,
 			tcp_rsk(req)->rcv_nxt,
-			req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale,
+			tcp_synack_window(req) >> inet_rsk(req)->rcv_wscale,
 			tcp_rsk_tsval(tcp_rsk(req)),
 			READ_ONCE(req->ts_recent),
 			0, &key,
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index b93619b2384b3..538c06f95918d 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -783,8 +783,11 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 
 	/* RFC793: "first check sequence number". */
 
-	if (paws_reject || !tcp_in_window(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq,
-					  tcp_rsk(req)->rcv_nxt, tcp_rsk(req)->rcv_nxt + req->rsk_rcv_wnd)) {
+	if (paws_reject || !tcp_in_window(TCP_SKB_CB(skb)->seq,
+					  TCP_SKB_CB(skb)->end_seq,
+					  tcp_rsk(req)->rcv_nxt,
+					  tcp_rsk(req)->rcv_nxt +
+					  tcp_synack_window(req))) {
 		/* Out of window: send ACK and drop. */
 		if (!(flg & TCP_FLAG_RST) &&
 		    !tcp_oow_rate_limited(sock_net(sk), skb,
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 4c3605485b68e..8c577b651bfcd 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1272,15 +1272,10 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
 	/* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV
 	 * sk->sk_state == TCP_SYN_RECV -> for Fast Open.
 	 */
-	/* RFC 7323 2.3
-	 * The window field (SEG.WND) of every outgoing segment, with the
-	 * exception of <SYN> segments, MUST be right-shifted by
-	 * Rcv.Wind.Shift bits:
-	 */
 	tcp_v6_send_ack(sk, skb, (sk->sk_state == TCP_LISTEN) ?
 			tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt,
 			tcp_rsk(req)->rcv_nxt,
-			req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale,
+			tcp_synack_window(req) >> inet_rsk(req)->rcv_wscale,
 			tcp_rsk_tsval(tcp_rsk(req)),
 			READ_ONCE(req->ts_recent), sk->sk_bound_dev_if,
 			&key, ipv6_get_dsfield(ipv6_hdr(skb)), 0,
-- 
GitLab


From 5233a55a5254ea38dcdd8d836a0f9ee886c3df51 Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Thu, 23 May 2024 16:59:22 +0100
Subject: [PATCH 309/950] mISDN: remove unused struct 'bf_ctx'

'bf_ctx' appears unused since the original
commit 960366cf8dbb ("Add mISDN DSP").

Remove it.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Link: https://lore.kernel.org/r/20240523155922.67329-1-linux@treblig.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/isdn/mISDN/dsp_blowfish.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/drivers/isdn/mISDN/dsp_blowfish.c b/drivers/isdn/mISDN/dsp_blowfish.c
index 0aa572f3858da..0e77c282c8624 100644
--- a/drivers/isdn/mISDN/dsp_blowfish.c
+++ b/drivers/isdn/mISDN/dsp_blowfish.c
@@ -73,11 +73,6 @@
  * crypto-api for faster implementation
  */
 
-struct bf_ctx {
-	u32 p[18];
-	u32 s[1024];
-};
-
 static const u32 bf_pbox[16 + 2] = {
 	0x243f6a88, 0x85a308d3, 0x13198a2e, 0x03707344,
 	0xa4093822, 0x299f31d0, 0x082efa98, 0xec4e6c89,
-- 
GitLab


From 0fe53c0ab018b3399b8d4be95f32fd017c9719e1 Mon Sep 17 00:00:00 2001
From: "Rob Herring (Arm)" <robh@kernel.org>
Date: Thu, 23 May 2024 12:17:31 -0500
Subject: [PATCH 310/950] dt-bindings: net: pse-pd: microchip,pd692x0: Fix
 missing "additionalProperties" constraints

The child nodes are missing "additionalProperties" constraints which
means any undocumented properties or child nodes are allowed. Add the
constraints, and fix the fallout of wrong manager node regex and
missing properties.

Fixes: 9c1de033afad ("dt-bindings: net: pse-pd: Add bindings for PD692x0 PSE controller")
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
Acked-by: Kory Maincent <kory.maincent@bootlin.com>
Link: https://lore.kernel.org/r/20240523171732.2836880-1-robh@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../bindings/net/pse-pd/microchip,pd692x0.yaml        | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/net/pse-pd/microchip,pd692x0.yaml b/Documentation/devicetree/bindings/net/pse-pd/microchip,pd692x0.yaml
index 828439398fdf9..fd4244fceced9 100644
--- a/Documentation/devicetree/bindings/net/pse-pd/microchip,pd692x0.yaml
+++ b/Documentation/devicetree/bindings/net/pse-pd/microchip,pd692x0.yaml
@@ -24,6 +24,7 @@ properties:
 
   managers:
     type: object
+    additionalProperties: false
     description:
       List of the PD69208T4/PD69204T4/PD69208M PSE managers. Each manager
       have 4 or 8 physical ports according to the chip version. No need to
@@ -47,8 +48,9 @@ properties:
       - "#size-cells"
 
     patternProperties:
-      "^manager@0[0-9a-b]$":
+      "^manager@[0-9a-b]$":
         type: object
+        additionalProperties: false
         description:
           PD69208T4/PD69204T4/PD69208M PSE manager exposing 4 or 8 physical
           ports.
@@ -69,9 +71,14 @@ properties:
         patternProperties:
           '^port@[0-7]$':
             type: object
+            additionalProperties: false
+
+            properties:
+              reg:
+                maxItems: 1
+
             required:
               - reg
-            additionalProperties: false
 
         required:
           - reg
-- 
GitLab


From 12f86b9af96a8b09969e4392311602f787b40834 Mon Sep 17 00:00:00 2001
From: "Rob Herring (Arm)" <robh@kernel.org>
Date: Thu, 23 May 2024 12:17:50 -0500
Subject: [PATCH 311/950] dt-bindings: net: pse-pd: ti,tps23881: Fix missing
 "additionalProperties" constraints

The child nodes are missing "additionalProperties" constraints which
means any undocumented properties or child nodes are allowed. Add the
constraints and all the undocumented properties exposed by the fix.

Fixes: f562202fedad ("dt-bindings: net: pse-pd: Add bindings for TPS23881 PSE controller")
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
Acked-by: Kory Maincent <kory.maincent@bootlin.com>
Link: https://lore.kernel.org/r/20240523171750.2837331-1-robh@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../bindings/net/pse-pd/ti,tps23881.yaml       | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/Documentation/devicetree/bindings/net/pse-pd/ti,tps23881.yaml b/Documentation/devicetree/bindings/net/pse-pd/ti,tps23881.yaml
index 4147adb11e101..6992d56832bf9 100644
--- a/Documentation/devicetree/bindings/net/pse-pd/ti,tps23881.yaml
+++ b/Documentation/devicetree/bindings/net/pse-pd/ti,tps23881.yaml
@@ -29,13 +29,31 @@ properties:
       of the ports conversion matrix that establishes relationship between
       the logical ports and the physical channels.
     type: object
+    additionalProperties: false
+
+    properties:
+      "#address-cells":
+        const: 1
+
+      "#size-cells":
+        const: 0
 
     patternProperties:
       '^channel@[0-7]$':
         type: object
+        additionalProperties: false
+
+        properties:
+          reg:
+            maxItems: 1
+
         required:
           - reg
 
+    required:
+      - "#address-cells"
+      - "#size-cells"
+
 unevaluatedProperties: false
 
 required:
-- 
GitLab


From bf0497f53c8535f99b72041529d3f7708a6e2c0d Mon Sep 17 00:00:00 2001
From: Xiaolei Wang <xiaolei.wang@windriver.com>
Date: Fri, 24 May 2024 13:05:28 +0800
Subject: [PATCH 312/950] net:fec: Add fec_enet_deinit()

When fec_probe() fails or fec_drv_remove() needs to release the
fec queue and remove a NAPI context, therefore add a function
corresponding to fec_enet_init() and call fec_enet_deinit() which
does the opposite to release memory and remove a NAPI context.

Fixes: 59d0f7465644 ("net: fec: init multi queue date structure")
Signed-off-by: Xiaolei Wang <xiaolei.wang@windriver.com>
Reviewed-by: Wei Fang <wei.fang@nxp.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://lore.kernel.org/r/20240524050528.4115581-1-xiaolei.wang@windriver.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/fec_main.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index a72d8a2eb0b31..881ece735dcf1 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -4130,6 +4130,14 @@ free_queue_mem:
 	return ret;
 }
 
+static void fec_enet_deinit(struct net_device *ndev)
+{
+	struct fec_enet_private *fep = netdev_priv(ndev);
+
+	netif_napi_del(&fep->napi);
+	fec_enet_free_queue(ndev);
+}
+
 #ifdef CONFIG_OF
 static int fec_reset_phy(struct platform_device *pdev)
 {
@@ -4524,6 +4532,7 @@ failed_register:
 	fec_enet_mii_remove(fep);
 failed_mii_init:
 failed_irq:
+	fec_enet_deinit(ndev);
 failed_init:
 	fec_ptp_stop(pdev);
 failed_reset:
@@ -4587,6 +4596,7 @@ fec_drv_remove(struct platform_device *pdev)
 	pm_runtime_put_noidle(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 
+	fec_enet_deinit(ndev);
 	free_netdev(ndev);
 }
 
-- 
GitLab


From 4fb679040d9f758eeb3b4d01bbde6405bf20e64e Mon Sep 17 00:00:00 2001
From: Horatiu Vultur <horatiu.vultur@microchip.com>
Date: Fri, 24 May 2024 10:53:50 +0200
Subject: [PATCH 313/950] net: micrel: Fix lan8841_config_intr after getting
 out of sleep mode

When the interrupt is enabled, the function lan8841_config_intr tries to
clear any pending interrupts by reading the interrupt status, then
checks the return value for errors and then continue to enable the
interrupt. It has been seen that once the system gets out of sleep mode,
the interrupt status has the value 0x400 meaning that the PHY detected
that the link was in low power. That is correct value but the problem is
that the check is wrong.  We try to check for errors but we return an
error also in this case which is not an error. Therefore fix this by
returning only when there is an error.

Fixes: a8f1a19d27ef ("net: micrel: Add support for lan8841 PHY")
Signed-off-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Reviewed-by: Suman Ghosh <sumang@marvell.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://lore.kernel.org/r/20240524085350.359812-1-horatiu.vultur@microchip.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/micrel.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index 1d769322b0593..2b8f8b7f1517c 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -4029,7 +4029,7 @@ static int lan8841_config_intr(struct phy_device *phydev)
 
 	if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
 		err = phy_read(phydev, LAN8814_INTS);
-		if (err)
+		if (err < 0)
 			return err;
 
 		/* Enable / disable interrupts. It is OK to enable PTP interrupt
@@ -4045,6 +4045,14 @@ static int lan8841_config_intr(struct phy_device *phydev)
 			return err;
 
 		err = phy_read(phydev, LAN8814_INTS);
+		if (err < 0)
+			return err;
+
+		/* Getting a positive value doesn't mean that is an error, it
+		 * just indicates what was the status. Therefore make sure to
+		 * clear the value and say that there is no error.
+		 */
+		err = 0;
 	}
 
 	return err;
-- 
GitLab


From 266aa3b4812e97942a8ce5c7aafa7da059f7b5b8 Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <aleksander.lobakin@intel.com>
Date: Fri, 24 May 2024 13:28:59 +0200
Subject: [PATCH 314/950] page_pool: fix &page_pool_params kdoc issues

After the tagged commit, @netdev got documented twice and the kdoc
script didn't notice that. Remove the second description added later
and move the initial one according to the field position.

After merging commit 5f8e4007c10d ("kernel-doc: fix
struct_group_tagged() parsing"), kdoc requires to describe struct
groups as well. &page_pool_params has 2 struct groups which
generated new warnings, describe them to resolve this.

Fixes: 403f11ac9ab7 ("page_pool: don't use driver-set flags field directly")
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Link: https://lore.kernel.org/r/20240524112859.2757403-1-aleksander.lobakin@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/page_pool/types.h | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h
index b088d131aeb0d..7e8477057f3d1 100644
--- a/include/net/page_pool/types.h
+++ b/include/net/page_pool/types.h
@@ -45,16 +45,17 @@ struct pp_alloc_cache {
 
 /**
  * struct page_pool_params - page pool parameters
+ * @fast:	params accessed frequently on hotpath
  * @order:	2^order pages on allocation
  * @pool_size:	size of the ptr_ring
  * @nid:	NUMA node id to allocate from pages from
  * @dev:	device, for DMA pre-mapping purposes
- * @netdev:	netdev this pool will serve (leave as NULL if none or multiple)
  * @napi:	NAPI which is the sole consumer of pages, otherwise NULL
  * @dma_dir:	DMA mapping direction
  * @max_len:	max DMA sync memory size for PP_FLAG_DMA_SYNC_DEV
  * @offset:	DMA sync address offset for PP_FLAG_DMA_SYNC_DEV
- * @netdev:	corresponding &net_device for Netlink introspection
+ * @slow:	params with slowpath access only (initialization and Netlink)
+ * @netdev:	netdev this pool will serve (leave as NULL if none or multiple)
  * @flags:	PP_FLAG_DMA_MAP, PP_FLAG_DMA_SYNC_DEV, PP_FLAG_SYSTEM_POOL
  */
 struct page_pool_params {
-- 
GitLab


From d514c8b54209de7a95ab37259fe32c7406976bd9 Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <aleksander.lobakin@intel.com>
Date: Thu, 23 May 2024 10:45:29 -0700
Subject: [PATCH 315/950] idpf: don't enable NAPI and interrupts prior to
 allocating Rx buffers

Currently, idpf enables NAPI and interrupts prior to allocating Rx
buffers.
This may lead to frame loss (there are no buffers to place incoming
frames) and even crashes on quick ifup-ifdown. Interrupts must be
enabled only after all the resources are here and available.
Split interrupt init into two phases: initialization and enabling,
and perform the second only after the queues are fully initialized.
Note that we can't just move interrupt initialization down the init
process, as the queues must have correct a ::q_vector pointer set
and NAPI already added in order to allocate buffers correctly.
Also, during the deinit process, disable HW interrupts first and
only then disable NAPI. Otherwise, there can be a HW event leading
to napi_schedule(), but the NAPI will already be unavailable.

Fixes: d4d558718266 ("idpf: initialize interrupts and enable vport")
Reported-by: Michal Kubiak <michal.kubiak@intel.com>
Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Krishneil Singh <krishneil.k.singh@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20240523-net-2024-05-23-intel-net-fixes-v1-1-17a923e0bb5f@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/idpf/idpf_lib.c  |  1 +
 drivers/net/ethernet/intel/idpf/idpf_txrx.c | 12 +++++++-----
 drivers/net/ethernet/intel/idpf/idpf_txrx.h |  1 +
 3 files changed, 9 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c
index 52ceda6306a3d..f1ee5584e8fa2 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_lib.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c
@@ -1394,6 +1394,7 @@ static int idpf_vport_open(struct idpf_vport *vport, bool alloc_res)
 	}
 
 	idpf_rx_init_buf_tail(vport);
+	idpf_vport_intr_ena(vport);
 
 	err = idpf_send_config_queues_msg(vport);
 	if (err) {
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
index 285da2177ee44..b023704bbbdab 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
@@ -3746,9 +3746,9 @@ static void idpf_vport_intr_ena_irq_all(struct idpf_vport *vport)
  */
 void idpf_vport_intr_deinit(struct idpf_vport *vport)
 {
+	idpf_vport_intr_dis_irq_all(vport);
 	idpf_vport_intr_napi_dis_all(vport);
 	idpf_vport_intr_napi_del_all(vport);
-	idpf_vport_intr_dis_irq_all(vport);
 	idpf_vport_intr_rel_irq(vport);
 }
 
@@ -4179,7 +4179,6 @@ int idpf_vport_intr_init(struct idpf_vport *vport)
 
 	idpf_vport_intr_map_vector_to_qs(vport);
 	idpf_vport_intr_napi_add_all(vport);
-	idpf_vport_intr_napi_ena_all(vport);
 
 	err = vport->adapter->dev_ops.reg_ops.intr_reg_init(vport);
 	if (err)
@@ -4193,17 +4192,20 @@ int idpf_vport_intr_init(struct idpf_vport *vport)
 	if (err)
 		goto unroll_vectors_alloc;
 
-	idpf_vport_intr_ena_irq_all(vport);
-
 	return 0;
 
 unroll_vectors_alloc:
-	idpf_vport_intr_napi_dis_all(vport);
 	idpf_vport_intr_napi_del_all(vport);
 
 	return err;
 }
 
+void idpf_vport_intr_ena(struct idpf_vport *vport)
+{
+	idpf_vport_intr_napi_ena_all(vport);
+	idpf_vport_intr_ena_irq_all(vport);
+}
+
 /**
  * idpf_config_rss - Send virtchnl messages to configure RSS
  * @vport: virtual port
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.h b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
index 3d046b81e507a..551391e204647 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
@@ -990,6 +990,7 @@ int idpf_vport_intr_alloc(struct idpf_vport *vport);
 void idpf_vport_intr_update_itr_ena_irq(struct idpf_q_vector *q_vector);
 void idpf_vport_intr_deinit(struct idpf_vport *vport);
 int idpf_vport_intr_init(struct idpf_vport *vport);
+void idpf_vport_intr_ena(struct idpf_vport *vport);
 enum pkt_hash_types idpf_ptype_to_htype(const struct idpf_rx_ptype_decoded *decoded);
 int idpf_config_rss(struct idpf_vport *vport);
 int idpf_init_rss(struct idpf_vport *vport);
-- 
GitLab


From 82617b9a04649e83ee8731918aeadbb6e6d7cbc7 Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Thu, 23 May 2024 10:45:30 -0700
Subject: [PATCH 316/950] ice: fix accounting if a VLAN already exists

The ice_vsi_add_vlan() function is used to add a VLAN filter for the target
VSI. This function prepares a filter in the switch table for the given VSI.
If it succeeds, the vsi->num_vlan counter is incremented.

It is not considered an error to add a VLAN which already exists in the
switch table, so the function explicitly checks and ignores -EEXIST. The
vsi->num_vlan counter is still incremented.

This seems incorrect, as it means we can double-count in the case where the
same VLAN is added twice by the caller. The actual table will have one less
filter than the count.

The ice_vsi_del_vlan() function similarly checks and handles the -ENOENT
condition for when deleting a filter that doesn't exist. This flow only
decrements the vsi->num_vlan if it actually deleted a filter.

The vsi->num_vlan counter is used only in a few places, primarily related
to tracking the number of non-zero VLANs. If the vsi->num_vlans gets out of
sync, then ice_vsi_num_non_zero_vlans() will incorrectly report more VLANs
than are present, and ice_vsi_has_non_zero_vlans() could return true
potentially in cases where there are only VLAN 0 filters left.

Fix this by only incrementing the vsi->num_vlan in the case where we
actually added an entry, and not in the case where the entry already
existed.

Fixes: a1ffafb0b4a4 ("ice: Support configuring the device to Double VLAN Mode")
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20240523-net-2024-05-23-intel-net-fixes-v1-2-17a923e0bb5f@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c
index 2e9ad27cb9d13..6e8f2aab60801 100644
--- a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c
@@ -45,14 +45,15 @@ int ice_vsi_add_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan)
 		return -EINVAL;
 
 	err = ice_fltr_add_vlan(vsi, vlan);
-	if (err && err != -EEXIST) {
+	if (!err)
+		vsi->num_vlan++;
+	else if (err == -EEXIST)
+		err = 0;
+	else
 		dev_err(ice_pf_to_dev(vsi->back), "Failure Adding VLAN %d on VSI %i, status %d\n",
 			vlan->vid, vsi->vsi_num, err);
-		return err;
-	}
 
-	vsi->num_vlan++;
-	return 0;
+	return err;
 }
 
 /**
-- 
GitLab


From 5597613fb3cf0e36d26cfd8fb2a63196da249333 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Fri, 24 May 2024 18:30:56 +0200
Subject: [PATCH 317/950] selftests: mptcp: lib: support flaky subtests

Some subtests can be unstable, failing once every X runs. Fixing them
can take time: there could be an issue in the kernel or in the subtest,
and it is then important to do a proper analysis, not to hide real bugs.

To avoid creating noises on the different CIs, it is important to have a
simple way to mark subtests as flaky, and ignore the errors. This is
what this patch introduces: subtests can be marked as flaky by setting
MPTCP_LIB_SUBTEST_FLAKY env var to 1, e.g.

  MPTCP_LIB_SUBTEST_FLAKY=1 <run flaky subtest>

The subtest will be executed, and errors (if any) will be ignored. It is
still good to run these subtests, as it exercises code, and the results
can still be useful for the on-going investigations.

Note that the MPTCP CI will continue to track these flaky subtests by
setting SELFTESTS_MPTCP_LIB_OVERRIDE_FLAKY env var to 1, and a ticket
has to be created before marking subtests as flaky.

Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://lore.kernel.org/r/20240524-upstream-net-20240524-selftests-mptcp-flaky-v1-1-a352362f3f8e@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../testing/selftests/net/mptcp/mptcp_lib.sh  | 30 +++++++++++++++++--
 1 file changed, 28 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh
index ad2ebda5cb64b..6ffa9b7a3260d 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh
@@ -21,6 +21,7 @@ declare -rx MPTCP_LIB_AF_INET6=10
 
 MPTCP_LIB_SUBTESTS=()
 MPTCP_LIB_SUBTESTS_DUPLICATED=0
+MPTCP_LIB_SUBTEST_FLAKY=0
 MPTCP_LIB_TEST_COUNTER=0
 MPTCP_LIB_TEST_FORMAT="%02u %-50s"
 MPTCP_LIB_IP_MPTCP=0
@@ -41,6 +42,16 @@ else
 	readonly MPTCP_LIB_COLOR_RESET=
 fi
 
+# SELFTESTS_MPTCP_LIB_OVERRIDE_FLAKY env var can be set not to ignore errors
+# from subtests marked as flaky
+mptcp_lib_override_flaky() {
+	[ "${SELFTESTS_MPTCP_LIB_OVERRIDE_FLAKY:-}" = 1 ]
+}
+
+mptcp_lib_subtest_is_flaky() {
+	[ "${MPTCP_LIB_SUBTEST_FLAKY}" = 1 ] && ! mptcp_lib_override_flaky
+}
+
 # $1: color, $2: text
 mptcp_lib_print_color() {
 	echo -e "${MPTCP_LIB_START_PRINT:-}${*}${MPTCP_LIB_COLOR_RESET}"
@@ -72,7 +83,16 @@ mptcp_lib_pr_skip() {
 }
 
 mptcp_lib_pr_fail() {
-	mptcp_lib_print_err "[FAIL]${1:+ ${*}}"
+	local title cmt
+
+	if mptcp_lib_subtest_is_flaky; then
+		title="IGNO"
+		cmt=" (flaky)"
+	else
+		title="FAIL"
+	fi
+
+	mptcp_lib_print_err "[${title}]${cmt}${1:+ ${*}}"
 }
 
 mptcp_lib_pr_info() {
@@ -208,7 +228,13 @@ mptcp_lib_result_pass() {
 
 # $1: test name
 mptcp_lib_result_fail() {
-	__mptcp_lib_result_add "not ok" "${1}"
+	if mptcp_lib_subtest_is_flaky; then
+		# It might sound better to use 'not ok # TODO' or 'ok # SKIP',
+		# but some CIs don't understand 'TODO' and treat SKIP as errors.
+		__mptcp_lib_result_add "ok" "${1} # IGNORE Flaky"
+	else
+		__mptcp_lib_result_add "not ok" "${1}"
+	fi
 }
 
 # $1: test name
-- 
GitLab


From cc73a6577ae64247898269d138dee6b73ff710cc Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Fri, 24 May 2024 18:30:57 +0200
Subject: [PATCH 318/950] selftests: mptcp: simult flows: mark 'unbalanced'
 tests as flaky

These tests are flaky since their introduction. This might be less or
not visible depending on the CI running the tests, especially if it is
also busy doing other tasks in parallel.

A first analysis shown that the transfer can be slowed down when there
are some re-injections at the MPTCP level. Such re-injections can of
course happen, and disturb the transfer, but it looks strange to have
them in this lab. That could be caused by the kernel having access to
less CPU cycles -- e.g. when other activities are executed in parallel
-- or by a misinterpretation on the MPTCP packet scheduler side.

While this is being investigated, the tests are marked as flaky not to
create noises in other CIs.

Fixes: 219d04992b68 ("mptcp: push pending frames when subflow has free space")
Link: https://github.com/multipath-tcp/mptcp_net-next/issues/475
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://lore.kernel.org/r/20240524-upstream-net-20240524-selftests-mptcp-flaky-v1-2-a352362f3f8e@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/mptcp/simult_flows.sh | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh
index 4b14b4412166b..f74e1c3c126d1 100755
--- a/tools/testing/selftests/net/mptcp/simult_flows.sh
+++ b/tools/testing/selftests/net/mptcp/simult_flows.sh
@@ -244,7 +244,7 @@ run_test()
 	do_transfer $small $large $time
 	lret=$?
 	mptcp_lib_result_code "${lret}" "${msg}"
-	if [ $lret -ne 0 ]; then
+	if [ $lret -ne 0 ] && ! mptcp_lib_subtest_is_flaky; then
 		ret=$lret
 		[ $bail -eq 0 ] || exit $ret
 	fi
@@ -254,7 +254,7 @@ run_test()
 	do_transfer $large $small $time
 	lret=$?
 	mptcp_lib_result_code "${lret}" "${msg}"
-	if [ $lret -ne 0 ]; then
+	if [ $lret -ne 0 ] && ! mptcp_lib_subtest_is_flaky; then
 		ret=$lret
 		[ $bail -eq 0 ] || exit $ret
 	fi
@@ -290,7 +290,7 @@ run_test 10 10 0 0 "balanced bwidth"
 run_test 10 10 1 25 "balanced bwidth with unbalanced delay"
 
 # we still need some additional infrastructure to pass the following test-cases
-run_test 10 3 0 0 "unbalanced bwidth"
+MPTCP_LIB_SUBTEST_FLAKY=1 run_test 10 3 0 0 "unbalanced bwidth"
 run_test 10 3 1 25 "unbalanced bwidth with unbalanced delay"
 run_test 10 3 25 1 "unbalanced bwidth with opposed, unbalanced delay"
 
-- 
GitLab


From 8c06ac2178a9dee887929232226e35a5cdda1793 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Fri, 24 May 2024 18:30:58 +0200
Subject: [PATCH 319/950] selftests: mptcp: join: mark 'fastclose' tests as
 flaky

These tests are flaky since their introduction. This might be less or
not visible depending on the CI running the tests, especially if it is
also busy doing other tasks in parallel, and if a debug kernel config is
being used.

It looks like this issue is often present with the NetDev CI. While this
is being investigated, the tests are marked as flaky not to create
noises on such CIs.

Fixes: 01542c9bf9ab ("selftests: mptcp: add fastclose testcase")
Link: https://github.com/multipath-tcp/mptcp_net-next/issues/324
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://lore.kernel.org/r/20240524-upstream-net-20240524-selftests-mptcp-flaky-v1-3-a352362f3f8e@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/mptcp/mptcp_join.sh | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index fefa9173bdaaa..b869b46823d7a 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -261,6 +261,8 @@ reset()
 
 	TEST_NAME="${1}"
 
+	MPTCP_LIB_SUBTEST_FLAKY=0 # reset if modified
+
 	if skip_test; then
 		MPTCP_LIB_TEST_COUNTER=$((MPTCP_LIB_TEST_COUNTER+1))
 		last_test_ignored=1
@@ -448,7 +450,9 @@ reset_with_tcp_filter()
 # $1: err msg
 fail_test()
 {
-	ret=${KSFT_FAIL}
+	if ! mptcp_lib_subtest_is_flaky; then
+		ret=${KSFT_FAIL}
+	fi
 
 	if [ ${#} -gt 0 ]; then
 		print_fail "${@}"
@@ -3069,6 +3073,7 @@ fullmesh_tests()
 fastclose_tests()
 {
 	if reset_check_counter "fastclose test" "MPTcpExtMPFastcloseTx"; then
+		MPTCP_LIB_SUBTEST_FLAKY=1
 		test_linkfail=1024 fastclose=client \
 			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 0 0 0
@@ -3077,6 +3082,7 @@ fastclose_tests()
 	fi
 
 	if reset_check_counter "fastclose server test" "MPTcpExtMPFastcloseRx"; then
+		MPTCP_LIB_SUBTEST_FLAKY=1
 		test_linkfail=1024 fastclose=server \
 			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 0 0 0 0 0 0 1
-- 
GitLab


From 38af56e6668b455f7dd0a8e2d9afe74100068e17 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Fri, 24 May 2024 18:30:59 +0200
Subject: [PATCH 320/950] selftests: mptcp: join: mark 'fail' tests as flaky

These tests are rarely unstable. It depends on the CI running the tests,
especially if it is also busy doing other tasks in parallel, and if a
debug kernel config is being used.

It looks like this issue is sometimes present with the NetDev CI. While
this is being investigated, the tests are marked as flaky not to create
noises on such CIs.

Fixes: b6e074e171bc ("selftests: mptcp: add infinite map testcase")
Link: https://github.com/multipath-tcp/mptcp_net-next/issues/491
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://lore.kernel.org/r/20240524-upstream-net-20240524-selftests-mptcp-flaky-v1-4-a352362f3f8e@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/mptcp/mptcp_join.sh | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index b869b46823d7a..2b66c5fa71ebf 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -3101,6 +3101,7 @@ fail_tests()
 {
 	# single subflow
 	if reset_with_fail "Infinite map" 1; then
+		MPTCP_LIB_SUBTEST_FLAKY=1
 		test_linkfail=128 \
 			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 0 0 0 +1 +0 1 0 1 "$(pedit_action_pkts)"
@@ -3109,6 +3110,7 @@ fail_tests()
 
 	# multiple subflows
 	if reset_with_fail "MP_FAIL MP_RST" 2; then
+		MPTCP_LIB_SUBTEST_FLAKY=1
 		tc -n $ns2 qdisc add dev ns2eth1 root netem rate 1mbit delay 5ms
 		pm_nl_set_limits $ns1 0 1
 		pm_nl_set_limits $ns2 0 1
-- 
GitLab


From c519cf9b7434183bb56ed1e200ac577a5fd34d9b Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@toblux.com>
Date: Mon, 27 May 2024 12:36:19 +0200
Subject: [PATCH 321/950] docs: netdev: Fix typo in Signed-off-by tag

s/of/off/

Signed-off-by: Thorsten Blum <thorsten.blum@toblux.com>
Fixes: e110ba659271 ("docs: netdev: add note about Changes Requested and revising commit messages")
Link: https://lore.kernel.org/r/20240527103618.265801-2-thorsten.blum@toblux.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/process/maintainer-netdev.rst | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/process/maintainer-netdev.rst b/Documentation/process/maintainer-netdev.rst
index fd96e4a3cef9c..5e1fcfad1c4c3 100644
--- a/Documentation/process/maintainer-netdev.rst
+++ b/Documentation/process/maintainer-netdev.rst
@@ -227,7 +227,7 @@ preferably including links to previous postings, for example::
   The amount of mooing will depend on packet rate so should match
   the diurnal cycle quite well.
 
-  Signed-of-by: Joe Defarmer <joe@barn.org>
+  Signed-off-by: Joe Defarmer <joe@barn.org>
   ---
   v3:
     - add a note about time-of-day mooing fluctuation to the commit message
-- 
GitLab


From 77b79df0268bee3ef38fd5e76e86a076ce02995d Mon Sep 17 00:00:00 2001
From: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Date: Wed, 8 May 2024 20:52:15 +0530
Subject: [PATCH 322/950] drm/xe: Change pcode timeout to 50msec while polling
 again
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Polling is initially attempted with timeout_base_ms enabled for
preemption, and if it exceeds this timeframe, another attempt is made
without preemption, allowing an additional 50 ms before timing out.

v2
- Rebase

v3
- Move warnings to separate patch (Lucas)

Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Fixes: 7dc9b92dcfef ("drm/xe: Remove i915_utils dependency from xe_pcode.")
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240508152216.3263109-2-himal.prasad.ghimiray@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
(cherry picked from commit c81858eb52266b3d6ba28ca4f62a198231a10cdc)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_pcode.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_pcode.c b/drivers/gpu/drm/xe/xe_pcode.c
index c010ef16fbf57..a5e7da8cf9441 100644
--- a/drivers/gpu/drm/xe/xe_pcode.c
+++ b/drivers/gpu/drm/xe/xe_pcode.c
@@ -191,7 +191,7 @@ int xe_pcode_request(struct xe_gt *gt, u32 mbox, u32 request,
 	drm_WARN_ON_ONCE(&gt_to_xe(gt)->drm, timeout_base_ms > 1);
 	preempt_disable();
 	ret = pcode_try_request(gt, mbox, request, reply_mask, reply, &status,
-				true, timeout_base_ms * 1000, true);
+				true, 50 * 1000, true);
 	preempt_enable();
 
 out:
-- 
GitLab


From c8ea2c31f5ea437199b239d76ad5db27343edb0c Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Mon, 15 Apr 2024 12:04:53 -0700
Subject: [PATCH 323/950] drm/xe: Only use reserved BCS instances for usm
 migrate exec queue
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The GuC context scheduling queue is 2 entires deep, thus it is possible
for a migration job to be stuck behind a fault if migration exec queue
shares engines with user jobs. This can deadlock as the migrate exec
queue is required to service page faults. Avoid deadlock by only using
reserved BCS instances for usm migrate exec queue.

Fixes: a043fbab7af5 ("drm/xe/pvc: Use fast copy engines as migrate engine on PVC")
Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: Niranjana Vishwanathapura <niranjana.vishwanathapura@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240415190453.696553-2-matthew.brost@intel.com
Reviewed-by: Brian Welty <brian.welty@intel.com>
(cherry picked from commit 04f4a70a183a688a60fe3882d6e4236ea02cfc67)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_migrate.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index 9f6e9b7f11c84..65e5a3f4c340f 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -34,7 +34,6 @@
 #include "xe_sync.h"
 #include "xe_trace.h"
 #include "xe_vm.h"
-#include "xe_wa.h"
 
 /**
  * struct xe_migrate - migrate context.
@@ -300,10 +299,6 @@ static int xe_migrate_prepare_vm(struct xe_tile *tile, struct xe_migrate *m,
 }
 
 /*
- * Due to workaround 16017236439, odd instance hardware copy engines are
- * faster than even instance ones.
- * This function returns the mask involving all fast copy engines and the
- * reserved copy engine to be used as logical mask for migrate engine.
  * Including the reserved copy engine is required to avoid deadlocks due to
  * migrate jobs servicing the faults gets stuck behind the job that faulted.
  */
@@ -317,8 +312,7 @@ static u32 xe_migrate_usm_logical_mask(struct xe_gt *gt)
 		if (hwe->class != XE_ENGINE_CLASS_COPY)
 			continue;
 
-		if (!XE_WA(gt, 16017236439) ||
-		    xe_gt_is_usm_hwe(gt, hwe) || hwe->instance & 1)
+		if (xe_gt_is_usm_hwe(gt, hwe))
 			logical_mask |= BIT(hwe->logical_instance);
 	}
 
@@ -369,6 +363,10 @@ struct xe_migrate *xe_migrate_init(struct xe_tile *tile)
 		if (!hwe || !logical_mask)
 			return ERR_PTR(-EINVAL);
 
+		/*
+		 * XXX: Currently only reserving 1 (likely slow) BCS instance on
+		 * PVC, may want to revisit if performance is needed.
+		 */
 		m->q = xe_exec_queue_create(xe, vm, logical_mask, 1, hwe,
 					    EXEC_QUEUE_FLAG_KERNEL |
 					    EXEC_QUEUE_FLAG_PERMANENT |
-- 
GitLab


From 6c5cd0807c79eb4c0cda70b48f6be668a241d584 Mon Sep 17 00:00:00 2001
From: Niranjana Vishwanathapura <niranjana.vishwanathapura@intel.com>
Date: Tue, 21 May 2024 13:17:11 -0700
Subject: [PATCH 324/950] drm/xe: Properly handle alloc_guc_id() failure
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Release the submission_state lock if alloc_guc_id() fails.

v2: Add Fixes tag and CC stable kernel

Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Cc: <stable@vger.kernel.org> # v6.8+
Signed-off-by: Niranjana Vishwanathapura <niranjana.vishwanathapura@intel.com>
Reviewed-by: Nirmoy Das <nirmoy.das@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240521201711.4934-1-niranjana.vishwanathapura@intel.com
(cherry picked from commit 40672b792a36894aff3a337b695f6136ee6ac5d4)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_guc_submit.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index c7d38469fb469..e4e3658e6a138 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -1240,6 +1240,7 @@ static int guc_exec_queue_init(struct xe_exec_queue *q)
 	return 0;
 
 err_entity:
+	mutex_unlock(&guc->submission_state.lock);
 	xe_sched_entity_fini(&ge->entity);
 err_sched:
 	xe_sched_fini(&ge->sched);
-- 
GitLab


From 195aba96b854dd664768f382cd1db375d8181f88 Mon Sep 17 00:00:00 2001
From: "Matthew R. Ochs" <mochs@nvidia.com>
Date: Wed, 22 May 2024 15:06:40 +0300
Subject: [PATCH 325/950] tpm_tis_spi: Account for SPI header when allocating
 TPM SPI xfer buffer

The TPM SPI transfer mechanism uses MAX_SPI_FRAMESIZE for computing the
maximum transfer length and the size of the transfer buffer. As such, it
does not account for the 4 bytes of header that prepends the SPI data
frame. This can result in out-of-bounds accesses and was confirmed with
KASAN.

Introduce SPI_HDRSIZE to account for the header and use to allocate the
transfer buffer.

Fixes: a86a42ac2bd6 ("tpm_tis_spi: Add hardware wait polling")
Signed-off-by: Matthew R. Ochs <mochs@nvidia.com>
Tested-by: Carol Soto <csoto@nvidia.com>
Reviewed-by: Jarkko Sakkinen <jarkko@kernel.org>
Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org>
---
 drivers/char/tpm/tpm_tis_spi_main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/char/tpm/tpm_tis_spi_main.c b/drivers/char/tpm/tpm_tis_spi_main.c
index 3f9eaf27b41b8..c9eca24bbad47 100644
--- a/drivers/char/tpm/tpm_tis_spi_main.c
+++ b/drivers/char/tpm/tpm_tis_spi_main.c
@@ -37,6 +37,7 @@
 #include "tpm_tis_spi.h"
 
 #define MAX_SPI_FRAMESIZE 64
+#define SPI_HDRSIZE 4
 
 /*
  * TCG SPI flow control is documented in section 6.4 of the spec[1]. In short,
@@ -247,7 +248,7 @@ static int tpm_tis_spi_write_bytes(struct tpm_tis_data *data, u32 addr,
 int tpm_tis_spi_init(struct spi_device *spi, struct tpm_tis_spi_phy *phy,
 		     int irq, const struct tpm_tis_phy_ops *phy_ops)
 {
-	phy->iobuf = devm_kmalloc(&spi->dev, MAX_SPI_FRAMESIZE, GFP_KERNEL);
+	phy->iobuf = devm_kmalloc(&spi->dev, SPI_HDRSIZE + MAX_SPI_FRAMESIZE, GFP_KERNEL);
 	if (!phy->iobuf)
 		return -ENOMEM;
 
-- 
GitLab


From f3d7ba9e1bc0c9080834f263d4887bd9c9ea491f Mon Sep 17 00:00:00 2001
From: Jarkko Sakkinen <jarkko@kernel.org>
Date: Mon, 27 May 2024 13:56:27 +0300
Subject: [PATCH 326/950] tpm: Open code tpm_buf_parameters()

With only single call site, this makes no sense (slipped out of the
radar during the review). Open code and document the action directly
to the site, to make it more readable.

Fixes: 1b6d7f9eb150 ("tpm: add session encryption protection to tpm2_get_random()")
Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org>
---
 drivers/char/tpm/tpm-buf.c  | 26 --------------------------
 drivers/char/tpm/tpm2-cmd.c | 10 +++++++++-
 include/linux/tpm.h         |  2 --
 3 files changed, 9 insertions(+), 29 deletions(-)

diff --git a/drivers/char/tpm/tpm-buf.c b/drivers/char/tpm/tpm-buf.c
index 647c6ca92ac3c..cad0048bcc3c6 100644
--- a/drivers/char/tpm/tpm-buf.c
+++ b/drivers/char/tpm/tpm-buf.c
@@ -223,30 +223,4 @@ u32 tpm_buf_read_u32(struct tpm_buf *buf, off_t *offset)
 }
 EXPORT_SYMBOL_GPL(tpm_buf_read_u32);
 
-static u16 tpm_buf_tag(struct tpm_buf *buf)
-{
-	struct tpm_header *head = (struct tpm_header *)buf->data;
-
-	return be16_to_cpu(head->tag);
-}
-
-/**
- * tpm_buf_parameters - return the TPM response parameters area of the tpm_buf
- * @buf: tpm_buf to use
- *
- * Where the parameters are located depends on the tag of a TPM
- * command (it's immediately after the header for TPM_ST_NO_SESSIONS
- * or 4 bytes after for TPM_ST_SESSIONS). Evaluate this and return a
- * pointer to the first byte of the parameters area.
- *
- * @return: pointer to parameters area
- */
-u8 *tpm_buf_parameters(struct tpm_buf *buf)
-{
-	int offset = TPM_HEADER_SIZE;
-
-	if (tpm_buf_tag(buf) == TPM2_ST_SESSIONS)
-		offset += 4;
 
-	return &buf->data[offset];
-}
diff --git a/drivers/char/tpm/tpm2-cmd.c b/drivers/char/tpm/tpm2-cmd.c
index 0cdf892ec2a7d..1e856259219e2 100644
--- a/drivers/char/tpm/tpm2-cmd.c
+++ b/drivers/char/tpm/tpm2-cmd.c
@@ -281,6 +281,7 @@ struct tpm2_get_random_out {
 int tpm2_get_random(struct tpm_chip *chip, u8 *dest, size_t max)
 {
 	struct tpm2_get_random_out *out;
+	struct tpm_header *head;
 	struct tpm_buf buf;
 	u32 recd;
 	u32 num_bytes = max;
@@ -288,6 +289,7 @@ int tpm2_get_random(struct tpm_chip *chip, u8 *dest, size_t max)
 	int total = 0;
 	int retries = 5;
 	u8 *dest_ptr = dest;
+	off_t offset;
 
 	if (!num_bytes || max > TPM_MAX_RNG_DATA)
 		return -EINVAL;
@@ -320,7 +322,13 @@ int tpm2_get_random(struct tpm_chip *chip, u8 *dest, size_t max)
 			goto out;
 		}
 
-		out = (struct tpm2_get_random_out *)tpm_buf_parameters(&buf);
+		head = (struct tpm_header *)buf.data;
+		offset = TPM_HEADER_SIZE;
+		/* Skip the parameter size field: */
+		if (be16_to_cpu(head->tag) == TPM2_ST_SESSIONS)
+			offset += 4;
+
+		out = (struct tpm2_get_random_out *)&buf.data[offset];
 		recd = min_t(u32, be16_to_cpu(out->size), num_bytes);
 		if (tpm_buf_length(&buf) <
 		    TPM_HEADER_SIZE +
diff --git a/include/linux/tpm.h b/include/linux/tpm.h
index c17e4efbb2e5c..b3217200df28a 100644
--- a/include/linux/tpm.h
+++ b/include/linux/tpm.h
@@ -437,8 +437,6 @@ u8 tpm_buf_read_u8(struct tpm_buf *buf, off_t *offset);
 u16 tpm_buf_read_u16(struct tpm_buf *buf, off_t *offset);
 u32 tpm_buf_read_u32(struct tpm_buf *buf, off_t *offset);
 
-u8 *tpm_buf_parameters(struct tpm_buf *buf);
-
 /*
  * Check if TPM device is in the firmware upgrade mode.
  */
-- 
GitLab


From d9cbd8343b010016fcaabc361c37720dcafddcbe Mon Sep 17 00:00:00 2001
From: yunshui <jiangyunshui@kylinos.cn>
Date: Thu, 23 May 2024 11:35:20 +0800
Subject: [PATCH 327/950] bpf, net: Use DEV_STAT_INC()

syzbot/KCSAN reported that races happen when multiple CPUs updating
dev->stats.tx_error concurrently. Adopt SMP safe DEV_STATS_INC() to
update the dev->stats fields.

Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: yunshui <jiangyunshui@kylinos.cn>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20240523033520.4029314-1-jiangyunshui@kylinos.cn
---
 net/core/filter.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/core/filter.c b/net/core/filter.c
index c6edfe9f41bcc..7c46ecba3b01b 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2274,12 +2274,12 @@ static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev,
 
 	err = bpf_out_neigh_v6(net, skb, dev, nh);
 	if (unlikely(net_xmit_eval(err)))
-		dev->stats.tx_errors++;
+		DEV_STATS_INC(dev, tx_errors);
 	else
 		ret = NET_XMIT_SUCCESS;
 	goto out_xmit;
 out_drop:
-	dev->stats.tx_errors++;
+	DEV_STATS_INC(dev, tx_errors);
 	kfree_skb(skb);
 out_xmit:
 	return ret;
@@ -2380,12 +2380,12 @@ static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev,
 
 	err = bpf_out_neigh_v4(net, skb, dev, nh);
 	if (unlikely(net_xmit_eval(err)))
-		dev->stats.tx_errors++;
+		DEV_STATS_INC(dev, tx_errors);
 	else
 		ret = NET_XMIT_SUCCESS;
 	goto out_xmit;
 out_drop:
-	dev->stats.tx_errors++;
+	DEV_STATS_INC(dev, tx_errors);
 	kfree_skb(skb);
 out_xmit:
 	return ret;
-- 
GitLab


From 4b4647add7d3c8530493f7247d11e257ee425bf0 Mon Sep 17 00:00:00 2001
From: Thadeu Lima de Souza Cascardo <cascardo@igalia.com>
Date: Fri, 24 May 2024 11:47:02 -0300
Subject: [PATCH 328/950] sock_map: avoid race between sock_map_close and
 sk_psock_put

sk_psock_get will return NULL if the refcount of psock has gone to 0, which
will happen when the last call of sk_psock_put is done. However,
sk_psock_drop may not have finished yet, so the close callback will still
point to sock_map_close despite psock being NULL.

This can be reproduced with a thread deleting an element from the sock map,
while the second one creates a socket, adds it to the map and closes it.

That will trigger the WARN_ON_ONCE:

------------[ cut here ]------------
WARNING: CPU: 1 PID: 7220 at net/core/sock_map.c:1701 sock_map_close+0x2a2/0x2d0 net/core/sock_map.c:1701
Modules linked in:
CPU: 1 PID: 7220 Comm: syz-executor380 Not tainted 6.9.0-syzkaller-07726-g3c999d1ae3c7 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 04/02/2024
RIP: 0010:sock_map_close+0x2a2/0x2d0 net/core/sock_map.c:1701
Code: df e8 92 29 88 f8 48 8b 1b 48 89 d8 48 c1 e8 03 42 80 3c 20 00 74 08 48 89 df e8 79 29 88 f8 4c 8b 23 eb 89 e8 4f 15 23 f8 90 <0f> 0b 90 48 83 c4 08 5b 41 5c 41 5d 41 5e 41 5f 5d e9 13 26 3d 02
RSP: 0018:ffffc9000441fda8 EFLAGS: 00010293
RAX: ffffffff89731ae1 RBX: ffffffff94b87540 RCX: ffff888029470000
RDX: 0000000000000000 RSI: ffffffff8bcab5c0 RDI: ffffffff8c1faba0
RBP: 0000000000000000 R08: ffffffff92f9b61f R09: 1ffffffff25f36c3
R10: dffffc0000000000 R11: fffffbfff25f36c4 R12: ffffffff89731840
R13: ffff88804b587000 R14: ffff88804b587000 R15: ffffffff89731870
FS:  000055555e080380(0000) GS:ffff8880b9500000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000000000000 CR3: 00000000207d4000 CR4: 0000000000350ef0
Call Trace:
 <TASK>
 unix_release+0x87/0xc0 net/unix/af_unix.c:1048
 __sock_release net/socket.c:659 [inline]
 sock_close+0xbe/0x240 net/socket.c:1421
 __fput+0x42b/0x8a0 fs/file_table.c:422
 __do_sys_close fs/open.c:1556 [inline]
 __se_sys_close fs/open.c:1541 [inline]
 __x64_sys_close+0x7f/0x110 fs/open.c:1541
 do_syscall_x64 arch/x86/entry/common.c:52 [inline]
 do_syscall_64+0xf5/0x240 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
RIP: 0033:0x7fb37d618070
Code: 00 00 48 c7 c2 b8 ff ff ff f7 d8 64 89 02 b8 ff ff ff ff eb d4 e8 10 2c 00 00 80 3d 31 f0 07 00 00 74 17 b8 03 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 48 c3 0f 1f 80 00 00 00 00 48 83 ec 18 89 7c
RSP: 002b:00007ffcd4a525d8 EFLAGS: 00000202 ORIG_RAX: 0000000000000003
RAX: ffffffffffffffda RBX: 0000000000000005 RCX: 00007fb37d618070
RDX: 0000000000000010 RSI: 00000000200001c0 RDI: 0000000000000004
RBP: 0000000000000000 R08: 0000000100000000 R09: 0000000100000000
R10: 0000000000000000 R11: 0000000000000202 R12: 0000000000000000
R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000
 </TASK>

Use sk_psock, which will only check that the pointer is not been set to
NULL yet, which should only happen after the callbacks are restored. If,
then, a reference can still be gotten, we may call sk_psock_stop and cancel
psock->work.

As suggested by Paolo Abeni, reorder the condition so the control flow is
less convoluted.

After that change, the reproducer does not trigger the WARN_ON_ONCE
anymore.

Suggested-by: Paolo Abeni <pabeni@redhat.com>
Reported-by: syzbot+07a2e4a1a57118ef7355@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=07a2e4a1a57118ef7355
Fixes: aadb2bb83ff7 ("sock_map: Fix a potential use-after-free in sock_map_close()")
Fixes: 5b4a79ba65a1 ("bpf, sockmap: Don't let sock_map_{close,destroy,unhash} call itself")
Cc: stable@vger.kernel.org
Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@igalia.com>
Acked-by: Jakub Sitnicki <jakub@cloudflare.com>
Link: https://lore.kernel.org/r/20240524144702.1178377-1-cascardo@igalia.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/core/sock_map.c | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 63c016b4c1696..d3dbb92153f2f 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -1674,19 +1674,23 @@ void sock_map_close(struct sock *sk, long timeout)
 
 	lock_sock(sk);
 	rcu_read_lock();
-	psock = sk_psock_get(sk);
-	if (unlikely(!psock)) {
-		rcu_read_unlock();
-		release_sock(sk);
-		saved_close = READ_ONCE(sk->sk_prot)->close;
-	} else {
+	psock = sk_psock(sk);
+	if (likely(psock)) {
 		saved_close = psock->saved_close;
 		sock_map_remove_links(sk, psock);
+		psock = sk_psock_get(sk);
+		if (unlikely(!psock))
+			goto no_psock;
 		rcu_read_unlock();
 		sk_psock_stop(psock);
 		release_sock(sk);
 		cancel_delayed_work_sync(&psock->work);
 		sk_psock_put(sk, psock);
+	} else {
+		saved_close = READ_ONCE(sk->sk_prot)->close;
+no_psock:
+		rcu_read_unlock();
+		release_sock(sk);
 	}
 
 	/* Make sure we do not recurse. This is a bug.
-- 
GitLab


From f09fc6cee0dcfc38148ee6b6dd04f93e353d22f2 Mon Sep 17 00:00:00 2001
From: Jarkko Sakkinen <jarkko@kernel.org>
Date: Tue, 28 May 2024 12:52:21 +0300
Subject: [PATCH 329/950] tpm: Rename TPM2_OA_TMPL to TPM2_OA_NULL_KEY and make
 it local

Rename and document TPM2_OA_TMPL, as originally requested in the patch
set review, but left unaddressed without any appropriate reasoning. The
new name is TPM2_OA_NULL_KEY, has a documentation and is local only to
tpm2-sessions.c.

Link: https://lore.kernel.org/linux-integrity/ddbeb8111f48a8ddb0b8fca248dff6cc9d7079b2.camel@HansenPartnership.com/
Link: https://lore.kernel.org/linux-integrity/CZCKTWU6ZCC9.2UTEQPEVICYHL@suppilovahvero/
Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org>
---
 drivers/char/tpm/tpm2-sessions.c | 21 +++++++++++++++++++--
 include/linux/tpm.h              | 15 ---------------
 2 files changed, 19 insertions(+), 17 deletions(-)

diff --git a/drivers/char/tpm/tpm2-sessions.c b/drivers/char/tpm/tpm2-sessions.c
index ea8860661876e..907ac9956a78f 100644
--- a/drivers/char/tpm/tpm2-sessions.c
+++ b/drivers/char/tpm/tpm2-sessions.c
@@ -80,6 +80,9 @@
 /* maximum number of names the TPM must remember for authorization */
 #define AUTH_MAX_NAMES	3
 
+#define AES_KEY_BYTES	AES_KEYSIZE_128
+#define AES_KEY_BITS	(AES_KEY_BYTES*8)
+
 static int tpm2_create_primary(struct tpm_chip *chip, u32 hierarchy,
 			       u32 *handle, u8 *name);
 
@@ -954,6 +957,20 @@ int tpm2_start_auth_session(struct tpm_chip *chip)
 }
 EXPORT_SYMBOL(tpm2_start_auth_session);
 
+/*
+ * A mask containing the object attributes for the kernel held null primary key
+ * used in HMAC encryption. For more information on specific attributes look up
+ * to "8.3 TPMA_OBJECT (Object Attributes)".
+ */
+#define TPM2_OA_NULL_KEY ( \
+	TPM2_OA_NO_DA | \
+	TPM2_OA_FIXED_TPM | \
+	TPM2_OA_FIXED_PARENT | \
+	TPM2_OA_SENSITIVE_DATA_ORIGIN |	\
+	TPM2_OA_USER_WITH_AUTH | \
+	TPM2_OA_DECRYPT | \
+	TPM2_OA_RESTRICTED)
+
 /**
  * tpm2_parse_create_primary() - parse the data returned from TPM_CC_CREATE_PRIMARY
  *
@@ -1018,7 +1035,7 @@ static int tpm2_parse_create_primary(struct tpm_chip *chip, struct tpm_buf *buf,
 	val = tpm_buf_read_u32(buf, &offset_t);
 
 	/* object properties */
-	if (val != TPM2_OA_TMPL)
+	if (val != TPM2_OA_NULL_KEY)
 		return -EINVAL;
 
 	/* auth policy (empty) */
@@ -1178,7 +1195,7 @@ static int tpm2_create_primary(struct tpm_chip *chip, u32 hierarchy,
 	tpm_buf_append_u16(&template, TPM_ALG_SHA256);
 
 	/* object properties */
-	tpm_buf_append_u32(&template, TPM2_OA_TMPL);
+	tpm_buf_append_u32(&template, TPM2_OA_NULL_KEY);
 
 	/* sauth policy (empty) */
 	tpm_buf_append_u16(&template, 0);
diff --git a/include/linux/tpm.h b/include/linux/tpm.h
index b3217200df28a..21a67dc9efe80 100644
--- a/include/linux/tpm.h
+++ b/include/linux/tpm.h
@@ -394,21 +394,6 @@ enum tpm2_object_attributes {
 	TPM2_OA_SIGN			= BIT(18),
 };
 
-/*
- * definitions for the canonical template.  These are mandated
- * by the TCG key template documents
- */
-
-#define AES_KEY_BYTES	AES_KEYSIZE_128
-#define AES_KEY_BITS	(AES_KEY_BYTES*8)
-#define TPM2_OA_TMPL	(TPM2_OA_NO_DA |			\
-			 TPM2_OA_FIXED_TPM |			\
-			 TPM2_OA_FIXED_PARENT |			\
-			 TPM2_OA_SENSITIVE_DATA_ORIGIN |	\
-			 TPM2_OA_USER_WITH_AUTH |		\
-			 TPM2_OA_DECRYPT |			\
-			 TPM2_OA_RESTRICTED)
-
 enum tpm2_session_attributes {
 	TPM2_SA_CONTINUE_SESSION	= BIT(0),
 	TPM2_SA_AUDIT_EXCLUSIVE		= BIT(1),
-- 
GitLab


From d3e43a8fa43effdbb62c7edc206df7ac67772205 Mon Sep 17 00:00:00 2001
From: Jarkko Sakkinen <jarkko@kernel.org>
Date: Tue, 28 May 2024 12:58:41 +0300
Subject: [PATCH 330/950] tpm: Enable TCG_TPM2_HMAC by default only for X86_64

Given the not fully root caused performance issues on non-x86 platforms,
enable the feature by default only for x86-64. That is the platform it
brings the most value and has gone most of the QA. Can be reconsidered
later and can be obviously opt-in enabled too on any arch.

Link: https://lore.kernel.org/linux-integrity/bf67346ef623ff3c452c4f968b7d900911e250c3.camel@gmail.com/#t
Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org>
---
 drivers/char/tpm/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/char/tpm/Kconfig b/drivers/char/tpm/Kconfig
index e63a6a17793c8..cf0be8a7939de 100644
--- a/drivers/char/tpm/Kconfig
+++ b/drivers/char/tpm/Kconfig
@@ -29,7 +29,7 @@ if TCG_TPM
 
 config TCG_TPM2_HMAC
 	bool "Use HMAC and encrypted transactions on the TPM bus"
-	default y
+	default X86_64
 	select CRYPTO_ECDH
 	select CRYPTO_LIB_AESCFB
 	select CRYPTO_LIB_SHA256
-- 
GitLab


From 8a42886cae307663f3f999846926bd6e64392000 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Mon, 27 May 2024 17:18:49 +0200
Subject: [PATCH 331/950] ALSA: seq: Fix missing bank setup between MIDI1/MIDI2
 UMP conversion

When a UMP packet is converted between MIDI1 and MIDI2 protocols, the
bank selection may be lost.  The conversion from MIDI1 to MIDI2 needs
the encoding of the bank into UMP_MSG_STATUS_PROGRAM bits, while the
conversion from MIDI2 to MIDI1 needs the extraction from that
instead.

This patch implements the missing bank selection mechanism in those
conversions.

Fixes: e9e02819a98a ("ALSA: seq: Automatic conversion of UMP events")
Link: https://lore.kernel.org/r/20240527151852.29036-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/core/seq/seq_ump_convert.c | 38 ++++++++++++++++++++++++++++++++
 1 file changed, 38 insertions(+)

diff --git a/sound/core/seq/seq_ump_convert.c b/sound/core/seq/seq_ump_convert.c
index ee6ac649df836..c21be87f5da9e 100644
--- a/sound/core/seq/seq_ump_convert.c
+++ b/sound/core/seq/seq_ump_convert.c
@@ -368,6 +368,7 @@ static int cvt_ump_midi1_to_midi2(struct snd_seq_client *dest,
 	struct snd_seq_ump_event ev_cvt;
 	const union snd_ump_midi1_msg *midi1 = (const union snd_ump_midi1_msg *)event->ump;
 	union snd_ump_midi2_msg *midi2 = (union snd_ump_midi2_msg *)ev_cvt.ump;
+	struct snd_seq_ump_midi2_bank *cc;
 
 	ev_cvt = *event;
 	memset(&ev_cvt.ump, 0, sizeof(ev_cvt.ump));
@@ -387,11 +388,29 @@ static int cvt_ump_midi1_to_midi2(struct snd_seq_client *dest,
 		midi2->paf.data = upscale_7_to_32bit(midi1->paf.data);
 		break;
 	case UMP_MSG_STATUS_CC:
+		cc = &dest_port->midi2_bank[midi1->note.channel];
+		switch (midi1->cc.index) {
+		case UMP_CC_BANK_SELECT:
+			cc->bank_set = 1;
+			cc->cc_bank_msb = midi1->cc.data;
+			return 0; // skip
+		case UMP_CC_BANK_SELECT_LSB:
+			cc->bank_set = 1;
+			cc->cc_bank_lsb = midi1->cc.data;
+			return 0; // skip
+		}
 		midi2->cc.index = midi1->cc.index;
 		midi2->cc.data = upscale_7_to_32bit(midi1->cc.data);
 		break;
 	case UMP_MSG_STATUS_PROGRAM:
 		midi2->pg.program = midi1->pg.program;
+		cc = &dest_port->midi2_bank[midi1->note.channel];
+		if (cc->bank_set) {
+			midi2->pg.bank_valid = 1;
+			midi2->pg.bank_msb = cc->cc_bank_msb;
+			midi2->pg.bank_lsb = cc->cc_bank_lsb;
+			cc->bank_set = 0;
+		}
 		break;
 	case UMP_MSG_STATUS_CHANNEL_PRESSURE:
 		midi2->caf.data = upscale_7_to_32bit(midi1->caf.data);
@@ -419,6 +438,7 @@ static int cvt_ump_midi2_to_midi1(struct snd_seq_client *dest,
 	struct snd_seq_ump_event ev_cvt;
 	union snd_ump_midi1_msg *midi1 = (union snd_ump_midi1_msg *)ev_cvt.ump;
 	const union snd_ump_midi2_msg *midi2 = (const union snd_ump_midi2_msg *)event->ump;
+	int err;
 	u16 v;
 
 	ev_cvt = *event;
@@ -443,6 +463,24 @@ static int cvt_ump_midi2_to_midi1(struct snd_seq_client *dest,
 		midi1->cc.data = downscale_32_to_7bit(midi2->cc.data);
 		break;
 	case UMP_MSG_STATUS_PROGRAM:
+		if (midi2->pg.bank_valid) {
+			midi1->cc.status = UMP_MSG_STATUS_CC;
+			midi1->cc.index = UMP_CC_BANK_SELECT;
+			midi1->cc.data = midi2->pg.bank_msb;
+			err = __snd_seq_deliver_single_event(dest, dest_port,
+							     (struct snd_seq_event *)&ev_cvt,
+							     atomic, hop);
+			if (err < 0)
+				return err;
+			midi1->cc.index = UMP_CC_BANK_SELECT_LSB;
+			midi1->cc.data = midi2->pg.bank_lsb;
+			err = __snd_seq_deliver_single_event(dest, dest_port,
+							     (struct snd_seq_event *)&ev_cvt,
+							     atomic, hop);
+			if (err < 0)
+				return err;
+			midi1->note.status = midi2->note.status;
+		}
 		midi1->pg.program = midi2->pg.program;
 		break;
 	case UMP_MSG_STATUS_CHANNEL_PRESSURE:
-- 
GitLab


From a200df7deb3186cd7b55abb77ab96dfefb8a4f09 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Mon, 27 May 2024 17:18:50 +0200
Subject: [PATCH 332/950] ALSA: seq: Don't clear bank selection at event -> UMP
 MIDI2 conversion

The current code to convert from a legacy sequencer event to UMP MIDI2
clears the bank selection at each time the program change is
submitted.  This is confusing and may lead to incorrect bank values
tranmitted to the destination in the end.

Drop the line to clear the bank info and keep the provided values.

Fixes: e9e02819a98a ("ALSA: seq: Automatic conversion of UMP events")
Link: https://lore.kernel.org/r/20240527151852.29036-2-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/core/seq/seq_ump_convert.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/sound/core/seq/seq_ump_convert.c b/sound/core/seq/seq_ump_convert.c
index c21be87f5da9e..f5d22dd008426 100644
--- a/sound/core/seq/seq_ump_convert.c
+++ b/sound/core/seq/seq_ump_convert.c
@@ -892,7 +892,6 @@ static int pgm_ev_to_ump_midi2(const struct snd_seq_event *event,
 		data->pg.bank_msb = cc->cc_bank_msb;
 		data->pg.bank_lsb = cc->cc_bank_lsb;
 		cc->bank_set = 0;
-		cc->cc_bank_msb = cc->cc_bank_lsb = 0;
 	}
 	return 1;
 }
-- 
GitLab


From e662c90a6debc3bd8d8eff916ad21d9ec458dfcd Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Mon, 27 May 2024 14:38:08 -0500
Subject: [PATCH 333/950] ALSA/hda: intel-dsp-config: reduce log verbosity

The information on PCI class/subclass was interesting in the Skylake
timeframe, since the DSP was only enabled on a limited number of
platforms. Now most Intel platforms do enable the DSP, so the
information is less interesting to log.

When a DSP driver is used, the common helper may be called multiple
times due to deferred probes, but there's no reason to print the same
information multiple times. Using dev_info_once() covers all the
existing usages for internal cards with DSPs. External cards don't
rely on DSPs so far.

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Reviewed-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://lore.kernel.org/r/20240527193808.165652-1-pierre-louis.bossart@linux.intel.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/intel-dsp-config.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/sound/hda/intel-dsp-config.c b/sound/hda/intel-dsp-config.c
index cfdb1b73c88c2..537863447358e 100644
--- a/sound/hda/intel-dsp-config.c
+++ b/sound/hda/intel-dsp-config.c
@@ -668,7 +668,7 @@ int snd_intel_dsp_driver_probe(struct pci_dev *pci)
 		return SND_INTEL_DSP_DRIVER_LEGACY;
 	}
 
-	dev_info(&pci->dev, "DSP detected with PCI class/subclass/prog-if info 0x%06x\n", pci->class);
+	dev_dbg(&pci->dev, "DSP detected with PCI class/subclass/prog-if info 0x%06x\n", pci->class);
 
 	/* find the configuration for the specific device */
 	cfg = snd_intel_dsp_find_config(pci, config_table, ARRAY_SIZE(config_table));
@@ -678,12 +678,12 @@ int snd_intel_dsp_driver_probe(struct pci_dev *pci)
 	if (cfg->flags & FLAG_SOF) {
 		if (cfg->flags & FLAG_SOF_ONLY_IF_SOUNDWIRE &&
 		    snd_intel_dsp_check_soundwire(pci) > 0) {
-			dev_info(&pci->dev, "SoundWire enabled on CannonLake+ platform, using SOF driver\n");
+			dev_info_once(&pci->dev, "SoundWire enabled on CannonLake+ platform, using SOF driver\n");
 			return SND_INTEL_DSP_DRIVER_SOF;
 		}
 		if (cfg->flags & FLAG_SOF_ONLY_IF_DMIC &&
 		    snd_intel_dsp_check_dmic(pci)) {
-			dev_info(&pci->dev, "Digital mics found on Skylake+ platform, using SOF driver\n");
+			dev_info_once(&pci->dev, "Digital mics found on Skylake+ platform, using SOF driver\n");
 			return SND_INTEL_DSP_DRIVER_SOF;
 		}
 		if (!(cfg->flags & FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE))
@@ -694,7 +694,7 @@ int snd_intel_dsp_driver_probe(struct pci_dev *pci)
 	if (cfg->flags & FLAG_SST) {
 		if (cfg->flags & FLAG_SST_ONLY_IF_DMIC) {
 			if (snd_intel_dsp_check_dmic(pci)) {
-				dev_info(&pci->dev, "Digital mics found on Skylake+ platform, using SST driver\n");
+				dev_info_once(&pci->dev, "Digital mics found on Skylake+ platform, using SST driver\n");
 				return SND_INTEL_DSP_DRIVER_SST;
 			}
 		} else {
-- 
GitLab


From c65b6521115ed478471bf8c4a3687059fcea01aa Mon Sep 17 00:00:00 2001
From: Gou Hao <gouhao@uniontech.com>
Date: Sun, 26 May 2024 22:57:17 +0800
Subject: [PATCH 334/950] net/core: remove redundant sk_callback_lock
 initialization

sk_callback_lock has already been initialized in sk_init_common().

Signed-off-by: Gou Hao <gouhao@uniontech.com>
Reviewed-by: Breno Leitao <leitao@debian.org>
Link: https://lore.kernel.org/r/20240526145718.9542-1-gouhao@uniontech.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/core/sock.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/core/sock.c b/net/core/sock.c
index 8629f9aecf91a..67b10954e0cfb 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -3460,7 +3460,6 @@ void sock_init_data_uid(struct socket *sock, struct sock *sk, kuid_t uid)
 	}
 	sk->sk_uid	=	uid;
 
-	rwlock_init(&sk->sk_callback_lock);
 	if (sk->sk_kern_sock)
 		lockdep_set_class_and_name(
 			&sk->sk_callback_lock,
-- 
GitLab


From de31e96cf423848a1d541142446801430c12da3c Mon Sep 17 00:00:00 2001
From: Gou Hao <gouhao@uniontech.com>
Date: Sun, 26 May 2024 22:57:18 +0800
Subject: [PATCH 335/950] net/core: move the lockdep-init of sk_callback_lock
 to sk_init_common()

In commit cdfbabfb2f0c ("net: Work around lockdep limitation in
sockets that use sockets"), it introduces 'af_kern_callback_keys'
to lockdep-init of sk_callback_lock according to 'sk_kern_sock',
it modifies sock_init_data() only, and sk_clone_lock() calls
sk_init_common() to initialize sk_callback_lock too, so the
lockdep-init of sk_callback_lock should be moved to sk_init_common().

Signed-off-by: Gou Hao <gouhao@uniontech.com>
Link: https://lore.kernel.org/r/20240526145718.9542-2-gouhao@uniontech.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/core/sock.c | 18 ++++++------------
 1 file changed, 6 insertions(+), 12 deletions(-)

diff --git a/net/core/sock.c b/net/core/sock.c
index 67b10954e0cfb..521e6373d4f73 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2262,7 +2262,12 @@ static void sk_init_common(struct sock *sk)
 	lockdep_set_class_and_name(&sk->sk_error_queue.lock,
 			af_elock_keys + sk->sk_family,
 			af_family_elock_key_strings[sk->sk_family]);
-	lockdep_set_class_and_name(&sk->sk_callback_lock,
+	if (sk->sk_kern_sock)
+		lockdep_set_class_and_name(&sk->sk_callback_lock,
+			af_kern_callback_keys + sk->sk_family,
+			af_family_kern_clock_key_strings[sk->sk_family]);
+	else
+		lockdep_set_class_and_name(&sk->sk_callback_lock,
 			af_callback_keys + sk->sk_family,
 			af_family_clock_key_strings[sk->sk_family]);
 }
@@ -3460,17 +3465,6 @@ void sock_init_data_uid(struct socket *sock, struct sock *sk, kuid_t uid)
 	}
 	sk->sk_uid	=	uid;
 
-	if (sk->sk_kern_sock)
-		lockdep_set_class_and_name(
-			&sk->sk_callback_lock,
-			af_kern_callback_keys + sk->sk_family,
-			af_family_kern_clock_key_strings[sk->sk_family]);
-	else
-		lockdep_set_class_and_name(
-			&sk->sk_callback_lock,
-			af_callback_keys + sk->sk_family,
-			af_family_clock_key_strings[sk->sk_family]);
-
 	sk->sk_state_change	=	sock_def_wakeup;
 	sk->sk_data_ready	=	sock_def_readable;
 	sk->sk_write_space	=	sock_def_write_space;
-- 
GitLab


From 72b6a2d6506843375c7b91197f49ef38ca0c6d0f Mon Sep 17 00:00:00 2001
From: Alina Yu <alina_yu@richtek.com>
Date: Tue, 28 May 2024 14:01:13 +0800
Subject: [PATCH 336/950] regulator: rtq2208: Fix invalid memory access when
 devm_of_regulator_put_matches is called

In this patch, a software bug has been fixed.
rtq2208_ldo_match is no longer a local variable.
It prevents invalid memory access when devm_of_regulator_put_matches
 is called.

Signed-off-by: Alina Yu <alina_yu@richtek.com>
Link: https://msgid.link/r/4ce8c4f16f1cf3aa4e5f36c0694dd3c5ccf3cd1c.1716870419.git.alina_yu@richtek.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/rtq2208-regulator.c | 22 ++++++++++++----------
 1 file changed, 12 insertions(+), 10 deletions(-)

diff --git a/drivers/regulator/rtq2208-regulator.c b/drivers/regulator/rtq2208-regulator.c
index b90e53d922d6d..c31b6dc3229ca 100644
--- a/drivers/regulator/rtq2208-regulator.c
+++ b/drivers/regulator/rtq2208-regulator.c
@@ -228,6 +228,11 @@ static const struct regulator_ops rtq2208_regulator_ldo_ops = {
 	.set_suspend_disable = rtq2208_set_suspend_disable,
 };
 
+static struct of_regulator_match rtq2208_ldo_match[] = {
+	{.name = "ldo2", },
+	{.name = "ldo1", },
+};
+
 static unsigned int rtq2208_of_map_mode(unsigned int mode)
 {
 	switch (mode) {
@@ -322,8 +327,7 @@ static irqreturn_t rtq2208_irq_handler(int irqno, void *devid)
 	return IRQ_HANDLED;
 }
 
-static int rtq2208_of_get_fixed_voltage(struct device *dev,
-					struct of_regulator_match *rtq2208_ldo_match, int n_fixed)
+static int rtq2208_of_get_ldo_dvs_ability(struct device *dev)
 {
 	struct device_node *np;
 	struct of_regulator_match *match;
@@ -338,14 +342,14 @@ static int rtq2208_of_get_fixed_voltage(struct device *dev,
 	if (!np)
 		np = dev->of_node;
 
-	ret = of_regulator_match(dev, np, rtq2208_ldo_match, n_fixed);
+	ret = of_regulator_match(dev, np, rtq2208_ldo_match, ARRAY_SIZE(rtq2208_ldo_match));
 
 	of_node_put(np);
 
 	if (ret < 0)
 		return ret;
 
-	for (i = 0; i < n_fixed; i++) {
+	for (i = 0; i < ARRAY_SIZE(rtq2208_ldo_match); i++) {
 		match = rtq2208_ldo_match + i;
 		init_data = match->init_data;
 		rdesc = (struct rtq2208_regulator_desc *)match->driver_data;
@@ -388,8 +392,7 @@ static const struct linear_range rtq2208_vout_range[] = {
 	REGULATOR_LINEAR_RANGE(1310000, 181, 255, 10000),
 };
 
-static void rtq2208_init_regulator_desc(struct rtq2208_regulator_desc *rdesc, int mtp_sel,
-					int idx, struct of_regulator_match *rtq2208_ldo_match, int *ldo_idx)
+static void rtq2208_init_regulator_desc(struct rtq2208_regulator_desc *rdesc, int mtp_sel, int idx)
 {
 	struct regulator_desc *desc;
 	static const struct {
@@ -461,8 +464,7 @@ static void rtq2208_init_regulator_desc(struct rtq2208_regulator_desc *rdesc, in
 static int rtq2208_parse_regulator_dt_data(int n_regulator, const unsigned int *regulator_idx_table,
 		struct rtq2208_regulator_desc *rdesc[RTQ2208_LDO_MAX], struct device *dev)
 {
-	struct of_regulator_match rtq2208_ldo_match[2];
-	int mtp_sel, ret, i, idx, ldo_idx = 0;
+	int mtp_sel, i, idx, ret;
 
 	/* get mtp_sel0 or mtp_sel1 */
 	mtp_sel = device_property_read_bool(dev, "richtek,mtp-sel-high");
@@ -474,7 +476,7 @@ static int rtq2208_parse_regulator_dt_data(int n_regulator, const unsigned int *
 		if (!rdesc[i])
 			return -ENOMEM;
 
-		rtq2208_init_regulator_desc(rdesc[i], mtp_sel, idx, rtq2208_ldo_match, &ldo_idx);
+		rtq2208_init_regulator_desc(rdesc[i], mtp_sel, idx);
 
 		/* init ldo dvs ability */
 		if (idx >= RTQ2208_LDO2)
@@ -482,7 +484,7 @@ static int rtq2208_parse_regulator_dt_data(int n_regulator, const unsigned int *
 	}
 
 	/* init ldo fixed_uV */
-	ret = rtq2208_of_get_fixed_voltage(dev, rtq2208_ldo_match, ldo_idx);
+	ret = rtq2208_of_get_ldo_dvs_ability(dev);
 	if (ret)
 		return dev_err_probe(dev, ret, "Failed to get ldo fixed_uV\n");
 
-- 
GitLab


From 233e27b4d21c3e44eb863f03e566d3a22e81a7ae Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Tue, 28 May 2024 15:28:52 +0900
Subject: [PATCH 337/950] null_blk: Print correct max open zones limit in
 null_init_zoned_dev()

When changing the maximum number of open zones, print that number
instead of the total number of zones.

Fixes: dc4d137ee3b7 ("null_blk: add support for max open/active zone limit for zoned devices")
Cc: stable@vger.kernel.org
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Niklas Cassel <cassel@kernel.org>
Link: https://lore.kernel.org/r/20240528062852.437599-1-dlemoal@kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/null_blk/zoned.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/block/null_blk/zoned.c b/drivers/block/null_blk/zoned.c
index 5b5a63adacc17..79c8e5e99f7ff 100644
--- a/drivers/block/null_blk/zoned.c
+++ b/drivers/block/null_blk/zoned.c
@@ -108,7 +108,7 @@ int null_init_zoned_dev(struct nullb_device *dev,
 	if (dev->zone_max_active && dev->zone_max_open > dev->zone_max_active) {
 		dev->zone_max_open = dev->zone_max_active;
 		pr_info("changed the maximum number of open zones to %u\n",
-			dev->nr_zones);
+			dev->zone_max_open);
 	} else if (dev->zone_max_open >= dev->nr_zones - dev->zone_nr_conv) {
 		dev->zone_max_open = 0;
 		pr_info("zone_max_open limit disabled, limit >= zone count\n");
-- 
GitLab


From bafea1c58b24be594d97841ced1b7ae0347bf6e3 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 23 May 2024 20:26:13 +0200
Subject: [PATCH 338/950] sd: also set max_user_sectors when setting
 max_sectors

sd can set a max_sectors value that is lower than the max_hw_sectors
limit based on the block limits VPD page.   While this is rather unusual,
it used to work until the max_user_sectors field was split out to cleanly
deal with conflicting hardware and user limits when the hardware limit
changes.  Also set max_user_sectors to ensure the limit can properly be
stacked.

Fixes: 4f563a64732d ("block: add a max_user_discard_sectors queue limit")
Reported-by: Mike Snitzer <snitzer@kernel.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Mike Snitzer <snitzer@kernel.org>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Link: https://lore.kernel.org/r/20240523182618.602003-2-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/scsi/sd.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 332eb9dac22d9..f6c822c9cbd2d 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -3700,8 +3700,10 @@ static int sd_revalidate_disk(struct gendisk *disk)
 	 */
 	if (sdkp->first_scan ||
 	    q->limits.max_sectors > q->limits.max_dev_sectors ||
-	    q->limits.max_sectors > q->limits.max_hw_sectors)
+	    q->limits.max_sectors > q->limits.max_hw_sectors) {
 		q->limits.max_sectors = rw_max;
+		q->limits.max_user_sectors = rw_max;
+	}
 
 	sdkp->first_scan = 0;
 
-- 
GitLab


From e528bede6f4e6822afdf0fa80be46ea9199f0911 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 23 May 2024 20:26:14 +0200
Subject: [PATCH 339/950] block: stack max_user_sectors

The max_user_sectors is one of the three factors determining the actual
max_sectors limit for READ/WRITE requests.  Because of that it needs to
be stacked at least for the device mapper multi-path case where requests
are directly inserted on the lower device.  For SCSI disks this is
important because the sd driver actually sets it's own advisory limit
that is lower than max_hw_sectors based on the block limits VPD page.
While this is a bit odd an unusual, the same effect can happen if a
user or udev script tweaks the value manually.

Fixes: 4f563a64732d ("block: add a max_user_discard_sectors queue limit")
Reported-by: Mike Snitzer <snitzer@kernel.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Mike Snitzer <snitzer@kernel.org>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Link: https://lore.kernel.org/r/20240523182618.602003-3-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-settings.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/block/blk-settings.c b/block/blk-settings.c
index a7fe8e90240a6..7a672021daee6 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -611,6 +611,8 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 	unsigned int top, bottom, alignment, ret = 0;
 
 	t->max_sectors = min_not_zero(t->max_sectors, b->max_sectors);
+	t->max_user_sectors = min_not_zero(t->max_user_sectors,
+			b->max_user_sectors);
 	t->max_hw_sectors = min_not_zero(t->max_hw_sectors, b->max_hw_sectors);
 	t->max_dev_sectors = min_not_zero(t->max_dev_sectors, b->max_dev_sectors);
 	t->max_write_zeroes_sectors = min(t->max_write_zeroes_sectors,
-- 
GitLab


From e993db2d6e5207f1ae061c2ac554ab1f714c741d Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@kernel.org>
Date: Fri, 24 May 2024 12:46:51 +0200
Subject: [PATCH 340/950] block: check for max_hw_sectors underflow

The logical block size need to be smaller than the max_hw_sector
setting, otherwise we can't even transfer a single LBA.

Signed-off-by: Hannes Reinecke <hare@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: John Garry <john.g.garry@oracle.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-settings.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/block/blk-settings.c b/block/blk-settings.c
index 7a672021daee6..effeb9a639bb4 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -104,6 +104,7 @@ static int blk_validate_zoned_limits(struct queue_limits *lim)
 static int blk_validate_limits(struct queue_limits *lim)
 {
 	unsigned int max_hw_sectors;
+	unsigned int logical_block_sectors;
 
 	/*
 	 * Unless otherwise specified, default to 512 byte logical blocks and a
@@ -134,8 +135,11 @@ static int blk_validate_limits(struct queue_limits *lim)
 		lim->max_hw_sectors = BLK_SAFE_MAX_SECTORS;
 	if (WARN_ON_ONCE(lim->max_hw_sectors < PAGE_SECTORS))
 		return -EINVAL;
+	logical_block_sectors = lim->logical_block_size >> SECTOR_SHIFT;
+	if (WARN_ON_ONCE(logical_block_sectors > lim->max_hw_sectors))
+		return -EINVAL;
 	lim->max_hw_sectors = round_down(lim->max_hw_sectors,
-			lim->logical_block_size >> SECTOR_SHIFT);
+			logical_block_sectors);
 
 	/*
 	 * The actual max_sectors value is a complex beast and also takes the
@@ -153,7 +157,7 @@ static int blk_validate_limits(struct queue_limits *lim)
 		lim->max_sectors = min(max_hw_sectors, BLK_DEF_MAX_SECTORS_CAP);
 	}
 	lim->max_sectors = round_down(lim->max_sectors,
-			lim->logical_block_size >> SECTOR_SHIFT);
+			logical_block_sectors);
 
 	/*
 	 * Random default for the maximum number of segments.  Driver should not
-- 
GitLab


From a14a68b76954e73031ca6399abace17dcb77c17a Mon Sep 17 00:00:00 2001
From: Dongsheng Yang <dongsheng.yang@easystack.cn>
Date: Tue, 28 May 2024 20:09:12 +0800
Subject: [PATCH 341/950] bcache: allow allocator to invalidate bucket in gc

Currently, if the gc is running, when the allocator found free_inc
is empty, allocator has to wait the gc finish. Before that, the
IO is blocked.

But actually, there would be some buckets is reclaimable before gc,
and gc will never mark this kind of bucket to be unreclaimable.

So we can put these buckets into free_inc in gc running to avoid
IO being blocked.

Signed-off-by: Dongsheng Yang <dongsheng.yang@easystack.cn>
Signed-off-by: Mingzhe Zou <mingzhe.zou@easystack.cn>
Signed-off-by: Coly Li <colyli@suse.de>
Link: https://lore.kernel.org/r/20240528120914.28705-2-colyli@suse.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/md/bcache/alloc.c  | 13 +++++--------
 drivers/md/bcache/bcache.h |  1 +
 drivers/md/bcache/btree.c  |  7 ++++++-
 3 files changed, 12 insertions(+), 9 deletions(-)

diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c
index ce13c272c3872..32a46343097dd 100644
--- a/drivers/md/bcache/alloc.c
+++ b/drivers/md/bcache/alloc.c
@@ -129,12 +129,9 @@ static inline bool can_inc_bucket_gen(struct bucket *b)
 
 bool bch_can_invalidate_bucket(struct cache *ca, struct bucket *b)
 {
-	BUG_ON(!ca->set->gc_mark_valid);
-
-	return (!GC_MARK(b) ||
-		GC_MARK(b) == GC_MARK_RECLAIMABLE) &&
-		!atomic_read(&b->pin) &&
-		can_inc_bucket_gen(b);
+	return (ca->set->gc_mark_valid || b->reclaimable_in_gc) &&
+	       ((!GC_MARK(b) || GC_MARK(b) == GC_MARK_RECLAIMABLE) &&
+	       !atomic_read(&b->pin) && can_inc_bucket_gen(b));
 }
 
 void __bch_invalidate_one_bucket(struct cache *ca, struct bucket *b)
@@ -148,6 +145,7 @@ void __bch_invalidate_one_bucket(struct cache *ca, struct bucket *b)
 	bch_inc_gen(ca, b);
 	b->prio = INITIAL_PRIO;
 	atomic_inc(&b->pin);
+	b->reclaimable_in_gc = 0;
 }
 
 static void bch_invalidate_one_bucket(struct cache *ca, struct bucket *b)
@@ -352,8 +350,7 @@ static int bch_allocator_thread(void *arg)
 		 */
 
 retry_invalidate:
-		allocator_wait(ca, ca->set->gc_mark_valid &&
-			       !ca->invalidate_needs_gc);
+		allocator_wait(ca, !ca->invalidate_needs_gc);
 		invalidate_buckets(ca);
 
 		/*
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index 4e6afa89921fe..1d33e40d26ea5 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -200,6 +200,7 @@ struct bucket {
 	uint8_t		gen;
 	uint8_t		last_gc; /* Most out of date gen in the btree */
 	uint16_t	gc_mark; /* Bitfield used by GC. See below for field */
+	uint16_t	reclaimable_in_gc:1;
 };
 
 /*
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index d011a7154d330..4e6ccf2c8a0bf 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -1741,18 +1741,20 @@ static void btree_gc_start(struct cache_set *c)
 
 	mutex_lock(&c->bucket_lock);
 
-	c->gc_mark_valid = 0;
 	c->gc_done = ZERO_KEY;
 
 	ca = c->cache;
 	for_each_bucket(b, ca) {
 		b->last_gc = b->gen;
+		if (bch_can_invalidate_bucket(ca, b))
+			b->reclaimable_in_gc = 1;
 		if (!atomic_read(&b->pin)) {
 			SET_GC_MARK(b, 0);
 			SET_GC_SECTORS_USED(b, 0);
 		}
 	}
 
+	c->gc_mark_valid = 0;
 	mutex_unlock(&c->bucket_lock);
 }
 
@@ -1809,6 +1811,9 @@ static void bch_btree_gc_finish(struct cache_set *c)
 	for_each_bucket(b, ca) {
 		c->need_gc	= max(c->need_gc, bucket_gc_gen(b));
 
+		if (b->reclaimable_in_gc)
+			b->reclaimable_in_gc = 0;
+
 		if (atomic_read(&b->pin))
 			continue;
 
-- 
GitLab


From 05356938a4be356adde4eab4425c6822f3c7d706 Mon Sep 17 00:00:00 2001
From: Coly Li <colyli@suse.de>
Date: Tue, 28 May 2024 20:09:13 +0800
Subject: [PATCH 342/950] bcache: call force_wake_up_gc() if necessary in
 check_should_bypass()

If there are extreme heavy write I/O continuously hit on relative small
cache device (512GB in my testing), it is possible to make counter
c->gc_stats.in_use continue to increase and exceed CUTOFF_CACHE_ADD.

If 'c->gc_stats.in_use > CUTOFF_CACHE_ADD' happens, all following write
requests will bypass the cache device because check_should_bypass()
returns 'true'. Because all writes bypass the cache device, counter
c->sectors_to_gc has no chance to be negative value, and garbage
collection thread won't be waken up even the whole cache becomes clean
after writeback accomplished. The aftermath is that all write I/Os go
directly into backing device even the cache device is clean.

To avoid the above situation, this patch uses a quite conservative way
to fix: if 'c->gc_stats.in_use > CUTOFF_CACHE_ADD' happens, only wakes
up garbage collection thread when the whole cache device is clean.

Before the fix, the writes-always-bypass situation happens after 10+
hours write I/O pressure on 512GB Intel optane memory which acts as
cache device. After this fix, such situation doesn't happen after 36+
hours testing.

Signed-off-by: Coly Li <colyli@suse.de>
Link: https://lore.kernel.org/r/20240528120914.28705-3-colyli@suse.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/md/bcache/request.c | 16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)

diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index 83d112bd2b1c0..af345dc6fde14 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -369,10 +369,24 @@ static bool check_should_bypass(struct cached_dev *dc, struct bio *bio)
 	struct io *i;
 
 	if (test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags) ||
-	    c->gc_stats.in_use > CUTOFF_CACHE_ADD ||
 	    (bio_op(bio) == REQ_OP_DISCARD))
 		goto skip;
 
+	if (c->gc_stats.in_use > CUTOFF_CACHE_ADD) {
+		/*
+		 * If cached buckets are all clean now, 'true' will be
+		 * returned and all requests will bypass the cache device.
+		 * Then c->sectors_to_gc has no chance to be negative, and
+		 * gc thread won't wake up and caching won't work forever.
+		 * Here call force_wake_up_gc() to avoid such aftermath.
+		 */
+		if (BDEV_STATE(&dc->sb) == BDEV_STATE_CLEAN &&
+		    c->gc_mark_valid)
+			force_wake_up_gc(c);
+
+		goto skip;
+	}
+
 	if (mode == CACHE_MODE_NONE ||
 	    (mode == CACHE_MODE_WRITEAROUND &&
 	     op_is_write(bio_op(bio))))
-- 
GitLab


From 74d4ce92e08d5669d66fd890403724faa4286c21 Mon Sep 17 00:00:00 2001
From: Coly Li <colyli@suse.de>
Date: Tue, 28 May 2024 20:09:14 +0800
Subject: [PATCH 343/950] bcache: code cleanup in __bch_bucket_alloc_set()

In __bch_bucket_alloc_set() the lines after lable 'err:' indeed do
nothing useful after multiple cache devices are removed from bcache
code. This cleanup patch drops the useless code to save a bit CPU
cycles.

Signed-off-by: Coly Li <colyli@suse.de>
Link: https://lore.kernel.org/r/20240528120914.28705-4-colyli@suse.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/md/bcache/alloc.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c
index 32a46343097dd..48ce750bf70af 100644
--- a/drivers/md/bcache/alloc.c
+++ b/drivers/md/bcache/alloc.c
@@ -498,8 +498,8 @@ int __bch_bucket_alloc_set(struct cache_set *c, unsigned int reserve,
 
 	ca = c->cache;
 	b = bch_bucket_alloc(ca, reserve, wait);
-	if (b == -1)
-		goto err;
+	if (b < 0)
+		return -1;
 
 	k->ptr[0] = MAKE_PTR(ca->buckets[b].gen,
 			     bucket_to_sector(c, b),
@@ -508,10 +508,6 @@ int __bch_bucket_alloc_set(struct cache_set *c, unsigned int reserve,
 	SET_KEY_PTRS(k, 1);
 
 	return 0;
-err:
-	bch_bucket_free(c, k);
-	bkey_put(c, k);
-	return -1;
 }
 
 int bch_bucket_alloc_set(struct cache_set *c, unsigned int reserve,
-- 
GitLab


From b2ff2698508ffc31c2dcbce58785d8b9dc847e1b Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Sun, 26 May 2024 18:24:25 +0100
Subject: [PATCH 344/950] net: ethernet: starfire: remove unused structs

'short_rx_done_desc' and 'basic_rx_done_desc' are unused since
commit fdecea66687d ("  [netdrvr starfire] Add GPL'd firmware, remove
compat code").

Remove them.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/adaptec/starfire.c | 8 --------
 1 file changed, 8 deletions(-)

diff --git a/drivers/net/ethernet/adaptec/starfire.c b/drivers/net/ethernet/adaptec/starfire.c
index 857361c74f5dd..e1b8794b14c90 100644
--- a/drivers/net/ethernet/adaptec/starfire.c
+++ b/drivers/net/ethernet/adaptec/starfire.c
@@ -441,14 +441,6 @@ enum rx_desc_bits {
 };
 
 /* Completion queue entry. */
-struct short_rx_done_desc {
-	__le32 status;			/* Low 16 bits is length. */
-};
-struct basic_rx_done_desc {
-	__le32 status;			/* Low 16 bits is length. */
-	__le16 vlanid;
-	__le16 status2;
-};
 struct csum_rx_done_desc {
 	__le32 status;			/* Low 16 bits is length. */
 	__le16 csum;			/* Partial checksum */
-- 
GitLab


From a09892f6e281397fc8c4ffd512c8a0fd0a81dd32 Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Sun, 26 May 2024 18:24:26 +0100
Subject: [PATCH 345/950] net: ethernet: liquidio: remove unused structs

'niclist' and 'oct_link_status_resp' are unused since the original
commit f21fb3ed364b ("Add support of Cavium Liquidio ethernet
adapters").

Remove them.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/cavium/liquidio/lio_main.c    | 6 ------
 drivers/net/ethernet/cavium/liquidio/octeon_droq.c | 5 -----
 2 files changed, 11 deletions(-)

diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c
index 34f02a8ec2ca3..1d79f6eaa41f6 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c
@@ -92,12 +92,6 @@ static int octeon_console_debug_enabled(u32 console)
 /* time to wait for possible in-flight requests in milliseconds */
 #define WAIT_INFLIGHT_REQUEST	msecs_to_jiffies(1000)
 
-struct oct_link_status_resp {
-	u64 rh;
-	struct oct_link_info link_info;
-	u64 status;
-};
-
 struct oct_timestamp_resp {
 	u64 rh;
 	u64 timestamp;
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c
index 0d6ee30affb91..eef12fdd246d3 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c
@@ -30,11 +30,6 @@
 #include "cn23xx_pf_device.h"
 #include "cn23xx_vf_device.h"
 
-struct niclist {
-	struct list_head list;
-	void *ptr;
-};
-
 struct __dispatch {
 	struct list_head list;
 	struct octeon_recv_info *rinfo;
-- 
GitLab


From ef7f9febb33d22e687226211c67aa50158a0205b Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Sun, 26 May 2024 18:24:27 +0100
Subject: [PATCH 346/950] net: ethernet: mlx4: remove unused struct
 'mlx4_port_config'

'mlx4_port_config was added by
commit ab9c17a009ee ("mlx4_core: Modify driver initialization flow to
accommodate SRIOV for Ethernet")
but remained unused.

Remove it.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/mellanox/mlx4/main.c | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 98688e4dbec5e..febeadfdd5a58 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -169,12 +169,6 @@ module_param_array(port_type_array, int, &arr_argc, 0444);
 MODULE_PARM_DESC(port_type_array, "Array of port types: HW_DEFAULT (0) is default "
 				"1 for IB, 2 for Ethernet");
 
-struct mlx4_port_config {
-	struct list_head list;
-	enum mlx4_port_type port_type[MLX4_MAX_PORTS + 1];
-	struct pci_dev *pdev;
-};
-
 static atomic_t pf_loading = ATOMIC_INIT(0);
 
 static int mlx4_devlink_ierr_reset_get(struct devlink *devlink, u32 id,
-- 
GitLab


From 18ae4c093cd23b741607fd35ba449f80fbd9f322 Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Sun, 26 May 2024 18:24:28 +0100
Subject: [PATCH 347/950] net: ethernet: 8390: ne2k-pci: remove unused struct
 'ne2k_pci_card'

'ne2k_pci_card' is unused since 2.3.99-pre3 in March 2000.

Remove it.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/8390/ne2k-pci.c | 11 -----------
 1 file changed, 11 deletions(-)

diff --git a/drivers/net/ethernet/8390/ne2k-pci.c b/drivers/net/ethernet/8390/ne2k-pci.c
index 65f56a98c0a06..1a34da07c0db2 100644
--- a/drivers/net/ethernet/8390/ne2k-pci.c
+++ b/drivers/net/ethernet/8390/ne2k-pci.c
@@ -186,17 +186,6 @@ static void ne2k_pci_block_output(struct net_device *dev, const int count,
 static const struct ethtool_ops ne2k_pci_ethtool_ops;
 
 
-
-/* There is no room in the standard 8390 structure for extra info we need,
- * so we build a meta/outer-wrapper structure..
- */
-struct ne2k_pci_card {
-	struct net_device *dev;
-	struct pci_dev *pci_dev;
-};
-
-
-
 /* NEx000-clone boards have a Station Address (SA) PROM (SAPROM) in the packet
  * buffer memory space.  By-the-spec NE2000 clones have 0x57,0x57 in bytes
  * 0x0e,0x0f of the SAPROM, while other supposed NE2000 clones must be
-- 
GitLab


From c30ff5f3aec3f77e13cfd7373390639bfdcffba7 Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Sun, 26 May 2024 21:59:22 +0100
Subject: [PATCH 348/950] net: usb: remove unused structs 'usb_context'

Both lan78xx and smsc75xx have a 'usb_context'
struct which is unused, since their original commits.

Remove them.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Link: https://lore.kernel.org/r/20240526205922.176578-1-linux@treblig.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/usb/lan78xx.c  | 5 -----
 drivers/net/usb/smsc75xx.c | 5 -----
 2 files changed, 10 deletions(-)

diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 5a2c38b63012c..7a5cc49ebec66 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -380,11 +380,6 @@ struct skb_data {		/* skb->cb is one of these */
 	int num_of_packet;
 };
 
-struct usb_context {
-	struct usb_ctrlrequest req;
-	struct lan78xx_net *dev;
-};
-
 #define EVENT_TX_HALT			0
 #define EVENT_RX_HALT			1
 #define EVENT_RX_MEMORY			2
diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c
index 0726e18bee6fc..78c821349f484 100644
--- a/drivers/net/usb/smsc75xx.c
+++ b/drivers/net/usb/smsc75xx.c
@@ -61,11 +61,6 @@ struct smsc75xx_priv {
 	u8 suspend_flags;
 };
 
-struct usb_context {
-	struct usb_ctrlrequest req;
-	struct usbnet *dev;
-};
-
 static bool turbo_mode = true;
 module_param(turbo_mode, bool, 0644);
 MODULE_PARM_DESC(turbo_mode, "Enable multiple frames per Rx transaction");
-- 
GitLab


From 56a5cf538c3f2d935b0d81040a8303b6e7fc5fd8 Mon Sep 17 00:00:00 2001
From: MD Danish Anwar <danishanwar@ti.com>
Date: Mon, 27 May 2024 12:00:15 +0530
Subject: [PATCH 349/950] net: ti: icssg-prueth: Fix start counter for ft1
 filter

The start counter for FT1 filter is wrongly set to 0 in the driver.
FT1 is used for source address violation (SAV) check and source address
starts at Byte 6 not Byte 0. Fix this by changing start counter to
ETH_ALEN in icssg_ft1_set_mac_addr().

Fixes: e9b4ece7d74b ("net: ti: icssg-prueth: Add Firmware config and classification APIs.")
Signed-off-by: MD Danish Anwar <danishanwar@ti.com>
Link: https://lore.kernel.org/r/20240527063015.263748-1-danishanwar@ti.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/ti/icssg/icssg_classifier.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/ti/icssg/icssg_classifier.c b/drivers/net/ethernet/ti/icssg/icssg_classifier.c
index 79ba47bb3602e..f7d21da1a0fb6 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_classifier.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_classifier.c
@@ -455,7 +455,7 @@ void icssg_ft1_set_mac_addr(struct regmap *miig_rt, int slice, u8 *mac_addr)
 {
 	const u8 mask_addr[] = { 0, 0, 0, 0, 0, 0, };
 
-	rx_class_ft1_set_start_len(miig_rt, slice, 0, 6);
+	rx_class_ft1_set_start_len(miig_rt, slice, ETH_ALEN, ETH_ALEN);
 	rx_class_ft1_set_da(miig_rt, slice, 0, mac_addr);
 	rx_class_ft1_set_da_mask(miig_rt, slice, 0, mask_addr);
 	rx_class_ft1_cfg_set_type(miig_rt, slice, 0, FT1_CFG_TYPE_EQ);
-- 
GitLab


From f13e01b89daf42330a4a722f451e48c3e2edfc8d Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Fri, 17 May 2024 12:48:25 +0100
Subject: [PATCH 350/950] btrfs: ensure fast fsync waits for ordered extents
 after a write failure

If a write path in COW mode fails, either before submitting a bio for the
new extents or an actual IO error happens, we can end up allowing a fast
fsync to log file extent items that point to unwritten extents.

This is because dropping the extent maps happens when completing ordered
extents, at btrfs_finish_one_ordered(), and the completion of an ordered
extent is executed in a work queue.

This can result in a fast fsync to start logging file extent items based
on existing extent maps before the ordered extents complete, therefore
resulting in a log that has file extent items that point to unwritten
extents, resulting in a corrupt file if a crash happens after and the log
tree is replayed the next time the fs is mounted.

This can happen for both direct IO writes and buffered writes.

For example consider a direct IO write, in COW mode, that fails at
btrfs_dio_submit_io() because btrfs_extract_ordered_extent() returned an
error:

1) We call btrfs_finish_ordered_extent() with the 'uptodate' parameter
   set to false, meaning an error happened;

2) That results in marking the ordered extent with the BTRFS_ORDERED_IOERR
   flag;

3) btrfs_finish_ordered_extent() queues the completion of the ordered
   extent - so that btrfs_finish_one_ordered() will be executed later in
   a work queue. That function will drop extent maps in the range when
   it's executed, since the extent maps point to unwritten locations
   (signaled by the BTRFS_ORDERED_IOERR flag);

4) After calling btrfs_finish_ordered_extent() we keep going down the
   write path and unlock the inode;

5) After that a fast fsync starts and locks the inode;

6) Before the work queue executes btrfs_finish_one_ordered(), the fsync
   task sees the extent maps that point to the unwritten locations and
   logs file extent items based on them - it does not know they are
   unwritten, and the fast fsync path does not wait for ordered extents
   to complete, which is an intentional behaviour in order to reduce
   latency.

For the buffered write case, here's one example:

1) A fast fsync begins, and it starts by flushing delalloc and waiting for
   the writeback to complete by calling filemap_fdatawait_range();

2) Flushing the dellaloc created a new extent map X;

3) During the writeback some IO error happened, and at the end io callback
   (end_bbio_data_write()) we call btrfs_finish_ordered_extent(), which
   sets the BTRFS_ORDERED_IOERR flag in the ordered extent and queues its
   completion;

4) After queuing the ordered extent completion, the end io callback clears
   the writeback flag from all pages (or folios), and from that moment the
   fast fsync can proceed;

5) The fast fsync proceeds sees extent map X and logs a file extent item
   based on extent map X, resulting in a log that points to an unwritten
   data extent - because the ordered extent completion hasn't run yet, it
   happens only after the logging.

To fix this make btrfs_finish_ordered_extent() set the inode flag
BTRFS_INODE_NEEDS_FULL_SYNC in case an error happened for a COW write,
so that a fast fsync will wait for ordered extent completion.

Note that this issues of using extent maps that point to unwritten
locations can not happen for reads, because in read paths we start by
locking the extent range and wait for any ordered extents in the range
to complete before looking for extent maps.

Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/btrfs_inode.h  | 10 ++++++++++
 fs/btrfs/file.c         | 16 ++++++++++++++++
 fs/btrfs/ordered-data.c | 31 +++++++++++++++++++++++++++++++
 3 files changed, 57 insertions(+)

diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 91c994b569f3b..6ed495ca7a311 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -89,6 +89,16 @@ enum {
 	BTRFS_INODE_FREE_SPACE_INODE,
 	/* Set when there are no capabilities in XATTs for the inode. */
 	BTRFS_INODE_NO_CAP_XATTR,
+	/*
+	 * Set if an error happened when doing a COW write before submitting a
+	 * bio or during writeback. Used for both buffered writes and direct IO
+	 * writes. This is to signal a fast fsync that it has to wait for
+	 * ordered extents to complete and therefore not log extent maps that
+	 * point to unwritten extents (when an ordered extent completes and it
+	 * has the BTRFS_ORDERED_IOERR flag set, it drops extent maps in its
+	 * range).
+	 */
+	BTRFS_INODE_COW_WRITE_ERROR,
 };
 
 /* in memory btrfs inode */
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 0c7c1b42028e3..00670596bf065 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1885,6 +1885,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	 */
 	if (full_sync || btrfs_is_zoned(fs_info)) {
 		ret = btrfs_wait_ordered_range(inode, start, len);
+		clear_bit(BTRFS_INODE_COW_WRITE_ERROR, &BTRFS_I(inode)->runtime_flags);
 	} else {
 		/*
 		 * Get our ordered extents as soon as possible to avoid doing
@@ -1894,6 +1895,21 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 		btrfs_get_ordered_extents_for_logging(BTRFS_I(inode),
 						      &ctx.ordered_extents);
 		ret = filemap_fdatawait_range(inode->i_mapping, start, end);
+		if (ret)
+			goto out_release_extents;
+
+		/*
+		 * Check and clear the BTRFS_INODE_COW_WRITE_ERROR now after
+		 * starting and waiting for writeback, because for buffered IO
+		 * it may have been set during the end IO callback
+		 * (end_bbio_data_write() -> btrfs_finish_ordered_extent()) in
+		 * case an error happened and we need to wait for ordered
+		 * extents to complete so that any extent maps that point to
+		 * unwritten locations are dropped and we don't log them.
+		 */
+		if (test_and_clear_bit(BTRFS_INODE_COW_WRITE_ERROR,
+				       &BTRFS_I(inode)->runtime_flags))
+			ret = btrfs_wait_ordered_range(inode, start, len);
 	}
 
 	if (ret)
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index c5bdd674f55c5..35a413ce935d9 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -388,6 +388,37 @@ bool btrfs_finish_ordered_extent(struct btrfs_ordered_extent *ordered,
 	ret = can_finish_ordered_extent(ordered, page, file_offset, len, uptodate);
 	spin_unlock_irqrestore(&inode->ordered_tree_lock, flags);
 
+	/*
+	 * If this is a COW write it means we created new extent maps for the
+	 * range and they point to unwritten locations if we got an error either
+	 * before submitting a bio or during IO.
+	 *
+	 * We have marked the ordered extent with BTRFS_ORDERED_IOERR, and we
+	 * are queuing its completion below. During completion, at
+	 * btrfs_finish_one_ordered(), we will drop the extent maps for the
+	 * unwritten extents.
+	 *
+	 * However because completion runs in a work queue we can end up having
+	 * a fast fsync running before that. In the case of direct IO, once we
+	 * unlock the inode the fsync might start, and we queue the completion
+	 * before unlocking the inode. In the case of buffered IO when writeback
+	 * finishes (end_bbio_data_write()) we queue the completion, so if the
+	 * writeback was triggered by a fast fsync, the fsync might start
+	 * logging before ordered extent completion runs in the work queue.
+	 *
+	 * The fast fsync will log file extent items based on the extent maps it
+	 * finds, so if by the time it collects extent maps the ordered extent
+	 * completion didn't happen yet, it will log file extent items that
+	 * point to unwritten extents, resulting in a corruption if a crash
+	 * happens and the log tree is replayed. Note that a fast fsync does not
+	 * wait for completion of ordered extents in order to reduce latency.
+	 *
+	 * Set a flag in the inode so that the next fast fsync will wait for
+	 * ordered extents to complete before starting to log.
+	 */
+	if (!uptodate && !test_bit(BTRFS_ORDERED_NOCOW, &ordered->flags))
+		set_bit(BTRFS_INODE_COW_WRITE_ERROR, &inode->runtime_flags);
+
 	if (ret)
 		btrfs_queue_ordered_fn(ordered);
 	return ret;
-- 
GitLab


From 43cad521c6d228ea0c51e248f8e5b3a6295a2849 Mon Sep 17 00:00:00 2001
From: Dhananjay Ugwekar <Dhananjay.Ugwekar@amd.com>
Date: Tue, 30 Apr 2024 14:07:06 +0530
Subject: [PATCH 351/950] tools/power/cpupower: Fix Pstate frequency reporting
 on AMD Family 1Ah CPUs

Update cpupower's P-State frequency calculation and reporting with AMD
Family 1Ah+ processors, when using the acpi-cpufreq driver. This is due
to a change in the PStateDef MSR layout in AMD Family 1Ah+.

Tested on 4th and 5th Gen AMD EPYC system

Signed-off-by: Ananth Narayan <Ananth.Narayan@amd.com>
Signed-off-by: Dhananjay Ugwekar <Dhananjay.Ugwekar@amd.com>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 tools/power/cpupower/utils/helpers/amd.c | 26 +++++++++++++++++++++---
 1 file changed, 23 insertions(+), 3 deletions(-)

diff --git a/tools/power/cpupower/utils/helpers/amd.c b/tools/power/cpupower/utils/helpers/amd.c
index c519cc89c97f4..0a56e22240fc8 100644
--- a/tools/power/cpupower/utils/helpers/amd.c
+++ b/tools/power/cpupower/utils/helpers/amd.c
@@ -41,6 +41,16 @@ union core_pstate {
 		unsigned res1:31;
 		unsigned en:1;
 	} pstatedef;
+	/* since fam 1Ah: */
+	struct {
+		unsigned fid:12;
+		unsigned res1:2;
+		unsigned vid:8;
+		unsigned iddval:8;
+		unsigned idddiv:2;
+		unsigned res2:31;
+		unsigned en:1;
+	} pstatedef2;
 	unsigned long long val;
 };
 
@@ -48,6 +58,10 @@ static int get_did(union core_pstate pstate)
 {
 	int t;
 
+	/* Fam 1Ah onward do not use did */
+	if (cpupower_cpu_info.family >= 0x1A)
+		return 0;
+
 	if (cpupower_cpu_info.caps & CPUPOWER_CAP_AMD_PSTATEDEF)
 		t = pstate.pstatedef.did;
 	else if (cpupower_cpu_info.family == 0x12)
@@ -61,12 +75,18 @@ static int get_did(union core_pstate pstate)
 static int get_cof(union core_pstate pstate)
 {
 	int t;
-	int fid, did, cof;
+	int fid, did, cof = 0;
 
 	did = get_did(pstate);
 	if (cpupower_cpu_info.caps & CPUPOWER_CAP_AMD_PSTATEDEF) {
-		fid = pstate.pstatedef.fid;
-		cof = 200 * fid / did;
+		if (cpupower_cpu_info.family >= 0x1A) {
+			fid = pstate.pstatedef2.fid;
+			if (fid > 0x0f)
+				cof = (fid * 5);
+		} else {
+			fid = pstate.pstatedef.fid;
+			cof = 200 * fid / did;
+		}
 	} else {
 		t = 0x10;
 		fid = pstate.pstate.fid;
-- 
GitLab


From 1292bc2ebf63e705ae18bbaaf9cea21b68d37ee6 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Fri, 24 May 2024 13:59:34 -0400
Subject: [PATCH 352/950] bcachefs: Plumb bkey into __btree_err()

It can be useful to know the exact byte offset within a btree node where
an error occured.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/btree_io.c | 85 ++++++++++++++++++++++--------------------
 1 file changed, 45 insertions(+), 40 deletions(-)

diff --git a/fs/bcachefs/btree_io.c b/fs/bcachefs/btree_io.c
index cbf8f5d906021..829c1b91477d7 100644
--- a/fs/bcachefs/btree_io.c
+++ b/fs/bcachefs/btree_io.c
@@ -519,7 +519,7 @@ void bch2_btree_init_next(struct btree_trans *trans, struct btree *b)
 
 static void btree_err_msg(struct printbuf *out, struct bch_fs *c,
 			  struct bch_dev *ca,
-			  struct btree *b, struct bset *i,
+			  struct btree *b, struct bset *i, struct bkey_packed *k,
 			  unsigned offset, int write)
 {
 	prt_printf(out, bch2_log_msg(c, "%s"),
@@ -537,15 +537,20 @@ static void btree_err_msg(struct printbuf *out, struct bch_fs *c,
 		   b->written, btree_ptr_sectors_written(&b->key));
 	if (i)
 		prt_printf(out, " bset u64s %u", le16_to_cpu(i->u64s));
+	if (k)
+		prt_printf(out, " bset byte offset %lu",
+			   (unsigned long)(void *)k -
+			   ((unsigned long)(void *)i & ~511UL));
 	prt_str(out, ": ");
 }
 
-__printf(9, 10)
+__printf(10, 11)
 static int __btree_err(int ret,
 		       struct bch_fs *c,
 		       struct bch_dev *ca,
 		       struct btree *b,
 		       struct bset *i,
+		       struct bkey_packed *k,
 		       int write,
 		       bool have_retry,
 		       enum bch_sb_error_id err_type,
@@ -555,7 +560,7 @@ static int __btree_err(int ret,
 	bool silent = c->curr_recovery_pass == BCH_RECOVERY_PASS_scan_for_btree_nodes;
 	va_list args;
 
-	btree_err_msg(&out, c, ca, b, i, b->written, write);
+	btree_err_msg(&out, c, ca, b, i, k, b->written, write);
 
 	va_start(args, fmt);
 	prt_vprintf(&out, fmt, args);
@@ -611,9 +616,9 @@ fsck_err:
 	return ret;
 }
 
-#define btree_err(type, c, ca, b, i, _err_type, msg, ...)		\
+#define btree_err(type, c, ca, b, i, k, _err_type, msg, ...)		\
 ({									\
-	int _ret = __btree_err(type, c, ca, b, i, write, have_retry,	\
+	int _ret = __btree_err(type, c, ca, b, i, k, write, have_retry,	\
 			       BCH_FSCK_ERR_##_err_type,		\
 			       msg, ##__VA_ARGS__);			\
 									\
@@ -690,7 +695,7 @@ static int validate_bset(struct bch_fs *c, struct bch_dev *ca,
 
 	btree_err_on(!bch2_version_compatible(version),
 		     -BCH_ERR_btree_node_read_err_incompatible,
-		     c, ca, b, i,
+		     c, ca, b, i, NULL,
 		     btree_node_unsupported_version,
 		     "unsupported bset version %u.%u",
 		     BCH_VERSION_MAJOR(version),
@@ -698,7 +703,7 @@ static int validate_bset(struct bch_fs *c, struct bch_dev *ca,
 
 	if (btree_err_on(version < c->sb.version_min,
 			 -BCH_ERR_btree_node_read_err_fixable,
-			 c, NULL, b, i,
+			 c, NULL, b, i, NULL,
 			 btree_node_bset_older_than_sb_min,
 			 "bset version %u older than superblock version_min %u",
 			 version, c->sb.version_min)) {
@@ -711,7 +716,7 @@ static int validate_bset(struct bch_fs *c, struct bch_dev *ca,
 	if (btree_err_on(BCH_VERSION_MAJOR(version) >
 			 BCH_VERSION_MAJOR(c->sb.version),
 			 -BCH_ERR_btree_node_read_err_fixable,
-			 c, NULL, b, i,
+			 c, NULL, b, i, NULL,
 			 btree_node_bset_newer_than_sb,
 			 "bset version %u newer than superblock version %u",
 			 version, c->sb.version)) {
@@ -723,13 +728,13 @@ static int validate_bset(struct bch_fs *c, struct bch_dev *ca,
 
 	btree_err_on(BSET_SEPARATE_WHITEOUTS(i),
 		     -BCH_ERR_btree_node_read_err_incompatible,
-		     c, ca, b, i,
+		     c, ca, b, i, NULL,
 		     btree_node_unsupported_version,
 		     "BSET_SEPARATE_WHITEOUTS no longer supported");
 
 	if (btree_err_on(offset + sectors > btree_sectors(c),
 			 -BCH_ERR_btree_node_read_err_fixable,
-			 c, ca, b, i,
+			 c, ca, b, i, NULL,
 			 bset_past_end_of_btree_node,
 			 "bset past end of btree node")) {
 		i->u64s = 0;
@@ -739,13 +744,13 @@ static int validate_bset(struct bch_fs *c, struct bch_dev *ca,
 
 	btree_err_on(offset && !i->u64s,
 		     -BCH_ERR_btree_node_read_err_fixable,
-		     c, ca, b, i,
+		     c, ca, b, i, NULL,
 		     bset_empty,
 		     "empty bset");
 
 	btree_err_on(BSET_OFFSET(i) && BSET_OFFSET(i) != offset,
 		     -BCH_ERR_btree_node_read_err_want_retry,
-		     c, ca, b, i,
+		     c, ca, b, i, NULL,
 		     bset_wrong_sector_offset,
 		     "bset at wrong sector offset");
 
@@ -761,20 +766,20 @@ static int validate_bset(struct bch_fs *c, struct bch_dev *ca,
 			/* XXX endianness */
 			btree_err_on(bp->seq != bn->keys.seq,
 				     -BCH_ERR_btree_node_read_err_must_retry,
-				     c, ca, b, NULL,
+				     c, ca, b, NULL, NULL,
 				     bset_bad_seq,
 				     "incorrect sequence number (wrong btree node)");
 		}
 
 		btree_err_on(BTREE_NODE_ID(bn) != b->c.btree_id,
 			     -BCH_ERR_btree_node_read_err_must_retry,
-			     c, ca, b, i,
+			     c, ca, b, i, NULL,
 			     btree_node_bad_btree,
 			     "incorrect btree id");
 
 		btree_err_on(BTREE_NODE_LEVEL(bn) != b->c.level,
 			     -BCH_ERR_btree_node_read_err_must_retry,
-			     c, ca, b, i,
+			     c, ca, b, i, NULL,
 			     btree_node_bad_level,
 			     "incorrect level");
 
@@ -793,7 +798,7 @@ static int validate_bset(struct bch_fs *c, struct bch_dev *ca,
 
 			btree_err_on(!bpos_eq(b->data->min_key, bp->min_key),
 				     -BCH_ERR_btree_node_read_err_must_retry,
-				     c, ca, b, NULL,
+				     c, ca, b, NULL, NULL,
 				     btree_node_bad_min_key,
 				     "incorrect min_key: got %s should be %s",
 				     (printbuf_reset(&buf1),
@@ -804,7 +809,7 @@ static int validate_bset(struct bch_fs *c, struct bch_dev *ca,
 
 		btree_err_on(!bpos_eq(bn->max_key, b->key.k.p),
 			     -BCH_ERR_btree_node_read_err_must_retry,
-			     c, ca, b, i,
+			     c, ca, b, i, NULL,
 			     btree_node_bad_max_key,
 			     "incorrect max key %s",
 			     (printbuf_reset(&buf1),
@@ -816,7 +821,7 @@ static int validate_bset(struct bch_fs *c, struct bch_dev *ca,
 
 		btree_err_on(bch2_bkey_format_invalid(c, &bn->format, write, &buf1),
 			     -BCH_ERR_btree_node_read_err_bad_node,
-			     c, ca, b, i,
+			     c, ca, b, i, NULL,
 			     btree_node_bad_format,
 			     "invalid bkey format: %s\n  %s", buf1.buf,
 			     (printbuf_reset(&buf2),
@@ -883,7 +888,7 @@ static int validate_bset_keys(struct bch_fs *c, struct btree *b,
 
 		if (btree_err_on(bkey_p_next(k) > vstruct_last(i),
 				 -BCH_ERR_btree_node_read_err_fixable,
-				 c, NULL, b, i,
+				 c, NULL, b, i, k,
 				 btree_node_bkey_past_bset_end,
 				 "key extends past end of bset")) {
 			i->u64s = cpu_to_le16((u64 *) k - i->_data);
@@ -892,14 +897,14 @@ static int validate_bset_keys(struct bch_fs *c, struct btree *b,
 
 		if (btree_err_on(k->format > KEY_FORMAT_CURRENT,
 				 -BCH_ERR_btree_node_read_err_fixable,
-				 c, NULL, b, i,
+				 c, NULL, b, i, k,
 				 btree_node_bkey_bad_format,
 				 "invalid bkey format %u", k->format))
 			goto drop_this_key;
 
 		if (btree_err_on(!bkeyp_u64s_valid(&b->format, k),
 				 -BCH_ERR_btree_node_read_err_fixable,
-				 c, NULL, b, i,
+				 c, NULL, b, i, k,
 				 btree_node_bkey_bad_u64s,
 				 "bad k->u64s %u (min %u max %zu)", k->u64s,
 				 bkeyp_key_u64s(&b->format, k),
@@ -921,7 +926,7 @@ static int validate_bset_keys(struct bch_fs *c, struct btree *b,
 			bch2_bkey_val_to_text(&buf, c, u.s_c);
 
 			btree_err(-BCH_ERR_btree_node_read_err_fixable,
-				  c, NULL, b, i,
+				  c, NULL, b, i, k,
 				  btree_node_bad_bkey,
 				  "invalid bkey: %s", buf.buf);
 			goto drop_this_key;
@@ -942,7 +947,7 @@ static int validate_bset_keys(struct bch_fs *c, struct btree *b,
 			bch2_bkey_to_text(&buf, u.k);
 
 			if (btree_err(-BCH_ERR_btree_node_read_err_fixable,
-				      c, NULL, b, i,
+				      c, NULL, b, i, k,
 				      btree_node_bkey_out_of_order,
 				      "%s", buf.buf))
 				goto drop_this_key;
@@ -1011,13 +1016,13 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca,
 
 	if (bch2_meta_read_fault("btree"))
 		btree_err(-BCH_ERR_btree_node_read_err_must_retry,
-			  c, ca, b, NULL,
+			  c, ca, b, NULL, NULL,
 			  btree_node_fault_injected,
 			  "dynamic fault");
 
 	btree_err_on(le64_to_cpu(b->data->magic) != bset_magic(c),
 		     -BCH_ERR_btree_node_read_err_must_retry,
-		     c, ca, b, NULL,
+		     c, ca, b, NULL, NULL,
 		     btree_node_bad_magic,
 		     "bad magic: want %llx, got %llx",
 		     bset_magic(c), le64_to_cpu(b->data->magic));
@@ -1032,7 +1037,7 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca,
 
 		btree_err_on(b->data->keys.seq != bp->seq,
 			     -BCH_ERR_btree_node_read_err_must_retry,
-			     c, ca, b, NULL,
+			     c, ca, b, NULL, NULL,
 			     btree_node_bad_seq,
 			     "got wrong btree node: got\n%s",
 			     (printbuf_reset(&buf),
@@ -1041,7 +1046,7 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca,
 	} else {
 		btree_err_on(!b->data->keys.seq,
 			     -BCH_ERR_btree_node_read_err_must_retry,
-			     c, ca, b, NULL,
+			     c, ca, b, NULL, NULL,
 			     btree_node_bad_seq,
 			     "bad btree header: seq 0\n%s",
 			     (printbuf_reset(&buf),
@@ -1060,7 +1065,7 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca,
 
 			btree_err_on(!bch2_checksum_type_valid(c, BSET_CSUM_TYPE(i)),
 				     -BCH_ERR_btree_node_read_err_want_retry,
-				     c, ca, b, i,
+				     c, ca, b, i, NULL,
 				     bset_unknown_csum,
 				     "unknown checksum type %llu", BSET_CSUM_TYPE(i));
 
@@ -1073,7 +1078,7 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca,
 
 			btree_err_on(csum_bad,
 				     -BCH_ERR_btree_node_read_err_want_retry,
-				     c, ca, b, i,
+				     c, ca, b, i, NULL,
 				     bset_bad_csum,
 				     "%s",
 				     (printbuf_reset(&buf),
@@ -1088,7 +1093,7 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca,
 			btree_err_on(btree_node_type_is_extents(btree_node_type(b)) &&
 				     !BTREE_NODE_NEW_EXTENT_OVERWRITE(b->data),
 				     -BCH_ERR_btree_node_read_err_incompatible,
-				     c, NULL, b, NULL,
+				     c, NULL, b, NULL, NULL,
 				     btree_node_unsupported_version,
 				     "btree node does not have NEW_EXTENT_OVERWRITE set");
 
@@ -1102,7 +1107,7 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca,
 
 			btree_err_on(!bch2_checksum_type_valid(c, BSET_CSUM_TYPE(i)),
 				     -BCH_ERR_btree_node_read_err_want_retry,
-				     c, ca, b, i,
+				     c, ca, b, i, NULL,
 				     bset_unknown_csum,
 				     "unknown checksum type %llu", BSET_CSUM_TYPE(i));
 
@@ -1114,7 +1119,7 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca,
 
 			btree_err_on(csum_bad,
 				     -BCH_ERR_btree_node_read_err_want_retry,
-				     c, ca, b, i,
+				     c, ca, b, i, NULL,
 				     bset_bad_csum,
 				     "%s",
 				     (printbuf_reset(&buf),
@@ -1152,14 +1157,14 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca,
 
 		btree_err_on(blacklisted && first,
 			     -BCH_ERR_btree_node_read_err_fixable,
-			     c, ca, b, i,
+			     c, ca, b, i, NULL,
 			     bset_blacklisted_journal_seq,
 			     "first btree node bset has blacklisted journal seq (%llu)",
 			     le64_to_cpu(i->journal_seq));
 
 		btree_err_on(blacklisted && ptr_written,
 			     -BCH_ERR_btree_node_read_err_fixable,
-			     c, ca, b, i,
+			     c, ca, b, i, NULL,
 			     first_bset_blacklisted_journal_seq,
 			     "found blacklisted bset (journal seq %llu) in btree node at offset %u-%u/%u",
 			     le64_to_cpu(i->journal_seq),
@@ -1178,7 +1183,7 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca,
 	if (ptr_written) {
 		btree_err_on(b->written < ptr_written,
 			     -BCH_ERR_btree_node_read_err_want_retry,
-			     c, ca, b, NULL,
+			     c, ca, b, NULL, NULL,
 			     btree_node_data_missing,
 			     "btree node data missing: expected %u sectors, found %u",
 			     ptr_written, b->written);
@@ -1191,7 +1196,7 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca,
 								      le64_to_cpu(bne->keys.journal_seq),
 								      true),
 				     -BCH_ERR_btree_node_read_err_want_retry,
-				     c, ca, b, NULL,
+				     c, ca, b, NULL, NULL,
 				     btree_node_bset_after_end,
 				     "found bset signature after last bset");
 	}
@@ -1235,7 +1240,7 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca,
 			bch2_bkey_val_to_text(&buf, c, u.s_c);
 
 			btree_err(-BCH_ERR_btree_node_read_err_fixable,
-				  c, NULL, b, i,
+				  c, NULL, b, i, k,
 				  btree_node_bad_bkey,
 				  "%s", buf.buf);
 
@@ -1471,18 +1476,18 @@ static CLOSURE_CALLBACK(btree_node_read_all_replicas_done)
 
 		written2 = btree_node_sectors_written(c, ra->buf[i]);
 		if (btree_err_on(written2 != written, -BCH_ERR_btree_node_read_err_fixable,
-				 c, NULL, b, NULL,
+				 c, NULL, b, NULL, NULL,
 				 btree_node_replicas_sectors_written_mismatch,
 				 "btree node sectors written mismatch: %u != %u",
 				 written, written2) ||
 		    btree_err_on(btree_node_has_extra_bsets(c, written2, ra->buf[i]),
 				 -BCH_ERR_btree_node_read_err_fixable,
-				 c, NULL, b, NULL,
+				 c, NULL, b, NULL, NULL,
 				 btree_node_bset_after_end,
 				 "found bset signature after last bset") ||
 		    btree_err_on(memcmp(ra->buf[best], ra->buf[i], written << 9),
 				 -BCH_ERR_btree_node_read_err_fixable,
-				 c, NULL, b, NULL,
+				 c, NULL, b, NULL, NULL,
 				 btree_node_replicas_data_mismatch,
 				 "btree node replicas content mismatch"))
 			dump_bset_maps = true;
-- 
GitLab


From 9e1a66e66870ebeebea9f674550118df3c12eaf6 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sun, 26 May 2024 13:24:31 -0400
Subject: [PATCH 353/950] bcachefs: Fix lookup_first_inode() when
 inode_generations are present

This function is used for finding the hash seed (which is the same in
all versions of an inode in different snapshots): ff an inode has been
deleted in a child snapshot we need to iterate until we find a live
version.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/fsck.c | 24 ++++++++++--------------
 1 file changed, 10 insertions(+), 14 deletions(-)

diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c
index c8f57465131c5..4cd28db9bad8d 100644
--- a/fs/bcachefs/fsck.c
+++ b/fs/bcachefs/fsck.c
@@ -77,21 +77,17 @@ static int lookup_first_inode(struct btree_trans *trans, u64 inode_nr,
 	struct bkey_s_c k;
 	int ret;
 
-	bch2_trans_iter_init(trans, &iter, BTREE_ID_inodes,
-			     POS(0, inode_nr),
-			     BTREE_ITER_all_snapshots);
-	k = bch2_btree_iter_peek(&iter);
-	ret = bkey_err(k);
-	if (ret)
-		goto err;
-
-	if (!k.k || !bkey_eq(k.k->p, POS(0, inode_nr))) {
-		ret = -BCH_ERR_ENOENT_inode;
-		goto err;
+	for_each_btree_key_norestart(trans, iter, BTREE_ID_inodes, POS(0, inode_nr),
+				     BTREE_ITER_all_snapshots, k, ret) {
+		if (k.k->p.offset != inode_nr)
+			break;
+		if (!bkey_is_inode(k.k))
+			continue;
+		ret = bch2_inode_unpack(k, inode);
+		goto found;
 	}
-
-	ret = bch2_inode_unpack(k, inode);
-err:
+	ret = -BCH_ERR_ENOENT_inode;
+found:
 	bch_err_msg(trans->c, ret, "fetching inode %llu", inode_nr);
 	bch2_trans_iter_exit(trans, &iter);
 	return ret;
-- 
GitLab


From 218e5e0c2a3acdb29ccbdfbfdd5e2def27d3aae2 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 27 May 2024 02:40:06 -0400
Subject: [PATCH 354/950] bcachefs: Fix locking assert

We now track whether a transaction is locked, and verify that we don't
have nodes locked when the transaction isn't locked; reorder relocks to
not pop the new assert.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/btree_key_cache.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/fs/bcachefs/btree_key_cache.c b/fs/bcachefs/btree_key_cache.c
index 75f5e6fe46349..34056aaece009 100644
--- a/fs/bcachefs/btree_key_cache.c
+++ b/fs/bcachefs/btree_key_cache.c
@@ -424,16 +424,16 @@ static int btree_key_cache_fill(struct btree_trans *trans,
 				goto err;
 			}
 
-			if (!bch2_btree_node_relock(trans, ck_path, 0)) {
+			ret = bch2_trans_relock(trans);
+			if (ret) {
 				kfree(new_k);
-				trace_and_count(trans->c, trans_restart_relock_key_cache_fill, trans, _THIS_IP_, ck_path);
-				ret = btree_trans_restart(trans, BCH_ERR_transaction_restart_key_cache_fill);
 				goto err;
 			}
 
-			ret = bch2_trans_relock(trans);
-			if (ret) {
+			if (!bch2_btree_node_relock(trans, ck_path, 0)) {
 				kfree(new_k);
+				trace_and_count(trans->c, trans_restart_relock_key_cache_fill, trans, _THIS_IP_, ck_path);
+				ret = btree_trans_restart(trans, BCH_ERR_transaction_restart_key_cache_fill);
 				goto err;
 			}
 		}
-- 
GitLab


From 82af5ceb5d9d1f0613be3b9161ec1104b85f00b8 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sun, 26 May 2024 22:22:30 -0400
Subject: [PATCH 355/950] bcachefs: Refactor delete_dead_snapshots()

Consolidate per-key work into delete_dead_snapshots_process_key(), so we
now walk all keys once, not twice.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/snapshot.c | 65 ++++++++++++++++--------------------------
 1 file changed, 25 insertions(+), 40 deletions(-)

diff --git a/fs/bcachefs/snapshot.c b/fs/bcachefs/snapshot.c
index 629900a5e6411..466fa3e6a4b65 100644
--- a/fs/bcachefs/snapshot.c
+++ b/fs/bcachefs/snapshot.c
@@ -1351,7 +1351,7 @@ int bch2_snapshot_node_create(struct btree_trans *trans, u32 parent,
  * that key to snapshot leaf nodes, where we can mutate it
  */
 
-static int snapshot_delete_key(struct btree_trans *trans,
+static int delete_dead_snapshots_process_key(struct btree_trans *trans,
 			       struct btree_iter *iter,
 			       struct bkey_s_c k,
 			       snapshot_id_list *deleted,
@@ -1360,26 +1360,26 @@ static int snapshot_delete_key(struct btree_trans *trans,
 {
 	struct bch_fs *c = trans->c;
 	u32 equiv = bch2_snapshot_equiv(c, k.k->p.snapshot);
+	if (!equiv) /* key for invalid snapshot node, but we chose not to delete */
+		return 0;
 
 	if (!bkey_eq(k.k->p, *last_pos))
 		equiv_seen->nr = 0;
-	*last_pos = k.k->p;
 
-	if (snapshot_list_has_id(deleted, k.k->p.snapshot) ||
-	    snapshot_list_has_id(equiv_seen, equiv)) {
+	if (snapshot_list_has_id(deleted, k.k->p.snapshot))
 		return bch2_btree_delete_at(trans, iter,
 					    BTREE_UPDATE_internal_snapshot_node);
-	} else {
-		return snapshot_list_add(c, equiv_seen, equiv);
-	}
-}
 
-static int move_key_to_correct_snapshot(struct btree_trans *trans,
-			       struct btree_iter *iter,
-			       struct bkey_s_c k)
-{
-	struct bch_fs *c = trans->c;
-	u32 equiv = bch2_snapshot_equiv(c, k.k->p.snapshot);
+	if (!bpos_eq(*last_pos, k.k->p) &&
+	    snapshot_list_has_id(equiv_seen, equiv))
+		return bch2_btree_delete_at(trans, iter,
+					    BTREE_UPDATE_internal_snapshot_node);
+
+	*last_pos = k.k->p;
+
+	int ret = snapshot_list_add_nodup(c, equiv_seen, equiv);
+	if (ret)
+		return ret;
 
 	/*
 	 * When we have a linear chain of snapshot nodes, we consider
@@ -1389,21 +1389,20 @@ static int move_key_to_correct_snapshot(struct btree_trans *trans,
 	 *
 	 * If there are multiple keys in different snapshots at the same
 	 * position, we're only going to keep the one in the newest
-	 * snapshot - the rest have been overwritten and are redundant,
-	 * and for the key we're going to keep we need to move it to the
-	 * equivalance class ID if it's not there already.
+	 * snapshot (we delete the others above) - the rest have been
+	 * overwritten and are redundant, and for the key we're going to keep we
+	 * need to move it to the equivalance class ID if it's not there
+	 * already.
 	 */
 	if (equiv != k.k->p.snapshot) {
 		struct bkey_i *new = bch2_bkey_make_mut_noupdate(trans, k);
-		struct btree_iter new_iter;
-		int ret;
-
-		ret = PTR_ERR_OR_ZERO(new);
+		int ret = PTR_ERR_OR_ZERO(new);
 		if (ret)
 			return ret;
 
 		new->k.p.snapshot = equiv;
 
+		struct btree_iter new_iter;
 		bch2_trans_iter_init(trans, &new_iter, iter->btree_id, new->k.p,
 				     BTREE_ITER_all_snapshots|
 				     BTREE_ITER_cached|
@@ -1538,7 +1537,6 @@ int bch2_delete_dead_snapshots(struct bch_fs *c)
 	struct btree_trans *trans;
 	snapshot_id_list deleted = { 0 };
 	snapshot_id_list deleted_interior = { 0 };
-	u32 id;
 	int ret = 0;
 
 	if (!test_and_clear_bit(BCH_FS_need_delete_dead_snapshots, &c->flags))
@@ -1585,33 +1583,20 @@ int bch2_delete_dead_snapshots(struct bch_fs *c)
 	if (ret)
 		goto err;
 
-	for (id = 0; id < BTREE_ID_NR; id++) {
+	for (unsigned btree = 0; btree < BTREE_ID_NR; btree++) {
 		struct bpos last_pos = POS_MIN;
 		snapshot_id_list equiv_seen = { 0 };
 		struct disk_reservation res = { 0 };
 
-		if (!btree_type_has_snapshots(id))
-			continue;
-
-		/*
-		 * deleted inodes btree is maintained by a trigger on the inodes
-		 * btree - no work for us to do here, and it's not safe to scan
-		 * it because we'll see out of date keys due to the btree write
-		 * buffer:
-		 */
-		if (id == BTREE_ID_deleted_inodes)
+		if (!btree_type_has_snapshots(btree))
 			continue;
 
 		ret = for_each_btree_key_commit(trans, iter,
-				id, POS_MIN,
-				BTREE_ITER_prefetch|BTREE_ITER_all_snapshots, k,
-				&res, NULL, BCH_TRANS_COMMIT_no_enospc,
-			snapshot_delete_key(trans, &iter, k, &deleted, &equiv_seen, &last_pos)) ?:
-		      for_each_btree_key_commit(trans, iter,
-				id, POS_MIN,
+				btree, POS_MIN,
 				BTREE_ITER_prefetch|BTREE_ITER_all_snapshots, k,
 				&res, NULL, BCH_TRANS_COMMIT_no_enospc,
-			move_key_to_correct_snapshot(trans, &iter, k));
+			delete_dead_snapshots_process_key(trans, &iter, k, &deleted,
+							  &equiv_seen, &last_pos));
 
 		bch2_disk_reservation_put(c, &res);
 		darray_exit(&equiv_seen);
-- 
GitLab


From 08f50005e09f3bf74a7cb5fd86335d3c4077df51 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sun, 26 May 2024 12:38:30 -0400
Subject: [PATCH 356/950] bcachefs: Run check_key_has_snapshot in
 snapshot_delete_keys()

delete_dead_snapshots now runs before the main fsck.c passes which check
for keys for invalid snapshots; thus, it needs those checks as well.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/fsck.c     | 27 ++++-----------------------
 fs/bcachefs/snapshot.c | 25 ++++++++++++++++++++++++-
 fs/bcachefs/snapshot.h |  1 +
 3 files changed, 29 insertions(+), 24 deletions(-)

diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c
index 4cd28db9bad8d..fd277bd58ed34 100644
--- a/fs/bcachefs/fsck.c
+++ b/fs/bcachefs/fsck.c
@@ -766,25 +766,6 @@ static int get_visible_inodes(struct btree_trans *trans,
 	return ret;
 }
 
-static int check_key_has_snapshot(struct btree_trans *trans,
-				  struct btree_iter *iter,
-				  struct bkey_s_c k)
-{
-	struct bch_fs *c = trans->c;
-	struct printbuf buf = PRINTBUF;
-	int ret = 0;
-
-	if (mustfix_fsck_err_on(!bch2_snapshot_equiv(c, k.k->p.snapshot), c,
-				bkey_in_missing_snapshot,
-				"key in missing snapshot: %s",
-				(bch2_bkey_val_to_text(&buf, c, k), buf.buf)))
-		ret = bch2_btree_delete_at(trans, iter,
-					    BTREE_UPDATE_internal_snapshot_node) ?: 1;
-fsck_err:
-	printbuf_exit(&buf);
-	return ret;
-}
-
 static int hash_redo_key(struct btree_trans *trans,
 			 const struct bch_hash_desc desc,
 			 struct bch_hash_info *hash_info,
@@ -979,7 +960,7 @@ static int check_inode(struct btree_trans *trans,
 	bool do_update = false;
 	int ret;
 
-	ret = check_key_has_snapshot(trans, iter, k);
+	ret = bch2_check_key_has_snapshot(trans, iter, k);
 	if (ret < 0)
 		goto err;
 	if (ret)
@@ -1483,7 +1464,7 @@ static int check_extent(struct btree_trans *trans, struct btree_iter *iter,
 	struct printbuf buf = PRINTBUF;
 	int ret = 0;
 
-	ret = check_key_has_snapshot(trans, iter, k);
+	ret = bch2_check_key_has_snapshot(trans, iter, k);
 	if (ret) {
 		ret = ret < 0 ? ret : 0;
 		goto out;
@@ -2006,7 +1987,7 @@ static int check_dirent(struct btree_trans *trans, struct btree_iter *iter,
 	struct printbuf buf = PRINTBUF;
 	int ret = 0;
 
-	ret = check_key_has_snapshot(trans, iter, k);
+	ret = bch2_check_key_has_snapshot(trans, iter, k);
 	if (ret) {
 		ret = ret < 0 ? ret : 0;
 		goto out;
@@ -2161,7 +2142,7 @@ static int check_xattr(struct btree_trans *trans, struct btree_iter *iter,
 	struct inode_walker_entry *i;
 	int ret;
 
-	ret = check_key_has_snapshot(trans, iter, k);
+	ret = bch2_check_key_has_snapshot(trans, iter, k);
 	if (ret < 0)
 		return ret;
 	if (ret)
diff --git a/fs/bcachefs/snapshot.c b/fs/bcachefs/snapshot.c
index 466fa3e6a4b65..51918acfd7268 100644
--- a/fs/bcachefs/snapshot.c
+++ b/fs/bcachefs/snapshot.c
@@ -1042,6 +1042,25 @@ err:
 	return ret;
 }
 
+int bch2_check_key_has_snapshot(struct btree_trans *trans,
+				struct btree_iter *iter,
+				struct bkey_s_c k)
+{
+	struct bch_fs *c = trans->c;
+	struct printbuf buf = PRINTBUF;
+	int ret = 0;
+
+	if (fsck_err_on(!bch2_snapshot_equiv(c, k.k->p.snapshot), c,
+			bkey_in_missing_snapshot,
+			"key in missing snapshot %s, delete?",
+			(bch2_bkey_val_to_text(&buf, c, k), buf.buf)))
+		ret = bch2_btree_delete_at(trans, iter,
+					    BTREE_UPDATE_internal_snapshot_node) ?: 1;
+fsck_err:
+	printbuf_exit(&buf);
+	return ret;
+}
+
 /*
  * Mark a snapshot as deleted, for future cleanup:
  */
@@ -1358,6 +1377,10 @@ static int delete_dead_snapshots_process_key(struct btree_trans *trans,
 			       snapshot_id_list *equiv_seen,
 			       struct bpos *last_pos)
 {
+	int ret = bch2_check_key_has_snapshot(trans, iter, k);
+	if (ret)
+		return ret < 0 ? ret : 0;
+
 	struct bch_fs *c = trans->c;
 	u32 equiv = bch2_snapshot_equiv(c, k.k->p.snapshot);
 	if (!equiv) /* key for invalid snapshot node, but we chose not to delete */
@@ -1377,7 +1400,7 @@ static int delete_dead_snapshots_process_key(struct btree_trans *trans,
 
 	*last_pos = k.k->p;
 
-	int ret = snapshot_list_add_nodup(c, equiv_seen, equiv);
+	ret = snapshot_list_add_nodup(c, equiv_seen, equiv);
 	if (ret)
 		return ret;
 
diff --git a/fs/bcachefs/snapshot.h b/fs/bcachefs/snapshot.h
index ab13d8f4b41e1..31b0ee03e9628 100644
--- a/fs/bcachefs/snapshot.h
+++ b/fs/bcachefs/snapshot.h
@@ -242,6 +242,7 @@ int bch2_snapshot_node_create(struct btree_trans *, u32,
 int bch2_check_snapshot_trees(struct bch_fs *);
 int bch2_check_snapshots(struct bch_fs *);
 int bch2_reconstruct_snapshots(struct bch_fs *);
+int bch2_check_key_has_snapshot(struct btree_trans *, struct btree_iter *, struct bkey_s_c);
 
 int bch2_snapshot_node_set_deleted(struct btree_trans *, u32);
 void bch2_delete_dead_snapshots_work(struct work_struct *);
-- 
GitLab


From 247c056bde2ebc9fad2fc62332dc7cc99b58d720 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 27 May 2024 16:30:19 -0400
Subject: [PATCH 357/950] bcachefs: Fix setting of downgrade recovery
 passes/errors

bch2_check_version_downgrade() was setting c->sb.version, which
bch2_sb_set_downgrade() expects to be at the previous version; and it
shouldn't even have been set directly because c->sb.version is updated
by write_super().

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/super-io.c | 12 +++---------
 1 file changed, 3 insertions(+), 9 deletions(-)

diff --git a/fs/bcachefs/super-io.c b/fs/bcachefs/super-io.c
index f1bee6c5222d2..d73a0222f7095 100644
--- a/fs/bcachefs/super-io.c
+++ b/fs/bcachefs/super-io.c
@@ -1132,18 +1132,12 @@ bool bch2_check_version_downgrade(struct bch_fs *c)
 	 * c->sb will be checked before we write the superblock, so update it as
 	 * well:
 	 */
-	if (BCH_SB_VERSION_UPGRADE_COMPLETE(c->disk_sb.sb) > bcachefs_metadata_version_current) {
+	if (BCH_SB_VERSION_UPGRADE_COMPLETE(c->disk_sb.sb) > bcachefs_metadata_version_current)
 		SET_BCH_SB_VERSION_UPGRADE_COMPLETE(c->disk_sb.sb, bcachefs_metadata_version_current);
-		c->sb.version_upgrade_complete = bcachefs_metadata_version_current;
-	}
-	if (c->sb.version > bcachefs_metadata_version_current) {
+	if (c->sb.version > bcachefs_metadata_version_current)
 		c->disk_sb.sb->version = cpu_to_le16(bcachefs_metadata_version_current);
-		c->sb.version = bcachefs_metadata_version_current;
-	}
-	if (c->sb.version_min > bcachefs_metadata_version_current) {
+	if (c->sb.version_min > bcachefs_metadata_version_current)
 		c->disk_sb.sb->version_min = cpu_to_le16(bcachefs_metadata_version_current);
-		c->sb.version_min = bcachefs_metadata_version_current;
-	}
 	c->disk_sb.sb->compat[0] &= cpu_to_le64((1ULL << BCH_COMPAT_NR) - 1);
 	return ret;
 }
-- 
GitLab


From b4131076c16fdd2bc6cb09cfa7e0cfe278aa49a1 Mon Sep 17 00:00:00 2001
From: Jeff Johnson <quic_jjohnson@quicinc.com>
Date: Mon, 27 May 2024 12:01:18 -0700
Subject: [PATCH 358/950] bcachefs: add missing MODULE_DESCRIPTION()

Fix the 'make W=1' warning:
WARNING: modpost: missing MODULE_DESCRIPTION() in fs/bcachefs/mean_and_variance_test.o

Signed-off-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/mean_and_variance_test.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/bcachefs/mean_and_variance_test.c b/fs/bcachefs/mean_and_variance_test.c
index 4c298e74723db..e9d9c0212e44b 100644
--- a/fs/bcachefs/mean_and_variance_test.c
+++ b/fs/bcachefs/mean_and_variance_test.c
@@ -217,4 +217,5 @@ static struct kunit_suite mean_and_variance_test_suite = {
 kunit_test_suite(mean_and_variance_test_suite);
 
 MODULE_AUTHOR("Daniel B. Hill");
+MODULE_DESCRIPTION("bcachefs filesystem mean and variance unit tests");
 MODULE_LICENSE("GPL");
-- 
GitLab


From 088d0de81220a74d7d553febb81656927f10bb16 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 27 May 2024 18:40:50 -0400
Subject: [PATCH 359/950] bcachefs: btree_gc can now handle unknown btrees

Compatibility fix - we no longer have a separate table for which order
gc walks btrees in, and special case the stripes btree directly.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/bcachefs.h       | 44 +-----------------------------------
 fs/bcachefs/btree_gc.c       |  9 ++++----
 fs/bcachefs/btree_gc.h       | 44 ++++++++++++++++--------------------
 fs/bcachefs/btree_gc_types.h | 29 ++++++++++++++++++++++++
 fs/bcachefs/ec.c             |  2 +-
 5 files changed, 55 insertions(+), 73 deletions(-)
 create mode 100644 fs/bcachefs/btree_gc_types.h

diff --git a/fs/bcachefs/bcachefs.h b/fs/bcachefs/bcachefs.h
index bc0ea2c4efef2..2a538eb2af110 100644
--- a/fs/bcachefs/bcachefs.h
+++ b/fs/bcachefs/bcachefs.h
@@ -457,6 +457,7 @@ enum bch_time_stats {
 };
 
 #include "alloc_types.h"
+#include "btree_gc_types.h"
 #include "btree_types.h"
 #include "btree_node_scan_types.h"
 #include "btree_write_buffer_types.h"
@@ -488,49 +489,6 @@ enum bch_time_stats {
 
 struct btree;
 
-enum gc_phase {
-	GC_PHASE_NOT_RUNNING,
-	GC_PHASE_START,
-	GC_PHASE_SB,
-
-	GC_PHASE_BTREE_stripes,
-	GC_PHASE_BTREE_extents,
-	GC_PHASE_BTREE_inodes,
-	GC_PHASE_BTREE_dirents,
-	GC_PHASE_BTREE_xattrs,
-	GC_PHASE_BTREE_alloc,
-	GC_PHASE_BTREE_quotas,
-	GC_PHASE_BTREE_reflink,
-	GC_PHASE_BTREE_subvolumes,
-	GC_PHASE_BTREE_snapshots,
-	GC_PHASE_BTREE_lru,
-	GC_PHASE_BTREE_freespace,
-	GC_PHASE_BTREE_need_discard,
-	GC_PHASE_BTREE_backpointers,
-	GC_PHASE_BTREE_bucket_gens,
-	GC_PHASE_BTREE_snapshot_trees,
-	GC_PHASE_BTREE_deleted_inodes,
-	GC_PHASE_BTREE_logged_ops,
-	GC_PHASE_BTREE_rebalance_work,
-	GC_PHASE_BTREE_subvolume_children,
-
-	GC_PHASE_PENDING_DELETE,
-};
-
-struct gc_pos {
-	enum gc_phase		phase;
-	u16			level;
-	struct bpos		pos;
-};
-
-struct reflink_gc {
-	u64		offset;
-	u32		size;
-	u32		refcount;
-};
-
-typedef GENRADIX(struct reflink_gc) reflink_gc_table;
-
 struct io_count {
 	u64			sectors[2][BCH_DATA_NR];
 };
diff --git a/fs/bcachefs/btree_gc.c b/fs/bcachefs/btree_gc.c
index 8035c8b797ab3..e9e901feda291 100644
--- a/fs/bcachefs/btree_gc.c
+++ b/fs/bcachefs/btree_gc.c
@@ -673,8 +673,7 @@ static int bch2_gc_btree(struct btree_trans *trans, enum btree_id btree, bool in
 
 static inline int btree_id_gc_phase_cmp(enum btree_id l, enum btree_id r)
 {
-	return  (int) btree_id_to_gc_phase(l) -
-		(int) btree_id_to_gc_phase(r);
+	return cmp_int(gc_btree_order(l), gc_btree_order(r));
 }
 
 static int bch2_gc_btrees(struct bch_fs *c)
@@ -711,7 +710,7 @@ fsck_err:
 static int bch2_mark_superblocks(struct bch_fs *c)
 {
 	mutex_lock(&c->sb_lock);
-	gc_pos_set(c, gc_phase(GC_PHASE_SB));
+	gc_pos_set(c, gc_phase(GC_PHASE_sb));
 
 	int ret = bch2_trans_mark_dev_sbs_flags(c, BTREE_TRIGGER_gc);
 	mutex_unlock(&c->sb_lock);
@@ -1209,7 +1208,7 @@ int bch2_check_allocations(struct bch_fs *c)
 	if (ret)
 		goto out;
 
-	gc_pos_set(c, gc_phase(GC_PHASE_START));
+	gc_pos_set(c, gc_phase(GC_PHASE_start));
 
 	ret = bch2_mark_superblocks(c);
 	BUG_ON(ret);
@@ -1231,7 +1230,7 @@ out:
 
 	percpu_down_write(&c->mark_lock);
 	/* Indicates that gc is no longer in progress: */
-	__gc_pos_set(c, gc_phase(GC_PHASE_NOT_RUNNING));
+	__gc_pos_set(c, gc_phase(GC_PHASE_not_running));
 
 	bch2_gc_free(c);
 	percpu_up_write(&c->mark_lock);
diff --git a/fs/bcachefs/btree_gc.h b/fs/bcachefs/btree_gc.h
index 1b6489d8e0f4f..876d81e2017d7 100644
--- a/fs/bcachefs/btree_gc.h
+++ b/fs/bcachefs/btree_gc.h
@@ -3,6 +3,7 @@
 #define _BCACHEFS_BTREE_GC_H
 
 #include "bkey.h"
+#include "btree_gc_types.h"
 #include "btree_types.h"
 
 int bch2_check_topology(struct bch_fs *);
@@ -32,36 +33,15 @@ int bch2_check_allocations(struct bch_fs *);
 /* Position of (the start of) a gc phase: */
 static inline struct gc_pos gc_phase(enum gc_phase phase)
 {
-	return (struct gc_pos) {
-		.phase	= phase,
-		.level	= 0,
-		.pos	= POS_MIN,
-	};
-}
-
-static inline int gc_pos_cmp(struct gc_pos l, struct gc_pos r)
-{
-	return   cmp_int(l.phase, r.phase) ?:
-		-cmp_int(l.level, r.level) ?:
-		 bpos_cmp(l.pos, r.pos);
-}
-
-static inline enum gc_phase btree_id_to_gc_phase(enum btree_id id)
-{
-	switch (id) {
-#define x(name, v, ...) case BTREE_ID_##name: return GC_PHASE_BTREE_##name;
-	BCH_BTREE_IDS()
-#undef x
-	default:
-		BUG();
-	}
+	return (struct gc_pos) { .phase	= phase, };
 }
 
 static inline struct gc_pos gc_pos_btree(enum btree_id btree, unsigned level,
 					 struct bpos pos)
 {
 	return (struct gc_pos) {
-		.phase	= btree_id_to_gc_phase(btree),
+		.phase	= GC_PHASE_btree,
+		.btree	= btree,
 		.level	= level,
 		.pos	= pos,
 	};
@@ -76,6 +56,22 @@ static inline struct gc_pos gc_pos_btree_node(struct btree *b)
 	return gc_pos_btree(b->c.btree_id, b->c.level, b->key.k.p);
 }
 
+static inline int gc_btree_order(enum btree_id btree)
+{
+	if (btree == BTREE_ID_stripes)
+		return -1;
+	return btree;
+}
+
+static inline int gc_pos_cmp(struct gc_pos l, struct gc_pos r)
+{
+	return   cmp_int(l.phase, r.phase) ?:
+		 cmp_int(gc_btree_order(l.btree),
+			 gc_btree_order(r.btree)) ?:
+		-cmp_int(l.level, r.level) ?:
+		 bpos_cmp(l.pos, r.pos);
+}
+
 static inline bool gc_visited(struct bch_fs *c, struct gc_pos pos)
 {
 	unsigned seq;
diff --git a/fs/bcachefs/btree_gc_types.h b/fs/bcachefs/btree_gc_types.h
new file mode 100644
index 0000000000000..b82c24bcc0880
--- /dev/null
+++ b/fs/bcachefs/btree_gc_types.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _BCACHEFS_BTREE_GC_TYPES_H
+#define _BCACHEFS_BTREE_GC_TYPES_H
+
+#include <linux/generic-radix-tree.h>
+
+enum gc_phase {
+	GC_PHASE_not_running,
+	GC_PHASE_start,
+	GC_PHASE_sb,
+	GC_PHASE_btree,
+};
+
+struct gc_pos {
+	enum gc_phase		phase:8;
+	enum btree_id		btree:8;
+	u16			level;
+	struct bpos		pos;
+};
+
+struct reflink_gc {
+	u64		offset;
+	u32		size;
+	u32		refcount;
+};
+
+typedef GENRADIX(struct reflink_gc) reflink_gc_table;
+
+#endif /* _BCACHEFS_BTREE_GC_TYPES_H */
diff --git a/fs/bcachefs/ec.c b/fs/bcachefs/ec.c
index b26dc74246623..d8b9beca37762 100644
--- a/fs/bcachefs/ec.c
+++ b/fs/bcachefs/ec.c
@@ -908,7 +908,7 @@ static int __ec_stripe_mem_alloc(struct bch_fs *c, size_t idx, gfp_t gfp)
 	if (!genradix_ptr_alloc(&c->stripes, idx, gfp))
 		return -BCH_ERR_ENOMEM_ec_stripe_mem_alloc;
 
-	if (c->gc_pos.phase != GC_PHASE_NOT_RUNNING &&
+	if (c->gc_pos.phase != GC_PHASE_not_running &&
 	    !genradix_ptr_alloc(&c->gc_stripes, idx, gfp))
 		return -BCH_ERR_ENOMEM_ec_stripe_mem_alloc;
 
-- 
GitLab


From f1d4fed13fa0c0f8c99cdbbc27460f1e1f46fd4e Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 27 May 2024 19:17:09 -0400
Subject: [PATCH 360/950] bcachefs: Better fsck error message for key version

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/btree_gc.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/fs/bcachefs/btree_gc.c b/fs/bcachefs/btree_gc.c
index e9e901feda291..dc97991bcd6ad 100644
--- a/fs/bcachefs/btree_gc.c
+++ b/fs/bcachefs/btree_gc.c
@@ -585,16 +585,17 @@ static int bch2_gc_mark_key(struct btree_trans *trans, enum btree_id btree_id,
 
 		if (fsck_err_on(k.k->version.lo > atomic64_read(&c->key_version), c,
 				bkey_version_in_future,
-				"key version number higher than recorded: %llu > %llu",
-				k.k->version.lo,
-				atomic64_read(&c->key_version)))
+				"key version number higher than recorded %llu\n  %s",
+				atomic64_read(&c->key_version),
+				(bch2_bkey_val_to_text(&buf, c, k), buf.buf)))
 			atomic64_set(&c->key_version, k.k->version.lo);
 	}
 
 	if (mustfix_fsck_err_on(level && !bch2_dev_btree_bitmap_marked(c, k),
 				c, btree_bitmap_not_marked,
 				"btree ptr not marked in member info btree allocated bitmap\n  %s",
-				(bch2_bkey_val_to_text(&buf, c, k),
+				(printbuf_reset(&buf),
+				 bch2_bkey_val_to_text(&buf, c, k),
 				 buf.buf))) {
 		mutex_lock(&c->sb_lock);
 		bch2_dev_btree_bitmap_mark(c, k);
-- 
GitLab


From be647e2c76b27f409cdd520f66c95be888b553a3 Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Tue, 21 May 2024 06:41:45 -0700
Subject: [PATCH 361/950] nvme: use srcu for iterating namespace list

The nvme pci driver synchronizes with all the namespace queues during a
reset to ensure that there's no pending timeout work.

Meanwhile the timeout work potentially iterates those same namespaces to
freeze their queues.

Each of those namespace iterations use the same read lock. If a write
lock should somehow get between the synchronize and freeze steps, then
forward progress is deadlocked.

We had been relying on the nvme controller state machine to ensure the
reset work wouldn't conflict with timeout work. That guarantee may be a
bit fragile to rely on, so iterate the namespace lists without taking
potentially circular locks, as reported by lockdep.

Link: https://lore.kernel.org/all/20220930001943.zdbvolc3gkekfmcv@shindev/
Reported-by: Shinichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Tested-by: Shinichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/core.c      | 99 +++++++++++++++++++++--------------
 drivers/nvme/host/ioctl.c     | 15 +++---
 drivers/nvme/host/multipath.c | 21 ++++----
 drivers/nvme/host/nvme.h      |  4 +-
 4 files changed, 83 insertions(+), 56 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 7706df2373494..f5d150c62955d 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -678,7 +678,7 @@ static void nvme_free_ns(struct kref *kref)
 	kfree(ns);
 }
 
-static inline bool nvme_get_ns(struct nvme_ns *ns)
+bool nvme_get_ns(struct nvme_ns *ns)
 {
 	return kref_get_unless_zero(&ns->kref);
 }
@@ -3684,9 +3684,10 @@ out_unlock:
 struct nvme_ns *nvme_find_get_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 {
 	struct nvme_ns *ns, *ret = NULL;
+	int srcu_idx;
 
-	down_read(&ctrl->namespaces_rwsem);
-	list_for_each_entry(ns, &ctrl->namespaces, list) {
+	srcu_idx = srcu_read_lock(&ctrl->srcu);
+	list_for_each_entry_rcu(ns, &ctrl->namespaces, list) {
 		if (ns->head->ns_id == nsid) {
 			if (!nvme_get_ns(ns))
 				continue;
@@ -3696,7 +3697,7 @@ struct nvme_ns *nvme_find_get_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 		if (ns->head->ns_id > nsid)
 			break;
 	}
-	up_read(&ctrl->namespaces_rwsem);
+	srcu_read_unlock(&ctrl->srcu, srcu_idx);
 	return ret;
 }
 EXPORT_SYMBOL_NS_GPL(nvme_find_get_ns, NVME_TARGET_PASSTHRU);
@@ -3710,7 +3711,7 @@ static void nvme_ns_add_to_ctrl_list(struct nvme_ns *ns)
 
 	list_for_each_entry_reverse(tmp, &ns->ctrl->namespaces, list) {
 		if (tmp->head->ns_id < ns->head->ns_id) {
-			list_add(&ns->list, &tmp->list);
+			list_add_rcu(&ns->list, &tmp->list);
 			return;
 		}
 	}
@@ -3776,17 +3777,18 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info)
 	if (nvme_update_ns_info(ns, info))
 		goto out_unlink_ns;
 
-	down_write(&ctrl->namespaces_rwsem);
+	mutex_lock(&ctrl->namespaces_lock);
 	/*
 	 * Ensure that no namespaces are added to the ctrl list after the queues
 	 * are frozen, thereby avoiding a deadlock between scan and reset.
 	 */
 	if (test_bit(NVME_CTRL_FROZEN, &ctrl->flags)) {
-		up_write(&ctrl->namespaces_rwsem);
+		mutex_unlock(&ctrl->namespaces_lock);
 		goto out_unlink_ns;
 	}
 	nvme_ns_add_to_ctrl_list(ns);
-	up_write(&ctrl->namespaces_rwsem);
+	mutex_unlock(&ctrl->namespaces_lock);
+	synchronize_srcu(&ctrl->srcu);
 	nvme_get_ctrl(ctrl);
 
 	if (device_add_disk(ctrl->device, ns->disk, nvme_ns_attr_groups))
@@ -3809,9 +3811,10 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info)
 
  out_cleanup_ns_from_list:
 	nvme_put_ctrl(ctrl);
-	down_write(&ctrl->namespaces_rwsem);
-	list_del_init(&ns->list);
-	up_write(&ctrl->namespaces_rwsem);
+	mutex_lock(&ctrl->namespaces_lock);
+	list_del_rcu(&ns->list);
+	mutex_unlock(&ctrl->namespaces_lock);
+	synchronize_srcu(&ctrl->srcu);
  out_unlink_ns:
 	mutex_lock(&ctrl->subsys->lock);
 	list_del_rcu(&ns->siblings);
@@ -3861,9 +3864,10 @@ static void nvme_ns_remove(struct nvme_ns *ns)
 		nvme_cdev_del(&ns->cdev, &ns->cdev_device);
 	del_gendisk(ns->disk);
 
-	down_write(&ns->ctrl->namespaces_rwsem);
-	list_del_init(&ns->list);
-	up_write(&ns->ctrl->namespaces_rwsem);
+	mutex_lock(&ns->ctrl->namespaces_lock);
+	list_del_rcu(&ns->list);
+	mutex_unlock(&ns->ctrl->namespaces_lock);
+	synchronize_srcu(&ns->ctrl->srcu);
 
 	if (last_path)
 		nvme_mpath_shutdown_disk(ns->head);
@@ -3953,16 +3957,17 @@ static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl,
 	struct nvme_ns *ns, *next;
 	LIST_HEAD(rm_list);
 
-	down_write(&ctrl->namespaces_rwsem);
+	mutex_lock(&ctrl->namespaces_lock);
 	list_for_each_entry_safe(ns, next, &ctrl->namespaces, list) {
 		if (ns->head->ns_id > nsid)
-			list_move_tail(&ns->list, &rm_list);
+			list_splice_init_rcu(&ns->list, &rm_list,
+					     synchronize_rcu);
 	}
-	up_write(&ctrl->namespaces_rwsem);
+	mutex_unlock(&ctrl->namespaces_lock);
+	synchronize_srcu(&ctrl->srcu);
 
 	list_for_each_entry_safe(ns, next, &rm_list, list)
 		nvme_ns_remove(ns);
-
 }
 
 static int nvme_scan_ns_list(struct nvme_ctrl *ctrl)
@@ -4132,9 +4137,10 @@ void nvme_remove_namespaces(struct nvme_ctrl *ctrl)
 	/* this is a no-op when called from the controller reset handler */
 	nvme_change_ctrl_state(ctrl, NVME_CTRL_DELETING_NOIO);
 
-	down_write(&ctrl->namespaces_rwsem);
-	list_splice_init(&ctrl->namespaces, &ns_list);
-	up_write(&ctrl->namespaces_rwsem);
+	mutex_lock(&ctrl->namespaces_lock);
+	list_splice_init_rcu(&ctrl->namespaces, &ns_list, synchronize_rcu);
+	mutex_unlock(&ctrl->namespaces_lock);
+	synchronize_srcu(&ctrl->srcu);
 
 	list_for_each_entry_safe(ns, next, &ns_list, list)
 		nvme_ns_remove(ns);
@@ -4582,6 +4588,7 @@ static void nvme_free_ctrl(struct device *dev)
 	key_put(ctrl->tls_key);
 	nvme_free_cels(ctrl);
 	nvme_mpath_uninit(ctrl);
+	cleanup_srcu_struct(&ctrl->srcu);
 	nvme_auth_stop(ctrl);
 	nvme_auth_free(ctrl);
 	__free_page(ctrl->discard_page);
@@ -4614,10 +4621,15 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 	ctrl->passthru_err_log_enabled = false;
 	clear_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags);
 	spin_lock_init(&ctrl->lock);
+	mutex_init(&ctrl->namespaces_lock);
+
+	ret = init_srcu_struct(&ctrl->srcu);
+	if (ret)
+		return ret;
+
 	mutex_init(&ctrl->scan_lock);
 	INIT_LIST_HEAD(&ctrl->namespaces);
 	xa_init(&ctrl->cels);
-	init_rwsem(&ctrl->namespaces_rwsem);
 	ctrl->dev = dev;
 	ctrl->ops = ops;
 	ctrl->quirks = quirks;
@@ -4697,6 +4709,7 @@ out_release_instance:
 out:
 	if (ctrl->discard_page)
 		__free_page(ctrl->discard_page);
+	cleanup_srcu_struct(&ctrl->srcu);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(nvme_init_ctrl);
@@ -4705,22 +4718,24 @@ EXPORT_SYMBOL_GPL(nvme_init_ctrl);
 void nvme_mark_namespaces_dead(struct nvme_ctrl *ctrl)
 {
 	struct nvme_ns *ns;
+	int srcu_idx;
 
-	down_read(&ctrl->namespaces_rwsem);
-	list_for_each_entry(ns, &ctrl->namespaces, list)
+	srcu_idx = srcu_read_lock(&ctrl->srcu);
+	list_for_each_entry_rcu(ns, &ctrl->namespaces, list)
 		blk_mark_disk_dead(ns->disk);
-	up_read(&ctrl->namespaces_rwsem);
+	srcu_read_unlock(&ctrl->srcu, srcu_idx);
 }
 EXPORT_SYMBOL_GPL(nvme_mark_namespaces_dead);
 
 void nvme_unfreeze(struct nvme_ctrl *ctrl)
 {
 	struct nvme_ns *ns;
+	int srcu_idx;
 
-	down_read(&ctrl->namespaces_rwsem);
-	list_for_each_entry(ns, &ctrl->namespaces, list)
+	srcu_idx = srcu_read_lock(&ctrl->srcu);
+	list_for_each_entry_rcu(ns, &ctrl->namespaces, list)
 		blk_mq_unfreeze_queue(ns->queue);
-	up_read(&ctrl->namespaces_rwsem);
+	srcu_read_unlock(&ctrl->srcu, srcu_idx);
 	clear_bit(NVME_CTRL_FROZEN, &ctrl->flags);
 }
 EXPORT_SYMBOL_GPL(nvme_unfreeze);
@@ -4728,14 +4743,15 @@ EXPORT_SYMBOL_GPL(nvme_unfreeze);
 int nvme_wait_freeze_timeout(struct nvme_ctrl *ctrl, long timeout)
 {
 	struct nvme_ns *ns;
+	int srcu_idx;
 
-	down_read(&ctrl->namespaces_rwsem);
-	list_for_each_entry(ns, &ctrl->namespaces, list) {
+	srcu_idx = srcu_read_lock(&ctrl->srcu);
+	list_for_each_entry_rcu(ns, &ctrl->namespaces, list) {
 		timeout = blk_mq_freeze_queue_wait_timeout(ns->queue, timeout);
 		if (timeout <= 0)
 			break;
 	}
-	up_read(&ctrl->namespaces_rwsem);
+	srcu_read_unlock(&ctrl->srcu, srcu_idx);
 	return timeout;
 }
 EXPORT_SYMBOL_GPL(nvme_wait_freeze_timeout);
@@ -4743,23 +4759,25 @@ EXPORT_SYMBOL_GPL(nvme_wait_freeze_timeout);
 void nvme_wait_freeze(struct nvme_ctrl *ctrl)
 {
 	struct nvme_ns *ns;
+	int srcu_idx;
 
-	down_read(&ctrl->namespaces_rwsem);
-	list_for_each_entry(ns, &ctrl->namespaces, list)
+	srcu_idx = srcu_read_lock(&ctrl->srcu);
+	list_for_each_entry_rcu(ns, &ctrl->namespaces, list)
 		blk_mq_freeze_queue_wait(ns->queue);
-	up_read(&ctrl->namespaces_rwsem);
+	srcu_read_unlock(&ctrl->srcu, srcu_idx);
 }
 EXPORT_SYMBOL_GPL(nvme_wait_freeze);
 
 void nvme_start_freeze(struct nvme_ctrl *ctrl)
 {
 	struct nvme_ns *ns;
+	int srcu_idx;
 
 	set_bit(NVME_CTRL_FROZEN, &ctrl->flags);
-	down_read(&ctrl->namespaces_rwsem);
-	list_for_each_entry(ns, &ctrl->namespaces, list)
+	srcu_idx = srcu_read_lock(&ctrl->srcu);
+	list_for_each_entry_rcu(ns, &ctrl->namespaces, list)
 		blk_freeze_queue_start(ns->queue);
-	up_read(&ctrl->namespaces_rwsem);
+	srcu_read_unlock(&ctrl->srcu, srcu_idx);
 }
 EXPORT_SYMBOL_GPL(nvme_start_freeze);
 
@@ -4802,11 +4820,12 @@ EXPORT_SYMBOL_GPL(nvme_unquiesce_admin_queue);
 void nvme_sync_io_queues(struct nvme_ctrl *ctrl)
 {
 	struct nvme_ns *ns;
+	int srcu_idx;
 
-	down_read(&ctrl->namespaces_rwsem);
-	list_for_each_entry(ns, &ctrl->namespaces, list)
+	srcu_idx = srcu_read_lock(&ctrl->srcu);
+	list_for_each_entry_rcu(ns, &ctrl->namespaces, list)
 		blk_sync_queue(ns->queue);
-	up_read(&ctrl->namespaces_rwsem);
+	srcu_read_unlock(&ctrl->srcu, srcu_idx);
 }
 EXPORT_SYMBOL_GPL(nvme_sync_io_queues);
 
diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c
index 499a8bb7cac7d..9d9d2a127c4ec 100644
--- a/drivers/nvme/host/ioctl.c
+++ b/drivers/nvme/host/ioctl.c
@@ -789,15 +789,15 @@ static int nvme_dev_user_cmd(struct nvme_ctrl *ctrl, void __user *argp,
 		bool open_for_write)
 {
 	struct nvme_ns *ns;
-	int ret;
+	int ret, srcu_idx;
 
-	down_read(&ctrl->namespaces_rwsem);
+	srcu_idx = srcu_read_lock(&ctrl->srcu);
 	if (list_empty(&ctrl->namespaces)) {
 		ret = -ENOTTY;
 		goto out_unlock;
 	}
 
-	ns = list_first_entry(&ctrl->namespaces, struct nvme_ns, list);
+	ns = list_first_or_null_rcu(&ctrl->namespaces, struct nvme_ns, list);
 	if (ns != list_last_entry(&ctrl->namespaces, struct nvme_ns, list)) {
 		dev_warn(ctrl->device,
 			"NVME_IOCTL_IO_CMD not supported when multiple namespaces present!\n");
@@ -807,15 +807,18 @@ static int nvme_dev_user_cmd(struct nvme_ctrl *ctrl, void __user *argp,
 
 	dev_warn(ctrl->device,
 		"using deprecated NVME_IOCTL_IO_CMD ioctl on the char device!\n");
-	kref_get(&ns->kref);
-	up_read(&ctrl->namespaces_rwsem);
+	if (!nvme_get_ns(ns)) {
+		ret = -ENXIO;
+		goto out_unlock;
+	}
+	srcu_read_unlock(&ctrl->srcu, srcu_idx);
 
 	ret = nvme_user_cmd(ctrl, ns, argp, 0, open_for_write);
 	nvme_put_ns(ns);
 	return ret;
 
 out_unlock:
-	up_read(&ctrl->namespaces_rwsem);
+	srcu_read_unlock(&ctrl->srcu, srcu_idx);
 	return ret;
 }
 
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 1bee176fd850e..d8b6b4648eaff 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -151,16 +151,17 @@ void nvme_mpath_end_request(struct request *rq)
 void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl)
 {
 	struct nvme_ns *ns;
+	int srcu_idx;
 
-	down_read(&ctrl->namespaces_rwsem);
-	list_for_each_entry(ns, &ctrl->namespaces, list) {
+	srcu_idx = srcu_read_lock(&ctrl->srcu);
+	list_for_each_entry_rcu(ns, &ctrl->namespaces, list) {
 		if (!ns->head->disk)
 			continue;
 		kblockd_schedule_work(&ns->head->requeue_work);
 		if (nvme_ctrl_state(ns->ctrl) == NVME_CTRL_LIVE)
 			disk_uevent(ns->head->disk, KOBJ_CHANGE);
 	}
-	up_read(&ctrl->namespaces_rwsem);
+	srcu_read_unlock(&ctrl->srcu, srcu_idx);
 }
 
 static const char *nvme_ana_state_names[] = {
@@ -194,13 +195,14 @@ out:
 void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl)
 {
 	struct nvme_ns *ns;
+	int srcu_idx;
 
-	down_read(&ctrl->namespaces_rwsem);
-	list_for_each_entry(ns, &ctrl->namespaces, list) {
+	srcu_idx = srcu_read_lock(&ctrl->srcu);
+	list_for_each_entry_rcu(ns, &ctrl->namespaces, list) {
 		nvme_mpath_clear_current_path(ns);
 		kblockd_schedule_work(&ns->head->requeue_work);
 	}
-	up_read(&ctrl->namespaces_rwsem);
+	srcu_read_unlock(&ctrl->srcu, srcu_idx);
 }
 
 void nvme_mpath_revalidate_paths(struct nvme_ns *ns)
@@ -681,6 +683,7 @@ static int nvme_update_ana_state(struct nvme_ctrl *ctrl,
 	u32 nr_nsids = le32_to_cpu(desc->nnsids), n = 0;
 	unsigned *nr_change_groups = data;
 	struct nvme_ns *ns;
+	int srcu_idx;
 
 	dev_dbg(ctrl->device, "ANA group %d: %s.\n",
 			le32_to_cpu(desc->grpid),
@@ -692,8 +695,8 @@ static int nvme_update_ana_state(struct nvme_ctrl *ctrl,
 	if (!nr_nsids)
 		return 0;
 
-	down_read(&ctrl->namespaces_rwsem);
-	list_for_each_entry(ns, &ctrl->namespaces, list) {
+	srcu_idx = srcu_read_lock(&ctrl->srcu);
+	list_for_each_entry_rcu(ns, &ctrl->namespaces, list) {
 		unsigned nsid;
 again:
 		nsid = le32_to_cpu(desc->nsids[n]);
@@ -706,7 +709,7 @@ again:
 		if (ns->head->ns_id > nsid)
 			goto again;
 	}
-	up_read(&ctrl->namespaces_rwsem);
+	srcu_read_unlock(&ctrl->srcu, srcu_idx);
 	return 0;
 }
 
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index c43a30753d87a..f3a41133ac3f9 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -282,7 +282,8 @@ struct nvme_ctrl {
 	struct blk_mq_tag_set *tagset;
 	struct blk_mq_tag_set *admin_tagset;
 	struct list_head namespaces;
-	struct rw_semaphore namespaces_rwsem;
+	struct mutex namespaces_lock;
+	struct srcu_struct srcu;
 	struct device ctrl_device;
 	struct device *device;	/* char device */
 #ifdef CONFIG_NVME_HWMON
@@ -1160,6 +1161,7 @@ void nvme_passthru_end(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u32 effects,
 		       struct nvme_command *cmd, int status);
 struct nvme_ctrl *nvme_ctrl_from_file(struct file *file);
 struct nvme_ns *nvme_find_get_ns(struct nvme_ctrl *ctrl, unsigned nsid);
+bool nvme_get_ns(struct nvme_ns *ns);
 void nvme_put_ns(struct nvme_ns *ns);
 
 static inline bool nvme_multi_css(struct nvme_ctrl *ctrl)
-- 
GitLab


From c758b77d4a0a0ed3a1292b3fd7a2aeccd1a169a4 Mon Sep 17 00:00:00 2001
From: Sagi Grimberg <sagi@grimberg.me>
Date: Mon, 27 May 2024 22:38:52 +0300
Subject: [PATCH 362/950] nvmet: fix a possible leak when destroy a ctrl during
 qp establishment

In nvmet_sq_destroy we capture sq->ctrl early and if it is non-NULL we
know that a ctrl was allocated (in the admin connect request handler)
and we need to release pending AERs, clear ctrl->sqs and sq->ctrl
(for nvme-loop primarily), and drop the final reference on the ctrl.

However, a small window is possible where nvmet_sq_destroy starts (as
a result of the client giving up and disconnecting) concurrently with
the nvme admin connect cmd (which may be in an early stage). But *before*
kill_and_confirm of sq->ref (i.e. the admin connect managed to get an sq
live reference). In this case, sq->ctrl was allocated however after it was
captured in a local variable in nvmet_sq_destroy.
This prevented the final reference drop on the ctrl.

Solve this by re-capturing the sq->ctrl after all inflight request has
completed, where for sure sq->ctrl reference is final, and move forward
based on that.

This issue was observed in an environment with many hosts connecting
multiple ctrls simoutanuosly, creating a delay in allocating a ctrl
leading up to this race window.

Reported-by: Alex Turin <alex@vastdata.com>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/target/core.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index 2fde22323622e..06f0c587f3437 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -818,6 +818,15 @@ void nvmet_sq_destroy(struct nvmet_sq *sq)
 	percpu_ref_exit(&sq->ref);
 	nvmet_auth_sq_free(sq);
 
+	/*
+	 * we must reference the ctrl again after waiting for inflight IO
+	 * to complete. Because admin connect may have sneaked in after we
+	 * store sq->ctrl locally, but before we killed the percpu_ref. the
+	 * admin connect allocates and assigns sq->ctrl, which now needs a
+	 * final ref put, as this ctrl is going away.
+	 */
+	ctrl = sq->ctrl;
+
 	if (ctrl) {
 		/*
 		 * The teardown flow may take some time, and the host may not
-- 
GitLab


From a0fc1a053b7a212244ff109e44469b8deff280c5 Mon Sep 17 00:00:00 2001
From: Jeff Johnson <quic_jjohnson@quicinc.com>
Date: Fri, 24 May 2024 16:58:26 -0700
Subject: [PATCH 363/950] of: of_test: add MODULE_DESCRIPTION()

Fix the 'make W=1' warning:
WARNING: modpost: missing MODULE_DESCRIPTION() in drivers/of/of_test.o

Signed-off-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Link: https://lore.kernel.org/r/20240524-md-of-of_test-v1-1-6ebd078d620f@quicinc.com
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
---
 drivers/of/of_test.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/of/of_test.c b/drivers/of/of_test.c
index a9301d293f014..c85a258bc6ae6 100644
--- a/drivers/of/of_test.c
+++ b/drivers/of/of_test.c
@@ -54,4 +54,5 @@ static struct kunit_suite of_dtb_suite = {
 kunit_test_suites(
 	&of_dtb_suite,
 );
+MODULE_DESCRIPTION("KUnit tests for OF APIs");
 MODULE_LICENSE("GPL");
-- 
GitLab


From af69d862a8baa600b018f66aca8174b23c166a5f Mon Sep 17 00:00:00 2001
From: Jeff Johnson <quic_jjohnson@quicinc.com>
Date: Thu, 23 May 2024 08:18:05 -0700
Subject: [PATCH 364/950] wifi: ath12k: Fix devmem address prefix when logging

Currently when ath12k QMI logging is enabled, messages such as the
following can be logged:

ath12k_pci 0000:03:00.0: devmem [0] start ox113000 size 20480

Replace ox% with 0x% to get a proper hex address prefix:

ath12k_pci 0000:03:00.0: devmem [0] start 0x113000 size 20480

Signed-off-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240523-ox-v1-1-112ae7350059@quicinc.com
---
 drivers/net/wireless/ath/ath12k/qmi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath12k/qmi.c b/drivers/net/wireless/ath/ath12k/qmi.c
index f273cb93dedb8..b93ce9f87f612 100644
--- a/drivers/net/wireless/ath/ath12k/qmi.c
+++ b/drivers/net/wireless/ath/ath12k/qmi.c
@@ -2503,7 +2503,7 @@ static int ath12k_qmi_request_target_cap(struct ath12k_base *ab)
 			ab->qmi.dev_mem[i].size =
 				resp.dev_mem[i].size;
 			ath12k_dbg(ab, ATH12K_DBG_QMI,
-				   "devmem [%d] start ox%llx size %llu\n", i,
+				   "devmem [%d] start 0x%llx size %llu\n", i,
 				   ab->qmi.dev_mem[i].start,
 				   ab->qmi.dev_mem[i].size);
 		}
-- 
GitLab


From 5714e25f1d1875b300fb337dadfaa75324c1161a Mon Sep 17 00:00:00 2001
From: Baochen Qiang <quic_bqiang@quicinc.com>
Date: Fri, 24 May 2024 10:15:58 +0800
Subject: [PATCH 365/950] wifi: ath11k: fix wrong definition of CE ring's base
 address

Base address of CE ring is defined as u32, currently this works
because coherent DMA mask configured as 32 bit:

	#define ATH11K_PCI_COHERENT_DMA_MASK	32

However this mask could be changed once firmware bugs are fixed
to fully support 36 bit DMA addressing. So to protect against any
future changes to the DMA mask, change the type of the fields that
are dependent upon it.

This is found during code review. Compile tested only.

Fixes: d5c65159f289 ("ath11k: driver for Qualcomm IEEE 802.11ax devices")
Signed-off-by: Baochen Qiang <quic_bqiang@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240524021558.34452-1-quic_bqiang@quicinc.com
---
 drivers/net/wireless/ath/ath11k/ce.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/ce.h b/drivers/net/wireless/ath/ath11k/ce.h
index 69946fc700777..bcde2fcf02cf7 100644
--- a/drivers/net/wireless/ath/ath11k/ce.h
+++ b/drivers/net/wireless/ath/ath11k/ce.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
- * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2022, 2024 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH11K_CE_H
@@ -146,7 +146,7 @@ struct ath11k_ce_ring {
 	/* Host address space */
 	void *base_addr_owner_space_unaligned;
 	/* CE address space */
-	u32 base_addr_ce_space_unaligned;
+	dma_addr_t base_addr_ce_space_unaligned;
 
 	/* Actual start of descriptors.
 	 * Aligned to descriptor-size boundary.
@@ -156,7 +156,7 @@ struct ath11k_ce_ring {
 	void *base_addr_owner_space;
 
 	/* CE address space */
-	u32 base_addr_ce_space;
+	dma_addr_t base_addr_ce_space;
 
 	/* HAL ring id */
 	u32 hal_ring_id;
-- 
GitLab


From 0a993772e0f0934d730c0d451622c80e03a40ab1 Mon Sep 17 00:00:00 2001
From: Baochen Qiang <quic_bqiang@quicinc.com>
Date: Fri, 24 May 2024 10:36:42 +0800
Subject: [PATCH 366/950] wifi: ath12k: fix race due to setting
 ATH12K_FLAG_EXT_IRQ_ENABLED too early

Commit 5082b3e3027e ("wifi: ath11k: fix race due to setting
ATH11K_FLAG_EXT_IRQ_ENABLED too early") fixes a race in ath11k
driver. Since ath12k shares the same logic as ath11k, currently
the race also exists in ath12k: in ath12k_pci_ext_irq_enable(),
ATH12K_FLAG_EXT_IRQ_ENABLED is set before NAPI is enabled.
In cases where only one MSI vector is allocated, this results
in a race condition: after ATH12K_FLAG_EXT_IRQ_ENABLED is set
but before NAPI enabled, CE interrupt breaks in. Since IRQ is
shared by CE and data path, ath12k_pci_ext_interrupt_handler()
is also called where we call disable_irq_nosync() to disable
IRQ. Then napi_schedule() is called but it does nothing because
NAPI is not enabled at that time, meaning that
ath12k_pci_ext_grp_napi_poll() will never run, so we have
no chance to call enable_irq() to enable IRQ back. Since IRQ
is shared, all interrupts are disabled and we would finally
get no response from target.

So port ath11k fix here, this is done by setting
ATH12K_FLAG_EXT_IRQ_ENABLED after all NAPI and IRQ work are
done. With the fix, we are sure that by the time
ATH12K_FLAG_EXT_IRQ_ENABLED is set, NAPI is enabled.

Note that the fix above also introduce some side effects:
if ath12k_pci_ext_interrupt_handler() breaks in after NAPI
enabled but before ATH12K_FLAG_EXT_IRQ_ENABLED set, nothing
will be done by the handler this time, the work will be
postponed till the next time the IRQ fires.

This is found during code review.

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Signed-off-by: Baochen Qiang <quic_bqiang@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240524023642.37030-1-quic_bqiang@quicinc.com
---
 drivers/net/wireless/ath/ath12k/pci.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/pci.c b/drivers/net/wireless/ath/ath12k/pci.c
index ac75e8e3916bd..11b95d0370518 100644
--- a/drivers/net/wireless/ath/ath12k/pci.c
+++ b/drivers/net/wireless/ath/ath12k/pci.c
@@ -1107,14 +1107,14 @@ void ath12k_pci_ext_irq_enable(struct ath12k_base *ab)
 {
 	int i;
 
-	set_bit(ATH12K_FLAG_EXT_IRQ_ENABLED, &ab->dev_flags);
-
 	for (i = 0; i < ATH12K_EXT_IRQ_GRP_NUM_MAX; i++) {
 		struct ath12k_ext_irq_grp *irq_grp = &ab->ext_irq_grp[i];
 
 		napi_enable(&irq_grp->napi);
 		ath12k_pci_ext_grp_enable(irq_grp);
 	}
+
+	set_bit(ATH12K_FLAG_EXT_IRQ_ENABLED, &ab->dev_flags);
 }
 
 void ath12k_pci_ext_irq_disable(struct ath12k_base *ab)
-- 
GitLab


From 0ae570703754858a77cc42b3c9fff42e9f084608 Mon Sep 17 00:00:00 2001
From: Baochen Qiang <quic_bqiang@quicinc.com>
Date: Fri, 24 May 2024 10:40:21 +0800
Subject: [PATCH 367/950] wifi: ath12k: fix wrong definition of CE ring's base
 address

Base address of CE ring is defined as u32, currently this works
because DMA mask configured as 32 bit:

	#define ATH12K_PCI_DMA_MASK	32

However this mask could be changed once firmware bugs are fixed
to fully support 36 bit DMA addressing. So to protect against any
future changes to the DMA mask, change the type of the fields that
are dependent upon it.

This is found during code review. Compile tested only.

Fixes: d889913205cf ("wifi: ath12k: driver for Qualcomm Wi-Fi 7 devices")
Signed-off-by: Baochen Qiang <quic_bqiang@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240524024021.37711-1-quic_bqiang@quicinc.com
---
 drivers/net/wireless/ath/ath12k/ce.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/ce.h b/drivers/net/wireless/ath/ath12k/ce.h
index 79af3b6159f1c..857bc5f9e946a 100644
--- a/drivers/net/wireless/ath/ath12k/ce.h
+++ b/drivers/net/wireless/ath/ath12k/ce.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2022, 2024 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH12K_CE_H
@@ -119,7 +119,7 @@ struct ath12k_ce_ring {
 	/* Host address space */
 	void *base_addr_owner_space_unaligned;
 	/* CE address space */
-	u32 base_addr_ce_space_unaligned;
+	dma_addr_t base_addr_ce_space_unaligned;
 
 	/* Actual start of descriptors.
 	 * Aligned to descriptor-size boundary.
@@ -129,7 +129,7 @@ struct ath12k_ce_ring {
 	void *base_addr_owner_space;
 
 	/* CE address space */
-	u32 base_addr_ce_space;
+	dma_addr_t base_addr_ce_space;
 
 	/* HAL ring id */
 	u32 hal_ring_id;
-- 
GitLab


From c7a5096781732e0f9784551309484f3e103f6750 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andy.shevchenko@gmail.com>
Date: Tue, 28 May 2024 13:25:02 +0300
Subject: [PATCH 368/950] PNP: Make dev_is_pnp() to be a function and export it
 for modules

Since we have a dev_is_pnp() macro that utilises the address of the
pnp_bus_type variable, the users, which can be compiled as modules,
will fail to build. Convert the macro to be a function and export it
to the modules to prevent build breakage.

Reported-by: Woody Suwalski <terraluna977@gmail.com>
Closes: https://lore.kernel.org/r/cc8a93b2-2504-9754-e26c-5d5c3bd1265c@gmail.com
Fixes: 2a49b45cd0e7 ("PNP: Add dev_is_pnp() macro")
Signed-off-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/pnp/driver.c | 6 ++++++
 include/linux/pnp.h  | 4 ++--
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/pnp/driver.c b/drivers/pnp/driver.c
index 0a5d0d8befa84..3483e52e3a81d 100644
--- a/drivers/pnp/driver.c
+++ b/drivers/pnp/driver.c
@@ -266,6 +266,12 @@ const struct bus_type pnp_bus_type = {
 	.dev_groups = pnp_dev_groups,
 };
 
+bool dev_is_pnp(const struct device *dev)
+{
+	return dev->bus == &pnp_bus_type;
+}
+EXPORT_SYMBOL_GPL(dev_is_pnp);
+
 int pnp_register_driver(struct pnp_driver *drv)
 {
 	drv->driver.name = drv->name;
diff --git a/include/linux/pnp.h b/include/linux/pnp.h
index 82561242cda42..a8def1cea32c0 100644
--- a/include/linux/pnp.h
+++ b/include/linux/pnp.h
@@ -469,7 +469,7 @@ int compare_pnp_id(struct pnp_id *pos, const char *id);
 int pnp_register_driver(struct pnp_driver *drv);
 void pnp_unregister_driver(struct pnp_driver *drv);
 
-#define dev_is_pnp(d) ((d)->bus == &pnp_bus_type)
+bool dev_is_pnp(const struct device *dev);
 
 #else
 
@@ -502,7 +502,7 @@ static inline int compare_pnp_id(struct pnp_id *pos, const char *id) { return -E
 static inline int pnp_register_driver(struct pnp_driver *drv) { return -ENODEV; }
 static inline void pnp_unregister_driver(struct pnp_driver *drv) { }
 
-#define dev_is_pnp(d) false
+static inline bool dev_is_pnp(const struct device *dev) { return false; }
 
 #endif /* CONFIG_PNP */
 
-- 
GitLab


From edcde848c01eb071a91d479a6b3101d9cf48e905 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andy.shevchenko@gmail.com>
Date: Tue, 28 May 2024 13:25:03 +0300
Subject: [PATCH 369/950] PNP: Hide pnp_bus_type from the non-PNP code

The pnp_bus_type is defined only when CONFIG_PNP=y, while being
not guarded by ifdeffery in the header. Moreover, it's not used
outside of the PNP code. Move it to the internal header to make
sure no-one will try to (ab)use it.

Signed-off-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/pnp/base.h  | 1 +
 include/linux/pnp.h | 2 --
 2 files changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/pnp/base.h b/drivers/pnp/base.h
index e74a0f6a31572..4e80273dfb1ec 100644
--- a/drivers/pnp/base.h
+++ b/drivers/pnp/base.h
@@ -6,6 +6,7 @@
 
 extern struct mutex pnp_lock;
 extern const struct attribute_group *pnp_dev_groups[];
+extern const struct bus_type pnp_bus_type;
 
 int pnp_register_protocol(struct pnp_protocol *protocol);
 void pnp_unregister_protocol(struct pnp_protocol *protocol);
diff --git a/include/linux/pnp.h b/include/linux/pnp.h
index a8def1cea32c0..7f2ff95d2deb5 100644
--- a/include/linux/pnp.h
+++ b/include/linux/pnp.h
@@ -435,8 +435,6 @@ struct pnp_protocol {
 #define protocol_for_each_dev(protocol, dev)	\
 	list_for_each_entry(dev, &(protocol)->devices, protocol_list)
 
-extern const struct bus_type pnp_bus_type;
-
 #if defined(CONFIG_PNP)
 
 /* device management */
-- 
GitLab


From ac62f52138f752d6c74adc6321e4996d84caf5bb Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <linux@weissschuh.net>
Date: Sun, 26 May 2024 23:40:01 +0200
Subject: [PATCH 370/950] ACPI: AC: Properly notify powermanagement core about
 changes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The powermanagement core does various actions when a powersupply changes.
It calls into notifiers, LED triggers, other power supplies and emits an uevent.

To make sure that all these actions happen properly call power_supply_changed().

Reported-by: Rajas Paranjpe <paranjperajas@gmail.com>
Closes: https://github.com/MrChromebox/firmware/issues/420#issuecomment-2132251318
Signed-off-by: Thomas Weißschuh <linux@weissschuh.net>
Reviewed-by: Sebastian Reichel <sebastian.reichel@collabora.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/ac.c  | 4 ++--
 drivers/acpi/sbs.c | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/acpi/ac.c b/drivers/acpi/ac.c
index 2d4a35e6dd18d..09a87fa222c78 100644
--- a/drivers/acpi/ac.c
+++ b/drivers/acpi/ac.c
@@ -145,7 +145,7 @@ static void acpi_ac_notify(acpi_handle handle, u32 event, void *data)
 						  dev_name(&adev->dev), event,
 						  (u32) ac->state);
 		acpi_notifier_call_chain(adev, event, (u32) ac->state);
-		kobject_uevent(&ac->charger->dev.kobj, KOBJ_CHANGE);
+		power_supply_changed(ac->charger);
 	}
 }
 
@@ -268,7 +268,7 @@ static int acpi_ac_resume(struct device *dev)
 	if (acpi_ac_get_state(ac))
 		return 0;
 	if (old_state != ac->state)
-		kobject_uevent(&ac->charger->dev.kobj, KOBJ_CHANGE);
+		power_supply_changed(ac->charger);
 
 	return 0;
 }
diff --git a/drivers/acpi/sbs.c b/drivers/acpi/sbs.c
index 94e3c000df2e1..dc8164b182dcc 100644
--- a/drivers/acpi/sbs.c
+++ b/drivers/acpi/sbs.c
@@ -610,7 +610,7 @@ static void acpi_sbs_callback(void *context)
 	if (sbs->charger_exists) {
 		acpi_ac_get_present(sbs);
 		if (sbs->charger_present != saved_charger_state)
-			kobject_uevent(&sbs->charger->dev.kobj, KOBJ_CHANGE);
+			power_supply_changed(sbs->charger);
 	}
 
 	if (sbs->manager_present) {
@@ -622,7 +622,7 @@ static void acpi_sbs_callback(void *context)
 			acpi_battery_read(bat);
 			if (saved_battery_state == bat->present)
 				continue;
-			kobject_uevent(&bat->bat->dev.kobj, KOBJ_CHANGE);
+			power_supply_changed(bat->bat);
 		}
 	}
 }
-- 
GitLab


From 779b8a14afde110dd3502566be907289eba72447 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 28 May 2024 14:09:23 +0200
Subject: [PATCH 371/950] cpufreq: amd-pstate: remove global header file

When extra warnings are enabled, gcc points out a global variable
definition in a header:

In file included from drivers/cpufreq/amd-pstate-ut.c:29:
include/linux/amd-pstate.h:123:27: error: 'amd_pstate_mode_string' defined but not used [-Werror=unused-const-variable=]
  123 | static const char * const amd_pstate_mode_string[] = {
      |                           ^~~~~~~~~~~~~~~~~~~~~~

This header is only included from two files in the same directory,
and one of them uses only a single definition from it, so clean it
up by moving most of the contents into the driver that uses them,
and making shared bits a local header file.

Fixes: 36c5014e5460 ("cpufreq: amd-pstate: optimize driver working mode selection in amd_pstate_param()")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 MAINTAINERS                                   |  1 -
 drivers/cpufreq/amd-pstate-ut.c               |  3 +-
 drivers/cpufreq/amd-pstate.c                  | 34 ++++++++++++++++++-
 .../linux => drivers/cpufreq}/amd-pstate.h    | 33 ------------------
 4 files changed, 35 insertions(+), 36 deletions(-)
 rename {include/linux => drivers/cpufreq}/amd-pstate.h (82%)

diff --git a/MAINTAINERS b/MAINTAINERS
index d6c90161c7bfe..fc31870379f84 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1107,7 +1107,6 @@ L:	linux-pm@vger.kernel.org
 S:	Supported
 F:	Documentation/admin-guide/pm/amd-pstate.rst
 F:	drivers/cpufreq/amd-pstate*
-F:	include/linux/amd-pstate.h
 F:	tools/power/x86/amd_pstate_tracer/amd_pstate_trace.py
 
 AMD PTDMA DRIVER
diff --git a/drivers/cpufreq/amd-pstate-ut.c b/drivers/cpufreq/amd-pstate-ut.c
index f04ae67dda372..fc275d41d51e9 100644
--- a/drivers/cpufreq/amd-pstate-ut.c
+++ b/drivers/cpufreq/amd-pstate-ut.c
@@ -26,10 +26,11 @@
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/fs.h>
-#include <linux/amd-pstate.h>
 
 #include <acpi/cppc_acpi.h>
 
+#include "amd-pstate.h"
+
 /*
  * Abbreviations:
  * amd_pstate_ut: used as a shortform for AMD P-State unit test.
diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index 1b7e82a0ad2e6..91993647e09ef 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -36,7 +36,6 @@
 #include <linux/delay.h>
 #include <linux/uaccess.h>
 #include <linux/static_call.h>
-#include <linux/amd-pstate.h>
 #include <linux/topology.h>
 
 #include <acpi/processor.h>
@@ -46,6 +45,8 @@
 #include <asm/processor.h>
 #include <asm/cpufeature.h>
 #include <asm/cpu_device_id.h>
+
+#include "amd-pstate.h"
 #include "amd-pstate-trace.h"
 
 #define AMD_PSTATE_TRANSITION_LATENCY	20000
@@ -53,6 +54,37 @@
 #define CPPC_HIGHEST_PERF_PERFORMANCE	196
 #define CPPC_HIGHEST_PERF_DEFAULT	166
 
+#define AMD_CPPC_EPP_PERFORMANCE		0x00
+#define AMD_CPPC_EPP_BALANCE_PERFORMANCE	0x80
+#define AMD_CPPC_EPP_BALANCE_POWERSAVE		0xBF
+#define AMD_CPPC_EPP_POWERSAVE			0xFF
+
+/*
+ * enum amd_pstate_mode - driver working mode of amd pstate
+ */
+enum amd_pstate_mode {
+	AMD_PSTATE_UNDEFINED = 0,
+	AMD_PSTATE_DISABLE,
+	AMD_PSTATE_PASSIVE,
+	AMD_PSTATE_ACTIVE,
+	AMD_PSTATE_GUIDED,
+	AMD_PSTATE_MAX,
+};
+
+static const char * const amd_pstate_mode_string[] = {
+	[AMD_PSTATE_UNDEFINED]   = "undefined",
+	[AMD_PSTATE_DISABLE]     = "disable",
+	[AMD_PSTATE_PASSIVE]     = "passive",
+	[AMD_PSTATE_ACTIVE]      = "active",
+	[AMD_PSTATE_GUIDED]      = "guided",
+	NULL,
+};
+
+struct quirk_entry {
+	u32 nominal_freq;
+	u32 lowest_freq;
+};
+
 /*
  * TODO: We need more time to fine tune processors with shared memory solution
  * with community together.
diff --git a/include/linux/amd-pstate.h b/drivers/cpufreq/amd-pstate.h
similarity index 82%
rename from include/linux/amd-pstate.h
rename to drivers/cpufreq/amd-pstate.h
index d58fc022ec466..e6a28e7f4dbf1 100644
--- a/include/linux/amd-pstate.h
+++ b/drivers/cpufreq/amd-pstate.h
@@ -1,7 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * linux/include/linux/amd-pstate.h
- *
  * Copyright (C) 2022 Advanced Micro Devices, Inc.
  *
  * Author: Meng Li <li.meng@amd.com>
@@ -12,11 +10,6 @@
 
 #include <linux/pm_qos.h>
 
-#define AMD_CPPC_EPP_PERFORMANCE		0x00
-#define AMD_CPPC_EPP_BALANCE_PERFORMANCE	0x80
-#define AMD_CPPC_EPP_BALANCE_POWERSAVE		0xBF
-#define AMD_CPPC_EPP_POWERSAVE			0xFF
-
 /*********************************************************************
  *                        AMD P-state INTERFACE                       *
  *********************************************************************/
@@ -108,30 +101,4 @@ struct amd_cpudata {
 	bool	suspended;
 };
 
-/*
- * enum amd_pstate_mode - driver working mode of amd pstate
- */
-enum amd_pstate_mode {
-	AMD_PSTATE_UNDEFINED = 0,
-	AMD_PSTATE_DISABLE,
-	AMD_PSTATE_PASSIVE,
-	AMD_PSTATE_ACTIVE,
-	AMD_PSTATE_GUIDED,
-	AMD_PSTATE_MAX,
-};
-
-static const char * const amd_pstate_mode_string[] = {
-	[AMD_PSTATE_UNDEFINED]   = "undefined",
-	[AMD_PSTATE_DISABLE]     = "disable",
-	[AMD_PSTATE_PASSIVE]     = "passive",
-	[AMD_PSTATE_ACTIVE]      = "active",
-	[AMD_PSTATE_GUIDED]      = "guided",
-	NULL,
-};
-
-struct quirk_entry {
-	u32 nominal_freq;
-	u32 lowest_freq;
-};
-
 #endif /* _LINUX_AMD_PSTATE_H */
-- 
GitLab


From e4731baaf29438508197d3a8a6d4f5a8c51663f8 Mon Sep 17 00:00:00 2001
From: Dhananjay Ugwekar <Dhananjay.Ugwekar@amd.com>
Date: Mon, 27 May 2024 10:41:28 +0530
Subject: [PATCH 372/950] cpufreq: amd-pstate: Fix the inconsistency in max
 frequency units

The nominal frequency in cpudata is maintained in MHz whereas all other
frequencies are in KHz. This means we have to convert nominal frequency
value to KHz before we do any interaction with other frequency values.

In amd_pstate_set_boost(), this conversion from MHz to KHz is missed,
fix that.

Tested on a AMD Zen4 EPYC server

Before:
$ cat /sys/devices/system/cpu/cpufreq/policy*/scaling_max_freq | uniq
2151
$ cat /sys/devices/system/cpu/cpufreq/policy*/cpuinfo_min_freq | uniq
400000
$ cat /sys/devices/system/cpu/cpufreq/policy*/scaling_cur_freq | uniq
2151
409422

After:
$ cat /sys/devices/system/cpu/cpufreq/policy*/scaling_max_freq | uniq
2151000
$ cat /sys/devices/system/cpu/cpufreq/policy*/cpuinfo_min_freq | uniq
400000
$ cat /sys/devices/system/cpu/cpufreq/policy*/scaling_cur_freq | uniq
2151000
1799527

Fixes: ec437d71db77 ("cpufreq: amd-pstate: Introduce a new AMD P-State driver to support future processors")
Signed-off-by: Dhananjay Ugwekar <Dhananjay.Ugwekar@amd.com>
Acked-by: Mario Limonciello <mario.limonciello@amd.com>
Acked-by: Gautham R. Shenoy <gautham.shenoy@amd.com>
Tested-by: Peter Jung <ptr1337@cachyos.org>
Cc: 5.17+ <stable@vger.kernel.org> # 5.17+
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/amd-pstate.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index 91993647e09ef..9ad62dbe8bfbf 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -701,7 +701,7 @@ static int amd_pstate_set_boost(struct cpufreq_policy *policy, int state)
 	if (state)
 		policy->cpuinfo.max_freq = cpudata->max_freq;
 	else
-		policy->cpuinfo.max_freq = cpudata->nominal_freq;
+		policy->cpuinfo.max_freq = cpudata->nominal_freq * 1000;
 
 	policy->max = policy->cpuinfo.max_freq;
 
-- 
GitLab


From 016c22e410c6eabfc5164f514d2a0ad06eddf3ba Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Tue, 28 May 2024 16:47:34 -0400
Subject: [PATCH 373/950] bcachefs: split out sb-members_format.h

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/bcachefs_format.h   | 102 +----------------------------
 fs/bcachefs/sb-members_format.h | 110 ++++++++++++++++++++++++++++++++
 2 files changed, 111 insertions(+), 101 deletions(-)
 create mode 100644 fs/bcachefs/sb-members_format.h

diff --git a/fs/bcachefs/bcachefs_format.h b/fs/bcachefs/bcachefs_format.h
index d801e19cb4890..c4d10b528b549 100644
--- a/fs/bcachefs/bcachefs_format.h
+++ b/fs/bcachefs/bcachefs_format.h
@@ -513,6 +513,7 @@ struct bch_sb_field {
 #include "snapshot_format.h"
 #include "subvolume_format.h"
 #include "sb-counters_format.h"
+#include "sb-members_format.h"
 
 enum bch_sb_field_type {
 #define x(f, nr)	BCH_SB_FIELD_##f = nr,
@@ -545,106 +546,6 @@ struct bch_sb_field_journal_v2 {
 	}			d[];
 };
 
-/* BCH_SB_FIELD_members_v1: */
-
-#define BCH_MIN_NR_NBUCKETS	(1 << 6)
-
-#define BCH_IOPS_MEASUREMENTS()			\
-	x(seqread,	0)			\
-	x(seqwrite,	1)			\
-	x(randread,	2)			\
-	x(randwrite,	3)
-
-enum bch_iops_measurement {
-#define x(t, n) BCH_IOPS_##t = n,
-	BCH_IOPS_MEASUREMENTS()
-#undef x
-	BCH_IOPS_NR
-};
-
-#define BCH_MEMBER_ERROR_TYPES()		\
-	x(read,		0)			\
-	x(write,	1)			\
-	x(checksum,	2)
-
-enum bch_member_error_type {
-#define x(t, n) BCH_MEMBER_ERROR_##t = n,
-	BCH_MEMBER_ERROR_TYPES()
-#undef x
-	BCH_MEMBER_ERROR_NR
-};
-
-struct bch_member {
-	__uuid_t		uuid;
-	__le64			nbuckets;	/* device size */
-	__le16			first_bucket;   /* index of first bucket used */
-	__le16			bucket_size;	/* sectors */
-	__u8			btree_bitmap_shift;
-	__u8			pad[3];
-	__le64			last_mount;	/* time_t */
-
-	__le64			flags;
-	__le32			iops[4];
-	__le64			errors[BCH_MEMBER_ERROR_NR];
-	__le64			errors_at_reset[BCH_MEMBER_ERROR_NR];
-	__le64			errors_reset_time;
-	__le64			seq;
-	__le64			btree_allocated_bitmap;
-	/*
-	 * On recovery from a clean shutdown we don't normally read the journal,
-	 * but we still want to resume writing from where we left off so we
-	 * don't overwrite more than is necessary, for list journal debugging:
-	 */
-	__le32			last_journal_bucket;
-	__le32			last_journal_bucket_offset;
-};
-
-/*
- * This limit comes from the bucket_gens array - it's a single allocation, and
- * kernel allocation are limited to INT_MAX
- */
-#define BCH_MEMBER_NBUCKETS_MAX	(INT_MAX - 64)
-
-#define BCH_MEMBER_V1_BYTES	56
-
-LE64_BITMASK(BCH_MEMBER_STATE,		struct bch_member, flags,  0,  4)
-/* 4-14 unused, was TIER, HAS_(META)DATA, REPLACEMENT */
-LE64_BITMASK(BCH_MEMBER_DISCARD,	struct bch_member, flags, 14, 15)
-LE64_BITMASK(BCH_MEMBER_DATA_ALLOWED,	struct bch_member, flags, 15, 20)
-LE64_BITMASK(BCH_MEMBER_GROUP,		struct bch_member, flags, 20, 28)
-LE64_BITMASK(BCH_MEMBER_DURABILITY,	struct bch_member, flags, 28, 30)
-LE64_BITMASK(BCH_MEMBER_FREESPACE_INITIALIZED,
-					struct bch_member, flags, 30, 31)
-
-#if 0
-LE64_BITMASK(BCH_MEMBER_NR_READ_ERRORS,	struct bch_member, flags[1], 0,  20);
-LE64_BITMASK(BCH_MEMBER_NR_WRITE_ERRORS,struct bch_member, flags[1], 20, 40);
-#endif
-
-#define BCH_MEMBER_STATES()			\
-	x(rw,		0)			\
-	x(ro,		1)			\
-	x(failed,	2)			\
-	x(spare,	3)
-
-enum bch_member_state {
-#define x(t, n) BCH_MEMBER_STATE_##t = n,
-	BCH_MEMBER_STATES()
-#undef x
-	BCH_MEMBER_STATE_NR
-};
-
-struct bch_sb_field_members_v1 {
-	struct bch_sb_field	field;
-	struct bch_member	_members[]; //Members are now variable size
-};
-
-struct bch_sb_field_members_v2 {
-	struct bch_sb_field	field;
-	__le16			member_bytes; //size of single member entry
-	u8			pad[6];
-	struct bch_member	_members[];
-};
 
 /* BCH_SB_FIELD_crypt: */
 
@@ -909,7 +810,6 @@ unsigned bcachefs_metadata_required_upgrade_below = bcachefs_metadata_version_re
 #define bcachefs_metadata_version_current	(bcachefs_metadata_version_max - 1)
 
 #define BCH_SB_SECTOR			8
-#define BCH_SB_MEMBERS_MAX		64 /* XXX kill */
 
 #define BCH_SB_LAYOUT_SIZE_BITS_MAX	16 /* 32 MB */
 
diff --git a/fs/bcachefs/sb-members_format.h b/fs/bcachefs/sb-members_format.h
new file mode 100644
index 0000000000000..e2630548c0f68
--- /dev/null
+++ b/fs/bcachefs/sb-members_format.h
@@ -0,0 +1,110 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _BCACHEFS_SB_MEMBERS_FORMAT_H
+#define _BCACHEFS_SB_MEMBERS_FORMAT_H
+
+/*
+ * We refer to members with bitmasks in various places - but we need to get rid
+ * of this limit:
+ */
+#define BCH_SB_MEMBERS_MAX		64
+
+#define BCH_MIN_NR_NBUCKETS	(1 << 6)
+
+#define BCH_IOPS_MEASUREMENTS()			\
+	x(seqread,	0)			\
+	x(seqwrite,	1)			\
+	x(randread,	2)			\
+	x(randwrite,	3)
+
+enum bch_iops_measurement {
+#define x(t, n) BCH_IOPS_##t = n,
+	BCH_IOPS_MEASUREMENTS()
+#undef x
+	BCH_IOPS_NR
+};
+
+#define BCH_MEMBER_ERROR_TYPES()		\
+	x(read,		0)			\
+	x(write,	1)			\
+	x(checksum,	2)
+
+enum bch_member_error_type {
+#define x(t, n) BCH_MEMBER_ERROR_##t = n,
+	BCH_MEMBER_ERROR_TYPES()
+#undef x
+	BCH_MEMBER_ERROR_NR
+};
+
+struct bch_member {
+	__uuid_t		uuid;
+	__le64			nbuckets;	/* device size */
+	__le16			first_bucket;   /* index of first bucket used */
+	__le16			bucket_size;	/* sectors */
+	__u8			btree_bitmap_shift;
+	__u8			pad[3];
+	__le64			last_mount;	/* time_t */
+
+	__le64			flags;
+	__le32			iops[4];
+	__le64			errors[BCH_MEMBER_ERROR_NR];
+	__le64			errors_at_reset[BCH_MEMBER_ERROR_NR];
+	__le64			errors_reset_time;
+	__le64			seq;
+	__le64			btree_allocated_bitmap;
+	/*
+	 * On recovery from a clean shutdown we don't normally read the journal,
+	 * but we still want to resume writing from where we left off so we
+	 * don't overwrite more than is necessary, for list journal debugging:
+	 */
+	__le32			last_journal_bucket;
+	__le32			last_journal_bucket_offset;
+};
+
+/*
+ * This limit comes from the bucket_gens array - it's a single allocation, and
+ * kernel allocation are limited to INT_MAX
+ */
+#define BCH_MEMBER_NBUCKETS_MAX	(INT_MAX - 64)
+
+#define BCH_MEMBER_V1_BYTES	56
+
+LE64_BITMASK(BCH_MEMBER_STATE,		struct bch_member, flags,  0,  4)
+/* 4-14 unused, was TIER, HAS_(META)DATA, REPLACEMENT */
+LE64_BITMASK(BCH_MEMBER_DISCARD,	struct bch_member, flags, 14, 15)
+LE64_BITMASK(BCH_MEMBER_DATA_ALLOWED,	struct bch_member, flags, 15, 20)
+LE64_BITMASK(BCH_MEMBER_GROUP,		struct bch_member, flags, 20, 28)
+LE64_BITMASK(BCH_MEMBER_DURABILITY,	struct bch_member, flags, 28, 30)
+LE64_BITMASK(BCH_MEMBER_FREESPACE_INITIALIZED,
+					struct bch_member, flags, 30, 31)
+
+#if 0
+LE64_BITMASK(BCH_MEMBER_NR_READ_ERRORS,	struct bch_member, flags[1], 0,  20);
+LE64_BITMASK(BCH_MEMBER_NR_WRITE_ERRORS,struct bch_member, flags[1], 20, 40);
+#endif
+
+#define BCH_MEMBER_STATES()			\
+	x(rw,		0)			\
+	x(ro,		1)			\
+	x(failed,	2)			\
+	x(spare,	3)
+
+enum bch_member_state {
+#define x(t, n) BCH_MEMBER_STATE_##t = n,
+	BCH_MEMBER_STATES()
+#undef x
+	BCH_MEMBER_STATE_NR
+};
+
+struct bch_sb_field_members_v1 {
+	struct bch_sb_field	field;
+	struct bch_member	_members[]; //Members are now variable size
+};
+
+struct bch_sb_field_members_v2 {
+	struct bch_sb_field	field;
+	__le16			member_bytes; //size of single member entry
+	u8			pad[6];
+	struct bch_member	_members[];
+};
+
+#endif /* _BCACHEFS_SB_MEMBERS_FORMAT_H */
-- 
GitLab


From 4c5eef0c50ccc71e225f320835dc7cd51f64f961 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Tue, 28 May 2024 16:54:29 -0400
Subject: [PATCH 374/950] bcachefs: split out sb-downgrade_format.h

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/bcachefs_format.h     | 14 +-------------
 fs/bcachefs/sb-downgrade_format.h | 17 +++++++++++++++++
 2 files changed, 18 insertions(+), 13 deletions(-)
 create mode 100644 fs/bcachefs/sb-downgrade_format.h

diff --git a/fs/bcachefs/bcachefs_format.h b/fs/bcachefs/bcachefs_format.h
index c4d10b528b549..c966eb7e37b83 100644
--- a/fs/bcachefs/bcachefs_format.h
+++ b/fs/bcachefs/bcachefs_format.h
@@ -513,6 +513,7 @@ struct bch_sb_field {
 #include "snapshot_format.h"
 #include "subvolume_format.h"
 #include "sb-counters_format.h"
+#include "sb-downgrade_format.h"
 #include "sb-members_format.h"
 
 enum bch_sb_field_type {
@@ -546,7 +547,6 @@ struct bch_sb_field_journal_v2 {
 	}			d[];
 };
 
-
 /* BCH_SB_FIELD_crypt: */
 
 struct nonce {
@@ -738,18 +738,6 @@ struct bch_sb_field_ext {
 	__le64			btrees_lost_data;
 };
 
-struct bch_sb_field_downgrade_entry {
-	__le16			version;
-	__le64			recovery_passes[2];
-	__le16			nr_errors;
-	__le16			errors[] __counted_by(nr_errors);
-} __packed __aligned(2);
-
-struct bch_sb_field_downgrade {
-	struct bch_sb_field	field;
-	struct bch_sb_field_downgrade_entry entries[];
-};
-
 /* Superblock: */
 
 /*
diff --git a/fs/bcachefs/sb-downgrade_format.h b/fs/bcachefs/sb-downgrade_format.h
new file mode 100644
index 0000000000000..cffd932be3eca
--- /dev/null
+++ b/fs/bcachefs/sb-downgrade_format.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _BCACHEFS_SB_DOWNGRADE_FORMAT_H
+#define _BCACHEFS_SB_DOWNGRADE_FORMAT_H
+
+struct bch_sb_field_downgrade_entry {
+	__le16			version;
+	__le64			recovery_passes[2];
+	__le16			nr_errors;
+	__le16			errors[] __counted_by(nr_errors);
+} __packed __aligned(2);
+
+struct bch_sb_field_downgrade {
+	struct bch_sb_field	field;
+	struct bch_sb_field_downgrade_entry entries[];
+};
+
+#endif /* _BCACHEFS_SB_DOWNGRADE_FORMAT_H */
-- 
GitLab


From 1cdcc6e3c2cb69a235bd32eb0da51205e432f77f Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Tue, 28 May 2024 17:06:51 -0400
Subject: [PATCH 375/950] bcachefs: Split out disk_groups_format.h

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/bcachefs_format.h    | 19 +------------------
 fs/bcachefs/disk_groups_format.h | 21 +++++++++++++++++++++
 2 files changed, 22 insertions(+), 18 deletions(-)
 create mode 100644 fs/bcachefs/disk_groups_format.h

diff --git a/fs/bcachefs/bcachefs_format.h b/fs/bcachefs/bcachefs_format.h
index c966eb7e37b83..b7690fc3ffc62 100644
--- a/fs/bcachefs/bcachefs_format.h
+++ b/fs/bcachefs/bcachefs_format.h
@@ -507,6 +507,7 @@ struct bch_sb_field {
 #include "ec_format.h"
 #include "inode_format.h"
 #include "dirent_format.h"
+#include "disk_groups_format.h"
 #include "xattr_format.h"
 #include "quota_format.h"
 #include "logged_ops_format.h"
@@ -665,24 +666,6 @@ struct bch_sb_field_replicas {
 	struct bch_replicas_entry_v1 entries[];
 } __packed __aligned(8);
 
-/* BCH_SB_FIELD_disk_groups: */
-
-#define BCH_SB_LABEL_SIZE		32
-
-struct bch_disk_group {
-	__u8			label[BCH_SB_LABEL_SIZE];
-	__le64			flags[2];
-} __packed __aligned(8);
-
-LE64_BITMASK(BCH_GROUP_DELETED,		struct bch_disk_group, flags[0], 0,  1)
-LE64_BITMASK(BCH_GROUP_DATA_ALLOWED,	struct bch_disk_group, flags[0], 1,  6)
-LE64_BITMASK(BCH_GROUP_PARENT,		struct bch_disk_group, flags[0], 6, 24)
-
-struct bch_sb_field_disk_groups {
-	struct bch_sb_field	field;
-	struct bch_disk_group	entries[];
-} __packed __aligned(8);
-
 /*
  * On clean shutdown, store btree roots and current journal sequence number in
  * the superblock:
diff --git a/fs/bcachefs/disk_groups_format.h b/fs/bcachefs/disk_groups_format.h
new file mode 100644
index 0000000000000..698990bbf1d20
--- /dev/null
+++ b/fs/bcachefs/disk_groups_format.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _BCACHEFS_DISK_GROUPS_FORMAT_H
+#define _BCACHEFS_DISK_GROUPS_FORMAT_H
+
+#define BCH_SB_LABEL_SIZE		32
+
+struct bch_disk_group {
+	__u8			label[BCH_SB_LABEL_SIZE];
+	__le64			flags[2];
+} __packed __aligned(8);
+
+LE64_BITMASK(BCH_GROUP_DELETED,		struct bch_disk_group, flags[0], 0,  1)
+LE64_BITMASK(BCH_GROUP_DATA_ALLOWED,	struct bch_disk_group, flags[0], 1,  6)
+LE64_BITMASK(BCH_GROUP_PARENT,		struct bch_disk_group, flags[0], 6, 24)
+
+struct bch_sb_field_disk_groups {
+	struct bch_sb_field	field;
+	struct bch_disk_group	entries[];
+} __packed __aligned(8);
+
+#endif /* _BCACHEFS_DISK_GROUPS_FORMAT_H */
-- 
GitLab


From 24998050b69ac1f4caa41b66dbd245f4de366b3c Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Tue, 28 May 2024 17:13:52 -0400
Subject: [PATCH 376/950] bcachefs: Split out replicas_format.h

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/bcachefs_format.h | 37 +++++------------------------------
 fs/bcachefs/replicas_format.h | 31 +++++++++++++++++++++++++++++
 2 files changed, 36 insertions(+), 32 deletions(-)
 create mode 100644 fs/bcachefs/replicas_format.h

diff --git a/fs/bcachefs/bcachefs_format.h b/fs/bcachefs/bcachefs_format.h
index b7690fc3ffc62..66df1e5c2a876 100644
--- a/fs/bcachefs/bcachefs_format.h
+++ b/fs/bcachefs/bcachefs_format.h
@@ -503,19 +503,20 @@ struct bch_sb_field {
 
 #include "alloc_background_format.h"
 #include "extents_format.h"
-#include "reflink_format.h"
 #include "ec_format.h"
-#include "inode_format.h"
 #include "dirent_format.h"
 #include "disk_groups_format.h"
-#include "xattr_format.h"
-#include "quota_format.h"
+#include "inode_format.h"
 #include "logged_ops_format.h"
+#include "quota_format.h"
+#include "reflink_format.h"
+#include "replicas_format.h"
 #include "snapshot_format.h"
 #include "subvolume_format.h"
 #include "sb-counters_format.h"
 #include "sb-downgrade_format.h"
 #include "sb-members_format.h"
+#include "xattr_format.h"
 
 enum bch_sb_field_type {
 #define x(f, nr)	BCH_SB_FIELD_##f = nr,
@@ -596,8 +597,6 @@ LE64_BITMASK(BCH_KDF_SCRYPT_N,	struct bch_sb_field_crypt, kdf_flags,  0, 16);
 LE64_BITMASK(BCH_KDF_SCRYPT_R,	struct bch_sb_field_crypt, kdf_flags, 16, 32);
 LE64_BITMASK(BCH_KDF_SCRYPT_P,	struct bch_sb_field_crypt, kdf_flags, 32, 48);
 
-/* BCH_SB_FIELD_replicas: */
-
 #define BCH_DATA_TYPES()		\
 	x(free,		0)		\
 	x(sb,		1)		\
@@ -640,32 +639,6 @@ static inline bool data_type_is_hidden(enum bch_data_type type)
 	}
 }
 
-struct bch_replicas_entry_v0 {
-	__u8			data_type;
-	__u8			nr_devs;
-	__u8			devs[];
-} __packed;
-
-struct bch_sb_field_replicas_v0 {
-	struct bch_sb_field	field;
-	struct bch_replicas_entry_v0 entries[];
-} __packed __aligned(8);
-
-struct bch_replicas_entry_v1 {
-	__u8			data_type;
-	__u8			nr_devs;
-	__u8			nr_required;
-	__u8			devs[];
-} __packed;
-
-#define replicas_entry_bytes(_i)					\
-	(offsetof(typeof(*(_i)), devs) + (_i)->nr_devs)
-
-struct bch_sb_field_replicas {
-	struct bch_sb_field	field;
-	struct bch_replicas_entry_v1 entries[];
-} __packed __aligned(8);
-
 /*
  * On clean shutdown, store btree roots and current journal sequence number in
  * the superblock:
diff --git a/fs/bcachefs/replicas_format.h b/fs/bcachefs/replicas_format.h
new file mode 100644
index 0000000000000..b97208195d064
--- /dev/null
+++ b/fs/bcachefs/replicas_format.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _BCACHEFS_REPLICAS_FORMAT_H
+#define _BCACHEFS_REPLICAS_FORMAT_H
+
+struct bch_replicas_entry_v0 {
+	__u8			data_type;
+	__u8			nr_devs;
+	__u8			devs[];
+} __packed;
+
+struct bch_sb_field_replicas_v0 {
+	struct bch_sb_field	field;
+	struct bch_replicas_entry_v0 entries[];
+} __packed __aligned(8);
+
+struct bch_replicas_entry_v1 {
+	__u8			data_type;
+	__u8			nr_devs;
+	__u8			nr_required;
+	__u8			devs[];
+} __packed;
+
+struct bch_sb_field_replicas {
+	struct bch_sb_field	field;
+	struct bch_replicas_entry_v1 entries[];
+} __packed __aligned(8);
+
+#define replicas_entry_bytes(_i)					\
+	(offsetof(typeof(*(_i)), devs) + (_i)->nr_devs)
+
+#endif /* _BCACHEFS_REPLICAS_FORMAT_H */
-- 
GitLab


From 5c16c5748894652e8013dbcb27e54e8319c53b00 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Tue, 28 May 2024 17:20:40 -0400
Subject: [PATCH 377/950] bcachefs: Split out journal_seq_blacklist_format.h

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/bcachefs_format.h              | 11 +----------
 fs/bcachefs/journal_seq_blacklist_format.h | 15 +++++++++++++++
 2 files changed, 16 insertions(+), 10 deletions(-)
 create mode 100644 fs/bcachefs/journal_seq_blacklist_format.h

diff --git a/fs/bcachefs/bcachefs_format.h b/fs/bcachefs/bcachefs_format.h
index 66df1e5c2a876..89ac286f17f0b 100644
--- a/fs/bcachefs/bcachefs_format.h
+++ b/fs/bcachefs/bcachefs_format.h
@@ -507,6 +507,7 @@ struct bch_sb_field {
 #include "dirent_format.h"
 #include "disk_groups_format.h"
 #include "inode_format.h"
+#include "journal_seq_blacklist_format.h"
 #include "logged_ops_format.h"
 #include "quota_format.h"
 #include "reflink_format.h"
@@ -666,16 +667,6 @@ struct bch_sb_field_clean {
 	__u64			_data[];
 };
 
-struct journal_seq_blacklist_entry {
-	__le64			start;
-	__le64			end;
-};
-
-struct bch_sb_field_journal_seq_blacklist {
-	struct bch_sb_field	field;
-	struct journal_seq_blacklist_entry start[];
-};
-
 struct bch_sb_field_errors {
 	struct bch_sb_field	field;
 	struct bch_sb_field_error_entry {
diff --git a/fs/bcachefs/journal_seq_blacklist_format.h b/fs/bcachefs/journal_seq_blacklist_format.h
new file mode 100644
index 0000000000000..2566b12dbc045
--- /dev/null
+++ b/fs/bcachefs/journal_seq_blacklist_format.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _BCACHEFS_JOURNAL_SEQ_BLACKLIST_FORMAT_H
+#define _BCACHEFS_JOURNAL_SEQ_BLACKLIST_FORMAT_H
+
+struct journal_seq_blacklist_entry {
+	__le64			start;
+	__le64			end;
+};
+
+struct bch_sb_field_journal_seq_blacklist {
+	struct bch_sb_field	field;
+	struct journal_seq_blacklist_entry start[];
+};
+
+#endif /* _BCACHEFS_JOURNAL_SEQ_BLACKLIST_FORMAT_H */
-- 
GitLab


From 759bb4eabc727077145f3173f8ef6c2ac745c3d6 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Tue, 28 May 2024 17:23:01 -0400
Subject: [PATCH 378/950] bcachefs: Split out sb-errors_format.h

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/bcachefs_format.h  |  12 +-
 fs/bcachefs/sb-errors_format.h | 296 +++++++++++++++++++++++++++++++++
 fs/bcachefs/sb-errors_types.h  | 281 -------------------------------
 3 files changed, 297 insertions(+), 292 deletions(-)
 create mode 100644 fs/bcachefs/sb-errors_format.h

diff --git a/fs/bcachefs/bcachefs_format.h b/fs/bcachefs/bcachefs_format.h
index 89ac286f17f0b..90c12fe2a2cd3 100644
--- a/fs/bcachefs/bcachefs_format.h
+++ b/fs/bcachefs/bcachefs_format.h
@@ -516,6 +516,7 @@ struct bch_sb_field {
 #include "subvolume_format.h"
 #include "sb-counters_format.h"
 #include "sb-downgrade_format.h"
+#include "sb-errors_format.h"
 #include "sb-members_format.h"
 #include "xattr_format.h"
 
@@ -667,17 +668,6 @@ struct bch_sb_field_clean {
 	__u64			_data[];
 };
 
-struct bch_sb_field_errors {
-	struct bch_sb_field	field;
-	struct bch_sb_field_error_entry {
-		__le64		v;
-		__le64		last_error_time;
-	}			entries[];
-};
-
-LE64_BITMASK(BCH_SB_ERROR_ENTRY_ID,	struct bch_sb_field_error_entry, v,  0, 16);
-LE64_BITMASK(BCH_SB_ERROR_ENTRY_NR,	struct bch_sb_field_error_entry, v, 16, 64);
-
 struct bch_sb_field_ext {
 	struct bch_sb_field	field;
 	__le64			recovery_passes_required[2];
diff --git a/fs/bcachefs/sb-errors_format.h b/fs/bcachefs/sb-errors_format.h
new file mode 100644
index 0000000000000..84d2763bd597b
--- /dev/null
+++ b/fs/bcachefs/sb-errors_format.h
@@ -0,0 +1,296 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _BCACHEFS_SB_ERRORS_FORMAT_H
+#define _BCACHEFS_SB_ERRORS_FORMAT_H
+
+#define BCH_SB_ERRS()							\
+	x(clean_but_journal_not_empty,				0)	\
+	x(dirty_but_no_journal_entries,				1)	\
+	x(dirty_but_no_journal_entries_post_drop_nonflushes,	2)	\
+	x(sb_clean_journal_seq_mismatch,			3)	\
+	x(sb_clean_btree_root_mismatch,				4)	\
+	x(sb_clean_missing,					5)	\
+	x(jset_unsupported_version,				6)	\
+	x(jset_unknown_csum,					7)	\
+	x(jset_last_seq_newer_than_seq,				8)	\
+	x(jset_past_bucket_end,					9)	\
+	x(jset_seq_blacklisted,					10)	\
+	x(journal_entries_missing,				11)	\
+	x(journal_entry_replicas_not_marked,			12)	\
+	x(journal_entry_past_jset_end,				13)	\
+	x(journal_entry_replicas_data_mismatch,			14)	\
+	x(journal_entry_bkey_u64s_0,				15)	\
+	x(journal_entry_bkey_past_end,				16)	\
+	x(journal_entry_bkey_bad_format,			17)	\
+	x(journal_entry_bkey_invalid,				18)	\
+	x(journal_entry_btree_root_bad_size,			19)	\
+	x(journal_entry_blacklist_bad_size,			20)	\
+	x(journal_entry_blacklist_v2_bad_size,			21)	\
+	x(journal_entry_blacklist_v2_start_past_end,		22)	\
+	x(journal_entry_usage_bad_size,				23)	\
+	x(journal_entry_data_usage_bad_size,			24)	\
+	x(journal_entry_clock_bad_size,				25)	\
+	x(journal_entry_clock_bad_rw,				26)	\
+	x(journal_entry_dev_usage_bad_size,			27)	\
+	x(journal_entry_dev_usage_bad_dev,			28)	\
+	x(journal_entry_dev_usage_bad_pad,			29)	\
+	x(btree_node_unreadable,				30)	\
+	x(btree_node_fault_injected,				31)	\
+	x(btree_node_bad_magic,					32)	\
+	x(btree_node_bad_seq,					33)	\
+	x(btree_node_unsupported_version,			34)	\
+	x(btree_node_bset_older_than_sb_min,			35)	\
+	x(btree_node_bset_newer_than_sb,			36)	\
+	x(btree_node_data_missing,				37)	\
+	x(btree_node_bset_after_end,				38)	\
+	x(btree_node_replicas_sectors_written_mismatch,		39)	\
+	x(btree_node_replicas_data_mismatch,			40)	\
+	x(bset_unknown_csum,					41)	\
+	x(bset_bad_csum,					42)	\
+	x(bset_past_end_of_btree_node,				43)	\
+	x(bset_wrong_sector_offset,				44)	\
+	x(bset_empty,						45)	\
+	x(bset_bad_seq,						46)	\
+	x(bset_blacklisted_journal_seq,				47)	\
+	x(first_bset_blacklisted_journal_seq,			48)	\
+	x(btree_node_bad_btree,					49)	\
+	x(btree_node_bad_level,					50)	\
+	x(btree_node_bad_min_key,				51)	\
+	x(btree_node_bad_max_key,				52)	\
+	x(btree_node_bad_format,				53)	\
+	x(btree_node_bkey_past_bset_end,			54)	\
+	x(btree_node_bkey_bad_format,				55)	\
+	x(btree_node_bad_bkey,					56)	\
+	x(btree_node_bkey_out_of_order,				57)	\
+	x(btree_root_bkey_invalid,				58)	\
+	x(btree_root_read_error,				59)	\
+	x(btree_root_bad_min_key,				60)	\
+	x(btree_root_bad_max_key,				61)	\
+	x(btree_node_read_error,				62)	\
+	x(btree_node_topology_bad_min_key,			63)	\
+	x(btree_node_topology_bad_max_key,			64)	\
+	x(btree_node_topology_overwritten_by_prev_node,		65)	\
+	x(btree_node_topology_overwritten_by_next_node,		66)	\
+	x(btree_node_topology_interior_node_empty,		67)	\
+	x(fs_usage_hidden_wrong,				68)	\
+	x(fs_usage_btree_wrong,					69)	\
+	x(fs_usage_data_wrong,					70)	\
+	x(fs_usage_cached_wrong,				71)	\
+	x(fs_usage_reserved_wrong,				72)	\
+	x(fs_usage_persistent_reserved_wrong,			73)	\
+	x(fs_usage_nr_inodes_wrong,				74)	\
+	x(fs_usage_replicas_wrong,				75)	\
+	x(dev_usage_buckets_wrong,				76)	\
+	x(dev_usage_sectors_wrong,				77)	\
+	x(dev_usage_fragmented_wrong,				78)	\
+	x(dev_usage_buckets_ec_wrong,				79)	\
+	x(bkey_version_in_future,				80)	\
+	x(bkey_u64s_too_small,					81)	\
+	x(bkey_invalid_type_for_btree,				82)	\
+	x(bkey_extent_size_zero,				83)	\
+	x(bkey_extent_size_greater_than_offset,			84)	\
+	x(bkey_size_nonzero,					85)	\
+	x(bkey_snapshot_nonzero,				86)	\
+	x(bkey_snapshot_zero,					87)	\
+	x(bkey_at_pos_max,					88)	\
+	x(bkey_before_start_of_btree_node,			89)	\
+	x(bkey_after_end_of_btree_node,				90)	\
+	x(bkey_val_size_nonzero,				91)	\
+	x(bkey_val_size_too_small,				92)	\
+	x(alloc_v1_val_size_bad,				93)	\
+	x(alloc_v2_unpack_error,				94)	\
+	x(alloc_v3_unpack_error,				95)	\
+	x(alloc_v4_val_size_bad,				96)	\
+	x(alloc_v4_backpointers_start_bad,			97)	\
+	x(alloc_key_data_type_bad,				98)	\
+	x(alloc_key_empty_but_have_data,			99)	\
+	x(alloc_key_dirty_sectors_0,				100)	\
+	x(alloc_key_data_type_inconsistency,			101)	\
+	x(alloc_key_to_missing_dev_bucket,			102)	\
+	x(alloc_key_cached_inconsistency,			103)	\
+	x(alloc_key_cached_but_read_time_zero,			104)	\
+	x(alloc_key_to_missing_lru_entry,			105)	\
+	x(alloc_key_data_type_wrong,				106)	\
+	x(alloc_key_gen_wrong,					107)	\
+	x(alloc_key_dirty_sectors_wrong,			108)	\
+	x(alloc_key_cached_sectors_wrong,			109)	\
+	x(alloc_key_stripe_wrong,				110)	\
+	x(alloc_key_stripe_redundancy_wrong,			111)	\
+	x(bucket_sector_count_overflow,				112)	\
+	x(bucket_metadata_type_mismatch,			113)	\
+	x(need_discard_key_wrong,				114)	\
+	x(freespace_key_wrong,					115)	\
+	x(freespace_hole_missing,				116)	\
+	x(bucket_gens_val_size_bad,				117)	\
+	x(bucket_gens_key_wrong,				118)	\
+	x(bucket_gens_hole_wrong,				119)	\
+	x(bucket_gens_to_invalid_dev,				120)	\
+	x(bucket_gens_to_invalid_buckets,			121)	\
+	x(bucket_gens_nonzero_for_invalid_buckets,		122)	\
+	x(need_discard_freespace_key_to_invalid_dev_bucket,	123)	\
+	x(need_discard_freespace_key_bad,			124)	\
+	x(backpointer_bucket_offset_wrong,			125)	\
+	x(backpointer_to_missing_device,			126)	\
+	x(backpointer_to_missing_alloc,				127)	\
+	x(backpointer_to_missing_ptr,				128)	\
+	x(lru_entry_at_time_0,					129)	\
+	x(lru_entry_to_invalid_bucket,				130)	\
+	x(lru_entry_bad,					131)	\
+	x(btree_ptr_val_too_big,				132)	\
+	x(btree_ptr_v2_val_too_big,				133)	\
+	x(btree_ptr_has_non_ptr,				134)	\
+	x(extent_ptrs_invalid_entry,				135)	\
+	x(extent_ptrs_no_ptrs,					136)	\
+	x(extent_ptrs_too_many_ptrs,				137)	\
+	x(extent_ptrs_redundant_crc,				138)	\
+	x(extent_ptrs_redundant_stripe,				139)	\
+	x(extent_ptrs_unwritten,				140)	\
+	x(extent_ptrs_written_and_unwritten,			141)	\
+	x(ptr_to_invalid_device,				142)	\
+	x(ptr_to_duplicate_device,				143)	\
+	x(ptr_after_last_bucket,				144)	\
+	x(ptr_before_first_bucket,				145)	\
+	x(ptr_spans_multiple_buckets,				146)	\
+	x(ptr_to_missing_backpointer,				147)	\
+	x(ptr_to_missing_alloc_key,				148)	\
+	x(ptr_to_missing_replicas_entry,			149)	\
+	x(ptr_to_missing_stripe,				150)	\
+	x(ptr_to_incorrect_stripe,				151)	\
+	x(ptr_gen_newer_than_bucket_gen,			152)	\
+	x(ptr_too_stale,					153)	\
+	x(stale_dirty_ptr,					154)	\
+	x(ptr_bucket_data_type_mismatch,			155)	\
+	x(ptr_cached_and_erasure_coded,				156)	\
+	x(ptr_crc_uncompressed_size_too_small,			157)	\
+	x(ptr_crc_csum_type_unknown,				158)	\
+	x(ptr_crc_compression_type_unknown,			159)	\
+	x(ptr_crc_redundant,					160)	\
+	x(ptr_crc_uncompressed_size_too_big,			161)	\
+	x(ptr_crc_nonce_mismatch,				162)	\
+	x(ptr_stripe_redundant,					163)	\
+	x(reservation_key_nr_replicas_invalid,			164)	\
+	x(reflink_v_refcount_wrong,				165)	\
+	x(reflink_p_to_missing_reflink_v,			166)	\
+	x(stripe_pos_bad,					167)	\
+	x(stripe_val_size_bad,					168)	\
+	x(stripe_sector_count_wrong,				169)	\
+	x(snapshot_tree_pos_bad,				170)	\
+	x(snapshot_tree_to_missing_snapshot,			171)	\
+	x(snapshot_tree_to_missing_subvol,			172)	\
+	x(snapshot_tree_to_wrong_subvol,			173)	\
+	x(snapshot_tree_to_snapshot_subvol,			174)	\
+	x(snapshot_pos_bad,					175)	\
+	x(snapshot_parent_bad,					176)	\
+	x(snapshot_children_not_normalized,			177)	\
+	x(snapshot_child_duplicate,				178)	\
+	x(snapshot_child_bad,					179)	\
+	x(snapshot_skiplist_not_normalized,			180)	\
+	x(snapshot_skiplist_bad,				181)	\
+	x(snapshot_should_not_have_subvol,			182)	\
+	x(snapshot_to_bad_snapshot_tree,			183)	\
+	x(snapshot_bad_depth,					184)	\
+	x(snapshot_bad_skiplist,				185)	\
+	x(subvol_pos_bad,					186)	\
+	x(subvol_not_master_and_not_snapshot,			187)	\
+	x(subvol_to_missing_root,				188)	\
+	x(subvol_root_wrong_bi_subvol,				189)	\
+	x(bkey_in_missing_snapshot,				190)	\
+	x(inode_pos_inode_nonzero,				191)	\
+	x(inode_pos_blockdev_range,				192)	\
+	x(inode_unpack_error,					193)	\
+	x(inode_str_hash_invalid,				194)	\
+	x(inode_v3_fields_start_bad,				195)	\
+	x(inode_snapshot_mismatch,				196)	\
+	x(inode_unlinked_but_clean,				197)	\
+	x(inode_unlinked_but_nlink_nonzero,			198)	\
+	x(inode_checksum_type_invalid,				199)	\
+	x(inode_compression_type_invalid,			200)	\
+	x(inode_subvol_root_but_not_dir,			201)	\
+	x(inode_i_size_dirty_but_clean,				202)	\
+	x(inode_i_sectors_dirty_but_clean,			203)	\
+	x(inode_i_sectors_wrong,				204)	\
+	x(inode_dir_wrong_nlink,				205)	\
+	x(inode_dir_multiple_links,				206)	\
+	x(inode_multiple_links_but_nlink_0,			207)	\
+	x(inode_wrong_backpointer,				208)	\
+	x(inode_wrong_nlink,					209)	\
+	x(inode_unreachable,					210)	\
+	x(deleted_inode_but_clean,				211)	\
+	x(deleted_inode_missing,				212)	\
+	x(deleted_inode_is_dir,					213)	\
+	x(deleted_inode_not_unlinked,				214)	\
+	x(extent_overlapping,					215)	\
+	x(extent_in_missing_inode,				216)	\
+	x(extent_in_non_reg_inode,				217)	\
+	x(extent_past_end_of_inode,				218)	\
+	x(dirent_empty_name,					219)	\
+	x(dirent_val_too_big,					220)	\
+	x(dirent_name_too_long,					221)	\
+	x(dirent_name_embedded_nul,				222)	\
+	x(dirent_name_dot_or_dotdot,				223)	\
+	x(dirent_name_has_slash,				224)	\
+	x(dirent_d_type_wrong,					225)	\
+	x(inode_bi_parent_wrong,				226)	\
+	x(dirent_in_missing_dir_inode,				227)	\
+	x(dirent_in_non_dir_inode,				228)	\
+	x(dirent_to_missing_inode,				229)	\
+	x(dirent_to_missing_subvol,				230)	\
+	x(dirent_to_itself,					231)	\
+	x(quota_type_invalid,					232)	\
+	x(xattr_val_size_too_small,				233)	\
+	x(xattr_val_size_too_big,				234)	\
+	x(xattr_invalid_type,					235)	\
+	x(xattr_name_invalid_chars,				236)	\
+	x(xattr_in_missing_inode,				237)	\
+	x(root_subvol_missing,					238)	\
+	x(root_dir_missing,					239)	\
+	x(root_inode_not_dir,					240)	\
+	x(dir_loop,						241)	\
+	x(hash_table_key_duplicate,				242)	\
+	x(hash_table_key_wrong_offset,				243)	\
+	x(unlinked_inode_not_on_deleted_list,			244)	\
+	x(reflink_p_front_pad_bad,				245)	\
+	x(journal_entry_dup_same_device,			246)	\
+	x(inode_bi_subvol_missing,				247)	\
+	x(inode_bi_subvol_wrong,				248)	\
+	x(inode_points_to_missing_dirent,			249)	\
+	x(inode_points_to_wrong_dirent,				250)	\
+	x(inode_bi_parent_nonzero,				251)	\
+	x(dirent_to_missing_parent_subvol,			252)	\
+	x(dirent_not_visible_in_parent_subvol,			253)	\
+	x(subvol_fs_path_parent_wrong,				254)	\
+	x(subvol_root_fs_path_parent_nonzero,			255)	\
+	x(subvol_children_not_set,				256)	\
+	x(subvol_children_bad,					257)	\
+	x(subvol_loop,						258)	\
+	x(subvol_unreachable,					259)	\
+	x(btree_node_bkey_bad_u64s,				260)	\
+	x(btree_node_topology_empty_interior_node,		261)	\
+	x(btree_ptr_v2_min_key_bad,				262)	\
+	x(btree_root_unreadable_and_scan_found_nothing,		263)	\
+	x(snapshot_node_missing,				264)	\
+	x(dup_backpointer_to_bad_csum_extent,			265)	\
+	x(btree_bitmap_not_marked,				266)	\
+	x(sb_clean_entry_overrun,				267)	\
+	x(btree_ptr_v2_written_0,				268)	\
+	x(subvol_snapshot_bad,					269)	\
+	x(subvol_inode_bad,					270)
+
+enum bch_sb_error_id {
+#define x(t, n) BCH_FSCK_ERR_##t = n,
+	BCH_SB_ERRS()
+#undef x
+	BCH_SB_ERR_MAX
+};
+
+struct bch_sb_field_errors {
+	struct bch_sb_field	field;
+	struct bch_sb_field_error_entry {
+		__le64		v;
+		__le64		last_error_time;
+	}			entries[];
+};
+
+LE64_BITMASK(BCH_SB_ERROR_ENTRY_ID,	struct bch_sb_field_error_entry, v,  0, 16);
+LE64_BITMASK(BCH_SB_ERROR_ENTRY_NR,	struct bch_sb_field_error_entry, v, 16, 64);
+
+#endif /* _BCACHEFS_SB_ERRORS_FORMAT_H */
diff --git a/fs/bcachefs/sb-errors_types.h b/fs/bcachefs/sb-errors_types.h
index 666599d3fb9d7..40325239c3b0f 100644
--- a/fs/bcachefs/sb-errors_types.h
+++ b/fs/bcachefs/sb-errors_types.h
@@ -4,286 +4,6 @@
 
 #include "darray.h"
 
-#define BCH_SB_ERRS()							\
-	x(clean_but_journal_not_empty,				0)	\
-	x(dirty_but_no_journal_entries,				1)	\
-	x(dirty_but_no_journal_entries_post_drop_nonflushes,	2)	\
-	x(sb_clean_journal_seq_mismatch,			3)	\
-	x(sb_clean_btree_root_mismatch,				4)	\
-	x(sb_clean_missing,					5)	\
-	x(jset_unsupported_version,				6)	\
-	x(jset_unknown_csum,					7)	\
-	x(jset_last_seq_newer_than_seq,				8)	\
-	x(jset_past_bucket_end,					9)	\
-	x(jset_seq_blacklisted,					10)	\
-	x(journal_entries_missing,				11)	\
-	x(journal_entry_replicas_not_marked,			12)	\
-	x(journal_entry_past_jset_end,				13)	\
-	x(journal_entry_replicas_data_mismatch,			14)	\
-	x(journal_entry_bkey_u64s_0,				15)	\
-	x(journal_entry_bkey_past_end,				16)	\
-	x(journal_entry_bkey_bad_format,			17)	\
-	x(journal_entry_bkey_invalid,				18)	\
-	x(journal_entry_btree_root_bad_size,			19)	\
-	x(journal_entry_blacklist_bad_size,			20)	\
-	x(journal_entry_blacklist_v2_bad_size,			21)	\
-	x(journal_entry_blacklist_v2_start_past_end,		22)	\
-	x(journal_entry_usage_bad_size,				23)	\
-	x(journal_entry_data_usage_bad_size,			24)	\
-	x(journal_entry_clock_bad_size,				25)	\
-	x(journal_entry_clock_bad_rw,				26)	\
-	x(journal_entry_dev_usage_bad_size,			27)	\
-	x(journal_entry_dev_usage_bad_dev,			28)	\
-	x(journal_entry_dev_usage_bad_pad,			29)	\
-	x(btree_node_unreadable,				30)	\
-	x(btree_node_fault_injected,				31)	\
-	x(btree_node_bad_magic,					32)	\
-	x(btree_node_bad_seq,					33)	\
-	x(btree_node_unsupported_version,			34)	\
-	x(btree_node_bset_older_than_sb_min,			35)	\
-	x(btree_node_bset_newer_than_sb,			36)	\
-	x(btree_node_data_missing,				37)	\
-	x(btree_node_bset_after_end,				38)	\
-	x(btree_node_replicas_sectors_written_mismatch,		39)	\
-	x(btree_node_replicas_data_mismatch,			40)	\
-	x(bset_unknown_csum,					41)	\
-	x(bset_bad_csum,					42)	\
-	x(bset_past_end_of_btree_node,				43)	\
-	x(bset_wrong_sector_offset,				44)	\
-	x(bset_empty,						45)	\
-	x(bset_bad_seq,						46)	\
-	x(bset_blacklisted_journal_seq,				47)	\
-	x(first_bset_blacklisted_journal_seq,			48)	\
-	x(btree_node_bad_btree,					49)	\
-	x(btree_node_bad_level,					50)	\
-	x(btree_node_bad_min_key,				51)	\
-	x(btree_node_bad_max_key,				52)	\
-	x(btree_node_bad_format,				53)	\
-	x(btree_node_bkey_past_bset_end,			54)	\
-	x(btree_node_bkey_bad_format,				55)	\
-	x(btree_node_bad_bkey,					56)	\
-	x(btree_node_bkey_out_of_order,				57)	\
-	x(btree_root_bkey_invalid,				58)	\
-	x(btree_root_read_error,				59)	\
-	x(btree_root_bad_min_key,				60)	\
-	x(btree_root_bad_max_key,				61)	\
-	x(btree_node_read_error,				62)	\
-	x(btree_node_topology_bad_min_key,			63)	\
-	x(btree_node_topology_bad_max_key,			64)	\
-	x(btree_node_topology_overwritten_by_prev_node,		65)	\
-	x(btree_node_topology_overwritten_by_next_node,		66)	\
-	x(btree_node_topology_interior_node_empty,		67)	\
-	x(fs_usage_hidden_wrong,				68)	\
-	x(fs_usage_btree_wrong,					69)	\
-	x(fs_usage_data_wrong,					70)	\
-	x(fs_usage_cached_wrong,				71)	\
-	x(fs_usage_reserved_wrong,				72)	\
-	x(fs_usage_persistent_reserved_wrong,			73)	\
-	x(fs_usage_nr_inodes_wrong,				74)	\
-	x(fs_usage_replicas_wrong,				75)	\
-	x(dev_usage_buckets_wrong,				76)	\
-	x(dev_usage_sectors_wrong,				77)	\
-	x(dev_usage_fragmented_wrong,				78)	\
-	x(dev_usage_buckets_ec_wrong,				79)	\
-	x(bkey_version_in_future,				80)	\
-	x(bkey_u64s_too_small,					81)	\
-	x(bkey_invalid_type_for_btree,				82)	\
-	x(bkey_extent_size_zero,				83)	\
-	x(bkey_extent_size_greater_than_offset,			84)	\
-	x(bkey_size_nonzero,					85)	\
-	x(bkey_snapshot_nonzero,				86)	\
-	x(bkey_snapshot_zero,					87)	\
-	x(bkey_at_pos_max,					88)	\
-	x(bkey_before_start_of_btree_node,			89)	\
-	x(bkey_after_end_of_btree_node,				90)	\
-	x(bkey_val_size_nonzero,				91)	\
-	x(bkey_val_size_too_small,				92)	\
-	x(alloc_v1_val_size_bad,				93)	\
-	x(alloc_v2_unpack_error,				94)	\
-	x(alloc_v3_unpack_error,				95)	\
-	x(alloc_v4_val_size_bad,				96)	\
-	x(alloc_v4_backpointers_start_bad,			97)	\
-	x(alloc_key_data_type_bad,				98)	\
-	x(alloc_key_empty_but_have_data,			99)	\
-	x(alloc_key_dirty_sectors_0,				100)	\
-	x(alloc_key_data_type_inconsistency,			101)	\
-	x(alloc_key_to_missing_dev_bucket,			102)	\
-	x(alloc_key_cached_inconsistency,			103)	\
-	x(alloc_key_cached_but_read_time_zero,			104)	\
-	x(alloc_key_to_missing_lru_entry,			105)	\
-	x(alloc_key_data_type_wrong,				106)	\
-	x(alloc_key_gen_wrong,					107)	\
-	x(alloc_key_dirty_sectors_wrong,			108)	\
-	x(alloc_key_cached_sectors_wrong,			109)	\
-	x(alloc_key_stripe_wrong,				110)	\
-	x(alloc_key_stripe_redundancy_wrong,			111)	\
-	x(bucket_sector_count_overflow,				112)	\
-	x(bucket_metadata_type_mismatch,			113)	\
-	x(need_discard_key_wrong,				114)	\
-	x(freespace_key_wrong,					115)	\
-	x(freespace_hole_missing,				116)	\
-	x(bucket_gens_val_size_bad,				117)	\
-	x(bucket_gens_key_wrong,				118)	\
-	x(bucket_gens_hole_wrong,				119)	\
-	x(bucket_gens_to_invalid_dev,				120)	\
-	x(bucket_gens_to_invalid_buckets,			121)	\
-	x(bucket_gens_nonzero_for_invalid_buckets,		122)	\
-	x(need_discard_freespace_key_to_invalid_dev_bucket,	123)	\
-	x(need_discard_freespace_key_bad,			124)	\
-	x(backpointer_bucket_offset_wrong,			125)	\
-	x(backpointer_to_missing_device,			126)	\
-	x(backpointer_to_missing_alloc,				127)	\
-	x(backpointer_to_missing_ptr,				128)	\
-	x(lru_entry_at_time_0,					129)	\
-	x(lru_entry_to_invalid_bucket,				130)	\
-	x(lru_entry_bad,					131)	\
-	x(btree_ptr_val_too_big,				132)	\
-	x(btree_ptr_v2_val_too_big,				133)	\
-	x(btree_ptr_has_non_ptr,				134)	\
-	x(extent_ptrs_invalid_entry,				135)	\
-	x(extent_ptrs_no_ptrs,					136)	\
-	x(extent_ptrs_too_many_ptrs,				137)	\
-	x(extent_ptrs_redundant_crc,				138)	\
-	x(extent_ptrs_redundant_stripe,				139)	\
-	x(extent_ptrs_unwritten,				140)	\
-	x(extent_ptrs_written_and_unwritten,			141)	\
-	x(ptr_to_invalid_device,				142)	\
-	x(ptr_to_duplicate_device,				143)	\
-	x(ptr_after_last_bucket,				144)	\
-	x(ptr_before_first_bucket,				145)	\
-	x(ptr_spans_multiple_buckets,				146)	\
-	x(ptr_to_missing_backpointer,				147)	\
-	x(ptr_to_missing_alloc_key,				148)	\
-	x(ptr_to_missing_replicas_entry,			149)	\
-	x(ptr_to_missing_stripe,				150)	\
-	x(ptr_to_incorrect_stripe,				151)	\
-	x(ptr_gen_newer_than_bucket_gen,			152)	\
-	x(ptr_too_stale,					153)	\
-	x(stale_dirty_ptr,					154)	\
-	x(ptr_bucket_data_type_mismatch,			155)	\
-	x(ptr_cached_and_erasure_coded,				156)	\
-	x(ptr_crc_uncompressed_size_too_small,			157)	\
-	x(ptr_crc_csum_type_unknown,				158)	\
-	x(ptr_crc_compression_type_unknown,			159)	\
-	x(ptr_crc_redundant,					160)	\
-	x(ptr_crc_uncompressed_size_too_big,			161)	\
-	x(ptr_crc_nonce_mismatch,				162)	\
-	x(ptr_stripe_redundant,					163)	\
-	x(reservation_key_nr_replicas_invalid,			164)	\
-	x(reflink_v_refcount_wrong,				165)	\
-	x(reflink_p_to_missing_reflink_v,			166)	\
-	x(stripe_pos_bad,					167)	\
-	x(stripe_val_size_bad,					168)	\
-	x(stripe_sector_count_wrong,				169)	\
-	x(snapshot_tree_pos_bad,				170)	\
-	x(snapshot_tree_to_missing_snapshot,			171)	\
-	x(snapshot_tree_to_missing_subvol,			172)	\
-	x(snapshot_tree_to_wrong_subvol,			173)	\
-	x(snapshot_tree_to_snapshot_subvol,			174)	\
-	x(snapshot_pos_bad,					175)	\
-	x(snapshot_parent_bad,					176)	\
-	x(snapshot_children_not_normalized,			177)	\
-	x(snapshot_child_duplicate,				178)	\
-	x(snapshot_child_bad,					179)	\
-	x(snapshot_skiplist_not_normalized,			180)	\
-	x(snapshot_skiplist_bad,				181)	\
-	x(snapshot_should_not_have_subvol,			182)	\
-	x(snapshot_to_bad_snapshot_tree,			183)	\
-	x(snapshot_bad_depth,					184)	\
-	x(snapshot_bad_skiplist,				185)	\
-	x(subvol_pos_bad,					186)	\
-	x(subvol_not_master_and_not_snapshot,			187)	\
-	x(subvol_to_missing_root,				188)	\
-	x(subvol_root_wrong_bi_subvol,				189)	\
-	x(bkey_in_missing_snapshot,				190)	\
-	x(inode_pos_inode_nonzero,				191)	\
-	x(inode_pos_blockdev_range,				192)	\
-	x(inode_unpack_error,					193)	\
-	x(inode_str_hash_invalid,				194)	\
-	x(inode_v3_fields_start_bad,				195)	\
-	x(inode_snapshot_mismatch,				196)	\
-	x(inode_unlinked_but_clean,				197)	\
-	x(inode_unlinked_but_nlink_nonzero,			198)	\
-	x(inode_checksum_type_invalid,				199)	\
-	x(inode_compression_type_invalid,			200)	\
-	x(inode_subvol_root_but_not_dir,			201)	\
-	x(inode_i_size_dirty_but_clean,				202)	\
-	x(inode_i_sectors_dirty_but_clean,			203)	\
-	x(inode_i_sectors_wrong,				204)	\
-	x(inode_dir_wrong_nlink,				205)	\
-	x(inode_dir_multiple_links,				206)	\
-	x(inode_multiple_links_but_nlink_0,			207)	\
-	x(inode_wrong_backpointer,				208)	\
-	x(inode_wrong_nlink,					209)	\
-	x(inode_unreachable,					210)	\
-	x(deleted_inode_but_clean,				211)	\
-	x(deleted_inode_missing,				212)	\
-	x(deleted_inode_is_dir,					213)	\
-	x(deleted_inode_not_unlinked,				214)	\
-	x(extent_overlapping,					215)	\
-	x(extent_in_missing_inode,				216)	\
-	x(extent_in_non_reg_inode,				217)	\
-	x(extent_past_end_of_inode,				218)	\
-	x(dirent_empty_name,					219)	\
-	x(dirent_val_too_big,					220)	\
-	x(dirent_name_too_long,					221)	\
-	x(dirent_name_embedded_nul,				222)	\
-	x(dirent_name_dot_or_dotdot,				223)	\
-	x(dirent_name_has_slash,				224)	\
-	x(dirent_d_type_wrong,					225)	\
-	x(inode_bi_parent_wrong,				226)	\
-	x(dirent_in_missing_dir_inode,				227)	\
-	x(dirent_in_non_dir_inode,				228)	\
-	x(dirent_to_missing_inode,				229)	\
-	x(dirent_to_missing_subvol,				230)	\
-	x(dirent_to_itself,					231)	\
-	x(quota_type_invalid,					232)	\
-	x(xattr_val_size_too_small,				233)	\
-	x(xattr_val_size_too_big,				234)	\
-	x(xattr_invalid_type,					235)	\
-	x(xattr_name_invalid_chars,				236)	\
-	x(xattr_in_missing_inode,				237)	\
-	x(root_subvol_missing,					238)	\
-	x(root_dir_missing,					239)	\
-	x(root_inode_not_dir,					240)	\
-	x(dir_loop,						241)	\
-	x(hash_table_key_duplicate,				242)	\
-	x(hash_table_key_wrong_offset,				243)	\
-	x(unlinked_inode_not_on_deleted_list,			244)	\
-	x(reflink_p_front_pad_bad,				245)	\
-	x(journal_entry_dup_same_device,			246)	\
-	x(inode_bi_subvol_missing,				247)	\
-	x(inode_bi_subvol_wrong,				248)	\
-	x(inode_points_to_missing_dirent,			249)	\
-	x(inode_points_to_wrong_dirent,				250)	\
-	x(inode_bi_parent_nonzero,				251)	\
-	x(dirent_to_missing_parent_subvol,			252)	\
-	x(dirent_not_visible_in_parent_subvol,			253)	\
-	x(subvol_fs_path_parent_wrong,				254)	\
-	x(subvol_root_fs_path_parent_nonzero,			255)	\
-	x(subvol_children_not_set,				256)	\
-	x(subvol_children_bad,					257)	\
-	x(subvol_loop,						258)	\
-	x(subvol_unreachable,					259)	\
-	x(btree_node_bkey_bad_u64s,				260)	\
-	x(btree_node_topology_empty_interior_node,		261)	\
-	x(btree_ptr_v2_min_key_bad,				262)	\
-	x(btree_root_unreadable_and_scan_found_nothing,		263)	\
-	x(snapshot_node_missing,				264)	\
-	x(dup_backpointer_to_bad_csum_extent,			265)	\
-	x(btree_bitmap_not_marked,				266)	\
-	x(sb_clean_entry_overrun,				267)	\
-	x(btree_ptr_v2_written_0,				268)	\
-	x(subvol_snapshot_bad,					269)	\
-	x(subvol_inode_bad,					270)
-
-enum bch_sb_error_id {
-#define x(t, n) BCH_FSCK_ERR_##t = n,
-	BCH_SB_ERRS()
-#undef x
-	BCH_SB_ERR_MAX
-};
-
 struct bch_sb_error_entry_cpu {
 	u64			id:16,
 				nr:48;
@@ -293,4 +13,3 @@ struct bch_sb_error_entry_cpu {
 typedef DARRAY(struct bch_sb_error_entry_cpu) bch_sb_errors_cpu;
 
 #endif /* _BCACHEFS_SB_ERRORS_TYPES_H */
-
-- 
GitLab


From 8528bde1b66bab9a0abc2f521523abd00049c81b Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Tue, 28 May 2024 18:20:52 -0400
Subject: [PATCH 379/950] bcachefs: Fix uninitialized var warning

Can't actually be used uninitialized, but gcc was being silly.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/backpointers.c | 2 +-
 fs/bcachefs/buckets.c      | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/bcachefs/backpointers.c b/fs/bcachefs/backpointers.c
index 692b1c7d5018c..4321f9fb73bd9 100644
--- a/fs/bcachefs/backpointers.c
+++ b/fs/bcachefs/backpointers.c
@@ -690,7 +690,7 @@ static int check_extent_to_backpointers(struct btree_trans *trans,
 
 	ptrs = bch2_bkey_ptrs_c(k);
 	bkey_for_each_ptr_decode(k.k, ptrs, p, entry) {
-		struct bpos bucket_pos;
+		struct bpos bucket_pos = POS_MIN;
 		struct bch_backpointer bp;
 
 		if (p.ptr.cached)
diff --git a/fs/bcachefs/buckets.c b/fs/bcachefs/buckets.c
index b469586517a86..ed97712d0db1e 100644
--- a/fs/bcachefs/buckets.c
+++ b/fs/bcachefs/buckets.c
@@ -1134,7 +1134,7 @@ static int __trigger_extent(struct btree_trans *trans,
 	r.e.nr_required	= 1;
 
 	bkey_for_each_ptr_decode(k.k, ptrs, p, entry) {
-		s64 disk_sectors;
+		s64 disk_sectors = 0;
 		ret = bch2_trigger_pointer(trans, btree_id, level, k, p, entry, &disk_sectors, flags);
 		if (ret < 0)
 			return ret;
-- 
GitLab


From 33c563ebf8d3deed7d8addd20d77398ac737ef9a Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Wed, 8 May 2024 22:50:34 +0200
Subject: [PATCH 380/950] netfilter: nft_payload: skbuff vlan metadata mangle
 support

Userspace assumes vlan header is present at a given offset, but vlan
offload allows to store this in metadata fields of the skbuff. Hence
mangling vlan results in a garbled packet. Handle this transparently by
adding a parser to the kernel.

If vlan metadata is present and payload offset is over 12 bytes (source
and destination mac address fields), then subtract vlan header present
in vlan metadata, otherwise mangle vlan metadata based on offset and
length, extracting data from the source register.

This is similar to:

  8cfd23e67401 ("netfilter: nft_payload: work around vlan header stripping")

to deal with vlan payload mangling.

Fixes: 7ec3f7b47b8d ("netfilter: nft_payload: add packet mangling support")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nft_payload.c | 72 +++++++++++++++++++++++++++++++++----
 1 file changed, 65 insertions(+), 7 deletions(-)

diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c
index a3cb5dbcb362c..0c43d748e23ae 100644
--- a/net/netfilter/nft_payload.c
+++ b/net/netfilter/nft_payload.c
@@ -145,12 +145,12 @@ int nft_payload_inner_offset(const struct nft_pktinfo *pkt)
 	return pkt->inneroff;
 }
 
-static bool nft_payload_need_vlan_copy(const struct nft_payload *priv)
+static bool nft_payload_need_vlan_adjust(u32 offset, u32 len)
 {
-	unsigned int len = priv->offset + priv->len;
+	unsigned int boundary = offset + len;
 
 	/* data past ether src/dst requested, copy needed */
-	if (len > offsetof(struct ethhdr, h_proto))
+	if (boundary > offsetof(struct ethhdr, h_proto))
 		return true;
 
 	return false;
@@ -174,7 +174,7 @@ void nft_payload_eval(const struct nft_expr *expr,
 			goto err;
 
 		if (skb_vlan_tag_present(skb) &&
-		    nft_payload_need_vlan_copy(priv)) {
+		    nft_payload_need_vlan_adjust(priv->offset, priv->len)) {
 			if (!nft_payload_copy_vlan(dest, skb,
 						   priv->offset, priv->len))
 				goto err;
@@ -801,21 +801,79 @@ struct nft_payload_set {
 	u8			csum_flags;
 };
 
+/* This is not struct vlan_hdr. */
+struct nft_payload_vlan_hdr {
+	__be16			h_vlan_proto;
+	__be16			h_vlan_TCI;
+};
+
+static bool
+nft_payload_set_vlan(const u32 *src, struct sk_buff *skb, u8 offset, u8 len,
+		     int *vlan_hlen)
+{
+	struct nft_payload_vlan_hdr *vlanh;
+	__be16 vlan_proto;
+	u16 vlan_tci;
+
+	if (offset >= offsetof(struct vlan_ethhdr, h_vlan_encapsulated_proto)) {
+		*vlan_hlen = VLAN_HLEN;
+		return true;
+	}
+
+	switch (offset) {
+	case offsetof(struct vlan_ethhdr, h_vlan_proto):
+		if (len == 2) {
+			vlan_proto = nft_reg_load_be16(src);
+			skb->vlan_proto = vlan_proto;
+		} else if (len == 4) {
+			vlanh = (struct nft_payload_vlan_hdr *)src;
+			__vlan_hwaccel_put_tag(skb, vlanh->h_vlan_proto,
+					       ntohs(vlanh->h_vlan_TCI));
+		} else {
+			return false;
+		}
+		break;
+	case offsetof(struct vlan_ethhdr, h_vlan_TCI):
+		if (len != 2)
+			return false;
+
+		vlan_tci = ntohs(nft_reg_load_be16(src));
+		skb->vlan_tci = vlan_tci;
+		break;
+	default:
+		return false;
+	}
+
+	return true;
+}
+
 static void nft_payload_set_eval(const struct nft_expr *expr,
 				 struct nft_regs *regs,
 				 const struct nft_pktinfo *pkt)
 {
 	const struct nft_payload_set *priv = nft_expr_priv(expr);
-	struct sk_buff *skb = pkt->skb;
 	const u32 *src = &regs->data[priv->sreg];
-	int offset, csum_offset;
+	int offset, csum_offset, vlan_hlen = 0;
+	struct sk_buff *skb = pkt->skb;
 	__wsum fsum, tsum;
 
 	switch (priv->base) {
 	case NFT_PAYLOAD_LL_HEADER:
 		if (!skb_mac_header_was_set(skb))
 			goto err;
-		offset = skb_mac_header(skb) - skb->data;
+
+		if (skb_vlan_tag_present(skb) &&
+		    nft_payload_need_vlan_adjust(priv->offset, priv->len)) {
+			if (!nft_payload_set_vlan(src, skb,
+						  priv->offset, priv->len,
+						  &vlan_hlen))
+				goto err;
+
+			if (!vlan_hlen)
+				return;
+		}
+
+		offset = skb_mac_header(skb) - skb->data - vlan_hlen;
 		break;
 	case NFT_PAYLOAD_NETWORK_HEADER:
 		offset = skb_network_offset(skb);
-- 
GitLab


From 21a673bddc8fd4873c370caf9ae70ffc6d47e8d3 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Mon, 13 May 2024 12:27:15 +0200
Subject: [PATCH 381/950] netfilter: tproxy: bail out if IP has been disabled
 on the device

syzbot reports:
general protection fault, probably for non-canonical address 0xdffffc0000000003: 0000 [#1] PREEMPT SMP KASAN PTI
KASAN: null-ptr-deref in range [0x0000000000000018-0x000000000000001f]
[..]
RIP: 0010:nf_tproxy_laddr4+0xb7/0x340 net/ipv4/netfilter/nf_tproxy_ipv4.c:62
Call Trace:
 nft_tproxy_eval_v4 net/netfilter/nft_tproxy.c:56 [inline]
 nft_tproxy_eval+0xa9a/0x1a00 net/netfilter/nft_tproxy.c:168

__in_dev_get_rcu() can return NULL, so check for this.

Reported-and-tested-by: syzbot+b94a6818504ea90d7661@syzkaller.appspotmail.com
Fixes: cc6eb4338569 ("tproxy: use the interface primary IP address as a default value for --on-ip")
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/ipv4/netfilter/nf_tproxy_ipv4.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ipv4/netfilter/nf_tproxy_ipv4.c b/net/ipv4/netfilter/nf_tproxy_ipv4.c
index 69e3317996043..73e66a088e25e 100644
--- a/net/ipv4/netfilter/nf_tproxy_ipv4.c
+++ b/net/ipv4/netfilter/nf_tproxy_ipv4.c
@@ -58,6 +58,8 @@ __be32 nf_tproxy_laddr4(struct sk_buff *skb, __be32 user_laddr, __be32 daddr)
 
 	laddr = 0;
 	indev = __in_dev_get_rcu(skb->dev);
+	if (!indev)
+		return daddr;
 
 	in_dev_for_each_ifa_rcu(ifa, indev) {
 		if (ifa->ifa_flags & IFA_F_SECONDARY)
-- 
GitLab


From e8ded22ef0f4831279c363c264cd41cd9d59ca9e Mon Sep 17 00:00:00 2001
From: Eric Garver <eric@garver.life>
Date: Tue, 21 May 2024 10:25:05 -0400
Subject: [PATCH 382/950] netfilter: nft_fib: allow from forward/input without
 iif selector

This removes the restriction of needing iif selector in the
forward/input hooks for fib lookups when requested result is
oif/oifname.

Removing this restriction allows "loose" lookups from the forward hooks.

Fixes: be8be04e5ddb ("netfilter: nft_fib: reverse path filter for policy-based routing on iif")
Signed-off-by: Eric Garver <eric@garver.life>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nft_fib.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/net/netfilter/nft_fib.c b/net/netfilter/nft_fib.c
index 37cfe6dd712d8..b58f62195ff3e 100644
--- a/net/netfilter/nft_fib.c
+++ b/net/netfilter/nft_fib.c
@@ -35,11 +35,9 @@ int nft_fib_validate(const struct nft_ctx *ctx, const struct nft_expr *expr,
 	switch (priv->result) {
 	case NFT_FIB_RESULT_OIF:
 	case NFT_FIB_RESULT_OIFNAME:
-		hooks = (1 << NF_INET_PRE_ROUTING);
-		if (priv->flags & NFTA_FIB_F_IIF) {
-			hooks |= (1 << NF_INET_LOCAL_IN) |
-				 (1 << NF_INET_FORWARD);
-		}
+		hooks = (1 << NF_INET_PRE_ROUTING) |
+			(1 << NF_INET_LOCAL_IN) |
+			(1 << NF_INET_FORWARD);
 		break;
 	case NFT_FIB_RESULT_ADDRTYPE:
 		if (priv->flags & NFTA_FIB_F_IIF)
-- 
GitLab


From d55510527153d17a3af8cc2df69c04f95ae1350d Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Tue, 28 May 2024 15:55:51 -0700
Subject: [PATCH 383/950] cxl/test: Add missing vmalloc.h for
 tools/testing/cxl/test/mem.c
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

tools/testing/cxl/test/mem.c uses vmalloc() and vfree() but does not
include linux/vmalloc.h. Kernel v6.10 made changes that causes the
currently included headers not depend on vmalloc.h and therefore
mem.c can no longer compile. Add linux/vmalloc.h to fix compile
issue.

  CC [M]  tools/testing/cxl/test/mem.o
tools/testing/cxl/test/mem.c: In function ‘label_area_release’:
tools/testing/cxl/test/mem.c:1428:9: error: implicit declaration of function ‘vfree’; did you mean ‘kvfree’? [-Werror=implicit-function-declaration]
 1428 |         vfree(lsa);
      |         ^~~~~
      |         kvfree
tools/testing/cxl/test/mem.c: In function ‘cxl_mock_mem_probe’:
tools/testing/cxl/test/mem.c:1466:22: error: implicit declaration of function ‘vmalloc’; did you mean ‘kmalloc’? [-Werror=implicit-function-declaration]
 1466 |         mdata->lsa = vmalloc(LSA_SIZE);
      |                      ^~~~~~~
      |                      kmalloc

Fixes: 7d3eb23c4ccf ("tools/testing/cxl: Introduce a mock memory device + driver")
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Alison Schofield <alison.schofield@intel.com>
Link: https://lore.kernel.org/r/20240528225551.1025977-1-dave.jiang@intel.com
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
---
 tools/testing/cxl/test/mem.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c
index 6584443144de8..eaf091a3d3313 100644
--- a/tools/testing/cxl/test/mem.c
+++ b/tools/testing/cxl/test/mem.c
@@ -3,6 +3,7 @@
 
 #include <linux/platform_device.h>
 #include <linux/mod_devicetable.h>
+#include <linux/vmalloc.h>
 #include <linux/module.h>
 #include <linux/delay.h>
 #include <linux/sizes.h>
-- 
GitLab


From 49ba7b515c4c0719b866d16f068e62d16a8a3dd1 Mon Sep 17 00:00:00 2001
From: Li Zhijian <lizhijian@fujitsu.com>
Date: Tue, 7 May 2024 13:34:21 +0800
Subject: [PATCH 384/950] cxl/region: Fix memregion leaks in
 devm_cxl_add_region()

Move the mode verification to __create_region() before allocating the
memregion to avoid the memregion leaks.

Fixes: 6e099264185d ("cxl/region: Add volatile region creation support")
Signed-off-by: Li Zhijian <lizhijian@fujitsu.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Link: https://lore.kernel.org/r/20240507053421.456439-1-lizhijian@fujitsu.com
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
---
 drivers/cxl/core/region.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
index 00a9f0eef8dd2..3c2b6144be23c 100644
--- a/drivers/cxl/core/region.c
+++ b/drivers/cxl/core/region.c
@@ -2352,15 +2352,6 @@ static struct cxl_region *devm_cxl_add_region(struct cxl_root_decoder *cxlrd,
 	struct device *dev;
 	int rc;
 
-	switch (mode) {
-	case CXL_DECODER_RAM:
-	case CXL_DECODER_PMEM:
-		break;
-	default:
-		dev_err(&cxlrd->cxlsd.cxld.dev, "unsupported mode %d\n", mode);
-		return ERR_PTR(-EINVAL);
-	}
-
 	cxlr = cxl_region_alloc(cxlrd, id);
 	if (IS_ERR(cxlr))
 		return cxlr;
@@ -2415,6 +2406,15 @@ static struct cxl_region *__create_region(struct cxl_root_decoder *cxlrd,
 {
 	int rc;
 
+	switch (mode) {
+	case CXL_DECODER_RAM:
+	case CXL_DECODER_PMEM:
+		break;
+	default:
+		dev_err(&cxlrd->cxlsd.cxld.dev, "unsupported mode %d\n", mode);
+		return ERR_PTR(-EINVAL);
+	}
+
 	rc = memregion_alloc(GFP_KERNEL);
 	if (rc < 0)
 		return ERR_PTR(rc);
-- 
GitLab


From 83208cbf2f08c270033003e10f3e7351de64a5c5 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Tue, 28 May 2024 19:21:59 -0400
Subject: [PATCH 385/950] bcachefs: Don't return -EROFS from mount on
 inconsistency error

We were accidentally returning -EROFS during recovery on filesystem
inconsistency - since this is what the journal returns on emergency
shutdown.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/fs.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/fs/bcachefs/fs.c b/fs/bcachefs/fs.c
index 96040a95cf466..cd388f1702dc8 100644
--- a/fs/bcachefs/fs.c
+++ b/fs/bcachefs/fs.c
@@ -1939,8 +1939,7 @@ got_sb:
 
 	if (IS_ERR(sb)) {
 		ret = PTR_ERR(sb);
-		ret = bch2_err_class(ret);
-		return ERR_PTR(ret);
+		goto err;
 	}
 
 	c = sb->s_fs_info;
@@ -2016,6 +2015,15 @@ out:
 err_put_super:
 	__bch2_fs_stop(c);
 	deactivate_locked_super(sb);
+err:
+	/*
+	 * On an inconsistency error in recovery we might see an -EROFS derived
+	 * errorcode (from the journal), but we don't want to return that to
+	 * userspace as that causes util-linux to retry the mount RO - which is
+	 * confusing:
+	 */
+	if (bch2_err_matches(ret, EROFS) && ret != -EROFS)
+		ret = -EIO;
 	return ERR_PTR(bch2_err_class(ret));
 }
 
-- 
GitLab


From eb4e7726279a344c82e3c23be396bcfd0a4d5669 Mon Sep 17 00:00:00 2001
From: Mykyta Yatsenko <yatsenko@meta.com>
Date: Fri, 24 May 2024 14:18:40 +0100
Subject: [PATCH 386/950] libbpf: Configure log verbosity with env variable

Configure logging verbosity by setting LIBBPF_LOG_LEVEL environment
variable, which is applied only to default logger. Once user set their
custom logging callback, it is up to them to handle filtering.

Signed-off-by: Mykyta Yatsenko <yatsenko@meta.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20240524131840.114289-1-yatsenko@meta.com
---
 Documentation/bpf/libbpf/libbpf_overview.rst |  8 +++++++
 tools/lib/bpf/libbpf.c                       | 25 +++++++++++++++++++-
 tools/lib/bpf/libbpf.h                       |  5 +++-
 3 files changed, 36 insertions(+), 2 deletions(-)

diff --git a/Documentation/bpf/libbpf/libbpf_overview.rst b/Documentation/bpf/libbpf/libbpf_overview.rst
index f36a2d4ffea2b..f4d22f0c62b0e 100644
--- a/Documentation/bpf/libbpf/libbpf_overview.rst
+++ b/Documentation/bpf/libbpf/libbpf_overview.rst
@@ -219,6 +219,14 @@ compilation and skeleton generation. Using Libbpf-rs will make building user
 space part of the BPF application easier. Note that the BPF program themselves
 must still be written in plain C.
 
+libbpf logging
+==============
+
+By default, libbpf logs informational and warning messages to stderr. The
+verbosity of these messages can be controlled by setting the environment
+variable LIBBPF_LOG_LEVEL to either warn, info, or debug. A custom log
+callback can be set using ``libbpf_set_print()``.
+
 Additional Documentation
 ========================
 
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 5401f2df463d2..d1627a2ca30bb 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -229,7 +229,30 @@ static const char * const prog_type_name[] = {
 static int __base_pr(enum libbpf_print_level level, const char *format,
 		     va_list args)
 {
-	if (level == LIBBPF_DEBUG)
+	const char *env_var = "LIBBPF_LOG_LEVEL";
+	static enum libbpf_print_level min_level = LIBBPF_INFO;
+	static bool initialized;
+
+	if (!initialized) {
+		char *verbosity;
+
+		initialized = true;
+		verbosity = getenv(env_var);
+		if (verbosity) {
+			if (strcasecmp(verbosity, "warn") == 0)
+				min_level = LIBBPF_WARN;
+			else if (strcasecmp(verbosity, "debug") == 0)
+				min_level = LIBBPF_DEBUG;
+			else if (strcasecmp(verbosity, "info") == 0)
+				min_level = LIBBPF_INFO;
+			else
+				fprintf(stderr, "libbpf: unrecognized '%s' envvar value: '%s', should be one of 'warn', 'debug', or 'info'.\n",
+					env_var, verbosity);
+		}
+	}
+
+	/* if too verbose, skip logging  */
+	if (level > min_level)
 		return 0;
 
 	return vfprintf(stderr, format, args);
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index c3f77d9260fea..26e4e35528c53 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -98,7 +98,10 @@ typedef int (*libbpf_print_fn_t)(enum libbpf_print_level level,
 
 /**
  * @brief **libbpf_set_print()** sets user-provided log callback function to
- * be used for libbpf warnings and informational messages.
+ * be used for libbpf warnings and informational messages. If the user callback
+ * is not set, messages are logged to stderr by default. The verbosity of these
+ * messages can be controlled by setting the environment variable
+ * LIBBPF_LOG_LEVEL to either warn, info, or debug.
  * @param fn The log print function. If NULL, libbpf won't print anything.
  * @return Pointer to old print function.
  *
-- 
GitLab


From ed31adf6874db172e3212ac1ebaf701ed6190650 Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Sat, 25 May 2024 20:08:15 +0800
Subject: [PATCH 387/950] selftests/bpf: Drop struct post_socket_opts

It's not possible to have one generic/common "struct post_socket_opts"
for all tests. It's better to have the individual test define its own
callback opts struct.

So this patch drops struct post_socket_opts, and changes the second
parameter of post_socket_cb as "void *" type.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Link: https://lore.kernel.org/r/f8bda41c7cb9cb6979b2779f89fb3a684234304f.1716638248.git.tanggeliang@kylinos.cn
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/testing/selftests/bpf/network_helpers.c               | 2 +-
 tools/testing/selftests/bpf/network_helpers.h               | 4 +---
 tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c    | 2 +-
 tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c | 4 ++--
 4 files changed, 5 insertions(+), 7 deletions(-)

diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c
index 35250e6cde7fb..4d776b78929cb 100644
--- a/tools/testing/selftests/bpf/network_helpers.c
+++ b/tools/testing/selftests/bpf/network_helpers.c
@@ -133,7 +133,7 @@ int start_server(int family, int type, const char *addr_str, __u16 port,
 	return __start_server(type, (struct sockaddr *)&addr, addrlen, &opts);
 }
 
-static int reuseport_cb(int fd, const struct post_socket_opts *opts)
+static int reuseport_cb(int fd, void *opts)
 {
 	int on = 1;
 
diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h
index 883c7ea9d8d54..40011e0f584b7 100644
--- a/tools/testing/selftests/bpf/network_helpers.h
+++ b/tools/testing/selftests/bpf/network_helpers.h
@@ -21,8 +21,6 @@ typedef __u16 __sum16;
 #define VIP_NUM 5
 #define MAGIC_BYTES 123
 
-struct post_socket_opts {};
-
 struct network_helper_opts {
 	const char *cc;
 	int timeout_ms;
@@ -30,7 +28,7 @@ struct network_helper_opts {
 	bool noconnect;
 	int type;
 	int proto;
-	int (*post_socket_cb)(int fd, const struct post_socket_opts *opts);
+	int (*post_socket_cb)(int fd, void *opts);
 };
 
 /* ipv4 test vector */
diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c b/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c
index 1d3a20f01b607..7cd8be2780cac 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c
@@ -70,7 +70,7 @@ static void *server_thread(void *arg)
 	return (void *)(long)err;
 }
 
-static int custom_cb(int fd, const struct post_socket_opts *opts)
+static int custom_cb(int fd, void *opts)
 {
 	char buf;
 	int err;
diff --git a/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c b/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c
index 7b5fc98838cd3..aebc58c24dc57 100644
--- a/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c
+++ b/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c
@@ -139,14 +139,14 @@ out:
 	return ret;
 }
 
-static int v6only_true(int fd, const struct post_socket_opts *opts)
+static int v6only_true(int fd, void *opts)
 {
 	int mode = true;
 
 	return setsockopt(fd, IPPROTO_IPV6, IPV6_V6ONLY, &mode, sizeof(mode));
 }
 
-static int v6only_false(int fd, const struct post_socket_opts *opts)
+static int v6only_false(int fd, void *opts)
 {
 	int mode = false;
 
-- 
GitLab


From 6f802cb8988e8e41f2fdb74ac949d3a0ef9a9594 Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Sat, 25 May 2024 20:08:16 +0800
Subject: [PATCH 388/950] selftests/bpf: Add start_server_str helper

It's a tech debt that start_server() does not take the "opts" argument.
It's pretty handy to have start_server() as a helper that takes string
address.

So this patch creates a new helper start_server_str(). Then start_server()
can be a wrapper of it.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Link: https://lore.kernel.org/r/606e6cfd7e1aff8bc51ede49862eed0802e52170.1716638248.git.tanggeliang@kylinos.cn
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/testing/selftests/bpf/network_helpers.c | 22 ++++++++++++++-----
 tools/testing/selftests/bpf/network_helpers.h |  2 ++
 2 files changed, 18 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c
index 4d776b78929cb..0e8266f439e48 100644
--- a/tools/testing/selftests/bpf/network_helpers.c
+++ b/tools/testing/selftests/bpf/network_helpers.c
@@ -118,19 +118,29 @@ error_close:
 	return -1;
 }
 
-int start_server(int family, int type, const char *addr_str, __u16 port,
-		 int timeout_ms)
+int start_server_str(int family, int type, const char *addr_str, __u16 port,
+		     const struct network_helper_opts *opts)
 {
-	struct network_helper_opts opts = {
-		.timeout_ms	= timeout_ms,
-	};
 	struct sockaddr_storage addr;
 	socklen_t addrlen;
 
+	if (!opts)
+		opts = &default_opts;
+
 	if (make_sockaddr(family, addr_str, port, &addr, &addrlen))
 		return -1;
 
-	return __start_server(type, (struct sockaddr *)&addr, addrlen, &opts);
+	return __start_server(type, (struct sockaddr *)&addr, addrlen, opts);
+}
+
+int start_server(int family, int type, const char *addr_str, __u16 port,
+		 int timeout_ms)
+{
+	struct network_helper_opts opts = {
+		.timeout_ms	= timeout_ms,
+	};
+
+	return start_server_str(family, type, addr_str, port, &opts);
 }
 
 static int reuseport_cb(int fd, void *opts)
diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h
index 40011e0f584b7..4e3e6afe7d3a8 100644
--- a/tools/testing/selftests/bpf/network_helpers.h
+++ b/tools/testing/selftests/bpf/network_helpers.h
@@ -48,6 +48,8 @@ struct ipv6_packet {
 extern struct ipv6_packet pkt_v6;
 
 int settimeo(int fd, int timeout_ms);
+int start_server_str(int family, int type, const char *addr_str, __u16 port,
+		     const struct network_helper_opts *opts);
 int start_server(int family, int type, const char *addr, __u16 port,
 		 int timeout_ms);
 int *start_reuseport_server(int family, int type, const char *addr_str,
-- 
GitLab


From e078255abd53ac44c9133fd98d51645dbd196123 Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Sat, 25 May 2024 20:08:17 +0800
Subject: [PATCH 389/950] selftests/bpf: Use post_socket_cb in
 connect_to_fd_opts

Since the post_socket_cb() callback is added in struct network_helper_opts,
it's make sense to use it not only in __start_server(), but also in
connect_to_fd_opts(). Then it can be used to set TCP_CONGESTION sockopt.

Add a "void *" type member cb_opts into struct network_helper_opts, and add
a new struct named cb_opts in prog_tests/bpf_tcp_ca.c, then cc can be moved
into struct cb_opts from network_helper_opts. Define a new callback cc_cb()
to set TCP_CONGESTION sockopt, and set it to post_socket_cb pointer of opts.
Define a new cb_opts cubic, set it to cb_opts of opts. Pass this opts to
connect_to_fd_opts() in test_dctcp_fallback().

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Link: https://lore.kernel.org/r/b512bb8d8f6854c9ea5c409b69d1bf37c6f272c6.1716638248.git.tanggeliang@kylinos.cn
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/testing/selftests/bpf/network_helpers.c   |  5 ++---
 tools/testing/selftests/bpf/network_helpers.h   |  2 +-
 .../selftests/bpf/prog_tests/bpf_tcp_ca.c       | 17 ++++++++++++++++-
 3 files changed, 19 insertions(+), 5 deletions(-)

diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c
index 0e8266f439e48..8502917b6c7bb 100644
--- a/tools/testing/selftests/bpf/network_helpers.c
+++ b/tools/testing/selftests/bpf/network_helpers.c
@@ -348,9 +348,8 @@ int connect_to_fd_opts(int server_fd, const struct network_helper_opts *opts)
 	if (settimeo(fd, opts->timeout_ms))
 		goto error_close;
 
-	if (opts->cc && opts->cc[0] &&
-	    setsockopt(fd, SOL_TCP, TCP_CONGESTION, opts->cc,
-		       strlen(opts->cc) + 1))
+	if (opts->post_socket_cb &&
+	    opts->post_socket_cb(fd, opts->cb_opts))
 		goto error_close;
 
 	if (!opts->noconnect)
diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h
index 4e3e6afe7d3a8..11eea8e2e4f1e 100644
--- a/tools/testing/selftests/bpf/network_helpers.h
+++ b/tools/testing/selftests/bpf/network_helpers.h
@@ -22,13 +22,13 @@ typedef __u16 __sum16;
 #define MAGIC_BYTES 123
 
 struct network_helper_opts {
-	const char *cc;
 	int timeout_ms;
 	bool must_fail;
 	bool noconnect;
 	int type;
 	int proto;
 	int (*post_socket_cb)(int fd, void *opts);
+	void *cb_opts;
 };
 
 /* ipv4 test vector */
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
index 0aca025327948..6f034059888ab 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
@@ -23,6 +23,10 @@
 static const unsigned int total_bytes = 10 * 1024 * 1024;
 static int expected_stg = 0xeB9F;
 
+struct cb_opts {
+	const char *cc;
+};
+
 static int settcpca(int fd, const char *tcp_ca)
 {
 	int err;
@@ -81,6 +85,13 @@ done:
 	close(fd);
 }
 
+static int cc_cb(int fd, void *opts)
+{
+	struct cb_opts *cb_opts = (struct cb_opts *)opts;
+
+	return settcpca(fd, cb_opts->cc);
+}
+
 static void test_cubic(void)
 {
 	struct bpf_cubic *cubic_skel;
@@ -172,10 +183,13 @@ static void test_dctcp_fallback(void)
 {
 	int err, lfd = -1, cli_fd = -1, srv_fd = -1;
 	struct network_helper_opts opts = {
-		.cc = "cubic",
+		.post_socket_cb	= cc_cb,
 	};
 	struct bpf_dctcp *dctcp_skel;
 	struct bpf_link *link = NULL;
+	struct cb_opts cubic = {
+		.cc = "cubic",
+	};
 	char srv_cc[16];
 	socklen_t cc_len = sizeof(srv_cc);
 
@@ -195,6 +209,7 @@ static void test_dctcp_fallback(void)
 	    !ASSERT_OK(settcpca(lfd, "bpf_dctcp"), "lfd=>bpf_dctcp"))
 		goto done;
 
+	opts.cb_opts = &cubic;
 	cli_fd = connect_to_fd_opts(lfd, &opts);
 	if (!ASSERT_GE(cli_fd, 0, "cli_fd"))
 		goto done;
-- 
GitLab


From 79b330c57debe6b15f441e999bb62042afd5b08e Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Sat, 25 May 2024 20:08:18 +0800
Subject: [PATCH 390/950] selftests/bpf: Use post_socket_cb in start_server_str

This patch uses start_server_str() helper in test_dctcp_fallback() in
bpf_tcp_ca.c, instead of using start_server() and settcpca(). For
support opts in start_server_str() helper, opts->cb_opts needs to be
passed to post_socket_cb() in __start_server().

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Link: https://lore.kernel.org/r/414c749321fa150435f7fe8e12c80fec8b447c78.1716638248.git.tanggeliang@kylinos.cn
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/testing/selftests/bpf/network_helpers.c       | 3 ++-
 tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c | 9 ++++++---
 2 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c
index 8502917b6c7bb..e20caef06aae9 100644
--- a/tools/testing/selftests/bpf/network_helpers.c
+++ b/tools/testing/selftests/bpf/network_helpers.c
@@ -94,7 +94,8 @@ static int __start_server(int type, const struct sockaddr *addr, socklen_t addrl
 	if (settimeo(fd, opts->timeout_ms))
 		goto error_close;
 
-	if (opts->post_socket_cb && opts->post_socket_cb(fd, NULL)) {
+	if (opts->post_socket_cb &&
+	    opts->post_socket_cb(fd, opts->cb_opts)) {
 		log_err("Failed to call post_socket_cb");
 		goto error_close;
 	}
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
index 6f034059888ab..7a523c7a0c6a8 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
@@ -187,6 +187,9 @@ static void test_dctcp_fallback(void)
 	};
 	struct bpf_dctcp *dctcp_skel;
 	struct bpf_link *link = NULL;
+	struct cb_opts dctcp = {
+		.cc = "bpf_dctcp",
+	};
 	struct cb_opts cubic = {
 		.cc = "cubic",
 	};
@@ -204,9 +207,9 @@ static void test_dctcp_fallback(void)
 	if (!ASSERT_OK_PTR(link, "dctcp link"))
 		goto done;
 
-	lfd = start_server(AF_INET6, SOCK_STREAM, "::1", 0, 0);
-	if (!ASSERT_GE(lfd, 0, "lfd") ||
-	    !ASSERT_OK(settcpca(lfd, "bpf_dctcp"), "lfd=>bpf_dctcp"))
+	opts.cb_opts = &dctcp;
+	lfd = start_server_str(AF_INET6, SOCK_STREAM, "::1", 0, &opts);
+	if (!ASSERT_GE(lfd, 0, "lfd"))
 		goto done;
 
 	opts.cb_opts = &cubic;
-- 
GitLab


From ed61271af5230cef9b9329bb1eacc1b1a9800d07 Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Sat, 25 May 2024 20:08:19 +0800
Subject: [PATCH 391/950] selftests/bpf: Use start_server_str in do_test in
 bpf_tcp_ca

This patch uses new helper start_server_str() in do_test() in bpf_tcp_ca.c
to accept a struct network_helper_opts argument instead of using
start_server() and settcpca(). Then change the type of the first paramenter
of do_test() into a struct network_helper_opts one.

Define its own cb_opts and opts for each test, set its own cc name into
cb_opts.cc, and cc_cb() into post_socket_cb callback, then pass it to
do_test().

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Link: https://lore.kernel.org/r/6e1b6555e3284e77c8aa60668c61a66c5f99aa37.1716638248.git.tanggeliang@kylinos.cn
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 .../selftests/bpf/prog_tests/bpf_tcp_ca.c     | 66 +++++++++++++++----
 1 file changed, 55 insertions(+), 11 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
index 7a523c7a0c6a8..ebc7d46168801 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
@@ -38,12 +38,14 @@ static int settcpca(int fd, const char *tcp_ca)
 	return 0;
 }
 
-static void do_test(const char *tcp_ca, const struct bpf_map *sk_stg_map)
+static void do_test(const struct network_helper_opts *opts,
+		    const struct bpf_map *sk_stg_map)
 {
+	struct cb_opts *cb_opts = (struct cb_opts *)opts->cb_opts;
 	int lfd = -1, fd = -1;
 	int err;
 
-	lfd = start_server(AF_INET6, SOCK_STREAM, NULL, 0, 0);
+	lfd = start_server_str(AF_INET6, SOCK_STREAM, NULL, 0, opts);
 	if (!ASSERT_NEQ(lfd, -1, "socket"))
 		return;
 
@@ -53,7 +55,7 @@ static void do_test(const char *tcp_ca, const struct bpf_map *sk_stg_map)
 		return;
 	}
 
-	if (settcpca(lfd, tcp_ca) || settcpca(fd, tcp_ca))
+	if (settcpca(fd, cb_opts->cc))
 		goto done;
 
 	if (sk_stg_map) {
@@ -94,6 +96,13 @@ static int cc_cb(int fd, void *opts)
 
 static void test_cubic(void)
 {
+	struct cb_opts cb_opts = {
+		.cc = "bpf_cubic",
+	};
+	struct network_helper_opts opts = {
+		.post_socket_cb	= cc_cb,
+		.cb_opts	= &cb_opts,
+	};
 	struct bpf_cubic *cubic_skel;
 	struct bpf_link *link;
 
@@ -107,7 +116,7 @@ static void test_cubic(void)
 		return;
 	}
 
-	do_test("bpf_cubic", NULL);
+	do_test(&opts, NULL);
 
 	ASSERT_EQ(cubic_skel->bss->bpf_cubic_acked_called, 1, "pkts_acked called");
 
@@ -117,6 +126,13 @@ static void test_cubic(void)
 
 static void test_dctcp(void)
 {
+	struct cb_opts cb_opts = {
+		.cc = "bpf_dctcp",
+	};
+	struct network_helper_opts opts = {
+		.post_socket_cb	= cc_cb,
+		.cb_opts	= &cb_opts,
+	};
 	struct bpf_dctcp *dctcp_skel;
 	struct bpf_link *link;
 
@@ -130,7 +146,7 @@ static void test_dctcp(void)
 		return;
 	}
 
-	do_test("bpf_dctcp", dctcp_skel->maps.sk_stg_map);
+	do_test(&opts, dctcp_skel->maps.sk_stg_map);
 	ASSERT_EQ(dctcp_skel->bss->stg_result, expected_stg, "stg_result");
 
 	bpf_link__destroy(link);
@@ -315,6 +331,13 @@ static void test_unsupp_cong_op(void)
 
 static void test_update_ca(void)
 {
+	struct cb_opts cb_opts = {
+		.cc = "tcp_ca_update",
+	};
+	struct network_helper_opts opts = {
+		.post_socket_cb	= cc_cb,
+		.cb_opts	= &cb_opts,
+	};
 	struct tcp_ca_update *skel;
 	struct bpf_link *link;
 	int saved_ca1_cnt;
@@ -327,14 +350,14 @@ static void test_update_ca(void)
 	link = bpf_map__attach_struct_ops(skel->maps.ca_update_1);
 	ASSERT_OK_PTR(link, "attach_struct_ops");
 
-	do_test("tcp_ca_update", NULL);
+	do_test(&opts, NULL);
 	saved_ca1_cnt = skel->bss->ca1_cnt;
 	ASSERT_GT(saved_ca1_cnt, 0, "ca1_ca1_cnt");
 
 	err = bpf_link__update_map(link, skel->maps.ca_update_2);
 	ASSERT_OK(err, "update_map");
 
-	do_test("tcp_ca_update", NULL);
+	do_test(&opts, NULL);
 	ASSERT_EQ(skel->bss->ca1_cnt, saved_ca1_cnt, "ca2_ca1_cnt");
 	ASSERT_GT(skel->bss->ca2_cnt, 0, "ca2_ca2_cnt");
 
@@ -344,6 +367,13 @@ static void test_update_ca(void)
 
 static void test_update_wrong(void)
 {
+	struct cb_opts cb_opts = {
+		.cc = "tcp_ca_update",
+	};
+	struct network_helper_opts opts = {
+		.post_socket_cb	= cc_cb,
+		.cb_opts	= &cb_opts,
+	};
 	struct tcp_ca_update *skel;
 	struct bpf_link *link;
 	int saved_ca1_cnt;
@@ -356,14 +386,14 @@ static void test_update_wrong(void)
 	link = bpf_map__attach_struct_ops(skel->maps.ca_update_1);
 	ASSERT_OK_PTR(link, "attach_struct_ops");
 
-	do_test("tcp_ca_update", NULL);
+	do_test(&opts, NULL);
 	saved_ca1_cnt = skel->bss->ca1_cnt;
 	ASSERT_GT(saved_ca1_cnt, 0, "ca1_ca1_cnt");
 
 	err = bpf_link__update_map(link, skel->maps.ca_wrong);
 	ASSERT_ERR(err, "update_map");
 
-	do_test("tcp_ca_update", NULL);
+	do_test(&opts, NULL);
 	ASSERT_GT(skel->bss->ca1_cnt, saved_ca1_cnt, "ca2_ca1_cnt");
 
 	bpf_link__destroy(link);
@@ -372,6 +402,13 @@ static void test_update_wrong(void)
 
 static void test_mixed_links(void)
 {
+	struct cb_opts cb_opts = {
+		.cc = "tcp_ca_update",
+	};
+	struct network_helper_opts opts = {
+		.post_socket_cb	= cc_cb,
+		.cb_opts	= &cb_opts,
+	};
 	struct tcp_ca_update *skel;
 	struct bpf_link *link, *link_nl;
 	int err;
@@ -386,7 +423,7 @@ static void test_mixed_links(void)
 	link = bpf_map__attach_struct_ops(skel->maps.ca_update_1);
 	ASSERT_OK_PTR(link, "attach_struct_ops");
 
-	do_test("tcp_ca_update", NULL);
+	do_test(&opts, NULL);
 	ASSERT_GT(skel->bss->ca1_cnt, 0, "ca1_ca1_cnt");
 
 	err = bpf_link__update_map(link, skel->maps.ca_no_link);
@@ -473,6 +510,13 @@ static void test_tcp_ca_kfunc(void)
 
 static void test_cc_cubic(void)
 {
+	struct cb_opts cb_opts = {
+		.cc = "bpf_cc_cubic",
+	};
+	struct network_helper_opts opts = {
+		.post_socket_cb	= cc_cb,
+		.cb_opts	= &cb_opts,
+	};
 	struct bpf_cc_cubic *cc_cubic_skel;
 	struct bpf_link *link;
 
@@ -486,7 +530,7 @@ static void test_cc_cubic(void)
 		return;
 	}
 
-	do_test("bpf_cc_cubic", NULL);
+	do_test(&opts, NULL);
 
 	bpf_link__destroy(link);
 	bpf_cc_cubic__destroy(cc_cubic_skel);
-- 
GitLab


From e634134180885574d1fe7aa162777ba41e7fcd5b Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Mon, 27 May 2024 18:39:54 +0300
Subject: [PATCH 392/950] net/sched: taprio: make q->picos_per_byte available
 to fill_sched_entry()

In commit b5b73b26b3ca ("taprio: Fix allowing too small intervals"), a
comparison of user input against length_to_duration(q, ETH_ZLEN) was
introduced, to avoid RCU stalls due to frequent hrtimers.

The implementation of length_to_duration() depends on q->picos_per_byte
being set for the link speed. The blamed commit in the Fixes: tag has
moved this too late, so the checks introduced above are ineffective.
The q->picos_per_byte is zero at parse_taprio_schedule() ->
parse_sched_list() -> parse_sched_entry() -> fill_sched_entry() time.

Move the taprio_set_picos_per_byte() call as one of the first things in
taprio_change(), before the bulk of the netlink attribute parsing is
done. That's because it is needed there.

Add a selftest to make sure the issue doesn't get reintroduced.

Fixes: 09dbdf28f9f9 ("net/sched: taprio: fix calculation of maximum gate durations")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20240527153955.553333-1-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/sch_taprio.c                        |  4 +++-
 .../tc-testing/tc-tests/qdiscs/taprio.json    | 22 +++++++++++++++++++
 2 files changed, 25 insertions(+), 1 deletion(-)

diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 1ab17e8a72605..1189150553608 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -1848,6 +1848,9 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt,
 	}
 	q->flags = taprio_flags;
 
+	/* Needed for length_to_duration() during netlink attribute parsing */
+	taprio_set_picos_per_byte(dev, q);
+
 	err = taprio_parse_mqprio_opt(dev, mqprio, extack, q->flags);
 	if (err < 0)
 		return err;
@@ -1907,7 +1910,6 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt,
 	if (err < 0)
 		goto free_sched;
 
-	taprio_set_picos_per_byte(dev, q);
 	taprio_update_queue_max_sdu(q, new_admin, stab);
 
 	if (FULL_OFFLOAD_IS_ENABLED(q->flags))
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json
index 12da0a939e3e5..8f12f00a4f572 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json
@@ -132,6 +132,28 @@
             "echo \"1\" > /sys/bus/netdevsim/del_device"
         ]
     },
+    {
+        "id": "6f62",
+        "name": "Add taprio Qdisc with too short interval",
+        "category": [
+            "qdisc",
+            "taprio"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "echo \"1 1 8\" > /sys/bus/netdevsim/new_device"
+        ],
+        "cmdUnderTest": "$TC qdisc add dev $ETH root handle 1: taprio num_tc 2 queues 1@0 1@1 sched-entry S 01 300 sched-entry S 02 1700 clockid CLOCK_TAI",
+        "expExitCode": "2",
+        "verifyCmd": "$TC qdisc show dev $ETH",
+        "matchPattern": "qdisc taprio 1: root refcnt",
+        "matchCount": "0",
+        "teardown": [
+            "echo \"1\" > /sys/bus/netdevsim/del_device"
+        ]
+    },
     {
         "id": "3e1e",
         "name": "Add taprio Qdisc with an invalid cycle-time",
-- 
GitLab


From fb66df20a7201e60f2b13d7f95d031b31a8831d3 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Mon, 27 May 2024 18:39:55 +0300
Subject: [PATCH 393/950] net/sched: taprio: extend minimum interval
 restriction to entire cycle too

It is possible for syzbot to side-step the restriction imposed by the
blamed commit in the Fixes: tag, because the taprio UAPI permits a
cycle-time different from (and potentially shorter than) the sum of
entry intervals.

We need one more restriction, which is that the cycle time itself must
be larger than N * ETH_ZLEN bit times, where N is the number of schedule
entries. This restriction needs to apply regardless of whether the cycle
time came from the user or was the implicit, auto-calculated value, so
we move the existing "cycle == 0" check outside the "if "(!new->cycle_time)"
branch. This way covers both conditions and scenarios.

Add a selftest which illustrates the issue triggered by syzbot.

Fixes: b5b73b26b3ca ("taprio: Fix allowing too small intervals")
Reported-by: syzbot+a7d2b1d5d1af83035567@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/0000000000007d66bc06196e7c66@google.com/
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://lore.kernel.org/r/20240527153955.553333-2-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/sch_taprio.c                        | 10 ++++-----
 .../tc-testing/tc-tests/qdiscs/taprio.json    | 22 +++++++++++++++++++
 2 files changed, 27 insertions(+), 5 deletions(-)

diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 1189150553608..937a0c513c174 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -1151,11 +1151,6 @@ static int parse_taprio_schedule(struct taprio_sched *q, struct nlattr **tb,
 		list_for_each_entry(entry, &new->entries, list)
 			cycle = ktime_add_ns(cycle, entry->interval);
 
-		if (!cycle) {
-			NL_SET_ERR_MSG(extack, "'cycle_time' can never be 0");
-			return -EINVAL;
-		}
-
 		if (cycle < 0 || cycle > INT_MAX) {
 			NL_SET_ERR_MSG(extack, "'cycle_time' is too big");
 			return -EINVAL;
@@ -1164,6 +1159,11 @@ static int parse_taprio_schedule(struct taprio_sched *q, struct nlattr **tb,
 		new->cycle_time = cycle;
 	}
 
+	if (new->cycle_time < new->num_entries * length_to_duration(q, ETH_ZLEN)) {
+		NL_SET_ERR_MSG(extack, "'cycle_time' is too small");
+		return -EINVAL;
+	}
+
 	taprio_calculate_gate_durations(q, new);
 
 	return 0;
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json
index 8f12f00a4f572..557fb074acf0c 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json
@@ -154,6 +154,28 @@
             "echo \"1\" > /sys/bus/netdevsim/del_device"
         ]
     },
+    {
+        "id": "831f",
+        "name": "Add taprio Qdisc with too short cycle-time",
+        "category": [
+            "qdisc",
+            "taprio"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "echo \"1 1 8\" > /sys/bus/netdevsim/new_device"
+        ],
+        "cmdUnderTest": "$TC qdisc add dev $ETH root handle 1: taprio num_tc 2 queues 1@0 1@1 sched-entry S 01 200000 sched-entry S 02 200000 cycle-time 100 clockid CLOCK_TAI",
+        "expExitCode": "2",
+        "verifyCmd": "$TC qdisc show dev $ETH",
+        "matchPattern": "qdisc taprio 1: root refcnt",
+        "matchCount": "0",
+        "teardown": [
+            "echo \"1\" > /sys/bus/netdevsim/del_device"
+        ]
+    },
     {
         "id": "3e1e",
         "name": "Add taprio Qdisc with an invalid cycle-time",
-- 
GitLab


From 6994520a332887f1688464f250c9ec8002a89a8e Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 27 May 2024 21:16:56 +0200
Subject: [PATCH 394/950] r8169: disable interrupt source RxOverflow

Vendor driver calls this bit RxDescUnavail. All we do in the interrupt
handler in this case is scheduling NAPI. If we should be out of
RX descriptors, then NAPI is scheduled anyway. Therefore remove this
interrupt source. Tested on RTL8168h.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Sunil Goutham <sgoutham@marvell.com>
Link: https://lore.kernel.org/r/9b2054b2-0548-4f48-bf91-b646572093b4@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/realtek/r8169_main.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 7b9e04884575e..5c4296daf8f72 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -5086,12 +5086,10 @@ static void rtl_set_irq_mask(struct rtl8169_private *tp)
 	tp->irq_mask = RxOK | RxErr | TxOK | TxErr | LinkChg;
 
 	if (tp->mac_version <= RTL_GIGA_MAC_VER_06)
-		tp->irq_mask |= SYSErr | RxOverflow | RxFIFOOver;
+		tp->irq_mask |= SYSErr | RxFIFOOver;
 	else if (tp->mac_version == RTL_GIGA_MAC_VER_11)
 		/* special workaround needed */
 		tp->irq_mask |= RxFIFOOver;
-	else
-		tp->irq_mask |= RxOverflow;
 }
 
 static int rtl_alloc_irq(struct rtl8169_private *tp)
-- 
GitLab


From 982300c115d229565d7af8e8b38aa1ee7bb1f5bd Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 27 May 2024 21:20:16 +0200
Subject: [PATCH 395/950] r8169: remove detection of chip version 11 (early
 RTL8168b)

This early RTL8168b version was the first PCIe chip version, and it's
quite quirky. Last sign of life is from more than 15 yrs ago.
Let's remove detection of this chip version, we'll see whether anybody
complains. If not, support for this chip version can be removed a few
kernel versions later.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Link: https://lore.kernel.org/r/875cdcf4-843c-420a-ad5d-417447b68572@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/realtek/r8169_main.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 5c4296daf8f72..9246ea2118ff2 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -2274,7 +2274,9 @@ static enum mac_version rtl8169_get_mac_version(u16 xid, bool gmii)
 
 		/* 8168B family. */
 		{ 0x7c8, 0x380,	RTL_GIGA_MAC_VER_17 },
-		{ 0x7c8, 0x300,	RTL_GIGA_MAC_VER_11 },
+		/* This one is very old and rare, let's see if anybody complains.
+		 * { 0x7c8, 0x300,	RTL_GIGA_MAC_VER_11 },
+		 */
 
 		/* 8101 family. */
 		{ 0x7c8, 0x448,	RTL_GIGA_MAC_VER_39 },
-- 
GitLab


From 874aa96d78c791565781bb38570971f614d800ff Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <linux@weissschuh.net>
Date: Mon, 27 May 2024 19:04:19 +0200
Subject: [PATCH 396/950] net/neighbour: constify ctl_table arguments of
 utility function
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The sysctl core is preparing to only expose instances of
struct ctl_table as "const".
This will also affect the ctl_table argument of sysctl handlers.

As the function prototype of all sysctl handlers throughout the tree
needs to stay consistent that change will be done in one commit.

To reduce the size of that final commit, switch utility functions which
are not bound by "typedef proc_handler" to "const struct ctl_table".

No functional change.

Signed-off-by: Thomas Weißschuh <linux@weissschuh.net>
Link: https://lore.kernel.org/r/20240527-sysctl-const-handler-net-v1-1-16523767d0b2@weissschuh.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/neighbour.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 45fd88405b6b8..277751375b0a5 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -3578,7 +3578,7 @@ static void neigh_copy_dflt_parms(struct net *net, struct neigh_parms *p,
 	rcu_read_unlock();
 }
 
-static void neigh_proc_update(struct ctl_table *ctl, int write)
+static void neigh_proc_update(const struct ctl_table *ctl, int write)
 {
 	struct net_device *dev = ctl->extra1;
 	struct neigh_parms *p = ctl->extra2;
-- 
GitLab


From 551814313f113206800b025d89d4af99b2db13a2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <linux@weissschuh.net>
Date: Mon, 27 May 2024 19:04:20 +0200
Subject: [PATCH 397/950] net/ipv4/sysctl: constify ctl_table arguments of
 utility functions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The sysctl core is preparing to only expose instances of
struct ctl_table as "const".
This will also affect the ctl_table argument of sysctl handlers.

As the function prototype of all sysctl handlers throughout the tree
needs to stay consistent that change will be done in one commit.

To reduce the size of that final commit, switch utility functions which
are not bound by "typedef proc_handler" to "const struct ctl_table".

No functional change.

Signed-off-by: Thomas Weißschuh <linux@weissschuh.net>
Link: https://lore.kernel.org/r/20240527-sysctl-const-handler-net-v1-2-16523767d0b2@weissschuh.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/sysctl_net_ipv4.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 162a0a3b6ba52..d7892f34a15be 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -130,7 +130,8 @@ static int ipv4_privileged_ports(struct ctl_table *table, int write,
 	return ret;
 }
 
-static void inet_get_ping_group_range_table(struct ctl_table *table, kgid_t *low, kgid_t *high)
+static void inet_get_ping_group_range_table(const struct ctl_table *table,
+					    kgid_t *low, kgid_t *high)
 {
 	kgid_t *data = table->data;
 	struct net *net =
@@ -145,7 +146,8 @@ static void inet_get_ping_group_range_table(struct ctl_table *table, kgid_t *low
 }
 
 /* Update system visible IP port range */
-static void set_ping_group_range(struct ctl_table *table, kgid_t low, kgid_t high)
+static void set_ping_group_range(const struct ctl_table *table,
+				 kgid_t low, kgid_t high)
 {
 	kgid_t *data = table->data;
 	struct net *net =
-- 
GitLab


From c55eb03765f413d43ee96e2c4eeac27fde8e63d8 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <linux@weissschuh.net>
Date: Mon, 27 May 2024 19:04:21 +0200
Subject: [PATCH 398/950] net/ipv6/addrconf: constify ctl_table arguments of
 utility functions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The sysctl core is preparing to only expose instances of
struct ctl_table as "const".
This will also affect the ctl_table argument of sysctl handlers.

As the function prototype of all sysctl handlers throughout the tree
needs to stay consistent that change will be done in one commit.

To reduce the size of that final commit, switch utility functions which
are not bound by "typedef proc_handler" to "const struct ctl_table".

No functional change.

Signed-off-by: Thomas Weißschuh <linux@weissschuh.net>
Link: https://lore.kernel.org/r/20240527-sysctl-const-handler-net-v1-3-16523767d0b2@weissschuh.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/addrconf.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 5c424a0e7232f..1e69756d53d9c 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -863,7 +863,7 @@ static void addrconf_forward_change(struct net *net, __s32 newf)
 	}
 }
 
-static int addrconf_fixup_forwarding(struct ctl_table *table, int *p, int newf)
+static int addrconf_fixup_forwarding(const struct ctl_table *table, int *p, int newf)
 {
 	struct net *net;
 	int old;
@@ -931,7 +931,7 @@ static void addrconf_linkdown_change(struct net *net, __s32 newf)
 	}
 }
 
-static int addrconf_fixup_linkdown(struct ctl_table *table, int *p, int newf)
+static int addrconf_fixup_linkdown(const struct ctl_table *table, int *p, int newf)
 {
 	struct net *net;
 	int old;
@@ -6378,7 +6378,7 @@ static void addrconf_disable_change(struct net *net, __s32 newf)
 	}
 }
 
-static int addrconf_disable_ipv6(struct ctl_table *table, int *p, int newf)
+static int addrconf_disable_ipv6(const struct ctl_table *table, int *p, int newf)
 {
 	struct net *net = (struct net *)table->extra2;
 	int old;
@@ -6669,7 +6669,7 @@ void addrconf_disable_policy_idev(struct inet6_dev *idev, int val)
 }
 
 static
-int addrconf_disable_policy(struct ctl_table *ctl, int *valp, int val)
+int addrconf_disable_policy(const struct ctl_table *ctl, int *valp, int val)
 {
 	struct net *net = (struct net *)ctl->extra2;
 	struct inet6_dev *idev;
-- 
GitLab


From 7a20cd1e71d87907dbba8887cd434a2195699c85 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <linux@weissschuh.net>
Date: Mon, 27 May 2024 19:04:22 +0200
Subject: [PATCH 399/950] net/ipv6/ndisc: constify ctl_table arguments of
 utility function
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The sysctl core is preparing to only expose instances of
struct ctl_table as "const".
This will also affect the ctl_table argument of sysctl handlers.

As the function prototype of all sysctl handlers throughout the tree
needs to stay consistent that change will be done in one commit.

To reduce the size of that final commit, switch utility functions which
are not bound by "typedef proc_handler" to "const struct ctl_table".

No functional change.

Signed-off-by: Thomas Weißschuh <linux@weissschuh.net>
Link: https://lore.kernel.org/r/20240527-sysctl-const-handler-net-v1-4-16523767d0b2@weissschuh.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/ndisc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index d914b23256ce6..254b192c57050 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1936,7 +1936,7 @@ static struct notifier_block ndisc_netdev_notifier = {
 };
 
 #ifdef CONFIG_SYSCTL
-static void ndisc_warn_deprecated_sysctl(struct ctl_table *ctl,
+static void ndisc_warn_deprecated_sysctl(const struct ctl_table *ctl,
 					 const char *func, const char *dev_name)
 {
 	static char warncomm[TASK_COMM_LEN];
-- 
GitLab


From 0a9f788fdde4af08547455fcdc21e21b822218f2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <linux@weissschuh.net>
Date: Mon, 27 May 2024 19:04:23 +0200
Subject: [PATCH 400/950] ipvs: constify ctl_table arguments of utility
 functions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The sysctl core is preparing to only expose instances of
struct ctl_table as "const".
This will also affect the ctl_table argument of sysctl handlers.

As the function prototype of all sysctl handlers throughout the tree
needs to stay consistent that change will be done in one commit.

To reduce the size of that final commit, switch utility functions which
are not bound by "typedef proc_handler" to "const struct ctl_table".

No functional change.

Signed-off-by: Thomas Weißschuh <linux@weissschuh.net>
Link: https://lore.kernel.org/r/20240527-sysctl-const-handler-net-v1-5-16523767d0b2@weissschuh.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/netfilter/ipvs/ip_vs_ctl.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index b6d0dcf3a5c34..78a1cc72dc38a 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -1924,7 +1924,8 @@ proc_do_sync_ports(struct ctl_table *table, int write,
 	return rc;
 }
 
-static int ipvs_proc_est_cpumask_set(struct ctl_table *table, void *buffer)
+static int ipvs_proc_est_cpumask_set(const struct ctl_table *table,
+				     void *buffer)
 {
 	struct netns_ipvs *ipvs = table->extra2;
 	cpumask_var_t *valp = table->data;
@@ -1962,8 +1963,8 @@ out:
 	return ret;
 }
 
-static int ipvs_proc_est_cpumask_get(struct ctl_table *table, void *buffer,
-				     size_t size)
+static int ipvs_proc_est_cpumask_get(const struct ctl_table *table,
+				     void *buffer, size_t size)
 {
 	struct netns_ipvs *ipvs = table->extra2;
 	cpumask_var_t *valp = table->data;
-- 
GitLab


From e57f2187ccc125f1f14f6d2c83da80831fc3ce9a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Adri=C3=A1n=20Larumbe?= <adrian.larumbe@collabora.com>
Date: Thu, 23 May 2024 12:32:17 +0100
Subject: [PATCH 401/950] drm/panfrost: Fix dma_resv deadlock at drm object pin
 time
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When Panfrost must pin an object that is being prepared a dma-buf
attachment for on behalf of another driver, the core drm gem object pinning
code already takes a lock on the object's dma reservation.

However, Panfrost GEM object's pinning callback would eventually try taking
the lock on the same dma reservation when delegating pinning of the object
onto the shmem subsystem, which led to a deadlock.

This can be shown by enabling CONFIG_DEBUG_WW_MUTEX_SLOWPATH, which throws
the following recursive locking situation:

weston/3440 is trying to acquire lock:
ffff000000e235a0 (reservation_ww_class_mutex){+.+.}-{3:3}, at: drm_gem_shmem_pin+0x34/0xb8 [drm_shmem_helper]
but task is already holding lock:
ffff000000e235a0 (reservation_ww_class_mutex){+.+.}-{3:3}, at: drm_gem_pin+0x2c/0x80 [drm]

Fix it by replacing drm_gem_shmem_pin with its locked version, as the lock
had already been taken by drm_gem_pin().

Cc: Thomas Zimmermann <tzimmermann@suse.de>
Cc: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Cc: Boris Brezillon <boris.brezillon@collabora.com>
Cc: Steven Price <steven.price@arm.com>
Fixes: a78027847226 ("drm/gem: Acquire reservation lock in drm_gem_{pin/unpin}()")
Signed-off-by: Adrián Larumbe <adrian.larumbe@collabora.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240523113236.432585-2-adrian.larumbe@collabora.com
---
 drivers/gpu/drm/panfrost/panfrost_gem.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/panfrost/panfrost_gem.c b/drivers/gpu/drm/panfrost/panfrost_gem.c
index d47b40b82b0bc..8e0ff3efede7e 100644
--- a/drivers/gpu/drm/panfrost/panfrost_gem.c
+++ b/drivers/gpu/drm/panfrost/panfrost_gem.c
@@ -192,7 +192,7 @@ static int panfrost_gem_pin(struct drm_gem_object *obj)
 	if (bo->is_heap)
 		return -EINVAL;
 
-	return drm_gem_shmem_pin(&bo->base);
+	return drm_gem_shmem_pin_locked(&bo->base);
 }
 
 static enum drm_gem_object_status panfrost_gem_status(struct drm_gem_object *obj)
-- 
GitLab


From 8c2f5dd0c362ec036f0217da1d413ce2b8361080 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Adri=C3=A1n=20Larumbe?= <adrian.larumbe@collabora.com>
Date: Thu, 23 May 2024 12:32:18 +0100
Subject: [PATCH 402/950] drm/lima: Fix dma_resv deadlock at drm object pin
 time
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit a78027847226 ("drm/gem: Acquire reservation lock in
drm_gem_{pin/unpin}()") moved locking the DRM object's dma reservation to
drm_gem_pin(), but Lima's pin callback kept calling drm_gem_shmem_pin,
which also tries to lock the same dma_resv, leading to a double lock
situation.

As was already done for Panfrost in the previous commit, fix it by
replacing drm_gem_shmem_pin() with its locked variant.

Cc: Thomas Zimmermann <tzimmermann@suse.de>
Cc: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Cc: Boris Brezillon <boris.brezillon@collabora.com>
Cc: Steven Price <steven.price@arm.com>
Fixes: a78027847226 ("drm/gem: Acquire reservation lock in drm_gem_{pin/unpin}()")
Signed-off-by: Adrián Larumbe <adrian.larumbe@collabora.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Tested-by: Val Packett <val@packett.cool>
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240523113236.432585-3-adrian.larumbe@collabora.com
---
 drivers/gpu/drm/lima/lima_gem.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/lima/lima_gem.c b/drivers/gpu/drm/lima/lima_gem.c
index 7ea244d876ca6..9bb997dbb4b90 100644
--- a/drivers/gpu/drm/lima/lima_gem.c
+++ b/drivers/gpu/drm/lima/lima_gem.c
@@ -185,7 +185,7 @@ static int lima_gem_pin(struct drm_gem_object *obj)
 	if (bo->heap_size)
 		return -EINVAL;
 
-	return drm_gem_shmem_pin(&bo->base);
+	return drm_gem_shmem_pin_locked(&bo->base);
 }
 
 static int lima_gem_vmap(struct drm_gem_object *obj, struct iosys_map *map)
-- 
GitLab


From 3b8407e81ed76c0d84d710c2a177a8fe24292702 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Adri=C3=A1n=20Larumbe?= <adrian.larumbe@collabora.com>
Date: Thu, 23 May 2024 12:32:19 +0100
Subject: [PATCH 403/950] drm/gem-shmem: Add import attachment warning to
 locked pin function
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit ec144244a43f ("drm/gem-shmem: Acquire reservation lock in GEM
pin/unpin callbacks") moved locking DRM object's dma reservation to
drm_gem_shmem_object_pin, and made drm_gem_shmem_pin_locked public, so
we need to make sure the not-imported check warning is also added to
the latter.

Cc: Thomas Zimmermann <tzimmermann@suse.de>
Cc: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Cc: Boris Brezillon <boris.brezillon@collabora.com>
Fixes: a78027847226 ("drm/gem: Acquire reservation lock in drm_gem_{pin/unpin}()")
Signed-off-by: Adrián Larumbe <adrian.larumbe@collabora.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240523113236.432585-4-adrian.larumbe@collabora.com
---
 drivers/gpu/drm/drm_gem_shmem_helper.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c
index 885a62c2e1be2..53c003983ad18 100644
--- a/drivers/gpu/drm/drm_gem_shmem_helper.c
+++ b/drivers/gpu/drm/drm_gem_shmem_helper.c
@@ -233,6 +233,8 @@ int drm_gem_shmem_pin_locked(struct drm_gem_shmem_object *shmem)
 
 	dma_resv_assert_held(shmem->base.resv);
 
+	drm_WARN_ON(shmem->base.dev, shmem->base.import_attach);
+
 	ret = drm_gem_shmem_get_pages(shmem);
 
 	return ret;
-- 
GitLab


From a607468b521cc99ca64f19947cb7a40f8c814730 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Sun, 19 May 2024 13:24:30 +0900
Subject: [PATCH 404/950] kconfig: remove unused expr_is_no()

This has not been used since commit e911503085ae ("Kconfig: Remove
bad inference rules expr_eliminate_dups2()").

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 scripts/kconfig/expr.h | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/scripts/kconfig/expr.h b/scripts/kconfig/expr.h
index d965e427753eb..fa50fc45622e3 100644
--- a/scripts/kconfig/expr.h
+++ b/scripts/kconfig/expr.h
@@ -302,11 +302,6 @@ static inline int expr_is_yes(struct expr *e)
 	return !e || (e->type == E_SYMBOL && e->left.sym == &symbol_yes);
 }
 
-static inline int expr_is_no(struct expr *e)
-{
-	return e && (e->type == E_SYMBOL && e->left.sym == &symbol_no);
-}
-
 #ifdef __cplusplus
 }
 #endif
-- 
GitLab


From aabdc960a283ba78086b0bf66ee74326f49e218e Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Sun, 19 May 2024 18:22:27 +0900
Subject: [PATCH 405/950] kconfig: fix comparison to constant symbols, 'm', 'n'

Currently, comparisons to 'm' or 'n' result in incorrect output.

[Test Code]

    config MODULES
            def_bool y
            modules

    config A
            def_tristate m

    config B
            def_bool A > n

CONFIG_B is unset, while CONFIG_B=y is expected.

The reason for the issue is because Kconfig compares the tristate values
as strings.

Currently, the .type fields in the constant symbol definitions,
symbol_{yes,mod,no} are unspecified, i.e., S_UNKNOWN.

When expr_calc_value() evaluates 'A > n', it checks the types of 'A' and
'n' to determine how to compare them.

The left-hand side, 'A', is a tristate symbol with a value of 'm', which
corresponds to a numeric value of 1. (Internally, 'y', 'm', and 'n' are
represented as 2, 1, and 0, respectively.)

The right-hand side, 'n', has an unknown type, so it is treated as the
string "n" during the comparison.

expr_calc_value() compares two values numerically only when both can
have numeric values. Otherwise, they are compared as strings.

    symbol    numeric value    ASCII code
    -------------------------------------
      y           2             0x79
      m           1             0x6d
      n           0             0x6e

'm' is greater than 'n' if compared numerically (since 1 is greater
than 0), but smaller than 'n' if compared as strings (since the ASCII
code 0x6d is smaller than 0x6e).

Specifying .type=S_TRISTATE for symbol_{yes,mod,no} fixes the above
test code.

Doing so, however, would cause a regression to the following test code.

[Test Code 2]

    config MODULES
            def_bool n
            modules

    config A
            def_tristate n

    config B
            def_bool A = m

You would get CONFIG_B=y, while CONFIG_B should not be set.

The reason is because sym_get_string_value() turns 'm' into 'n' when the
module feature is disabled. Consequently, expr_calc_value() evaluates
'A = n' instead of 'A = m'. This oddity has been hidden because the type
of 'm' was previously S_UNKNOWN instead of S_TRISTATE.

sym_get_string_value() should not tweak the string because the tristate
value has already been correctly calculated. There is no reason to
return the string "n" where its tristate value is mod.

Fixes: 31847b67bec0 ("kconfig: allow use of relations other than (in)equality")
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 scripts/kconfig/symbol.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/scripts/kconfig/symbol.c b/scripts/kconfig/symbol.c
index aa0e25ee5119e..0e439d3d48d11 100644
--- a/scripts/kconfig/symbol.c
+++ b/scripts/kconfig/symbol.c
@@ -14,6 +14,7 @@
 
 struct symbol symbol_yes = {
 	.name = "y",
+	.type = S_TRISTATE,
 	.curr = { "y", yes },
 	.menus = LIST_HEAD_INIT(symbol_yes.menus),
 	.flags = SYMBOL_CONST|SYMBOL_VALID,
@@ -21,6 +22,7 @@ struct symbol symbol_yes = {
 
 struct symbol symbol_mod = {
 	.name = "m",
+	.type = S_TRISTATE,
 	.curr = { "m", mod },
 	.menus = LIST_HEAD_INIT(symbol_mod.menus),
 	.flags = SYMBOL_CONST|SYMBOL_VALID,
@@ -28,6 +30,7 @@ struct symbol symbol_mod = {
 
 struct symbol symbol_no = {
 	.name = "n",
+	.type = S_TRISTATE,
 	.curr = { "n", no },
 	.menus = LIST_HEAD_INIT(symbol_no.menus),
 	.flags = SYMBOL_CONST|SYMBOL_VALID,
@@ -820,8 +823,7 @@ const char *sym_get_string_value(struct symbol *sym)
 		case no:
 			return "n";
 		case mod:
-			sym_calc_value(modules_sym);
-			return (modules_sym->curr.tri == no) ? "n" : "m";
+			return "m";
 		case yes:
 			return "y";
 		}
-- 
GitLab


From 31894d35b51ba61e2931cbf28e80114a4f72bc2b Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Sun, 19 May 2024 22:34:02 +0900
Subject: [PATCH 406/950] kconfig: remove redundant check in expr_join_or()

The check for 'sym1 == sym2' is redundant here because it has already
been done a few lines above:

    if (sym1 != sym2)
            return NULL;

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 scripts/kconfig/expr.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/kconfig/expr.c b/scripts/kconfig/expr.c
index a290de36307ba..4d95fce5f9a7a 100644
--- a/scripts/kconfig/expr.c
+++ b/scripts/kconfig/expr.c
@@ -476,7 +476,7 @@ static struct expr *expr_join_or(struct expr *e1, struct expr *e2)
 			return expr_alloc_comp(E_UNEQUAL, sym1, &symbol_yes);
 		}
 	}
-	if (sym1->type == S_BOOLEAN && sym1 == sym2) {
+	if (sym1->type == S_BOOLEAN) {
 		if ((e1->type == E_NOT && e1->left.expr->type == E_SYMBOL && e2->type == E_SYMBOL) ||
 		    (e2->type == E_NOT && e2->left.expr->type == E_SYMBOL && e1->type == E_SYMBOL))
 			return expr_alloc_symbol(&symbol_yes);
-- 
GitLab


From 659bbf7e1b08267b8e1dd900b316edcb6f6d9e2e Mon Sep 17 00:00:00 2001
From: Douglas Anderson <dianders@chromium.org>
Date: Mon, 20 May 2024 12:56:52 -0700
Subject: [PATCH 407/950] kbuild: scripts/gdb: Replace missed $(srctree)/$(src)
 w/ $(src)

Recently we went through the source tree and replaced
$(srctree)/$(src) w/ $(src). However, the gdb scripts Makefile had a
hidden $(srctree)/$(src) that looked like this:

  $(abspath $(srctree))/$(src)

Because we missed that then my installed kernel had symlinks that
looked like this:

  __init__.py ->
    ${INSTALL_DIR}/$(INSTALL_DIR}/scripts/gdb/linux/__init__.py

Let's also replace the midden $(abspath $(srctree))/$(src) with
$(src). Now:

  __init__.py ->
    $(INSTALL_DIR}/scripts/gdb/linux/__init__.py

Fixes: b1992c3772e6 ("kbuild: use $(src) instead of $(srctree)/$(src) for source directory")
Signed-off-by: Douglas Anderson <dianders@chromium.org>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 scripts/gdb/linux/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/gdb/linux/Makefile b/scripts/gdb/linux/Makefile
index d77ad9079d0f9..fd1402c0a1a18 100644
--- a/scripts/gdb/linux/Makefile
+++ b/scripts/gdb/linux/Makefile
@@ -5,7 +5,7 @@ ifdef building_out_of_srctree
 symlinks := $(patsubst $(src)/%,%,$(wildcard $(src)/*.py))
 
 quiet_cmd_symlink = SYMLINK $@
-      cmd_symlink = ln -fsn $(patsubst $(obj)/%,$(abspath $(srctree))/$(src)/%,$@) $@
+      cmd_symlink = ln -fsn $(patsubst $(obj)/%,$(src)/%,$@) $@
 
 always-y += $(symlinks)
 $(addprefix $(obj)/, $(symlinks)): FORCE
-- 
GitLab


From 04b8cb0945b4bf679c71dc2351e0d3c25481e3c6 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Mon, 20 May 2024 21:42:09 +0900
Subject: [PATCH 408/950] kbuild: avoid unneeded kallsyms step 3

Since commit 951bcae6c5a0 ("kallsyms: Avoid weak references for kallsyms
symbols"), the kallsyms step 3 always occurs.

You can compare the build logs.

[Before 951bcae6c5a0]

  $ git checkout 951bcae6c5a0^
  $ make defconfig all
       [ snip ]
    LD      .tmp_vmlinux.kallsyms1
    NM      .tmp_vmlinux.kallsyms1.syms
    KSYMS   .tmp_vmlinux.kallsyms1.S
    AS      .tmp_vmlinux.kallsyms1.S
    LD      .tmp_vmlinux.kallsyms2
    NM      .tmp_vmlinux.kallsyms2.syms
    KSYMS   .tmp_vmlinux.kallsyms2.S
    AS      .tmp_vmlinux.kallsyms2.S
    LD      vmlinux

[After 951bcae6c5a0]

  $ git checkout 951bcae6c5a0
  $ make defconfig all
       [ snip ]
    LD      .tmp_vmlinux.kallsyms1
    NM      .tmp_vmlinux.kallsyms1.syms
    KSYMS   .tmp_vmlinux.kallsyms1.S
    AS      .tmp_vmlinux.kallsyms1.S
    LD      .tmp_vmlinux.kallsyms2
    NM      .tmp_vmlinux.kallsyms2.syms
    KSYMS   .tmp_vmlinux.kallsyms2.S
    AS      .tmp_vmlinux.kallsyms2.S
    LD      .tmp_vmlinux.kallsyms3             # should not happen
    NM      .tmp_vmlinux.kallsyms3.syms        # should not happen
    KSYMS   .tmp_vmlinux.kallsyms3.S           # should not happen
    AS      .tmp_vmlinux.kallsyms3.S           # should not happen
    LD      vmlinux

The resulting vmlinux is correct, but it always requires an additional
linking step.

The symbols produced by kallsyms are excluded from kallsyms itself
because they were previously missing in step 1. With those symbols
excluded, the symbol lists matched between step 1 and step 2,
eliminating the need for step 3. Now, this has a negative effect.

Since 951bcae6c5a0, the PROVIDE() directives provide the fallback
definitions, which are not trimmed from the sysbol list in step 1
because ${kallsymso_prev} is empty at this point.

In step 2, ${kallsymso_prev} is set, and the kallsyms_* symbols are
trimmed from the symbol list.

Due to the table size difference between step 1 and step 2 (the former
is larger due to the presence of kallsyms_*), step 3 is triggered.

Now that the kallsyms_* symbols are always linked, let's stop omitting
them from kallsyms. This avoids unnecessary step 3.

Fixes: 951bcae6c5a0 ("kallsyms: Avoid weak references for kallsyms symbols")
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 scripts/link-vmlinux.sh |  6 +++---
 scripts/mksysmap        | 11 +----------
 2 files changed, 4 insertions(+), 13 deletions(-)

diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
index 7862a81017477..b0d39a927fbc8 100755
--- a/scripts/link-vmlinux.sh
+++ b/scripts/link-vmlinux.sh
@@ -179,7 +179,7 @@ kallsyms_step()
 	kallsyms_S=${kallsyms_vmlinux}.S
 
 	vmlinux_link ${kallsyms_vmlinux} "${kallsymso_prev}" ${btf_vmlinux_bin_o}
-	mksysmap ${kallsyms_vmlinux} ${kallsyms_vmlinux}.syms ${kallsymso_prev}
+	mksysmap ${kallsyms_vmlinux} ${kallsyms_vmlinux}.syms
 	kallsyms ${kallsyms_vmlinux}.syms ${kallsyms_S}
 
 	info AS ${kallsyms_S}
@@ -193,7 +193,7 @@ kallsyms_step()
 mksysmap()
 {
 	info NM ${2}
-	${CONFIG_SHELL} "${srctree}/scripts/mksysmap" ${1} ${2} ${3}
+	${CONFIG_SHELL} "${srctree}/scripts/mksysmap" ${1} ${2}
 }
 
 sorttable()
@@ -282,7 +282,7 @@ if is_enabled CONFIG_DEBUG_INFO_BTF && is_enabled CONFIG_BPF; then
 	${RESOLVE_BTFIDS} vmlinux
 fi
 
-mksysmap vmlinux System.map ${kallsymso}
+mksysmap vmlinux System.map
 
 if is_enabled CONFIG_BUILDTIME_TABLE_SORT; then
 	info SORTTAB vmlinux
diff --git a/scripts/mksysmap b/scripts/mksysmap
index 57ff5656d566f..e46bafe333bdc 100755
--- a/scripts/mksysmap
+++ b/scripts/mksysmap
@@ -4,7 +4,7 @@
 # tools to retrieve the actual addresses of symbols in the kernel.
 #
 # Usage
-# mksysmap vmlinux System.map [exclude]
+# mksysmap vmlinux System.map
 
 
 #####
@@ -92,13 +92,4 @@ ${NM} -n ${1} | sed >${2} -e "
 # ppc stub
 /\.long_branch\./d
 /\.plt_branch\./d
-
-# ---------------------------------------------------------------------------
-# Ignored kallsyms symbols
-#
-# If the 3rd parameter exists, symbols from it will be omitted from the output.
-# This makes kallsyms have the identical symbol lists in the step 1 and 2.
-# Without this, the step2 would get new symbols generated by scripts/kallsyms.c
-# when CONFIG_KALLSYMS_ALL is enabled. That might require one more pass.
-$(if [ $# -ge 3 ]; then ${NM} ${3} | sed -n '/ U /!s:.* \([^ ]*\)$:/ \1$/d:p'; fi)
 "
-- 
GitLab


From b18b047002b7d3b19d9fb905c1bd2a214016c153 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Mon, 20 May 2024 21:42:10 +0900
Subject: [PATCH 409/950] kbuild: change scripts/mksysmap into sed script

The previous commit removed the subshell execution from scripts/mksysmap,
which is now simple enough to become a sed script.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 scripts/link-vmlinux.sh |  2 +-
 scripts/mksysmap        | 19 ++++++-------------
 2 files changed, 7 insertions(+), 14 deletions(-)

diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
index b0d39a927fbc8..c22a213ea6a9c 100755
--- a/scripts/link-vmlinux.sh
+++ b/scripts/link-vmlinux.sh
@@ -193,7 +193,7 @@ kallsyms_step()
 mksysmap()
 {
 	info NM ${2}
-	${CONFIG_SHELL} "${srctree}/scripts/mksysmap" ${1} ${2}
+	${NM} -n "${1}" | "${srctree}/scripts/mksysmap" > "${2}"
 }
 
 sorttable()
diff --git a/scripts/mksysmap b/scripts/mksysmap
index e46bafe333bdc..c12723a046556 100755
--- a/scripts/mksysmap
+++ b/scripts/mksysmap
@@ -1,22 +1,16 @@
-#!/bin/sh -x
-# Based on the vmlinux file create the System.map file
+#!/bin/sed -f
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# sed script to filter out symbols that are not needed for System.map,
+# or not suitable for kallsyms. The input should be 'nm -n <file>'.
+#
 # System.map is used by module-init tools and some debugging
 # tools to retrieve the actual addresses of symbols in the kernel.
 #
-# Usage
-# mksysmap vmlinux System.map
-
-
-#####
-# Generate System.map (actual filename passed as second argument)
-# The following refers to the symbol type as per nm(1).
-
 # readprofile starts reading symbols when _stext is found, and
 # continue until it finds a symbol which is not either of 'T', 't',
 # 'W' or 'w'.
 #
-
-${NM} -n ${1} | sed >${2} -e "
 # ---------------------------------------------------------------------------
 # Ignored symbol types
 #
@@ -92,4 +86,3 @@ ${NM} -n ${1} | sed >${2} -e "
 # ppc stub
 /\.long_branch\./d
 /\.plt_branch\./d
-"
-- 
GitLab


From 3430f65d6130ccbc86f0ff45642eeb9e2032a600 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Mon, 20 May 2024 21:42:11 +0900
Subject: [PATCH 410/950] kbuild: fix short log for AS in link-vmlinux.sh

In convention, short logs print the output file, not the input file.

Let's change the suffix for 'AS' since it assembles *.S into *.o.

[Before]

  LD      .tmp_vmlinux.kallsyms1
  NM      .tmp_vmlinux.kallsyms1.syms
  KSYMS   .tmp_vmlinux.kallsyms1.S
  AS      .tmp_vmlinux.kallsyms1.S
  LD      .tmp_vmlinux.kallsyms2
  NM      .tmp_vmlinux.kallsyms2.syms
  KSYMS   .tmp_vmlinux.kallsyms2.S
  AS      .tmp_vmlinux.kallsyms2.S
  LD      vmlinux

[After]

  LD      .tmp_vmlinux.kallsyms1
  NM      .tmp_vmlinux.kallsyms1.syms
  KSYMS   .tmp_vmlinux.kallsyms1.S
  AS      .tmp_vmlinux.kallsyms1.o
  LD      .tmp_vmlinux.kallsyms2
  NM      .tmp_vmlinux.kallsyms2.syms
  KSYMS   .tmp_vmlinux.kallsyms2.S
  AS      .tmp_vmlinux.kallsyms2.o
  LD      vmlinux

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 scripts/link-vmlinux.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
index c22a213ea6a9c..7aca51b24e9fb 100755
--- a/scripts/link-vmlinux.sh
+++ b/scripts/link-vmlinux.sh
@@ -182,7 +182,7 @@ kallsyms_step()
 	mksysmap ${kallsyms_vmlinux} ${kallsyms_vmlinux}.syms
 	kallsyms ${kallsyms_vmlinux}.syms ${kallsyms_S}
 
-	info AS ${kallsyms_S}
+	info AS ${kallsymso}
 	${CC} ${NOSTDINC_FLAGS} ${LINUXINCLUDE} ${KBUILD_CPPFLAGS} \
 	      ${KBUILD_AFLAGS} ${KBUILD_AFLAGS_KERNEL} \
 	      -c -o ${kallsymso} ${kallsyms_S}
-- 
GitLab


From 3c562a70cf4da331baef60ebb3f0e30b254006e9 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Wed, 22 May 2024 19:43:11 +0900
Subject: [PATCH 411/950] kbuild: remove a stale comment about cleaning in
 link-vmlinux.sh

Remove the left-over of commit 51eb95e2da41 ("kbuild: Don't remove
link-vmlinux temporary files on exit/signal").

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 scripts/link-vmlinux.sh | 1 -
 1 file changed, 1 deletion(-)

diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
index 7aca51b24e9fb..46ce5d04dbeb1 100755
--- a/scripts/link-vmlinux.sh
+++ b/scripts/link-vmlinux.sh
@@ -201,7 +201,6 @@ sorttable()
 	${objtree}/scripts/sorttable ${1}
 }
 
-# Delete output files in case of error
 cleanup()
 {
 	rm -f .btf.*
-- 
GitLab


From e06a698ae62b9ee5ca98e65be2c90a61464192e6 Mon Sep 17 00:00:00 2001
From: Chen-Yu Tsai <wenst@chromium.org>
Date: Tue, 28 May 2024 16:52:18 +0800
Subject: [PATCH 412/950] scripts/make_fit: Drop fdt image entry compatible
 string

According to the FIT image source file format document found in U-boot [1]
and the split-out FIT image specification [2], under "'/images' node" ->
"Conditionally mandatory property", the "compatible" property is described
as "compatible method for loading image", i.e., not the compatible string
embedded in the FDT or used for matching.

Drop the compatible string from the fdt image entry node.

While at it also fix up a typo in the document section of output_dtb.

[1] U-boot source "doc/usage/fit/source_file_format.rst", or on the website:
    https://docs.u-boot.org/en/latest/usage/fit/source_file_format.html
[2] https://github.com/open-source-firmware/flat-image-tree/blob/main/source/chapter2-source-file-format.rst

Fixes: 7a23b027ec17 ("arm64: boot: Support Flat Image Tree")
Signed-off-by: Chen-Yu Tsai <wenst@chromium.org>
Reviewed-by: Simon Glass <sjg@chromium.org>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 scripts/make_fit.py | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/scripts/make_fit.py b/scripts/make_fit.py
index 3de90c5a094b7..263147df80a44 100755
--- a/scripts/make_fit.py
+++ b/scripts/make_fit.py
@@ -190,7 +190,7 @@ def output_dtb(fsw, seq, fname, arch, compress):
     Args:
         fsw (libfdt.FdtSw): Object to use for writing
         seq (int): Sequence number (1 for first)
-        fmame (str): Filename containing the DTB
+        fname (str): Filename containing the DTB
         arch: FIT architecture, e.g. 'arm64'
         compress (str): Compressed algorithm, e.g. 'gzip'
 
@@ -211,7 +211,6 @@ def output_dtb(fsw, seq, fname, arch, compress):
         fsw.property_string('type', 'flat_dt')
         fsw.property_string('arch', arch)
         fsw.property_string('compression', compress)
-        fsw.property('compatible', bytes(compat))
 
         with open(fname, 'rb') as inf:
             compressed = compress_data(inf, compress)
-- 
GitLab


From 0e49e940d1bc47e5f8937aa981337debaae69bd8 Mon Sep 17 00:00:00 2001
From: Avraham Stern <avraham.stern@intel.com>
Date: Mon, 27 May 2024 19:05:56 +0300
Subject: [PATCH 413/950] wifi: iwlwifi: mvm: add an option to use ptp clock
 for rx timestamp

Add a debugfs option to use the ptp clock time for rx device
timestamps. This can be useful to e.g. synchronize multiple NICs or
reporting the timestamp in the system clock instead of gp2.

Signed-off-by: Avraham Stern <avraham.stern@intel.com>
Reviewed-by: Gregory Greenman <gregory.greenman@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240527190228.b197b4f3f9ed.I578ee916d5f517a2e3a89e890a8ea24065946427@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c | 3 +++
 drivers/net/wireless/intel/iwlwifi/mvm/mvm.h     | 3 +++
 drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c    | 8 ++++++++
 3 files changed, 14 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
index 96c9382b98fb5..879640a7d46a5 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
@@ -2441,6 +2441,9 @@ void iwl_mvm_dbgfs_register(struct iwl_mvm *mvm)
 	debugfs_create_file("mem", 0600, mvm->debugfs_dir, mvm,
 			    &iwl_dbgfs_mem_ops);
 
+	debugfs_create_bool("rx_ts_ptp", 0600, mvm->debugfs_dir,
+			    &mvm->rx_ts_ptp);
+
 	/*
 	 * Create a symlink with mac80211. It will be removed when mac80211
 	 * exists (before the opmode exists which removes the target.)
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index 770a7098b0f9b..879fa1065bec5 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -1309,6 +1309,9 @@ struct iwl_mvm {
 	struct iwl_phy_specific_cfg phy_filters;
 #endif
 
+	/* report rx timestamp in ptp clock time */
+	bool rx_ts_ptp;
+
 	unsigned long last_6ghz_passive_scan_jiffies;
 	unsigned long last_reset_or_resume_time_jiffies;
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
index 2f9e2254fb467..5af169f3d708a 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
@@ -1954,6 +1954,14 @@ static void iwl_mvm_rx_fill_status(struct iwl_mvm *mvm,
 	iwl_mvm_decode_lsig(skb, phy_data);
 
 	rx_status->device_timestamp = phy_data->gp2_on_air_rise;
+
+	if (mvm->rx_ts_ptp && mvm->monitor_on) {
+		u64 adj_time =
+			iwl_mvm_ptp_get_adj_time(mvm, phy_data->gp2_on_air_rise * NSEC_PER_USEC);
+
+		rx_status->device_timestamp = div64_u64(adj_time, NSEC_PER_USEC);
+	}
+
 	rx_status->freq = ieee80211_channel_to_frequency(phy_data->channel,
 							 rx_status->band);
 	iwl_mvm_get_signal_strength(mvm, rx_status, rate_n_flags,
-- 
GitLab


From 94854648b5b0774447dace5e8802c641b24da4af Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 27 May 2024 19:05:57 +0300
Subject: [PATCH 414/950] wifi: iwlwifi: mvm: report 64-bit radiotap timestamp

Use the new RX_FLAG_MACTIME_IS_RTAP_TS64 in mac80211 to report
a 64-bit timestamp in the mactime for radiotap only, in case we
report the synchronized PTP clock timestamp (otherwise we really
only have 32 bits anyway).

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Reviewed-by: Gregory Greenman <gregory.greenman@intel.com>
Reviewed-by: Benjamin Berg <benjamin.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240527190228.4fc44356e7df.Ic8642d35f1090a415e09299a1bd409f51dfb6351@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
index 5af169f3d708a..ff8d801b4e659 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
@@ -1959,7 +1959,9 @@ static void iwl_mvm_rx_fill_status(struct iwl_mvm *mvm,
 		u64 adj_time =
 			iwl_mvm_ptp_get_adj_time(mvm, phy_data->gp2_on_air_rise * NSEC_PER_USEC);
 
-		rx_status->device_timestamp = div64_u64(adj_time, NSEC_PER_USEC);
+		rx_status->mactime = div64_u64(adj_time, NSEC_PER_USEC);
+		rx_status->flag |= RX_FLAG_MACTIME_IS_RTAP_TS64;
+		rx_status->flag &= ~RX_FLAG_MACTIME;
 	}
 
 	rx_status->freq = ieee80211_channel_to_frequency(phy_data->channel,
-- 
GitLab


From e1b44c8f7ba40801365dc8689f0cd88acd2ee901 Mon Sep 17 00:00:00 2001
From: Avri Altman <avri.altman@intel.com>
Date: Mon, 27 May 2024 19:05:58 +0300
Subject: [PATCH 415/950] wifi: iwlwifi: mvm: Enable p2p low latency

Enable p2p low latency by default.

Signed-off-by: Avri Altman <avri.altman@intel.com>
Reviewed-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240527190228.21b431bdfc26.I018e330d1e6a76e967b25e9542c2260f0f6ed2a8@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/constants.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/constants.h b/drivers/net/wireless/intel/iwlwifi/mvm/constants.h
index 3cbeaddf43586..eda6634b4fb57 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/constants.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/constants.h
@@ -23,7 +23,7 @@
 #define IWL_MVM_WOWLAN_PS_RX_DATA_TIMEOUT	(10 * USEC_PER_MSEC)
 #define IWL_MVM_SHORT_PS_TX_DATA_TIMEOUT	(2 * 1024) /* defined in TU */
 #define IWL_MVM_SHORT_PS_RX_DATA_TIMEOUT	(40 * 1024) /* defined in TU */
-#define IWL_MVM_P2P_LOWLATENCY_PS_ENABLE	0
+#define IWL_MVM_P2P_LOWLATENCY_PS_ENABLE	1
 #define IWL_MVM_UAPSD_RX_DATA_TIMEOUT		(50 * USEC_PER_MSEC)
 #define IWL_MVM_UAPSD_TX_DATA_TIMEOUT		(50 * USEC_PER_MSEC)
 #define IWL_MVM_UAPSD_QUEUES		(IEEE80211_WMM_IE_STA_QOSINFO_AC_VO |\
-- 
GitLab


From a423e37ecc3ede97621815da4923fbca5497c4a1 Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Mon, 27 May 2024 19:05:59 +0300
Subject: [PATCH 416/950] wifi: iwlwifi: mvm: remove IWL_MVM_USE_NSSN_SYNC

This is not used and not needed anymore.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240527190228.c5edfb967e35.I34a3d54a1dc90d9b2937b0bcbbc508fe3cd41773@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/constants.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/constants.h b/drivers/net/wireless/intel/iwlwifi/mvm/constants.h
index eda6634b4fb57..c991eaeade157 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/constants.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/constants.h
@@ -114,7 +114,6 @@
 #define IWL_MVM_D3_DEBUG			false
 #define IWL_MVM_USE_TWT				true
 #define IWL_MVM_AMPDU_CONSEC_DROPS_DELBA	20
-#define IWL_MVM_USE_NSSN_SYNC			0
 #define IWL_MVM_FTM_INITIATOR_ENABLE_SMOOTH     false
 #define IWL_MVM_FTM_INITIATOR_SMOOTH_ALPHA      40
 /*  20016 pSec is 6 meter RTT, meaning 3 meter range */
-- 
GitLab


From fb82e76a3b3b23c4a51fe254fa78497bfa42007c Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Mon, 27 May 2024 19:06:00 +0300
Subject: [PATCH 417/950] wifi: iwlwifi: mvm: move a constant to constants.h

Move IWL_MVM_MIN_BEACON_INTERVAL_TU to constants.h

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240527190228.395f5b24ff82.Id78a5a404c3ae15cbbc950b1f1d7e500a8b92a43@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/constants.h | 1 +
 drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c  | 2 --
 2 files changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/constants.h b/drivers/net/wireless/intel/iwlwifi/mvm/constants.h
index c991eaeade157..d840653cc9079 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/constants.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/constants.h
@@ -123,6 +123,7 @@
 #define IWL_MVM_DISABLE_AP_FILS			false
 #define IWL_MVM_6GHZ_PASSIVE_SCAN_TIMEOUT       3000 /* in seconds */
 #define IWL_MVM_6GHZ_PASSIVE_SCAN_ASSOC_TIMEOUT 60   /* in seconds */
+#define IWL_MVM_MIN_BEACON_INTERVAL_TU		16
 #define IWL_MVM_AUTO_EML_ENABLE                 true
 #define IWL_MVM_MISSED_BEACONS_EXIT_ESR_THRESH	7
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index 8ec699d9f316a..28540fd4a8da0 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -3716,8 +3716,6 @@ static void iwl_mvm_rs_rate_init_all_links(struct iwl_mvm *mvm,
 	}
 }
 
-#define IWL_MVM_MIN_BEACON_INTERVAL_TU 16
-
 static bool iwl_mvm_vif_conf_from_sta(struct iwl_mvm *mvm,
 				      struct ieee80211_vif *vif,
 				      struct ieee80211_sta *sta)
-- 
GitLab


From 6b82f4e119d1e27632cb350a6165c02a8ec9db07 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 27 May 2024 19:06:01 +0300
Subject: [PATCH 418/950] wifi: iwlwifi: mvm: handle TPE advertised by AP

6 GHz BSS SP client shall respect TX power limits advertised
by the AP in TPE elements, send the data to the firmware using
the AP_TX_POWER_CONSTRAINTS_CMD command, so do that.

Co-developed-by: Mukesh Sisodiya <mukesh.sisodiya@intel.com>
Signed-off-by: Mukesh Sisodiya <mukesh.sisodiya@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240527190228.32f1e2e1447c.I58ac91c38585362aa42bb4a8a59c7d88e67bc40b@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 .../net/wireless/intel/iwlwifi/mvm/mac80211.c | 11 ++++
 .../wireless/intel/iwlwifi/mvm/mld-mac80211.c | 55 ++++++++++++++++---
 drivers/net/wireless/intel/iwlwifi/mvm/mvm.h  |  6 ++
 3 files changed, 63 insertions(+), 9 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index 28540fd4a8da0..7b030995a6a49 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -2731,6 +2731,13 @@ iwl_mvm_bss_info_changed_station_common(struct iwl_mvm *mvm,
 
 	if (changes & BSS_CHANGED_BANDWIDTH)
 		iwl_mvm_update_link_smps(vif, link_conf);
+
+	if (changes & BSS_CHANGED_TPE) {
+		IWL_DEBUG_CALIB(mvm, "Changing TPE\n");
+		iwl_mvm_send_ap_tx_power_constraint_cmd(mvm, vif,
+							link_conf,
+							false);
+	}
 }
 
 static void iwl_mvm_bss_info_changed_station(struct iwl_mvm *mvm,
@@ -5085,6 +5092,10 @@ static int __iwl_mvm_assign_vif_chanctx(struct iwl_mvm *mvm,
 		}
 
 		iwl_mvm_update_quotas(mvm, false, NULL);
+
+		iwl_mvm_send_ap_tx_power_constraint_cmd(mvm, vif,
+							link_conf,
+							false);
 	}
 
 	goto out;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
index f69f7df40a6dd..3a1504e95b0f7 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
@@ -347,6 +347,11 @@ __iwl_mvm_mld_assign_vif_chanctx(struct iwl_mvm *mvm,
 		rcu_read_unlock();
 	}
 
+	if (vif->type == NL80211_IFTYPE_STATION)
+		iwl_mvm_send_ap_tx_power_constraint_cmd(mvm, vif,
+							link_conf,
+							false);
+
 	/* then activate */
 	ret = iwl_mvm_link_changed(mvm, vif, link_conf,
 				   LINK_CONTEXT_MODIFY_ACTIVE |
@@ -526,9 +531,37 @@ static void iwl_mvm_mld_unassign_vif_chanctx(struct ieee80211_hw *hw,
 }
 
 static void
+iwl_mvm_tpe_sta_cmd_data(struct iwl_txpower_constraints_cmd *cmd,
+			 const struct ieee80211_bss_conf *bss_info)
+{
+	u8 i;
+
+	/*
+	 * NOTE: the 0 here is IEEE80211_TPE_CAT_6GHZ_DEFAULT,
+	 * we fully ignore IEEE80211_TPE_CAT_6GHZ_SUBORDINATE
+	 */
+
+	BUILD_BUG_ON(ARRAY_SIZE(cmd->psd_pwr) !=
+		     ARRAY_SIZE(bss_info->tpe.psd_local[0].power));
+
+	/* if not valid, mac80211 puts default (max value) */
+	for (i = 0; i < ARRAY_SIZE(cmd->psd_pwr); i++)
+		cmd->psd_pwr[i] = min(bss_info->tpe.psd_local[0].power[i],
+				      bss_info->tpe.psd_reg_client[0].power[i]);
+
+	BUILD_BUG_ON(ARRAY_SIZE(cmd->eirp_pwr) !=
+		     ARRAY_SIZE(bss_info->tpe.max_local[0].power));
+
+	for (i = 0; i < ARRAY_SIZE(cmd->eirp_pwr); i++)
+		cmd->eirp_pwr[i] = min(bss_info->tpe.max_local[0].power[i],
+				       bss_info->tpe.max_reg_client[0].power[i]);
+}
+
+void
 iwl_mvm_send_ap_tx_power_constraint_cmd(struct iwl_mvm *mvm,
 					struct ieee80211_vif *vif,
-					struct ieee80211_bss_conf *bss_conf)
+					struct ieee80211_bss_conf *bss_conf,
+					bool is_ap)
 {
 	struct iwl_txpower_constraints_cmd cmd = {};
 	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
@@ -548,19 +581,22 @@ iwl_mvm_send_ap_tx_power_constraint_cmd(struct iwl_mvm *mvm,
 	    link_info->fw_link_id == IWL_MVM_FW_LINK_ID_INVALID)
 		return;
 
-	if (bss_conf->chanreq.oper.chan->band != NL80211_BAND_6GHZ ||
-	    bss_conf->chanreq.oper.chan->flags &
-		    IEEE80211_CHAN_NO_6GHZ_VLP_CLIENT)
+	if (bss_conf->chanreq.oper.chan->band != NL80211_BAND_6GHZ)
 		return;
 
 	cmd.link_id = cpu_to_le16(link_info->fw_link_id);
-	/*
-	 * Currently supporting VLP Soft AP only.
-	 */
-	cmd.ap_type = cpu_to_le16(IWL_6GHZ_AP_TYPE_VLP);
 	memset(cmd.psd_pwr, DEFAULT_TPE_TX_POWER, sizeof(cmd.psd_pwr));
 	memset(cmd.eirp_pwr, DEFAULT_TPE_TX_POWER, sizeof(cmd.eirp_pwr));
 
+	if (is_ap) {
+		cmd.ap_type = cpu_to_le16(IWL_6GHZ_AP_TYPE_VLP);
+	} else if (bss_conf->power_type == IEEE80211_REG_UNSET_AP) {
+		return;
+	} else {
+		cmd.ap_type = cpu_to_le16(bss_conf->power_type - 1);
+		iwl_mvm_tpe_sta_cmd_data(&cmd, bss_conf);
+	}
+
 	ret = iwl_mvm_send_cmd_pdu(mvm,
 				   WIDE_ID(PHY_OPS_GROUP,
 					   AP_TX_POWER_CONSTRAINTS_CMD),
@@ -582,7 +618,8 @@ static int iwl_mvm_mld_start_ap_ibss(struct ieee80211_hw *hw,
 	guard(mvm)(mvm);
 
 	if (vif->type == NL80211_IFTYPE_AP)
-		iwl_mvm_send_ap_tx_power_constraint_cmd(mvm, vif, link_conf);
+		iwl_mvm_send_ap_tx_power_constraint_cmd(mvm, vif,
+							link_conf, true);
 
 	/* Send the beacon template */
 	ret = iwl_mvm_mac_ctxt_beacon_changed(mvm, vif, link_conf);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index 879fa1065bec5..82080d920d590 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -2961,4 +2961,10 @@ iwl_mvm_bt_coex_calculate_esr_mode(struct iwl_mvm *mvm,
 				   bool primary);
 int iwl_mvm_esr_non_bss_link(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 			     unsigned int link_id, bool active);
+
+void
+iwl_mvm_send_ap_tx_power_constraint_cmd(struct iwl_mvm *mvm,
+					struct ieee80211_vif *vif,
+					struct ieee80211_bss_conf *bss_conf,
+					bool is_ap);
 #endif /* __IWL_MVM_H__ */
-- 
GitLab


From 8a039ef63170860ddcccd615543ea000c10b444f Mon Sep 17 00:00:00 2001
From: Avraham Stern <avraham.stern@intel.com>
Date: Mon, 27 May 2024 19:06:02 +0300
Subject: [PATCH 419/950] wifi: iwlwifi: mvm: initiator: move setting target
 flags into a function

Move setting the target flags into a dedicated function to support
different versions of the target struct.
This is done as preparation for moving to the new range request
version.

Signed-off-by: Avraham Stern <avraham.stern@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240527190228.9d22b61ce589.I7dbe596b4f677638d9a48c3f39b0826a9e35bea4@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 .../intel/iwlwifi/mvm/ftm-initiator.c         | 49 ++++++++++++-------
 1 file changed, 30 insertions(+), 19 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c
index 72a3d71f46f04..98b1bbfc84bcc 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c
@@ -434,44 +434,55 @@ iwl_mvm_ftm_put_target_v2(struct iwl_mvm *mvm,
 #define FTM_PUT_FLAG(flag)	(target->initiator_ap_flags |= \
 				 cpu_to_le32(IWL_INITIATOR_AP_FLAGS_##flag))
 
+#define FTM_SET_FLAG(flag)	(*flags |= \
+				 cpu_to_le32(IWL_INITIATOR_AP_FLAGS_##flag))
+
 static void
-iwl_mvm_ftm_put_target_common(struct iwl_mvm *mvm,
-			      struct cfg80211_pmsr_request_peer *peer,
-			      struct iwl_tof_range_req_ap_entry_v6 *target)
+iwl_mvm_ftm_set_target_flags(struct iwl_mvm *mvm,
+			     struct cfg80211_pmsr_request_peer *peer,
+			     __le32 *flags)
 {
-	memcpy(target->bssid, peer->addr, ETH_ALEN);
-	target->burst_period =
-		cpu_to_le16(peer->ftm.burst_period);
-	target->samples_per_burst = peer->ftm.ftms_per_burst;
-	target->num_of_bursts = peer->ftm.num_bursts_exp;
-	target->ftmr_max_retries = peer->ftm.ftmr_retries;
-	target->initiator_ap_flags = cpu_to_le32(0);
+	*flags = cpu_to_le32(0);
 
 	if (peer->ftm.asap)
-		FTM_PUT_FLAG(ASAP);
+		FTM_SET_FLAG(ASAP);
 
 	if (peer->ftm.request_lci)
-		FTM_PUT_FLAG(LCI_REQUEST);
+		FTM_SET_FLAG(LCI_REQUEST);
 
 	if (peer->ftm.request_civicloc)
-		FTM_PUT_FLAG(CIVIC_REQUEST);
+		FTM_SET_FLAG(CIVIC_REQUEST);
 
 	if (IWL_MVM_FTM_INITIATOR_DYNACK)
-		FTM_PUT_FLAG(DYN_ACK);
+		FTM_SET_FLAG(DYN_ACK);
 
 	if (IWL_MVM_FTM_INITIATOR_ALGO == IWL_TOF_ALGO_TYPE_LINEAR_REG)
-		FTM_PUT_FLAG(ALGO_LR);
+		FTM_SET_FLAG(ALGO_LR);
 	else if (IWL_MVM_FTM_INITIATOR_ALGO == IWL_TOF_ALGO_TYPE_FFT)
-		FTM_PUT_FLAG(ALGO_FFT);
+		FTM_SET_FLAG(ALGO_FFT);
 
 	if (peer->ftm.trigger_based)
-		FTM_PUT_FLAG(TB);
+		FTM_SET_FLAG(TB);
 	else if (peer->ftm.non_trigger_based)
-		FTM_PUT_FLAG(NON_TB);
+		FTM_SET_FLAG(NON_TB);
 
 	if ((peer->ftm.trigger_based || peer->ftm.non_trigger_based) &&
 	    peer->ftm.lmr_feedback)
-		FTM_PUT_FLAG(LMR_FEEDBACK);
+		FTM_SET_FLAG(LMR_FEEDBACK);
+}
+
+static void
+iwl_mvm_ftm_put_target_common(struct iwl_mvm *mvm,
+			      struct cfg80211_pmsr_request_peer *peer,
+			      struct iwl_tof_range_req_ap_entry_v6 *target)
+{
+	memcpy(target->bssid, peer->addr, ETH_ALEN);
+	target->burst_period =
+		cpu_to_le16(peer->ftm.burst_period);
+	target->samples_per_burst = peer->ftm.ftms_per_burst;
+	target->num_of_bursts = peer->ftm.num_bursts_exp;
+	target->ftmr_max_retries = peer->ftm.ftmr_retries;
+	iwl_mvm_ftm_set_target_flags(mvm, peer, &target->initiator_ap_flags);
 }
 
 static int
-- 
GitLab


From 94df6cbd4c4aea633a9b4bbfab835dcfee21578b Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Mon, 27 May 2024 19:06:03 +0300
Subject: [PATCH 420/950] wifi: iwlwifi: mvm: Remove debug related code

This code is intended for internal testing. Remove it.

Fixes: 30ce039094b5 ("wifi: iwlwifi: mvm: Don't allow EMLSR when the RSSI is low")
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240527190228.c3b89828efb2.I7ded6348d2fb0cb7e103c4eee033451924c3461d@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/tests/links.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tests/links.c b/drivers/net/wireless/intel/iwlwifi/mvm/tests/links.c
index f49e3c98b1ba4..6a680b5d03e02 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/tests/links.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tests/links.c
@@ -393,9 +393,6 @@ static void test_valid_link_pair(struct kunit *test)
 	chandef_a.width = params->cw_a ?: NL80211_CHAN_WIDTH_20;
 	chandef_b.width = params->cw_b ?: NL80211_CHAN_WIDTH_20;
 
-#ifdef CONFIG_IWLWIFI_SUPPORT_DEBUG_OVERRIDES
-	trans->dbg_cfg = default_dbg_config;
-#endif
 	mvm.trans = trans;
 
 	mvm.last_bt_notif.wifi_loss_low_rssi = params->bt;
-- 
GitLab


From 16ec82d3473c10ea7435432a0ed01bf9125b9ca5 Mon Sep 17 00:00:00 2001
From: Avraham Stern <avraham.stern@intel.com>
Date: Mon, 27 May 2024 19:06:04 +0300
Subject: [PATCH 421/950] wifi: iwlwifi: mvm: initiator: move setting the
 sta_id into a function

Move setting the target's sta_id (and related flags) into a function
to support different versions of the target struct.
This is done as preparation for moving to the new range request
version.

Signed-off-by: Avraham Stern <avraham.stern@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240527190228.18e3a6a6f1cb.I85e3ee607b3947448532bc16730f8898a11c92b8@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 .../intel/iwlwifi/mvm/ftm-initiator.c         | 55 ++++++++++---------
 1 file changed, 30 insertions(+), 25 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c
index 98b1bbfc84bcc..8596e6f7d1dc0 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c
@@ -431,9 +431,6 @@ iwl_mvm_ftm_put_target_v2(struct iwl_mvm *mvm,
 	return 0;
 }
 
-#define FTM_PUT_FLAG(flag)	(target->initiator_ap_flags |= \
-				 cpu_to_le32(IWL_INITIATOR_AP_FLAGS_##flag))
-
 #define FTM_SET_FLAG(flag)	(*flags |= \
 				 cpu_to_le32(IWL_INITIATOR_AP_FLAGS_##flag))
 
@@ -525,21 +522,10 @@ iwl_mvm_ftm_put_target_v4(struct iwl_mvm *mvm,
 	return 0;
 }
 
-static int
-iwl_mvm_ftm_put_target(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
-		       struct cfg80211_pmsr_request_peer *peer,
-		       struct iwl_tof_range_req_ap_entry_v6 *target)
+static int iwl_mvm_ftm_set_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
+			       struct cfg80211_pmsr_request_peer *peer,
+			       u8 *sta_id, __le32 *flags)
 {
-	int ret;
-
-	ret = iwl_mvm_ftm_target_chandef_v2(mvm, peer, &target->channel_num,
-					    &target->format_bw,
-					    &target->ctrl_ch_position);
-	if (ret)
-		return ret;
-
-	iwl_mvm_ftm_put_target_common(mvm, peer, target);
-
 	if (vif->cfg.assoc) {
 		struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
 		struct ieee80211_sta *sta;
@@ -551,8 +537,8 @@ iwl_mvm_ftm_put_target(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 			if (memcmp(peer->addr, link_conf->bssid, ETH_ALEN))
 				continue;
 
-			target->sta_id = mvmvif->link[link_id]->ap_sta_id;
-			sta = rcu_dereference(mvm->fw_id_to_mac_id[target->sta_id]);
+			*sta_id = mvmvif->link[link_id]->ap_sta_id;
+			sta = rcu_dereference(mvm->fw_id_to_mac_id[*sta_id]);
 			if (WARN_ON_ONCE(IS_ERR_OR_NULL(sta))) {
 				rcu_read_unlock();
 				return PTR_ERR_OR_ZERO(sta);
@@ -560,23 +546,42 @@ iwl_mvm_ftm_put_target(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 
 			if (sta->mfp && (peer->ftm.trigger_based ||
 					 peer->ftm.non_trigger_based))
-				FTM_PUT_FLAG(PMF);
+				FTM_SET_FLAG(PMF);
 			break;
 		}
 		rcu_read_unlock();
 
 #ifdef CONFIG_IWLWIFI_DEBUGFS
 		if (mvmvif->ftm_unprotected) {
-			target->sta_id = IWL_MVM_INVALID_STA;
-			target->initiator_ap_flags &=
-				~cpu_to_le32(IWL_INITIATOR_AP_FLAGS_PMF);
+			*sta_id = IWL_MVM_INVALID_STA;
+			*flags &= ~cpu_to_le32(IWL_INITIATOR_AP_FLAGS_PMF);
 		}
-
 #endif
 	} else {
-		target->sta_id = IWL_MVM_INVALID_STA;
+		*sta_id = IWL_MVM_INVALID_STA;
 	}
 
+	return 0;
+}
+
+static int
+iwl_mvm_ftm_put_target(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
+		       struct cfg80211_pmsr_request_peer *peer,
+		       struct iwl_tof_range_req_ap_entry_v6 *target)
+{
+	int ret;
+
+	ret = iwl_mvm_ftm_target_chandef_v2(mvm, peer, &target->channel_num,
+					    &target->format_bw,
+					    &target->ctrl_ch_position);
+	if (ret)
+		return ret;
+
+	iwl_mvm_ftm_put_target_common(mvm, peer, target);
+
+	iwl_mvm_ftm_set_sta(mvm, vif, peer, &target->sta_id,
+			    &target->initiator_ap_flags);
+
 	/*
 	 * TODO: Beacon interval is currently unknown, so use the common value
 	 * of 100 TUs.
-- 
GitLab


From 626be4bf99f6250cd66da5d311a72ad7455c5a64 Mon Sep 17 00:00:00 2001
From: Avraham Stern <avraham.stern@intel.com>
Date: Mon, 27 May 2024 19:06:05 +0300
Subject: [PATCH 422/950] wifi: iwlwifi: mvm: modify
 iwl_mvm_ftm_set_secured_ranging() parameters

Modify iwl_mvm_ftm_set_secured_ranging() parameters to support
multiple versions of the target struct.
This is done as preparation for moving to the new range request
version.

Signed-off-by: Avraham Stern <avraham.stern@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240527190228.56d6aee320b3.I5a52fa93cd791d0229b392a20f076b7cebb110cd@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 .../intel/iwlwifi/mvm/ftm-initiator.c         | 54 ++++++++++++-------
 1 file changed, 34 insertions(+), 20 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c
index 8596e6f7d1dc0..f5bf99f7fc2ea 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c
@@ -40,6 +40,12 @@ struct iwl_mvm_ftm_pasn_entry {
 	u32 flags;
 };
 
+struct iwl_mvm_ftm_iter_data {
+	u8 *cipher;
+	u8 *bssid;
+	u8 *tk;
+};
+
 int iwl_mvm_ftm_add_pasn_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 			     u8 *addr, u32 cipher, u8 *tk, u32 tk_len,
 			     u8 *hltk, u32 hltk_len)
@@ -719,7 +725,7 @@ static void iter(struct ieee80211_hw *hw,
 		 struct ieee80211_key_conf *key,
 		 void *data)
 {
-	struct iwl_tof_range_req_ap_entry_v6 *target = data;
+	struct iwl_mvm_ftm_iter_data *target = data;
 
 	if (!sta || memcmp(sta->addr, target->bssid, ETH_ALEN))
 		return;
@@ -730,16 +736,16 @@ static void iter(struct ieee80211_hw *hw,
 		return;
 
 	memcpy(target->tk, key->key, key->keylen);
-	target->cipher = iwl_mvm_cipher_to_location_cipher(key->cipher);
-	WARN_ON(target->cipher == IWL_LOCATION_CIPHER_INVALID);
+	*target->cipher = iwl_mvm_cipher_to_location_cipher(key->cipher);
+	WARN_ON(*target->cipher == IWL_LOCATION_CIPHER_INVALID);
 }
 
 static void
 iwl_mvm_ftm_set_secured_ranging(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
-				struct iwl_tof_range_req_ap_entry_v7 *target)
+				u8 *bssid, u8 *cipher, u8 *hltk, u8 *tk,
+				u8 *rx_pn, u8 *tx_pn, __le32 *flags)
 {
 	struct iwl_mvm_ftm_pasn_entry *entry;
-	u32 flags = le32_to_cpu(target->initiator_ap_flags);
 #ifdef CONFIG_IWLWIFI_DEBUGFS
 	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
 
@@ -747,35 +753,39 @@ iwl_mvm_ftm_set_secured_ranging(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 		return;
 #endif
 
-	if (!(flags & (IWL_INITIATOR_AP_FLAGS_NON_TB |
+	if (!(le32_to_cpu(*flags) & (IWL_INITIATOR_AP_FLAGS_NON_TB |
 		       IWL_INITIATOR_AP_FLAGS_TB)))
 		return;
 
 	lockdep_assert_held(&mvm->mutex);
 
 	list_for_each_entry(entry, &mvm->ftm_initiator.pasn_list, list) {
-		if (memcmp(entry->addr, target->bssid, sizeof(entry->addr)))
+		if (memcmp(entry->addr, bssid, sizeof(entry->addr)))
 			continue;
 
-		target->cipher = entry->cipher;
+		*cipher = entry->cipher;
 
 		if (entry->flags & IWL_MVM_PASN_FLAG_HAS_HLTK)
-			memcpy(target->hltk, entry->hltk, sizeof(target->hltk));
+			memcpy(hltk, entry->hltk, sizeof(entry->hltk));
 		else
-			memset(target->hltk, 0, sizeof(target->hltk));
+			memset(hltk, 0, sizeof(entry->hltk));
 
 		if (vif->cfg.assoc &&
-		    !memcmp(vif->bss_conf.bssid, target->bssid,
-			    sizeof(target->bssid)))
-			ieee80211_iter_keys(mvm->hw, vif, iter, target);
-		else
-			memcpy(target->tk, entry->tk, sizeof(target->tk));
+		    !memcmp(vif->bss_conf.bssid, bssid, ETH_ALEN)) {
+			struct iwl_mvm_ftm_iter_data target;
+
+			target.cipher = cipher;
+			target.bssid = bssid;
+			target.tk = tk;
+			ieee80211_iter_keys(mvm->hw, vif, iter, &target);
+		} else {
+			memcpy(tk, entry->tk, sizeof(entry->tk));
+		}
 
-		memcpy(target->rx_pn, entry->rx_pn, sizeof(target->rx_pn));
-		memcpy(target->tx_pn, entry->tx_pn, sizeof(target->tx_pn));
+		memcpy(rx_pn, entry->rx_pn, sizeof(entry->rx_pn));
+		memcpy(tx_pn, entry->tx_pn, sizeof(entry->tx_pn));
 
-		target->initiator_ap_flags |=
-			cpu_to_le32(IWL_INITIATOR_AP_FLAGS_SECURED);
+		FTM_SET_FLAG(SECURED);
 		return;
 	}
 }
@@ -789,7 +799,11 @@ iwl_mvm_ftm_put_target_v7(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 	if (err)
 		return err;
 
-	iwl_mvm_ftm_set_secured_ranging(mvm, vif, target);
+	iwl_mvm_ftm_set_secured_ranging(mvm, vif, target->bssid,
+					&target->cipher, target->hltk,
+					target->tk, target->rx_pn,
+					target->tx_pn,
+					&target->initiator_ap_flags);
 	return err;
 }
 
-- 
GitLab


From d29fc6af1ab845fd0e9ab1e2e6060ba6146bacbb Mon Sep 17 00:00:00 2001
From: Avraham Stern <avraham.stern@intel.com>
Date: Mon, 27 May 2024 19:06:06 +0300
Subject: [PATCH 423/950] wifi: iwlwifi: mvm: add support for version 14 of the
 range request command

This version adds a testing option to send an incorrect SAC in the
first NDPA.

Signed-off-by: Avraham Stern <avraham.stern@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240527190228.8f36ccb1cc74.I9b76461634f308e75dc3cd016d0b0bce812c6e9d@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 .../wireless/intel/iwlwifi/fw/api/location.h  | 105 ++++++++++++++++++
 .../wireless/intel/iwlwifi/mvm/constants.h    |   1 +
 .../intel/iwlwifi/mvm/ftm-initiator.c         | 102 +++++++++++++++++
 3 files changed, 208 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/location.h b/drivers/net/wireless/intel/iwlwifi/fw/api/location.h
index 25530a29317e8..c20bb289a6233 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/location.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/location.h
@@ -2,6 +2,7 @@
 /*
  * Copyright (C) 2015-2017 Intel Deutschland GmbH
  * Copyright (C) 2018-2022 Intel Corporation
+ * Copyright (C) 2024 Intel Corporation
  */
 #ifndef __iwl_fw_api_location_h__
 #define __iwl_fw_api_location_h__
@@ -561,6 +562,8 @@ struct iwl_tof_range_req_ap_entry_v2 {
  *	the responder asked for LMR feedback although the initiator did not set
  *	the LMR feedback bit in the FTM request. If not set, the initiator will
  *	continue with the session and will provide the LMR feedback.
+ * @IWL_INITIATOR_AP_FLAGS_TEST_INCORRECT_SAC: send an incorrect SAC in the
+ *	first NDP exchange. This is used for testing.
  */
 enum iwl_initiator_ap_flags {
 	IWL_INITIATOR_AP_FLAGS_ASAP = BIT(1),
@@ -577,6 +580,7 @@ enum iwl_initiator_ap_flags {
 	IWL_INITIATOR_AP_FLAGS_USE_CALIB = BIT(13),
 	IWL_INITIATOR_AP_FLAGS_PMF = BIT(14),
 	IWL_INITIATOR_AP_FLAGS_TERMINATE_ON_LMR_FEEDBACK = BIT(15),
+	IWL_INITIATOR_AP_FLAGS_TEST_INCORRECT_SAC = BIT(16),
 };
 
 /**
@@ -797,6 +801,7 @@ struct iwl_tof_range_req_ap_entry_v7 {
 } __packed; /* LOCATION_RANGE_REQ_AP_ENTRY_CMD_API_S_VER_7 */
 
 #define IWL_LOCATION_MAX_STS_POS	3
+#define IWL_LOCATION_TOTAL_LTF_POS	6
 
 /**
  * struct iwl_tof_range_req_ap_entry_v8 - AP configuration parameters
@@ -953,6 +958,78 @@ struct iwl_tof_range_req_ap_entry_v9 {
 	__le16 min_time_between_msr;
 } __packed; /* LOCATION_RANGE_REQ_AP_ENTRY_CMD_API_S_VER_9 */
 
+/**
+ * struct iwl_tof_range_req_ap_entry_v10 - AP configuration parameters
+ * @initiator_ap_flags: see &enum iwl_initiator_ap_flags.
+ * @band: 0 for 5.2 GHz, 1 for 2.4 GHz, 2 for 6GHz
+ * @channel_num: AP Channel number
+ * @format_bw: bits 0 - 3: &enum iwl_location_frame_format.
+ *             bits 4 - 7: &enum iwl_location_bw.
+ * @ctrl_ch_position: Coding of the control channel position relative to the
+ *	center frequency, see iwl_mvm_get_ctrl_pos().
+ * @bssid: AP's BSSID
+ * @burst_period: For EDCA based ranging: Recommended value to be sent to the
+ *	AP. Measurement periodicity In units of 100ms. ignored if
+ *	num_of_bursts_exp = 0.
+ *	For non trigger based NDP ranging, the maximum time between
+ *	measurements in units of milliseconds.
+ * @samples_per_burst: the number of FTMs pairs in single Burst (1-31);
+ * @num_of_bursts: Recommended value to be sent to the AP. 2s Exponent of
+ *	the number of measurement iterations (min 2^0 = 1, max 2^14)
+ * @sta_id: the station id of the AP. Only relevant when associated to the AP,
+ *	otherwise should be set to &IWL_MVM_INVALID_STA.
+ * @cipher: pairwise cipher suite for secured measurement.
+ *          &enum iwl_location_cipher.
+ * @hltk: HLTK to be used for secured 11az measurement
+ * @tk: TK to be used for secured 11az measurement
+ * @calib: An array of calibration values per FTM rx bandwidth.
+ *         If &IWL_INITIATOR_AP_FLAGS_USE_CALIB is set, the fw will use the
+ *         calibration value that corresponds to the rx bandwidth of the FTM
+ *         frame.
+ * @beacon_interval: beacon interval of the AP in TUs. Only required if
+ *	&IWL_INITIATOR_AP_FLAGS_TB is set.
+ * @rx_pn: the next expected PN for protected management frames Rx. LE byte
+ *	order. Only valid if &IWL_INITIATOR_AP_FLAGS_SECURED is set and sta_id
+ *	is set to &IWL_MVM_INVALID_STA.
+ * @tx_pn: the next PN to use for protected management frames Tx. LE byte
+ *	order. Only valid if &IWL_INITIATOR_AP_FLAGS_SECURED is set and sta_id
+ *	is set to &IWL_MVM_INVALID_STA.
+ * @r2i_ndp_params: parameters for R2I NDP ranging negotiation.
+ *      bits 0 - 2: max LTF repetitions
+ *      bits 3 - 5: max number of spatial streams
+ *      bits 6 - 7: max total LTFs. One of
+ *		&enum ieee80211_range_params_max_total_ltf.
+ * @i2r_ndp_params: parameters for I2R NDP ranging negotiation.
+ *      bits 0 - 2: max LTF repetitions
+ *      bits 3 - 5: max number of spatial streams (supported values are < 2)
+ *      bits 6 - 7: max total LTFs. One of
+ *		&enum ieee80211_range_params_max_total_ltf.
+ * @min_time_between_msr: For non trigger based NDP ranging, the minimum time
+ *	between measurements in units of milliseconds
+ */
+struct iwl_tof_range_req_ap_entry_v10 {
+	__le32 initiator_ap_flags;
+	u8 band;
+	u8 channel_num;
+	u8 format_bw;
+	u8 ctrl_ch_position;
+	u8 bssid[ETH_ALEN];
+	__le16 burst_period;
+	u8 samples_per_burst;
+	u8 num_of_bursts;
+	u8 sta_id;
+	u8 cipher;
+	u8 hltk[HLTK_11AZ_LEN];
+	u8 tk[TK_11AZ_LEN];
+	__le16 calib[IWL_TOF_BW_NUM];
+	__le16 beacon_interval;
+	u8 rx_pn[IEEE80211_CCMP_PN_LEN];
+	u8 tx_pn[IEEE80211_CCMP_PN_LEN];
+	u8 r2i_ndp_params;
+	u8 i2r_ndp_params;
+	__le16 min_time_between_msr;
+} __packed; /* LOCATION_RANGE_REQ_AP_ENTRY_CMD_API_S_VER_9 */
+
 /**
  * enum iwl_tof_response_mode
  * @IWL_MVM_TOF_RESPONSE_ASAP: report each AP measurement separately as soon as
@@ -1230,6 +1307,34 @@ struct iwl_tof_range_req_cmd_v13 {
 	struct iwl_tof_range_req_ap_entry_v9 ap[IWL_MVM_TOF_MAX_APS];
 } __packed; /* LOCATION_RANGE_REQ_CMD_API_S_VER_13 */
 
+/**
+ * struct iwl_tof_range_req_cmd_v14 - start measurement cmd
+ * @initiator_flags: see flags @ iwl_tof_initiator_flags
+ * @request_id: A Token incremented per request. The same Token will be
+ *		sent back in the range response
+ * @num_of_ap: Number of APs to measure (error if > IWL_MVM_TOF_MAX_APS)
+ * @range_req_bssid: ranging request BSSID
+ * @macaddr_mask: Bits set to 0 shall be copied from the MAC address template.
+ *		  Bits set to 1 shall be randomized by the UMAC
+ * @macaddr_template: MAC address template to use for non-randomized bits
+ * @req_timeout_ms: Requested timeout of the response in units of milliseconds.
+ *	This is the session time for completing the measurement.
+ * @tsf_mac_id: report the measurement start time for each ap in terms of the
+ *	TSF of this mac id. 0xff to disable TSF reporting.
+ * @ap: per-AP request data, see &struct iwl_tof_range_req_ap_entry_v10.
+ */
+struct iwl_tof_range_req_cmd_v14 {
+	__le32 initiator_flags;
+	u8 request_id;
+	u8 num_of_ap;
+	u8 range_req_bssid[ETH_ALEN];
+	u8 macaddr_mask[ETH_ALEN];
+	u8 macaddr_template[ETH_ALEN];
+	__le32 req_timeout_ms;
+	__le32 tsf_mac_id;
+	struct iwl_tof_range_req_ap_entry_v10 ap[IWL_MVM_TOF_MAX_APS];
+} __packed; /* LOCATION_RANGE_REQ_CMD_API_S_VER_13 */
+
 /*
  * enum iwl_tof_range_request_status - status of the sent request
  * @IWL_TOF_RANGE_REQUEST_STATUS_SUCCESSFUL - FW successfully received the
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/constants.h b/drivers/net/wireless/intel/iwlwifi/mvm/constants.h
index d840653cc9079..1abe9e9fd46b7 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/constants.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/constants.h
@@ -100,6 +100,7 @@
 #define IWL_MVM_FTM_INITIATOR_ALGO		IWL_TOF_ALGO_TYPE_MAX_LIKE
 #define IWL_MVM_FTM_INITIATOR_DYNACK		true
 #define IWL_MVM_FTM_LMR_FEEDBACK_TERMINATE	false
+#define IWL_MVM_FTM_TEST_INCORRECT_SAC	        false
 #define IWL_MVM_FTM_R2I_MAX_REP			7
 #define IWL_MVM_FTM_I2R_MAX_REP			7
 #define IWL_MVM_FTM_R2I_MAX_STS			1
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c
index f5bf99f7fc2ea..00d447e40cc63 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c
@@ -950,6 +950,105 @@ static int iwl_mvm_ftm_start_v13(struct iwl_mvm *mvm,
 	return iwl_mvm_ftm_send_cmd(mvm, &hcmd);
 }
 
+static int
+iwl_mvm_ftm_put_target_v10(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
+			   struct cfg80211_pmsr_request_peer *peer,
+			   struct iwl_tof_range_req_ap_entry_v10 *target)
+{
+	u32 i2r_max_sts, flags;
+	int ret;
+
+	ret = iwl_mvm_ftm_target_chandef_v2(mvm, peer, &target->channel_num,
+					    &target->format_bw,
+					    &target->ctrl_ch_position);
+	if (ret)
+		return ret;
+
+	memcpy(target->bssid, peer->addr, ETH_ALEN);
+	target->burst_period =
+		cpu_to_le16(peer->ftm.burst_period);
+	target->samples_per_burst = peer->ftm.ftms_per_burst;
+	target->num_of_bursts = peer->ftm.num_bursts_exp;
+	iwl_mvm_ftm_set_target_flags(mvm, peer, &target->initiator_ap_flags);
+	iwl_mvm_ftm_set_sta(mvm, vif, peer, &target->sta_id,
+			    &target->initiator_ap_flags);
+	iwl_mvm_ftm_set_secured_ranging(mvm, vif, target->bssid,
+					&target->cipher, target->hltk,
+					target->tk, target->rx_pn,
+					target->tx_pn,
+					&target->initiator_ap_flags);
+
+	i2r_max_sts = IWL_MVM_FTM_I2R_MAX_STS > 1 ? 1 :
+		IWL_MVM_FTM_I2R_MAX_STS;
+
+	target->r2i_ndp_params = IWL_MVM_FTM_R2I_MAX_REP |
+		(IWL_MVM_FTM_R2I_MAX_STS << IWL_LOCATION_MAX_STS_POS) |
+		(IWL_MVM_FTM_R2I_MAX_TOTAL_LTF << IWL_LOCATION_TOTAL_LTF_POS);
+	target->i2r_ndp_params = IWL_MVM_FTM_I2R_MAX_REP |
+		(i2r_max_sts << IWL_LOCATION_MAX_STS_POS) |
+		(IWL_MVM_FTM_I2R_MAX_TOTAL_LTF << IWL_LOCATION_TOTAL_LTF_POS);
+
+	if (peer->ftm.non_trigger_based) {
+		target->min_time_between_msr =
+			cpu_to_le16(IWL_MVM_FTM_NON_TB_MIN_TIME_BETWEEN_MSR);
+		target->burst_period =
+			cpu_to_le16(IWL_MVM_FTM_NON_TB_MAX_TIME_BETWEEN_MSR);
+	} else {
+		target->min_time_between_msr = cpu_to_le16(0);
+	}
+
+	target->band =
+		iwl_mvm_phy_band_from_nl80211(peer->chandef.chan->band);
+
+	/*
+	 * TODO: Beacon interval is currently unknown, so use the common value
+	 * of 100 TUs.
+	 */
+	target->beacon_interval = cpu_to_le16(100);
+
+	/*
+	 * If secure LTF is turned off, replace the flag with PMF only
+	 */
+	flags = le32_to_cpu(target->initiator_ap_flags);
+	if (flags & IWL_INITIATOR_AP_FLAGS_SECURED) {
+		if (!IWL_MVM_FTM_INITIATOR_SECURE_LTF)
+			flags &= ~IWL_INITIATOR_AP_FLAGS_SECURED;
+
+		flags |= IWL_INITIATOR_AP_FLAGS_PMF;
+		target->initiator_ap_flags = cpu_to_le32(flags);
+	}
+
+	return 0;
+}
+
+static int iwl_mvm_ftm_start_v14(struct iwl_mvm *mvm,
+				 struct ieee80211_vif *vif,
+				 struct cfg80211_pmsr_request *req)
+{
+	struct iwl_tof_range_req_cmd_v14 cmd;
+	struct iwl_host_cmd hcmd = {
+		.id = WIDE_ID(LOCATION_GROUP, TOF_RANGE_REQ_CMD),
+		.dataflags[0] = IWL_HCMD_DFL_DUP,
+		.data[0] = &cmd,
+		.len[0] = sizeof(cmd),
+	};
+	u8 i;
+	int err;
+
+	iwl_mvm_ftm_cmd_common(mvm, vif, (void *)&cmd, req);
+
+	for (i = 0; i < cmd.num_of_ap; i++) {
+		struct cfg80211_pmsr_request_peer *peer = &req->peers[i];
+		struct iwl_tof_range_req_ap_entry_v10 *target = &cmd.ap[i];
+
+		err = iwl_mvm_ftm_put_target_v10(mvm, vif, peer, target);
+		if (err)
+			return err;
+	}
+
+	return iwl_mvm_ftm_send_cmd(mvm, &hcmd);
+}
+
 int iwl_mvm_ftm_start(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 		      struct cfg80211_pmsr_request *req)
 {
@@ -968,6 +1067,9 @@ int iwl_mvm_ftm_start(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 						   IWL_FW_CMD_VER_UNKNOWN);
 
 		switch (cmd_ver) {
+		case 14:
+			err = iwl_mvm_ftm_start_v14(mvm, vif, req);
+			break;
 		case 13:
 			err = iwl_mvm_ftm_start_v13(mvm, vif, req);
 			break;
-- 
GitLab


From f1c9ba4403dd5b0abe7a9c4bbb55e09f1ee98bd0 Mon Sep 17 00:00:00 2001
From: Avraham Stern <avraham.stern@intel.com>
Date: Mon, 27 May 2024 19:06:07 +0300
Subject: [PATCH 424/950] wifi: iwlwifi: mvm: add support for version 10 of the
 responder config command

This version adds the band to the responder config command.

Signed-off-by: Avraham Stern <avraham.stern@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240527190228.af09129ebd74.I9356e2504a4c19961d4856494416ae49b36bfe62@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 .../wireless/intel/iwlwifi/fw/api/location.h  | 52 +++++++++++++++++++
 .../intel/iwlwifi/mvm/ftm-responder.c         | 15 ++++--
 2 files changed, 62 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/location.h b/drivers/net/wireless/intel/iwlwifi/fw/api/location.h
index c20bb289a6233..7c158a8dfed03 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/location.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/location.h
@@ -391,6 +391,58 @@ struct iwl_tof_responder_config_cmd_v9 {
 	__le16 max_time_between_msr;
 } __packed; /* TOF_RESPONDER_CONFIG_CMD_API_S_VER_8 */
 
+/**
+ * struct iwl_tof_responder_config_cmd - ToF AP mode
+ * @cmd_valid_fields: &iwl_tof_responder_cmd_valid_field
+ * @responder_cfg_flags: &iwl_tof_responder_cfg_flags
+ * @format_bw: bits 0 - 3: &enum iwl_location_frame_format.
+ *             bits 4 - 7: &enum iwl_location_bw.
+ * @bss_color: current AP bss_color
+ * @channel_num: current AP Channel
+ * @ctrl_ch_position: coding of the control channel position relative to
+ *	the center frequency, see iwl_mvm_get_ctrl_pos()
+ * @sta_id: index of the AP STA when in AP mode
+ * @band: current AP band
+ * @toa_offset: Artificial addition [pSec] for the ToA - to be used for debug
+ *	purposes, simulating station movement by adding various values
+ *	to this field
+ * @common_calib: XVT: common calibration value
+ * @specific_calib: XVT: specific calibration value
+ * @bssid: Current AP BSSID
+ * @r2i_ndp_params: parameters for R2I NDP.
+ *	bits 0 - 2: max number of LTF repetitions
+ *	bits 3 - 5: max number of spatial streams (supported values are < 2)
+ *	bits 6 - 7: max number of total LTFs see
+ *	&enum ieee80211_range_params_max_total_ltf
+ * @i2r_ndp_params: parameters for I2R NDP.
+ *	bits 0 - 2: max number of LTF repetitions
+ *	bits 3 - 5: max number of spatial streams
+ *	bits 6 - 7: max number of total LTFs see
+ *	&enum ieee80211_range_params_max_total_ltf
+ * @min_time_between_msr: for non trigger based NDP ranging, minimum time
+ *	between measurements in milliseconds.
+ * @max_time_between_msr: for non trigger based NDP ranging, maximum time
+ *	between measurements in milliseconds.
+ */
+struct iwl_tof_responder_config_cmd {
+	__le32 cmd_valid_fields;
+	__le32 responder_cfg_flags;
+	u8 format_bw;
+	u8 bss_color;
+	u8 channel_num;
+	u8 ctrl_ch_position;
+	u8 sta_id;
+	u8 band;
+	__le16 toa_offset;
+	__le16 common_calib;
+	__le16 specific_calib;
+	u8 bssid[ETH_ALEN];
+	u8 r2i_ndp_params;
+	u8 i2r_ndp_params;
+	__le16 min_time_between_msr;
+	__le16 max_time_between_msr;
+} __packed; /* TOF_RESPONDER_CONFIG_CMD_API_S_VER_10 */
+
 #define IWL_LCI_CIVIC_IE_MAX_SIZE	400
 
 /**
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-responder.c b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-responder.c
index 8e760300a1ab4..e4caa362f597b 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-responder.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-responder.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
  * Copyright (C) 2015-2017 Intel Deutschland GmbH
- * Copyright (C) 2018-2023 Intel Corporation
+ * Copyright (C) 2018-2024 Intel Corporation
  */
 #include <net/cfg80211.h>
 #include <linux/etherdevice.h>
@@ -88,7 +88,7 @@ static int iwl_mvm_ftm_responder_set_bw_v2(struct cfg80211_chan_def *chandef,
 
 static void
 iwl_mvm_ftm_responder_set_ndp(struct iwl_mvm *mvm,
-			      struct iwl_tof_responder_config_cmd_v9 *cmd)
+			      struct iwl_tof_responder_config_cmd *cmd)
 {
 	/* Up to 2 R2I STS are allowed on the responder */
 	u32 r2i_max_sts = IWL_MVM_FTM_R2I_MAX_STS < 2 ?
@@ -117,7 +117,7 @@ iwl_mvm_ftm_responder_cmd(struct iwl_mvm *mvm,
 	 * field interpretation is different), so the same struct can be use
 	 * for all cases.
 	 */
-	struct iwl_tof_responder_config_cmd_v9 cmd = {
+	struct iwl_tof_responder_config_cmd cmd = {
 		.channel_num = chandef->chan->hw_value,
 		.cmd_valid_fields =
 			cpu_to_le32(IWL_TOF_RESPONDER_CMD_VALID_CHAN_INFO |
@@ -131,8 +131,13 @@ iwl_mvm_ftm_responder_cmd(struct iwl_mvm *mvm,
 
 	lockdep_assert_held(&mvm->mutex);
 
+	if (cmd_ver == 10) {
+		cmd.band =
+			iwl_mvm_phy_band_from_nl80211(chandef->chan->band);
+	}
+
 	/* Use a default of bss_color=1 for now */
-	if (cmd_ver == 9) {
+	if (cmd_ver >= 9) {
 		cmd.cmd_valid_fields |=
 			cpu_to_le32(IWL_TOF_RESPONDER_CMD_VALID_BSS_COLOR |
 				    IWL_TOF_RESPONDER_CMD_VALID_MIN_MAX_TIME_BETWEEN_MSR);
@@ -148,7 +153,7 @@ iwl_mvm_ftm_responder_cmd(struct iwl_mvm *mvm,
 	}
 
 	if (cmd_ver >= 8)
-		iwl_mvm_ftm_responder_set_ndp(mvm, &cmd);
+		iwl_mvm_ftm_responder_set_ndp(mvm, (void *)&cmd);
 
 	if (cmd_ver >= 7)
 		err = iwl_mvm_ftm_responder_set_bw_v2(chandef, &cmd.format_bw,
-- 
GitLab


From d9b7531fe98a0c2a0387270557cf0a514c28dd28 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 27 May 2024 19:06:08 +0300
Subject: [PATCH 425/950] wifi: iwlwifi: mvm: use only beacon BSS load for
 active links

For active links, don't take information that may have been
received in probe responses, as those are not protected. For
inactive links, there may not be a choice.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240527190228.6947dc462fa9.I2076961211d6785c8a15b4308e0e87a413148222@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/link.c      | 14 ++++++++++++--
 .../net/wireless/intel/iwlwifi/mvm/tests/links.c   |  1 +
 2 files changed, 13 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/link.c b/drivers/net/wireless/intel/iwlwifi/mvm/link.c
index 0745229c8c375..02a475a1f1b8a 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/link.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/link.c
@@ -492,17 +492,27 @@ iwl_mvm_get_puncturing_factor(const struct ieee80211_bss_conf *link_conf)
 static unsigned int
 iwl_mvm_get_chan_load(struct ieee80211_bss_conf *link_conf)
 {
+	struct ieee80211_vif *vif = link_conf->vif;
 	struct iwl_mvm_vif_link_info *mvm_link =
 		iwl_mvm_vif_from_mac80211(link_conf->vif)->link[link_conf->link_id];
 	const struct element *bss_load_elem;
 	const struct ieee80211_bss_load_elem *bss_load;
 	enum nl80211_band band = link_conf->chanreq.oper.chan->band;
+	const struct cfg80211_bss_ies *ies;
 	unsigned int chan_load;
 	u32 chan_load_by_us;
 
 	rcu_read_lock();
-	bss_load_elem = ieee80211_bss_get_elem(link_conf->bss,
-					       WLAN_EID_QBSS_LOAD);
+	if (ieee80211_vif_link_active(vif, link_conf->link_id))
+		ies = rcu_dereference(link_conf->bss->beacon_ies);
+	else
+		ies = rcu_dereference(link_conf->bss->ies);
+
+	if (ies)
+		bss_load_elem = cfg80211_find_elem(WLAN_EID_QBSS_LOAD,
+						   ies->data, ies->len);
+	else
+		bss_load_elem = NULL;
 
 	/* If there isn't BSS Load element, take the defaults */
 	if (!bss_load_elem ||
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tests/links.c b/drivers/net/wireless/intel/iwlwifi/mvm/tests/links.c
index 6a680b5d03e02..47b8e7b64ead4 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/tests/links.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tests/links.c
@@ -208,6 +208,7 @@ static void setup_link_conf(struct kunit *test)
 	bss_load->channel_util = params->channel_util;
 
 	rcu_assign_pointer(bss.ies, ies);
+	rcu_assign_pointer(bss.beacon_ies, ies);
 }
 
 static void test_link_grading(struct kunit *test)
-- 
GitLab


From 6958c4becdf89c2877edd901458ae18ecd06169f Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Mon, 27 May 2024 19:06:09 +0300
Subject: [PATCH 426/950] wifi: iwlwifi: mvm: add debug data for MPDU counting

It is hard to debug issues of EMLSR entry/exit due to low throughput.
Add debug data.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Reviewed-by: Johannes Berg <johannes.berg@intel.com>
Link: https://msgid.link/20240527190228.77ef3c2654dc.I1796a3995da2a49dd5102d33766af1ad416dd60b@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c | 2 ++
 drivers/net/wireless/intel/iwlwifi/mvm/rx.c           | 3 +++
 drivers/net/wireless/intel/iwlwifi/mvm/sta.c          | 3 +++
 3 files changed, 8 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
index 3a1504e95b0f7..d972fcbc2cf7a 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
@@ -224,6 +224,8 @@ static void iwl_mvm_restart_mpdu_count(struct iwl_mvm *mvm,
 		mvmsta->mpdu_counters[q].window_start = jiffies;
 		spin_unlock_bh(&mvmsta->mpdu_counters[q].lock);
 	}
+
+	IWL_DEBUG_STATS(mvm, "MPDU counters are cleared\n");
 }
 
 static int iwl_mvm_esr_mode_active(struct iwl_mvm *mvm,
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rx.c b/drivers/net/wireless/intel/iwlwifi/mvm/rx.c
index 4fa8066a89b6a..b7185ddcca87e 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rx.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rx.c
@@ -1010,6 +1010,9 @@ static void iwl_mvm_update_esr_mode_tpt(struct iwl_mvm *mvm)
 		spin_unlock_bh(&mvmsta->mpdu_counters[q].lock);
 	}
 
+	IWL_DEBUG_STATS(mvm, "total Tx MPDUs: %ld. total Rx MPDUs: %ld\n",
+			total_tx, total_rx);
+
 	/* If we don't have enough MPDUs - exit EMLSR */
 	if (total_tx < IWL_MVM_ENTER_ESR_TPT_THRESH &&
 	    total_rx < IWL_MVM_ENTER_ESR_TPT_THRESH) {
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
index 20d4968d692a3..276bcccb7a388 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
@@ -4429,6 +4429,7 @@ void iwl_mvm_count_mpdu(struct iwl_mvm_sta *mvm_sta, u8 fw_sta_id, u32 count,
 			bool tx, int queue)
 {
 	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(mvm_sta->vif);
+	struct iwl_mvm *mvm = mvmvif->mvm;
 	struct iwl_mvm_tpt_counter *queue_counter;
 	struct iwl_mvm_mpdu_counter *link_counter;
 	u32 total_mpdus = 0;
@@ -4465,6 +4466,8 @@ void iwl_mvm_count_mpdu(struct iwl_mvm_sta *mvm_sta, u8 fw_sta_id, u32 count,
 		memset(queue_counter->per_link, 0,
 		       sizeof(queue_counter->per_link));
 		queue_counter->window_start = jiffies;
+
+		IWL_DEBUG_STATS(mvm, "MPDU counters are cleared\n");
 	}
 
 	for (int i = 0; i < IWL_MVM_FW_MAX_LINK_ID; i++)
-- 
GitLab


From d9196023b2c2528af96eeae9aee28f25ea112b43 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 27 May 2024 19:06:10 +0300
Subject: [PATCH 427/950] wifi: iwlwifi: mvm: show full firmware ID in debugfs

The firmware prefix is unused today, but it might still be
useful to have some information. Since the prefix will get
the intel/ directory in some cases, replace the prefix by
the full FW id which has all the information.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240527190228.527a1c72996d.If7588b854149d51605031fc9a70a650534351ef4@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
index 879640a7d46a5..2b2b5b76b5ecb 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
@@ -754,7 +754,6 @@ static ssize_t iwl_dbgfs_fw_ver_read(struct file *file, char __user *user_buf,
 	struct iwl_mvm *mvm = file->private_data;
 	char *buff, *pos, *endpos;
 	static const size_t bufsz = 1024;
-	char _fw_name_pre[FW_NAME_PRE_BUFSIZE];
 	int ret;
 
 	buff = kmalloc(bufsz, GFP_KERNEL);
@@ -764,8 +763,8 @@ static ssize_t iwl_dbgfs_fw_ver_read(struct file *file, char __user *user_buf,
 	pos = buff;
 	endpos = pos + bufsz;
 
-	pos += scnprintf(pos, endpos - pos, "FW prefix: %s\n",
-			 iwl_drv_get_fwname_pre(mvm->trans, _fw_name_pre));
+	pos += scnprintf(pos, endpos - pos, "FW id: %s\n",
+			 mvm->fwrt.fw->fw_version);
 	pos += scnprintf(pos, endpos - pos, "FW: %s\n",
 			 mvm->fwrt.fw->human_readable);
 	pos += scnprintf(pos, endpos - pos, "Device: %s\n",
-- 
GitLab


From 05ce6e9b059d8a45b97848bceccd495a98509e4a Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Mon, 27 May 2024 19:06:11 +0300
Subject: [PATCH 428/950] wifi: iwlwifi: mvm: declare band variable in the
 scope

band is not used outside of the for loop, declare it inside it.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Reviewed-by: Johannes Berg <johannes.berg@intel.com>
Link: https://msgid.link/20240527190228.b634d184980a.I9d9e71125f9a77ba4f9a33a7a2ff1e8e78e17767@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
index 5132964661c80..712dabb30acc4 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
@@ -1730,7 +1730,6 @@ iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg,
 	const u16 *nvm_chan;
 	struct ieee80211_regdomain *regd, *copy_rd;
 	struct ieee80211_reg_rule *rule;
-	enum nl80211_band band;
 	int center_freq, prev_center_freq = 0;
 	int valid_rules = 0;
 	bool new_rule;
@@ -1774,8 +1773,10 @@ iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg,
 	reg_capa = iwl_get_reg_capa(cap, resp_ver);
 
 	for (ch_idx = 0; ch_idx < num_of_ch; ch_idx++) {
+		enum nl80211_band band =
+			iwl_nl80211_band_from_channel_idx(ch_idx);
+
 		ch_flags = (u16)__le32_to_cpup(channels + ch_idx);
-		band = iwl_nl80211_band_from_channel_idx(ch_idx);
 		center_freq = ieee80211_channel_to_frequency(nvm_chan[ch_idx],
 							     band);
 		new_rule = false;
-- 
GitLab


From db680c60a89ccb36e11fa561be2583764fc8a21e Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Mon, 27 May 2024 19:06:12 +0300
Subject: [PATCH 429/950] wifi: iwlwifi: mvm: fix a wrong comment

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Reviewed-by: Johannes Berg <johannes.berg@intel.com>
Link: https://msgid.link/20240527190228.2105ffcf747d.Ic838959b812b6cb4cbb856e8c0bcaad2f46ac71b@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c
index 3b2875f2cab74..5e17559c7bd44 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c
@@ -241,7 +241,7 @@ int iwl_mvm_mld_add_bcast_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 				       IWL_MAX_TID_COUNT, &wdg_timeout);
 }
 
-/* Allocate a new station entry for the broadcast station to the given vif,
+/* Allocate a new station entry for the multicast station to the given vif,
  * and send it to the FW.
  * Note that each AP/GO mac should have its own multicast station.
  */
-- 
GitLab


From e506f8e755158560c151b1768a954e3c6c28bb34 Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Mon, 27 May 2024 19:06:13 +0300
Subject: [PATCH 430/950] wifi: iwlwifi: remove redundant prints

Upon start, the different opmodes are currently printing:
1. HW rev, which is already print by iwlwifi
2. The HW name (e.g. "Intel(R) Wi-Fi 7 BE201 320MHz")

cleanup things such as the hw rev won't be printed again, the HW name will
be printed by iwlwifi instead of each opmode.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Reviewed-by: Johannes Berg <johannes.berg@intel.com>
Reviewed-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Link: https://msgid.link/20240527190228.5c589c7abed0.I3590c4ee0ee99d1b207852c32d25d326afb327dd@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/ops.c  | 3 ---
 drivers/net/wireless/intel/iwlwifi/pcie/drv.c | 2 ++
 2 files changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
index 516decc647dda..ed9487062093d 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
@@ -1450,9 +1450,6 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 		goto out_free;
 	}
 
-	IWL_INFO(mvm, "Detected %s, REV=0x%X\n",
-		 mvm->trans->name, mvm->trans->hw_rev);
-
 	if (iwlwifi_mod_params.nvm_file)
 		mvm->nvm_file_name = iwlwifi_mod_params.nvm_file;
 	else
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
index fed2754be6802..92e48cff49de2 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
@@ -1476,6 +1476,8 @@ static int iwl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (!iwl_trans->name)
 		iwl_trans->name = iwl_trans->cfg->name;
 
+	IWL_INFO(iwl_trans, "Detected %s\n", iwl_trans->name);
+
 	if (iwl_trans->trans_cfg->mq_rx_supported) {
 		if (WARN_ON(!iwl_trans->cfg->num_rbds)) {
 			ret = -EINVAL;
-- 
GitLab


From 5860c6f59220a15bf7b6cfc674a6cbb6dc861df8 Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Mon, 27 May 2024 19:06:14 +0300
Subject: [PATCH 431/950] wifi: iwlwifi: move amsdu_size parsing to iwlwifi

The code that is parsing the amsdu_size module parameter and mapping it
to the corresponding Rx buffer size is common to all opmodes.
Move it into a function in iwlwifi, as preparation to a new op mode we
are working on.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Reviewed-by: Johannes Berg <johannes.berg@intel.com>
Link: https://msgid.link/20240527190228.a3430d32923d.Iab3c22ef0df685f72f22dafc47021f0dc7bd6fa5@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 .../wireless/intel/iwlwifi/iwl-modparams.h    | 21 ++++++++++++++++++-
 drivers/net/wireless/intel/iwlwifi/mvm/ops.c  | 19 +----------------
 2 files changed, 21 insertions(+), 19 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-modparams.h b/drivers/net/wireless/intel/iwlwifi/iwl-modparams.h
index 1cf26ab4f4887..21eabfc3ffc84 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-modparams.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-modparams.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2005-2014, 2018-2022 Intel Corporation
+ * Copyright (C) 2005-2014, 2018-2022, 2024 Intel Corporation
  */
 #ifndef __iwl_modparams_h__
 #define __iwl_modparams_h__
@@ -106,4 +106,23 @@ static inline bool iwl_enable_tx_ampdu(void)
 	return true;
 }
 
+/* Verify amsdu_size module parameter and convert it to a rxb size */
+static inline enum iwl_amsdu_size
+iwl_amsdu_size_to_rxb_size(void)
+{
+	switch (iwlwifi_mod_params.amsdu_size) {
+	case IWL_AMSDU_8K:
+		return IWL_AMSDU_8K;
+	case IWL_AMSDU_12K:
+		return IWL_AMSDU_12K;
+	default:
+		pr_err("%s: Unsupported amsdu_size: %d\n", KBUILD_MODNAME,
+		       iwlwifi_mod_params.amsdu_size);
+		fallthrough;
+	case IWL_AMSDU_DEF:
+	case IWL_AMSDU_4K:
+		return IWL_AMSDU_4K;
+	}
+}
+
 #endif /* #__iwl_modparams_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
index ed9487062093d..85178fe1b7eac 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
@@ -1373,24 +1373,7 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 	trans_cfg.no_reclaim_cmds = no_reclaim_cmds;
 	trans_cfg.n_no_reclaim_cmds = ARRAY_SIZE(no_reclaim_cmds);
 
-	switch (iwlwifi_mod_params.amsdu_size) {
-	case IWL_AMSDU_DEF:
-		trans_cfg.rx_buf_size = IWL_AMSDU_4K;
-		break;
-	case IWL_AMSDU_4K:
-		trans_cfg.rx_buf_size = IWL_AMSDU_4K;
-		break;
-	case IWL_AMSDU_8K:
-		trans_cfg.rx_buf_size = IWL_AMSDU_8K;
-		break;
-	case IWL_AMSDU_12K:
-		trans_cfg.rx_buf_size = IWL_AMSDU_12K;
-		break;
-	default:
-		pr_err("%s: Unsupported amsdu_size: %d\n", KBUILD_MODNAME,
-		       iwlwifi_mod_params.amsdu_size);
-		trans_cfg.rx_buf_size = IWL_AMSDU_4K;
-	}
+	trans_cfg.rx_buf_size = iwl_amsdu_size_to_rxb_size();
 
 	trans->wide_cmd_header = true;
 	trans_cfg.bc_table_dword =
-- 
GitLab


From fca7018d4b47504b9b23e847fd54b1f85f2371c6 Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Mon, 27 May 2024 19:06:15 +0300
Subject: [PATCH 432/950] wifi: iwlwifi: move Bz and Gl iwl_dev_info entries

The iwl_dev_info entries for these devices were incorrectly positioned
within the array, out of chronological order. Move them arround.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Reviewed-by: Johannes Berg <johannes.berg@intel.com>
Reviewed-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Link: https://msgid.link/20240527190228.a75e9a1eb86c.I003980f8ca60a96019657e396e848a07df6b92a4@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/pcie/drv.c | 52 +++++++++----------
 1 file changed, 26 insertions(+), 26 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
index 92e48cff49de2..d6da25e24818f 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
@@ -997,32 +997,6 @@ VISIBLE_IF_IWLWIFI_KUNIT const struct iwl_dev_info iwl_dev_info_table[] = {
 		      IWL_CFG_160, IWL_CFG_ANY, IWL_CFG_CDB,
 		      iwlax411_2ax_cfg_so_gf4_a0, iwl_ax411_name),
 
-/* Bz */
-/* FIXME: need to change the naming according to the actual CRF */
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_BZ, IWL_CFG_ANY,
-		      IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
-		      iwl_cfg_bz, iwl_fm_name),
-
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_BZ_W, IWL_CFG_ANY,
-		      IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
-		      iwl_cfg_bz, iwl_fm_name),
-
-/* Ga (Gl) */
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_GL, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_FM, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_320, IWL_CFG_ANY, IWL_CFG_NO_CDB,
-		      iwl_cfg_gl, iwl_gl_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_GL, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_FM, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_NO_320, IWL_CFG_ANY, IWL_CFG_NO_CDB,
-		      iwl_cfg_gl, iwl_mtp_name),
-
 /* SoF with JF2 */
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
@@ -1103,6 +1077,32 @@ VISIBLE_IF_IWLWIFI_KUNIT const struct iwl_dev_info iwl_dev_info_table[] = {
 		      IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
 		      iwlax210_2ax_cfg_so_jf_b0, iwl9462_name),
 
+/* Bz */
+/* FIXME: need to change the naming according to the actual CRF */
+	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_MAC_TYPE_BZ, IWL_CFG_ANY,
+		      IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+		      iwl_cfg_bz, iwl_fm_name),
+
+	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_MAC_TYPE_BZ_W, IWL_CFG_ANY,
+		      IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+		      iwl_cfg_bz, iwl_fm_name),
+
+/* Ga (Gl) */
+	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_MAC_TYPE_GL, IWL_CFG_ANY,
+		      IWL_CFG_RF_TYPE_FM, IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_320, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+		      iwl_cfg_gl, iwl_gl_name),
+	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_MAC_TYPE_GL, IWL_CFG_ANY,
+		      IWL_CFG_RF_TYPE_FM, IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_NO_320, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+		      iwl_cfg_gl, iwl_mtp_name),
+
 /* Sc */
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_SC, IWL_CFG_ANY,
-- 
GitLab


From 647535760a00a854c185dd4d7e6eccfea30ea0d5 Mon Sep 17 00:00:00 2001
From: Janusz Krzysztofik <janusz.krzysztofik@linux.intel.com>
Date: Mon, 6 May 2024 20:02:50 +0200
Subject: [PATCH 433/950] Revert "drm/i915: Remove extra multi-gt
 pm-references"

This reverts commit 1f33dc0c1189efb9ae19c6fc22b64dd3e26261fb.

There was a patch supposed to fix an issue of illegal attempts to free a
still active i915 VMA object when parking a GT believed to be idle,
reported by CI on 2-GT Meteor Lake.  As a solution, an extra wakeref for
a Primary GT was acquired from i915_gem_do_execbuffer() -- see commit
f56fe3e91787 ("drm/i915: Fix a VMA UAF for multi-gt platform").

However, that fix occurred insufficient -- the issue was still reported by
CI.  That wakeref was released on exit from i915_gem_do_execbuffer(), then
potentially before completion of the request and deactivation of its
associated VMAs.  Moreover, CI reports indicated that single-GT platforms
also suffered sporadically from the same race.

Since that issue was fixed by another commit f3c71b2ded5c ("drm/i915/vma:
Fix UAF on destroy against retire race"), the changes introduced by that
insufficient fix were dropped as no longer useful.  However, that series
resulted in another VMA UAF scenario now being triggered in CI.

<4> [260.290809] ------------[ cut here ]------------
<4> [260.290988] list_del corruption. prev->next should be ffff888118c5d990, but was ffff888118c5a510. (prev=ffff888118c5a510)
<4> [260.291004] WARNING: CPU: 2 PID: 1143 at lib/list_debug.c:62 __list_del_entry_valid_or_report+0xb7/0xe0
..
<4> [260.291055] CPU: 2 PID: 1143 Comm: kms_plane Not tainted 6.9.0-rc2-CI_DRM_14524-ga25d180c6853+ #1
<4> [260.291058] Hardware name: Intel Corporation Meteor Lake Client Platform/MTL-P LP5x T3 RVP, BIOS MTLPFWI1.R00.3471.D91.2401310918 01/31/2024
<4> [260.291060] RIP: 0010:__list_del_entry_valid_or_report+0xb7/0xe0
...
<4> [260.291087] Call Trace:
<4> [260.291089]  <TASK>
<4> [260.291124]  i915_vma_reopen+0x43/0x80 [i915]
<4> [260.291298]  eb_lookup_vmas+0x9cb/0xcc0 [i915]
<4> [260.291579]  i915_gem_do_execbuffer+0xc9a/0x26d0 [i915]
<4> [260.291883]  i915_gem_execbuffer2_ioctl+0x123/0x2a0 [i915]
...
<4> [260.292301]  </TASK>
...
<4> [260.292506] ---[ end trace 0000000000000000 ]---
<4> [260.292782] general protection fault, probably for non-canonical address 0x6b6b6b6b6b6b6ca3: 0000 [#1] PREEMPT SMP NOPTI
<4> [260.303575] CPU: 2 PID: 1143 Comm: kms_plane Tainted: G        W          6.9.0-rc2-CI_DRM_14524-ga25d180c6853+ #1
<4> [260.313851] Hardware name: Intel Corporation Meteor Lake Client Platform/MTL-P LP5x T3 RVP, BIOS MTLPFWI1.R00.3471.D91.2401310918 01/31/2024
<4> [260.326359] RIP: 0010:eb_validate_vmas+0x114/0xd80 [i915]
...
<4> [260.428756] Call Trace:
<4> [260.431192]  <TASK>
<4> [639.283393]  i915_gem_do_execbuffer+0xd05/0x26d0 [i915]
<4> [639.305245]  i915_gem_execbuffer2_ioctl+0x123/0x2a0 [i915]
...
<4> [639.411134]  </TASK>
...
<4> [639.449979] ---[ end trace 0000000000000000 ]---

We defer actually closing, unbinding and destroying a VMA until next idle
point, or until the object is freed in the meantime.  By postponing the
unbind, we allow for the VMA to be reopened by the client, avoiding the
work required to rebind the VMA.

Starting from commit b0647a5e79b1 ("drm/i915: Avoid live-lock with
i915_vma_parked()"), we assume that as long as a GT is held idle, no VMA
would be reopened while we destroy them.  That assumption is no longer
true in multi-GT configurations, where a VMA we reopen may be handled by a
GT different from the one that we already keep active via its engine while
we set up an execbuf request.

Restoring the extra GT0 PM wakeref removed from i915_gem_do_execbuffer()
processing path seems to fix this issue.

Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/10608
Signed-off-by: Janusz Krzysztofik <janusz.krzysztofik@linux.intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Nirmoy Das <nirmoy.das@linux.intel.com>
Reviewed-by: Nirmoy Das <nirmoy.das@linux.intel.com>
Fixes: 1f33dc0c1189 ("drm/i915: Remove extra multi-gt pm-references")
Link: https://patchwork.freedesktop.org/patch/msgid/20240506180253.96858-2-janusz.krzysztofik@linux.intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
(cherry picked from commit 749670a58d935303ad1ce529acc73f12de25832e)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 42619fc05de48..090724fa766c9 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -255,6 +255,7 @@ struct i915_execbuffer {
 	struct intel_context *context; /* logical state for the request */
 	struct i915_gem_context *gem_context; /** caller's context */
 	intel_wakeref_t wakeref;
+	intel_wakeref_t wakeref_gt0;
 
 	/** our requests to build */
 	struct i915_request *requests[MAX_ENGINE_INSTANCE + 1];
@@ -2685,6 +2686,7 @@ static int
 eb_select_engine(struct i915_execbuffer *eb)
 {
 	struct intel_context *ce, *child;
+	struct intel_gt *gt;
 	unsigned int idx;
 	int err;
 
@@ -2708,10 +2710,17 @@ eb_select_engine(struct i915_execbuffer *eb)
 		}
 	}
 	eb->num_batches = ce->parallel.number_children + 1;
+	gt = ce->engine->gt;
 
 	for_each_child(ce, child)
 		intel_context_get(child);
 	eb->wakeref = intel_gt_pm_get(ce->engine->gt);
+	/*
+	 * Keep GT0 active on MTL so that i915_vma_parked() doesn't
+	 * free VMAs while execbuf ioctl is validating VMAs.
+	 */
+	if (gt->info.id)
+		eb->wakeref_gt0 = intel_gt_pm_get(to_gt(gt->i915));
 
 	if (!test_bit(CONTEXT_ALLOC_BIT, &ce->flags)) {
 		err = intel_context_alloc_state(ce);
@@ -2750,6 +2759,9 @@ eb_select_engine(struct i915_execbuffer *eb)
 	return err;
 
 err:
+	if (gt->info.id)
+		intel_gt_pm_put(to_gt(gt->i915), eb->wakeref_gt0);
+
 	intel_gt_pm_put(ce->engine->gt, eb->wakeref);
 	for_each_child(ce, child)
 		intel_context_put(child);
@@ -2763,6 +2775,12 @@ eb_put_engine(struct i915_execbuffer *eb)
 	struct intel_context *child;
 
 	i915_vm_put(eb->context->vm);
+	/*
+	 * This works in conjunction with eb_select_engine() to prevent
+	 * i915_vma_parked() from interfering while execbuf validates vmas.
+	 */
+	if (eb->gt->info.id)
+		intel_gt_pm_put(to_gt(eb->gt->i915), eb->wakeref_gt0);
 	intel_gt_pm_put(eb->context->engine->gt, eb->wakeref);
 	for_each_child(eb->context, child)
 		intel_context_put(child);
-- 
GitLab


From 70cb9188ffc75e643debf292fcddff36c9dbd4ae Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 23 Apr 2024 18:23:10 +0200
Subject: [PATCH 434/950] drm/i915/gt: Disarm breadcrumbs if engines are
 already idle

The breadcrumbs use a GT wakeref for guarding the interrupt, but are
disarmed during release of the engine wakeref. This leaves a hole where
we may attach a breadcrumb just as the engine is parking (after it has
parked its breadcrumbs), execute the irq worker with some signalers still
attached, but never be woken again.

That issue manifests itself in CI with IGT runner timeouts while tests
are waiting indefinitely for release of all GT wakerefs.

<6> [209.151778] i915: Running live_engine_pm_selftests/live_engine_busy_stats
<7> [209.231628] i915 0000:00:02.0: [drm:intel_power_well_disable [i915]] disabling PW_5
<7> [209.231816] i915 0000:00:02.0: [drm:intel_power_well_disable [i915]] disabling PW_4
<7> [209.231944] i915 0000:00:02.0: [drm:intel_power_well_disable [i915]] disabling PW_3
<7> [209.232056] i915 0000:00:02.0: [drm:intel_power_well_disable [i915]] disabling PW_2
<7> [209.232166] i915 0000:00:02.0: [drm:intel_power_well_disable [i915]] disabling DC_off
<7> [209.232270] i915 0000:00:02.0: [drm:skl_enable_dc6 [i915]] Enabling DC6
<7> [209.232368] i915 0000:00:02.0: [drm:gen9_set_dc_state.part.0 [i915]] Setting DC state from 00 to 02
<4> [299.356116] [IGT] Inactivity timeout exceeded. Killing the current test with SIGQUIT.
...
<6> [299.356526] sysrq: Show State
...
<6> [299.373964] task:i915_selftest   state:D stack:11784 pid:5578  tgid:5578  ppid:873    flags:0x00004002
<6> [299.373967] Call Trace:
<6> [299.373968]  <TASK>
<6> [299.373970]  __schedule+0x3bb/0xda0
<6> [299.373974]  schedule+0x41/0x110
<6> [299.373976]  intel_wakeref_wait_for_idle+0x82/0x100 [i915]
<6> [299.374083]  ? __pfx_var_wake_function+0x10/0x10
<6> [299.374087]  live_engine_busy_stats+0x9b/0x500 [i915]
<6> [299.374173]  __i915_subtests+0xbe/0x240 [i915]
<6> [299.374277]  ? __pfx___intel_gt_live_setup+0x10/0x10 [i915]
<6> [299.374369]  ? __pfx___intel_gt_live_teardown+0x10/0x10 [i915]
<6> [299.374456]  intel_engine_live_selftests+0x1c/0x30 [i915]
<6> [299.374547]  __run_selftests+0xbb/0x190 [i915]
<6> [299.374635]  i915_live_selftests+0x4b/0x90 [i915]
<6> [299.374717]  i915_pci_probe+0x10d/0x210 [i915]

At the end of the interrupt worker, if there are no more engines awake,
disarm the breadcrumb and go to sleep.

Fixes: 9d5612ca165a ("drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission")
Closes: https://gitlab.freedesktop.org/drm/intel/issues/10026
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Andrzej Hajda <andrzej.hajda@intel.com>
Cc: <stable@vger.kernel.org> # v5.12+
Signed-off-by: Janusz Krzysztofik <janusz.krzysztofik@linux.intel.com>
Acked-by: Nirmoy Das <nirmoy.das@intel.com>
Reviewed-by: Andrzej Hajda <andrzej.hajda@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240423165505.465734-2-janusz.krzysztofik@linux.intel.com
(cherry picked from commit fbad43eccae5cb14594195c20113369aabaa22b5)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/gt/intel_breadcrumbs.c | 15 +++++++--------
 1 file changed, 7 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
index d650beb8ed22f..20b9b04ec1e0b 100644
--- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
+++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
@@ -263,8 +263,13 @@ static void signal_irq_work(struct irq_work *work)
 		i915_request_put(rq);
 	}
 
+	/* Lazy irq enabling after HW submission */
 	if (!READ_ONCE(b->irq_armed) && !list_empty(&b->signalers))
 		intel_breadcrumbs_arm_irq(b);
+
+	/* And confirm that we still want irqs enabled before we yield */
+	if (READ_ONCE(b->irq_armed) && !atomic_read(&b->active))
+		intel_breadcrumbs_disarm_irq(b);
 }
 
 struct intel_breadcrumbs *
@@ -315,13 +320,7 @@ void __intel_breadcrumbs_park(struct intel_breadcrumbs *b)
 		return;
 
 	/* Kick the work once more to drain the signalers, and disarm the irq */
-	irq_work_sync(&b->irq_work);
-	while (READ_ONCE(b->irq_armed) && !atomic_read(&b->active)) {
-		local_irq_disable();
-		signal_irq_work(&b->irq_work);
-		local_irq_enable();
-		cond_resched();
-	}
+	irq_work_queue(&b->irq_work);
 }
 
 void intel_breadcrumbs_free(struct kref *kref)
@@ -404,7 +403,7 @@ static void insert_breadcrumb(struct i915_request *rq)
 	 * the request as it may have completed and raised the interrupt as
 	 * we were attaching it into the lists.
 	 */
-	if (!b->irq_armed || __i915_request_is_complete(rq))
+	if (!READ_ONCE(b->irq_armed) || __i915_request_is_complete(rq))
 		irq_work_queue(&b->irq_work);
 }
 
-- 
GitLab


From d4f36db62396b73bed383c0b6e48d36278cafa78 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 30 Apr 2024 09:48:09 -0700
Subject: [PATCH 435/950] drm/i915/guc: avoid FIELD_PREP warning

With gcc-7 and earlier, there are lots of warnings like

In file included from <command-line>:0:0:
In function '__guc_context_policy_add_priority.isra.66',
    inlined from '__guc_context_set_prio.isra.67' at drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c:3292:3,
    inlined from 'guc_context_set_prio' at drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c:3320:2:
include/linux/compiler_types.h:399:38: error: call to '__compiletime_assert_631' declared with attribute error: FIELD_PREP: mask is not constant
  _compiletime_assert(condition, msg, __compiletime_assert_, __COUNTER__)
                                      ^
...
drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c:2422:3: note: in expansion of macro 'FIELD_PREP'
   FIELD_PREP(GUC_KLV_0_KEY, GUC_CONTEXT_POLICIES_KLV_ID_##id) | \
   ^~~~~~~~~~

Make sure that GUC_KLV_0_KEY is an unsigned value to avoid the warning.

Fixes: 77b6f79df66e ("drm/i915/guc: Update to GuC version 69.0.3")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Signed-off-by: Julia Filipchuk <julia.filipchuk@intel.com>
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240430164809.482131-1-julia.filipchuk@intel.com
(cherry picked from commit 364e039827ef628c650c21c1afe1c54d9c3296d9)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/gt/uc/abi/guc_klvs_abi.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/uc/abi/guc_klvs_abi.h b/drivers/gpu/drm/i915/gt/uc/abi/guc_klvs_abi.h
index bebf28e3c4794..525587cfe1af9 100644
--- a/drivers/gpu/drm/i915/gt/uc/abi/guc_klvs_abi.h
+++ b/drivers/gpu/drm/i915/gt/uc/abi/guc_klvs_abi.h
@@ -29,9 +29,9 @@
  */
 
 #define GUC_KLV_LEN_MIN				1u
-#define GUC_KLV_0_KEY				(0xffff << 16)
-#define GUC_KLV_0_LEN				(0xffff << 0)
-#define GUC_KLV_n_VALUE				(0xffffffff << 0)
+#define GUC_KLV_0_KEY				(0xffffu << 16)
+#define GUC_KLV_0_LEN				(0xffffu << 0)
+#define GUC_KLV_n_VALUE				(0xffffffffu << 0)
 
 /**
  * DOC: GuC Self Config KLVs
-- 
GitLab


From 33defcacd207196a6b35857087e6335590adad62 Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Date: Tue, 28 May 2024 22:39:18 +0300
Subject: [PATCH 436/950] drm/panel/lg-sw43408: select
 CONFIG_DRM_DISPLAY_DP_HELPER

This panel driver uses DSC PPS functions and as such depends on the
DRM_DISPLAY_DP_HELPER. Select this symbol to make required functions
available to the driver.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202404200800.kYsRYyli-lkp@intel.com/
Fixes: 069a6c0e94f9 ("drm: panel: Add LG sw43408 panel driver")
Reviewed-by: Neil Armstrong <neil.armstrong@linaro.org>
Reviewed-by: Marijn Suijten <marijn.suijten@somainline.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20240528-panel-sw43408-fix-v4-1-330b42445bcc@linaro.org
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
---
 drivers/gpu/drm/panel/Kconfig | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/panel/Kconfig b/drivers/gpu/drm/panel/Kconfig
index 982324ef5a41b..2ae0eb0638f32 100644
--- a/drivers/gpu/drm/panel/Kconfig
+++ b/drivers/gpu/drm/panel/Kconfig
@@ -340,6 +340,8 @@ config DRM_PANEL_LG_SW43408
 	depends on OF
 	depends on DRM_MIPI_DSI
 	depends on BACKLIGHT_CLASS_DEVICE
+	select DRM_DISPLAY_DP_HELPER
+	select DRM_DISPLAY_HELPER
 	help
 	  Say Y here if you want to enable support for LG sw43408 panel.
 	  The panel has a 1080x2160@60Hz resolution and uses 24 bit RGB per
-- 
GitLab


From 659a3062c705753a9ec6fd28a4c67ee4254f9584 Mon Sep 17 00:00:00 2001
From: Nirmoy Das <nirmoy.das@intel.com>
Date: Thu, 16 May 2024 17:14:03 +0200
Subject: [PATCH 437/950] drm/i915/selftests: Set always_coherent to false when
 reading from CPU

Commit 8d4ba9fc1c6c ("drm/i915/selftests: Pick correct caching mode.")
was not complete  as for non LLC  sharing platforms cpu read can happen
from LLC which probably doesn't have the latest changes made by GPU.

Cc: Andi Shyti <andi.shyti@linux.intel.com>
Cc: Janusz Krzysztofik <janusz.krzysztofik@linux.intel.com>
Cc: Jonathan Cavitt <jonathan.cavitt@intel.com>
Fixes: 8d4ba9fc1c6c ("drm/i915/selftests: Pick correct caching mode.")
Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240516151403.2875-1-nirmoy.das@intel.com
Signed-off-by: Nirmoy Das <nirmoy.das@intel.com>
(cherry picked from commit 007ed70831426d4cc108d879d688de6b8e3e6d45)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c
index 65a931ea80e9b..3527b8f446fe3 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c
@@ -196,7 +196,7 @@ static int verify_access(struct drm_i915_private *i915,
 	if (err)
 		goto out_file;
 
-	mode = intel_gt_coherent_map_type(to_gt(i915), native_obj, true);
+	mode = intel_gt_coherent_map_type(to_gt(i915), native_obj, false);
 	vaddr = i915_gem_object_pin_map_unlocked(native_obj, mode);
 	if (IS_ERR(vaddr)) {
 		err = PTR_ERR(vaddr);
-- 
GitLab


From 8c318cb70c88aa02068db7518e852b909c9b400f Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Date: Tue, 28 May 2024 22:39:19 +0300
Subject: [PATCH 438/950] drm/panel/lg-sw43408: mark sw43408_backlight_ops as
 static

Fix sparse warning regarding symbol 'sw43408_backlight_ops' not being
declared.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202404200739.hbWZvOhR-lkp@intel.com/
Reviewed-by: Neil Armstrong <neil.armstrong@linaro.org>
Fixes: 069a6c0e94f9 ("drm: panel: Add LG sw43408 panel driver")
Reviewed-by: Marijn Suijten <marijn.suijten@somainline.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20240528-panel-sw43408-fix-v4-2-330b42445bcc@linaro.org
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
---
 drivers/gpu/drm/panel/panel-lg-sw43408.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/panel/panel-lg-sw43408.c b/drivers/gpu/drm/panel/panel-lg-sw43408.c
index 115f4702d59f7..2b3a73696dcec 100644
--- a/drivers/gpu/drm/panel/panel-lg-sw43408.c
+++ b/drivers/gpu/drm/panel/panel-lg-sw43408.c
@@ -182,7 +182,7 @@ static int sw43408_backlight_update_status(struct backlight_device *bl)
 	return mipi_dsi_dcs_set_display_brightness_large(dsi, brightness);
 }
 
-const struct backlight_ops sw43408_backlight_ops = {
+static const struct backlight_ops sw43408_backlight_ops = {
 	.update_status = sw43408_backlight_update_status,
 };
 
-- 
GitLab


From ee01b6a386eaf9984b58a2476e8f531149679da9 Mon Sep 17 00:00:00 2001
From: Andi Shyti <andi.shyti@linux.intel.com>
Date: Fri, 17 May 2024 11:06:16 +0200
Subject: [PATCH 439/950] drm/i915/gt: Fix CCS id's calculation for CCS mode
 setting

The whole point of the previous fixes has been to change the CCS
hardware configuration to generate only one stream available to
the compute users. We did this by changing the info.engine_mask
that is set during device probe, reset during the detection of
the fused engines, and finally reset again when choosing the CCS
mode.

We can't use the engine_mask variable anymore, as with the
current configuration, it imposes only one CCS no matter what the
hardware configuration is.

Before changing the engine_mask for the third time, save it and
use it for calculating the CCS mode.

After the previous changes, the user reported a performance drop
to around 1/4. We have tested that the compute operations, with
the current patch, have improved by the same factor.

Fixes: 6db31251bb26 ("drm/i915/gt: Enable only one CCS for compute workload")
Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
Cc: Chris Wilson <chris.p.wilson@linux.intel.com>
Cc: Gnattu OC <gnattuoc@me.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Tested-by: Jian Ye <jian.ye@intel.com>
Reviewed-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Tested-by: Gnattu OC <gnattuoc@me.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240517090616.242529-1-andi.shyti@linux.intel.com
(cherry picked from commit a09d2327a9ba8e3f5be238bc1b7ca2809255b464)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/gt/intel_engine_cs.c   | 6 ++++++
 drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.c | 2 +-
 drivers/gpu/drm/i915/gt/intel_gt_types.h    | 8 ++++++++
 3 files changed, 15 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 5c8e9ee3b0083..3b740ca250009 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -885,6 +885,12 @@ static intel_engine_mask_t init_engine_mask(struct intel_gt *gt)
 	if (IS_DG2(gt->i915)) {
 		u8 first_ccs = __ffs(CCS_MASK(gt));
 
+		/*
+		 * Store the number of active cslices before
+		 * changing the CCS engine configuration
+		 */
+		gt->ccs.cslices = CCS_MASK(gt);
+
 		/* Mask off all the CCS engine */
 		info->engine_mask &= ~GENMASK(CCS3, CCS0);
 		/* Put back in the first CCS engine */
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.c b/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.c
index 99b71bb7da0a6..3c62a44e9106c 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.c
@@ -19,7 +19,7 @@ unsigned int intel_gt_apply_ccs_mode(struct intel_gt *gt)
 
 	/* Build the value for the fixed CCS load balancing */
 	for (cslice = 0; cslice < I915_MAX_CCS; cslice++) {
-		if (CCS_MASK(gt) & BIT(cslice))
+		if (gt->ccs.cslices & BIT(cslice))
 			/*
 			 * If available, assign the cslice
 			 * to the first available engine...
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_types.h b/drivers/gpu/drm/i915/gt/intel_gt_types.h
index def7dd0eb6f19..cfdd2ad5e9549 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_types.h
@@ -207,6 +207,14 @@ struct intel_gt {
 					    [MAX_ENGINE_INSTANCE + 1];
 	enum intel_submission_method submission_method;
 
+	struct {
+		/*
+		 * Mask of the non fused CCS slices
+		 * to be used for the load balancing
+		 */
+		intel_engine_mask_t cslices;
+	} ccs;
+
 	/*
 	 * Default address space (either GGTT or ppGTT depending on arch).
 	 *
-- 
GitLab


From 43e2b37e2ab660c3565d4cff27922bc70e79c3f1 Mon Sep 17 00:00:00 2001
From: Vidya Srinivas <vidya.srinivas@intel.com>
Date: Mon, 20 May 2024 22:26:34 +0530
Subject: [PATCH 440/950] drm/i915/dpt: Make DPT object unshrinkable
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In some scenarios, the DPT object gets shrunk but
the actual framebuffer did not and thus its still
there on the DPT's vm->bound_list. Then it tries to
rewrite the PTEs via a stale CPU mapping. This causes panic.

Cc: stable@vger.kernel.org
Reported-by: Shawn Lee <shawn.c.lee@intel.com>
Fixes: 0dc987b699ce ("drm/i915/display: Add smem fallback allocation for dpt")
Signed-off-by: Vidya Srinivas <vidya.srinivas@intel.com>
[vsyrjala: Add TODO comment]
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240520165634.1162470-1-vidya.srinivas@intel.com
(cherry picked from commit 51064d471c53dcc8eddd2333c3f1c1d9131ba36c)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/gem/i915_gem_object.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h
index 3560a062d2872..5d7446a48ae79 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h
@@ -284,7 +284,9 @@ bool i915_gem_object_has_iomem(const struct drm_i915_gem_object *obj);
 static inline bool
 i915_gem_object_is_shrinkable(const struct drm_i915_gem_object *obj)
 {
-	return i915_gem_object_type_has(obj, I915_GEM_OBJECT_IS_SHRINKABLE);
+	/* TODO: make DPT shrinkable when it has no bound vmas */
+	return i915_gem_object_type_has(obj, I915_GEM_OBJECT_IS_SHRINKABLE) &&
+		!obj->is_dpt;
 }
 
 static inline bool
-- 
GitLab


From 75800e2e4203ea83bbc9d4f63ad97ea582244a08 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Tue, 21 May 2024 17:30:22 +0300
Subject: [PATCH 441/950] drm/i915: Fix audio component initialization

After registering the audio component in i915_audio_component_init()
the audio driver may call i915_audio_component_get_power() via the
component ops. This could program AUD_FREQ_CNTRL with an uninitialized
value if the latter function is called before display.audio.freq_cntrl
gets initialized. The get_power() function also does a modeset which in
the above case happens too early before the initialization step and
triggers the

"Reject display access from task"

error message added by the Fixes: commit below.

Fix the above issue by registering the audio component only after the
initialization step.

Fixes: 87c1694533c9 ("drm/i915: save AUD_FREQ_CNTRL state at audio domain suspend")
Closes: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/10291
Cc: stable@vger.kernel.org # v5.5+
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240521143022.3784539-1-imre.deak@intel.com
(cherry picked from commit fdd0b80172758ce284f19fa8a26d90c61e4371d2)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/intel_audio.c    | 32 ++++++++++++-------
 drivers/gpu/drm/i915/display/intel_audio.h    |  1 +
 .../drm/i915/display/intel_display_driver.c   |  2 ++
 3 files changed, 24 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_audio.c b/drivers/gpu/drm/i915/display/intel_audio.c
index ed81e1466c4b5..40e7d862675ee 100644
--- a/drivers/gpu/drm/i915/display/intel_audio.c
+++ b/drivers/gpu/drm/i915/display/intel_audio.c
@@ -1252,17 +1252,6 @@ static const struct component_ops i915_audio_component_bind_ops = {
 static void i915_audio_component_init(struct drm_i915_private *i915)
 {
 	u32 aud_freq, aud_freq_init;
-	int ret;
-
-	ret = component_add_typed(i915->drm.dev,
-				  &i915_audio_component_bind_ops,
-				  I915_COMPONENT_AUDIO);
-	if (ret < 0) {
-		drm_err(&i915->drm,
-			"failed to add audio component (%d)\n", ret);
-		/* continue with reduced functionality */
-		return;
-	}
 
 	if (DISPLAY_VER(i915) >= 9) {
 		aud_freq_init = intel_de_read(i915, AUD_FREQ_CNTRL);
@@ -1285,6 +1274,21 @@ static void i915_audio_component_init(struct drm_i915_private *i915)
 
 	/* init with current cdclk */
 	intel_audio_cdclk_change_post(i915);
+}
+
+static void i915_audio_component_register(struct drm_i915_private *i915)
+{
+	int ret;
+
+	ret = component_add_typed(i915->drm.dev,
+				  &i915_audio_component_bind_ops,
+				  I915_COMPONENT_AUDIO);
+	if (ret < 0) {
+		drm_err(&i915->drm,
+			"failed to add audio component (%d)\n", ret);
+		/* continue with reduced functionality */
+		return;
+	}
 
 	i915->display.audio.component_registered = true;
 }
@@ -1317,6 +1321,12 @@ void intel_audio_init(struct drm_i915_private *i915)
 		i915_audio_component_init(i915);
 }
 
+void intel_audio_register(struct drm_i915_private *i915)
+{
+	if (!i915->display.audio.lpe.platdev)
+		i915_audio_component_register(i915);
+}
+
 /**
  * intel_audio_deinit() - deinitialize the audio driver
  * @i915: the i915 drm device private data
diff --git a/drivers/gpu/drm/i915/display/intel_audio.h b/drivers/gpu/drm/i915/display/intel_audio.h
index 9327954b801e5..576c061d72a45 100644
--- a/drivers/gpu/drm/i915/display/intel_audio.h
+++ b/drivers/gpu/drm/i915/display/intel_audio.h
@@ -28,6 +28,7 @@ void intel_audio_codec_get_config(struct intel_encoder *encoder,
 void intel_audio_cdclk_change_pre(struct drm_i915_private *dev_priv);
 void intel_audio_cdclk_change_post(struct drm_i915_private *dev_priv);
 void intel_audio_init(struct drm_i915_private *dev_priv);
+void intel_audio_register(struct drm_i915_private *i915);
 void intel_audio_deinit(struct drm_i915_private *dev_priv);
 void intel_audio_sdp_split_update(const struct intel_crtc_state *crtc_state);
 
diff --git a/drivers/gpu/drm/i915/display/intel_display_driver.c b/drivers/gpu/drm/i915/display/intel_display_driver.c
index 89bd032ed995e..794b4af380558 100644
--- a/drivers/gpu/drm/i915/display/intel_display_driver.c
+++ b/drivers/gpu/drm/i915/display/intel_display_driver.c
@@ -540,6 +540,8 @@ void intel_display_driver_register(struct drm_i915_private *i915)
 
 	intel_display_driver_enable_user_access(i915);
 
+	intel_audio_register(i915);
+
 	intel_display_debugfs_register(i915);
 
 	/*
-- 
GitLab


From a0ca76e5b7d550fcd74753d5fdaaf23f1a9bfdb4 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Thu, 23 May 2024 12:11:40 +0200
Subject: [PATCH 442/950] wifi: mac80211: check
 ieee80211_bss_info_change_notify() against MLD

It's not valid to call ieee80211_bss_info_change_notify() with
an sdata that's an MLD, remove the FIXME comment (it's not true)
and add a warning.

Reviewed-by: Miriam Rachel Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240523121140.97a589b13d24.I61988788d81fb3cf97a490dfd3167f67a141d1fd@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 4eaea0a9975b4..40fbf397ce740 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -337,6 +337,8 @@ void ieee80211_bss_info_change_notify(struct ieee80211_sub_if_data *sdata,
 
 	might_sleep();
 
+	WARN_ON_ONCE(ieee80211_vif_is_mld(&sdata->vif));
+
 	if (!changed || sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
 		return;
 
@@ -369,7 +371,6 @@ void ieee80211_bss_info_change_notify(struct ieee80211_sub_if_data *sdata,
 	if (changed & ~BSS_CHANGED_VIF_CFG_FLAGS) {
 		u64 ch = changed & ~BSS_CHANGED_VIF_CFG_FLAGS;
 
-		/* FIXME: should be for each link */
 		trace_drv_link_info_changed(local, sdata, &sdata->vif.bss_conf,
 					    changed);
 		if (local->ops->link_info_changed)
-- 
GitLab


From 6322e0e75a01d30b914fa87470ad00d8db844f72 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Thu, 23 May 2024 12:03:52 +0200
Subject: [PATCH 443/950] wifi: mac80211: handle HW restart during ROC

If we have a HW restart in the middle of a ROC period,
then there are two cases:
 - if it's a software ROC, we really don't need to do
   anything, since the ROC work will still be queued
   and will run later, albeit with the interruption
   due to the restart;
 - if it's a hardware ROC, then it may have begun or
   not, if it did begin already we can only remove it
   and tell userspace about that.

In both cases, this fixes the warning that would appear
in ieee80211_start_next_roc() in this case.

In the case of some drivers such as iwlwifi, the part of
restarting is never going to happen since the driver will
cancel the ROC, but flushing the work to ensure nothing
is pending here will also result in no longer being able
to trigger the warning in this case.

Reviewed-by: Miriam Rachel Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240523120352.f1924b5411ea.Ifc02a45a5ce23868dc7e428bad8d0e6996dd10f4@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/ieee80211_i.h |  1 +
 net/mac80211/offchannel.c  | 35 ++++++++++++++++++++++++++++++++++-
 net/mac80211/util.c        |  3 +--
 3 files changed, 36 insertions(+), 3 deletions(-)

diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 76965d64a0fae..3fd7b1adbfab1 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -1978,6 +1978,7 @@ void ieee80211_offchannel_stop_vifs(struct ieee80211_local *local);
 void ieee80211_offchannel_return(struct ieee80211_local *local);
 void ieee80211_roc_setup(struct ieee80211_local *local);
 void ieee80211_start_next_roc(struct ieee80211_local *local);
+void ieee80211_reconfig_roc(struct ieee80211_local *local);
 void ieee80211_roc_purge(struct ieee80211_local *local,
 			 struct ieee80211_sub_if_data *sdata);
 int ieee80211_remain_on_channel(struct wiphy *wiphy, struct wireless_dev *wdev,
diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c
index 65e1e9e971fd6..28d03196ef75a 100644
--- a/net/mac80211/offchannel.c
+++ b/net/mac80211/offchannel.c
@@ -8,7 +8,7 @@
  * Copyright 2006-2007	Jiri Benc <jbenc@suse.cz>
  * Copyright 2007, Michael Wu <flamingice@sourmilk.net>
  * Copyright 2009	Johannes Berg <johannes@sipsolutions.net>
- * Copyright (C) 2019, 2022-2023 Intel Corporation
+ * Copyright (C) 2019, 2022-2024 Intel Corporation
  */
 #include <linux/export.h>
 #include <net/mac80211.h>
@@ -413,6 +413,39 @@ void ieee80211_start_next_roc(struct ieee80211_local *local)
 	}
 }
 
+void ieee80211_reconfig_roc(struct ieee80211_local *local)
+{
+	struct ieee80211_roc_work *roc, *tmp;
+
+	/*
+	 * In the software implementation can just continue with the
+	 * interruption due to reconfig, roc_work is still queued if
+	 * needed.
+	 */
+	if (!local->ops->remain_on_channel)
+		return;
+
+	/* flush work so nothing from the driver is still pending */
+	wiphy_work_flush(local->hw.wiphy, &local->hw_roc_start);
+	wiphy_work_flush(local->hw.wiphy, &local->hw_roc_done);
+
+	list_for_each_entry_safe(roc, tmp, &local->roc_list, list) {
+		if (!roc->started)
+			break;
+
+		if (!roc->hw_begun) {
+			/* it didn't start in HW yet, so we can restart it */
+			roc->started = false;
+			continue;
+		}
+
+		/* otherwise destroy it and tell userspace */
+		ieee80211_roc_notify_destroy(roc);
+	}
+
+	ieee80211_start_next_roc(local);
+}
+
 static void __ieee80211_roc_work(struct ieee80211_local *local)
 {
 	struct ieee80211_roc_work *roc;
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 43625ca87d5e8..927f752a02093 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -2175,8 +2175,7 @@ int ieee80211_reconfig(struct ieee80211_local *local)
 		local->in_reconfig = false;
 		barrier();
 
-		/* Restart deferred ROCs */
-		ieee80211_start_next_roc(local);
+		ieee80211_reconfig_roc(local);
 
 		/* Requeue all works */
 		list_for_each_entry(sdata, &local->interfaces, list)
-- 
GitLab


From 8526f8c877baf3f9e678b31fd7d1066b776775cc Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Thu, 23 May 2024 12:02:13 +0200
Subject: [PATCH 444/950] wifi: nl80211: clean up coalescing rule handling

There's no need to allocate a tiny struct and then
an array again, just allocate the two together and
use __counted_by(). Also unify the freeing.

Reviewed-by: Miriam Rachel Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240523120213.48a40cfb96f9.Ia02bf8f8fefbf533c64c5fa26175848d4a3a7899@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h |  2 +-
 net/wireless/core.c    |  3 ++-
 net/wireless/nl80211.c | 47 ++++++++++++++----------------------------
 net/wireless/nl80211.h |  4 ++--
 4 files changed, 21 insertions(+), 35 deletions(-)

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index d79180bec7a1f..5da9bb0ac6a47 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -3566,8 +3566,8 @@ struct cfg80211_coalesce_rules {
  * @n_rules: number of rules
  */
 struct cfg80211_coalesce {
-	struct cfg80211_coalesce_rules *rules;
 	int n_rules;
+	struct cfg80211_coalesce_rules rules[] __counted_by(n_rules);
 };
 
 /**
diff --git a/net/wireless/core.c b/net/wireless/core.c
index 61f7cd8a8e9ce..7c35349b95966 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -1145,7 +1145,8 @@ void wiphy_unregister(struct wiphy *wiphy)
 	flush_work(&rdev->background_cac_abort_wk);
 
 	cfg80211_rdev_free_wowlan(rdev);
-	cfg80211_rdev_free_coalesce(rdev);
+	cfg80211_free_coalesce(rdev->coalesce);
+	rdev->coalesce = NULL;
 }
 EXPORT_SYMBOL(wiphy_unregister);
 
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 6ba988a6f5a22..8ff5f79d446ae 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -13897,9 +13897,8 @@ nla_put_failure:
 	return -ENOBUFS;
 }
 
-void cfg80211_rdev_free_coalesce(struct cfg80211_registered_device *rdev)
+void cfg80211_free_coalesce(struct cfg80211_coalesce *coalesce)
 {
-	struct cfg80211_coalesce *coalesce = rdev->coalesce;
 	int i, j;
 	struct cfg80211_coalesce_rules *rule;
 
@@ -13908,13 +13907,13 @@ void cfg80211_rdev_free_coalesce(struct cfg80211_registered_device *rdev)
 
 	for (i = 0; i < coalesce->n_rules; i++) {
 		rule = &coalesce->rules[i];
+		if (!rule)
+			continue;
 		for (j = 0; j < rule->n_patterns; j++)
 			kfree(rule->patterns[j].mask);
 		kfree(rule->patterns);
 	}
-	kfree(coalesce->rules);
 	kfree(coalesce);
-	rdev->coalesce = NULL;
 }
 
 static int nl80211_parse_coalesce_rule(struct cfg80211_registered_device *rdev,
@@ -14012,17 +14011,16 @@ static int nl80211_set_coalesce(struct sk_buff *skb, struct genl_info *info)
 {
 	struct cfg80211_registered_device *rdev = info->user_ptr[0];
 	const struct wiphy_coalesce_support *coalesce = rdev->wiphy.coalesce;
-	struct cfg80211_coalesce new_coalesce = {};
-	struct cfg80211_coalesce *n_coalesce;
-	int err, rem_rule, n_rules = 0, i, j;
+	struct cfg80211_coalesce *new_coalesce;
+	int err, rem_rule, n_rules = 0, i;
 	struct nlattr *rule;
-	struct cfg80211_coalesce_rules *tmp_rule;
 
 	if (!rdev->wiphy.coalesce || !rdev->ops->set_coalesce)
 		return -EOPNOTSUPP;
 
 	if (!info->attrs[NL80211_ATTR_COALESCE_RULE]) {
-		cfg80211_rdev_free_coalesce(rdev);
+		cfg80211_free_coalesce(rdev->coalesce);
+		rdev->coalesce = NULL;
 		rdev_set_coalesce(rdev, NULL);
 		return 0;
 	}
@@ -14033,47 +14031,34 @@ static int nl80211_set_coalesce(struct sk_buff *skb, struct genl_info *info)
 	if (n_rules > coalesce->n_rules)
 		return -EINVAL;
 
-	new_coalesce.rules = kcalloc(n_rules, sizeof(new_coalesce.rules[0]),
-				     GFP_KERNEL);
-	if (!new_coalesce.rules)
+	new_coalesce = kzalloc(struct_size(new_coalesce, rules, n_rules),
+			       GFP_KERNEL);
+	if (!new_coalesce)
 		return -ENOMEM;
 
-	new_coalesce.n_rules = n_rules;
+	new_coalesce->n_rules = n_rules;
 	i = 0;
 
 	nla_for_each_nested(rule, info->attrs[NL80211_ATTR_COALESCE_RULE],
 			    rem_rule) {
 		err = nl80211_parse_coalesce_rule(rdev, rule,
-						  &new_coalesce.rules[i]);
+						  &new_coalesce->rules[i]);
 		if (err)
 			goto error;
 
 		i++;
 	}
 
-	err = rdev_set_coalesce(rdev, &new_coalesce);
+	err = rdev_set_coalesce(rdev, new_coalesce);
 	if (err)
 		goto error;
 
-	n_coalesce = kmemdup(&new_coalesce, sizeof(new_coalesce), GFP_KERNEL);
-	if (!n_coalesce) {
-		err = -ENOMEM;
-		goto error;
-	}
-	cfg80211_rdev_free_coalesce(rdev);
-	rdev->coalesce = n_coalesce;
+	cfg80211_free_coalesce(rdev->coalesce);
+	rdev->coalesce = new_coalesce;
 
 	return 0;
 error:
-	for (i = 0; i < new_coalesce.n_rules; i++) {
-		tmp_rule = &new_coalesce.rules[i];
-		if (!tmp_rule)
-			continue;
-		for (j = 0; j < tmp_rule->n_patterns; j++)
-			kfree(tmp_rule->patterns[j].mask);
-		kfree(tmp_rule->patterns);
-	}
-	kfree(new_coalesce.rules);
+	cfg80211_free_coalesce(new_coalesce);
 
 	return err;
 }
diff --git a/net/wireless/nl80211.h b/net/wireless/nl80211.h
index 6376f3a87f8ab..ffaab9a92e5bc 100644
--- a/net/wireless/nl80211.h
+++ b/net/wireless/nl80211.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Portions of this file
- * Copyright (C) 2018, 2020-2022 Intel Corporation
+ * Copyright (C) 2018, 2020-2024 Intel Corporation
  */
 #ifndef __NET_WIRELESS_NL80211_H
 #define __NET_WIRELESS_NL80211_H
@@ -119,7 +119,7 @@ nl80211_radar_notify(struct cfg80211_registered_device *rdev,
 
 void nl80211_send_ap_stopped(struct wireless_dev *wdev, unsigned int link_id);
 
-void cfg80211_rdev_free_coalesce(struct cfg80211_registered_device *rdev);
+void cfg80211_free_coalesce(struct cfg80211_coalesce *coalesce);
 
 /* peer measurement */
 int nl80211_pmsr_start(struct sk_buff *skb, struct genl_info *info);
-- 
GitLab


From edb32776196afa393c074d6a2733e3a69e66b299 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 29 May 2024 10:37:59 +0200
Subject: [PATCH 445/950] ALSA: seq: Fix incorrect UMP type for system messages

When converting a legacy system message to a UMP packet, it forgot to
modify the UMP type field but keeping the default type (either type 2
or 4).  Correct to the right type for system messages.

Fixes: e9e02819a98a ("ALSA: seq: Automatic conversion of UMP events")
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20240529083800.5742-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/core/seq/seq_ump_convert.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sound/core/seq/seq_ump_convert.c b/sound/core/seq/seq_ump_convert.c
index f5d22dd008426..add70b4c2885d 100644
--- a/sound/core/seq/seq_ump_convert.c
+++ b/sound/core/seq/seq_ump_convert.c
@@ -739,6 +739,7 @@ static int system_1p_ev_to_ump_midi1(const struct snd_seq_event *event,
 				     union snd_ump_midi1_msg *data,
 				     unsigned char status)
 {
+	data->system.type = UMP_MSG_TYPE_SYSTEM; // override
 	data->system.status = status;
 	data->system.parm1 = event->data.control.value & 0x7f;
 	return 1;
@@ -750,6 +751,7 @@ static int system_2p_ev_to_ump_midi1(const struct snd_seq_event *event,
 				     union snd_ump_midi1_msg *data,
 				     unsigned char status)
 {
+	data->system.type = UMP_MSG_TYPE_SYSTEM; // override
 	data->system.status = status;
 	data->system.parm1 = (event->data.control.value >> 7) & 0x7f;
 	data->system.parm2 = event->data.control.value & 0x7f;
-- 
GitLab


From fe85f6e607d75b856e7229924c71f55e005f8284 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 29 May 2024 10:38:21 +0200
Subject: [PATCH 446/950] ALSA: ump: Don't clear bank selection after sending a
 program change

The current code clears the bank selection MSB/LSB after sending a
program change, but this can be wrong, as many apps may not send the
full bank selection with both MSB and LSB but sending only one.
Better to keep the previous bank set.

Fixes: 0b5288f5fe63 ("ALSA: ump: Add legacy raw MIDI support")
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20240529083823.5778-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/core/ump_convert.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/sound/core/ump_convert.c b/sound/core/ump_convert.c
index de04799fdb69a..f67c44c83fde4 100644
--- a/sound/core/ump_convert.c
+++ b/sound/core/ump_convert.c
@@ -404,7 +404,6 @@ static int cvt_legacy_cmd_to_ump(struct ump_cvt_to_ump *cvt,
 			midi2->pg.bank_msb = cc->cc_bank_msb;
 			midi2->pg.bank_lsb = cc->cc_bank_lsb;
 			cc->bank_set = 0;
-			cc->cc_bank_msb = cc->cc_bank_lsb = 0;
 		}
 		break;
 	case UMP_MSG_STATUS_CHANNEL_PRESSURE:
-- 
GitLab


From 6d40dbc75877110c5e0d661dd77f6cfce916765e Mon Sep 17 00:00:00 2001
From: Alexandre Belloni <alexandre.belloni@bootlin.com>
Date: Tue, 28 May 2024 21:18:50 +0200
Subject: [PATCH 447/950] ALSA: pcm: fix typo in comment

Fix the typo in the comment for SNDRV_PCM_RATE_KNOT

Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Link: https://lore.kernel.org/r/20240528191850.63314-1-alexandre.belloni@bootlin.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/pcm.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/sound/pcm.h b/include/sound/pcm.h
index 61c6054618c8e..3edd7a7346daa 100644
--- a/include/sound/pcm.h
+++ b/include/sound/pcm.h
@@ -124,7 +124,7 @@ struct snd_pcm_ops {
 #define SNDRV_PCM_RATE_768000		(1U<<16)	/* 768000Hz */
 
 #define SNDRV_PCM_RATE_CONTINUOUS	(1U<<30)	/* continuous range */
-#define SNDRV_PCM_RATE_KNOT		(1U<<31)	/* supports more non-continuos rates */
+#define SNDRV_PCM_RATE_KNOT		(1U<<31)	/* supports more non-continuous rates */
 
 #define SNDRV_PCM_RATE_8000_44100	(SNDRV_PCM_RATE_8000|SNDRV_PCM_RATE_11025|\
 					 SNDRV_PCM_RATE_16000|SNDRV_PCM_RATE_22050|\
-- 
GitLab


From 2942dfab630444d46aaa37fb7d629b620abbf6ba Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Mon, 27 May 2024 21:26:44 +0200
Subject: [PATCH 448/950] net: ethernet: cortina: Restore TSO support

An earlier commit deleted the TSO support in the Cortina Gemini
driver because the driver was confusing gso_size and MTU,
probably because what the Linux kernel calls "gso_size" was
called "MTU" in the datasheet.

Restore the functionality properly reading the gso_size from
the skbuff.

Tested with iperf3, running a server on a different machine
and client on the device with the cortina gemini ethernet:

Connecting to host 192.168.1.2, port 5201
60008000.ethernet-port eth0: segment offloading mss = 05ea len=1c8a
60008000.ethernet-port eth0: segment offloading mss = 05ea len=1c8a
60008000.ethernet-port eth0: segment offloading mss = 05ea len=27da
60008000.ethernet-port eth0: segment offloading mss = 05ea len=0b92
60008000.ethernet-port eth0: segment offloading mss = 05ea len=2bda
(...)

(The hardware MSS 0x05ea here includes the ethernet headers.)

If I disable all segment offloading on the receiving host and
dump packets using tcpdump -xx like this:

ethtool -K enp2s0 gro off gso off tso off
tcpdump -xx -i enp2s0 host 192.168.1.136

I get segmented packages such as this when running iperf3:

23:16:54.024139 IP OpenWrt.lan.59168 > Fecusia.targus-getdata1:
Flags [.], seq 1486:2934, ack 1, win 4198,
options [nop,nop,TS val 3886192908 ecr 3601341877], length 1448
0x0000:  fc34 9701 a0c6 14d6 4da8 3c4f 0800 4500
0x0010:  05dc 16a0 4000 4006 9aa1 c0a8 0188 c0a8
0x0020:  0102 e720 1451 ff25 9822 4c52 29cf 8010
0x0030:  1066 ac8c 0000 0101 080a e7a2 990c d6a8
(...)
0x05c0:  5e49 e109 fe8c 4617 5e18 7a82 7eae d647
0x05d0:  e8ee ae64 dc88 c897 3f8a 07a4 3a33 6b1b
0x05e0:  3501 a30f 2758 cc44 4b4a

Several such packets often follow after each other verifying
the segmentation into 0x05a8 (1448) byte packages also on the
reveiving end. As can be seen, the ethernet frames are
0x05ea (1514) in size.

Performance with iperf3 before this patch: ~15.5 Mbit/s
Performance with iperf3 after this patch: ~175 Mbit/s

This was running a 60 second test (twice) the best measurement
was 179 Mbit/s.

For comparison if I run iperf3 with UDP I get around 1.05 Mbit/s
both before and after this patch.

While this is a gigabit ethernet interface, the CPU is a cheap
D-Link DIR-685 router (based on the ARMv5 Faraday FA526 at
~50 MHz), and the software is not supposed to drive traffic,
as the device has a DSA chip, so this kind of numbers can be
expected.

Fixes: ac631873c9e7 ("net: ethernet: cortina: Drop TSO support")
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cortina/gemini.c | 23 +++++++++++++++++++----
 1 file changed, 19 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c
index 5f0c9e1771dbf..7ebd61a3a49b0 100644
--- a/drivers/net/ethernet/cortina/gemini.c
+++ b/drivers/net/ethernet/cortina/gemini.c
@@ -79,7 +79,8 @@ MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)");
 #define GMAC0_IRQ4_8 (GMAC0_MIB_INT_BIT | GMAC0_RX_OVERRUN_INT_BIT)
 
 #define GMAC_OFFLOAD_FEATURES (NETIF_F_SG | NETIF_F_IP_CSUM | \
-			       NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM)
+			       NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM | \
+			       NETIF_F_TSO | NETIF_F_TSO_ECN | NETIF_F_TSO6)
 
 /**
  * struct gmac_queue_page - page buffer per-page info
@@ -1148,13 +1149,25 @@ static int gmac_map_tx_bufs(struct net_device *netdev, struct sk_buff *skb,
 	skb_frag_t *skb_frag;
 	dma_addr_t mapping;
 	void *buffer;
+	u16 mss;
 	int ret;
 
-	/* TODO: implement proper TSO using MTU in word3 */
 	word1 = skb->len;
 	word3 = SOF_BIT;
 
-	if (skb->len >= ETH_FRAME_LEN) {
+	mss = skb_shinfo(skb)->gso_size;
+	if (mss) {
+		/* This means we are dealing with TCP and skb->len is the
+		 * sum total of all the segments. The TSO will deal with
+		 * chopping this up for us.
+		 */
+		/* The accelerator needs the full frame size here */
+		mss += skb_tcp_all_headers(skb);
+		netdev_dbg(netdev, "segment offloading mss = %04x len=%04x\n",
+			   mss, skb->len);
+		word1 |= TSS_MTU_ENABLE_BIT;
+		word3 |= mss;
+	} else if (skb->len >= ETH_FRAME_LEN) {
 		/* Hardware offloaded checksumming isn't working on frames
 		 * bigger than 1514 bytes. A hypothesis about this is that the
 		 * checksum buffer is only 1518 bytes, so when the frames get
@@ -1169,7 +1182,9 @@ static int gmac_map_tx_bufs(struct net_device *netdev, struct sk_buff *skb,
 				return ret;
 		}
 		word1 |= TSS_BYPASS_BIT;
-	} else if (skb->ip_summed == CHECKSUM_PARTIAL) {
+	}
+
+	if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		int tcp = 0;
 
 		/* We do not switch off the checksumming on non TCP/UDP
-- 
GitLab


From b062938fd9afec844c50571fddd8d81623a60ee1 Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Mon, 27 May 2024 14:19:40 -0500
Subject: [PATCH 449/950] ASoC: Intel: sof-sdw: fix missing SPI_MASTER
 dependency

The addition of the Cirrus Logic 'sidecar' amps adds a dependency on SPI_MASTER.

Kconfig warnings: (for reference only)
   WARNING: unmet direct dependencies detected for SND_SOC_CS35L56_SPI
   Depends on [n]:
     SOUND [=y] && SND [=y] && SND_SOC [=y] && SPI_MASTER [=n] &&
     (SOUNDWIRE [=y] || !SOUNDWIRE [=y])
   Selected by [y]:
    - SND_SOC_INTEL_SOUNDWIRE_SOF_MACH [=y] && SOUND [=y] && SND [=y]
      && SND_SOC [=y] && SND_SOC_INTEL_MACH [=y] &&
      SND_SOC_SOF_INTEL_SOUNDWIRE [=y] && I2C [=y] && ACPI [=y] &&
      (MFD_INTEL_LPSS [=y] || COMPILE_TEST [=n]) &&
      (SND_SOC_INTEL_USER_FRIENDLY_LONG_NAMES [=y] || COMPILE_TEST
      [=n]) && SOUNDWIRE [=y]

Fixes: b831b4dca48d ("ASoC: intel: sof_sdw: Add support for cs42l43-cs35l56 sidecar amps")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202405140758.o2HY4nYD-lkp@intel.com/
Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Reviewed-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://msgid.link/r/20240527191940.30107-1-pierre-louis.bossart@linux.intel.com
Reviewed-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/boards/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/intel/boards/Kconfig b/sound/soc/intel/boards/Kconfig
index 3ed81ab649c53..4e0586034de4b 100644
--- a/sound/soc/intel/boards/Kconfig
+++ b/sound/soc/intel/boards/Kconfig
@@ -652,7 +652,7 @@ if SND_SOC_SOF_INTEL_SOUNDWIRE
 
 config SND_SOC_INTEL_SOUNDWIRE_SOF_MACH
 	tristate "SoundWire generic machine driver"
-	depends on I2C && ACPI
+	depends on I2C && SPI_MASTER && ACPI
 	depends on MFD_INTEL_LPSS || COMPILE_TEST
 	depends on SND_SOC_INTEL_USER_FRIENDLY_LONG_NAMES || COMPILE_TEST
 	depends on SOUNDWIRE
-- 
GitLab


From e9022b31db80019025967b03df1d059433e9f26d Mon Sep 17 00:00:00 2001
From: Minda Chen <minda.chen@starfivetech.com>
Date: Tue, 28 May 2024 09:51:20 +0800
Subject: [PATCH 450/950] MAINTAINERS: dwmac: starfive: update Maintainer

Update the maintainer of starfive dwmac driver.

Signed-off-by: Minda Chen <minda.chen@starfivetech.com>
Acked-by: Emil Renner Berthing <emil.renner.berthing@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index e80db76fe3937..90930a03e7a56 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -21318,7 +21318,7 @@ F:	arch/riscv/boot/dts/starfive/
 
 STARFIVE DWMAC GLUE LAYER
 M:	Emil Renner Berthing <kernel@esmil.dk>
-M:	Samin Guo <samin.guo@starfivetech.com>
+M:	Minda Chen <minda.chen@starfivetech.com>
 S:	Maintained
 F:	Documentation/devicetree/bindings/net/starfive,jh7110-dwmac.yaml
 F:	drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c
-- 
GitLab


From 068648aab72c9ba7b0597354ef4d81ffaac7b979 Mon Sep 17 00:00:00 2001
From: Edward Adam Davis <eadavis@qq.com>
Date: Tue, 28 May 2024 11:12:31 +0800
Subject: [PATCH 451/950] nfc/nci: Add the inconsistency check between the
 input data length and count

write$nci(r0, &(0x7f0000000740)=ANY=[@ANYBLOB="610501"], 0xf)

Syzbot constructed a write() call with a data length of 3 bytes but a count value
of 15, which passed too little data to meet the basic requirements of the function
nci_rf_intf_activated_ntf_packet().

Therefore, increasing the comparison between data length and count value to avoid
problems caused by inconsistent data length and count.

Reported-and-tested-by: syzbot+71bfed2b2bcea46c98f2@syzkaller.appspotmail.com
Signed-off-by: Edward Adam Davis <eadavis@qq.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/nfc/virtual_ncidev.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/nfc/virtual_ncidev.c b/drivers/nfc/virtual_ncidev.c
index 590b038e449e5..6b89d596ba9af 100644
--- a/drivers/nfc/virtual_ncidev.c
+++ b/drivers/nfc/virtual_ncidev.c
@@ -125,6 +125,10 @@ static ssize_t virtual_ncidev_write(struct file *file,
 		kfree_skb(skb);
 		return -EFAULT;
 	}
+	if (strnlen(skb->data, count) != count) {
+		kfree_skb(skb);
+		return -EINVAL;
+	}
 
 	nci_recv_frame(vdev->ndev, skb);
 	return count;
-- 
GitLab


From c1d96671088f03e7a685ce1fd3d745af85193141 Mon Sep 17 00:00:00 2001
From: Vineeth Karumanchi <vineeth.karumanchi@amd.com>
Date: Tue, 28 May 2024 11:50:07 +0530
Subject: [PATCH 452/950] dt-bindings: net: xilinx_gmii2rgmii: Add clock
 support

Add "clocks" bindings for the input clock.

Signed-off-by: Vineeth Karumanchi <vineeth.karumanchi@amd.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../devicetree/bindings/net/xlnx,gmii-to-rgmii.yaml          | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/Documentation/devicetree/bindings/net/xlnx,gmii-to-rgmii.yaml b/Documentation/devicetree/bindings/net/xlnx,gmii-to-rgmii.yaml
index 0f781dac6717c..eb803ddd13e0a 100644
--- a/Documentation/devicetree/bindings/net/xlnx,gmii-to-rgmii.yaml
+++ b/Documentation/devicetree/bindings/net/xlnx,gmii-to-rgmii.yaml
@@ -31,6 +31,10 @@ properties:
   phy-handle:
     $ref: ethernet-controller.yaml#/properties/phy-handle
 
+  clocks:
+    items:
+      - description: 200/375 MHz free-running clock is used as input clock.
+
 required:
   - compatible
   - reg
@@ -51,5 +55,6 @@ examples:
             compatible = "xlnx,gmii-to-rgmii-1.0";
             reg = <8>;
             phy-handle = <&phy>;
+            clocks = <&dummy>;
         };
     };
-- 
GitLab


From daab0ac53e774f14ea78a1849358dbefb0d3efd2 Mon Sep 17 00:00:00 2001
From: Vineeth Karumanchi <vineeth.karumanchi@amd.com>
Date: Tue, 28 May 2024 11:50:08 +0530
Subject: [PATCH 453/950] net: phy: xilinx-gmii2rgmii: Adopt clock support

Add clock support to the gmii_to_rgmii IP.
Make clk optional to keep DTB backward compatibility.

Signed-off-by: Vineeth Karumanchi <vineeth.karumanchi@amd.com>
Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/xilinx_gmii2rgmii.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/phy/xilinx_gmii2rgmii.c b/drivers/net/phy/xilinx_gmii2rgmii.c
index 7b1bc5fcef9b2..7c51daecf18ee 100644
--- a/drivers/net/phy/xilinx_gmii2rgmii.c
+++ b/drivers/net/phy/xilinx_gmii2rgmii.c
@@ -15,6 +15,7 @@
 #include <linux/mii.h>
 #include <linux/mdio.h>
 #include <linux/phy.h>
+#include <linux/clk.h>
 #include <linux/of_mdio.h>
 
 #define XILINX_GMII2RGMII_REG		0x10
@@ -85,11 +86,17 @@ static int xgmiitorgmii_probe(struct mdio_device *mdiodev)
 	struct device *dev = &mdiodev->dev;
 	struct device_node *np = dev->of_node, *phy_node;
 	struct gmii2rgmii *priv;
+	struct clk *clkin;
 
 	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
 		return -ENOMEM;
 
+	clkin = devm_clk_get_optional_enabled(dev, NULL);
+	if (IS_ERR(clkin))
+		return dev_err_probe(dev, PTR_ERR(clkin),
+					"Failed to get and enable clock from Device Tree\n");
+
 	phy_node = of_parse_phandle(np, "phy-handle", 0);
 	if (!phy_node) {
 		dev_err(dev, "Couldn't parse phy-handle\n");
-- 
GitLab


From b1e7cee96127468c2483cf10c2899c9b5cf79bf8 Mon Sep 17 00:00:00 2001
From: Puranjay Mohan <puranjay@kernel.org>
Date: Mon, 13 May 2024 10:02:48 +0000
Subject: [PATCH 454/950] powerpc/bpf: enforce full ordering for ATOMIC
 operations with BPF_FETCH

The Linux Kernel Memory Model [1][2] requires RMW operations that have a
return value to be fully ordered.

BPF atomic operations with BPF_FETCH (including BPF_XCHG and
BPF_CMPXCHG) return a value back so they need to be JITed to fully
ordered operations. POWERPC currently emits relaxed operations for
these.

We can show this by running the following litmus-test:

  PPC SB+atomic_add+fetch

  {
      0:r0=x;  (* dst reg assuming offset is 0 *)
      0:r1=2;  (* src reg *)
      0:r2=1;
      0:r4=y;  (* P0 writes to this, P1 reads this *)
      0:r5=z;  (* P1 writes to this, P0 reads this *)
      0:r6=0;

      1:r2=1;
      1:r4=y;
      1:r5=z;
  }

  P0                      | P1            ;
  stw         r2, 0(r4)   | stw  r2,0(r5) ;
                          |               ;
  loop:lwarx  r3, r6, r0  |               ;
  mr          r8, r3      |               ;
  add         r3, r3, r1  | sync          ;
  stwcx.      r3, r6, r0  |               ;
  bne         loop        |               ;
  mr          r1, r8      |               ;
                          |               ;
  lwa         r7, 0(r5)   | lwa  r7,0(r4) ;

  ~exists(0:r7=0 /\ 1:r7=0)

  Witnesses
  Positive: 9 Negative: 3
  Condition ~exists (0:r7=0 /\ 1:r7=0)
  Observation SB+atomic_add+fetch Sometimes 3 9

This test shows that the older store in P0 is reordered with a newer
load to a different address. Although there is a RMW operation with
fetch between them. Adding a sync before and after RMW fixes the issue:

  Witnesses
  Positive: 9 Negative: 0
  Condition ~exists (0:r7=0 /\ 1:r7=0)
  Observation SB+atomic_add+fetch Never 0 9

[1] https://www.kernel.org/doc/Documentation/memory-barriers.txt
[2] https://www.kernel.org/doc/Documentation/atomic_t.txt

Fixes: aea7ef8a82c0 ("powerpc/bpf/32: add support for BPF_ATOMIC bitwise operations")
Fixes: 2d9206b22743 ("powerpc/bpf/32: Add instructions for atomic_[cmp]xchg")
Fixes: dbe6e2456fb0 ("powerpc/bpf/64: add support for atomic fetch operations")
Fixes: 1e82dfaa7819 ("powerpc/bpf/64: Add instructions for atomic_[cmp]xchg")
Cc: stable@vger.kernel.org # v6.0+
Signed-off-by: Puranjay Mohan <puranjay@kernel.org>
Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Reviewed-by: Naveen N Rao <naveen@kernel.org>
Acked-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://msgid.link/20240513100248.110535-1-puranjay@kernel.org
---
 arch/powerpc/net/bpf_jit_comp32.c | 12 ++++++++++++
 arch/powerpc/net/bpf_jit_comp64.c | 12 ++++++++++++
 2 files changed, 24 insertions(+)

diff --git a/arch/powerpc/net/bpf_jit_comp32.c b/arch/powerpc/net/bpf_jit_comp32.c
index 43b97032a91c0..a0c4f1bde83e8 100644
--- a/arch/powerpc/net/bpf_jit_comp32.c
+++ b/arch/powerpc/net/bpf_jit_comp32.c
@@ -900,6 +900,15 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code
 
 			/* Get offset into TMP_REG */
 			EMIT(PPC_RAW_LI(tmp_reg, off));
+			/*
+			 * Enforce full ordering for operations with BPF_FETCH by emitting a 'sync'
+			 * before and after the operation.
+			 *
+			 * This is a requirement in the Linux Kernel Memory Model.
+			 * See __cmpxchg_u32() in asm/cmpxchg.h as an example.
+			 */
+			if ((imm & BPF_FETCH) && IS_ENABLED(CONFIG_SMP))
+				EMIT(PPC_RAW_SYNC());
 			tmp_idx = ctx->idx * 4;
 			/* load value from memory into r0 */
 			EMIT(PPC_RAW_LWARX(_R0, tmp_reg, dst_reg, 0));
@@ -953,6 +962,9 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code
 
 			/* For the BPF_FETCH variant, get old data into src_reg */
 			if (imm & BPF_FETCH) {
+				/* Emit 'sync' to enforce full ordering */
+				if (IS_ENABLED(CONFIG_SMP))
+					EMIT(PPC_RAW_SYNC());
 				EMIT(PPC_RAW_MR(ret_reg, ax_reg));
 				if (!fp->aux->verifier_zext)
 					EMIT(PPC_RAW_LI(ret_reg - 1, 0)); /* higher 32-bit */
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 8afc14a4a1258..7703dcf48be86 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -846,6 +846,15 @@ emit_clear:
 
 			/* Get offset into TMP_REG_1 */
 			EMIT(PPC_RAW_LI(tmp1_reg, off));
+			/*
+			 * Enforce full ordering for operations with BPF_FETCH by emitting a 'sync'
+			 * before and after the operation.
+			 *
+			 * This is a requirement in the Linux Kernel Memory Model.
+			 * See __cmpxchg_u64() in asm/cmpxchg.h as an example.
+			 */
+			if ((imm & BPF_FETCH) && IS_ENABLED(CONFIG_SMP))
+				EMIT(PPC_RAW_SYNC());
 			tmp_idx = ctx->idx * 4;
 			/* load value from memory into TMP_REG_2 */
 			if (size == BPF_DW)
@@ -908,6 +917,9 @@ emit_clear:
 			PPC_BCC_SHORT(COND_NE, tmp_idx);
 
 			if (imm & BPF_FETCH) {
+				/* Emit 'sync' to enforce full ordering */
+				if (IS_ENABLED(CONFIG_SMP))
+					EMIT(PPC_RAW_SYNC());
 				EMIT(PPC_RAW_MR(ret_reg, _R0));
 				/*
 				 * Skip unnecessary zero-extension for 32-bit cmpxchg.
-- 
GitLab


From ffa077b2f6ad124ec3d23fbddc5e4b0ff2647af8 Mon Sep 17 00:00:00 2001
From: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Date: Wed, 29 May 2024 15:12:01 +0300
Subject: [PATCH 455/950] ASoC: SOF: ipc4-topology: Fix input format query of
 process modules without base extension

If a process module does not have base config extension then the same
format applies to all of it's inputs and the process->base_config_ext is
NULL, causing NULL dereference when specifically crafted topology and
sequences used.

Fixes: 648fea128476 ("ASoC: SOF: ipc4-topology: set copier output format for process module")
Signed-off-by: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Reviewed-by: Seppo Ingalsuo <seppo.ingalsuo@linux.intel.com>
Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Cc: stable@vger.kernel.org
Link: https://msgid.link/r/20240529121201.14687-1-peter.ujfalusi@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sof/ipc4-topology.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/sound/soc/sof/ipc4-topology.c b/sound/soc/sof/ipc4-topology.c
index beff109893247..33e8c5f7d9ca0 100644
--- a/sound/soc/sof/ipc4-topology.c
+++ b/sound/soc/sof/ipc4-topology.c
@@ -217,6 +217,14 @@ sof_ipc4_get_input_pin_audio_fmt(struct snd_sof_widget *swidget, int pin_index)
 	}
 
 	process = swidget->private;
+
+	/*
+	 * For process modules without base config extension, base module config
+	 * format is used for all input pins
+	 */
+	if (process->init_config != SOF_IPC4_MODULE_INIT_CONFIG_TYPE_BASE_CFG_WITH_EXT)
+		return &process->base_config.audio_fmt;
+
 	base_cfg_ext = process->base_config_ext;
 
 	/*
-- 
GitLab


From 4a69c1264ff41bc5bf7c03101ada0454fbf08868 Mon Sep 17 00:00:00 2001
From: Witold Sadowski <wsadowski@marvell.com>
Date: Wed, 29 May 2024 00:40:32 -0700
Subject: [PATCH 456/950] spi: cadence: Ensure data lines set to low during
 dummy-cycle period

During dummy-cycles xSPI will switch GPIO into Hi-Z mode. In that dummy
period voltage on data lines will slowly drop, what can cause
unintentional modebyte transmission. Value send to SPI memory chip will
depend on last address, and clock frequency.
To prevent unforeseen consequences of that behaviour, force send
single modebyte(0x00).
Modebyte will be send only if number of dummy-cycles is not equal
to 0. Code must also reduce dummycycle byte count by one - as one byte
is send as modebyte.

Signed-off-by: Witold Sadowski <wsadowski@marvell.com>
Link: https://msgid.link/r/20240529074037.1345882-2-wsadowski@marvell.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-cadence-xspi.c | 20 +++++++++++++++-----
 1 file changed, 15 insertions(+), 5 deletions(-)

diff --git a/drivers/spi/spi-cadence-xspi.c b/drivers/spi/spi-cadence-xspi.c
index 2209e9fc378fa..2e3eacd46b723 100644
--- a/drivers/spi/spi-cadence-xspi.c
+++ b/drivers/spi/spi-cadence-xspi.c
@@ -145,6 +145,9 @@
 #define CDNS_XSPI_STIG_DONE_FLAG		BIT(0)
 #define CDNS_XSPI_TRD_STATUS			0x0104
 
+#define MODE_NO_OF_BYTES			GENMASK(25, 24)
+#define MODEBYTES_COUNT			1
+
 /* Helper macros for filling command registers */
 #define CDNS_XSPI_CMD_FLD_P1_INSTR_CMD_1(op, data_phase) ( \
 	FIELD_PREP(CDNS_XSPI_CMD_INSTR_TYPE, (data_phase) ? \
@@ -157,9 +160,10 @@
 	FIELD_PREP(CDNS_XSPI_CMD_P1_R2_ADDR3, ((op)->addr.val >> 24) & 0xFF) | \
 	FIELD_PREP(CDNS_XSPI_CMD_P1_R2_ADDR4, ((op)->addr.val >> 32) & 0xFF))
 
-#define CDNS_XSPI_CMD_FLD_P1_INSTR_CMD_3(op) ( \
+#define CDNS_XSPI_CMD_FLD_P1_INSTR_CMD_3(op, modebytes) ( \
 	FIELD_PREP(CDNS_XSPI_CMD_P1_R3_ADDR5, ((op)->addr.val >> 40) & 0xFF) | \
 	FIELD_PREP(CDNS_XSPI_CMD_P1_R3_CMD, (op)->cmd.opcode) | \
+	FIELD_PREP(MODE_NO_OF_BYTES, modebytes) | \
 	FIELD_PREP(CDNS_XSPI_CMD_P1_R3_NUM_ADDR_BYTES, (op)->addr.nbytes))
 
 #define CDNS_XSPI_CMD_FLD_P1_INSTR_CMD_4(op, chipsel) ( \
@@ -173,12 +177,12 @@
 #define CDNS_XSPI_CMD_FLD_DSEQ_CMD_2(op) \
 	FIELD_PREP(CDNS_XSPI_CMD_DSEQ_R2_DCNT_L, (op)->data.nbytes & 0xFFFF)
 
-#define CDNS_XSPI_CMD_FLD_DSEQ_CMD_3(op) ( \
+#define CDNS_XSPI_CMD_FLD_DSEQ_CMD_3(op, dummybytes) ( \
 	FIELD_PREP(CDNS_XSPI_CMD_DSEQ_R3_DCNT_H, \
 		((op)->data.nbytes >> 16) & 0xffff) | \
 	FIELD_PREP(CDNS_XSPI_CMD_DSEQ_R3_NUM_OF_DUMMY, \
 		  (op)->dummy.buswidth != 0 ? \
-		  (((op)->dummy.nbytes * 8) / (op)->dummy.buswidth) : \
+		  (((dummybytes) * 8) / (op)->dummy.buswidth) : \
 		  0))
 
 #define CDNS_XSPI_CMD_FLD_DSEQ_CMD_4(op, chipsel) ( \
@@ -351,6 +355,7 @@ static int cdns_xspi_send_stig_command(struct cdns_xspi_dev *cdns_xspi,
 	u32 cmd_regs[6];
 	u32 cmd_status;
 	int ret;
+	int dummybytes = op->dummy.nbytes;
 
 	ret = cdns_xspi_wait_for_controller_idle(cdns_xspi);
 	if (ret < 0)
@@ -365,7 +370,12 @@ static int cdns_xspi_send_stig_command(struct cdns_xspi_dev *cdns_xspi,
 	memset(cmd_regs, 0, sizeof(cmd_regs));
 	cmd_regs[1] = CDNS_XSPI_CMD_FLD_P1_INSTR_CMD_1(op, data_phase);
 	cmd_regs[2] = CDNS_XSPI_CMD_FLD_P1_INSTR_CMD_2(op);
-	cmd_regs[3] = CDNS_XSPI_CMD_FLD_P1_INSTR_CMD_3(op);
+	if (dummybytes != 0) {
+		cmd_regs[3] = CDNS_XSPI_CMD_FLD_P1_INSTR_CMD_3(op, 1);
+		dummybytes--;
+	} else {
+		cmd_regs[3] = CDNS_XSPI_CMD_FLD_P1_INSTR_CMD_3(op, 0);
+	}
 	cmd_regs[4] = CDNS_XSPI_CMD_FLD_P1_INSTR_CMD_4(op,
 						       cdns_xspi->cur_cs);
 
@@ -375,7 +385,7 @@ static int cdns_xspi_send_stig_command(struct cdns_xspi_dev *cdns_xspi,
 		cmd_regs[0] = CDNS_XSPI_STIG_DONE_FLAG;
 		cmd_regs[1] = CDNS_XSPI_CMD_FLD_DSEQ_CMD_1(op);
 		cmd_regs[2] = CDNS_XSPI_CMD_FLD_DSEQ_CMD_2(op);
-		cmd_regs[3] = CDNS_XSPI_CMD_FLD_DSEQ_CMD_3(op);
+		cmd_regs[3] = CDNS_XSPI_CMD_FLD_DSEQ_CMD_3(op, dummybytes);
 		cmd_regs[4] = CDNS_XSPI_CMD_FLD_DSEQ_CMD_4(op,
 							   cdns_xspi->cur_cs);
 
-- 
GitLab


From b7d7f11a291830fdf69d3301075dd0fb347ced84 Mon Sep 17 00:00:00 2001
From: Nicolas Escande <nico.escande@gmail.com>
Date: Tue, 28 May 2024 16:26:05 +0200
Subject: [PATCH 457/950] wifi: mac80211: mesh: Fix leak of mesh_preq_queue
 objects

The hwmp code use objects of type mesh_preq_queue, added to a list in
ieee80211_if_mesh, to keep track of mpath we need to resolve. If the mpath
gets deleted, ex mesh interface is removed, the entries in that list will
never get cleaned. Fix this by flushing all corresponding items of the
preq_queue in mesh_path_flush_pending().

This should take care of KASAN reports like this:

unreferenced object 0xffff00000668d800 (size 128):
  comm "kworker/u8:4", pid 67, jiffies 4295419552 (age 1836.444s)
  hex dump (first 32 bytes):
    00 1f 05 09 00 00 ff ff 00 d5 68 06 00 00 ff ff  ..........h.....
    8e 97 ea eb 3e b8 01 00 00 00 00 00 00 00 00 00  ....>...........
  backtrace:
    [<000000007302a0b6>] __kmem_cache_alloc_node+0x1e0/0x35c
    [<00000000049bd418>] kmalloc_trace+0x34/0x80
    [<0000000000d792bb>] mesh_queue_preq+0x44/0x2a8
    [<00000000c99c3696>] mesh_nexthop_resolve+0x198/0x19c
    [<00000000926bf598>] ieee80211_xmit+0x1d0/0x1f4
    [<00000000fc8c2284>] __ieee80211_subif_start_xmit+0x30c/0x764
    [<000000005926ee38>] ieee80211_subif_start_xmit+0x9c/0x7a4
    [<000000004c86e916>] dev_hard_start_xmit+0x174/0x440
    [<0000000023495647>] __dev_queue_xmit+0xe24/0x111c
    [<00000000cfe9ca78>] batadv_send_skb_packet+0x180/0x1e4
    [<000000007bacc5d5>] batadv_v_elp_periodic_work+0x2f4/0x508
    [<00000000adc3cd94>] process_one_work+0x4b8/0xa1c
    [<00000000b36425d1>] worker_thread+0x9c/0x634
    [<0000000005852dd5>] kthread+0x1bc/0x1c4
    [<000000005fccd770>] ret_from_fork+0x10/0x20
unreferenced object 0xffff000009051f00 (size 128):
  comm "kworker/u8:4", pid 67, jiffies 4295419553 (age 1836.440s)
  hex dump (first 32 bytes):
    90 d6 92 0d 00 00 ff ff 00 d8 68 06 00 00 ff ff  ..........h.....
    36 27 92 e4 02 e0 01 00 00 58 79 06 00 00 ff ff  6'.......Xy.....
  backtrace:
    [<000000007302a0b6>] __kmem_cache_alloc_node+0x1e0/0x35c
    [<00000000049bd418>] kmalloc_trace+0x34/0x80
    [<0000000000d792bb>] mesh_queue_preq+0x44/0x2a8
    [<00000000c99c3696>] mesh_nexthop_resolve+0x198/0x19c
    [<00000000926bf598>] ieee80211_xmit+0x1d0/0x1f4
    [<00000000fc8c2284>] __ieee80211_subif_start_xmit+0x30c/0x764
    [<000000005926ee38>] ieee80211_subif_start_xmit+0x9c/0x7a4
    [<000000004c86e916>] dev_hard_start_xmit+0x174/0x440
    [<0000000023495647>] __dev_queue_xmit+0xe24/0x111c
    [<00000000cfe9ca78>] batadv_send_skb_packet+0x180/0x1e4
    [<000000007bacc5d5>] batadv_v_elp_periodic_work+0x2f4/0x508
    [<00000000adc3cd94>] process_one_work+0x4b8/0xa1c
    [<00000000b36425d1>] worker_thread+0x9c/0x634
    [<0000000005852dd5>] kthread+0x1bc/0x1c4
    [<000000005fccd770>] ret_from_fork+0x10/0x20

Fixes: 050ac52cbe1f ("mac80211: code for on-demand Hybrid Wireless Mesh Protocol")
Signed-off-by: Nicolas Escande <nico.escande@gmail.com>
Link: https://msgid.link/20240528142605.1060566-1-nico.escande@gmail.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mesh_pathtbl.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c
index a6b62169f0848..c0a5c75cddcb9 100644
--- a/net/mac80211/mesh_pathtbl.c
+++ b/net/mac80211/mesh_pathtbl.c
@@ -1017,10 +1017,23 @@ void mesh_path_discard_frame(struct ieee80211_sub_if_data *sdata,
  */
 void mesh_path_flush_pending(struct mesh_path *mpath)
 {
+	struct ieee80211_sub_if_data *sdata = mpath->sdata;
+	struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh;
+	struct mesh_preq_queue *preq, *tmp;
 	struct sk_buff *skb;
 
 	while ((skb = skb_dequeue(&mpath->frame_queue)) != NULL)
 		mesh_path_discard_frame(mpath->sdata, skb);
+
+	spin_lock_bh(&ifmsh->mesh_preq_queue_lock);
+	list_for_each_entry_safe(preq, tmp, &ifmsh->preq_queue.list, list) {
+		if (ether_addr_equal(mpath->dst, preq->dst)) {
+			list_del(&preq->list);
+			kfree(preq);
+			--ifmsh->preq_queue_len;
+		}
+	}
+	spin_unlock_bh(&ifmsh->mesh_preq_queue_lock);
 }
 
 /**
-- 
GitLab


From 6f6291f09a322c1c1578badac8072d049363f4e6 Mon Sep 17 00:00:00 2001
From: Nicolas Escande <nico.escande@gmail.com>
Date: Mon, 27 May 2024 16:17:59 +0200
Subject: [PATCH 458/950] wifi: mac80211: mesh: init nonpeer_pm to active by
 default in mesh sdata

With a ath9k device I can see that:
	iw phy phy0 interface add mesh0 type mp
	ip link set mesh0 up
	iw dev mesh0 scan

Will start a scan with the Power Management bit set in the Frame Control Field.
This is because we set this bit depending on the nonpeer_pm variable of the mesh
iface sdata and when there are no active links on the interface it remains to
NL80211_MESH_POWER_UNKNOWN.

As soon as links starts to be established, it wil switch to
NL80211_MESH_POWER_ACTIVE as it is the value set by befault on the per sta
nonpeer_pm field.
As we want no power save by default, (as expressed with the per sta ini values),
lets init it to the expected default value of NL80211_MESH_POWER_ACTIVE.

Also please note that we cannot change the default value from userspace prior to
establishing a link as using NL80211_CMD_SET_MESH_CONFIG will not work before
NL80211_CMD_JOIN_MESH has been issued. So too late for our initial scan.

Signed-off-by: Nicolas Escande <nico.escande@gmail.com>
Link: https://msgid.link/20240527141759.299411-1-nico.escande@gmail.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mesh.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c
index cbc9b5e40cb35..6d4510221c98e 100644
--- a/net/mac80211/mesh.c
+++ b/net/mac80211/mesh.c
@@ -1776,6 +1776,7 @@ void ieee80211_mesh_init_sdata(struct ieee80211_sub_if_data *sdata)
 	ifmsh->last_preq = jiffies;
 	ifmsh->next_perr = jiffies;
 	ifmsh->csa_role = IEEE80211_MESH_CSA_ROLE_NONE;
+	ifmsh->nonpeer_pm = NL80211_MESH_POWER_ACTIVE;
 	/* Allocate all mesh structures when creating the first mesh interface. */
 	if (!mesh_allocated)
 		ieee80211s_init();
-- 
GitLab


From 44c06bbde6443de206b30f513100b5670b23fc5e Mon Sep 17 00:00:00 2001
From: Remi Pommarel <repk@triplefau.lt>
Date: Wed, 29 May 2024 08:57:53 +0200
Subject: [PATCH 459/950] wifi: mac80211: Fix deadlock in
 ieee80211_sta_ps_deliver_wakeup()

The ieee80211_sta_ps_deliver_wakeup() function takes sta->ps_lock to
synchronizes with ieee80211_tx_h_unicast_ps_buf() which is called from
softirq context. However using only spin_lock() to get sta->ps_lock in
ieee80211_sta_ps_deliver_wakeup() does not prevent softirq to execute
on this same CPU, to run ieee80211_tx_h_unicast_ps_buf() and try to
take this same lock ending in deadlock. Below is an example of rcu stall
that arises in such situation.

 rcu: INFO: rcu_sched self-detected stall on CPU
 rcu:    2-....: (42413413 ticks this GP) idle=b154/1/0x4000000000000000 softirq=1763/1765 fqs=21206996
 rcu:    (t=42586894 jiffies g=2057 q=362405 ncpus=4)
 CPU: 2 PID: 719 Comm: wpa_supplicant Tainted: G        W          6.4.0-02158-g1b062f552873 #742
 Hardware name: RPT (r1) (DT)
 pstate: 00000005 (nzcv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--)
 pc : queued_spin_lock_slowpath+0x58/0x2d0
 lr : invoke_tx_handlers_early+0x5b4/0x5c0
 sp : ffff00001ef64660
 x29: ffff00001ef64660 x28: ffff000009bc1070 x27: ffff000009bc0ad8
 x26: ffff000009bc0900 x25: ffff00001ef647a8 x24: 0000000000000000
 x23: ffff000009bc0900 x22: ffff000009bc0900 x21: ffff00000ac0e000
 x20: ffff00000a279e00 x19: ffff00001ef646e8 x18: 0000000000000000
 x17: ffff800016468000 x16: ffff00001ef608c0 x15: 0010533c93f64f80
 x14: 0010395c9faa3946 x13: 0000000000000000 x12: 00000000fa83b2da
 x11: 000000012edeceea x10: ffff0000010fbe00 x9 : 0000000000895440
 x8 : 000000000010533c x7 : ffff00000ad8b740 x6 : ffff00000c350880
 x5 : 0000000000000007 x4 : 0000000000000001 x3 : 0000000000000000
 x2 : 0000000000000000 x1 : 0000000000000001 x0 : ffff00000ac0e0e8
 Call trace:
  queued_spin_lock_slowpath+0x58/0x2d0
  ieee80211_tx+0x80/0x12c
  ieee80211_tx_pending+0x110/0x278
  tasklet_action_common.constprop.0+0x10c/0x144
  tasklet_action+0x20/0x28
  _stext+0x11c/0x284
  ____do_softirq+0xc/0x14
  call_on_irq_stack+0x24/0x34
  do_softirq_own_stack+0x18/0x20
  do_softirq+0x74/0x7c
  __local_bh_enable_ip+0xa0/0xa4
  _ieee80211_wake_txqs+0x3b0/0x4b8
  __ieee80211_wake_queue+0x12c/0x168
  ieee80211_add_pending_skbs+0xec/0x138
  ieee80211_sta_ps_deliver_wakeup+0x2a4/0x480
  ieee80211_mps_sta_status_update.part.0+0xd8/0x11c
  ieee80211_mps_sta_status_update+0x18/0x24
  sta_apply_parameters+0x3bc/0x4c0
  ieee80211_change_station+0x1b8/0x2dc
  nl80211_set_station+0x444/0x49c
  genl_family_rcv_msg_doit.isra.0+0xa4/0xfc
  genl_rcv_msg+0x1b0/0x244
  netlink_rcv_skb+0x38/0x10c
  genl_rcv+0x34/0x48
  netlink_unicast+0x254/0x2bc
  netlink_sendmsg+0x190/0x3b4
  ____sys_sendmsg+0x1e8/0x218
  ___sys_sendmsg+0x68/0x8c
  __sys_sendmsg+0x44/0x84
  __arm64_sys_sendmsg+0x20/0x28
  do_el0_svc+0x6c/0xe8
  el0_svc+0x14/0x48
  el0t_64_sync_handler+0xb0/0xb4
  el0t_64_sync+0x14c/0x150

Using spin_lock_bh()/spin_unlock_bh() instead prevents softirq to raise
on the same CPU that is holding the lock.

Fixes: 1d147bfa6429 ("mac80211: fix AP powersave TX vs. wakeup race")
Signed-off-by: Remi Pommarel <repk@triplefau.lt>
Link: https://msgid.link/8e36fe07d0fbc146f89196cd47a53c8a0afe84aa.1716910344.git.repk@triplefau.lt
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/sta_info.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index da5fdd6f5c852..aa22f09e6d145 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -1724,7 +1724,7 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta)
 	skb_queue_head_init(&pending);
 
 	/* sync with ieee80211_tx_h_unicast_ps_buf */
-	spin_lock(&sta->ps_lock);
+	spin_lock_bh(&sta->ps_lock);
 	/* Send all buffered frames to the station */
 	for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) {
 		int count = skb_queue_len(&pending), tmp;
@@ -1753,7 +1753,7 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta)
 	 */
 	clear_sta_flag(sta, WLAN_STA_PSPOLL);
 	clear_sta_flag(sta, WLAN_STA_UAPSD);
-	spin_unlock(&sta->ps_lock);
+	spin_unlock_bh(&sta->ps_lock);
 
 	atomic_dec(&ps->num_sta_ps);
 
-- 
GitLab


From 4dc3a3893dae5a7f73e5809273aca0f1f3548d55 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Thu, 23 May 2024 12:05:33 +0200
Subject: [PATCH 460/950] wifi: cfg80211: validate HE operation element parsing

Validate that the HE operation element has the correct
length before parsing it.

Cc: stable@vger.kernel.org
Fixes: 645f3d85129d ("wifi: cfg80211: handle UHB AP and STA power type")
Reviewed-by: Miriam Rachel Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240523120533.677025eb4a92.I44c091029ef113c294e8fe8b9bf871bf5dbeeb27@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/scan.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 127853877a0ad..8daed8232b054 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -2128,7 +2128,8 @@ static bool cfg80211_6ghz_power_type_valid(const u8 *ie, size_t ielen,
 	struct ieee80211_he_operation *he_oper;
 
 	tmp = cfg80211_find_ext_elem(WLAN_EID_EXT_HE_OPERATION, ie, ielen);
-	if (tmp && tmp->datalen >= sizeof(*he_oper) + 1) {
+	if (tmp && tmp->datalen >= sizeof(*he_oper) + 1 &&
+	    tmp->datalen >= ieee80211_he_oper_size(tmp->data + 1)) {
 		const struct ieee80211_he_6ghz_oper *he_6ghz_oper;
 
 		he_oper = (void *)&tmp->data[1];
-- 
GitLab


From e296c95eac655008d5a709b8cf54d0018da1c916 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 22 May 2024 12:41:25 +0200
Subject: [PATCH 461/950] wifi: cfg80211: fully move wiphy work to unbound
 workqueue

Previously I had moved the wiphy work to the unbound
system workqueue, but missed that when it restarts and
during resume it was still using the normal system
workqueue. Fix that.

Fixes: 91d20ab9d9ca ("wifi: cfg80211: use system_unbound_wq for wiphy work")
Reviewed-by: Miriam Rachel Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240522124126.7ca959f2cbd3.I3e2a71ef445d167b84000ccf934ea245aef8d395@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/core.c  | 2 +-
 net/wireless/sysfs.c | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/wireless/core.c b/net/wireless/core.c
index 3fb1b637352a9..4b1f45e3070e0 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -431,7 +431,7 @@ static void cfg80211_wiphy_work(struct work_struct *work)
 	if (wk) {
 		list_del_init(&wk->entry);
 		if (!list_empty(&rdev->wiphy_work_list))
-			schedule_work(work);
+			queue_work(system_unbound_wq, work);
 		spin_unlock_irq(&rdev->wiphy_work_lock);
 
 		wk->func(&rdev->wiphy, wk);
diff --git a/net/wireless/sysfs.c b/net/wireless/sysfs.c
index 565511a3f461e..62f26618f6747 100644
--- a/net/wireless/sysfs.c
+++ b/net/wireless/sysfs.c
@@ -5,7 +5,7 @@
  *
  * Copyright 2005-2006	Jiri Benc <jbenc@suse.cz>
  * Copyright 2006	Johannes Berg <johannes@sipsolutions.net>
- * Copyright (C) 2020-2021, 2023 Intel Corporation
+ * Copyright (C) 2020-2021, 2023-2024 Intel Corporation
  */
 
 #include <linux/device.h>
@@ -137,7 +137,7 @@ static int wiphy_resume(struct device *dev)
 	if (rdev->wiphy.registered && rdev->ops->resume)
 		ret = rdev_resume(rdev);
 	rdev->suspended = false;
-	schedule_work(&rdev->wiphy_work);
+	queue_work(system_unbound_wq, &rdev->wiphy_work);
 	wiphy_unlock(&rdev->wiphy);
 
 	if (ret)
-- 
GitLab


From 642f89daa34567d02f312d03e41523a894906dae Mon Sep 17 00:00:00 2001
From: Remi Pommarel <repk@triplefau.lt>
Date: Tue, 21 May 2024 21:47:26 +0200
Subject: [PATCH 462/950] wifi: cfg80211: Lock wiphy in cfg80211_get_station

Wiphy should be locked before calling rdev_get_station() (see lockdep
assert in ieee80211_get_station()).

This fixes the following kernel NULL dereference:

 Unable to handle kernel NULL pointer dereference at virtual address 0000000000000050
 Mem abort info:
   ESR = 0x0000000096000006
   EC = 0x25: DABT (current EL), IL = 32 bits
   SET = 0, FnV = 0
   EA = 0, S1PTW = 0
   FSC = 0x06: level 2 translation fault
 Data abort info:
   ISV = 0, ISS = 0x00000006
   CM = 0, WnR = 0
 user pgtable: 4k pages, 48-bit VAs, pgdp=0000000003001000
 [0000000000000050] pgd=0800000002dca003, p4d=0800000002dca003, pud=08000000028e9003, pmd=0000000000000000
 Internal error: Oops: 0000000096000006 [#1] SMP
 Modules linked in: netconsole dwc3_meson_g12a dwc3_of_simple dwc3 ip_gre gre ath10k_pci ath10k_core ath9k ath9k_common ath9k_hw ath
 CPU: 0 PID: 1091 Comm: kworker/u8:0 Not tainted 6.4.0-02144-g565f9a3a7911-dirty #705
 Hardware name: RPT (r1) (DT)
 Workqueue: bat_events batadv_v_elp_throughput_metric_update
 pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--)
 pc : ath10k_sta_statistics+0x10/0x2dc [ath10k_core]
 lr : sta_set_sinfo+0xcc/0xbd4
 sp : ffff000007b43ad0
 x29: ffff000007b43ad0 x28: ffff0000071fa900 x27: ffff00000294ca98
 x26: ffff000006830880 x25: ffff000006830880 x24: ffff00000294c000
 x23: 0000000000000001 x22: ffff000007b43c90 x21: ffff800008898acc
 x20: ffff00000294c6e8 x19: ffff000007b43c90 x18: 0000000000000000
 x17: 445946354d552d78 x16: 62661f7200000000 x15: 57464f445946354d
 x14: 0000000000000000 x13: 00000000000000e3 x12: d5f0acbcebea978e
 x11: 00000000000000e3 x10: 000000010048fe41 x9 : 0000000000000000
 x8 : ffff000007b43d90 x7 : 000000007a1e2125 x6 : 0000000000000000
 x5 : ffff0000024e0900 x4 : ffff800000a0250c x3 : ffff000007b43c90
 x2 : ffff00000294ca98 x1 : ffff000006831920 x0 : 0000000000000000
 Call trace:
  ath10k_sta_statistics+0x10/0x2dc [ath10k_core]
  sta_set_sinfo+0xcc/0xbd4
  ieee80211_get_station+0x2c/0x44
  cfg80211_get_station+0x80/0x154
  batadv_v_elp_get_throughput+0x138/0x1fc
  batadv_v_elp_throughput_metric_update+0x1c/0xa4
  process_one_work+0x1ec/0x414
  worker_thread+0x70/0x46c
  kthread+0xdc/0xe0
  ret_from_fork+0x10/0x20
 Code: a9bb7bfd 910003fd a90153f3 f9411c40 (f9402814)

This happens because STA has time to disconnect and reconnect before
batadv_v_elp_throughput_metric_update() delayed work gets scheduled. In
this situation, ath10k_sta_state() can be in the middle of resetting
arsta data when the work queue get chance to be scheduled and ends up
accessing it. Locking wiphy prevents that.

Fixes: 7406353d43c8 ("cfg80211: implement cfg80211_get_station cfg80211 API")
Signed-off-by: Remi Pommarel <repk@triplefau.lt>
Reviewed-by: Nicolas Escande <nico.escande@gmail.com>
Acked-by: Antonio Quartulli <a@unstable.cc>
Link: https://msgid.link/983b24a6a176e0800c01aedcd74480d9b551cb13.1716046653.git.repk@triplefau.lt
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/util.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/net/wireless/util.c b/net/wireless/util.c
index 2bde8a3546313..082c6f9c5416e 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -2549,6 +2549,7 @@ int cfg80211_get_station(struct net_device *dev, const u8 *mac_addr,
 {
 	struct cfg80211_registered_device *rdev;
 	struct wireless_dev *wdev;
+	int ret;
 
 	wdev = dev->ieee80211_ptr;
 	if (!wdev)
@@ -2560,7 +2561,11 @@ int cfg80211_get_station(struct net_device *dev, const u8 *mac_addr,
 
 	memset(sinfo, 0, sizeof(*sinfo));
 
-	return rdev_get_station(rdev, dev, mac_addr, sinfo);
+	wiphy_lock(&rdev->wiphy);
+	ret = rdev_get_station(rdev, dev, mac_addr, sinfo);
+	wiphy_unlock(&rdev->wiphy);
+
+	return ret;
 }
 EXPORT_SYMBOL(cfg80211_get_station);
 
-- 
GitLab


From ab904521f4de52fef4f179d2dfc1877645ef5f5c Mon Sep 17 00:00:00 2001
From: Lin Ma <linma@zju.edu.cn>
Date: Tue, 21 May 2024 15:50:59 +0800
Subject: [PATCH 463/950] wifi: cfg80211: pmsr: use correct nla_get_uX
 functions

The commit 9bb7e0f24e7e ("cfg80211: add peer measurement with FTM
initiator API") defines four attributes NL80211_PMSR_FTM_REQ_ATTR_
{NUM_BURSTS_EXP}/{BURST_PERIOD}/{BURST_DURATION}/{FTMS_PER_BURST} in
following ways.

static const struct nla_policy
nl80211_pmsr_ftm_req_attr_policy[NL80211_PMSR_FTM_REQ_ATTR_MAX + 1] = {
    ...
    [NL80211_PMSR_FTM_REQ_ATTR_NUM_BURSTS_EXP] =
        NLA_POLICY_MAX(NLA_U8, 15),
    [NL80211_PMSR_FTM_REQ_ATTR_BURST_PERIOD] = { .type = NLA_U16 },
    [NL80211_PMSR_FTM_REQ_ATTR_BURST_DURATION] =
        NLA_POLICY_MAX(NLA_U8, 15),
    [NL80211_PMSR_FTM_REQ_ATTR_FTMS_PER_BURST] =
        NLA_POLICY_MAX(NLA_U8, 31),
    ...
};

That is, those attributes are expected to be NLA_U8 and NLA_U16 types.
However, the consumers of these attributes in `pmsr_parse_ftm` blindly
all use `nla_get_u32`, which is incorrect and causes functionality issues
on little-endian platforms. Hence, fix them with the correct `nla_get_u8`
and `nla_get_u16` functions.

Fixes: 9bb7e0f24e7e ("cfg80211: add peer measurement with FTM initiator API")
Signed-off-by: Lin Ma <linma@zju.edu.cn>
Link: https://msgid.link/20240521075059.47999-1-linma@zju.edu.cn
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/pmsr.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/wireless/pmsr.c b/net/wireless/pmsr.c
index e106dcea39778..c569c37da3175 100644
--- a/net/wireless/pmsr.c
+++ b/net/wireless/pmsr.c
@@ -56,7 +56,7 @@ static int pmsr_parse_ftm(struct cfg80211_registered_device *rdev,
 	out->ftm.burst_period = 0;
 	if (tb[NL80211_PMSR_FTM_REQ_ATTR_BURST_PERIOD])
 		out->ftm.burst_period =
-			nla_get_u32(tb[NL80211_PMSR_FTM_REQ_ATTR_BURST_PERIOD]);
+			nla_get_u16(tb[NL80211_PMSR_FTM_REQ_ATTR_BURST_PERIOD]);
 
 	out->ftm.asap = !!tb[NL80211_PMSR_FTM_REQ_ATTR_ASAP];
 	if (out->ftm.asap && !capa->ftm.asap) {
@@ -75,7 +75,7 @@ static int pmsr_parse_ftm(struct cfg80211_registered_device *rdev,
 	out->ftm.num_bursts_exp = 0;
 	if (tb[NL80211_PMSR_FTM_REQ_ATTR_NUM_BURSTS_EXP])
 		out->ftm.num_bursts_exp =
-			nla_get_u32(tb[NL80211_PMSR_FTM_REQ_ATTR_NUM_BURSTS_EXP]);
+			nla_get_u8(tb[NL80211_PMSR_FTM_REQ_ATTR_NUM_BURSTS_EXP]);
 
 	if (capa->ftm.max_bursts_exponent >= 0 &&
 	    out->ftm.num_bursts_exp > capa->ftm.max_bursts_exponent) {
@@ -88,7 +88,7 @@ static int pmsr_parse_ftm(struct cfg80211_registered_device *rdev,
 	out->ftm.burst_duration = 15;
 	if (tb[NL80211_PMSR_FTM_REQ_ATTR_BURST_DURATION])
 		out->ftm.burst_duration =
-			nla_get_u32(tb[NL80211_PMSR_FTM_REQ_ATTR_BURST_DURATION]);
+			nla_get_u8(tb[NL80211_PMSR_FTM_REQ_ATTR_BURST_DURATION]);
 
 	out->ftm.ftms_per_burst = 0;
 	if (tb[NL80211_PMSR_FTM_REQ_ATTR_FTMS_PER_BURST])
@@ -107,7 +107,7 @@ static int pmsr_parse_ftm(struct cfg80211_registered_device *rdev,
 	out->ftm.ftmr_retries = 3;
 	if (tb[NL80211_PMSR_FTM_REQ_ATTR_NUM_FTMR_RETRIES])
 		out->ftm.ftmr_retries =
-			nla_get_u32(tb[NL80211_PMSR_FTM_REQ_ATTR_NUM_FTMR_RETRIES]);
+			nla_get_u8(tb[NL80211_PMSR_FTM_REQ_ATTR_NUM_FTMR_RETRIES]);
 
 	out->ftm.request_lci = !!tb[NL80211_PMSR_FTM_REQ_ATTR_REQUEST_LCI];
 	if (out->ftm.request_lci && !capa->ftm.request_lci) {
-- 
GitLab


From 02c665f048a439c0d58cc45334c94634bd7c18e6 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 15 May 2024 13:34:10 +0200
Subject: [PATCH 464/950] wifi: mac80211: apply mcast rate only if interface is
 up

If the interface isn't enabled, don't apply multicast
rate changes immediately.

Reported-by: syzbot+de87c09cc7b964ea2e23@syzkaller.appspotmail.com
Link: https://msgid.link/20240515133410.d6cffe5756cc.I47b624a317e62bdb4609ff7fa79403c0c444d32d@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/cfg.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index b08e5d7687e3f..99abbb9e8477b 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -2958,8 +2958,9 @@ static int ieee80211_set_mcast_rate(struct wiphy *wiphy, struct net_device *dev,
 	memcpy(sdata->vif.bss_conf.mcast_rate, rate,
 	       sizeof(int) * NUM_NL80211_BANDS);
 
-	ieee80211_link_info_change_notify(sdata, &sdata->deflink,
-					  BSS_CHANGED_MCAST_RATE);
+	if (ieee80211_sdata_running(sdata))
+		ieee80211_link_info_change_notify(sdata, &sdata->deflink,
+						  BSS_CHANGED_MCAST_RATE);
 
 	return 0;
 }
-- 
GitLab


From 177c6ae9725d783f9e96f02593ce8fb2639be22f Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 15 May 2024 13:53:19 +0200
Subject: [PATCH 465/950] wifi: mac80211: handle tasklet frames before stopping

The code itself doesn't want to handle frames from the driver
if it's already stopped, but if the tasklet was queued before
and runs after the stop, then all bets are off. Flush queues
before actually stopping, RX should be off at this point since
all the interfaces are removed already, etc.

Reported-by: syzbot+8830db5d3593b5546d2e@syzkaller.appspotmail.com
Link: https://msgid.link/20240515135318.b05f11385c9a.I41c1b33a2e1814c3a7ef352cd7f2951b91785617@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/ieee80211_i.h |  2 ++
 net/mac80211/main.c        | 10 ++++++++--
 net/mac80211/util.c        |  2 ++
 3 files changed, 12 insertions(+), 2 deletions(-)

diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index eb62b7d4b4f7e..3cedfdc9099b7 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -1845,6 +1845,8 @@ void ieee80211_link_info_change_notify(struct ieee80211_sub_if_data *sdata,
 void ieee80211_configure_filter(struct ieee80211_local *local);
 u64 ieee80211_reset_erp_info(struct ieee80211_sub_if_data *sdata);
 
+void ieee80211_handle_queued_frames(struct ieee80211_local *local);
+
 u64 ieee80211_mgmt_tx_cookie(struct ieee80211_local *local);
 int ieee80211_attach_ack_skb(struct ieee80211_local *local, struct sk_buff *skb,
 			     u64 *cookie, gfp_t gfp);
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 4eaea0a9975b4..1132dea0e290e 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -423,9 +423,8 @@ u64 ieee80211_reset_erp_info(struct ieee80211_sub_if_data *sdata)
 	       BSS_CHANGED_ERP_SLOT;
 }
 
-static void ieee80211_tasklet_handler(struct tasklet_struct *t)
+void ieee80211_handle_queued_frames(struct ieee80211_local *local)
 {
-	struct ieee80211_local *local = from_tasklet(local, t, tasklet);
 	struct sk_buff *skb;
 
 	while ((skb = skb_dequeue(&local->skb_queue)) ||
@@ -450,6 +449,13 @@ static void ieee80211_tasklet_handler(struct tasklet_struct *t)
 	}
 }
 
+static void ieee80211_tasklet_handler(struct tasklet_struct *t)
+{
+	struct ieee80211_local *local = from_tasklet(local, t, tasklet);
+
+	ieee80211_handle_queued_frames(local);
+}
+
 static void ieee80211_restart_work(struct work_struct *work)
 {
 	struct ieee80211_local *local =
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 0b893e9589594..283bfc99417e5 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -1567,6 +1567,8 @@ u32 ieee80211_sta_get_rates(struct ieee80211_sub_if_data *sdata,
 
 void ieee80211_stop_device(struct ieee80211_local *local)
 {
+	ieee80211_handle_queued_frames(local);
+
 	ieee80211_led_radio(local, false);
 	ieee80211_mod_tpt_led_trig(local, 0, IEEE80211_TPT_LEDTRIG_FL_RADIO);
 
-- 
GitLab


From f7a8b10bfd614d7a9a16fbe80d28ead4f063cb00 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 10 May 2024 11:37:38 +0200
Subject: [PATCH 466/950] wifi: cfg80211: fix 6 GHz scan request building

The 6 GHz scan request struct allocated by cfg80211_scan_6ghz() is
meant to be formed this way:

 [base struct][channels][ssids][6ghz_params]

It is allocated with [channels] as the maximum number of channels
supported by the driver in the 6 GHz band, since allocation is
before knowing how many there will be.

However, the inner pointers are set incorrectly: initially, the
6 GHz scan parameters pointer is set:

 [base struct][channels]
                        ^ scan_6ghz_params

and later the SSID pointer is set to the end of the actually
_used_ channels.

 [base struct][channels]
                  ^ ssids

If many APs were to be discovered, and many channels used, and
there were many SSIDs, then the SSIDs could overlap the 6 GHz
parameters.

Additionally, the request->ssids for most of the function points
to the original request still (given the struct copy) but is used
normally, which is confusing.

Clear this up, by actually using the allocated space for 6 GHz
parameters _after_ the SSIDs, and set up the SSIDs initially so
they are used more clearly. Just like in nl80211.c, set them
only if there actually are SSIDs though.

Finally, also copy the elements (ie/ie_len) so they're part of
the same request, not pointing to the old request.

Co-developed-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Reviewed-by: Ilan Peer <ilan.peer@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Link: https://msgid.link/20240510113738.4190692ef4ee.I0cb19188be17a8abd029805e3373c0a7777c214c@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/rdev-ops.h |  6 +++++-
 net/wireless/scan.c     | 47 +++++++++++++++++++++++++++--------------
 2 files changed, 36 insertions(+), 17 deletions(-)

diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h
index 43897a5269b6a..755af47b88b91 100644
--- a/net/wireless/rdev-ops.h
+++ b/net/wireless/rdev-ops.h
@@ -2,7 +2,7 @@
 /*
  * Portions of this file
  * Copyright(c) 2016-2017 Intel Deutschland GmbH
- * Copyright (C) 2018, 2021-2023 Intel Corporation
+ * Copyright (C) 2018, 2021-2024 Intel Corporation
  */
 #ifndef __CFG80211_RDEV_OPS
 #define __CFG80211_RDEV_OPS
@@ -458,6 +458,10 @@ static inline int rdev_scan(struct cfg80211_registered_device *rdev,
 			    struct cfg80211_scan_request *request)
 {
 	int ret;
+
+	if (WARN_ON_ONCE(!request->n_ssids && request->ssids))
+		return -EINVAL;
+
 	trace_rdev_scan(&rdev->wiphy, request);
 	ret = rdev->ops->scan(&rdev->wiphy, request);
 	trace_rdev_return_int(&rdev->wiphy, ret);
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 8daed8232b054..2f2a3163968a7 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -812,6 +812,7 @@ static int cfg80211_scan_6ghz(struct cfg80211_registered_device *rdev)
 	LIST_HEAD(coloc_ap_list);
 	bool need_scan_psc = true;
 	const struct ieee80211_sband_iftype_data *iftd;
+	size_t size, offs_ssids, offs_6ghz_params, offs_ies;
 
 	rdev_req->scan_6ghz = true;
 
@@ -877,10 +878,15 @@ static int cfg80211_scan_6ghz(struct cfg80211_registered_device *rdev)
 		spin_unlock_bh(&rdev->bss_lock);
 	}
 
-	request = kzalloc(struct_size(request, channels, n_channels) +
-			  sizeof(*request->scan_6ghz_params) * count +
-			  sizeof(*request->ssids) * rdev_req->n_ssids,
-			  GFP_KERNEL);
+	size = struct_size(request, channels, n_channels);
+	offs_ssids = size;
+	size += sizeof(*request->ssids) * rdev_req->n_ssids;
+	offs_6ghz_params = size;
+	size += sizeof(*request->scan_6ghz_params) * count;
+	offs_ies = size;
+	size += rdev_req->ie_len;
+
+	request = kzalloc(size, GFP_KERNEL);
 	if (!request) {
 		cfg80211_free_coloc_ap_list(&coloc_ap_list);
 		return -ENOMEM;
@@ -888,8 +894,26 @@ static int cfg80211_scan_6ghz(struct cfg80211_registered_device *rdev)
 
 	*request = *rdev_req;
 	request->n_channels = 0;
-	request->scan_6ghz_params =
-		(void *)&request->channels[n_channels];
+	request->n_6ghz_params = 0;
+	if (rdev_req->n_ssids) {
+		/*
+		 * Add the ssids from the parent scan request to the new
+		 * scan request, so the driver would be able to use them
+		 * in its probe requests to discover hidden APs on PSC
+		 * channels.
+		 */
+		request->ssids = (void *)request + offs_ssids;
+		memcpy(request->ssids, rdev_req->ssids,
+		       sizeof(*request->ssids) * request->n_ssids);
+	}
+	request->scan_6ghz_params = (void *)request + offs_6ghz_params;
+
+	if (rdev_req->ie_len) {
+		void *ie = (void *)request + offs_ies;
+
+		memcpy(ie, rdev_req->ie, rdev_req->ie_len);
+		request->ie = ie;
+	}
 
 	/*
 	 * PSC channels should not be scanned in case of direct scan with 1 SSID
@@ -978,17 +1002,8 @@ skip:
 
 	if (request->n_channels) {
 		struct cfg80211_scan_request *old = rdev->int_scan_req;
-		rdev->int_scan_req = request;
 
-		/*
-		 * Add the ssids from the parent scan request to the new scan
-		 * request, so the driver would be able to use them in its
-		 * probe requests to discover hidden APs on PSC channels.
-		 */
-		request->ssids = (void *)&request->channels[request->n_channels];
-		request->n_ssids = rdev_req->n_ssids;
-		memcpy(request->ssids, rdev_req->ssids, sizeof(*request->ssids) *
-		       request->n_ssids);
+		rdev->int_scan_req = request;
 
 		/*
 		 * If this scan follows a previous scan, save the scan start
-- 
GitLab


From 8ecc4d7a7cd3e9704b63b8e4f6cd8b6b7314210f Mon Sep 17 00:00:00 2001
From: Aditya Kumar Singh <quic_adisi@quicinc.com>
Date: Thu, 9 May 2024 08:55:55 +0530
Subject: [PATCH 467/950] wifi: mac80211: pass proper link id for channel
 switch started notification

Original changes[1] posted is having proper changes. However, at the same
time, there was chandef puncturing changes which had a conflict with this.
While applying, two errors crept in -
   a) Whitespace error.
   b) Link ID being passed to channel switch started notifier function is
      0. However proper link ID is present in the function.

Fix these now.

[1] https://lore.kernel.org/all/20240130140918.1172387-5-quic_adisi@quicinc.com/

Fixes: 1a96bb4e8a79 ("wifi: mac80211: start and finalize channel switch on link basis")
Signed-off-by: Aditya Kumar Singh <quic_adisi@quicinc.com>
Link: https://msgid.link/20240509032555.263933-1-quic_adisi@quicinc.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/cfg.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 99abbb9e8477b..83ad6c9709fe6 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -4017,7 +4017,7 @@ __ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev,
 		goto out;
 	}
 
-	link_data->csa_chanreq = chanreq; 
+	link_data->csa_chanreq = chanreq;
 	link_conf->csa_active = true;
 
 	if (params->block_tx &&
@@ -4028,7 +4028,7 @@ __ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev,
 	}
 
 	cfg80211_ch_switch_started_notify(sdata->dev,
-					  &link_data->csa_chanreq.oper, 0,
+					  &link_data->csa_chanreq.oper, link_id,
 					  params->count, params->block_tx);
 
 	if (changed) {
-- 
GitLab


From 92158790ce4391ce4c35d8dfbce759195e4724cb Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Sun, 12 May 2024 15:25:00 +0300
Subject: [PATCH 468/950] wifi: iwlwifi: mvm: don't initialize csa_work twice

The initialization of this worker moved to iwl_mvm_mac_init_mvmvif
but we removed only from the pre-MLD version of the add_interface
callback. Remove it also from the MLD version.

Fixes: 0bcc2155983e ("wifi: iwlwifi: mvm: init vif works only once")
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Reviewed-by: Johannes Berg <johannes.berg@intel.com>
Link: https://msgid.link/20240512152312.4f15b41604f0.Iec912158e5a706175531d3736d77d25adf02fba4@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
index 0a3b7284eeddf..fcfd2dd7568e5 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
@@ -75,8 +75,6 @@ static int iwl_mvm_mld_mac_add_interface(struct ieee80211_hw *hw,
 		goto out_free_bf;
 
 	iwl_mvm_tcm_add_vif(mvm, vif);
-	INIT_DELAYED_WORK(&mvmvif->csa_work,
-			  iwl_mvm_channel_switch_disconnect_wk);
 
 	if (vif->type == NL80211_IFTYPE_MONITOR) {
 		mvm->monitor_on = true;
-- 
GitLab


From 98b7017ddb914a32152ed9aec7468386fff85f8f Mon Sep 17 00:00:00 2001
From: Shaul Triebitz <shaul.triebitz@intel.com>
Date: Sun, 12 May 2024 15:25:04 +0300
Subject: [PATCH 469/950] wifi: iwlwifi: mvm: always set the TWT IE offset

In beacon template version 14, make sure to always set
the TWT IE offset before sending the beacon template command,
also in the debugfs inject_beacon_ie path.
If the TWT IE does not exist, the offset will be set to zero.

Fixes: bf0212fd8faa ("wifi: iwlwifi: mvm: add beacon template version 14")
Signed-off-by: Shaul Triebitz <shaul.triebitz@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240512152312.eb27175c345a.If30ef24aba10fe47fd42a7a9703eb8903035e294@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c  | 9 +++++++++
 drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c | 2 +-
 drivers/net/wireless/intel/iwlwifi/mvm/mvm.h      | 1 +
 3 files changed, 11 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
index 79f4ac8cbc729..8101ecbb478b6 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
@@ -1617,6 +1617,15 @@ static int _iwl_dbgfs_inject_beacon_ie(struct iwl_mvm *mvm, char *bin, int len)
 					 &beacon_cmd.tim_size,
 					 beacon->data, beacon->len);
 
+		if (iwl_fw_lookup_cmd_ver(mvm->fw,
+					  BEACON_TEMPLATE_CMD, 0) >= 14) {
+			u32 offset = iwl_mvm_find_ie_offset(beacon->data,
+							    WLAN_EID_S1G_TWT,
+							    beacon->len);
+
+			beacon_cmd.btwt_offset = cpu_to_le32(offset);
+		}
+
 		iwl_mvm_mac_ctxt_send_beacon_cmd(mvm, beacon, &beacon_cmd,
 						 sizeof(beacon_cmd));
 	}
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
index 5a06f887769a6..5144fa0f96b0e 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
@@ -873,7 +873,7 @@ void iwl_mvm_mac_ctxt_set_tim(struct iwl_mvm *mvm,
 	}
 }
 
-static u32 iwl_mvm_find_ie_offset(u8 *beacon, u8 eid, u32 frame_size)
+u32 iwl_mvm_find_ie_offset(u8 *beacon, u8 eid, u32 frame_size)
 {
 	struct ieee80211_mgmt *mgmt = (void *)beacon;
 	const u8 *ie;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index 1f58c727fa632..0a1959bd40799 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -1758,6 +1758,7 @@ u8 iwl_mvm_next_antenna(struct iwl_mvm *mvm, u8 valid, u8 last_idx);
 void iwl_mvm_get_sync_time(struct iwl_mvm *mvm, int clock_type, u32 *gp2,
 			   u64 *boottime, ktime_t *realtime);
 u32 iwl_mvm_get_systime(struct iwl_mvm *mvm);
+u32 iwl_mvm_find_ie_offset(u8 *beacon, u8 eid, u32 frame_size);
 
 /* Tx / Host Commands */
 int __must_check iwl_mvm_send_cmd(struct iwl_mvm *mvm,
-- 
GitLab


From 788e4c75f831d06fcfbbec1d455fac429521e607 Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Sun, 12 May 2024 07:31:06 +0300
Subject: [PATCH 470/950] wifi: iwlwifi: mvm: fix a crash on 7265

Since IWL_FW_CMD_VER_UNKNOWN = 99, then my change to consider
cmd_ver >= 7 instead of cmd_ver = 7 included also firmwares that don't
advertise the command version at all. This made us send a command with a
bad size and because of that, the firmware hit a BAD_COMMAND immediately
after handling the REDUCE_TX_POWER_CMD command.

Fixes: 8f892e225f41 ("wifi: iwlwifi: mvm: support iwl_dev_tx_power_cmd_v8")
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Reviewed-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240512072733.eb20ff5050d3.Ie4fc6f5496cd296fd6ff20d15e98676f28a3cccd@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/fw.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
index e7f5978ef2d71..ca7fcae6995ee 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
@@ -895,8 +895,8 @@ int iwl_mvm_sar_select_profile(struct iwl_mvm *mvm, int prof_a, int prof_b)
 	int ret;
 	u16 len = 0;
 	u32 n_subbands;
-	u8 cmd_ver = iwl_fw_lookup_cmd_ver(mvm->fw, cmd_id,
-					   IWL_FW_CMD_VER_UNKNOWN);
+	u8 cmd_ver = iwl_fw_lookup_cmd_ver(mvm->fw, cmd_id, 3);
+
 	if (cmd_ver >= 7) {
 		len = sizeof(cmd.v7);
 		n_subbands = IWL_NUM_SUB_BANDS_V2;
-- 
GitLab


From b7ffca99313d856f7d1cc89038d9061b128e8e97 Mon Sep 17 00:00:00 2001
From: Yedidya Benshimol <yedidya.ben.shimol@intel.com>
Date: Fri, 10 May 2024 17:06:29 +0300
Subject: [PATCH 471/950] wifi: iwlwifi: mvm: d3: fix WoWLAN command version
 lookup

After moving from commands to notificaitons in the d3 resume flow,
removing the WOWLAN_GET_STATUSES and REPLY_OFFLOADS_QUERY_CMD causes
the return of the default value when looking up their version.
Returning zero here results in the driver sending the not supported
NON_QOS_TX_COUNTER_CMD.

Signed-off-by: Yedidya Benshimol <yedidya.ben.shimol@intel.com>
Reviewed-by: Gregory Greenman <gregory.greenman@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240510170500.8cabfd580614.If3a0db9851f56041f8f5360959354abd5379224a@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/d3.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
index 71e6b06481a93..e37ae34acba60 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
@@ -2341,7 +2341,8 @@ static bool iwl_mvm_setup_connection_keep(struct iwl_mvm *mvm,
 
 out:
 	if (iwl_fw_lookup_notif_ver(mvm->fw, LONG_GROUP,
-				    WOWLAN_GET_STATUSES, 0) < 10) {
+				    WOWLAN_GET_STATUSES,
+				    IWL_FW_CMD_VER_UNKNOWN) < 10) {
 		mvmvif->seqno_valid = true;
 		/* +0x10 because the set API expects next-to-use, not last-used */
 		mvmvif->seqno = status->non_qos_seq_ctr + 0x10;
-- 
GitLab


From 4a7aace2899711592327463c1a29ffee44fcc66e Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 10 May 2024 17:06:33 +0300
Subject: [PATCH 472/950] wifi: iwlwifi: mvm: revert gen2 TX A-MPDU size to 64

We don't actually support >64 even for HE devices, so revert
back to 64. This fixes an issue where the session is refused
because the queue is configured differently from the actual
session later.

Fixes: 514c30696fbc ("iwlwifi: add support for IEEE802.11ax")
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Reviewed-by: Liad Kaufman <liad.kaufman@intel.com>
Reviewed-by: Luciano Coelho <luciano.coelho@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240510170500.52f7b4cf83aa.If47e43adddf7fe250ed7f5571fbb35d8221c7c47@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/rs.h | 9 ++-------
 1 file changed, 2 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs.h b/drivers/net/wireless/intel/iwlwifi/mvm/rs.h
index 376b23b409dca..6cd4ec4d8f344 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rs.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs.h
@@ -122,13 +122,8 @@ enum {
 
 #define LINK_QUAL_AGG_FRAME_LIMIT_DEF	(63)
 #define LINK_QUAL_AGG_FRAME_LIMIT_MAX	(63)
-/*
- * FIXME - various places in firmware API still use u8,
- * e.g. LQ command and SCD config command.
- * This should be 256 instead.
- */
-#define LINK_QUAL_AGG_FRAME_LIMIT_GEN2_DEF	(255)
-#define LINK_QUAL_AGG_FRAME_LIMIT_GEN2_MAX	(255)
+#define LINK_QUAL_AGG_FRAME_LIMIT_GEN2_DEF	(64)
+#define LINK_QUAL_AGG_FRAME_LIMIT_GEN2_MAX	(64)
 #define LINK_QUAL_AGG_FRAME_LIMIT_MIN	(0)
 
 #define LQ_SIZE		2	/* 2 mode tables:  "Active" and "Search" */
-- 
GitLab


From 0f2e9f6f21d1ff292363cdfb5bc4d492eeaff76e Mon Sep 17 00:00:00 2001
From: Mordechay Goodstein <mordechay.goodstein@intel.com>
Date: Fri, 10 May 2024 17:06:35 +0300
Subject: [PATCH 473/950] wifi: iwlwifi: mvm: set properly mac header

In the driver we only use skb_put* for adding data to the skb, hence data
never moves and skb_reset_mac_haeder would set mac_header to the first
time data was added and not to mac80211 header, fix this my using the
actual len of bytes added for setting the mac header.

Fixes: 3f7a9d577d47 ("wifi: iwlwifi: mvm: simplify by using SKB MAC header pointer")
Signed-off-by: Mordechay Goodstein <mordechay.goodstein@intel.com>
Reviewed-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240510170500.12f2de2909c3.I72a819b96f2fe55bde192a8fd31a4b96c301aa73@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
index d78af29281522..489cfb0a4ab1e 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
@@ -2450,8 +2450,11 @@ void iwl_mvm_rx_monitor_no_data(struct iwl_mvm *mvm, struct napi_struct *napi,
 	 *
 	 * We mark it as mac header, for upper layers to know where
 	 * all radio tap header ends.
+	 *
+	 * Since data doesn't move data while putting data on skb and that is
+	 * the only way we use, data + len is the next place that hdr would be put
 	 */
-	skb_reset_mac_header(skb);
+	skb_set_mac_header(skb, skb->len);
 
 	/*
 	 * Override the nss from the rx_vec since the rate_n_flags has
-- 
GitLab


From 87821b67dea87addbc4ab093ba752753b002176a Mon Sep 17 00:00:00 2001
From: Shahar S Matityahu <shahar.s.matityahu@intel.com>
Date: Fri, 10 May 2024 17:06:39 +0300
Subject: [PATCH 474/950] wifi: iwlwifi: dbg_ini: move iwl_dbg_tlv_free outside
 of debugfs ifdef

The driver should call iwl_dbg_tlv_free even if debugfs is not defined
since ini mode does not depend on debugfs ifdef.

Fixes: 68f6f492c4fa ("iwlwifi: trans: support loading ini TLVs from external file")
Signed-off-by: Shahar S Matityahu <shahar.s.matityahu@intel.com>
Reviewed-by: Luciano Coelho <luciano.coelho@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240510170500.c8e3723f55b0.I5e805732b0be31ee6b83c642ec652a34e974ff10@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/iwl-drv.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
index 33654f228ee87..d156a9c641940 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
@@ -1815,8 +1815,8 @@ struct iwl_drv *iwl_drv_start(struct iwl_trans *trans)
 err_fw:
 #ifdef CONFIG_IWLWIFI_DEBUGFS
 	debugfs_remove_recursive(drv->dbgfs_drv);
-	iwl_dbg_tlv_free(drv->trans);
 #endif
+	iwl_dbg_tlv_free(drv->trans);
 	kfree(drv);
 err:
 	return ERR_PTR(ret);
-- 
GitLab


From cc3ba78f202de9752aceb16342ab62bdfbffac7e Mon Sep 17 00:00:00 2001
From: Benjamin Berg <benjamin.berg@intel.com>
Date: Mon, 13 May 2024 13:27:08 +0300
Subject: [PATCH 475/950] wifi: iwlwifi: mvm: remove stale STA link data during
 restart

If pre-recovery mac80211 tried to disable a link but this disablement
failed, then there might be a mismatch between mac80211 assuming the
link has been disabled and the driver still having the data around.
During recover itself, that is not a problem, but should the link be
activated again at a later point, iwlwifi will refuse the activation as
it detects the inconsistent state.

Solve this corner-case by iterating the station in the restart cleanup
handler.

Signed-off-by: Benjamin Berg <benjamin.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240513132416.d2fd60338055.I840d4fdce5fd49fe69896d928b071067e3730259@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 .../net/wireless/intel/iwlwifi/mvm/mac80211.c | 37 +++++++++++++++++++
 .../net/wireless/intel/iwlwifi/mvm/mld-sta.c  | 10 ++---
 drivers/net/wireless/intel/iwlwifi/mvm/sta.h  |  5 +++
 3 files changed, 47 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index 486a6b8f3c97f..628b50ee02443 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -1128,6 +1128,39 @@ static void iwl_mvm_cleanup_iterator(void *data, u8 *mac,
 	RCU_INIT_POINTER(mvmvif->deflink.probe_resp_data, NULL);
 }
 
+static void iwl_mvm_cleanup_sta_iterator(void *data, struct ieee80211_sta *sta)
+{
+	struct iwl_mvm *mvm = data;
+	struct iwl_mvm_sta *mvm_sta;
+	struct ieee80211_vif *vif;
+	int link_id;
+
+	mvm_sta = iwl_mvm_sta_from_mac80211(sta);
+	vif = mvm_sta->vif;
+
+	if (!sta->valid_links)
+		return;
+
+	for (link_id = 0; link_id < ARRAY_SIZE((sta)->link); link_id++) {
+		struct iwl_mvm_link_sta *mvm_link_sta;
+
+		mvm_link_sta =
+			rcu_dereference_check(mvm_sta->link[link_id],
+					      lockdep_is_held(&mvm->mutex));
+		if (mvm_link_sta && !(vif->active_links & BIT(link_id))) {
+			/*
+			 * We have a link STA but the link is inactive in
+			 * mac80211. This will happen if we failed to
+			 * deactivate the link but mac80211 roll back the
+			 * deactivation of the link.
+			 * Delete the stale data to avoid issues later on.
+			 */
+			iwl_mvm_mld_free_sta_link(mvm, mvm_sta, mvm_link_sta,
+						  link_id, false);
+		}
+	}
+}
+
 static void iwl_mvm_restart_cleanup(struct iwl_mvm *mvm)
 {
 	iwl_mvm_stop_device(mvm);
@@ -1150,6 +1183,10 @@ static void iwl_mvm_restart_cleanup(struct iwl_mvm *mvm)
 	 */
 	ieee80211_iterate_interfaces(mvm->hw, 0, iwl_mvm_cleanup_iterator, mvm);
 
+	/* cleanup stations as links may be gone after restart */
+	ieee80211_iterate_stations_atomic(mvm->hw,
+					  iwl_mvm_cleanup_sta_iterator, mvm);
+
 	mvm->p2p_device_vif = NULL;
 
 	iwl_mvm_reset_phy_ctxts(mvm);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c
index b7a461dba41ee..ae3cde0e64f3f 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c
@@ -515,11 +515,11 @@ static int iwl_mvm_mld_cfg_sta(struct iwl_mvm *mvm, struct ieee80211_sta *sta,
 	return iwl_mvm_mld_send_sta_cmd(mvm, &cmd);
 }
 
-static void iwl_mvm_mld_free_sta_link(struct iwl_mvm *mvm,
-				      struct iwl_mvm_sta *mvm_sta,
-				      struct iwl_mvm_link_sta *mvm_sta_link,
-				      unsigned int link_id,
-				      bool is_in_fw)
+void iwl_mvm_mld_free_sta_link(struct iwl_mvm *mvm,
+			       struct iwl_mvm_sta *mvm_sta,
+			       struct iwl_mvm_link_sta *mvm_sta_link,
+			       unsigned int link_id,
+			       bool is_in_fw)
 {
 	RCU_INIT_POINTER(mvm->fw_id_to_mac_id[mvm_sta_link->sta_id],
 			 is_in_fw ? ERR_PTR(-EINVAL) : NULL);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h
index 264f1f9394b6d..754a05a8c189b 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h
@@ -662,6 +662,11 @@ int iwl_mvm_mld_update_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 			   struct ieee80211_sta *sta);
 int iwl_mvm_mld_rm_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 		       struct ieee80211_sta *sta);
+void iwl_mvm_mld_free_sta_link(struct iwl_mvm *mvm,
+			       struct iwl_mvm_sta *mvm_sta,
+			       struct iwl_mvm_link_sta *mvm_sta_link,
+			       unsigned int link_id,
+			       bool is_in_fw);
 int iwl_mvm_mld_rm_sta_id(struct iwl_mvm *mvm, u8 sta_id);
 int iwl_mvm_mld_update_sta_links(struct iwl_mvm *mvm,
 				 struct ieee80211_vif *vif,
-- 
GitLab


From 08b16d1b5997dc378533318e2a9cd73c7a898284 Mon Sep 17 00:00:00 2001
From: Yedidya Benshimol <yedidya.ben.shimol@intel.com>
Date: Mon, 13 May 2024 13:27:09 +0300
Subject: [PATCH 476/950] wifi: iwlwifi: mvm: Handle BIGTK cipher in kek_kck
 cmd

The BIGTK cipher field was added to the kek_kck_material_cmd
but wasn't assigned. Fix that by differentiating between the
IGTK/BIGTK keys and assign the ciphers fields accordingly.

Signed-off-by: Yedidya Benshimol <yedidya.ben.shimol@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240513132416.7fd0b22b7267.Ie9b581652b74bd7806980364d59e1b2e78e682c0@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/d3.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
index e37ae34acba60..54f4acbbd05bd 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
@@ -595,6 +595,12 @@ static void iwl_mvm_wowlan_gtk_type_iter(struct ieee80211_hw *hw,
 					 void *_data)
 {
 	struct wowlan_key_gtk_type_iter *data = _data;
+	__le32 *cipher = NULL;
+
+	if (key->keyidx == 4 || key->keyidx == 5)
+		cipher = &data->kek_kck_cmd->igtk_cipher;
+	if (key->keyidx == 6 || key->keyidx == 7)
+		cipher = &data->kek_kck_cmd->bigtk_cipher;
 
 	switch (key->cipher) {
 	default:
@@ -606,10 +612,13 @@ static void iwl_mvm_wowlan_gtk_type_iter(struct ieee80211_hw *hw,
 		return;
 	case WLAN_CIPHER_SUITE_BIP_GMAC_256:
 	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
-		data->kek_kck_cmd->igtk_cipher = cpu_to_le32(STA_KEY_FLG_GCMP);
+		if (cipher)
+			*cipher = cpu_to_le32(STA_KEY_FLG_GCMP);
 		return;
 	case WLAN_CIPHER_SUITE_AES_CMAC:
-		data->kek_kck_cmd->igtk_cipher = cpu_to_le32(STA_KEY_FLG_CCM);
+	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
+		if (cipher)
+			*cipher = cpu_to_le32(STA_KEY_FLG_CCM);
 		return;
 	case WLAN_CIPHER_SUITE_CCMP:
 		if (!sta)
-- 
GitLab


From 4d08c0b3357cba0aeffaf3abc62cae0c154f2816 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 13 May 2024 13:27:10 +0300
Subject: [PATCH 477/950] wifi: iwlwifi: mvm: handle BA session teardown in
 RF-kill

When entering RF-kill, mac80211 tears down BA sessions, but
due to RF-kill the commands aren't sent to the device. As a
result, there can be frames pending on the reorder buffer or
perhaps even received while doing so, leading to warnings.

Avoid the warnings by doing the BA session teardown normally
even in RF-kill, which also requires queue sync.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240513132416.0762cd80fb3d.I43c5877f3b546159b2db4f36d6d956b333c41cf0@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c |  2 +-
 drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c  |  3 ++-
 drivers/net/wireless/intel/iwlwifi/mvm/sta.c      | 12 ++++++++----
 3 files changed, 11 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index 628b50ee02443..de9f0b4465456 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -6385,7 +6385,7 @@ void iwl_mvm_sync_rx_queues_internal(struct iwl_mvm *mvm,
 		.len[0] = sizeof(cmd),
 		.data[1] = data,
 		.len[1] = size,
-		.flags = sync ? 0 : CMD_ASYNC,
+		.flags = CMD_SEND_IN_RFKILL | (sync ? 0 : CMD_ASYNC),
 	};
 	int ret;
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c
index ae3cde0e64f3f..9d139b56e1527 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c
@@ -1014,7 +1014,8 @@ static int iwl_mvm_mld_update_sta_baids(struct iwl_mvm *mvm,
 
 		cmd.modify.tid = cpu_to_le32(data->tid);
 
-		ret = iwl_mvm_send_cmd_pdu(mvm, cmd_id, 0, sizeof(cmd), &cmd);
+		ret = iwl_mvm_send_cmd_pdu(mvm, cmd_id, CMD_SEND_IN_RFKILL,
+					   sizeof(cmd), &cmd);
 		data->sta_mask = new_sta_mask;
 		if (ret)
 			return ret;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
index 20d4968d692a3..cc79fe991c263 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
@@ -2848,7 +2848,12 @@ static int iwl_mvm_fw_baid_op_cmd(struct iwl_mvm *mvm,
 		.action = start ? cpu_to_le32(IWL_RX_BAID_ACTION_ADD) :
 				  cpu_to_le32(IWL_RX_BAID_ACTION_REMOVE),
 	};
-	u32 cmd_id = WIDE_ID(DATA_PATH_GROUP, RX_BAID_ALLOCATION_CONFIG_CMD);
+	struct iwl_host_cmd hcmd = {
+		.id = WIDE_ID(DATA_PATH_GROUP, RX_BAID_ALLOCATION_CONFIG_CMD),
+		.flags = CMD_SEND_IN_RFKILL,
+		.len[0] = sizeof(cmd),
+		.data[0] = &cmd,
+	};
 	int ret;
 
 	BUILD_BUG_ON(sizeof(struct iwl_rx_baid_cfg_resp) != sizeof(baid));
@@ -2860,7 +2865,7 @@ static int iwl_mvm_fw_baid_op_cmd(struct iwl_mvm *mvm,
 		cmd.alloc.ssn = cpu_to_le16(ssn);
 		cmd.alloc.win_size = cpu_to_le16(buf_size);
 		baid = -EIO;
-	} else if (iwl_fw_lookup_cmd_ver(mvm->fw, cmd_id, 1) == 1) {
+	} else if (iwl_fw_lookup_cmd_ver(mvm->fw, hcmd.id, 1) == 1) {
 		cmd.remove_v1.baid = cpu_to_le32(baid);
 		BUILD_BUG_ON(sizeof(cmd.remove_v1) > sizeof(cmd.remove));
 	} else {
@@ -2869,8 +2874,7 @@ static int iwl_mvm_fw_baid_op_cmd(struct iwl_mvm *mvm,
 		cmd.remove.tid = cpu_to_le32(tid);
 	}
 
-	ret = iwl_mvm_send_cmd_pdu_status(mvm, cmd_id, sizeof(cmd),
-					  &cmd, &baid);
+	ret = iwl_mvm_send_cmd_status(mvm, &hcmd, &baid);
 	if (ret)
 		return ret;
 
-- 
GitLab


From 989830d1cf16bd149bf0690d889a9caef95fb5b1 Mon Sep 17 00:00:00 2001
From: Ayala Beker <ayala.beker@intel.com>
Date: Mon, 13 May 2024 13:27:11 +0300
Subject: [PATCH 478/950] wifi: iwlwifi: mvm: properly set 6 GHz channel direct
 probe option

Ensure that the 6 GHz channel is configured with a valid direct BSSID,
avoiding any invalid or multicast BSSID addresses.

Signed-off-by: Ayala Beker <ayala.beker@intel.com>
Reviewed-by: Ilan Peer <ilan.peer@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240513132416.91a631a0fe60.I2ea2616af9b8a2eaf959b156c69cf65a2f1204d4@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/scan.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
index a7ec172eeade8..890d4d79b172b 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
@@ -1730,7 +1730,10 @@ iwl_mvm_umac_scan_fill_6g_chan_list(struct iwl_mvm *mvm,
 				break;
 		}
 
-		if (k == idex_b && idex_b < SCAN_BSSID_MAX_SIZE) {
+		if (k == idex_b && idex_b < SCAN_BSSID_MAX_SIZE &&
+		    !WARN_ONCE(!is_valid_ether_addr(scan_6ghz_params[j].bssid),
+			       "scan: invalid BSSID at index %u, index_b=%u\n",
+			       j, idex_b)) {
 			memcpy(&pp->bssid_array[idex_b++],
 			       scan_6ghz_params[j].bssid, ETH_ALEN);
 		}
-- 
GitLab


From 60d62757df30b74bf397a2847a6db7385c6ee281 Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Mon, 13 May 2024 13:27:12 +0300
Subject: [PATCH 479/950] wifi: iwlwifi: mvm: check n_ssids before accessing
 the ssids

In some versions of cfg80211, the ssids poinet might be a valid one even
though n_ssids is 0. Accessing the pointer in this case will cuase an
out-of-bound access. Fix this by checking n_ssids first.

Fixes: c1a7515393e4 ("iwlwifi: mvm: add adaptive dwell support")
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Reviewed-by: Ilan Peer <ilan.peer@intel.com>
Reviewed-by: Johannes Berg <johannes.berg@intel.com>
Link: https://msgid.link/20240513132416.6e4d1762bf0d.I5a0e6cc8f02050a766db704d15594c61fe583d45@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/scan.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
index 890d4d79b172b..9739c38ef8241 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
@@ -1313,7 +1313,7 @@ static void iwl_mvm_scan_umac_dwell(struct iwl_mvm *mvm,
 		if (IWL_MVM_ADWELL_MAX_BUDGET)
 			cmd->v7.adwell_max_budget =
 				cpu_to_le16(IWL_MVM_ADWELL_MAX_BUDGET);
-		else if (params->ssids && params->ssids[0].ssid_len)
+		else if (params->n_ssids && params->ssids[0].ssid_len)
 			cmd->v7.adwell_max_budget =
 				cpu_to_le16(IWL_SCAN_ADWELL_MAX_BUDGET_DIRECTED_SCAN);
 		else
@@ -1418,7 +1418,7 @@ iwl_mvm_scan_umac_dwell_v11(struct iwl_mvm *mvm,
 	if (IWL_MVM_ADWELL_MAX_BUDGET)
 		general_params->adwell_max_budget =
 			cpu_to_le16(IWL_MVM_ADWELL_MAX_BUDGET);
-	else if (params->ssids && params->ssids[0].ssid_len)
+	else if (params->n_ssids && params->ssids[0].ssid_len)
 		general_params->adwell_max_budget =
 			cpu_to_le16(IWL_SCAN_ADWELL_MAX_BUDGET_DIRECTED_SCAN);
 	else
-- 
GitLab


From e6dd2936ce7ce94a1915b799f8af8193ec628e87 Mon Sep 17 00:00:00 2001
From: Ilan Peer <ilan.peer@intel.com>
Date: Mon, 13 May 2024 13:27:13 +0300
Subject: [PATCH 480/950] wifi: iwlwifi: mvm: Fix scan abort handling with HW
 rfkill

When HW rfkill is toggled to disable the RF, the flow to stop scan is
called. When trying to send the command to abort the scan, since
HW rfkill is toggled, the command is not sent due to rfkill being
asserted, and -ERFKILL is returned from iwl_trans_send_cmd(), but this
is silently ignored in iwl_mvm_send_cmd() and thus the scan abort flow
continues to wait for scan complete notification and fails. Since it
fails, the UID to type mapping is not cleared, and thus a warning is
later fired when trying to stop the interface.

To fix this, modify the UMAC scan abort flow to force sending the
scan abort command even when in rfkill, so stop the FW from accessing
the radio etc.

Signed-off-by: Ilan Peer <ilan.peer@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240513132416.8cbe2f8c1a97.Iffe235c12a919dafec88eef399eb1f7bae2c5bdb@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/scan.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
index 9739c38ef8241..b5f664ae5a17d 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
@@ -3322,10 +3322,11 @@ static int iwl_mvm_umac_scan_abort(struct iwl_mvm *mvm, int type)
 
 	ret = iwl_mvm_send_cmd_pdu(mvm,
 				   WIDE_ID(IWL_ALWAYS_LONG_GROUP, SCAN_ABORT_UMAC),
-				   0, sizeof(cmd), &cmd);
+				   CMD_SEND_IN_RFKILL, sizeof(cmd), &cmd);
 	if (!ret)
 		mvm->scan_uid_status[uid] = type << IWL_MVM_SCAN_STOPPING_SHIFT;
 
+	IWL_DEBUG_SCAN(mvm, "Scan abort: ret=%d\n", ret);
 	return ret;
 }
 
-- 
GitLab


From 4bb95f4535489ed830cf9b34b0a891e384d1aee4 Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Mon, 13 May 2024 13:27:14 +0300
Subject: [PATCH 481/950] wifi: iwlwifi: mvm: don't read past the mfuart
 notifcation

In case the firmware sends a notification that claims it has more data
than it has, we will read past that was allocated for the notification.
Remove the print of the buffer, we won't see it by default. If needed,
we can see the content with tracing.

This was reported by KFENCE.

Fixes: bdccdb854f2f ("iwlwifi: mvm: support MFUART dump in case of MFUART assert")
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Reviewed-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240513132416.ba82a01a559e.Ia91dd20f5e1ca1ad380b95e68aebf2794f553d9b@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/fw.c | 10 ----------
 1 file changed, 10 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
index ca7fcae6995ee..f4937a100cbe9 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
@@ -94,20 +94,10 @@ void iwl_mvm_mfu_assert_dump_notif(struct iwl_mvm *mvm,
 {
 	struct iwl_rx_packet *pkt = rxb_addr(rxb);
 	struct iwl_mfu_assert_dump_notif *mfu_dump_notif = (void *)pkt->data;
-	__le32 *dump_data = mfu_dump_notif->data;
-	int n_words = le32_to_cpu(mfu_dump_notif->data_size) / sizeof(__le32);
-	int i;
 
 	if (mfu_dump_notif->index_num == 0)
 		IWL_INFO(mvm, "MFUART assert id 0x%x occurred\n",
 			 le32_to_cpu(mfu_dump_notif->assert_id));
-
-	for (i = 0; i < n_words; i++)
-		IWL_DEBUG_INFO(mvm,
-			       "MFUART assert dump, dword %u: 0x%08x\n",
-			       le16_to_cpu(mfu_dump_notif->index_num) *
-			       n_words + i,
-			       le32_to_cpu(dump_data[i]));
 }
 
 static bool iwl_alive_fn(struct iwl_notif_wait_data *notif_wait,
-- 
GitLab


From 0c2fd18f7ec552796179c14f13a0e06942f09d16 Mon Sep 17 00:00:00 2001
From: Lingbo Kong <quic_lingbok@quicinc.com>
Date: Thu, 16 May 2024 10:18:53 +0800
Subject: [PATCH 482/950] wifi: mac80211: fix Spatial Reuse element size check
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently, the way to check the size of Spatial Reuse IE data in the
ieee80211_parse_extension_element() is incorrect.

This is because the len variable in the ieee80211_parse_extension_element()
function is equal to the size of Spatial Reuse IE data minus one and the
value of returned by the ieee80211_he_spr_size() function is equal to
the length of Spatial Reuse IE data. So the result of the
len >= ieee80211_he_spr_size(data) statement always false.

To address this issue and make it consistent with the logic used elsewhere
with ieee80211_he_oper_size(), change the
"len >= ieee80211_he_spr_size(data)" to
“len >= ieee80211_he_spr_size(data) - 1”.

Fixes: 9d0480a7c05b ("wifi: mac80211: move element parsing to a new file")
Signed-off-by: Lingbo Kong <quic_lingbok@quicinc.com>
Link: https://msgid.link/20240516021854.5682-2-quic_lingbok@quicinc.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/parse.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/mac80211/parse.c b/net/mac80211/parse.c
index 55e5497f89781..055a60e90979b 100644
--- a/net/mac80211/parse.c
+++ b/net/mac80211/parse.c
@@ -111,7 +111,7 @@ ieee80211_parse_extension_element(u32 *crc,
 		if (params->mode < IEEE80211_CONN_MODE_HE)
 			break;
 		if (len >= sizeof(*elems->he_spr) &&
-		    len >= ieee80211_he_spr_size(data))
+		    len >= ieee80211_he_spr_size(data) - 1)
 			elems->he_spr = data;
 		break;
 	case WLAN_EID_EXT_HE_6GHZ_CAPA:
-- 
GitLab


From a26d8dc5227f449a54518a8b40733a54c6600a8b Mon Sep 17 00:00:00 2001
From: Lingbo Kong <quic_lingbok@quicinc.com>
Date: Thu, 16 May 2024 10:18:54 +0800
Subject: [PATCH 483/950] wifi: mac80211: correctly parse Spatial Reuse
 Parameter Set element

Currently, the way of parsing Spatial Reuse Parameter Set element is
incorrect and some members of struct ieee80211_he_obss_pd are not assigned.

To address this issue, it must be parsed in the order of the elements of
Spatial Reuse Parameter Set defined in the IEEE Std 802.11ax specification.

The diagram of the Spatial Reuse Parameter Set element (IEEE Std 802.11ax
-2021-9.4.2.252).

-------------------------------------------------------------------------
|       |      |         |       |Non-SRG|  SRG  | SRG   | SRG  | SRG   |
|Element|Length| Element |  SR   |OBSS PD|OBSS PD|OBSS PD| BSS  |Partial|
|   ID  |      |   ID    |Control|  Max  |  Min  | Max   |Color | BSSID |
|       |      |Extension|       | Offset| Offset|Offset |Bitmap|Bitmap |
-------------------------------------------------------------------------

Fixes: 1ced169cc1c2 ("mac80211: allow setting spatial reuse parameters from bss_conf")
Signed-off-by: Lingbo Kong <quic_lingbok@quicinc.com>
Link: https://msgid.link/20240516021854.5682-3-quic_lingbok@quicinc.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/he.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/net/mac80211/he.c b/net/mac80211/he.c
index 9f5ffdc9db284..ecbb042dd0433 100644
--- a/net/mac80211/he.c
+++ b/net/mac80211/he.c
@@ -230,15 +230,21 @@ ieee80211_he_spr_ie_to_bss_conf(struct ieee80211_vif *vif,
 
 	if (!he_spr_ie_elem)
 		return;
+
+	he_obss_pd->sr_ctrl = he_spr_ie_elem->he_sr_control;
 	data = he_spr_ie_elem->optional;
 
 	if (he_spr_ie_elem->he_sr_control &
 	    IEEE80211_HE_SPR_NON_SRG_OFFSET_PRESENT)
-		data++;
+		he_obss_pd->non_srg_max_offset = *data++;
+
 	if (he_spr_ie_elem->he_sr_control &
 	    IEEE80211_HE_SPR_SRG_INFORMATION_PRESENT) {
-		he_obss_pd->max_offset = *data++;
 		he_obss_pd->min_offset = *data++;
+		he_obss_pd->max_offset = *data++;
+		memcpy(he_obss_pd->bss_color_bitmap, data, 8);
+		data += 8;
+		memcpy(he_obss_pd->partial_bssid_bitmap, data, 8);
 		he_obss_pd->enable = true;
 	}
 }
-- 
GitLab


From 92ecbb3ac6f3fe8ae9edf3226c76aa17b6800699 Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Fri, 17 May 2024 18:33:32 +0300
Subject: [PATCH 484/950] wifi: mac80211: fix UBSAN noise in
 ieee80211_prep_hw_scan()

When testing the previous patch with CONFIG_UBSAN_BOUNDS, I've
noticed the following:

UBSAN: array-index-out-of-bounds in net/mac80211/scan.c:372:4
index 0 is out of range for type 'struct ieee80211_channel *[]'
CPU: 0 PID: 1435 Comm: wpa_supplicant Not tainted 6.9.0+ #1
Hardware name: LENOVO 20UN005QRT/20UN005QRT <...BIOS details...>
Call Trace:
 <TASK>
 dump_stack_lvl+0x2d/0x90
 __ubsan_handle_out_of_bounds+0xe7/0x140
 ? timerqueue_add+0x98/0xb0
 ieee80211_prep_hw_scan+0x2db/0x480 [mac80211]
 ? __kmalloc+0xe1/0x470
 __ieee80211_start_scan+0x541/0x760 [mac80211]
 rdev_scan+0x1f/0xe0 [cfg80211]
 nl80211_trigger_scan+0x9b6/0xae0 [cfg80211]
 ...<the rest is not too useful...>

Since '__ieee80211_start_scan()' leaves 'hw_scan_req->req.n_channels'
uninitialized, actual boundaries of 'hw_scan_req->req.channels' can't
be checked in 'ieee80211_prep_hw_scan()'. Although an initialization
of 'hw_scan_req->req.n_channels' introduces some confusion around
allocated vs. used VLA members, this shouldn't be a problem since
everything is correctly adjusted soon in 'ieee80211_prep_hw_scan()'.

Cleanup 'kmalloc()' math in '__ieee80211_start_scan()' by using the
convenient 'struct_size()' as well.

Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Link: https://msgid.link/20240517153332.18271-2-dmantipov@yandex.ru
[improve (imho) indentation a bit]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/scan.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index 3da1c5c450358..8ecc4b710b0e6 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -744,15 +744,21 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata,
 			local->hw_scan_ies_bufsize *= n_bands;
 		}
 
-		local->hw_scan_req = kmalloc(
-				sizeof(*local->hw_scan_req) +
-				req->n_channels * sizeof(req->channels[0]) +
-				local->hw_scan_ies_bufsize, GFP_KERNEL);
+		local->hw_scan_req = kmalloc(struct_size(local->hw_scan_req,
+							 req.channels,
+							 req->n_channels) +
+					     local->hw_scan_ies_bufsize,
+					     GFP_KERNEL);
 		if (!local->hw_scan_req)
 			return -ENOMEM;
 
 		local->hw_scan_req->req.ssids = req->ssids;
 		local->hw_scan_req->req.n_ssids = req->n_ssids;
+		/* None of the channels are actually set
+		 * up but let UBSAN know the boundaries.
+		 */
+		local->hw_scan_req->req.n_channels = req->n_channels;
+
 		ies = (u8 *)local->hw_scan_req +
 			sizeof(*local->hw_scan_req) +
 			req->n_channels * sizeof(req->channels[0]);
-- 
GitLab


From 9dedabe95b49ec9b0d16ce8f0ed1f9a12dd4a040 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Wed, 29 May 2024 11:42:35 -0400
Subject: [PATCH 485/950] spi: Assign dummy scatterlist to unidirectional
 transfers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit 8cc3bad9d9d6 ("spi: Remove unneded check for orig_nents")
introduced a regression: unmapped data could now be passed to the DMA
APIs, resulting in null pointer dereferences. Commit 9f788ba457b4 ("spi:
Don't mark message DMA mapped when no transfer in it is") and commit
da560097c056 ("spi: Check if transfer is mapped before calling DMA sync
APIs") addressed the problem, but only partially. Unidirectional
transactions will still result in null pointer dereference. To prevent
that from happening, assign a dummy scatterlist when no data is mapped,
so that the DMA API can be called and not result in a null pointer
dereference.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reported-by: Neil Armstrong <neil.armstrong@linaro.org>
Closes: https://lore.kernel.org/r/8ae675b5-fcf9-4c9b-b06a-4462f70e1322@linaro.org
Reported-by: Nícolas F. R. A. Prado <nfraprado@collabora.com>
Closes: https://lore.kernel.org/all/d3679496-2e4e-4a7c-97ed-f193bd53af1d@notapiano
Closes: https://lore.kernel.org/all/4748499f-789c-45a8-b50a-2dd09f4bac8c@notapiano
Fixes: 8cc3bad9d9d6 ("spi: Remove unneded check for orig_nents")
Tested-by: Nícolas F. R. A. Prado <nfraprado@collabora.com>
[nfraprado: wrote the commit message]
Signed-off-by: Nícolas F. R. A. Prado <nfraprado@collabora.com>
Link: https://msgid.link/r/20240529-dma-oops-dummy-v1-1-bb43aacfb11b@collabora.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index f94420858c224..9bc9fd10d538d 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -1220,6 +1220,11 @@ void spi_unmap_buf(struct spi_controller *ctlr, struct device *dev,
 	spi_unmap_buf_attrs(ctlr, dev, sgt, dir, 0);
 }
 
+/* Dummy SG for unidirect transfers */
+static struct scatterlist dummy_sg = {
+	.page_link = SG_END,
+};
+
 static int __spi_map_msg(struct spi_controller *ctlr, struct spi_message *msg)
 {
 	struct device *tx_dev, *rx_dev;
@@ -1258,6 +1263,8 @@ static int __spi_map_msg(struct spi_controller *ctlr, struct spi_message *msg)
 						attrs);
 			if (ret != 0)
 				return ret;
+		} else {
+			xfer->tx_sg.sgl = &dummy_sg;
 		}
 
 		if (xfer->rx_buf != NULL) {
@@ -1271,6 +1278,8 @@ static int __spi_map_msg(struct spi_controller *ctlr, struct spi_message *msg)
 
 				return ret;
 			}
+		} else {
+			xfer->rx_sg.sgl = &dummy_sg;
 		}
 	}
 	/* No transfer has been mapped, bail out with success */
-- 
GitLab


From 06fe9b1df1086b42718d632aa57e8f7cd1a66a21 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Wed, 29 May 2024 09:38:38 -0600
Subject: [PATCH 486/950] io_uring: don't attempt to mmap larger than what the
 user asks for
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If IORING_FEAT_SINGLE_MMAP is ignored, as can happen if an application
uses an ancient liburing or does setup manually, then 3 mmap's are
required to map the ring into userspace. The kernel will still have
collapsed the mappings, however userspace may ask for mapping them
individually. If so, then we should not use the full number of ring
pages, as it may exceed the partial mapping. Doing so will yield an
-EFAULT from vm_insert_pages(), as we pass in more pages than what the
application asked for.

Cap the number of pages to match what the application asked for, for
the particular mapping operation.

Reported-by: Lucas Mülling <lmulling@proton.me>
Link: https://github.com/axboe/liburing/issues/1157
Fixes: 3ab1db3c6039 ("io_uring: get rid of remap_pfn_range() for mapping rings/sqes")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/memmap.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/io_uring/memmap.c b/io_uring/memmap.c
index 4785d6af5fee9..a0f32a255fd1e 100644
--- a/io_uring/memmap.c
+++ b/io_uring/memmap.c
@@ -244,6 +244,7 @@ __cold int io_uring_mmap(struct file *file, struct vm_area_struct *vma)
 	struct io_ring_ctx *ctx = file->private_data;
 	size_t sz = vma->vm_end - vma->vm_start;
 	long offset = vma->vm_pgoff << PAGE_SHIFT;
+	unsigned int npages;
 	void *ptr;
 
 	ptr = io_uring_validate_mmap_request(file, vma->vm_pgoff, sz);
@@ -253,8 +254,8 @@ __cold int io_uring_mmap(struct file *file, struct vm_area_struct *vma)
 	switch (offset & IORING_OFF_MMAP_MASK) {
 	case IORING_OFF_SQ_RING:
 	case IORING_OFF_CQ_RING:
-		return io_uring_mmap_pages(ctx, vma, ctx->ring_pages,
-						ctx->n_ring_pages);
+		npages = min(ctx->n_ring_pages, (sz + PAGE_SIZE - 1) >> PAGE_SHIFT);
+		return io_uring_mmap_pages(ctx, vma, ctx->ring_pages, npages);
 	case IORING_OFF_SQES:
 		return io_uring_mmap_pages(ctx, vma, ctx->sqe_pages,
 						ctx->n_sqe_pages);
-- 
GitLab


From 3bd27a847a3a4827a948387cc8f0dbc9fa5931d5 Mon Sep 17 00:00:00 2001
From: Matthias Maennich <maennich@google.com>
Date: Tue, 28 May 2024 11:32:43 +0000
Subject: [PATCH 487/950] kheaders: explicitly define file modes for archived
 headers

Build environments might be running with different umask settings
resulting in indeterministic file modes for the files contained in
kheaders.tar.xz. The file itself is served with 444, i.e. world
readable. Archive the files explicitly with 744,a+X to improve
reproducibility across build environments.

--mode=0444 is not suitable as directories need to be executable. Also,
444 makes it hard to delete all the readonly files after extraction.

Cc: stable@vger.kernel.org
Signed-off-by: Matthias Maennich <maennich@google.com>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 kernel/gen_kheaders.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/gen_kheaders.sh b/kernel/gen_kheaders.sh
index 6d443ea22bb73..8b6e0c2bc0dfe 100755
--- a/kernel/gen_kheaders.sh
+++ b/kernel/gen_kheaders.sh
@@ -84,7 +84,7 @@ find $cpio_dir -type f -print0 |
 
 # Create archive and try to normalize metadata for reproducibility.
 tar "${KBUILD_BUILD_TIMESTAMP:+--mtime=$KBUILD_BUILD_TIMESTAMP}" \
-    --owner=0 --group=0 --sort=name --numeric-owner \
+    --owner=0 --group=0 --sort=name --numeric-owner --mode=u=rw,go=r,a+X \
     -I $XZ -cf $tarfile -C $cpio_dir/ . > /dev/null
 
 echo $headers_md5 > kernel/kheaders.md5
-- 
GitLab


From 6e58e0173507e506a5627741358bc770f220e356 Mon Sep 17 00:00:00 2001
From: Miguel Ojeda <ojeda@kernel.org>
Date: Tue, 28 May 2024 18:31:50 +0200
Subject: [PATCH 488/950] kheaders: use `command -v` to test for existence of
 `cpio`

Commit 13e1df09284d ("kheaders: explicitly validate existence of cpio
command") added an explicit check for `cpio` using `type`.

However, `type` in `dash` (which is used in some popular distributions
and base images as the shell script runner) prints the missing message
to standard output, and thus no error is printed:

    $ bash -c 'type missing >/dev/null'
    bash: line 1: type: missing: not found
    $ dash -c 'type missing >/dev/null'
    $

For instance, this issue may be seen by loongarch builders, given its
defconfig enables CONFIG_IKHEADERS since commit 9cc1df421f00 ("LoongArch:
Update Loongson-3 default config file").

Therefore, use `command -v` instead to have consistent behavior, and
take the chance to provide a more explicit error.

Fixes: 13e1df09284d ("kheaders: explicitly validate existence of cpio command")
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 kernel/gen_kheaders.sh | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/kernel/gen_kheaders.sh b/kernel/gen_kheaders.sh
index 8b6e0c2bc0dfe..383fd43ac6122 100755
--- a/kernel/gen_kheaders.sh
+++ b/kernel/gen_kheaders.sh
@@ -14,7 +14,12 @@ include/
 arch/$SRCARCH/include/
 "
 
-type cpio > /dev/null
+if ! command -v cpio >/dev/null; then
+	echo >&2 "***"
+	echo >&2 "*** 'cpio' could not be found."
+	echo >&2 "***"
+	exit 1
+fi
 
 # Support incremental builds by skipping archive generation
 # if timestamps of files being archived are not changed.
-- 
GitLab


From 1b1c9f0fd3fb70adf1f3b0aec58ab037d6e595d0 Mon Sep 17 00:00:00 2001
From: "Rob Herring (Arm)" <robh@kernel.org>
Date: Tue, 28 May 2024 15:02:32 -0500
Subject: [PATCH 489/950] dt-bindings: kbuild: Fix dt_binding_check on
 unconfigured build

The 'dt_binding_check' target shouldn't depend on the kernel
configuration, but it has since commit 604a57ba9781 ("dt-bindings:
kbuild: Add separate target/dependency for processed-schema.json").
That is because CHECK_DT_BINDING make variable was dropped, but
scripts/dtc/Makefile was missed. The CHECK_DTBS variable can be used
instead.

Reported-by: Francesco Dolcini <francesco.dolcini@toradex.com>
Fixes: 604a57ba9781 ("dt-bindings: kbuild: Add separate target/dependency for processed-schema.json")
Signed-off-by: "Rob Herring (Arm)" <robh@kernel.org>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 scripts/dtc/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/dtc/Makefile b/scripts/dtc/Makefile
index a186570725412..b47f4daa4515d 100644
--- a/scripts/dtc/Makefile
+++ b/scripts/dtc/Makefile
@@ -3,7 +3,7 @@
 
 # *** Also keep .gitignore in sync when changing ***
 hostprogs-always-$(CONFIG_DTC)		+= dtc fdtoverlay
-hostprogs-always-$(CHECK_DT_BINDING)	+= dtc
+hostprogs-always-$(CHECK_DTBS)		+= dtc
 
 dtc-objs	:= dtc.o flattree.o fstree.o data.o livetree.o treesource.o \
 		   srcpos.o checks.o util.o
-- 
GitLab


From 4a4be1ad3a6efea16c56615f31117590fd881358 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Wed, 29 May 2024 09:39:34 -0700
Subject: [PATCH 490/950] Revert "vfs: Delete the associated dentry when
 deleting a file"

This reverts commit 681ce8623567ba7e7333908e9826b77145312dda.

We gave it a try, but it turns out the kernel test robot did in fact
find performance regressions for it, so we'll have to look at the more
involved alternative fixes for Yafang Shao's Elasticsearch load issue.

There were several alternatives discussed, they just weren't as simple
as this first attempt.

The report is of a -7.4% regression of filebench.sum_operations/s, which
appears significant enough to trigger my "this patch may get reverted if
somebody finds a performance regression on some other load" rule.

So it's still the case that we should end up deleting dentries more
aggressively - or just be better at pruning them later - but it needs a
bit more finesse than this simple thing.

Link: https://lore.kernel.org/all/202405291318.4dfbb352-oliver.sang@intel.com/
Cc: Yafang Shao <laoar.shao@gmail.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Christian Brauner <brauner@kernel.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/dcache.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/fs/dcache.c b/fs/dcache.c
index 1ee6404b430ba..407095188f83a 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -2360,17 +2360,19 @@ EXPORT_SYMBOL(d_hash_and_lookup);
  * - unhash this dentry and free it.
  *
  * Usually, we want to just turn this into
- * a negative dentry, but certain workloads can
- * generate a large number of negative dentries.
- * Therefore, it would be better to simply
- * unhash it.
+ * a negative dentry, but if anybody else is
+ * currently using the dentry or the inode
+ * we can't do that and we fall back on removing
+ * it from the hash queues and waiting for
+ * it to be deleted later when it has no users
  */
  
 /**
  * d_delete - delete a dentry
  * @dentry: The dentry to delete
  *
- * Remove the dentry from the hash queues so it can be deleted later.
+ * Turn the dentry into a negative dentry if possible, otherwise
+ * remove it from the hash queues so it can be deleted later
  */
  
 void d_delete(struct dentry * dentry)
@@ -2379,8 +2381,6 @@ void d_delete(struct dentry * dentry)
 
 	spin_lock(&inode->i_lock);
 	spin_lock(&dentry->d_lock);
-	__d_drop(dentry);
-
 	/*
 	 * Are we the only user?
 	 */
@@ -2388,6 +2388,7 @@ void d_delete(struct dentry * dentry)
 		dentry->d_flags &= ~DCACHE_CANT_MOUNT;
 		dentry_unlink_inode(dentry);
 	} else {
+		__d_drop(dentry);
 		spin_unlock(&dentry->d_lock);
 		spin_unlock(&inode->i_lock);
 	}
-- 
GitLab


From ac0d71ee534e67c7e53439e8e9cb45ed40731660 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 29 May 2024 18:47:16 +0200
Subject: [PATCH 491/950] ALSA: ump: Don't accept an invalid UMP protocol
 number

When a UMP Stream Configuration message is received, the driver tries
to switch the protocol, but there was no sanity check of the protocol,
hence it can pass an invalid value.  Add the check and bail out if a
wrong value is passed.

Fixes: a79807683781 ("ALSA: ump: Add helper to change MIDI protocol")
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20240529164723.18309-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/core/ump.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/sound/core/ump.c b/sound/core/ump.c
index fd6a68a542788..117c7ecc48563 100644
--- a/sound/core/ump.c
+++ b/sound/core/ump.c
@@ -685,10 +685,17 @@ static void seq_notify_protocol(struct snd_ump_endpoint *ump)
  */
 int snd_ump_switch_protocol(struct snd_ump_endpoint *ump, unsigned int protocol)
 {
+	unsigned int type;
+
 	protocol &= ump->info.protocol_caps;
 	if (protocol == ump->info.protocol)
 		return 0;
 
+	type = protocol & SNDRV_UMP_EP_INFO_PROTO_MIDI_MASK;
+	if (type != SNDRV_UMP_EP_INFO_PROTO_MIDI1 &&
+	    type != SNDRV_UMP_EP_INFO_PROTO_MIDI2)
+		return 0;
+
 	ump->info.protocol = protocol;
 	ump_dbg(ump, "New protocol = %x (caps = %x)\n",
 		protocol, ump->info.protocol_caps);
-- 
GitLab


From bc42ca002d5d211f9c57334b9b4c25ddb0b4ec35 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 29 May 2024 18:47:17 +0200
Subject: [PATCH 492/950] ALSA: ump: Set default protocol when not given
 explicitly

When an inquiry of the current protocol via UMP Stream Configuration
message fails by some reason, we may leave the current protocol
undefined, which may lead to unexpected behavior.  Better to assume a
valid protocol found in the protocol capability bits instead.

For a device that doesn't support the UMP v1.2 feature, it won't reach
to this code path, and USB MIDI GTB descriptor would be used for
determining the protocol, instead.

Link: https://lore.kernel.org/r/20240529164723.18309-2-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/core/ump.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/sound/core/ump.c b/sound/core/ump.c
index 117c7ecc48563..3f61220c23b4e 100644
--- a/sound/core/ump.c
+++ b/sound/core/ump.c
@@ -967,6 +967,14 @@ int snd_ump_parse_endpoint(struct snd_ump_endpoint *ump)
 	if (err < 0)
 		ump_dbg(ump, "Unable to get UMP EP stream config\n");
 
+	/* If no protocol is set by some reason, assume the valid one */
+	if (!(ump->info.protocol & SNDRV_UMP_EP_INFO_PROTO_MIDI_MASK)) {
+		if (ump->info.protocol_caps & SNDRV_UMP_EP_INFO_PROTO_MIDI2)
+			ump->info.protocol |= SNDRV_UMP_EP_INFO_PROTO_MIDI2;
+		else if (ump->info.protocol_caps & SNDRV_UMP_EP_INFO_PROTO_MIDI1)
+			ump->info.protocol |= SNDRV_UMP_EP_INFO_PROTO_MIDI1;
+	}
+
 	/* Query and create blocks from Function Blocks */
 	for (blk = 0; blk < ump->info.num_blocks; blk++) {
 		err = create_block_from_fb_info(ump, blk);
-- 
GitLab


From 95d7c452a26564ef0c427f2806761b857106d8c4 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Tue, 21 May 2024 12:52:42 +0200
Subject: [PATCH 493/950] spi: stm32: Don't warn about spurious interrupts
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The dev_warn to notify about a spurious interrupt was introduced with
the reasoning that these are unexpected. However spurious interrupts
tend to trigger continously and the error message on the serial console
prevents that the core's detection of spurious interrupts kicks in
(which disables the irq) and just floods the console.

Fixes: c64e7efe46b7 ("spi: stm32: make spurious and overrun interrupts visible")
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://msgid.link/r/20240521105241.62400-2-u.kleine-koenig@pengutronix.de
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-stm32.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/spi/spi-stm32.c b/drivers/spi/spi-stm32.c
index e4e7ddb7524a9..4c4ff074e3f6f 100644
--- a/drivers/spi/spi-stm32.c
+++ b/drivers/spi/spi-stm32.c
@@ -1057,7 +1057,7 @@ static irqreturn_t stm32h7_spi_irq_thread(int irq, void *dev_id)
 		mask |= STM32H7_SPI_SR_TXP | STM32H7_SPI_SR_RXP;
 
 	if (!(sr & mask)) {
-		dev_warn(spi->dev, "spurious IT (sr=0x%08x, ier=0x%08x)\n",
+		dev_vdbg(spi->dev, "spurious IT (sr=0x%08x, ier=0x%08x)\n",
 			 sr, ier);
 		spin_unlock_irqrestore(&spi->lock, flags);
 		return IRQ_NONE;
-- 
GitLab


From 84081a885394fc94055c24c727c99c321df6abac Mon Sep 17 00:00:00 2001
From: "Rob Herring (Arm)" <robh@kernel.org>
Date: Fri, 3 May 2024 10:44:02 -0500
Subject: [PATCH 494/950] dt-bindings: arm: sunxi: Fix incorrect '-' usage

Commit 6bc6bf8a940a ("dt-bindings: arm: sunxi: document Anbernic RG35XX
handheld gaming device variants") mistakenly added '-' on each line
which created empty (i.e. description only) schemas matching anything.
This causes validation to fail on all the root node compatibles as
there are multiple oneOf clauses passing.

Fixes: 6bc6bf8a940a ("dt-bindings: arm: sunxi: document Anbernic RG35XX handheld gaming device variants")
Reviewed-by: Ryan Walklin <ryan@testtoast.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20240503154402.967632-1-robh@kernel.org
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
---
 Documentation/devicetree/bindings/arm/sunxi.yaml | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/Documentation/devicetree/bindings/arm/sunxi.yaml b/Documentation/devicetree/bindings/arm/sunxi.yaml
index c6d0d8d81ed4d..c2a158b75e497 100644
--- a/Documentation/devicetree/bindings/arm/sunxi.yaml
+++ b/Documentation/devicetree/bindings/arm/sunxi.yaml
@@ -57,17 +57,17 @@ properties:
           - const: allwinner,sun8i-v3s
 
       - description: Anbernic RG35XX (2024)
-      - items:
+        items:
           - const: anbernic,rg35xx-2024
           - const: allwinner,sun50i-h700
 
       - description: Anbernic RG35XX Plus
-      - items:
+        items:
           - const: anbernic,rg35xx-plus
           - const: allwinner,sun50i-h700
 
       - description: Anbernic RG35XX H
-      - items:
+        items:
           - const: anbernic,rg35xx-h
           - const: allwinner,sun50i-h700
 
-- 
GitLab


From 321e4fa68ce15660ec578bdec5cc9607635087cf Mon Sep 17 00:00:00 2001
From: "Rob Herring (Arm)" <robh@kernel.org>
Date: Thu, 23 May 2024 10:42:07 -0500
Subject: [PATCH 495/950] dt-bindings: arm: stm32: st,mlahb: Drop spurious
 "reg" property from example

"reg" is not documented nor used for st,mlahb, so drop it from the
example to fix the warning:

Documentation/devicetree/bindings/arm/stm32/st,mlahb.example.dtb: ahb@38000000: Unevaluated properties are not allowed ('reg' was unexpected)
        from schema $id: http://devicetree.org/schemas/arm/stm32/st,mlahb.yaml#

Since "reg" is dropped, the unit-address must be as well.

Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20240523154208.2457864-1-robh@kernel.org
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
---
 Documentation/devicetree/bindings/arm/stm32/st,mlahb.yaml | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/arm/stm32/st,mlahb.yaml b/Documentation/devicetree/bindings/arm/stm32/st,mlahb.yaml
index d2dce238ff5d6..3e996346b2644 100644
--- a/Documentation/devicetree/bindings/arm/stm32/st,mlahb.yaml
+++ b/Documentation/devicetree/bindings/arm/stm32/st,mlahb.yaml
@@ -54,11 +54,10 @@ unevaluatedProperties: false
 
 examples:
   - |
-    mlahb: ahb@38000000 {
+    ahb {
       compatible = "st,mlahb", "simple-bus";
       #address-cells = <1>;
       #size-cells = <1>;
-      reg = <0x10000000 0x40000>;
       ranges;
       dma-ranges = <0x00000000 0x38000000 0x10000>,
                    <0x10000000 0x10000000 0x60000>,
-- 
GitLab


From 2032e61e24fe9fe55d6c7a34fb5506c911b3e280 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@kernel.org>
Date: Thu, 16 May 2024 16:27:33 +0100
Subject: [PATCH 496/950] kselftest/alsa: Ensure _GNU_SOURCE is defined

The pcmtest driver tests use the kselftest harness which requires that
_GNU_SOURCE is defined but nothing causes it to be defined.  Since the
KHDR_INCLUDES Makefile variable has had the required define added let's
use that, this should provide some futureproofing.

Fixes: daef47b89efd ("selftests: Compile kselftest headers with -D_GNU_SOURCE")
Signed-off-by: Mark Brown <broonie@kernel.org>
Reviewed-by: Muhammad Usama Anjum <usama.anjum@collabora.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 tools/testing/selftests/alsa/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/alsa/Makefile b/tools/testing/selftests/alsa/Makefile
index 5af9ba8a4645b..c1ce39874e2b5 100644
--- a/tools/testing/selftests/alsa/Makefile
+++ b/tools/testing/selftests/alsa/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 #
 
-CFLAGS += $(shell pkg-config --cflags alsa)
+CFLAGS += $(shell pkg-config --cflags alsa) $(KHDR_INCLUDES)
 LDLIBS += $(shell pkg-config --libs alsa)
 ifeq ($(LDLIBS),)
 LDLIBS += -lasound
-- 
GitLab


From f6c3c83db1d939ebdb8c8922748ae647d8126d91 Mon Sep 17 00:00:00 2001
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Date: Tue, 21 May 2024 09:00:22 +0900
Subject: [PATCH 497/950] selftests/ftrace: Fix to check required event file

The dynevent/test_duplicates.tc test case uses `syscalls/sys_enter_openat`
event for defining eprobe on it. Since this `syscalls` events depend on
CONFIG_FTRACE_SYSCALLS=y, if it is not set, the test will fail.

Add the event file to `required` line so that the test will return
`unsupported` result.

Fixes: 297e1dcdca3d ("selftests/ftrace: Add selftest for testing duplicate eprobes and kprobes")
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 .../testing/selftests/ftrace/test.d/dynevent/test_duplicates.tc | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/test_duplicates.tc b/tools/testing/selftests/ftrace/test.d/dynevent/test_duplicates.tc
index d3a79da215c8b..5f72abe6fa79b 100644
--- a/tools/testing/selftests/ftrace/test.d/dynevent/test_duplicates.tc
+++ b/tools/testing/selftests/ftrace/test.d/dynevent/test_duplicates.tc
@@ -1,7 +1,7 @@
 #!/bin/sh
 # SPDX-License-Identifier: GPL-2.0
 # description: Generic dynamic event - check if duplicate events are caught
-# requires: dynamic_events "e[:[<group>/][<event>]] <attached-group>.<attached-event> [<args>]":README
+# requires: dynamic_events "e[:[<group>/][<event>]] <attached-group>.<attached-event> [<args>]":README events/syscalls/sys_enter_openat
 
 echo 0 > events/enable
 
-- 
GitLab


From 7ea794604bf6a3be8bb4b0f1483eb1d3972eac93 Mon Sep 17 00:00:00 2001
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Date: Tue, 21 May 2024 09:00:32 +0900
Subject: [PATCH 498/950] selftests/ftrace: Update required config

Update required config options for running all tests.
This also sorts the config entries alphabetically.

Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 tools/testing/selftests/ftrace/config | 26 +++++++++++++++++++-------
 1 file changed, 19 insertions(+), 7 deletions(-)

diff --git a/tools/testing/selftests/ftrace/config b/tools/testing/selftests/ftrace/config
index e59d985eeff0c..048a312abf405 100644
--- a/tools/testing/selftests/ftrace/config
+++ b/tools/testing/selftests/ftrace/config
@@ -1,16 +1,28 @@
-CONFIG_KPROBES=y
+CONFIG_BPF_SYSCALL=y
+CONFIG_DEBUG_INFO_BTF=y
+CONFIG_DEBUG_INFO_DWARF4=y
+CONFIG_EPROBE_EVENTS=y
+CONFIG_FPROBE=y
+CONFIG_FPROBE_EVENTS=y
 CONFIG_FTRACE=y
+CONFIG_FTRACE_SYSCALLS=y
+CONFIG_FUNCTION_GRAPH_RETVAL=y
 CONFIG_FUNCTION_PROFILER=y
-CONFIG_TRACER_SNAPSHOT=y
-CONFIG_STACK_TRACER=y
 CONFIG_HIST_TRIGGERS=y
-CONFIG_SCHED_TRACER=y
-CONFIG_PREEMPT_TRACER=y
 CONFIG_IRQSOFF_TRACER=y
-CONFIG_PREEMPTIRQ_DELAY_TEST=m
+CONFIG_KALLSYMS_ALL=y
+CONFIG_KPROBES=y
+CONFIG_KPROBE_EVENTS=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
+CONFIG_PREEMPTIRQ_DELAY_TEST=m
+CONFIG_PREEMPT_TRACER=y
+CONFIG_PROBE_EVENTS_BTF_ARGS=y
 CONFIG_SAMPLES=y
 CONFIG_SAMPLE_FTRACE_DIRECT=m
 CONFIG_SAMPLE_TRACE_PRINTK=m
-CONFIG_KALLSYMS_ALL=y
+CONFIG_SCHED_TRACER=y
+CONFIG_STACK_TRACER=y
+CONFIG_TRACER_SNAPSHOT=y
+CONFIG_UPROBES=y
+CONFIG_UPROBE_EVENTS=y
-- 
GitLab


From 23a4b108accc29a6125ed14de4a044689ffeda78 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Google)" <rostedt@goodmis.org>
Date: Mon, 20 May 2024 20:57:37 -0400
Subject: [PATCH 499/950] tracing/selftests: Fix kprobe event name test for
 .isra. functions

The kprobe_eventname.tc test checks if a function with .isra. can have a
kprobe attached to it. It loops through the kallsyms file for all the
functions that have the .isra. name, and checks if it exists in the
available_filter_functions file, and if it does, it uses it to attach a
kprobe to it.

The issue is that kprobes can not attach to functions that are listed more
than once in available_filter_functions. With the latest kernel, the
function that is found is: rapl_event_update.isra.0

  # grep rapl_event_update.isra.0 /sys/kernel/tracing/available_filter_functions
  rapl_event_update.isra.0
  rapl_event_update.isra.0

It is listed twice. This causes the attached kprobe to it to fail which in
turn fails the test. Instead of just picking the function function that is
found in available_filter_functions, pick the first one that is listed
only once in available_filter_functions.

Cc: stable@vger.kernel.org
Fixes: 604e3548236d ("selftests/ftrace: Select an existing function in kprobe_eventname test")
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 .../testing/selftests/ftrace/test.d/kprobe/kprobe_eventname.tc | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_eventname.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_eventname.tc
index 1f6981ef7afa0..ba19b81cef39a 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_eventname.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_eventname.tc
@@ -30,7 +30,8 @@ find_dot_func() {
 	fi
 
 	grep " [tT] .*\.isra\..*" /proc/kallsyms | cut -f 3 -d " " | while read f; do
-		if grep -s $f available_filter_functions; then
+		cnt=`grep -s $f available_filter_functions | wc -l`;
+		if [ $cnt -eq 1 ]; then
 			echo $f
 			break
 		fi
-- 
GitLab


From bc4d5f5d2debf8bb65fba188313481549ead8576 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Tue, 21 May 2024 13:01:11 +1000
Subject: [PATCH 500/950] selftests: cachestat: Fix build warnings on ppc64
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix warnings like:
  test_cachestat.c: In function ‘print_cachestat’:
  test_cachestat.c:30:38: warning: format ‘%llu’ expects argument of
  type ‘long long unsigned int’, but argument 2 has type ‘__u64’ {aka
  ‘long unsigned int’} [-Wformat=]

By switching to unsigned long long for u64 for ppc64 builds.

Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 tools/testing/selftests/cachestat/test_cachestat.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/testing/selftests/cachestat/test_cachestat.c b/tools/testing/selftests/cachestat/test_cachestat.c
index b171fd53b004e..632ab44737ec3 100644
--- a/tools/testing/selftests/cachestat/test_cachestat.c
+++ b/tools/testing/selftests/cachestat/test_cachestat.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #define _GNU_SOURCE
+#define __SANE_USERSPACE_TYPES__ // Use ll64
 
 #include <stdio.h>
 #include <stdbool.h>
-- 
GitLab


From 84b6df4c49a1cc2854a16937acd5fd3e6315d083 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Tue, 21 May 2024 13:03:25 +1000
Subject: [PATCH 501/950] selftests/openat2: Fix build warnings on ppc64
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix warnings like:

  openat2_test.c: In function ‘test_openat2_flags’:
  openat2_test.c:303:73: warning: format ‘%llX’ expects argument of type
  ‘long long unsigned int’, but argument 5 has type ‘__u64’ {aka ‘long
  unsigned int’} [-Wformat=]

By switching to unsigned long long for u64 for ppc64 builds.

Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Reviewed-by: Muhammad Usama Anjum <usama.anjum@collabora.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 tools/testing/selftests/openat2/openat2_test.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/testing/selftests/openat2/openat2_test.c b/tools/testing/selftests/openat2/openat2_test.c
index 9024754530b23..5790ab446527f 100644
--- a/tools/testing/selftests/openat2/openat2_test.c
+++ b/tools/testing/selftests/openat2/openat2_test.c
@@ -5,6 +5,7 @@
  */
 
 #define _GNU_SOURCE
+#define __SANE_USERSPACE_TYPES__ // Use ll64
 #include <fcntl.h>
 #include <sched.h>
 #include <sys/stat.h>
-- 
GitLab


From e8b8c5264d4ebd248f60a5cef077fe615806e7a0 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Tue, 21 May 2024 12:26:16 +1000
Subject: [PATCH 502/950] selftests/overlayfs: Fix build error on ppc64
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix build error on ppc64:
  dev_in_maps.c: In function ‘get_file_dev_and_inode’:
  dev_in_maps.c:60:59: error: format ‘%llu’ expects argument of type
  ‘long long unsigned int *’, but argument 7 has type ‘__u64 *’ {aka ‘long
  unsigned int *’} [-Werror=format=]

By switching to unsigned long long for u64 for ppc64 builds.

Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 tools/testing/selftests/filesystems/overlayfs/dev_in_maps.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/testing/selftests/filesystems/overlayfs/dev_in_maps.c b/tools/testing/selftests/filesystems/overlayfs/dev_in_maps.c
index 759f86e7d263e..2862aae58b79a 100644
--- a/tools/testing/selftests/filesystems/overlayfs/dev_in_maps.c
+++ b/tools/testing/selftests/filesystems/overlayfs/dev_in_maps.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #define _GNU_SOURCE
+#define __SANE_USERSPACE_TYPES__ // Use ll64
 
 #include <inttypes.h>
 #include <unistd.h>
-- 
GitLab


From 7b038b564b3e2a752d2211e7b0c3c29fd2f6e197 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Wed, 29 May 2024 16:28:41 -0400
Subject: [PATCH 503/950] bcachefs: Fix failure to return error on misaligned
 dio write

This was reported as an error when running coreutils shred.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/fs-io-direct.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/fs/bcachefs/fs-io-direct.c b/fs/bcachefs/fs-io-direct.c
index 09d21aef879af..049b61bc9a5b3 100644
--- a/fs/bcachefs/fs-io-direct.c
+++ b/fs/bcachefs/fs-io-direct.c
@@ -609,8 +609,10 @@ ssize_t bch2_direct_write(struct kiocb *req, struct iov_iter *iter)
 	if (unlikely(ret))
 		goto err_put_write_ref;
 
-	if (unlikely((req->ki_pos|iter->count) & (block_bytes(c) - 1)))
+	if (unlikely((req->ki_pos|iter->count) & (block_bytes(c) - 1))) {
+		ret = -EINVAL;
 		goto err_put_write_ref;
+	}
 
 	inode_dio_begin(&inode->v);
 	bch2_pagecache_block_get(inode);
-- 
GitLab


From ba46b3bda296c4f82b061ac40b90f49d2a00a380 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Wed, 15 May 2024 11:25:49 -0400
Subject: [PATCH 504/950] drm/amdgpu: Adjust logic in
 amdgpu_device_partner_bandwidth()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use current speed/width on devices which don't support
dynamic PCIe switching.

Fixes: 466a7d115326 ("drm/amd: Use the first non-dGPU PCI device for BW limits")
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/3289
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 861ccff78af95..932dc93b2e631 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -5944,13 +5944,18 @@ static void amdgpu_device_partner_bandwidth(struct amdgpu_device *adev,
 	*speed = PCI_SPEED_UNKNOWN;
 	*width = PCIE_LNK_WIDTH_UNKNOWN;
 
-	while ((parent = pci_upstream_bridge(parent))) {
-		/* skip upstream/downstream switches internal to dGPU*/
-		if (parent->vendor == PCI_VENDOR_ID_ATI)
-			continue;
-		*speed = pcie_get_speed_cap(parent);
-		*width = pcie_get_width_cap(parent);
-		break;
+	if (amdgpu_device_pcie_dynamic_switching_supported(adev)) {
+		while ((parent = pci_upstream_bridge(parent))) {
+			/* skip upstream/downstream switches internal to dGPU*/
+			if (parent->vendor == PCI_VENDOR_ID_ATI)
+				continue;
+			*speed = pcie_get_speed_cap(parent);
+			*width = pcie_get_width_cap(parent);
+			break;
+		}
+	} else {
+		/* use the current speeds rather than max if switching is not supported */
+		pcie_bandwidth_available(adev->pdev, NULL, speed, width);
 	}
 }
 
-- 
GitLab


From 05d9e24ddb15160164ba6e917a88c00907dc2434 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Thu, 16 May 2024 09:51:26 -0400
Subject: [PATCH 505/950] drm/amdgpu: silence UBSAN warning
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Convert a variable sized array from [1] to [].

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/include/atomfirmware.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/include/atomfirmware.h b/drivers/gpu/drm/amd/include/atomfirmware.h
index 1acb2d2c5597b..5716918372001 100644
--- a/drivers/gpu/drm/amd/include/atomfirmware.h
+++ b/drivers/gpu/drm/amd/include/atomfirmware.h
@@ -3583,7 +3583,7 @@ struct atom_gpio_voltage_object_v4
    uint8_t  phase_delay_us;                      // phase delay in unit of micro second
    uint8_t  reserved;   
    uint32_t gpio_mask_val;                         // GPIO Mask value
-   struct atom_voltage_gpio_map_lut voltage_gpio_lut[1];
+   struct atom_voltage_gpio_map_lut voltage_gpio_lut[] __counted_by(gpio_entry_num);
 };
 
 struct  atom_svid2_voltage_object_v4
-- 
GitLab


From a0cf36546cc24ae1c95d72253c7795d4d2fc77aa Mon Sep 17 00:00:00 2001
From: Jesse Zhang <jesse.zhang@amd.com>
Date: Thu, 23 May 2024 17:14:45 +0800
Subject: [PATCH 506/950] drm/amdgpu: fix dereference null return value for the
 function amdgpu_vm_pt_parent
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The pointer parent may be NULLed by the function amdgpu_vm_pt_parent.
To make the code more robust, check the pointer parent.

Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
Suggested-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c
index 7fdd306a48a0e..f07647a9a9d97 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c
@@ -706,11 +706,15 @@ int amdgpu_vm_pde_update(struct amdgpu_vm_update_params *params,
 			 struct amdgpu_vm_bo_base *entry)
 {
 	struct amdgpu_vm_bo_base *parent = amdgpu_vm_pt_parent(entry);
-	struct amdgpu_bo *bo = parent->bo, *pbo;
+	struct amdgpu_bo *bo, *pbo;
 	struct amdgpu_vm *vm = params->vm;
 	uint64_t pde, pt, flags;
 	unsigned int level;
 
+	if (WARN_ON(!parent))
+		return -EINVAL;
+
+	bo = parent->bo;
 	for (level = 0, pbo = bo->parent; pbo; ++level)
 		pbo = pbo->parent;
 
-- 
GitLab


From dd2b75fd9a79bf418e088656822af06fc253dbe3 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Mon, 20 May 2024 14:41:31 -0400
Subject: [PATCH 507/950] Revert "drm/amdkfd: fix gfx_target_version for
 certain 11.0.3 devices"

This reverts commit 28ebbb4981cb1fad12e0b1227dbecc88810b1ee8.

Revert this commit as apparently the LLVM code to take advantage of
this never landed.

Reviewed-by: Feifei Xu <Feifei.Xu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: Feifei Xu <feifei.xu@amd.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_device.c | 11 ++---------
 1 file changed, 2 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 9596bca572129..afc57df421cd9 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -408,15 +408,8 @@ struct kfd_dev *kgd2kfd_probe(struct amdgpu_device *adev, bool vf)
 			f2g = &gfx_v11_kfd2kgd;
 			break;
 		case IP_VERSION(11, 0, 3):
-			if ((adev->pdev->device == 0x7460 &&
-			     adev->pdev->revision == 0x00) ||
-			    (adev->pdev->device == 0x7461 &&
-			     adev->pdev->revision == 0x00))
-				/* Note: Compiler version is 11.0.5 while HW version is 11.0.3 */
-				gfx_target_version = 110005;
-			else
-				/* Note: Compiler version is 11.0.1 while HW version is 11.0.3 */
-				gfx_target_version = 110001;
+			/* Note: Compiler version is 11.0.1 while HW version is 11.0.3 */
+			gfx_target_version = 110001;
 			f2g = &gfx_v11_kfd2kgd;
 			break;
 		case IP_VERSION(11, 5, 0):
-- 
GitLab


From 1f327dfc846ae82e16e52ed9c559d566826486d2 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Wed, 22 May 2024 15:26:50 -0400
Subject: [PATCH 508/950] drm/amdkfd: simplify APU VRAM handling

With commit 89773b85599a
("drm/amdkfd: Let VRAM allocations go to GTT domain on small APUs")
big and small APU "VRAM" handling in KFD was unified.  Since AMD_IS_APU
is set for both big and small APUs, we can simplify the checks in
the code.

v2: clean up a few more places (Lang)

Acked-by: Felix Kuehling <felix.kuehling@amd.com>
Reviewed-by: Lang Yu <Lang.Yu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 16 ++++++++--------
 drivers/gpu/drm/amd/amdkfd/kfd_migrate.c         |  2 +-
 drivers/gpu/drm/amd/amdkfd/kfd_svm.c             |  6 ++----
 drivers/gpu/drm/amd/amdkfd/kfd_svm.h             |  1 -
 4 files changed, 11 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 8975cf41a91ac..48ad0c04aa72b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -196,7 +196,7 @@ int amdgpu_amdkfd_reserve_mem_limit(struct amdgpu_device *adev,
 			return -EINVAL;
 
 		vram_size = KFD_XCP_MEMORY_SIZE(adev, xcp_id);
-		if (adev->gmc.is_app_apu || adev->flags & AMD_IS_APU) {
+		if (adev->flags & AMD_IS_APU) {
 			system_mem_needed = size;
 			ttm_mem_needed = size;
 		}
@@ -233,7 +233,7 @@ int amdgpu_amdkfd_reserve_mem_limit(struct amdgpu_device *adev,
 	if (adev && xcp_id >= 0) {
 		adev->kfd.vram_used[xcp_id] += vram_needed;
 		adev->kfd.vram_used_aligned[xcp_id] +=
-				(adev->gmc.is_app_apu || adev->flags & AMD_IS_APU) ?
+				(adev->flags & AMD_IS_APU) ?
 				vram_needed :
 				ALIGN(vram_needed, VRAM_AVAILABLITY_ALIGN);
 	}
@@ -261,7 +261,7 @@ void amdgpu_amdkfd_unreserve_mem_limit(struct amdgpu_device *adev,
 
 		if (adev) {
 			adev->kfd.vram_used[xcp_id] -= size;
-			if (adev->gmc.is_app_apu || adev->flags & AMD_IS_APU) {
+			if (adev->flags & AMD_IS_APU) {
 				adev->kfd.vram_used_aligned[xcp_id] -= size;
 				kfd_mem_limit.system_mem_used -= size;
 				kfd_mem_limit.ttm_mem_used -= size;
@@ -890,7 +890,7 @@ static int kfd_mem_attach(struct amdgpu_device *adev, struct kgd_mem *mem,
 	 * if peer device has large BAR. In contrast, access over xGMI is
 	 * allowed for both small and large BAR configurations of peer device
 	 */
-	if ((adev != bo_adev && !(adev->gmc.is_app_apu || adev->flags & AMD_IS_APU)) &&
+	if ((adev != bo_adev && !(adev->flags & AMD_IS_APU)) &&
 	    ((mem->domain == AMDGPU_GEM_DOMAIN_VRAM) ||
 	     (mem->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_DOORBELL) ||
 	     (mem->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_MMIO_REMAP))) {
@@ -1658,7 +1658,7 @@ size_t amdgpu_amdkfd_get_available_memory(struct amdgpu_device *adev,
 		- atomic64_read(&adev->vram_pin_size)
 		- reserved_for_pt;
 
-	if (adev->gmc.is_app_apu || adev->flags & AMD_IS_APU) {
+	if (adev->flags & AMD_IS_APU) {
 		system_mem_available = no_system_mem_limit ?
 					kfd_mem_limit.max_system_mem_limit :
 					kfd_mem_limit.max_system_mem_limit -
@@ -1706,7 +1706,7 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(
 	if (flags & KFD_IOC_ALLOC_MEM_FLAGS_VRAM) {
 		domain = alloc_domain = AMDGPU_GEM_DOMAIN_VRAM;
 
-		if (adev->gmc.is_app_apu || adev->flags & AMD_IS_APU) {
+		if (adev->flags & AMD_IS_APU) {
 			domain = AMDGPU_GEM_DOMAIN_GTT;
 			alloc_domain = AMDGPU_GEM_DOMAIN_GTT;
 			alloc_flags = 0;
@@ -1953,7 +1953,7 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu(
 	if (size) {
 		if (!is_imported &&
 		   (mem->bo->preferred_domains == AMDGPU_GEM_DOMAIN_VRAM ||
-		   ((adev->gmc.is_app_apu || adev->flags & AMD_IS_APU) &&
+		   ((adev->flags & AMD_IS_APU) &&
 		    mem->bo->preferred_domains == AMDGPU_GEM_DOMAIN_GTT)))
 			*size = bo_size;
 		else
@@ -2376,7 +2376,7 @@ static int import_obj_create(struct amdgpu_device *adev,
 	(*mem)->bo = bo;
 	(*mem)->va = va;
 	(*mem)->domain = (bo->preferred_domains & AMDGPU_GEM_DOMAIN_VRAM) &&
-			 !(adev->gmc.is_app_apu || adev->flags & AMD_IS_APU) ?
+			 !(adev->flags & AMD_IS_APU) ?
 			 AMDGPU_GEM_DOMAIN_VRAM : AMDGPU_GEM_DOMAIN_GTT;
 
 	(*mem)->mapped_to_gpu_memory = 0;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
index 4816fcb9803a9..8ee3d07ffbdfa 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
@@ -1023,7 +1023,7 @@ int kgd2kfd_init_zone_device(struct amdgpu_device *adev)
 	if (amdgpu_ip_version(adev, GC_HWIP, 0) < IP_VERSION(9, 0, 1))
 		return -EINVAL;
 
-	if (adev->gmc.is_app_apu || adev->flags & AMD_IS_APU)
+	if (adev->flags & AMD_IS_APU)
 		return 0;
 
 	pgmap = &kfddev->pgmap;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index 069b81eeea03c..31e500859ab01 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -2619,8 +2619,7 @@ svm_range_best_restore_location(struct svm_range *prange,
 		return -1;
 	}
 
-	if (node->adev->gmc.is_app_apu ||
-	    node->adev->flags & AMD_IS_APU)
+	if (node->adev->flags & AMD_IS_APU)
 		return 0;
 
 	if (prange->preferred_loc == gpuid ||
@@ -3338,8 +3337,7 @@ svm_range_best_prefetch_location(struct svm_range *prange)
 		goto out;
 	}
 
-	if (bo_node->adev->gmc.is_app_apu ||
-	    bo_node->adev->flags & AMD_IS_APU) {
+	if (bo_node->adev->flags & AMD_IS_APU) {
 		best_loc = 0;
 		goto out;
 	}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.h b/drivers/gpu/drm/amd/amdkfd/kfd_svm.h
index 9c37bd0567efa..70c1776611c47 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.h
@@ -201,7 +201,6 @@ void svm_range_list_lock_and_flush_work(struct svm_range_list *svms, struct mm_s
  * is initialized to not 0 when page migration register device memory.
  */
 #define KFD_IS_SVM_API_SUPPORTED(adev) ((adev)->kfd.pgmap.type != 0 ||\
-					(adev)->gmc.is_app_apu ||\
 					((adev)->flags & AMD_IS_APU))
 
 void svm_range_bo_unref_async(struct svm_range_bo *svm_bo);
-- 
GitLab


From a9bc5a19e4958fe664254d1ad2dc2a9f5868c210 Mon Sep 17 00:00:00 2001
From: Rajneesh Bhardwaj <rajneesh.bhardwaj@amd.com>
Date: Wed, 22 May 2024 15:04:29 -0400
Subject: [PATCH 509/950] drm/amdgpu: Make CPX mode auto default in NPS4

On GFXIP9.4.3, make CPX mode as the default compute mode if the node is
setup in NPS4 memory partition mode. This change is only applicable for
dGPU, for APU, continue to use TPX mode.

Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Rajneesh Bhardwaj <rajneesh.bhardwaj@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c b/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c
index 414ea3f560a7a..d4e2aed2efa33 100644
--- a/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c
+++ b/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c
@@ -422,7 +422,7 @@ __aqua_vanjaram_get_auto_mode(struct amdgpu_xcp_mgr *xcp_mgr)
 
 	if (adev->gmc.num_mem_partitions == num_xcc / 2)
 		return (adev->flags & AMD_IS_APU) ? AMDGPU_TPX_PARTITION_MODE :
-						    AMDGPU_QPX_PARTITION_MODE;
+						    AMDGPU_CPX_PARTITION_MODE;
 
 	if (adev->gmc.num_mem_partitions == 2 && !(adev->flags & AMD_IS_APU))
 		return AMDGPU_DPX_PARTITION_MODE;
-- 
GitLab


From 67c7d4fa267bcfe8d68fb36d938e3c6e0912b57d Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 9 May 2024 13:37:27 +0200
Subject: [PATCH 510/950] drm/amd/pm: remove deprecated I2C_CLASS_SPD support
 from newly added SMU_14_0_2

Support for I2C_CLASS_SPD  is currently being removed from the kernel.
Only remaining step is to remove the definition of I2C_CLASS_SPD.
Setting I2C_CLASS_SPD  in a driver is a no-op meanwhile, so remove it
here.

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
index 706265220292a..90703f4542aba 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
@@ -1562,7 +1562,6 @@ static int smu_v14_0_2_i2c_control_init(struct smu_context *smu)
 		smu_i2c->port = i;
 		mutex_init(&smu_i2c->mutex);
 		control->owner = THIS_MODULE;
-		control->class = I2C_CLASS_SPD;
 		control->dev.parent = &adev->pdev->dev;
 		control->algo = &smu_v14_0_2_i2c_algo;
 		snprintf(control->name, sizeof(control->name), "AMDGPU SMU %d", i);
-- 
GitLab


From fa0bc8f297b29126b5ae983406e9bc76d48a9a8e Mon Sep 17 00:00:00 2001
From: Armin Wolf <W_Armin@gmx.de>
Date: Wed, 22 May 2024 23:08:09 +0200
Subject: [PATCH 511/950] hwmon: (dell-smm) Add Dell G15 5511 to fan control
 whitelist
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

A user reported that he needs to disable BIOS fan control on his
Dell G15 5511 in order to be able to control the fans.

Closes: https://github.com/Wer-Wolf/i8kutils/issues/5
Signed-off-by: Armin Wolf <W_Armin@gmx.de>
Acked-by: Pali Rohár <pali@kernel.org>
Link: https://lore.kernel.org/r/20240522210809.294488-1-W_Armin@gmx.de
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/dell-smm-hwmon.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/hwmon/dell-smm-hwmon.c b/drivers/hwmon/dell-smm-hwmon.c
index 48a81c64f00d2..942526bd4775f 100644
--- a/drivers/hwmon/dell-smm-hwmon.c
+++ b/drivers/hwmon/dell-smm-hwmon.c
@@ -1545,6 +1545,14 @@ static const struct dmi_system_id i8k_whitelist_fan_control[] __initconst = {
 		},
 		.driver_data = (void *)&i8k_fan_control_data[I8K_FAN_30A3_31A3],
 	},
+	{
+		.ident = "Dell G15 5511",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Dell G15 5511"),
+		},
+		.driver_data = (void *)&i8k_fan_control_data[I8K_FAN_30A3_31A3],
+	},
 	{ }
 };
 
-- 
GitLab


From a94ff8e50c20bde6d50864849a98b106e45d30c6 Mon Sep 17 00:00:00 2001
From: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Date: Thu, 23 May 2024 17:47:14 +0200
Subject: [PATCH 512/950] hwmon: (ltc2992) Fix memory leak in
 ltc2992_parse_dt()

A new error path was added to the fwnode_for_each_available_node() loop
in ltc2992_parse_dt(), which leads to an early return that requires a
call to fwnode_handle_put() to avoid a memory leak in that case.

Add the missing fwnode_handle_put() in the error path from a zero value
shunt resistor.

Cc: stable@vger.kernel.org
Fixes: 10b029020487 ("hwmon: (ltc2992) Avoid division by zero")
Signed-off-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Link: https://lore.kernel.org/r/20240523-fwnode_for_each_available_child_node_scoped-v2-1-701f3a03f2fb@gmail.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/ltc2992.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/hwmon/ltc2992.c b/drivers/hwmon/ltc2992.c
index 229aed15d5caa..d4a93223cd3b3 100644
--- a/drivers/hwmon/ltc2992.c
+++ b/drivers/hwmon/ltc2992.c
@@ -876,9 +876,11 @@ static int ltc2992_parse_dt(struct ltc2992_state *st)
 
 		ret = fwnode_property_read_u32(child, "shunt-resistor-micro-ohms", &val);
 		if (!ret) {
-			if (!val)
+			if (!val) {
+				fwnode_handle_put(child);
 				return dev_err_probe(&st->client->dev, -EINVAL,
 						     "shunt resistor value cannot be zero\n");
+			}
 			st->r_sense_uohm[addr] = val;
 		}
 	}
-- 
GitLab


From 4665415975b0827e9646cab91c61d02a6b364d59 Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Fri, 17 May 2024 10:30:33 +0800
Subject: [PATCH 513/950] bpf: Add bits iterator

Add three new kfuncs for the bits iterator:
- bpf_iter_bits_new
  Initialize a new bits iterator for a given memory area. Due to the
  limitation of bpf memalloc, the max number of words (8-byte units) that
  can be iterated over is limited to (4096 / 8).
- bpf_iter_bits_next
  Get the next bit in a bpf_iter_bits
- bpf_iter_bits_destroy
  Destroy a bpf_iter_bits

The bits iterator facilitates the iteration of the bits of a memory area,
such as cpumask. It can be used in any context and on any address.

Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20240517023034.48138-2-laoar.shao@gmail.com
---
 kernel/bpf/helpers.c | 119 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 119 insertions(+)

diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 2a69a9a36c0fc..6f1abcb4b0840 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -2744,6 +2744,122 @@ __bpf_kfunc void bpf_preempt_enable(void)
 	preempt_enable();
 }
 
+struct bpf_iter_bits {
+	__u64 __opaque[2];
+} __aligned(8);
+
+struct bpf_iter_bits_kern {
+	union {
+		unsigned long *bits;
+		unsigned long bits_copy;
+	};
+	u32 nr_bits;
+	int bit;
+} __aligned(8);
+
+/**
+ * bpf_iter_bits_new() - Initialize a new bits iterator for a given memory area
+ * @it: The new bpf_iter_bits to be created
+ * @unsafe_ptr__ign: A pointer pointing to a memory area to be iterated over
+ * @nr_words: The size of the specified memory area, measured in 8-byte units.
+ * Due to the limitation of memalloc, it can't be greater than 512.
+ *
+ * This function initializes a new bpf_iter_bits structure for iterating over
+ * a memory area which is specified by the @unsafe_ptr__ign and @nr_words. It
+ * copies the data of the memory area to the newly created bpf_iter_bits @it for
+ * subsequent iteration operations.
+ *
+ * On success, 0 is returned. On failure, ERR is returned.
+ */
+__bpf_kfunc int
+bpf_iter_bits_new(struct bpf_iter_bits *it, const u64 *unsafe_ptr__ign, u32 nr_words)
+{
+	struct bpf_iter_bits_kern *kit = (void *)it;
+	u32 nr_bytes = nr_words * sizeof(u64);
+	u32 nr_bits = BYTES_TO_BITS(nr_bytes);
+	int err;
+
+	BUILD_BUG_ON(sizeof(struct bpf_iter_bits_kern) != sizeof(struct bpf_iter_bits));
+	BUILD_BUG_ON(__alignof__(struct bpf_iter_bits_kern) !=
+		     __alignof__(struct bpf_iter_bits));
+
+	kit->nr_bits = 0;
+	kit->bits_copy = 0;
+	kit->bit = -1;
+
+	if (!unsafe_ptr__ign || !nr_words)
+		return -EINVAL;
+
+	/* Optimization for u64 mask */
+	if (nr_bits == 64) {
+		err = bpf_probe_read_kernel_common(&kit->bits_copy, nr_bytes, unsafe_ptr__ign);
+		if (err)
+			return -EFAULT;
+
+		kit->nr_bits = nr_bits;
+		return 0;
+	}
+
+	/* Fallback to memalloc */
+	kit->bits = bpf_mem_alloc(&bpf_global_ma, nr_bytes);
+	if (!kit->bits)
+		return -ENOMEM;
+
+	err = bpf_probe_read_kernel_common(kit->bits, nr_bytes, unsafe_ptr__ign);
+	if (err) {
+		bpf_mem_free(&bpf_global_ma, kit->bits);
+		return err;
+	}
+
+	kit->nr_bits = nr_bits;
+	return 0;
+}
+
+/**
+ * bpf_iter_bits_next() - Get the next bit in a bpf_iter_bits
+ * @it: The bpf_iter_bits to be checked
+ *
+ * This function returns a pointer to a number representing the value of the
+ * next bit in the bits.
+ *
+ * If there are no further bits available, it returns NULL.
+ */
+__bpf_kfunc int *bpf_iter_bits_next(struct bpf_iter_bits *it)
+{
+	struct bpf_iter_bits_kern *kit = (void *)it;
+	u32 nr_bits = kit->nr_bits;
+	const unsigned long *bits;
+	int bit;
+
+	if (nr_bits == 0)
+		return NULL;
+
+	bits = nr_bits == 64 ? &kit->bits_copy : kit->bits;
+	bit = find_next_bit(bits, nr_bits, kit->bit + 1);
+	if (bit >= nr_bits) {
+		kit->nr_bits = 0;
+		return NULL;
+	}
+
+	kit->bit = bit;
+	return &kit->bit;
+}
+
+/**
+ * bpf_iter_bits_destroy() - Destroy a bpf_iter_bits
+ * @it: The bpf_iter_bits to be destroyed
+ *
+ * Destroy the resource associated with the bpf_iter_bits.
+ */
+__bpf_kfunc void bpf_iter_bits_destroy(struct bpf_iter_bits *it)
+{
+	struct bpf_iter_bits_kern *kit = (void *)it;
+
+	if (kit->nr_bits <= 64)
+		return;
+	bpf_mem_free(&bpf_global_ma, kit->bits);
+}
+
 __bpf_kfunc_end_defs();
 
 BTF_KFUNCS_START(generic_btf_ids)
@@ -2826,6 +2942,9 @@ BTF_ID_FLAGS(func, bpf_wq_set_callback_impl)
 BTF_ID_FLAGS(func, bpf_wq_start)
 BTF_ID_FLAGS(func, bpf_preempt_disable)
 BTF_ID_FLAGS(func, bpf_preempt_enable)
+BTF_ID_FLAGS(func, bpf_iter_bits_new, KF_ITER_NEW)
+BTF_ID_FLAGS(func, bpf_iter_bits_next, KF_ITER_NEXT | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_iter_bits_destroy, KF_ITER_DESTROY)
 BTF_KFUNCS_END(common_btf_ids)
 
 static const struct btf_kfunc_id_set common_kfunc_set = {
-- 
GitLab


From 6ba7acdb93b4ecb554d5838fca3f5f0fcf9fff14 Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Fri, 17 May 2024 10:30:34 +0800
Subject: [PATCH 514/950] selftests/bpf: Add selftest for bits iter

Add test cases for the bits iter:

- Positive cases
  - Bit mask representing a single word (8-byte unit)
  - Bit mask representing data spanning more than one word
  - The index of the set bit

- Nagative cases
  - bpf_iter_bits_destroy() is required after calling
    bpf_iter_bits_new()
  - bpf_iter_bits_destroy() can only destroy an initialized iter
  - bpf_iter_bits_next() must use an initialized iter
  - Bit mask representing zero words
  - Bit mask representing fewer words than expected
  - Case for ENOMEM
  - Case for NULL pointer

Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20240517023034.48138-3-laoar.shao@gmail.com
---
 .../selftests/bpf/prog_tests/verifier.c       |   2 +
 .../selftests/bpf/progs/verifier_bits_iter.c  | 153 ++++++++++++++++++
 2 files changed, 155 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/progs/verifier_bits_iter.c

diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c
index c60db8beeb734..8743340b5bf6b 100644
--- a/tools/testing/selftests/bpf/prog_tests/verifier.c
+++ b/tools/testing/selftests/bpf/prog_tests/verifier.c
@@ -85,6 +85,7 @@
 #include "verifier_xadd.skel.h"
 #include "verifier_xdp.skel.h"
 #include "verifier_xdp_direct_packet_access.skel.h"
+#include "verifier_bits_iter.skel.h"
 
 #define MAX_ENTRIES 11
 
@@ -200,6 +201,7 @@ void test_verifier_var_off(void)              { RUN(verifier_var_off); }
 void test_verifier_xadd(void)                 { RUN(verifier_xadd); }
 void test_verifier_xdp(void)                  { RUN(verifier_xdp); }
 void test_verifier_xdp_direct_packet_access(void) { RUN(verifier_xdp_direct_packet_access); }
+void test_verifier_bits_iter(void) { RUN(verifier_bits_iter); }
 
 static int init_test_val_map(struct bpf_object *obj, char *map_name)
 {
diff --git a/tools/testing/selftests/bpf/progs/verifier_bits_iter.c b/tools/testing/selftests/bpf/progs/verifier_bits_iter.c
new file mode 100644
index 0000000000000..716113c2bce21
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_bits_iter.c
@@ -0,0 +1,153 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2024 Yafang Shao <laoar.shao@gmail.com> */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+#include "bpf_misc.h"
+#include "task_kfunc_common.h"
+
+char _license[] SEC("license") = "GPL";
+
+int bpf_iter_bits_new(struct bpf_iter_bits *it, const u64 *unsafe_ptr__ign,
+		      u32 nr_bits) __ksym __weak;
+int *bpf_iter_bits_next(struct bpf_iter_bits *it) __ksym __weak;
+void bpf_iter_bits_destroy(struct bpf_iter_bits *it) __ksym __weak;
+
+SEC("iter.s/cgroup")
+__description("bits iter without destroy")
+__failure __msg("Unreleased reference")
+int BPF_PROG(no_destroy, struct bpf_iter_meta *meta, struct cgroup *cgrp)
+{
+	struct bpf_iter_bits it;
+	u64 data = 1;
+
+	bpf_iter_bits_new(&it, &data, 1);
+	bpf_iter_bits_next(&it);
+	return 0;
+}
+
+SEC("iter/cgroup")
+__description("uninitialized iter in ->next()")
+__failure __msg("expected an initialized iter_bits as arg #1")
+int BPF_PROG(next_uninit, struct bpf_iter_meta *meta, struct cgroup *cgrp)
+{
+	struct bpf_iter_bits *it = NULL;
+
+	bpf_iter_bits_next(it);
+	return 0;
+}
+
+SEC("iter/cgroup")
+__description("uninitialized iter in ->destroy()")
+__failure __msg("expected an initialized iter_bits as arg #1")
+int BPF_PROG(destroy_uninit, struct bpf_iter_meta *meta, struct cgroup *cgrp)
+{
+	struct bpf_iter_bits it = {};
+
+	bpf_iter_bits_destroy(&it);
+	return 0;
+}
+
+SEC("syscall")
+__description("null pointer")
+__success __retval(0)
+int null_pointer(void)
+{
+	int nr = 0;
+	int *bit;
+
+	bpf_for_each(bits, bit, NULL, 1)
+		nr++;
+	return nr;
+}
+
+SEC("syscall")
+__description("bits copy")
+__success __retval(10)
+int bits_copy(void)
+{
+	u64 data = 0xf7310UL; /* 4 + 3 + 2 + 1 + 0*/
+	int nr = 0;
+	int *bit;
+
+	bpf_for_each(bits, bit, &data, 1)
+		nr++;
+	return nr;
+}
+
+SEC("syscall")
+__description("bits memalloc")
+__success __retval(64)
+int bits_memalloc(void)
+{
+	u64 data[2];
+	int nr = 0;
+	int *bit;
+
+	__builtin_memset(&data, 0xf0, sizeof(data)); /* 4 * 16 */
+	bpf_for_each(bits, bit, &data[0], sizeof(data) / sizeof(u64))
+		nr++;
+	return nr;
+}
+
+SEC("syscall")
+__description("bit index")
+__success __retval(8)
+int bit_index(void)
+{
+	u64 data = 0x100;
+	int bit_idx = 0;
+	int *bit;
+
+	bpf_for_each(bits, bit, &data, 1) {
+		if (*bit == 0)
+			continue;
+		bit_idx = *bit;
+	}
+	return bit_idx;
+}
+
+SEC("syscall")
+__description("bits nomem")
+__success __retval(0)
+int bits_nomem(void)
+{
+	u64 data[4];
+	int nr = 0;
+	int *bit;
+
+	__builtin_memset(&data, 0xff, sizeof(data));
+	bpf_for_each(bits, bit, &data[0], 513) /* Be greater than 512 */
+		nr++;
+	return nr;
+}
+
+SEC("syscall")
+__description("fewer words")
+__success __retval(1)
+int fewer_words(void)
+{
+	u64 data[2] = {0x1, 0xff};
+	int nr = 0;
+	int *bit;
+
+	bpf_for_each(bits, bit, &data[0], 1)
+		nr++;
+	return nr;
+}
+
+SEC("syscall")
+__description("zero words")
+__success __retval(0)
+int zero_words(void)
+{
+	u64 data[2] = {0x1, 0xff};
+	int nr = 0;
+	int *bit;
+
+	bpf_for_each(bits, bit, &data[0], 0)
+		nr++;
+	return nr;
+}
-- 
GitLab


From 126913479e88e7e0114efe380d2437cc70d9dc05 Mon Sep 17 00:00:00 2001
From: Alexander Sverdlin <alexander.sverdlin@siemens.com>
Date: Tue, 28 May 2024 09:31:13 +0200
Subject: [PATCH 515/950] net: dsa: lan9303: imply SMSC_PHY

Both LAN9303 and LAN9354 have internal PHYs on both external ports.
Therefore a configuration without SMSC PHY support is non-practical at
least and leads to:

LAN9303_MDIO 8000f00.mdio:00: Found LAN9303 rev. 1
mdio_bus 8000f00.mdio:00: deferred probe pending: (reason unknown)

Signed-off-by: Alexander Sverdlin <alexander.sverdlin@siemens.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://lore.kernel.org/r/20240528073147.3604083-1-alexander.sverdlin@siemens.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/dsa/Kconfig b/drivers/net/dsa/Kconfig
index 3092b391031a8..8508b5145bc14 100644
--- a/drivers/net/dsa/Kconfig
+++ b/drivers/net/dsa/Kconfig
@@ -102,6 +102,7 @@ config NET_DSA_SMSC_LAN9303
 	tristate
 	select NET_DSA_TAG_LAN9303
 	select REGMAP
+	imply SMSC_PHY
 	help
 	  This enables support for the Microchip LAN9303/LAN9354 3 port ethernet
 	  switch chips.
-- 
GitLab


From 544a74c32bcc2eff5f93b9f638f687170e7274e9 Mon Sep 17 00:00:00 2001
From: Jonas Karlman <jonas@kwiboo.se>
Date: Tue, 28 May 2024 09:37:48 +0000
Subject: [PATCH 516/950] dt-bindings: net: rockchip-dwmac: Fix
 rockchip,rk3308-gmac compatible

Schema validation using rockchip,rk3308-gmac compatible fails with:

  ethernet@ff4e0000: compatible: ['rockchip,rk3308-gmac'] does not contain items matching the given schema
        from schema $id: http://devicetree.org/schemas/net/rockchip-dwmac.yaml#
  ethernet@ff4e0000: Unevaluated properties are not allowed ('interrupt-names', 'interrupts', 'phy-mode',
                     'reg', 'reset-names', 'resets', 'snps,reset-active-low', 'snps,reset-delays-us',
                     'snps,reset-gpio' were unexpected)
        from schema $id: http://devicetree.org/schemas/net/rockchip-dwmac.yaml#

Add rockchip,rk3308-gmac to snps,dwmac.yaml to fix DT schema validation.

Fixes: 2cc8c910f515 ("dt-bindings: net: rockchip-dwmac: add rk3308 gmac compatible")
Signed-off-by: Jonas Karlman <jonas@kwiboo.se>
Reviewed-by: Heiko Stuebner <heiko@sntech.de>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20240528093751.3690231-1-jonas@kwiboo.se
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/devicetree/bindings/net/snps,dwmac.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/net/snps,dwmac.yaml b/Documentation/devicetree/bindings/net/snps,dwmac.yaml
index 21cc27e75f50a..3bab4e1f3fbf6 100644
--- a/Documentation/devicetree/bindings/net/snps,dwmac.yaml
+++ b/Documentation/devicetree/bindings/net/snps,dwmac.yaml
@@ -76,6 +76,7 @@ properties:
         - rockchip,rk3128-gmac
         - rockchip,rk3228-gmac
         - rockchip,rk3288-gmac
+        - rockchip,rk3308-gmac
         - rockchip,rk3328-gmac
         - rockchip,rk3366-gmac
         - rockchip,rk3368-gmac
-- 
GitLab


From c3390677f6258748a91bf37b9bb21eab89f63b42 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Tue, 28 May 2024 01:42:24 -0700
Subject: [PATCH 517/950] netconsole: Do not shutdown dynamic configuration if
 cmdline is invalid

If a user provides an invalid netconsole configuration during boot time
(e.g., specifying an invalid ethX interface), netconsole will be
entirely disabled. Consequently, the user won't be able to create new
entries in /sys/kernel/config/netconsole/ as that directory does not
exist.

Apart from misconfiguration, another issue arises when ethX is loaded as
a module and the netconsole= line in the command line points to ethX,
resulting in an obvious failure. This renders netconsole unusable, as
/sys/kernel/config/netconsole/ will never appear. This is more annoying
since users reconfigure (or just toggle) the configuratin later (see
commit 5fbd6cdbe304b ("netconsole: Attach cmdline target to dynamic
target"))

Create /sys/kernel/config/netconsole/ even if the command line arguments
are invalid, so, users can create dynamic entries in netconsole.

Reported-by: Aijay Adams <aijay@meta.com>
Signed-off-by: Breno Leitao <leitao@debian.org>
Link: https://lore.kernel.org/r/20240528084225.3215853-1-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/netconsole.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c
index d7070dd4fe736..ab8a0623b1a17 100644
--- a/drivers/net/netconsole.c
+++ b/drivers/net/netconsole.c
@@ -1262,6 +1262,8 @@ static int __init init_netconsole(void)
 		while ((target_config = strsep(&input, ";"))) {
 			nt = alloc_param_target(target_config, count);
 			if (IS_ERR(nt)) {
+				if (IS_ENABLED(CONFIG_NETCONSOLE_DYNAMIC))
+					continue;
 				err = PTR_ERR(nt);
 				goto fail;
 			}
-- 
GitLab


From 5e514f1cba090e1c8fff03e92a175eccfe46305f Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 28 May 2024 12:52:50 +0000
Subject: [PATCH 518/950] tcp: add tcp_done_with_error() helper

tcp_reset() ends with a sequence that is carefuly ordered.

We need to fix [e]poll bugs in the following patches,
it makes sense to use a common helper.

Suggested-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Link: https://lore.kernel.org/r/20240528125253.1966136-2-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/tcp.h    |  1 +
 net/ipv4/tcp.c       |  2 +-
 net/ipv4/tcp_input.c | 32 +++++++++++++++++++++-----------
 3 files changed, 23 insertions(+), 12 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 060e95b331a28..32815a40dea16 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -677,6 +677,7 @@ void tcp_skb_collapse_tstamp(struct sk_buff *skb,
 /* tcp_input.c */
 void tcp_rearm_rto(struct sock *sk);
 void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req);
+void tcp_done_with_error(struct sock *sk, int err);
 void tcp_reset(struct sock *sk, struct sk_buff *skb);
 void tcp_fin(struct sock *sk);
 void tcp_check_space(struct sock *sk);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 681b54e1f3a64..2a8f8d8676ff1 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -598,7 +598,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 		 */
 		mask |= EPOLLOUT | EPOLLWRNORM;
 	}
-	/* This barrier is coupled with smp_wmb() in tcp_reset() */
+	/* This barrier is coupled with smp_wmb() in tcp_done_with_error() */
 	smp_rmb();
 	if (READ_ONCE(sk->sk_err) ||
 	    !skb_queue_empty_lockless(&sk->sk_error_queue))
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 9c04a9c8be9df..5aadf64e554d8 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4436,9 +4436,26 @@ static enum skb_drop_reason tcp_sequence(const struct tcp_sock *tp,
 	return SKB_NOT_DROPPED_YET;
 }
 
+
+void tcp_done_with_error(struct sock *sk, int err)
+{
+	/* This barrier is coupled with smp_rmb() in tcp_poll() */
+	WRITE_ONCE(sk->sk_err, err);
+	smp_wmb();
+
+	tcp_write_queue_purge(sk);
+	tcp_done(sk);
+
+	if (!sock_flag(sk, SOCK_DEAD))
+		sk_error_report(sk);
+}
+EXPORT_SYMBOL(tcp_done_with_error);
+
 /* When we get a reset we do this. */
 void tcp_reset(struct sock *sk, struct sk_buff *skb)
 {
+	int err;
+
 	trace_tcp_receive_reset(sk);
 
 	/* mptcp can't tell us to ignore reset pkts,
@@ -4450,24 +4467,17 @@ void tcp_reset(struct sock *sk, struct sk_buff *skb)
 	/* We want the right error as BSD sees it (and indeed as we do). */
 	switch (sk->sk_state) {
 	case TCP_SYN_SENT:
-		WRITE_ONCE(sk->sk_err, ECONNREFUSED);
+		err = ECONNREFUSED;
 		break;
 	case TCP_CLOSE_WAIT:
-		WRITE_ONCE(sk->sk_err, EPIPE);
+		err = EPIPE;
 		break;
 	case TCP_CLOSE:
 		return;
 	default:
-		WRITE_ONCE(sk->sk_err, ECONNRESET);
+		err = ECONNRESET;
 	}
-	/* This barrier is coupled with smp_rmb() in tcp_poll() */
-	smp_wmb();
-
-	tcp_write_queue_purge(sk);
-	tcp_done(sk);
-
-	if (!sock_flag(sk, SOCK_DEAD))
-		sk_error_report(sk);
+	tcp_done_with_error(sk, err);
 }
 
 /*
-- 
GitLab


From 853c3bd7b7917670224c9fe5245bd045cac411dd Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 28 May 2024 12:52:51 +0000
Subject: [PATCH 519/950] tcp: fix race in tcp_write_err()

I noticed flakes in a packetdrill test, expecting an epoll_wait()
to return EPOLLERR | EPOLLHUP on a failed connect() attempt,
after multiple SYN retransmits. It sometimes return EPOLLERR only.

The issue is that tcp_write_err():
 1) writes an error in sk->sk_err,
 2) calls sk_error_report(),
 3) then calls tcp_done().

tcp_done() is writing SHUTDOWN_MASK into sk->sk_shutdown,
among other things.

Problem is that the awaken user thread (from 2) sk_error_report())
might call tcp_poll() before tcp_done() has written sk->sk_shutdown.

tcp_poll() only sees a non zero sk->sk_err and returns EPOLLERR.

This patch fixes the issue by making sure to call sk_error_report()
after tcp_done().

tcp_write_err() also lacks an smp_wmb().

We can reuse tcp_done_with_error() to factor out the details,
as Neal suggested.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Link: https://lore.kernel.org/r/20240528125253.1966136-3-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/tcp_timer.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 83fe7f62f7f10..3e8604ae7d06c 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -74,11 +74,7 @@ u32 tcp_clamp_probe0_to_user_timeout(const struct sock *sk, u32 when)
 
 static void tcp_write_err(struct sock *sk)
 {
-	WRITE_ONCE(sk->sk_err, READ_ONCE(sk->sk_err_soft) ? : ETIMEDOUT);
-	sk_error_report(sk);
-
-	tcp_write_queue_purge(sk);
-	tcp_done(sk);
+	tcp_done_with_error(sk, READ_ONCE(sk->sk_err_soft) ? : ETIMEDOUT);
 	__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONTIMEOUT);
 }
 
-- 
GitLab


From 5ce4645c23cf5f048eb8e9ce49e514bababdee85 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 28 May 2024 12:52:52 +0000
Subject: [PATCH 520/950] tcp: fix races in tcp_abort()

tcp_abort() has the same issue than the one fixed in the prior patch
in tcp_write_err().

In order to get consistent results from tcp_poll(), we must call
sk_error_report() after tcp_done().

We can use tcp_done_with_error() to centralize this logic.

Fixes: c1e64e298b8c ("net: diag: Support destroying TCP sockets.")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Link: https://lore.kernel.org/r/20240528125253.1966136-4-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/tcp.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 2a8f8d8676ff1..5fa68e7f6ddbf 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -4576,14 +4576,10 @@ int tcp_abort(struct sock *sk, int err)
 	bh_lock_sock(sk);
 
 	if (!sock_flag(sk, SOCK_DEAD)) {
-		WRITE_ONCE(sk->sk_err, err);
-		/* This barrier is coupled with smp_rmb() in tcp_poll() */
-		smp_wmb();
-		sk_error_report(sk);
 		if (tcp_need_reset(sk->sk_state))
 			tcp_send_active_reset(sk, GFP_ATOMIC,
 					      SK_RST_REASON_NOT_SPECIFIED);
-		tcp_done(sk);
+		tcp_done_with_error(sk, err);
 	}
 
 	bh_unlock_sock(sk);
-- 
GitLab


From fde6f897f2a184546bf5516ac736523ef24dc6a7 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 28 May 2024 12:52:53 +0000
Subject: [PATCH 521/950] tcp: fix races in tcp_v[46]_err()

These functions have races when they:

1) Write sk->sk_err
2) call sk_error_report(sk)
3) call tcp_done(sk)

As described in prior patches in this series:

An smp_wmb() is missing.
We should call tcp_done() before sk_error_report(sk)
to have consistent tcp_poll() results on SMP hosts.

Use tcp_done_with_error() where we centralized the
correct sequence.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Link: https://lore.kernel.org/r/20240528125253.1966136-5-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/tcp_ipv4.c | 11 +++--------
 net/ipv6/tcp_ipv6.c | 10 +++-------
 2 files changed, 6 insertions(+), 15 deletions(-)

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 8f70b8d1d1e56..041c7eda9abe2 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -611,15 +611,10 @@ int tcp_v4_err(struct sk_buff *skb, u32 info)
 
 		ip_icmp_error(sk, skb, err, th->dest, info, (u8 *)th);
 
-		if (!sock_owned_by_user(sk)) {
-			WRITE_ONCE(sk->sk_err, err);
-
-			sk_error_report(sk);
-
-			tcp_done(sk);
-		} else {
+		if (!sock_owned_by_user(sk))
+			tcp_done_with_error(sk, err);
+		else
 			WRITE_ONCE(sk->sk_err_soft, err);
-		}
 		goto out;
 	}
 
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 750aa681779ca..1ac7502e1bf5b 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -490,14 +490,10 @@ static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 
 		ipv6_icmp_error(sk, skb, err, th->dest, ntohl(info), (u8 *)th);
 
-		if (!sock_owned_by_user(sk)) {
-			WRITE_ONCE(sk->sk_err, err);
-			sk_error_report(sk);		/* Wake people up to see the error (see connect in sock.c) */
-
-			tcp_done(sk);
-		} else {
+		if (!sock_owned_by_user(sk))
+			tcp_done_with_error(sk, err);
+		else
 			WRITE_ONCE(sk->sk_err_soft, err);
-		}
 		goto out;
 	case TCP_LISTEN:
 		break;
-- 
GitLab


From 78269025e192ec8122ddd87a1ec2805598d8a1ab Mon Sep 17 00:00:00 2001
From: Alexander Sverdlin <alexander.sverdlin@siemens.com>
Date: Tue, 28 May 2024 09:59:49 +0200
Subject: [PATCH 522/950] net: ethernet: ti: am65-cpsw-nuss: rename phy_node ->
 port_np

Rename phy_node to port_np to better reflect what it actually is,
because the new phylink API takes netdev node (or DSA port node),
and resolves the phandle internally.

Signed-off-by: Alexander Sverdlin <alexander.sverdlin@siemens.com>
Link: https://lore.kernel.org/r/20240528075954.3608118-2-alexander.sverdlin@siemens.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/ti/am65-cpsw-nuss.c | 6 +++---
 drivers/net/ethernet/ti/am65-cpsw-nuss.h | 2 +-
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
index 4e50b37928885..eaadf8f09c401 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
@@ -896,7 +896,7 @@ static int am65_cpsw_nuss_ndo_slave_open(struct net_device *ndev)
 	/* mac_sl should be configured via phy-link interface */
 	am65_cpsw_sl_ctl_reset(port);
 
-	ret = phylink_of_phy_connect(port->slave.phylink, port->slave.phy_node, 0);
+	ret = phylink_of_phy_connect(port->slave.phylink, port->slave.port_np, 0);
 	if (ret)
 		goto error_cleanup;
 
@@ -2611,7 +2611,7 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common)
 				of_property_read_bool(port_np, "ti,mac-only");
 
 		/* get phy/link info */
-		port->slave.phy_node = port_np;
+		port->slave.port_np = port_np;
 		ret = of_get_phy_mode(port_np, &port->slave.phy_if);
 		if (ret) {
 			dev_err(dev, "%pOF read phy-mode err %d\n",
@@ -2760,7 +2760,7 @@ am65_cpsw_nuss_init_port_ndev(struct am65_cpsw_common *common, u32 port_idx)
 	}
 
 	phylink = phylink_create(&port->slave.phylink_config,
-				 of_node_to_fwnode(port->slave.phy_node),
+				 of_node_to_fwnode(port->slave.port_np),
 				 port->slave.phy_if,
 				 &am65_cpsw_phylink_mac_ops);
 	if (IS_ERR(phylink))
diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.h b/drivers/net/ethernet/ti/am65-cpsw-nuss.h
index d8ce88dc9c89a..e2ce2be320bd6 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.h
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.h
@@ -30,7 +30,7 @@ struct am65_cpts;
 struct am65_cpsw_slave_data {
 	bool				mac_only;
 	struct cpsw_sl			*mac_sl;
-	struct device_node		*phy_node;
+	struct device_node		*port_np;
 	phy_interface_t			phy_if;
 	struct phy			*ifphy;
 	struct phy			*serdes_phy;
-- 
GitLab


From 29c71bf2a05a11f0d139590d37d92547477d5eb2 Mon Sep 17 00:00:00 2001
From: Alexander Sverdlin <alexander.sverdlin@siemens.com>
Date: Tue, 28 May 2024 09:59:50 +0200
Subject: [PATCH 523/950] net: ethernet: ti: am65-cpsw-nuss: populate netdev
 of_node

So that of_find_net_device_by_node() can find cpsw-nuss ports and other DSA
switches can be stacked downstream.

Signed-off-by: Alexander Sverdlin <alexander.sverdlin@siemens.com>
Link: https://lore.kernel.org/r/20240528075954.3608118-3-alexander.sverdlin@siemens.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/ti/am65-cpsw-nuss.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
index eaadf8f09c401..e6f87ac394fe6 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
@@ -2703,6 +2703,7 @@ am65_cpsw_nuss_init_port_ndev(struct am65_cpsw_common *common, u32 port_idx)
 	mutex_init(&ndev_priv->mm_lock);
 	port->qos.link_speed = SPEED_UNKNOWN;
 	SET_NETDEV_DEV(port->ndev, dev);
+	port->ndev->dev.of_node = port->slave.port_np;
 
 	eth_hw_addr_set(port->ndev, port->slave.mac_addr);
 
-- 
GitLab


From 92f1655aa2b2294d0b49925f3b875a634bd3b59e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 28 May 2024 11:43:53 +0000
Subject: [PATCH 524/950] net: fix __dst_negative_advice() race

__dst_negative_advice() does not enforce proper RCU rules when
sk->dst_cache must be cleared, leading to possible UAF.

RCU rules are that we must first clear sk->sk_dst_cache,
then call dst_release(old_dst).

Note that sk_dst_reset(sk) is implementing this protocol correctly,
while __dst_negative_advice() uses the wrong order.

Given that ip6_negative_advice() has special logic
against RTF_CACHE, this means each of the three ->negative_advice()
existing methods must perform the sk_dst_reset() themselves.

Note the check against NULL dst is centralized in
__dst_negative_advice(), there is no need to duplicate
it in various callbacks.

Many thanks to Clement Lecigne for tracking this issue.

This old bug became visible after the blamed commit, using UDP sockets.

Fixes: a87cb3e48ee8 ("net: Facility to report route quality of connected sockets")
Reported-by: Clement Lecigne <clecigne@google.com>
Diagnosed-by: Clement Lecigne <clecigne@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Tom Herbert <tom@herbertland.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20240528114353.1794151-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/dst_ops.h  |  2 +-
 include/net/sock.h     | 13 +++----------
 net/ipv4/route.c       | 22 ++++++++--------------
 net/ipv6/route.c       | 29 +++++++++++++++--------------
 net/xfrm/xfrm_policy.c | 11 +++--------
 5 files changed, 30 insertions(+), 47 deletions(-)

diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h
index 6d1c8541183db..3a9001a042a5c 100644
--- a/include/net/dst_ops.h
+++ b/include/net/dst_ops.h
@@ -24,7 +24,7 @@ struct dst_ops {
 	void			(*destroy)(struct dst_entry *);
 	void			(*ifdown)(struct dst_entry *,
 					  struct net_device *dev);
-	struct dst_entry *	(*negative_advice)(struct dst_entry *);
+	void			(*negative_advice)(struct sock *sk, struct dst_entry *);
 	void			(*link_failure)(struct sk_buff *);
 	void			(*update_pmtu)(struct dst_entry *dst, struct sock *sk,
 					       struct sk_buff *skb, u32 mtu,
diff --git a/include/net/sock.h b/include/net/sock.h
index 5f4d0629348f3..953c8dc4e259e 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2063,17 +2063,10 @@ sk_dst_get(const struct sock *sk)
 
 static inline void __dst_negative_advice(struct sock *sk)
 {
-	struct dst_entry *ndst, *dst = __sk_dst_get(sk);
+	struct dst_entry *dst = __sk_dst_get(sk);
 
-	if (dst && dst->ops->negative_advice) {
-		ndst = dst->ops->negative_advice(dst);
-
-		if (ndst != dst) {
-			rcu_assign_pointer(sk->sk_dst_cache, ndst);
-			sk_tx_queue_clear(sk);
-			WRITE_ONCE(sk->sk_dst_pending_confirm, 0);
-		}
-	}
+	if (dst && dst->ops->negative_advice)
+		dst->ops->negative_advice(sk, dst);
 }
 
 static inline void dst_negative_advice(struct sock *sk)
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 5fd54103174f7..b3073d1c8f8f7 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -129,7 +129,8 @@ struct dst_entry	*ipv4_dst_check(struct dst_entry *dst, u32 cookie);
 static unsigned int	 ipv4_default_advmss(const struct dst_entry *dst);
 INDIRECT_CALLABLE_SCOPE
 unsigned int		ipv4_mtu(const struct dst_entry *dst);
-static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst);
+static void		ipv4_negative_advice(struct sock *sk,
+					     struct dst_entry *dst);
 static void		 ipv4_link_failure(struct sk_buff *skb);
 static void		 ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
 					   struct sk_buff *skb, u32 mtu,
@@ -825,22 +826,15 @@ static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buf
 	__ip_do_redirect(rt, skb, &fl4, true);
 }
 
-static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst)
+static void ipv4_negative_advice(struct sock *sk,
+				 struct dst_entry *dst)
 {
 	struct rtable *rt = dst_rtable(dst);
-	struct dst_entry *ret = dst;
 
-	if (rt) {
-		if (dst->obsolete > 0) {
-			ip_rt_put(rt);
-			ret = NULL;
-		} else if ((rt->rt_flags & RTCF_REDIRECTED) ||
-			   rt->dst.expires) {
-			ip_rt_put(rt);
-			ret = NULL;
-		}
-	}
-	return ret;
+	if ((dst->obsolete > 0) ||
+	    (rt->rt_flags & RTCF_REDIRECTED) ||
+	    rt->dst.expires)
+		sk_dst_reset(sk);
 }
 
 /*
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index bbc2a0dd93142..a504b88ec06b5 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -87,7 +87,8 @@ struct dst_entry	*ip6_dst_check(struct dst_entry *dst, u32 cookie);
 static unsigned int	 ip6_default_advmss(const struct dst_entry *dst);
 INDIRECT_CALLABLE_SCOPE
 unsigned int		ip6_mtu(const struct dst_entry *dst);
-static struct dst_entry *ip6_negative_advice(struct dst_entry *);
+static void		ip6_negative_advice(struct sock *sk,
+					    struct dst_entry *dst);
 static void		ip6_dst_destroy(struct dst_entry *);
 static void		ip6_dst_ifdown(struct dst_entry *,
 				       struct net_device *dev);
@@ -2770,24 +2771,24 @@ INDIRECT_CALLABLE_SCOPE struct dst_entry *ip6_dst_check(struct dst_entry *dst,
 }
 EXPORT_INDIRECT_CALLABLE(ip6_dst_check);
 
-static struct dst_entry *ip6_negative_advice(struct dst_entry *dst)
+static void ip6_negative_advice(struct sock *sk,
+				struct dst_entry *dst)
 {
 	struct rt6_info *rt = dst_rt6_info(dst);
 
-	if (rt) {
-		if (rt->rt6i_flags & RTF_CACHE) {
-			rcu_read_lock();
-			if (rt6_check_expired(rt)) {
-				rt6_remove_exception_rt(rt);
-				dst = NULL;
-			}
-			rcu_read_unlock();
-		} else {
-			dst_release(dst);
-			dst = NULL;
+	if (rt->rt6i_flags & RTF_CACHE) {
+		rcu_read_lock();
+		if (rt6_check_expired(rt)) {
+			/* counteract the dst_release() in sk_dst_reset() */
+			dst_hold(dst);
+			sk_dst_reset(sk);
+
+			rt6_remove_exception_rt(rt);
 		}
+		rcu_read_unlock();
+		return;
 	}
-	return dst;
+	sk_dst_reset(sk);
 }
 
 static void ip6_link_failure(struct sk_buff *skb)
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 475b904fe68b8..66e07de2de35c 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -3910,15 +3910,10 @@ static void xfrm_link_failure(struct sk_buff *skb)
 	/* Impossible. Such dst must be popped before reaches point of failure. */
 }
 
-static struct dst_entry *xfrm_negative_advice(struct dst_entry *dst)
+static void xfrm_negative_advice(struct sock *sk, struct dst_entry *dst)
 {
-	if (dst) {
-		if (dst->obsolete) {
-			dst_release(dst);
-			dst = NULL;
-		}
-	}
-	return dst;
+	if (dst->obsolete)
+		sk_dst_reset(sk);
 }
 
 static void xfrm_init_pmtu(struct xfrm_dst **bundle, int nr)
-- 
GitLab


From c697f515b6390b17e4a54a6f93aedf27133929c5 Mon Sep 17 00:00:00 2001
From: Donald Hunter <donald.hunter@gmail.com>
Date: Tue, 28 May 2024 15:06:49 +0100
Subject: [PATCH 525/950] doc: netlink: Fix generated .rst for multi-line docs

Fix the newline replacement in ynl-gen-rst.py to put spaces between
concatenated lines. This fixes the broken doc string formatting.

See the dpll docs for an example of broken concatenation:

https://docs.kernel.org/6.9/networking/netlink_spec/dpll.html#lock-status

Signed-off-by: Donald Hunter <donald.hunter@gmail.com>
Link: https://lore.kernel.org/r/20240528140652.9445-2-donald.hunter@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/net/ynl/ynl-gen-rst.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/net/ynl/ynl-gen-rst.py b/tools/net/ynl/ynl-gen-rst.py
index 657e881d2ea4a..5c7465d6befa0 100755
--- a/tools/net/ynl/ynl-gen-rst.py
+++ b/tools/net/ynl/ynl-gen-rst.py
@@ -49,7 +49,7 @@ def inline(text: str) -> str:
 def sanitize(text: str) -> str:
     """Remove newlines and multiple spaces"""
     # This is useful for some fields that are spread across multiple lines
-    return str(text).replace("\n", "").strip()
+    return str(text).replace("\n", " ").strip()
 
 
 def rst_fields(key: str, value: str, level: int = 0) -> str:
-- 
GitLab


From ebf9004136c76b7b62fe628a4bc88b3e894b4b95 Mon Sep 17 00:00:00 2001
From: Donald Hunter <donald.hunter@gmail.com>
Date: Tue, 28 May 2024 15:06:50 +0100
Subject: [PATCH 526/950] doc: netlink: Don't 'sanitize' op docstrings in
 generated .rst

The doc strings for do/dump ops are emitted as toplevel .rst constructs
so they can be multi-line. Pass multi-line text straight through to the
.rst to retain any simple formatting from the .yaml

This fixes e.g. list formatting for the pin-get docs in dpll.yaml:

https://docs.kernel.org/6.9/networking/netlink_spec/dpll.html#pin-get

Signed-off-by: Donald Hunter <donald.hunter@gmail.com>
Link: https://lore.kernel.org/r/20240528140652.9445-3-donald.hunter@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/dpll.yaml | 1 +
 tools/net/ynl/ynl-gen-rst.py          | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/Documentation/netlink/specs/dpll.yaml b/Documentation/netlink/specs/dpll.yaml
index 95b0eb1486bf7..94132d30e0e03 100644
--- a/Documentation/netlink/specs/dpll.yaml
+++ b/Documentation/netlink/specs/dpll.yaml
@@ -479,6 +479,7 @@ operations:
       name: pin-get
       doc: |
         Get list of pins and its attributes.
+
         - dump request without any attributes given - list all the pins in the
           system
         - dump request with target dpll - list all the pins registered with
diff --git a/tools/net/ynl/ynl-gen-rst.py b/tools/net/ynl/ynl-gen-rst.py
index 5c7465d6befa0..1096a71d7867a 100755
--- a/tools/net/ynl/ynl-gen-rst.py
+++ b/tools/net/ynl/ynl-gen-rst.py
@@ -178,7 +178,7 @@ def parse_operations(operations: List[Dict[str, Any]], namespace: str) -> str:
 
     for operation in operations:
         lines.append(rst_section(namespace, 'operation', operation["name"]))
-        lines.append(rst_paragraph(sanitize(operation["doc"])) + "\n")
+        lines.append(rst_paragraph(operation["doc"]) + "\n")
 
         for key in operation.keys():
             if key in preprocessed:
-- 
GitLab


From cb7351ac17862cf8d4e00831ce4aa27f53bda01c Mon Sep 17 00:00:00 2001
From: Donald Hunter <donald.hunter@gmail.com>
Date: Tue, 28 May 2024 15:06:51 +0100
Subject: [PATCH 527/950] doc: netlink: Fix formatting of op flags in generated
 .rst

Generate op flags as an inline list instead of a stringified python
value.

Signed-off-by: Donald Hunter <donald.hunter@gmail.com>
Link: https://lore.kernel.org/r/20240528140652.9445-4-donald.hunter@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/net/ynl/ynl-gen-rst.py | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/tools/net/ynl/ynl-gen-rst.py b/tools/net/ynl/ynl-gen-rst.py
index 1096a71d7867a..a957725b20dc5 100755
--- a/tools/net/ynl/ynl-gen-rst.py
+++ b/tools/net/ynl/ynl-gen-rst.py
@@ -172,7 +172,7 @@ def parse_do_attributes(attrs: Dict[str, Any], level: int = 0) -> str:
 
 def parse_operations(operations: List[Dict[str, Any]], namespace: str) -> str:
     """Parse operations block"""
-    preprocessed = ["name", "doc", "title", "do", "dump"]
+    preprocessed = ["name", "doc", "title", "do", "dump", "flags"]
     linkable = ["fixed-header", "attribute-set"]
     lines = []
 
@@ -188,6 +188,8 @@ def parse_operations(operations: List[Dict[str, Any]], namespace: str) -> str:
             if key in linkable:
                 value = rst_ref(namespace, key, value)
             lines.append(rst_fields(key, value, 0))
+        if 'flags' in operation:
+            lines.append(rst_fields('flags', rst_list_inline(operation['flags'])))
 
         if "do" in operation:
             lines.append(rst_paragraph(":do:", 0))
-- 
GitLab


From 9104feed4c6454b9a720e7e11047be7e5cd83487 Mon Sep 17 00:00:00 2001
From: Donald Hunter <donald.hunter@gmail.com>
Date: Tue, 28 May 2024 15:06:52 +0100
Subject: [PATCH 528/950] doc: netlink: Fix op pre and post fields in generated
 .rst

The generated .rst has pre and post headings without any values, e.g.
here:

https://docs.kernel.org/6.9/networking/netlink_spec/dpll.html#device-id-get

Emit keys and values in the generated .rst

Signed-off-by: Donald Hunter <donald.hunter@gmail.com>
Link: https://lore.kernel.org/r/20240528140652.9445-5-donald.hunter@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/net/ynl/ynl-gen-rst.py | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/tools/net/ynl/ynl-gen-rst.py b/tools/net/ynl/ynl-gen-rst.py
index a957725b20dc5..6c56d0d726b41 100755
--- a/tools/net/ynl/ynl-gen-rst.py
+++ b/tools/net/ynl/ynl-gen-rst.py
@@ -156,7 +156,10 @@ def parse_do(do_dict: Dict[str, Any], level: int = 0) -> str:
     lines = []
     for key in do_dict.keys():
         lines.append(rst_paragraph(bold(key), level + 1))
-        lines.append(parse_do_attributes(do_dict[key], level + 1) + "\n")
+        if key in ['request', 'reply']:
+            lines.append(parse_do_attributes(do_dict[key], level + 1) + "\n")
+        else:
+            lines.append(headroom(level + 2) + do_dict[key] + "\n")
 
     return "\n".join(lines)
 
-- 
GitLab


From bbb31b7ae14594aa2a7e74923ee38f312404ad66 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Tue, 28 May 2024 16:05:09 +0100
Subject: [PATCH 529/950] net: dsa: remove mac_prepare()/mac_finish() shims

No DSA driver makes use of the mac_prepare()/mac_finish() shimmed
operations anymore, so we can remove these.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Link: https://lore.kernel.org/r/E1sByNx-00ELW1-Vp@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/dsa.h |  6 ------
 net/dsa/dsa.c     |  2 --
 net/dsa/port.c    | 32 --------------------------------
 3 files changed, 40 deletions(-)

diff --git a/include/net/dsa.h b/include/net/dsa.h
index b60e7e410aba7..f9ae3ca66b6f1 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -882,15 +882,9 @@ struct dsa_switch_ops {
 	struct phylink_pcs *(*phylink_mac_select_pcs)(struct dsa_switch *ds,
 						      int port,
 						      phy_interface_t iface);
-	int	(*phylink_mac_prepare)(struct dsa_switch *ds, int port,
-				       unsigned int mode,
-				       phy_interface_t interface);
 	void	(*phylink_mac_config)(struct dsa_switch *ds, int port,
 				      unsigned int mode,
 				      const struct phylink_link_state *state);
-	int	(*phylink_mac_finish)(struct dsa_switch *ds, int port,
-				      unsigned int mode,
-				      phy_interface_t interface);
 	void	(*phylink_mac_link_down)(struct dsa_switch *ds, int port,
 					 unsigned int mode,
 					 phy_interface_t interface);
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index 12521a7d40481..668c729946ea6 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -1507,9 +1507,7 @@ static int dsa_switch_probe(struct dsa_switch *ds)
 
 	if (ds->phylink_mac_ops) {
 		if (ds->ops->phylink_mac_select_pcs ||
-		    ds->ops->phylink_mac_prepare ||
 		    ds->ops->phylink_mac_config ||
-		    ds->ops->phylink_mac_finish ||
 		    ds->ops->phylink_mac_link_down ||
 		    ds->ops->phylink_mac_link_up)
 			return -EINVAL;
diff --git a/net/dsa/port.c b/net/dsa/port.c
index 9a249d4ac3a5d..e23db9507546b 100644
--- a/net/dsa/port.c
+++ b/net/dsa/port.c
@@ -1549,21 +1549,6 @@ dsa_port_phylink_mac_select_pcs(struct phylink_config *config,
 	return pcs;
 }
 
-static int dsa_port_phylink_mac_prepare(struct phylink_config *config,
-					unsigned int mode,
-					phy_interface_t interface)
-{
-	struct dsa_port *dp = dsa_phylink_to_port(config);
-	struct dsa_switch *ds = dp->ds;
-	int err = 0;
-
-	if (ds->ops->phylink_mac_prepare)
-		err = ds->ops->phylink_mac_prepare(ds, dp->index, mode,
-						   interface);
-
-	return err;
-}
-
 static void dsa_port_phylink_mac_config(struct phylink_config *config,
 					unsigned int mode,
 					const struct phylink_link_state *state)
@@ -1577,21 +1562,6 @@ static void dsa_port_phylink_mac_config(struct phylink_config *config,
 	ds->ops->phylink_mac_config(ds, dp->index, mode, state);
 }
 
-static int dsa_port_phylink_mac_finish(struct phylink_config *config,
-				       unsigned int mode,
-				       phy_interface_t interface)
-{
-	struct dsa_port *dp = dsa_phylink_to_port(config);
-	struct dsa_switch *ds = dp->ds;
-	int err = 0;
-
-	if (ds->ops->phylink_mac_finish)
-		err = ds->ops->phylink_mac_finish(ds, dp->index, mode,
-						  interface);
-
-	return err;
-}
-
 static void dsa_port_phylink_mac_link_down(struct phylink_config *config,
 					   unsigned int mode,
 					   phy_interface_t interface)
@@ -1624,9 +1594,7 @@ static void dsa_port_phylink_mac_link_up(struct phylink_config *config,
 
 static const struct phylink_mac_ops dsa_port_phylink_mac_ops = {
 	.mac_select_pcs = dsa_port_phylink_mac_select_pcs,
-	.mac_prepare = dsa_port_phylink_mac_prepare,
 	.mac_config = dsa_port_phylink_mac_config,
-	.mac_finish = dsa_port_phylink_mac_finish,
 	.mac_link_down = dsa_port_phylink_mac_link_down,
 	.mac_link_up = dsa_port_phylink_mac_link_up,
 };
-- 
GitLab


From ef0e51dccdc43fd849720589c3214d97b2fd453f Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Tue, 28 May 2024 16:15:42 +0100
Subject: [PATCH 530/950] net: dsa: felix: provide own phylink MAC operations

Convert felix to provide its own phylink MAC operations, thus
avoiding the shim layer in DSA's port.c.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Tested-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://lore.kernel.org/r/E1sByYA-00EM0y-Jn@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/ocelot/felix.c           | 54 ++++++++++++++++--------
 drivers/net/dsa/ocelot/felix.h           |  1 +
 drivers/net/dsa/ocelot/felix_vsc9959.c   |  1 +
 drivers/net/dsa/ocelot/ocelot_ext.c      |  1 +
 drivers/net/dsa/ocelot/seville_vsc9953.c |  1 +
 5 files changed, 40 insertions(+), 18 deletions(-)

diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c
index 61e95487732dc..3aa66bf9eafc3 100644
--- a/drivers/net/dsa/ocelot/felix.c
+++ b/drivers/net/dsa/ocelot/felix.c
@@ -1050,24 +1050,32 @@ static void felix_phylink_get_caps(struct dsa_switch *ds, int port,
 		  config->supported_interfaces);
 }
 
-static void felix_phylink_mac_config(struct dsa_switch *ds, int port,
+static void felix_phylink_mac_config(struct phylink_config *config,
 				     unsigned int mode,
 				     const struct phylink_link_state *state)
 {
-	struct ocelot *ocelot = ds->priv;
-	struct felix *felix = ocelot_to_felix(ocelot);
+	struct dsa_port *dp = dsa_phylink_to_port(config);
+	struct ocelot *ocelot = dp->ds->priv;
+	int port = dp->index;
+	struct felix *felix;
+
+	felix = ocelot_to_felix(ocelot);
 
 	if (felix->info->phylink_mac_config)
 		felix->info->phylink_mac_config(ocelot, port, mode, state);
 }
 
-static struct phylink_pcs *felix_phylink_mac_select_pcs(struct dsa_switch *ds,
-							int port,
-							phy_interface_t iface)
+static struct phylink_pcs *
+felix_phylink_mac_select_pcs(struct phylink_config *config,
+			     phy_interface_t iface)
 {
-	struct ocelot *ocelot = ds->priv;
-	struct felix *felix = ocelot_to_felix(ocelot);
+	struct dsa_port *dp = dsa_phylink_to_port(config);
+	struct ocelot *ocelot = dp->ds->priv;
 	struct phylink_pcs *pcs = NULL;
+	int port = dp->index;
+	struct felix *felix;
+
+	felix = ocelot_to_felix(ocelot);
 
 	if (felix->pcs && felix->pcs[port])
 		pcs = felix->pcs[port];
@@ -1075,11 +1083,13 @@ static struct phylink_pcs *felix_phylink_mac_select_pcs(struct dsa_switch *ds,
 	return pcs;
 }
 
-static void felix_phylink_mac_link_down(struct dsa_switch *ds, int port,
+static void felix_phylink_mac_link_down(struct phylink_config *config,
 					unsigned int link_an_mode,
 					phy_interface_t interface)
 {
-	struct ocelot *ocelot = ds->priv;
+	struct dsa_port *dp = dsa_phylink_to_port(config);
+	struct ocelot *ocelot = dp->ds->priv;
+	int port = dp->index;
 	struct felix *felix;
 
 	felix = ocelot_to_felix(ocelot);
@@ -1088,15 +1098,19 @@ static void felix_phylink_mac_link_down(struct dsa_switch *ds, int port,
 				     felix->info->quirks);
 }
 
-static void felix_phylink_mac_link_up(struct dsa_switch *ds, int port,
+static void felix_phylink_mac_link_up(struct phylink_config *config,
+				      struct phy_device *phydev,
 				      unsigned int link_an_mode,
 				      phy_interface_t interface,
-				      struct phy_device *phydev,
 				      int speed, int duplex,
 				      bool tx_pause, bool rx_pause)
 {
-	struct ocelot *ocelot = ds->priv;
-	struct felix *felix = ocelot_to_felix(ocelot);
+	struct dsa_port *dp = dsa_phylink_to_port(config);
+	struct ocelot *ocelot = dp->ds->priv;
+	int port = dp->index;
+	struct felix *felix;
+
+	felix = ocelot_to_felix(ocelot);
 
 	ocelot_phylink_mac_link_up(ocelot, port, phydev, link_an_mode,
 				   interface, speed, duplex, tx_pause, rx_pause,
@@ -2083,6 +2097,14 @@ static void felix_get_mm_stats(struct dsa_switch *ds, int port,
 	ocelot_port_get_mm_stats(ocelot, port, stats);
 }
 
+const struct phylink_mac_ops felix_phylink_mac_ops = {
+	.mac_select_pcs		= felix_phylink_mac_select_pcs,
+	.mac_config		= felix_phylink_mac_config,
+	.mac_link_down		= felix_phylink_mac_link_down,
+	.mac_link_up		= felix_phylink_mac_link_up,
+};
+EXPORT_SYMBOL_GPL(felix_phylink_mac_ops);
+
 const struct dsa_switch_ops felix_switch_ops = {
 	.get_tag_protocol		= felix_get_tag_protocol,
 	.change_tag_protocol		= felix_change_tag_protocol,
@@ -2104,10 +2126,6 @@ const struct dsa_switch_ops felix_switch_ops = {
 	.get_sset_count			= felix_get_sset_count,
 	.get_ts_info			= felix_get_ts_info,
 	.phylink_get_caps		= felix_phylink_get_caps,
-	.phylink_mac_config		= felix_phylink_mac_config,
-	.phylink_mac_select_pcs		= felix_phylink_mac_select_pcs,
-	.phylink_mac_link_down		= felix_phylink_mac_link_down,
-	.phylink_mac_link_up		= felix_phylink_mac_link_up,
 	.port_enable			= felix_port_enable,
 	.port_fast_age			= felix_port_fast_age,
 	.port_fdb_dump			= felix_fdb_dump,
diff --git a/drivers/net/dsa/ocelot/felix.h b/drivers/net/dsa/ocelot/felix.h
index dbf5872fe3673..4d3489aaa6597 100644
--- a/drivers/net/dsa/ocelot/felix.h
+++ b/drivers/net/dsa/ocelot/felix.h
@@ -82,6 +82,7 @@ struct felix_tag_proto_ops {
 			      struct netlink_ext_ack *extack);
 };
 
+extern const struct phylink_mac_ops felix_phylink_mac_ops;
 extern const struct dsa_switch_ops felix_switch_ops;
 
 /* DSA glue / front-end for struct ocelot */
diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c
index 85952d841f285..d4799a908abcf 100644
--- a/drivers/net/dsa/ocelot/felix_vsc9959.c
+++ b/drivers/net/dsa/ocelot/felix_vsc9959.c
@@ -2717,6 +2717,7 @@ static int felix_pci_probe(struct pci_dev *pdev,
 	ds->num_ports = felix->info->num_ports;
 	ds->num_tx_queues = felix->info->num_tx_queues;
 	ds->ops = &felix_switch_ops;
+	ds->phylink_mac_ops = &felix_phylink_mac_ops;
 	ds->priv = ocelot;
 	felix->ds = ds;
 	felix->tag_proto = DSA_TAG_PROTO_OCELOT;
diff --git a/drivers/net/dsa/ocelot/ocelot_ext.c b/drivers/net/dsa/ocelot/ocelot_ext.c
index 22187d831c4b9..a8927dc7aca4f 100644
--- a/drivers/net/dsa/ocelot/ocelot_ext.c
+++ b/drivers/net/dsa/ocelot/ocelot_ext.c
@@ -96,6 +96,7 @@ static int ocelot_ext_probe(struct platform_device *pdev)
 	ds->num_tx_queues = felix->info->num_tx_queues;
 
 	ds->ops = &felix_switch_ops;
+	ds->phylink_mac_ops = &felix_phylink_mac_ops;
 	ds->priv = ocelot;
 	felix->ds = ds;
 	felix->tag_proto = DSA_TAG_PROTO_OCELOT;
diff --git a/drivers/net/dsa/ocelot/seville_vsc9953.c b/drivers/net/dsa/ocelot/seville_vsc9953.c
index 049930da05218..5ac8897e232b5 100644
--- a/drivers/net/dsa/ocelot/seville_vsc9953.c
+++ b/drivers/net/dsa/ocelot/seville_vsc9953.c
@@ -1009,6 +1009,7 @@ static int seville_probe(struct platform_device *pdev)
 	ds->dev = &pdev->dev;
 	ds->num_ports = felix->info->num_ports;
 	ds->ops = &felix_switch_ops;
+	ds->phylink_mac_ops = &felix_phylink_mac_ops;
 	ds->priv = ocelot;
 	felix->ds = ds;
 	felix->tag_proto = DSA_TAG_PROTO_SEVILLE;
-- 
GitLab


From c53a46b16ce2605181688ea6af5f6c8d7fb3c9c1 Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@toblux.com>
Date: Tue, 28 May 2024 18:00:37 +0200
Subject: [PATCH 531/950] net: smc91x: Remove commented out code

Remove commented out code

Signed-off-by: Thorsten Blum <thorsten.blum@toblux.com>
Link: https://lore.kernel.org/r/20240528160036.404946-2-thorsten.blum@toblux.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/smsc/smc91x.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/net/ethernet/smsc/smc91x.c b/drivers/net/ethernet/smsc/smc91x.c
index 78ff3af7911ad..907498848028b 100644
--- a/drivers/net/ethernet/smsc/smc91x.c
+++ b/drivers/net/ethernet/smsc/smc91x.c
@@ -1574,12 +1574,8 @@ smc_ethtool_set_link_ksettings(struct net_device *dev,
 		    (cmd->base.port != PORT_TP && cmd->base.port != PORT_AUI))
 			return -EINVAL;
 
-//		lp->port = cmd->base.port;
 		lp->ctl_rfduplx = cmd->base.duplex == DUPLEX_FULL;
 
-//		if (netif_running(dev))
-//			smc_set_port(dev);
-
 		ret = 0;
 	}
 
-- 
GitLab


From b8c8abefc07b47f0dc9342530b7618237df96724 Mon Sep 17 00:00:00 2001
From: Alexander Mikhalitsyn <aleksandr.mikhalitsyn@canonical.com>
Date: Tue, 28 May 2024 22:30:30 +0200
Subject: [PATCH 532/950] ipv4: correctly iterate over the target netns in
 inet_dump_ifaddr()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

A recent change to inet_dump_ifaddr had the function incorrectly iterate
over net rather than tgt_net, resulting in the data coming for the
incorrect network namespace.

Fixes: cdb2f80f1c10 ("inet: use xa_array iterator to implement inet_dump_ifaddr()")
Reported-by: Stéphane Graber <stgraber@stgraber.org>
Closes: https://github.com/lxc/incus/issues/892
Bisected-by: Stéphane Graber <stgraber@stgraber.org>
Signed-off-by: Alexander Mikhalitsyn <aleksandr.mikhalitsyn@canonical.com>
Tested-by: Stéphane Graber <stgraber@stgraber.org>
Acked-by: Christian Brauner <brauner@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20240528203030.10839-1-aleksandr.mikhalitsyn@canonical.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/devinet.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index e827da128c5f5..f3892ee9dfb33 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1903,7 +1903,7 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb)
 
 	cb->seq = inet_base_seq(tgt_net);
 
-	for_each_netdev_dump(net, dev, ctx->ifindex) {
+	for_each_netdev_dump(tgt_net, dev, ctx->ifindex) {
 		in_dev = __in_dev_get_rcu(dev);
 		if (!in_dev)
 			continue;
-- 
GitLab


From 278d65ccdadb5f0fa0ceaf7b9cc97b305cd72822 Mon Sep 17 00:00:00 2001
From: Tristram Ha <tristram.ha@microchip.com>
Date: Tue, 28 May 2024 14:34:26 -0700
Subject: [PATCH 533/950] net: dsa: microchip: fix RGMII error in KSZ DSA
 driver

The driver should return RMII interface when XMII is running in RMII mode.

Fixes: 0ab7f6bf1675 ("net: dsa: microchip: ksz9477: use common xmii function")
Signed-off-by: Tristram Ha <tristram.ha@microchip.com>
Acked-by: Arun Ramadoss <arun.ramadoss@microchip.com>
Acked-by: Jerry Ray <jerry.ray@microchip.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://lore.kernel.org/r/1716932066-3342-1-git-send-email-Tristram.Ha@microchip.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/microchip/ksz_common.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c
index 1e0085cd9a9ad..2818e24e2a51d 100644
--- a/drivers/net/dsa/microchip/ksz_common.c
+++ b/drivers/net/dsa/microchip/ksz_common.c
@@ -3142,7 +3142,7 @@ phy_interface_t ksz_get_xmii(struct ksz_device *dev, int port, bool gbit)
 		else
 			interface = PHY_INTERFACE_MODE_MII;
 	} else if (val == bitval[P_RMII_SEL]) {
-		interface = PHY_INTERFACE_MODE_RGMII;
+		interface = PHY_INTERFACE_MODE_RMII;
 	} else {
 		interface = PHY_INTERFACE_MODE_RGMII;
 		if (data8 & P_RGMII_ID_EG_ENABLE)
-- 
GitLab


From bfd546a552e140b0a4c8a21527c39d6d21addb28 Mon Sep 17 00:00:00 2001
From: Hui Wang <hui.wang@canonical.com>
Date: Tue, 28 May 2024 15:06:04 -0700
Subject: [PATCH 534/950] e1000e: move force SMBUS near the end of enable_ulp
 function

The commit 861e8086029e ("e1000e: move force SMBUS from enable ulp
function to avoid PHY loss issue") introduces a regression on
PCH_MTP_I219_LM18 (PCIID: 0x8086550A). Without the referred commit, the
ethernet works well after suspend and resume, but after applying the
commit, the ethernet couldn't work anymore after the resume and the
dmesg shows that the NIC link changes to 10Mbps (1000Mbps originally):

    [   43.305084] e1000e 0000:00:1f.6 enp0s31f6: NIC Link is Up 10 Mbps Full Duplex, Flow Control: Rx/Tx

Without the commit, the force SMBUS code will not be executed if
"return 0" or "goto out" is executed in the enable_ulp(), and in my
case, the "goto out" is executed since FWSM_FW_VALID is set. But after
applying the commit, the force SMBUS code will be ran unconditionally.

Here move the force SMBUS code back to enable_ulp() and put it
immediately ahead of hw->phy.ops.release(hw), this could allow the
longest settling time as possible for interface in this function and
doesn't change the original code logic.

The issue was found on a Lenovo laptop with the ethernet hw as below:
00:1f.6 Ethernet controller [0200]: Intel Corporation Device [8086:550a]
(rev 20).

And this patch is verified (cable plug and unplug, system suspend
and resume) on Lenovo laptops with ethernet hw: [8086:550a],
[8086:550b], [8086:15bb], [8086:15be], [8086:1a1f], [8086:1a1c] and
[8086:0dc7].

Fixes: 861e8086029e ("e1000e: move force SMBUS from enable ulp function to avoid PHY loss issue")
Signed-off-by: Hui Wang <hui.wang@canonical.com>
Acked-by: Vitaly Lifshits <vitaly.lifshits@intel.com>
Tested-by: Naama Meir <naamax.meir@linux.intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Tested-by: Zhang Rui <rui.zhang@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20240528-net-2024-05-28-intel-net-fixes-v1-1-dc8593d2bbc6@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/e1000e/ich8lan.c | 22 +++++++++++++++++++++
 drivers/net/ethernet/intel/e1000e/netdev.c  | 18 -----------------
 2 files changed, 22 insertions(+), 18 deletions(-)

diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c
index f9e94be36e97f..2e98a2a0bead9 100644
--- a/drivers/net/ethernet/intel/e1000e/ich8lan.c
+++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c
@@ -1225,6 +1225,28 @@ s32 e1000_enable_ulp_lpt_lp(struct e1000_hw *hw, bool to_sx)
 	}
 
 release:
+	/* Switching PHY interface always returns MDI error
+	 * so disable retry mechanism to avoid wasting time
+	 */
+	e1000e_disable_phy_retry(hw);
+
+	/* Force SMBus mode in PHY */
+	ret_val = e1000_read_phy_reg_hv_locked(hw, CV_SMB_CTRL, &phy_reg);
+	if (ret_val) {
+		e1000e_enable_phy_retry(hw);
+		hw->phy.ops.release(hw);
+		goto out;
+	}
+	phy_reg |= CV_SMB_CTRL_FORCE_SMBUS;
+	e1000_write_phy_reg_hv_locked(hw, CV_SMB_CTRL, phy_reg);
+
+	e1000e_enable_phy_retry(hw);
+
+	/* Force SMBus mode in MAC */
+	mac_reg = er32(CTRL_EXT);
+	mac_reg |= E1000_CTRL_EXT_FORCE_SMBUS;
+	ew32(CTRL_EXT, mac_reg);
+
 	hw->phy.ops.release(hw);
 out:
 	if (ret_val)
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 220d62fca55d1..da5c59daf8ba9 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -6623,7 +6623,6 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool runtime)
 	struct e1000_hw *hw = &adapter->hw;
 	u32 ctrl, ctrl_ext, rctl, status, wufc;
 	int retval = 0;
-	u16 smb_ctrl;
 
 	/* Runtime suspend should only enable wakeup for link changes */
 	if (runtime)
@@ -6697,23 +6696,6 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool runtime)
 			if (retval)
 				return retval;
 		}
-
-		/* Force SMBUS to allow WOL */
-		/* Switching PHY interface always returns MDI error
-		 * so disable retry mechanism to avoid wasting time
-		 */
-		e1000e_disable_phy_retry(hw);
-
-		e1e_rphy(hw, CV_SMB_CTRL, &smb_ctrl);
-		smb_ctrl |= CV_SMB_CTRL_FORCE_SMBUS;
-		e1e_wphy(hw, CV_SMB_CTRL, smb_ctrl);
-
-		e1000e_enable_phy_retry(hw);
-
-		/* Force SMBus mode in MAC */
-		ctrl_ext = er32(CTRL_EXT);
-		ctrl_ext |= E1000_CTRL_EXT_FORCE_SMBUS;
-		ew32(CTRL_EXT, ctrl_ext);
 	}
 
 	/* Ensure that the appropriate bits are set in LPI_CTRL
-- 
GitLab


From 218ed820d364ddc2b0150951e6b1a1bd1e49469d Mon Sep 17 00:00:00 2001
From: Thinh Tran <thinhtr@linux.ibm.com>
Date: Tue, 28 May 2024 15:06:05 -0700
Subject: [PATCH 535/950] i40e: factoring out i40e_suspend/i40e_resume

Two new functions, i40e_io_suspend() and i40e_io_resume(), have been
introduced.  These functions were factored out from the existing
i40e_suspend() and i40e_resume() respectively.  This factoring was
done due to concerns about the logic of the I40E_SUSPENSED state, which
caused the device to be unable to recover.  The functions are now used
in the EEH handling for device suspend/resume callbacks.

The function i40e_enable_mc_magic_wake() has been moved ahead of
i40e_io_suspend() to ensure it is declared before being used.

Tested-by: Robert Thomas <rob.thomas@ibm.com>
Signed-off-by: Thinh Tran <thinhtr@linux.ibm.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20240528-net-2024-05-28-intel-net-fixes-v1-2-dc8593d2bbc6@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/i40e/i40e_main.c | 249 +++++++++++---------
 1 file changed, 135 insertions(+), 114 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 1f188c052828b..d5f25ea304bf7 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -16334,6 +16334,139 @@ unmap:
 	pci_disable_device(pdev);
 }
 
+/**
+ * i40e_enable_mc_magic_wake - enable multicast magic packet wake up
+ * using the mac_address_write admin q function
+ * @pf: pointer to i40e_pf struct
+ **/
+static void i40e_enable_mc_magic_wake(struct i40e_pf *pf)
+{
+	struct i40e_vsi *main_vsi = i40e_pf_get_main_vsi(pf);
+	struct i40e_hw *hw = &pf->hw;
+	u8 mac_addr[6];
+	u16 flags = 0;
+	int ret;
+
+	/* Get current MAC address in case it's an LAA */
+	if (main_vsi && main_vsi->netdev) {
+		ether_addr_copy(mac_addr, main_vsi->netdev->dev_addr);
+	} else {
+		dev_err(&pf->pdev->dev,
+			"Failed to retrieve MAC address; using default\n");
+		ether_addr_copy(mac_addr, hw->mac.addr);
+	}
+
+	/* The FW expects the mac address write cmd to first be called with
+	 * one of these flags before calling it again with the multicast
+	 * enable flags.
+	 */
+	flags = I40E_AQC_WRITE_TYPE_LAA_WOL;
+
+	if (hw->func_caps.flex10_enable && hw->partition_id != 1)
+		flags = I40E_AQC_WRITE_TYPE_LAA_ONLY;
+
+	ret = i40e_aq_mac_address_write(hw, flags, mac_addr, NULL);
+	if (ret) {
+		dev_err(&pf->pdev->dev,
+			"Failed to update MAC address registers; cannot enable Multicast Magic packet wake up");
+		return;
+	}
+
+	flags = I40E_AQC_MC_MAG_EN
+			| I40E_AQC_WOL_PRESERVE_ON_PFR
+			| I40E_AQC_WRITE_TYPE_UPDATE_MC_MAG;
+	ret = i40e_aq_mac_address_write(hw, flags, mac_addr, NULL);
+	if (ret)
+		dev_err(&pf->pdev->dev,
+			"Failed to enable Multicast Magic Packet wake up\n");
+}
+
+/**
+ * i40e_io_suspend - suspend all IO operations
+ * @pf: pointer to i40e_pf struct
+ *
+ **/
+static int i40e_io_suspend(struct i40e_pf *pf)
+{
+	struct i40e_hw *hw = &pf->hw;
+
+	set_bit(__I40E_DOWN, pf->state);
+
+	/* Ensure service task will not be running */
+	del_timer_sync(&pf->service_timer);
+	cancel_work_sync(&pf->service_task);
+
+	/* Client close must be called explicitly here because the timer
+	 * has been stopped.
+	 */
+	i40e_notify_client_of_netdev_close(pf, false);
+
+	if (test_bit(I40E_HW_CAP_WOL_MC_MAGIC_PKT_WAKE, pf->hw.caps) &&
+	    pf->wol_en)
+		i40e_enable_mc_magic_wake(pf);
+
+	/* Since we're going to destroy queues during the
+	 * i40e_clear_interrupt_scheme() we should hold the RTNL lock for this
+	 * whole section
+	 */
+	rtnl_lock();
+
+	i40e_prep_for_reset(pf);
+
+	wr32(hw, I40E_PFPM_APM, (pf->wol_en ? I40E_PFPM_APM_APME_MASK : 0));
+	wr32(hw, I40E_PFPM_WUFC, (pf->wol_en ? I40E_PFPM_WUFC_MAG_MASK : 0));
+
+	/* Clear the interrupt scheme and release our IRQs so that the system
+	 * can safely hibernate even when there are a large number of CPUs.
+	 * Otherwise hibernation might fail when mapping all the vectors back
+	 * to CPU0.
+	 */
+	i40e_clear_interrupt_scheme(pf);
+
+	rtnl_unlock();
+
+	return 0;
+}
+
+/**
+ * i40e_io_resume - resume IO operations
+ * @pf: pointer to i40e_pf struct
+ *
+ **/
+static int i40e_io_resume(struct i40e_pf *pf)
+{
+	struct device *dev = &pf->pdev->dev;
+	int err;
+
+	/* We need to hold the RTNL lock prior to restoring interrupt schemes,
+	 * since we're going to be restoring queues
+	 */
+	rtnl_lock();
+
+	/* We cleared the interrupt scheme when we suspended, so we need to
+	 * restore it now to resume device functionality.
+	 */
+	err = i40e_restore_interrupt_scheme(pf);
+	if (err) {
+		dev_err(dev, "Cannot restore interrupt scheme: %d\n",
+			err);
+	}
+
+	clear_bit(__I40E_DOWN, pf->state);
+	i40e_reset_and_rebuild(pf, false, true);
+
+	rtnl_unlock();
+
+	/* Clear suspended state last after everything is recovered */
+	clear_bit(__I40E_SUSPENDED, pf->state);
+
+	/* Restart the service task */
+	mod_timer(&pf->service_timer,
+		  round_jiffies(jiffies + pf->service_timer_period));
+
+	return 0;
+}
+
 /**
  * i40e_pci_error_detected - warning that something funky happened in PCI land
  * @pdev: PCI device information struct
@@ -16446,53 +16579,6 @@ static void i40e_pci_error_resume(struct pci_dev *pdev)
 	i40e_handle_reset_warning(pf, false);
 }
 
-/**
- * i40e_enable_mc_magic_wake - enable multicast magic packet wake up
- * using the mac_address_write admin q function
- * @pf: pointer to i40e_pf struct
- **/
-static void i40e_enable_mc_magic_wake(struct i40e_pf *pf)
-{
-	struct i40e_vsi *main_vsi = i40e_pf_get_main_vsi(pf);
-	struct i40e_hw *hw = &pf->hw;
-	u8 mac_addr[6];
-	u16 flags = 0;
-	int ret;
-
-	/* Get current MAC address in case it's an LAA */
-	if (main_vsi && main_vsi->netdev) {
-		ether_addr_copy(mac_addr, main_vsi->netdev->dev_addr);
-	} else {
-		dev_err(&pf->pdev->dev,
-			"Failed to retrieve MAC address; using default\n");
-		ether_addr_copy(mac_addr, hw->mac.addr);
-	}
-
-	/* The FW expects the mac address write cmd to first be called with
-	 * one of these flags before calling it again with the multicast
-	 * enable flags.
-	 */
-	flags = I40E_AQC_WRITE_TYPE_LAA_WOL;
-
-	if (hw->func_caps.flex10_enable && hw->partition_id != 1)
-		flags = I40E_AQC_WRITE_TYPE_LAA_ONLY;
-
-	ret = i40e_aq_mac_address_write(hw, flags, mac_addr, NULL);
-	if (ret) {
-		dev_err(&pf->pdev->dev,
-			"Failed to update MAC address registers; cannot enable Multicast Magic packet wake up");
-		return;
-	}
-
-	flags = I40E_AQC_MC_MAG_EN
-			| I40E_AQC_WOL_PRESERVE_ON_PFR
-			| I40E_AQC_WRITE_TYPE_UPDATE_MC_MAG;
-	ret = i40e_aq_mac_address_write(hw, flags, mac_addr, NULL);
-	if (ret)
-		dev_err(&pf->pdev->dev,
-			"Failed to enable Multicast Magic Packet wake up\n");
-}
-
 /**
  * i40e_shutdown - PCI callback for shutting down
  * @pdev: PCI device information struct
@@ -16552,48 +16638,11 @@ static void i40e_shutdown(struct pci_dev *pdev)
 static int i40e_suspend(struct device *dev)
 {
 	struct i40e_pf *pf = dev_get_drvdata(dev);
-	struct i40e_hw *hw = &pf->hw;
 
 	/* If we're already suspended, then there is nothing to do */
 	if (test_and_set_bit(__I40E_SUSPENDED, pf->state))
 		return 0;
-
-	set_bit(__I40E_DOWN, pf->state);
-
-	/* Ensure service task will not be running */
-	del_timer_sync(&pf->service_timer);
-	cancel_work_sync(&pf->service_task);
-
-	/* Client close must be called explicitly here because the timer
-	 * has been stopped.
-	 */
-	i40e_notify_client_of_netdev_close(pf, false);
-
-	if (test_bit(I40E_HW_CAP_WOL_MC_MAGIC_PKT_WAKE, pf->hw.caps) &&
-	    pf->wol_en)
-		i40e_enable_mc_magic_wake(pf);
-
-	/* Since we're going to destroy queues during the
-	 * i40e_clear_interrupt_scheme() we should hold the RTNL lock for this
-	 * whole section
-	 */
-	rtnl_lock();
-
-	i40e_prep_for_reset(pf);
-
-	wr32(hw, I40E_PFPM_APM, (pf->wol_en ? I40E_PFPM_APM_APME_MASK : 0));
-	wr32(hw, I40E_PFPM_WUFC, (pf->wol_en ? I40E_PFPM_WUFC_MAG_MASK : 0));
-
-	/* Clear the interrupt scheme and release our IRQs so that the system
-	 * can safely hibernate even when there are a large number of CPUs.
-	 * Otherwise hibernation might fail when mapping all the vectors back
-	 * to CPU0.
-	 */
-	i40e_clear_interrupt_scheme(pf);
-
-	rtnl_unlock();
-
-	return 0;
+	return i40e_io_suspend(pf);
 }
 
 /**
@@ -16603,39 +16652,11 @@ static int i40e_suspend(struct device *dev)
 static int i40e_resume(struct device *dev)
 {
 	struct i40e_pf *pf = dev_get_drvdata(dev);
-	int err;
 
 	/* If we're not suspended, then there is nothing to do */
 	if (!test_bit(__I40E_SUSPENDED, pf->state))
 		return 0;
-
-	/* We need to hold the RTNL lock prior to restoring interrupt schemes,
-	 * since we're going to be restoring queues
-	 */
-	rtnl_lock();
-
-	/* We cleared the interrupt scheme when we suspended, so we need to
-	 * restore it now to resume device functionality.
-	 */
-	err = i40e_restore_interrupt_scheme(pf);
-	if (err) {
-		dev_err(dev, "Cannot restore interrupt scheme: %d\n",
-			err);
-	}
-
-	clear_bit(__I40E_DOWN, pf->state);
-	i40e_reset_and_rebuild(pf, false, true);
-
-	rtnl_unlock();
-
-	/* Clear suspended state last after everything is recovered */
-	clear_bit(__I40E_SUSPENDED, pf->state);
-
-	/* Restart the service task */
-	mod_timer(&pf->service_timer,
-		  round_jiffies(jiffies + pf->service_timer_period));
-
-	return 0;
+	return i40e_io_resume(pf);
 }
 
 static const struct pci_error_handlers i40e_err_handler = {
-- 
GitLab


From c80b6538d35a7a60d874c5a76c3c5a82b6a28fbb Mon Sep 17 00:00:00 2001
From: Thinh Tran <thinhtr@linux.ibm.com>
Date: Tue, 28 May 2024 15:06:06 -0700
Subject: [PATCH 536/950] i40e: Fully suspend and resume IO operations in EEH
 case

When EEH events occurs, the callback functions in the i40e, which are
managed by the EEH driver, will completely suspend and resume all IO
operations.

- In the PCI error detected callback, replaced i40e_prep_for_reset()
  with i40e_io_suspend(). The change is to fully suspend all I/O
  operations
- In the PCI error slot reset callback, replaced pci_enable_device_mem()
  with pci_enable_device(). This change enables both I/O and memory of
  the device.
- In the PCI error resume callback, replaced i40e_handle_reset_warning()
  with i40e_io_resume(). This change allows the system to resume I/O
  operations

Fixes: a5f3d2c17b07 ("powerpc/pseries/pci: Add MSI domains")
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Robert Thomas <rob.thomas@ibm.com>
Signed-off-by: Thinh Tran <thinhtr@linux.ibm.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20240528-net-2024-05-28-intel-net-fixes-v1-3-dc8593d2bbc6@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/i40e/i40e_main.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index d5f25ea304bf7..284c3fad5a6e4 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -11171,6 +11171,8 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit,
 	ret = i40e_reset(pf);
 	if (!ret)
 		i40e_rebuild(pf, reinit, lock_acquired);
+	else
+		dev_err(&pf->pdev->dev, "%s: i40e_reset() FAILED", __func__);
 }
 
 /**
@@ -16491,7 +16493,7 @@ static pci_ers_result_t i40e_pci_error_detected(struct pci_dev *pdev,
 
 	/* shutdown all operations */
 	if (!test_bit(__I40E_SUSPENDED, pf->state))
-		i40e_prep_for_reset(pf);
+		i40e_io_suspend(pf);
 
 	/* Request a slot reset */
 	return PCI_ERS_RESULT_NEED_RESET;
@@ -16513,7 +16515,8 @@ static pci_ers_result_t i40e_pci_error_slot_reset(struct pci_dev *pdev)
 	u32 reg;
 
 	dev_dbg(&pdev->dev, "%s\n", __func__);
-	if (pci_enable_device_mem(pdev)) {
+	/* enable I/O and memory of the device  */
+	if (pci_enable_device(pdev)) {
 		dev_info(&pdev->dev,
 			 "Cannot re-enable PCI device after reset.\n");
 		result = PCI_ERS_RESULT_DISCONNECT;
@@ -16576,7 +16579,7 @@ static void i40e_pci_error_resume(struct pci_dev *pdev)
 	if (test_bit(__I40E_SUSPENDED, pf->state))
 		return;
 
-	i40e_handle_reset_warning(pf, false);
+	i40e_io_resume(pf);
 }
 
 /**
-- 
GitLab


From 2a6d8f2de2224ac46df94dc40f43f8b9701f6703 Mon Sep 17 00:00:00 2001
From: Paul Greenwalt <paul.greenwalt@intel.com>
Date: Tue, 28 May 2024 15:06:08 -0700
Subject: [PATCH 537/950] ice: fix 200G PHY types to link speed mapping

Commit 24407a01e57c ("ice: Add 200G speed/phy type use") added support
for 200G PHY speeds, but did not include the mapping of 200G PHY types
to link speed. As a result the driver is returning UNKNOWN link speed
when setting 200G ethtool advertised link modes.

To fix this add 200G PHY types to link speed mapping to
ice_get_link_speed_based_on_phy_type().

Fixes: 24407a01e57c ("ice: Add 200G speed/phy type use")
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Signed-off-by: Paul Greenwalt <paul.greenwalt@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20240528-net-2024-05-28-intel-net-fixes-v1-5-dc8593d2bbc6@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/ice/ice_common.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index 5649b257e6312..24716a3b494cd 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -3148,6 +3148,16 @@ ice_get_link_speed_based_on_phy_type(u64 phy_type_low, u64 phy_type_high)
 	case ICE_PHY_TYPE_HIGH_100G_AUI2:
 		speed_phy_type_high = ICE_AQ_LINK_SPEED_100GB;
 		break;
+	case ICE_PHY_TYPE_HIGH_200G_CR4_PAM4:
+	case ICE_PHY_TYPE_HIGH_200G_SR4:
+	case ICE_PHY_TYPE_HIGH_200G_FR4:
+	case ICE_PHY_TYPE_HIGH_200G_LR4:
+	case ICE_PHY_TYPE_HIGH_200G_DR4:
+	case ICE_PHY_TYPE_HIGH_200G_KR4_PAM4:
+	case ICE_PHY_TYPE_HIGH_200G_AUI4_AOC_ACC:
+	case ICE_PHY_TYPE_HIGH_200G_AUI4:
+		speed_phy_type_high = ICE_AQ_LINK_SPEED_200GB;
+		break;
 	default:
 		speed_phy_type_high = ICE_AQ_LINK_SPEED_UNKNOWN;
 		break;
-- 
GitLab


From a51c9b1c9ab2351e62933357fcad5bfad27f2400 Mon Sep 17 00:00:00 2001
From: Dave Ertman <david.m.ertman@intel.com>
Date: Tue, 28 May 2024 15:06:11 -0700
Subject: [PATCH 538/950] ice: check for unregistering correct number of
 devlink params

On module load, the ice driver checks for the lack of a specific PF
capability to determine if it should reduce the number of devlink params
to register.  One situation when this test returns true is when the
driver loads in safe mode.  The same check is not present on the unload
path when devlink params are unregistered.  This results in the driver
triggering a WARN_ON in the kernel devlink code.

The current check and code path uses a reduction in the number of elements
reported in the list of params.  This is fragile and not good for future
maintaining.

Change the parameters to be held in two lists, one always registered and
one dependent on the check.

Add a symmetrical check in the unload path so that the correct parameters
are unregistered as well.

Fixes: 109eb2917284 ("ice: Add tx_scheduling_layers devlink param")
CC: Lukasz Czapnik <lukasz.czapnik@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Dave Ertman <david.m.ertman@intel.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20240528-net-2024-05-28-intel-net-fixes-v1-8-dc8593d2bbc6@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/intel/ice/devlink/devlink.c  | 31 +++++++++++++------
 1 file changed, 22 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink.c b/drivers/net/ethernet/intel/ice/devlink/devlink.c
index c4b69655cdf57..704e9ad5144e8 100644
--- a/drivers/net/ethernet/intel/ice/devlink/devlink.c
+++ b/drivers/net/ethernet/intel/ice/devlink/devlink.c
@@ -1388,7 +1388,7 @@ enum ice_param_id {
 	ICE_DEVLINK_PARAM_ID_TX_SCHED_LAYERS,
 };
 
-static const struct devlink_param ice_devlink_params[] = {
+static const struct devlink_param ice_dvl_rdma_params[] = {
 	DEVLINK_PARAM_GENERIC(ENABLE_ROCE, BIT(DEVLINK_PARAM_CMODE_RUNTIME),
 			      ice_devlink_enable_roce_get,
 			      ice_devlink_enable_roce_set,
@@ -1397,6 +1397,9 @@ static const struct devlink_param ice_devlink_params[] = {
 			      ice_devlink_enable_iw_get,
 			      ice_devlink_enable_iw_set,
 			      ice_devlink_enable_iw_validate),
+};
+
+static const struct devlink_param ice_dvl_sched_params[] = {
 	DEVLINK_PARAM_DRIVER(ICE_DEVLINK_PARAM_ID_TX_SCHED_LAYERS,
 			     "tx_scheduling_layers",
 			     DEVLINK_PARAM_TYPE_U8,
@@ -1464,21 +1467,31 @@ int ice_devlink_register_params(struct ice_pf *pf)
 {
 	struct devlink *devlink = priv_to_devlink(pf);
 	struct ice_hw *hw = &pf->hw;
-	size_t params_size;
+	int status;
 
-	params_size =  ARRAY_SIZE(ice_devlink_params);
+	status = devl_params_register(devlink, ice_dvl_rdma_params,
+				      ARRAY_SIZE(ice_dvl_rdma_params));
+	if (status)
+		return status;
 
-	if (!hw->func_caps.common_cap.tx_sched_topo_comp_mode_en)
-		params_size--;
+	if (hw->func_caps.common_cap.tx_sched_topo_comp_mode_en)
+		status = devl_params_register(devlink, ice_dvl_sched_params,
+					      ARRAY_SIZE(ice_dvl_sched_params));
 
-	return devl_params_register(devlink, ice_devlink_params,
-				    params_size);
+	return status;
 }
 
 void ice_devlink_unregister_params(struct ice_pf *pf)
 {
-	devl_params_unregister(priv_to_devlink(pf), ice_devlink_params,
-			       ARRAY_SIZE(ice_devlink_params));
+	struct devlink *devlink = priv_to_devlink(pf);
+	struct ice_hw *hw = &pf->hw;
+
+	devl_params_unregister(devlink, ice_dvl_rdma_params,
+			       ARRAY_SIZE(ice_dvl_rdma_params));
+
+	if (hw->func_caps.common_cap.tx_sched_topo_comp_mode_en)
+		devl_params_unregister(devlink, ice_dvl_sched_params,
+				       ARRAY_SIZE(ice_dvl_sched_params));
 }
 
 #define ICE_DEVLINK_READ_BLK_SIZE (1024 * 1024)
-- 
GitLab


From 2dc8b1e7177d4f49f492ce648440caf2de0c3616 Mon Sep 17 00:00:00 2001
From: Shay Agroskin <shayagr@amazon.com>
Date: Tue, 28 May 2024 20:09:12 +0300
Subject: [PATCH 539/950] net: ena: Fix redundant device NUMA node override

The driver overrides the NUMA node id of the device regardless of
whether it knows its correct value (often setting it to -1 even though
the node id is advertised in 'struct device'). This can lead to
suboptimal configurations.

This patch fixes this behavior and makes the shared memory allocation
functions use the NUMA node id advertised by the underlying device.

Fixes: 1738cd3ed342 ("net: ena: Add a driver for Amazon Elastic Network Adapters (ENA)")
Signed-off-by: Shay Agroskin <shayagr@amazon.com>
Link: https://lore.kernel.org/r/20240528170912.1204417-1-shayagr@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/amazon/ena/ena_com.c | 11 -----------
 1 file changed, 11 deletions(-)

diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c
index 2d8a66ea82fab..713a595370bff 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.c
+++ b/drivers/net/ethernet/amazon/ena/ena_com.c
@@ -312,7 +312,6 @@ static int ena_com_init_io_sq(struct ena_com_dev *ena_dev,
 			      struct ena_com_io_sq *io_sq)
 {
 	size_t size;
-	int dev_node = 0;
 
 	memset(&io_sq->desc_addr, 0x0, sizeof(io_sq->desc_addr));
 
@@ -325,12 +324,9 @@ static int ena_com_init_io_sq(struct ena_com_dev *ena_dev,
 	size = io_sq->desc_entry_size * io_sq->q_depth;
 
 	if (io_sq->mem_queue_type == ENA_ADMIN_PLACEMENT_POLICY_HOST) {
-		dev_node = dev_to_node(ena_dev->dmadev);
-		set_dev_node(ena_dev->dmadev, ctx->numa_node);
 		io_sq->desc_addr.virt_addr =
 			dma_alloc_coherent(ena_dev->dmadev, size, &io_sq->desc_addr.phys_addr,
 					   GFP_KERNEL);
-		set_dev_node(ena_dev->dmadev, dev_node);
 		if (!io_sq->desc_addr.virt_addr) {
 			io_sq->desc_addr.virt_addr =
 				dma_alloc_coherent(ena_dev->dmadev, size,
@@ -354,10 +350,7 @@ static int ena_com_init_io_sq(struct ena_com_dev *ena_dev,
 		size = (size_t)io_sq->bounce_buf_ctrl.buffer_size *
 			io_sq->bounce_buf_ctrl.buffers_num;
 
-		dev_node = dev_to_node(ena_dev->dmadev);
-		set_dev_node(ena_dev->dmadev, ctx->numa_node);
 		io_sq->bounce_buf_ctrl.base_buffer = devm_kzalloc(ena_dev->dmadev, size, GFP_KERNEL);
-		set_dev_node(ena_dev->dmadev, dev_node);
 		if (!io_sq->bounce_buf_ctrl.base_buffer)
 			io_sq->bounce_buf_ctrl.base_buffer =
 				devm_kzalloc(ena_dev->dmadev, size, GFP_KERNEL);
@@ -397,7 +390,6 @@ static int ena_com_init_io_cq(struct ena_com_dev *ena_dev,
 			      struct ena_com_io_cq *io_cq)
 {
 	size_t size;
-	int prev_node = 0;
 
 	memset(&io_cq->cdesc_addr, 0x0, sizeof(io_cq->cdesc_addr));
 
@@ -409,11 +401,8 @@ static int ena_com_init_io_cq(struct ena_com_dev *ena_dev,
 
 	size = io_cq->cdesc_entry_size_in_bytes * io_cq->q_depth;
 
-	prev_node = dev_to_node(ena_dev->dmadev);
-	set_dev_node(ena_dev->dmadev, ctx->numa_node);
 	io_cq->cdesc_addr.virt_addr =
 		dma_alloc_coherent(ena_dev->dmadev, size, &io_cq->cdesc_addr.phys_addr, GFP_KERNEL);
-	set_dev_node(ena_dev->dmadev, prev_node);
 	if (!io_cq->cdesc_addr.virt_addr) {
 		io_cq->cdesc_addr.virt_addr =
 			dma_alloc_coherent(ena_dev->dmadev, size, &io_cq->cdesc_addr.phys_addr,
-- 
GitLab


From b21faf0edefc26df604fb783c53992e61503df33 Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Thu, 23 May 2024 17:43:37 +0300
Subject: [PATCH 540/950] wifi: rtlwifi: rtl8192d: Use "rtl92d" prefix

Some functions moved from rtl8192de still use the "rtl92de" prefix.
Rename them.

Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://msgid.link/abe3624d-f986-4a24-966c-67defa962e3f@gmail.com
---
 .../realtek/rtlwifi/rtl8192d/hw_common.c      | 94 +++++++++----------
 .../realtek/rtlwifi/rtl8192d/hw_common.h      | 28 +++---
 .../realtek/rtlwifi/rtl8192d/trx_common.c     | 92 +++++++++---------
 .../realtek/rtlwifi/rtl8192d/trx_common.h     | 16 ++--
 .../wireless/realtek/rtlwifi/rtl8192de/hw.c   | 18 ++--
 .../wireless/realtek/rtlwifi/rtl8192de/sw.c   | 20 ++--
 .../wireless/realtek/rtlwifi/rtl8192de/trx.c  |  2 +-
 7 files changed, 135 insertions(+), 135 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192d/hw_common.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192d/hw_common.c
index 6570d5e168e91..97e0d9c01e0ac 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192d/hw_common.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192d/hw_common.c
@@ -14,7 +14,7 @@
 #include "hw_common.h"
 #include "phy_common.h"
 
-void rtl92de_stop_tx_beacon(struct ieee80211_hw *hw)
+void rtl92d_stop_tx_beacon(struct ieee80211_hw *hw)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	u8 tmp1byte;
@@ -27,9 +27,9 @@ void rtl92de_stop_tx_beacon(struct ieee80211_hw *hw)
 	tmp1byte &= ~(BIT(0));
 	rtl_write_byte(rtlpriv, REG_TBTT_PROHIBIT + 2, tmp1byte);
 }
-EXPORT_SYMBOL_GPL(rtl92de_stop_tx_beacon);
+EXPORT_SYMBOL_GPL(rtl92d_stop_tx_beacon);
 
-void rtl92de_resume_tx_beacon(struct ieee80211_hw *hw)
+void rtl92d_resume_tx_beacon(struct ieee80211_hw *hw)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	u8 tmp1byte;
@@ -42,7 +42,7 @@ void rtl92de_resume_tx_beacon(struct ieee80211_hw *hw)
 	tmp1byte |= BIT(0);
 	rtl_write_byte(rtlpriv, REG_TBTT_PROHIBIT + 2, tmp1byte);
 }
-EXPORT_SYMBOL_GPL(rtl92de_resume_tx_beacon);
+EXPORT_SYMBOL_GPL(rtl92d_resume_tx_beacon);
 
 void rtl92d_get_hw_reg(struct ieee80211_hw *hw, u8 variable, u8 *val)
 {
@@ -285,7 +285,7 @@ void rtl92d_set_hw_reg(struct ieee80211_hw *hw, u8 variable, u8 *val)
 }
 EXPORT_SYMBOL_GPL(rtl92d_set_hw_reg);
 
-bool rtl92de_llt_write(struct ieee80211_hw *hw, u32 address, u32 data)
+bool rtl92d_llt_write(struct ieee80211_hw *hw, u32 address, u32 data)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	bool status = true;
@@ -307,9 +307,9 @@ bool rtl92de_llt_write(struct ieee80211_hw *hw, u32 address, u32 data)
 	} while (++count);
 	return status;
 }
-EXPORT_SYMBOL_GPL(rtl92de_llt_write);
+EXPORT_SYMBOL_GPL(rtl92d_llt_write);
 
-void rtl92de_enable_hw_security_config(struct ieee80211_hw *hw)
+void rtl92d_enable_hw_security_config(struct ieee80211_hw *hw)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	u8 sec_reg_value;
@@ -334,16 +334,16 @@ void rtl92de_enable_hw_security_config(struct ieee80211_hw *hw)
 		"The SECR-value %x\n", sec_reg_value);
 	rtlpriv->cfg->ops->set_hw_reg(hw, HW_VAR_WPA_CONFIG, &sec_reg_value);
 }
-EXPORT_SYMBOL_GPL(rtl92de_enable_hw_security_config);
+EXPORT_SYMBOL_GPL(rtl92d_enable_hw_security_config);
 
 /* don't set REG_EDCA_BE_PARAM here because
  * mac80211 will send pkt when scan
  */
-void rtl92de_set_qos(struct ieee80211_hw *hw, int aci)
+void rtl92d_set_qos(struct ieee80211_hw *hw, int aci)
 {
 	rtl92d_dm_init_edca_turbo(hw);
 }
-EXPORT_SYMBOL_GPL(rtl92de_set_qos);
+EXPORT_SYMBOL_GPL(rtl92d_set_qos);
 
 static enum version_8192d _rtl92d_read_chip_version(struct ieee80211_hw *hw)
 {
@@ -362,8 +362,8 @@ static enum version_8192d _rtl92d_read_chip_version(struct ieee80211_hw *hw)
 	return version;
 }
 
-static void _rtl92de_readpowervalue_fromprom(struct txpower_info *pwrinfo,
-					     u8 *efuse, bool autoloadfail)
+static void _rtl92d_readpowervalue_fromprom(struct txpower_info *pwrinfo,
+					    u8 *efuse, bool autoloadfail)
 {
 	u32 rfpath, eeaddr, group, offset, offset1, offset2;
 	u8 i, val8;
@@ -500,8 +500,8 @@ static void _rtl92de_readpowervalue_fromprom(struct txpower_info *pwrinfo,
 	}
 }
 
-static void _rtl92de_read_txpower_info(struct ieee80211_hw *hw,
-				       bool autoload_fail, u8 *hwinfo)
+static void _rtl92d_read_txpower_info(struct ieee80211_hw *hw,
+				      bool autoload_fail, u8 *hwinfo)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_efuse *rtlefuse = rtl_efuse(rtl_priv(hw));
@@ -509,7 +509,7 @@ static void _rtl92de_read_txpower_info(struct ieee80211_hw *hw,
 	u8 tempval[2], i, pwr, diff;
 	u32 ch, rfpath, group;
 
-	_rtl92de_readpowervalue_fromprom(&pwrinfo, hwinfo, autoload_fail);
+	_rtl92d_readpowervalue_fromprom(&pwrinfo, hwinfo, autoload_fail);
 	if (!autoload_fail) {
 		/* bit0~2 */
 		rtlefuse->eeprom_regulatory = (hwinfo[EEPROM_RF_OPT1] & 0x7);
@@ -613,8 +613,8 @@ static void _rtl92de_read_txpower_info(struct ieee80211_hw *hw,
 	}
 }
 
-static void _rtl92de_read_macphymode_from_prom(struct ieee80211_hw *hw,
-					       u8 *content)
+static void _rtl92d_read_macphymode_from_prom(struct ieee80211_hw *hw,
+					      u8 *content)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_hal *rtlhal = rtl_hal(rtl_priv(hw));
@@ -636,15 +636,15 @@ static void _rtl92de_read_macphymode_from_prom(struct ieee80211_hw *hw,
 	}
 }
 
-static void _rtl92de_read_macphymode_and_bandtype(struct ieee80211_hw *hw,
-						  u8 *content)
+static void _rtl92d_read_macphymode_and_bandtype(struct ieee80211_hw *hw,
+						 u8 *content)
 {
-	_rtl92de_read_macphymode_from_prom(hw, content);
+	_rtl92d_read_macphymode_from_prom(hw, content);
 	rtl92d_phy_config_macphymode(hw);
 	rtl92d_phy_config_macphymode_info(hw);
 }
 
-static void _rtl92de_efuse_update_chip_version(struct ieee80211_hw *hw)
+static void _rtl92d_efuse_update_chip_version(struct ieee80211_hw *hw)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	enum version_8192d chipver = rtlpriv->rtlhal.version;
@@ -676,7 +676,7 @@ static void _rtl92de_efuse_update_chip_version(struct ieee80211_hw *hw)
 	rtlpriv->rtlhal.version = chipver;
 }
 
-static void _rtl92de_read_adapter_info(struct ieee80211_hw *hw)
+static void _rtl92d_read_adapter_info(struct ieee80211_hw *hw)
 {
 	static const int params_pci[] = {
 		RTL8190_EEPROM_ID, EEPROM_VID, EEPROM_DID,
@@ -706,8 +706,8 @@ static void _rtl92de_read_adapter_info(struct ieee80211_hw *hw)
 	if (rtl_get_hwinfo(hw, rtlpriv, HWSET_MAX_SIZE, hwinfo, params))
 		goto exit;
 
-	_rtl92de_efuse_update_chip_version(hw);
-	_rtl92de_read_macphymode_and_bandtype(hw, hwinfo);
+	_rtl92d_efuse_update_chip_version(hw);
+	_rtl92d_read_macphymode_and_bandtype(hw, hwinfo);
 
 	/* Read Permanent MAC address for 2nd interface */
 	if (rtlhal->interfaceindex != 0)
@@ -717,7 +717,7 @@ static void _rtl92de_read_adapter_info(struct ieee80211_hw *hw)
 	rtlpriv->cfg->ops->set_hw_reg(hw, HW_VAR_ETHER_ADDR,
 				      rtlefuse->dev_addr);
 	rtl_dbg(rtlpriv, COMP_INIT, DBG_DMESG, "%pM\n", rtlefuse->dev_addr);
-	_rtl92de_read_txpower_info(hw, rtlefuse->autoload_failflag, hwinfo);
+	_rtl92d_read_txpower_info(hw, rtlefuse->autoload_failflag, hwinfo);
 
 	/* Read Channel Plan */
 	switch (rtlhal->bandset) {
@@ -739,7 +739,7 @@ exit:
 	kfree(hwinfo);
 }
 
-void rtl92de_read_eeprom_info(struct ieee80211_hw *hw)
+void rtl92d_read_eeprom_info(struct ieee80211_hw *hw)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_efuse *rtlefuse = rtl_efuse(rtl_priv(hw));
@@ -760,15 +760,15 @@ void rtl92de_read_eeprom_info(struct ieee80211_hw *hw)
 		rtl_dbg(rtlpriv, COMP_INIT, DBG_LOUD, "Autoload OK\n");
 
 		rtlefuse->autoload_failflag = false;
-		_rtl92de_read_adapter_info(hw);
+		_rtl92d_read_adapter_info(hw);
 	} else {
 		pr_err("Autoload ERR!!\n");
 	}
 }
-EXPORT_SYMBOL_GPL(rtl92de_read_eeprom_info);
+EXPORT_SYMBOL_GPL(rtl92d_read_eeprom_info);
 
-static void rtl92de_update_hal_rate_table(struct ieee80211_hw *hw,
-					  struct ieee80211_sta *sta)
+static void rtl92d_update_hal_rate_table(struct ieee80211_hw *hw,
+					 struct ieee80211_sta *sta)
 {
 	struct rtl_hal *rtlhal = rtl_hal(rtl_priv(hw));
 	struct rtl_mac *mac = rtl_mac(rtl_priv(hw));
@@ -851,9 +851,9 @@ static void rtl92de_update_hal_rate_table(struct ieee80211_hw *hw,
 		rtl_read_dword(rtlpriv, REG_ARFR0));
 }
 
-static void rtl92de_update_hal_rate_mask(struct ieee80211_hw *hw,
-					 struct ieee80211_sta *sta,
-					 u8 rssi_level, bool update_bw)
+static void rtl92d_update_hal_rate_mask(struct ieee80211_hw *hw,
+					struct ieee80211_sta *sta,
+					u8 rssi_level, bool update_bw)
 {
 	struct rtl_hal *rtlhal = rtl_hal(rtl_priv(hw));
 	struct rtl_mac *mac = rtl_mac(rtl_priv(hw));
@@ -1009,20 +1009,20 @@ static void rtl92de_update_hal_rate_mask(struct ieee80211_hw *hw,
 		sta_entry->ratr_index = ratr_index;
 }
 
-void rtl92de_update_hal_rate_tbl(struct ieee80211_hw *hw,
-				 struct ieee80211_sta *sta,
-				 u8 rssi_level, bool update_bw)
+void rtl92d_update_hal_rate_tbl(struct ieee80211_hw *hw,
+				struct ieee80211_sta *sta,
+				u8 rssi_level, bool update_bw)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 
 	if (rtlpriv->dm.useramask)
-		rtl92de_update_hal_rate_mask(hw, sta, rssi_level, update_bw);
+		rtl92d_update_hal_rate_mask(hw, sta, rssi_level, update_bw);
 	else
-		rtl92de_update_hal_rate_table(hw, sta);
+		rtl92d_update_hal_rate_table(hw, sta);
 }
-EXPORT_SYMBOL_GPL(rtl92de_update_hal_rate_tbl);
+EXPORT_SYMBOL_GPL(rtl92d_update_hal_rate_tbl);
 
-void rtl92de_update_channel_access_setting(struct ieee80211_hw *hw)
+void rtl92d_update_channel_access_setting(struct ieee80211_hw *hw)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_mac *mac = rtl_mac(rtl_priv(hw));
@@ -1036,9 +1036,9 @@ void rtl92de_update_channel_access_setting(struct ieee80211_hw *hw)
 		sifs_timer = 0x1010;
 	rtlpriv->cfg->ops->set_hw_reg(hw, HW_VAR_SIFS, (u8 *)&sifs_timer);
 }
-EXPORT_SYMBOL_GPL(rtl92de_update_channel_access_setting);
+EXPORT_SYMBOL_GPL(rtl92d_update_channel_access_setting);
 
-bool rtl92de_gpio_radio_on_off_checking(struct ieee80211_hw *hw, u8 *valid)
+bool rtl92d_gpio_radio_on_off_checking(struct ieee80211_hw *hw, u8 *valid)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_ps_ctl *ppsc = rtl_psc(rtl_priv(hw));
@@ -1093,11 +1093,11 @@ bool rtl92de_gpio_radio_on_off_checking(struct ieee80211_hw *hw, u8 *valid)
 	*valid = 1;
 	return !ppsc->hwradiooff;
 }
-EXPORT_SYMBOL_GPL(rtl92de_gpio_radio_on_off_checking);
+EXPORT_SYMBOL_GPL(rtl92d_gpio_radio_on_off_checking);
 
-void rtl92de_set_key(struct ieee80211_hw *hw, u32 key_index,
-		     u8 *p_macaddr, bool is_group, u8 enc_algo,
-		     bool is_wepkey, bool clear_all)
+void rtl92d_set_key(struct ieee80211_hw *hw, u32 key_index,
+		    u8 *p_macaddr, bool is_group, u8 enc_algo,
+		    bool is_wepkey, bool clear_all)
 {
 	static const u8 cam_const_addr[4][6] = {
 		{0x00, 0x00, 0x00, 0x00, 0x00, 0x00},
@@ -1222,4 +1222,4 @@ void rtl92de_set_key(struct ieee80211_hw *hw, u32 key_index,
 		}
 	}
 }
-EXPORT_SYMBOL_GPL(rtl92de_set_key);
+EXPORT_SYMBOL_GPL(rtl92d_set_key);
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192d/hw_common.h b/drivers/net/wireless/realtek/rtlwifi/rtl8192d/hw_common.h
index 2c07f5cc57660..4da1bab15f36a 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192d/hw_common.h
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192d/hw_common.h
@@ -4,21 +4,21 @@
 #ifndef __RTL92D_HW_COMMON_H__
 #define __RTL92D_HW_COMMON_H__
 
-void rtl92de_stop_tx_beacon(struct ieee80211_hw *hw);
-void rtl92de_resume_tx_beacon(struct ieee80211_hw *hw);
+void rtl92d_stop_tx_beacon(struct ieee80211_hw *hw);
+void rtl92d_resume_tx_beacon(struct ieee80211_hw *hw);
 void rtl92d_get_hw_reg(struct ieee80211_hw *hw, u8 variable, u8 *val);
 void rtl92d_set_hw_reg(struct ieee80211_hw *hw, u8 variable, u8 *val);
-bool rtl92de_llt_write(struct ieee80211_hw *hw, u32 address, u32 data);
-void rtl92de_enable_hw_security_config(struct ieee80211_hw *hw);
-void rtl92de_set_qos(struct ieee80211_hw *hw, int aci);
-void rtl92de_read_eeprom_info(struct ieee80211_hw *hw);
-void rtl92de_update_hal_rate_tbl(struct ieee80211_hw *hw,
-				 struct ieee80211_sta *sta,
-				 u8 rssi_level, bool update_bw);
-void rtl92de_update_channel_access_setting(struct ieee80211_hw *hw);
-bool rtl92de_gpio_radio_on_off_checking(struct ieee80211_hw *hw, u8 *valid);
-void rtl92de_set_key(struct ieee80211_hw *hw, u32 key_index,
-		     u8 *p_macaddr, bool is_group, u8 enc_algo,
-		     bool is_wepkey, bool clear_all);
+bool rtl92d_llt_write(struct ieee80211_hw *hw, u32 address, u32 data);
+void rtl92d_enable_hw_security_config(struct ieee80211_hw *hw);
+void rtl92d_set_qos(struct ieee80211_hw *hw, int aci);
+void rtl92d_read_eeprom_info(struct ieee80211_hw *hw);
+void rtl92d_update_hal_rate_tbl(struct ieee80211_hw *hw,
+				struct ieee80211_sta *sta,
+				u8 rssi_level, bool update_bw);
+void rtl92d_update_channel_access_setting(struct ieee80211_hw *hw);
+bool rtl92d_gpio_radio_on_off_checking(struct ieee80211_hw *hw, u8 *valid);
+void rtl92d_set_key(struct ieee80211_hw *hw, u32 key_index,
+		    u8 *p_macaddr, bool is_group, u8 enc_algo,
+		    bool is_wepkey, bool clear_all);
 
 #endif
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192d/trx_common.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192d/trx_common.c
index 72d2b7426d82f..9f9a34492030c 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192d/trx_common.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192d/trx_common.c
@@ -7,8 +7,8 @@
 #include "def.h"
 #include "trx_common.h"
 
-static long _rtl92de_translate_todbm(struct ieee80211_hw *hw,
-				     u8 signal_strength_index)
+static long _rtl92d_translate_todbm(struct ieee80211_hw *hw,
+				    u8 signal_strength_index)
 {
 	long signal_power;
 
@@ -17,13 +17,13 @@ static long _rtl92de_translate_todbm(struct ieee80211_hw *hw,
 	return signal_power;
 }
 
-static void _rtl92de_query_rxphystatus(struct ieee80211_hw *hw,
-				       struct rtl_stats *pstats,
-				       __le32 *pdesc,
-				       struct rx_fwinfo_92d *p_drvinfo,
-				       bool packet_match_bssid,
-				       bool packet_toself,
-				       bool packet_beacon)
+static void _rtl92d_query_rxphystatus(struct ieee80211_hw *hw,
+				      struct rtl_stats *pstats,
+				      __le32 *pdesc,
+				      struct rx_fwinfo_92d *p_drvinfo,
+				      bool packet_match_bssid,
+				      bool packet_toself,
+				      bool packet_beacon)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_phy *rtlphy = &rtlpriv->phy;
@@ -203,8 +203,8 @@ static void rtl92d_loop_over_paths(struct ieee80211_hw *hw,
 	}
 }
 
-static void _rtl92de_process_ui_rssi(struct ieee80211_hw *hw,
-				     struct rtl_stats *pstats)
+static void _rtl92d_process_ui_rssi(struct ieee80211_hw *hw,
+				    struct rtl_stats *pstats)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rt_smooth_data *ui_rssi;
@@ -226,15 +226,15 @@ static void _rtl92de_process_ui_rssi(struct ieee80211_hw *hw,
 	if (ui_rssi->index >= PHY_RSSI_SLID_WIN_MAX)
 		ui_rssi->index = 0;
 	tmpval = ui_rssi->total_val / ui_rssi->total_num;
-	rtlpriv->stats.signal_strength = _rtl92de_translate_todbm(hw, (u8)tmpval);
+	rtlpriv->stats.signal_strength = _rtl92d_translate_todbm(hw, (u8)tmpval);
 	pstats->rssi = rtlpriv->stats.signal_strength;
 
 	if (!pstats->is_cck && pstats->packet_toself)
 		rtl92d_loop_over_paths(hw, pstats);
 }
 
-static void _rtl92de_update_rxsignalstatistics(struct ieee80211_hw *hw,
-					       struct rtl_stats *pstats)
+static void _rtl92d_update_rxsignalstatistics(struct ieee80211_hw *hw,
+					      struct rtl_stats *pstats)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	int weighting = 0;
@@ -249,8 +249,8 @@ static void _rtl92de_update_rxsignalstatistics(struct ieee80211_hw *hw,
 		5 + pstats->recvsignalpower + weighting) / 6;
 }
 
-static void _rtl92de_process_pwdb(struct ieee80211_hw *hw,
-				  struct rtl_stats *pstats)
+static void _rtl92d_process_pwdb(struct ieee80211_hw *hw,
+				 struct rtl_stats *pstats)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_mac *mac = rtl_mac(rtl_priv(hw));
@@ -276,7 +276,7 @@ static void _rtl92de_process_pwdb(struct ieee80211_hw *hw,
 			      (pstats->rx_pwdb_all)) / (RX_SMOOTH_FACTOR);
 		}
 		rtlpriv->dm.undec_sm_pwdb = undec_sm_pwdb;
-		_rtl92de_update_rxsignalstatistics(hw, pstats);
+		_rtl92d_update_rxsignalstatistics(hw, pstats);
 	}
 }
 
@@ -301,8 +301,8 @@ static void rtl92d_loop_over_streams(struct ieee80211_hw *hw,
 	}
 }
 
-static void _rtl92de_process_ui_link_quality(struct ieee80211_hw *hw,
-					     struct rtl_stats *pstats)
+static void _rtl92d_process_ui_link_quality(struct ieee80211_hw *hw,
+					    struct rtl_stats *pstats)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rt_smooth_data *ui_link_quality;
@@ -330,24 +330,24 @@ static void _rtl92de_process_ui_link_quality(struct ieee80211_hw *hw,
 	rtl92d_loop_over_streams(hw, pstats);
 }
 
-static void _rtl92de_process_phyinfo(struct ieee80211_hw *hw,
-				     u8 *buffer,
-				     struct rtl_stats *pcurrent_stats)
+static void _rtl92d_process_phyinfo(struct ieee80211_hw *hw,
+				    u8 *buffer,
+				    struct rtl_stats *pcurrent_stats)
 {
 	if (!pcurrent_stats->packet_matchbssid &&
 	    !pcurrent_stats->packet_beacon)
 		return;
 
-	_rtl92de_process_ui_rssi(hw, pcurrent_stats);
-	_rtl92de_process_pwdb(hw, pcurrent_stats);
-	_rtl92de_process_ui_link_quality(hw, pcurrent_stats);
+	_rtl92d_process_ui_rssi(hw, pcurrent_stats);
+	_rtl92d_process_pwdb(hw, pcurrent_stats);
+	_rtl92d_process_ui_link_quality(hw, pcurrent_stats);
 }
 
-static void _rtl92de_translate_rx_signal_stuff(struct ieee80211_hw *hw,
-					       struct sk_buff *skb,
-					       struct rtl_stats *pstats,
-					       __le32 *pdesc,
-					       struct rx_fwinfo_92d *p_drvinfo)
+static void _rtl92d_translate_rx_signal_stuff(struct ieee80211_hw *hw,
+					      struct sk_buff *skb,
+					      struct rtl_stats *pstats,
+					      __le32 *pdesc,
+					      struct rx_fwinfo_92d *p_drvinfo)
 {
 	struct rtl_efuse *rtlefuse = rtl_efuse(rtl_priv(hw));
 	struct rtl_mac *mac = rtl_mac(rtl_priv(hw));
@@ -375,15 +375,15 @@ static void _rtl92de_translate_rx_signal_stuff(struct ieee80211_hw *hw,
 	packet_toself = packet_matchbssid &&
 			ether_addr_equal(praddr, rtlefuse->dev_addr);
 	packet_beacon = ieee80211_is_beacon(fc);
-	_rtl92de_query_rxphystatus(hw, pstats, pdesc, p_drvinfo,
-				   packet_matchbssid, packet_toself,
-				   packet_beacon);
-	_rtl92de_process_phyinfo(hw, tmp_buf, pstats);
+	_rtl92d_query_rxphystatus(hw, pstats, pdesc, p_drvinfo,
+				  packet_matchbssid, packet_toself,
+				  packet_beacon);
+	_rtl92d_process_phyinfo(hw, tmp_buf, pstats);
 }
 
-bool rtl92de_rx_query_desc(struct ieee80211_hw *hw, struct rtl_stats *stats,
-			   struct ieee80211_rx_status *rx_status,
-			   u8 *pdesc8, struct sk_buff *skb)
+bool rtl92d_rx_query_desc(struct ieee80211_hw *hw, struct rtl_stats *stats,
+			  struct ieee80211_rx_status *rx_status,
+			  u8 *pdesc8, struct sk_buff *skb)
 {
 	__le32 *pdesc = (__le32 *)pdesc8;
 	struct rx_fwinfo_92d *p_drvinfo;
@@ -423,17 +423,17 @@ bool rtl92de_rx_query_desc(struct ieee80211_hw *hw, struct rtl_stats *stats,
 	if (phystatus) {
 		p_drvinfo = (struct rx_fwinfo_92d *)(skb->data +
 						     stats->rx_bufshift);
-		_rtl92de_translate_rx_signal_stuff(hw, skb, stats, pdesc,
-						   p_drvinfo);
+		_rtl92d_translate_rx_signal_stuff(hw, skb, stats, pdesc,
+						  p_drvinfo);
 	}
 	/*rx_status->qual = stats->signal; */
 	rx_status->signal = stats->recvsignalpower + 10;
 	return true;
 }
-EXPORT_SYMBOL_GPL(rtl92de_rx_query_desc);
+EXPORT_SYMBOL_GPL(rtl92d_rx_query_desc);
 
-void rtl92de_set_desc(struct ieee80211_hw *hw, u8 *pdesc8, bool istx,
-		      u8 desc_name, u8 *val)
+void rtl92d_set_desc(struct ieee80211_hw *hw, u8 *pdesc8, bool istx,
+		     u8 desc_name, u8 *val)
 {
 	__le32 *pdesc = (__le32 *)pdesc8;
 
@@ -473,10 +473,10 @@ void rtl92de_set_desc(struct ieee80211_hw *hw, u8 *pdesc8, bool istx,
 		}
 	}
 }
-EXPORT_SYMBOL_GPL(rtl92de_set_desc);
+EXPORT_SYMBOL_GPL(rtl92d_set_desc);
 
-u64 rtl92de_get_desc(struct ieee80211_hw *hw,
-		     u8 *p_desc8, bool istx, u8 desc_name)
+u64 rtl92d_get_desc(struct ieee80211_hw *hw,
+		    u8 *p_desc8, bool istx, u8 desc_name)
 {
 	__le32 *p_desc = (__le32 *)p_desc8;
 	u32 ret = 0;
@@ -513,4 +513,4 @@ u64 rtl92de_get_desc(struct ieee80211_hw *hw,
 	}
 	return ret;
 }
-EXPORT_SYMBOL_GPL(rtl92de_get_desc);
+EXPORT_SYMBOL_GPL(rtl92d_get_desc);
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192d/trx_common.h b/drivers/net/wireless/realtek/rtlwifi/rtl8192d/trx_common.h
index 87d956d771ebe..528182b1eba68 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192d/trx_common.h
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192d/trx_common.h
@@ -393,13 +393,13 @@ struct rx_fwinfo_92d {
 #endif
 } __packed;
 
-bool rtl92de_rx_query_desc(struct ieee80211_hw *hw,
-			   struct rtl_stats *stats,
-			   struct ieee80211_rx_status *rx_status,
-			   u8 *pdesc, struct sk_buff *skb);
-void rtl92de_set_desc(struct ieee80211_hw *hw, u8 *pdesc, bool istx,
-		      u8 desc_name, u8 *val);
-u64 rtl92de_get_desc(struct ieee80211_hw *hw,
-		     u8 *p_desc, bool istx, u8 desc_name);
+bool rtl92d_rx_query_desc(struct ieee80211_hw *hw,
+			  struct rtl_stats *stats,
+			  struct ieee80211_rx_status *rx_status,
+			  u8 *pdesc, struct sk_buff *skb);
+void rtl92d_set_desc(struct ieee80211_hw *hw, u8 *pdesc, bool istx,
+		     u8 desc_name, u8 *val);
+u64 rtl92d_get_desc(struct ieee80211_hw *hw,
+		    u8 *p_desc, bool istx, u8 desc_name);
 
 #endif
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/hw.c
index 73b81e60cfa90..03f4314bdb2e6 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/hw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/hw.c
@@ -181,7 +181,7 @@ void rtl92de_set_hw_reg(struct ieee80211_hw *hw, u8 variable, u8 *val)
 		u8 btype_ibss = val[0];
 
 		if (btype_ibss)
-			rtl92de_stop_tx_beacon(hw);
+			rtl92d_stop_tx_beacon(hw);
 		_rtl92de_set_bcn_ctrl_reg(hw, 0, BIT(3));
 		rtl_write_dword(rtlpriv, REG_TSFTR,
 				(u32) (mac->tsf & 0xffffffff));
@@ -189,7 +189,7 @@ void rtl92de_set_hw_reg(struct ieee80211_hw *hw, u8 variable, u8 *val)
 				(u32) ((mac->tsf >> 32) & 0xffffffff));
 		_rtl92de_set_bcn_ctrl_reg(hw, BIT(3), 0);
 		if (btype_ibss)
-			rtl92de_resume_tx_beacon(hw);
+			rtl92d_resume_tx_beacon(hw);
 
 		break;
 	}
@@ -295,13 +295,13 @@ static bool _rtl92de_llt_table_init(struct ieee80211_hw *hw)
 
 	/* 18.  LLT_table_init(Adapter);  */
 	for (i = 0; i < (txpktbuf_bndy - 1); i++) {
-		status = rtl92de_llt_write(hw, i, i + 1);
+		status = rtl92d_llt_write(hw, i, i + 1);
 		if (!status)
 			return status;
 	}
 
 	/* end of list */
-	status = rtl92de_llt_write(hw, (txpktbuf_bndy - 1), 0xFF);
+	status = rtl92d_llt_write(hw, (txpktbuf_bndy - 1), 0xFF);
 	if (!status)
 		return status;
 
@@ -310,13 +310,13 @@ static bool _rtl92de_llt_table_init(struct ieee80211_hw *hw)
 	/* config this MAC as two MAC transfer. */
 	/* Otherwise used as local loopback buffer.  */
 	for (i = txpktbuf_bndy; i < maxpage; i++) {
-		status = rtl92de_llt_write(hw, i, (i + 1));
+		status = rtl92d_llt_write(hw, i, (i + 1));
 		if (!status)
 			return status;
 	}
 
 	/* Let last entry point to the start entry of ring buffer */
-	status = rtl92de_llt_write(hw, maxpage, txpktbuf_bndy);
+	status = rtl92d_llt_write(hw, maxpage, txpktbuf_bndy);
 	if (!status)
 		return status;
 
@@ -688,7 +688,7 @@ int rtl92de_hw_init(struct ieee80211_hw *hw)
 
 	/* reset hw sec */
 	rtl_cam_reset_all_entry(hw);
-	rtl92de_enable_hw_security_config(hw);
+	rtl92d_enable_hw_security_config(hw);
 
 	/* Read EEPROM TX power index and PHY_REG_PG.txt to capture correct */
 	/* TX power index for different rate set. */
@@ -742,11 +742,11 @@ static int _rtl92de_set_media_status(struct ieee80211_hw *hw,
 
 	if (type == NL80211_IFTYPE_UNSPECIFIED ||
 	    type == NL80211_IFTYPE_STATION) {
-		rtl92de_stop_tx_beacon(hw);
+		rtl92d_stop_tx_beacon(hw);
 		_rtl92de_enable_bcn_sub_func(hw);
 	} else if (type == NL80211_IFTYPE_ADHOC ||
 		type == NL80211_IFTYPE_AP) {
-		rtl92de_resume_tx_beacon(hw);
+		rtl92d_resume_tx_beacon(hw);
 		_rtl92de_disable_bcn_sub_func(hw);
 	} else {
 		rtl_dbg(rtlpriv, COMP_ERR, DBG_WARNING,
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/sw.c
index 5f6311c2aac47..f5ce4889523e3 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/sw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/sw.c
@@ -187,7 +187,7 @@ static void rtl92d_deinit_sw_vars(struct ieee80211_hw *hw)
 static struct rtl_hal_ops rtl8192de_hal_ops = {
 	.init_sw_vars = rtl92d_init_sw_vars,
 	.deinit_sw_vars = rtl92d_deinit_sw_vars,
-	.read_eeprom_info = rtl92de_read_eeprom_info,
+	.read_eeprom_info = rtl92d_read_eeprom_info,
 	.interrupt_recognized = rtl92de_interrupt_recognized,
 	.hw_init = rtl92de_hw_init,
 	.hw_disable = rtl92de_card_disable,
@@ -197,30 +197,30 @@ static struct rtl_hal_ops rtl8192de_hal_ops = {
 	.disable_interrupt = rtl92de_disable_interrupt,
 	.set_network_type = rtl92de_set_network_type,
 	.set_chk_bssid = rtl92de_set_check_bssid,
-	.set_qos = rtl92de_set_qos,
+	.set_qos = rtl92d_set_qos,
 	.set_bcn_reg = rtl92de_set_beacon_related_registers,
 	.set_bcn_intv = rtl92de_set_beacon_interval,
 	.update_interrupt_mask = rtl92de_update_interrupt_mask,
 	.get_hw_reg = rtl92de_get_hw_reg,
 	.set_hw_reg = rtl92de_set_hw_reg,
-	.update_rate_tbl = rtl92de_update_hal_rate_tbl,
+	.update_rate_tbl = rtl92d_update_hal_rate_tbl,
 	.fill_tx_desc = rtl92de_tx_fill_desc,
 	.fill_tx_cmddesc = rtl92de_tx_fill_cmddesc,
-	.query_rx_desc = rtl92de_rx_query_desc,
-	.set_channel_access = rtl92de_update_channel_access_setting,
-	.radio_onoff_checking = rtl92de_gpio_radio_on_off_checking,
+	.query_rx_desc = rtl92d_rx_query_desc,
+	.set_channel_access = rtl92d_update_channel_access_setting,
+	.radio_onoff_checking = rtl92d_gpio_radio_on_off_checking,
 	.set_bw_mode = rtl92d_phy_set_bw_mode,
 	.switch_channel = rtl92d_phy_sw_chnl,
 	.dm_watchdog = rtl92de_dm_watchdog,
 	.scan_operation_backup = rtl_phy_scan_operation_backup,
 	.set_rf_power_state = rtl92d_phy_set_rf_power_state,
 	.led_control = rtl92de_led_control,
-	.set_desc = rtl92de_set_desc,
-	.get_desc = rtl92de_get_desc,
+	.set_desc = rtl92d_set_desc,
+	.get_desc = rtl92d_get_desc,
 	.is_tx_desc_closed = rtl92de_is_tx_desc_closed,
 	.tx_polling = rtl92de_tx_polling,
-	.enable_hw_sec = rtl92de_enable_hw_security_config,
-	.set_key = rtl92de_set_key,
+	.enable_hw_sec = rtl92d_enable_hw_security_config,
+	.set_key = rtl92d_set_key,
 	.get_bbreg = rtl92d_phy_query_bb_reg,
 	.set_bbreg = rtl92d_phy_set_bb_reg,
 	.get_rfreg = rtl92d_phy_query_rf_reg,
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/trx.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/trx.c
index 2b9b352f77839..91bf399c9ef12 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/trx.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/trx.c
@@ -292,7 +292,7 @@ bool rtl92de_is_tx_desc_closed(struct ieee80211_hw *hw,
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
 	struct rtl8192_tx_ring *ring = &rtlpci->tx_ring[hw_queue];
 	u8 *entry = (u8 *)(&ring->desc[ring->idx]);
-	u8 own = (u8)rtl92de_get_desc(hw, entry, true, HW_DESC_OWN);
+	u8 own = (u8)rtl92d_get_desc(hw, entry, true, HW_DESC_OWN);
 
 	/* a beacon packet will only use the first
 	 * descriptor by defaut, and the own bit may not
-- 
GitLab


From ed4117567419a9f7e9bfc32855525ce56b98899a Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Thu, 23 May 2024 17:44:09 +0300
Subject: [PATCH 541/950] wifi: rtlwifi: Add rtl8192du/table.{c,h}

These contain the MAC, BB, RF, and AGC initialisation tables for
RTL8192DU.

Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://msgid.link/5ea548b9-5ec6-4358-aa5d-94071f2341cb@gmail.com
---
 .../realtek/rtlwifi/rtl8192du/table.c         | 1675 +++++++++++++++++
 .../realtek/rtlwifi/rtl8192du/table.h         |   29 +
 2 files changed, 1704 insertions(+)
 create mode 100644 drivers/net/wireless/realtek/rtlwifi/rtl8192du/table.c
 create mode 100644 drivers/net/wireless/realtek/rtlwifi/rtl8192du/table.h

diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192du/table.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/table.c
new file mode 100644
index 0000000000000..036701433d853
--- /dev/null
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/table.c
@@ -0,0 +1,1675 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2024  Realtek Corporation.*/
+
+#include <linux/types.h>
+
+#include "table.h"
+
+const u32 rtl8192du_phy_reg_2tarray[PHY_REG_2T_ARRAYLENGTH] = {
+	0x800, 0x80040002,
+	0x804, 0x00000003,
+	0x808, 0x0000fc00,
+	0x80c, 0x0000000a,
+	0x810, 0x10001331,
+	0x814, 0x020c3d10,
+	0x818, 0x02200385,
+	0x81c, 0x00000000,
+	0x820, 0x01000100,
+	0x824, 0x00390004,
+	0x828, 0x01000100,
+	0x82c, 0x00390004,
+	0x830, 0x27272727,
+	0x834, 0x27272727,
+	0x838, 0x27272727,
+	0x83c, 0x27272727,
+	0x840, 0x00010000,
+	0x844, 0x00010000,
+	0x848, 0x27272727,
+	0x84c, 0x27272727,
+	0x850, 0x00000000,
+	0x854, 0x00000000,
+	0x858, 0x569a569a,
+	0x85c, 0x0c1b25a4,
+	0x860, 0x66e60250,
+	0x864, 0x061f0150,
+	0x868, 0x27272727,
+	0x86c, 0x272b2b2b,
+	0x870, 0x07000700,
+	0x874, 0x22188000,
+	0x878, 0x08080808,
+	0x87c, 0x0001fff8,
+	0x880, 0xc0083070,
+	0x884, 0x00000cd5,
+	0x888, 0x00000000,
+	0x88c, 0xcc0000c0,
+	0x890, 0x00000800,
+	0x894, 0xfffffffe,
+	0x898, 0x40302010,
+	0x89c, 0x00706050,
+	0x900, 0x00000000,
+	0x904, 0x00000023,
+	0x908, 0x00000000,
+	0x90c, 0x81121313,
+	0xa00, 0x00d047c8,
+	0xa04, 0x80ff000c,
+	0xa08, 0x8c8a8300,
+	0xa0c, 0x2e68120f,
+	0xa10, 0x9500bb78,
+	0xa14, 0x11144028,
+	0xa18, 0x00881117,
+	0xa1c, 0x89140f00,
+	0xa20, 0x1a1b0000,
+	0xa24, 0x090e1317,
+	0xa28, 0x00000204,
+	0xa2c, 0x00d30000,
+	0xa70, 0x101fff00,
+	0xa74, 0x00000007,
+	0xc00, 0x40071d40,
+	0xc04, 0x03a05633,
+	0xc08, 0x001000e4,
+	0xc0c, 0x6c6c6c6c,
+	0xc10, 0x08800000,
+	0xc14, 0x40000100,
+	0xc18, 0x08800000,
+	0xc1c, 0x40000100,
+	0xc20, 0x00000000,
+	0xc24, 0x00000000,
+	0xc28, 0x00000000,
+	0xc2c, 0x00000000,
+	0xc30, 0x69e9ac44,
+	0xc34, 0x469652af,
+	0xc38, 0x49795994,
+	0xc3c, 0x0a979718,
+	0xc40, 0x1f7c403f,
+	0xc44, 0x000100b7,
+	0xc48, 0xec020107,
+	0xc4c, 0x007f037f,
+	0xc50, 0x69543420,
+	0xc54, 0x43bc009e,
+	0xc58, 0x69543420,
+	0xc5c, 0x433c00a8,
+	0xc60, 0x00000000,
+	0xc64, 0x7112848b,
+	0xc68, 0x47c00bff,
+	0xc6c, 0x00000036,
+	0xc70, 0x2c7f000d,
+	0xc74, 0x258610db,
+	0xc78, 0x0000001f,
+	0xc7c, 0x40b95612,
+	0xc80, 0x40000100,
+	0xc84, 0x20f60000,
+	0xc88, 0x40000100,
+	0xc8c, 0xa0e40000,
+	0xc90, 0x00121820,
+	0xc94, 0x00000007,
+	0xc98, 0x00121820,
+	0xc9c, 0x00007f7f,
+	0xca0, 0x00000000,
+	0xca4, 0x00000080,
+	0xca8, 0x00000000,
+	0xcac, 0x00000000,
+	0xcb0, 0x00000000,
+	0xcb4, 0x00000000,
+	0xcb8, 0x00000000,
+	0xcbc, 0x28000000,
+	0xcc0, 0x00000000,
+	0xcc4, 0x00000000,
+	0xcc8, 0x00000000,
+	0xccc, 0x00000000,
+	0xcd0, 0x00000000,
+	0xcd4, 0x00000000,
+	0xcd8, 0x64b11e20,
+	0xcdc, 0xe0767533,
+	0xce0, 0x00222222,
+	0xce4, 0x00000000,
+	0xce8, 0x37644302,
+	0xcec, 0x2f97d40c,
+	0xd00, 0x00080740,
+	0xd04, 0x00020403,
+	0xd08, 0x0000907f,
+	0xd0c, 0x20010201,
+	0xd10, 0xa0633333,
+	0xd14, 0x3333bc43,
+	0xd18, 0x7a8f5b6b,
+	0xd2c, 0xcc979975,
+	0xd30, 0x00000000,
+	0xd34, 0x80608404,
+	0xd38, 0x00000000,
+	0xd3c, 0x00027353,
+	0xd40, 0x00000000,
+	0xd44, 0x00000000,
+	0xd48, 0x00000000,
+	0xd4c, 0x00000000,
+	0xd50, 0x6437140a,
+	0xd54, 0x00000000,
+	0xd58, 0x00000000,
+	0xd5c, 0x30032064,
+	0xd60, 0x4653de68,
+	0xd64, 0x04518a3c,
+	0xd68, 0x00002101,
+	0xd6c, 0x2a201c16,
+	0xd70, 0x1812362e,
+	0xd74, 0x322c2220,
+	0xd78, 0x000e3c24,
+	0xe00, 0x2a2a2a2a,
+	0xe04, 0x2a2a2a2a,
+	0xe08, 0x03902a2a,
+	0xe10, 0x2a2a2a2a,
+	0xe14, 0x2a2a2a2a,
+	0xe18, 0x2a2a2a2a,
+	0xe1c, 0x2a2a2a2a,
+	0xe28, 0x00000000,
+	0xe30, 0x1000dc1f,
+	0xe34, 0x10008c1f,
+	0xe38, 0x02140102,
+	0xe3c, 0x681604c2,
+	0xe40, 0x01007c00,
+	0xe44, 0x01004800,
+	0xe48, 0xfb000000,
+	0xe4c, 0x000028d1,
+	0xe50, 0x1000dc1f,
+	0xe54, 0x10008c1f,
+	0xe58, 0x02140102,
+	0xe5c, 0x28160d05,
+	0xe60, 0x00000010,
+	0xe68, 0x001b25a4,
+	0xe6c, 0x63db25a4,
+	0xe70, 0x63db25a4,
+	0xe74, 0x0c126da4,
+	0xe78, 0x0c126da4,
+	0xe7c, 0x0c126da4,
+	0xe80, 0x0c126da4,
+	0xe84, 0x63db25a4,
+	0xe88, 0x0c126da4,
+	0xe8c, 0x63db25a4,
+	0xed0, 0x63db25a4,
+	0xed4, 0x63db25a4,
+	0xed8, 0x63db25a4,
+	0xedc, 0x001b25a4,
+	0xee0, 0x001b25a4,
+	0xeec, 0x6fdb25a4,
+	0xf14, 0x00000003,
+	0xf1c, 0x00000064,
+	0xf4c, 0x00000004,
+	0xf00, 0x00000300,
+};
+
+const u32 rtl8192du_phy_reg_array_pg[PHY_REG_ARRAY_PG_LENGTH] = {
+	0xe00, 0xffffffff, 0x07090c0c,
+	0xe04, 0xffffffff, 0x01020405,
+	0xe08, 0x0000ff00, 0x00000000,
+	0x86c, 0xffffff00, 0x00000000,
+	0xe10, 0xffffffff, 0x0b0c0c0e,
+	0xe14, 0xffffffff, 0x01030506,
+	0xe18, 0xffffffff, 0x0b0c0d0e,
+	0xe1c, 0xffffffff, 0x01030509,
+	0x830, 0xffffffff, 0x07090c0c,
+	0x834, 0xffffffff, 0x01020405,
+	0x838, 0xffffff00, 0x00000000,
+	0x86c, 0x000000ff, 0x00000000,
+	0x83c, 0xffffffff, 0x0b0c0c0e,
+	0x848, 0xffffffff, 0x01030506,
+	0x84c, 0xffffffff, 0x0b0c0d0e,
+	0x868, 0xffffffff, 0x01030509,
+	0xe00, 0xffffffff, 0x00000000,
+	0xe04, 0xffffffff, 0x00000000,
+	0xe08, 0x0000ff00, 0x00000000,
+	0x86c, 0xffffff00, 0x00000000,
+	0xe10, 0xffffffff, 0x00000000,
+	0xe14, 0xffffffff, 0x00000000,
+	0xe18, 0xffffffff, 0x00000000,
+	0xe1c, 0xffffffff, 0x00000000,
+	0x830, 0xffffffff, 0x00000000,
+	0x834, 0xffffffff, 0x00000000,
+	0x838, 0xffffff00, 0x00000000,
+	0x86c, 0x000000ff, 0x00000000,
+	0x83c, 0xffffffff, 0x00000000,
+	0x848, 0xffffffff, 0x00000000,
+	0x84c, 0xffffffff, 0x00000000,
+	0x868, 0xffffffff, 0x00000000,
+	0xe00, 0xffffffff, 0x04040404,
+	0xe04, 0xffffffff, 0x00020204,
+	0xe08, 0x0000ff00, 0x00000000,
+	0x86c, 0xffffff00, 0x00000000,
+	0xe10, 0xffffffff, 0x06060606,
+	0xe14, 0xffffffff, 0x00020406,
+	0xe18, 0xffffffff, 0x00000000,
+	0xe1c, 0xffffffff, 0x00000000,
+	0x830, 0xffffffff, 0x04040404,
+	0x834, 0xffffffff, 0x00020204,
+	0x838, 0xffffff00, 0x00000000,
+	0x86c, 0x000000ff, 0x00000000,
+	0x83c, 0xffffffff, 0x06060606,
+	0x848, 0xffffffff, 0x00020406,
+	0x84c, 0xffffffff, 0x00000000,
+	0x868, 0xffffffff, 0x00000000,
+	0xe00, 0xffffffff, 0x00000000,
+	0xe04, 0xffffffff, 0x00000000,
+	0xe08, 0x0000ff00, 0x00000000,
+	0x86c, 0xffffff00, 0x00000000,
+	0xe10, 0xffffffff, 0x00000000,
+	0xe14, 0xffffffff, 0x00000000,
+	0xe18, 0xffffffff, 0x00000000,
+	0xe1c, 0xffffffff, 0x00000000,
+	0x830, 0xffffffff, 0x00000000,
+	0x834, 0xffffffff, 0x00000000,
+	0x838, 0xffffff00, 0x00000000,
+	0x86c, 0x000000ff, 0x00000000,
+	0x83c, 0xffffffff, 0x00000000,
+	0x848, 0xffffffff, 0x00000000,
+	0x84c, 0xffffffff, 0x00000000,
+	0x868, 0xffffffff, 0x00000000,
+	0xe00, 0xffffffff, 0x00000000,
+	0xe04, 0xffffffff, 0x00000000,
+	0xe08, 0x0000ff00, 0x00000000,
+	0x86c, 0xffffff00, 0x00000000,
+	0xe10, 0xffffffff, 0x00000000,
+	0xe14, 0xffffffff, 0x00000000,
+	0xe18, 0xffffffff, 0x00000000,
+	0xe1c, 0xffffffff, 0x00000000,
+	0x830, 0xffffffff, 0x00000000,
+	0x834, 0xffffffff, 0x00000000,
+	0x838, 0xffffff00, 0x00000000,
+	0x86c, 0x000000ff, 0x00000000,
+	0x83c, 0xffffffff, 0x00000000,
+	0x848, 0xffffffff, 0x00000000,
+	0x84c, 0xffffffff, 0x00000000,
+	0x868, 0xffffffff, 0x00000000,
+	0xe00, 0xffffffff, 0x04040404,
+	0xe04, 0xffffffff, 0x00020204,
+	0xe08, 0x0000ff00, 0x00000000,
+	0x86c, 0xffffff00, 0x00000000,
+	0xe10, 0xffffffff, 0x00000000,
+	0xe14, 0xffffffff, 0x00000000,
+	0xe18, 0xffffffff, 0x00000000,
+	0xe1c, 0xffffffff, 0x00000000,
+	0x830, 0xffffffff, 0x04040404,
+	0x834, 0xffffffff, 0x00020204,
+	0x838, 0xffffff00, 0x00000000,
+	0x86c, 0x000000ff, 0x00000000,
+	0x83c, 0xffffffff, 0x00000000,
+	0x848, 0xffffffff, 0x00000000,
+	0x84c, 0xffffffff, 0x00000000,
+	0x868, 0xffffffff, 0x00000000,
+	0xe00, 0xffffffff, 0x00000000,
+	0xe04, 0xffffffff, 0x00000000,
+	0xe08, 0x0000ff00, 0x00000000,
+	0x86c, 0xffffff00, 0x00000000,
+	0xe10, 0xffffffff, 0x00000000,
+	0xe14, 0xffffffff, 0x00000000,
+	0xe18, 0xffffffff, 0x00000000,
+	0xe1c, 0xffffffff, 0x00000000,
+	0x830, 0xffffffff, 0x00000000,
+	0x834, 0xffffffff, 0x00000000,
+	0x838, 0xffffff00, 0x00000000,
+	0x86c, 0x000000ff, 0x00000000,
+	0x83c, 0xffffffff, 0x00000000,
+	0x848, 0xffffffff, 0x00000000,
+	0x84c, 0xffffffff, 0x00000000,
+	0x868, 0xffffffff, 0x00000000,
+	0xe00, 0xffffffff, 0x04040404,
+	0xe04, 0xffffffff, 0x00020204,
+	0xe08, 0x0000ff00, 0x00000000,
+	0x86c, 0xffffff00, 0x00000000,
+	0xe10, 0xffffffff, 0x08080808,
+	0xe14, 0xffffffff, 0x00040408,
+	0xe18, 0xffffffff, 0x00000000,
+	0xe1c, 0xffffffff, 0x00000000,
+	0x830, 0xffffffff, 0x04040404,
+	0x834, 0xffffffff, 0x00020204,
+	0x838, 0xffffff00, 0x00000000,
+	0x86c, 0x000000ff, 0x00000000,
+	0x83c, 0xffffffff, 0x08080808,
+	0x848, 0xffffffff, 0x00040408,
+	0x84c, 0xffffffff, 0x00000000,
+	0x868, 0xffffffff, 0x00000000,
+	0xe00, 0xffffffff, 0x04040404,
+	0xe04, 0xffffffff, 0x00020204,
+	0xe08, 0x0000ff00, 0x00000000,
+	0x86c, 0xffffff00, 0x00000000,
+	0xe10, 0xffffffff, 0x08080808,
+	0xe14, 0xffffffff, 0x00040408,
+	0xe18, 0xffffffff, 0x00000000,
+	0xe1c, 0xffffffff, 0x00000000,
+	0x830, 0xffffffff, 0x04040404,
+	0x834, 0xffffffff, 0x00020204,
+	0x838, 0xffffff00, 0x00000000,
+	0x86c, 0x000000ff, 0x00000000,
+	0x83c, 0xffffffff, 0x08080808,
+	0x848, 0xffffffff, 0x00040408,
+	0x84c, 0xffffffff, 0x00000000,
+	0x868, 0xffffffff, 0x00000000,
+	0xe00, 0xffffffff, 0x04040404,
+	0xe04, 0xffffffff, 0x00020204,
+	0xe08, 0x0000ff00, 0x00000000,
+	0x86c, 0xffffff00, 0x00000000,
+	0xe10, 0xffffffff, 0x08080808,
+	0xe14, 0xffffffff, 0x00040408,
+	0xe18, 0xffffffff, 0x00000000,
+	0xe1c, 0xffffffff, 0x00000000,
+	0x830, 0xffffffff, 0x04040404,
+	0x834, 0xffffffff, 0x00020204,
+	0x838, 0xffffff00, 0x00000000,
+	0x86c, 0x000000ff, 0x00000000,
+	0x83c, 0xffffffff, 0x08080808,
+	0x848, 0xffffffff, 0x00040408,
+	0x84c, 0xffffffff, 0x00000000,
+	0x868, 0xffffffff, 0x00000000,
+	0xe00, 0xffffffff, 0x04040404,
+	0xe04, 0xffffffff, 0x00020204,
+	0xe08, 0x0000ff00, 0x00000000,
+	0x86c, 0xffffff00, 0x00000000,
+	0xe10, 0xffffffff, 0x08080808,
+	0xe14, 0xffffffff, 0x00040408,
+	0xe18, 0xffffffff, 0x00000000,
+	0xe1c, 0xffffffff, 0x00000000,
+	0x830, 0xffffffff, 0x04040404,
+	0x834, 0xffffffff, 0x00020204,
+	0x838, 0xffffff00, 0x00000000,
+	0x86c, 0x000000ff, 0x00000000,
+	0x83c, 0xffffffff, 0x08080808,
+	0x848, 0xffffffff, 0x00040408,
+	0x84c, 0xffffffff, 0x00000000,
+	0x868, 0xffffffff, 0x00000000,
+	0xe00, 0xffffffff, 0x04040404,
+	0xe04, 0xffffffff, 0x00020204,
+	0xe08, 0x0000ff00, 0x00000000,
+	0x86c, 0xffffff00, 0x00000000,
+	0xe10, 0xffffffff, 0x08080808,
+	0xe14, 0xffffffff, 0x00040408,
+	0xe18, 0xffffffff, 0x00000000,
+	0xe1c, 0xffffffff, 0x00000000,
+	0x830, 0xffffffff, 0x04040404,
+	0x834, 0xffffffff, 0x00020204,
+	0x838, 0xffffff00, 0x00000000,
+	0x86c, 0x000000ff, 0x00000000,
+	0x83c, 0xffffffff, 0x08080808,
+	0x848, 0xffffffff, 0x00040408,
+	0x84c, 0xffffffff, 0x00000000,
+	0x868, 0xffffffff, 0x00000000,
+	0xe00, 0xffffffff, 0x04040404,
+	0xe04, 0xffffffff, 0x00020204,
+	0xe08, 0x0000ff00, 0x00000000,
+	0x86c, 0xffffff00, 0x00000000,
+	0xe10, 0xffffffff, 0x08080808,
+	0xe14, 0xffffffff, 0x00040408,
+	0xe18, 0xffffffff, 0x00000000,
+	0xe1c, 0xffffffff, 0x00000000,
+	0x830, 0xffffffff, 0x04040404,
+	0x834, 0xffffffff, 0x00020204,
+	0x838, 0xffffff00, 0x00000000,
+	0x86c, 0x000000ff, 0x00000000,
+	0x83c, 0xffffffff, 0x08080808,
+	0x848, 0xffffffff, 0x00040408,
+	0x84c, 0xffffffff, 0x00000000,
+	0x868, 0xffffffff, 0x00000000,
+};
+
+const u32 rtl8192du_radioa_2tarray[RADIOA_2T_ARRAYLENGTH] = {
+	0x000, 0x00030000,
+	0x001, 0x00030000,
+	0x002, 0x00000000,
+	0x003, 0x00018c63,
+	0x004, 0x00018c63,
+	0x008, 0x00084000,
+	0x00b, 0x0001c000,
+	0x00e, 0x00018c67,
+	0x00f, 0x00000851,
+	0x014, 0x00021440,
+	0x018, 0x00017524,
+	0x019, 0x00000000,
+	0x01d, 0x000a1290,
+	0x023, 0x00001558,
+	0x01a, 0x00030a99,
+	0x01b, 0x00040b00,
+	0x01c, 0x000fc339,
+	0x03a, 0x000a57eb,
+	0x03b, 0x00020000,
+	0x03c, 0x000ff454,
+	0x020, 0x0000aa52,
+	0x021, 0x00054000,
+	0x040, 0x0000aa52,
+	0x041, 0x00014000,
+	0x025, 0x000803be,
+	0x026, 0x000fc638,
+	0x027, 0x00077c18,
+	0x028, 0x000de471,
+	0x029, 0x000d7110,
+	0x02a, 0x0008cb04,
+	0x02b, 0x0004128b,
+	0x02c, 0x00001840,
+	0x043, 0x0002444f,
+	0x044, 0x0001adb0,
+	0x045, 0x00056467,
+	0x046, 0x0008992c,
+	0x047, 0x0000452c,
+	0x048, 0x000f9c43,
+	0x049, 0x00002e0c,
+	0x04a, 0x000546eb,
+	0x04b, 0x0008966c,
+	0x04c, 0x0000dde9,
+	0x018, 0x00007401,
+	0x000, 0x00070000,
+	0x012, 0x000dc000,
+	0x012, 0x00090000,
+	0x012, 0x00051000,
+	0x012, 0x00012000,
+	0x013, 0x000287b7,
+	0x013, 0x000247ab,
+	0x013, 0x0002079f,
+	0x013, 0x0001c793,
+	0x013, 0x0001839b,
+	0x013, 0x00014392,
+	0x013, 0x0001019a,
+	0x013, 0x0000c191,
+	0x013, 0x00008194,
+	0x013, 0x000040a0,
+	0x013, 0x00000018,
+	0x015, 0x0000f424,
+	0x015, 0x0004f424,
+	0x015, 0x0008f424,
+	0x016, 0x000e1330,
+	0x016, 0x000a1330,
+	0x016, 0x00061330,
+	0x016, 0x00021330,
+	0x018, 0x00017524,
+	0x000, 0x00070000,
+	0x012, 0x000cf000,
+	0x012, 0x000bc000,
+	0x012, 0x00078000,
+	0x012, 0x00000000,
+	0x013, 0x000287bc,
+	0x013, 0x000247b0,
+	0x013, 0x000203b4,
+	0x013, 0x0001c3a8,
+	0x013, 0x000181b4,
+	0x013, 0x000141a8,
+	0x013, 0x000100b4,
+	0x013, 0x0000c0a8,
+	0x013, 0x0000b030,
+	0x013, 0x00004024,
+	0x013, 0x00000018,
+	0x015, 0x0000f4c3,
+	0x015, 0x0004f4c3,
+	0x015, 0x0008f4c3,
+	0x016, 0x000e085f,
+	0x016, 0x000a085f,
+	0x016, 0x0006085f,
+	0x016, 0x0002085f,
+	0x018, 0x00037524,
+	0x000, 0x00070000,
+	0x012, 0x000cf000,
+	0x012, 0x000bc000,
+	0x012, 0x00078000,
+	0x012, 0x00000000,
+	0x013, 0x000287bc,
+	0x013, 0x000247b0,
+	0x013, 0x000203b4,
+	0x013, 0x0001c3a8,
+	0x013, 0x000181b4,
+	0x013, 0x000141a8,
+	0x013, 0x000100b4,
+	0x013, 0x0000c0a8,
+	0x013, 0x0000b030,
+	0x013, 0x00004024,
+	0x013, 0x00000018,
+	0x015, 0x0000f4c3,
+	0x015, 0x0004f4c3,
+	0x015, 0x0008f4c3,
+	0x016, 0x000e085f,
+	0x016, 0x000a085f,
+	0x016, 0x0006085f,
+	0x016, 0x0002085f,
+	0x018, 0x00057568,
+	0x000, 0x00070000,
+	0x012, 0x000cf000,
+	0x012, 0x000bc000,
+	0x012, 0x00078000,
+	0x012, 0x00000000,
+	0x013, 0x000287bc,
+	0x013, 0x000247b0,
+	0x013, 0x000203b4,
+	0x013, 0x0001c3a8,
+	0x013, 0x000181b4,
+	0x013, 0x000141a8,
+	0x013, 0x000100b4,
+	0x013, 0x0000c0a8,
+	0x013, 0x0000b030,
+	0x013, 0x00004024,
+	0x013, 0x00000018,
+	0x015, 0x0000f4c3,
+	0x015, 0x0004f4c3,
+	0x015, 0x0008f4c3,
+	0x016, 0x000e085f,
+	0x016, 0x000a085f,
+	0x016, 0x0006085f,
+	0x016, 0x0002085f,
+	0x030, 0x0004470f,
+	0x031, 0x00044ff0,
+	0x032, 0x00000070,
+	0x033, 0x000dd480,
+	0x034, 0x000ffac0,
+	0x035, 0x000b80c0,
+	0x036, 0x00077000,
+	0x037, 0x00064ff2,
+	0x038, 0x000e7661,
+	0x039, 0x00000e90,
+	0x000, 0x00030000,
+	0x018, 0x0000f401,
+	0x0fe, 0x00000000,
+	0x0fe, 0x00000000,
+	0x01e, 0x00088009,
+	0x01f, 0x00080003,
+	0x0fe, 0x00000000,
+	0x01e, 0x00088001,
+	0x01f, 0x00080000,
+	0x0fe, 0x00000000,
+	0x018, 0x00097524,
+	0x0fe, 0x00000000,
+	0x0fe, 0x00000000,
+	0x0fe, 0x00000000,
+	0x0fe, 0x00000000,
+	0x02b, 0x00041289,
+	0x0fe, 0x00000000,
+	0x02d, 0x0006aaaa,
+	0x02e, 0x000b4d01,
+	0x02d, 0x00080000,
+	0x02e, 0x00004d02,
+	0x02d, 0x00095555,
+	0x02e, 0x00054d03,
+	0x02d, 0x000aaaaa,
+	0x02e, 0x000b4d04,
+	0x02d, 0x000c0000,
+	0x02e, 0x00004d05,
+	0x02d, 0x000d5555,
+	0x02e, 0x00054d06,
+	0x02d, 0x000eaaaa,
+	0x02e, 0x000b4d07,
+	0x02d, 0x00000000,
+	0x02e, 0x00005108,
+	0x02d, 0x00015555,
+	0x02e, 0x00055109,
+	0x02d, 0x0002aaaa,
+	0x02e, 0x000b510a,
+	0x02d, 0x00040000,
+	0x02e, 0x0000510b,
+	0x02d, 0x00055555,
+	0x02e, 0x0005510c,
+};
+
+const u32 rtl8192du_radiob_2tarray[RADIOB_2T_ARRAYLENGTH] = {
+	0x000, 0x00030000,
+	0x001, 0x00030000,
+	0x002, 0x00000000,
+	0x003, 0x00018c63,
+	0x004, 0x00018c63,
+	0x008, 0x00084000,
+	0x00b, 0x0001c000,
+	0x00e, 0x00018c67,
+	0x00f, 0x00000851,
+	0x014, 0x00021440,
+	0x018, 0x00007401,
+	0x019, 0x00000060,
+	0x01d, 0x000a1290,
+	0x023, 0x00001558,
+	0x01a, 0x00030a99,
+	0x01b, 0x00040b00,
+	0x01c, 0x000fc339,
+	0x03a, 0x000a57eb,
+	0x03b, 0x00020000,
+	0x03c, 0x000ff454,
+	0x020, 0x0000aa52,
+	0x021, 0x00054000,
+	0x040, 0x0000aa52,
+	0x041, 0x00014000,
+	0x025, 0x000803be,
+	0x026, 0x000fc638,
+	0x027, 0x00077c18,
+	0x028, 0x000d1c31,
+	0x029, 0x000d7110,
+	0x02a, 0x000aeb04,
+	0x02b, 0x0004128b,
+	0x02c, 0x00001840,
+	0x043, 0x0002444f,
+	0x044, 0x0001adb0,
+	0x045, 0x00056467,
+	0x046, 0x0008992c,
+	0x047, 0x0000452c,
+	0x048, 0x000f9c43,
+	0x049, 0x00002e0c,
+	0x04a, 0x000546eb,
+	0x04b, 0x0008966c,
+	0x04c, 0x0000dde9,
+	0x018, 0x00007401,
+	0x000, 0x00070000,
+	0x012, 0x000dc000,
+	0x012, 0x00090000,
+	0x012, 0x00051000,
+	0x012, 0x00012000,
+	0x013, 0x000287b7,
+	0x013, 0x000247ab,
+	0x013, 0x0002079f,
+	0x013, 0x0001c793,
+	0x013, 0x0001839b,
+	0x013, 0x00014392,
+	0x013, 0x0001019a,
+	0x013, 0x0000c191,
+	0x013, 0x00008194,
+	0x013, 0x000040a0,
+	0x013, 0x00000018,
+	0x015, 0x0000f424,
+	0x015, 0x0004f424,
+	0x015, 0x0008f424,
+	0x016, 0x000e1330,
+	0x016, 0x000a1330,
+	0x016, 0x00061330,
+	0x016, 0x00021330,
+	0x018, 0x00017524,
+	0x000, 0x00070000,
+	0x012, 0x000cf000,
+	0x012, 0x000bc000,
+	0x012, 0x00078000,
+	0x012, 0x00000000,
+	0x013, 0x000287bc,
+	0x013, 0x000247b0,
+	0x013, 0x000203b4,
+	0x013, 0x0001c3a8,
+	0x013, 0x000181b4,
+	0x013, 0x000141a8,
+	0x013, 0x000100b4,
+	0x013, 0x0000c0a8,
+	0x013, 0x0000b030,
+	0x013, 0x00004024,
+	0x013, 0x00000018,
+	0x015, 0x0000f4c3,
+	0x015, 0x0004f4c3,
+	0x015, 0x0008f4c3,
+	0x016, 0x000e085f,
+	0x016, 0x000a085f,
+	0x016, 0x0006085f,
+	0x016, 0x0002085f,
+	0x018, 0x00037524,
+	0x000, 0x00070000,
+	0x012, 0x000cf000,
+	0x012, 0x000bc000,
+	0x012, 0x00078000,
+	0x012, 0x00000000,
+	0x013, 0x000287bc,
+	0x013, 0x000247b0,
+	0x013, 0x000203b4,
+	0x013, 0x0001c3a8,
+	0x013, 0x000181b4,
+	0x013, 0x000141a8,
+	0x013, 0x000100b4,
+	0x013, 0x0000c0a8,
+	0x013, 0x0000b030,
+	0x013, 0x00004024,
+	0x013, 0x00000018,
+	0x015, 0x0000f4c3,
+	0x015, 0x0004f4c3,
+	0x015, 0x0008f4c3,
+	0x016, 0x000e085f,
+	0x016, 0x000a085f,
+	0x016, 0x0006085f,
+	0x016, 0x0002085f,
+	0x018, 0x00057524,
+	0x000, 0x00070000,
+	0x012, 0x000cf000,
+	0x012, 0x000bc000,
+	0x012, 0x00078000,
+	0x012, 0x00000000,
+	0x013, 0x000287bc,
+	0x013, 0x000247b0,
+	0x013, 0x000203b4,
+	0x013, 0x0001c3a8,
+	0x013, 0x000181b4,
+	0x013, 0x000141a8,
+	0x013, 0x000100b4,
+	0x013, 0x0000c0a8,
+	0x013, 0x0000b030,
+	0x013, 0x00004024,
+	0x013, 0x00000018,
+	0x015, 0x0000f4c3,
+	0x015, 0x0004f4c3,
+	0x015, 0x0008f4c3,
+	0x016, 0x000e085f,
+	0x016, 0x000a085f,
+	0x016, 0x0006085f,
+	0x016, 0x0002085f,
+	0x030, 0x0004470f,
+	0x031, 0x00044ff0,
+	0x032, 0x00000070,
+	0x033, 0x000dd480,
+	0x034, 0x000ffac0,
+	0x035, 0x000b80c0,
+	0x036, 0x00077000,
+	0x037, 0x00064ff2,
+	0x038, 0x000e7661,
+	0x039, 0x00000e90,
+	0x000, 0x00030000,
+	0x018, 0x0000f401,
+	0x0fe, 0x00000000,
+	0x0fe, 0x00000000,
+	0x01e, 0x00088009,
+	0x01f, 0x00080003,
+	0x0fe, 0x00000000,
+	0x01e, 0x00088001,
+	0x01f, 0x00080000,
+	0x0fe, 0x00000000,
+	0x018, 0x00087401,
+	0x0fe, 0x00000000,
+	0x0fe, 0x00000000,
+	0x0fe, 0x00000000,
+	0x02b, 0x00041289,
+	0x0fe, 0x00000000,
+	0x02d, 0x00066666,
+	0x02e, 0x00064001,
+	0x02d, 0x00091111,
+	0x02e, 0x00014002,
+	0x02d, 0x000bbbbb,
+	0x02e, 0x000b4003,
+	0x02d, 0x000e6666,
+	0x02e, 0x00064004,
+	0x02d, 0x00088888,
+	0x02e, 0x00084005,
+	0x02d, 0x0009dddd,
+	0x02e, 0x000d4006,
+	0x02d, 0x000b3333,
+	0x02e, 0x00034007,
+	0x02d, 0x00048888,
+	0x02e, 0x00084408,
+	0x02d, 0x000bbbbb,
+	0x02e, 0x000b4409,
+	0x02d, 0x000e6666,
+	0x02e, 0x0006440a,
+	0x02d, 0x00011111,
+	0x02e, 0x0001480b,
+	0x02d, 0x0003bbbb,
+	0x02e, 0x000b480c,
+	0x02d, 0x00066666,
+	0x02e, 0x0006480d,
+	0x02d, 0x000ccccc,
+	0x02e, 0x000c480e,
+};
+
+const u32 rtl8192du_radioa_2t_int_paarray[RADIOA_2T_INT_PA_ARRAYLENGTH] = {
+	0x000, 0x00030000,
+	0x001, 0x00030000,
+	0x002, 0x00000000,
+	0x003, 0x00018c63,
+	0x004, 0x00018c63,
+	0x008, 0x00084000,
+	0x00b, 0x0001c000,
+	0x00e, 0x00018c67,
+	0x00f, 0x00000851,
+	0x014, 0x00021440,
+	0x018, 0x00017524,
+	0x019, 0x00000000,
+	0x01d, 0x000a1290,
+	0x023, 0x00001558,
+	0x01a, 0x00030a99,
+	0x01b, 0x00040b00,
+	0x01c, 0x000fc339,
+	0x03a, 0x000a57eb,
+	0x03b, 0x00020000,
+	0x03c, 0x000ff455,
+	0x020, 0x0000aa52,
+	0x021, 0x00054000,
+	0x040, 0x0000aa52,
+	0x041, 0x00014000,
+	0x025, 0x000803be,
+	0x026, 0x000fc638,
+	0x027, 0x00077c18,
+	0x028, 0x000de471,
+	0x029, 0x000d7110,
+	0x02a, 0x0008eb04,
+	0x02b, 0x0004128b,
+	0x02c, 0x00001840,
+	0x043, 0x0002444f,
+	0x044, 0x0001adb0,
+	0x045, 0x00056467,
+	0x046, 0x0008992c,
+	0x047, 0x0000452c,
+	0x048, 0x000c0443,
+	0x049, 0x00000730,
+	0x04a, 0x00050f0f,
+	0x04b, 0x000896ef,
+	0x04c, 0x0000ddee,
+	0x018, 0x00007401,
+	0x000, 0x00070000,
+	0x012, 0x000dc000,
+	0x012, 0x00090000,
+	0x012, 0x00051000,
+	0x012, 0x00012000,
+	0x013, 0x000287b7,
+	0x013, 0x000247ab,
+	0x013, 0x0002079f,
+	0x013, 0x0001c793,
+	0x013, 0x0001839b,
+	0x013, 0x00014392,
+	0x013, 0x0001019a,
+	0x013, 0x0000c191,
+	0x013, 0x00008194,
+	0x013, 0x000040a0,
+	0x013, 0x00000018,
+	0x015, 0x0000f424,
+	0x015, 0x0004f424,
+	0x015, 0x0008f424,
+	0x016, 0x000e1330,
+	0x016, 0x000a1330,
+	0x016, 0x00061330,
+	0x016, 0x00021330,
+	0x018, 0x00017524,
+	0x000, 0x00070000,
+	0x012, 0x000cf000,
+	0x012, 0x000bc000,
+	0x012, 0x00078000,
+	0x012, 0x00000000,
+	0x013, 0x000287bf,
+	0x013, 0x000247b3,
+	0x013, 0x000207a7,
+	0x013, 0x0001c79b,
+	0x013, 0x0001839f,
+	0x013, 0x00014393,
+	0x013, 0x00010399,
+	0x013, 0x0000c38d,
+	0x013, 0x00008199,
+	0x013, 0x0000418d,
+	0x013, 0x00000099,
+	0x015, 0x0000f495,
+	0x015, 0x0004f495,
+	0x015, 0x0008f495,
+	0x016, 0x000e1874,
+	0x016, 0x000a1874,
+	0x016, 0x00061874,
+	0x016, 0x00021874,
+	0x018, 0x00037564,
+	0x000, 0x00070000,
+	0x012, 0x000cf000,
+	0x012, 0x000bc000,
+	0x012, 0x00078000,
+	0x012, 0x00000000,
+	0x013, 0x000287bf,
+	0x013, 0x000247b3,
+	0x013, 0x000207a7,
+	0x013, 0x0001c79b,
+	0x013, 0x0001839f,
+	0x013, 0x00014393,
+	0x013, 0x00010399,
+	0x013, 0x0000c38d,
+	0x013, 0x00008199,
+	0x013, 0x0000418d,
+	0x013, 0x00000099,
+	0x015, 0x0000f495,
+	0x015, 0x0004f495,
+	0x015, 0x0008f495,
+	0x016, 0x000e1874,
+	0x016, 0x000a1874,
+	0x016, 0x00061874,
+	0x016, 0x00021874,
+	0x018, 0x00057595,
+	0x000, 0x00070000,
+	0x012, 0x000cf000,
+	0x012, 0x000bc000,
+	0x012, 0x00078000,
+	0x012, 0x00000000,
+	0x013, 0x000287bf,
+	0x013, 0x000247b3,
+	0x013, 0x000207a7,
+	0x013, 0x0001c79b,
+	0x013, 0x0001839f,
+	0x013, 0x00014393,
+	0x013, 0x00010399,
+	0x013, 0x0000c38d,
+	0x013, 0x00008199,
+	0x013, 0x0000418d,
+	0x013, 0x00000099,
+	0x015, 0x0000f495,
+	0x015, 0x0004f495,
+	0x015, 0x0008f495,
+	0x016, 0x000e1874,
+	0x016, 0x000a1874,
+	0x016, 0x00061874,
+	0x016, 0x00021874,
+	0x030, 0x0004470f,
+	0x031, 0x00044ff0,
+	0x032, 0x00000070,
+	0x033, 0x000dd480,
+	0x034, 0x000ffac0,
+	0x035, 0x000b80c0,
+	0x036, 0x00077000,
+	0x037, 0x00064ff2,
+	0x038, 0x000e7661,
+	0x039, 0x00000e90,
+	0x000, 0x00030000,
+	0x018, 0x0000f401,
+	0x0fe, 0x00000000,
+	0x0fe, 0x00000000,
+	0x01e, 0x00088009,
+	0x01f, 0x00080003,
+	0x0fe, 0x00000000,
+	0x01e, 0x00088001,
+	0x01f, 0x00080000,
+	0x0fe, 0x00000000,
+	0x018, 0x00097524,
+	0x0fe, 0x00000000,
+	0x0fe, 0x00000000,
+	0x0fe, 0x00000000,
+	0x0fe, 0x00000000,
+	0x02b, 0x00041289,
+	0x0fe, 0x00000000,
+	0x02d, 0x0006aaaa,
+	0x02e, 0x000b4d01,
+	0x02d, 0x00080000,
+	0x02e, 0x00004d02,
+	0x02d, 0x00095555,
+	0x02e, 0x00054d03,
+	0x02d, 0x000aaaaa,
+	0x02e, 0x000b4d04,
+	0x02d, 0x000c0000,
+	0x02e, 0x00004d05,
+	0x02d, 0x000d5555,
+	0x02e, 0x00054d06,
+	0x02d, 0x000eaaaa,
+	0x02e, 0x000b4d07,
+	0x02d, 0x00000000,
+	0x02e, 0x00005108,
+	0x02d, 0x00015555,
+	0x02e, 0x00055109,
+	0x02d, 0x0002aaaa,
+	0x02e, 0x000b510a,
+	0x02d, 0x00040000,
+	0x02e, 0x0000510b,
+	0x02d, 0x00055555,
+	0x02e, 0x0005510c,
+};
+
+const u32 rtl8192du_radiob_2t_int_paarray[RADIOB_2T_INT_PA_ARRAYLENGTH] = {
+	0x000, 0x00030000,
+	0x001, 0x00030000,
+	0x002, 0x00000000,
+	0x003, 0x00018c63,
+	0x004, 0x00018c63,
+	0x008, 0x00084000,
+	0x00b, 0x0001c000,
+	0x00e, 0x00018c67,
+	0x00f, 0x00000851,
+	0x014, 0x00021440,
+	0x018, 0x00007401,
+	0x019, 0x00000060,
+	0x01d, 0x000a1290,
+	0x023, 0x00001558,
+	0x01a, 0x00030a99,
+	0x01b, 0x00040b00,
+	0x01c, 0x000fc339,
+	0x03a, 0x000a57eb,
+	0x03b, 0x00020000,
+	0x03c, 0x000ff455,
+	0x020, 0x0000aa52,
+	0x021, 0x00054000,
+	0x040, 0x0000aa52,
+	0x041, 0x00014000,
+	0x025, 0x000803be,
+	0x026, 0x000fc638,
+	0x027, 0x00077c18,
+	0x028, 0x000d1c31,
+	0x029, 0x000d7110,
+	0x02a, 0x000aeb04,
+	0x02b, 0x0004128b,
+	0x02c, 0x00001840,
+	0x043, 0x0002444f,
+	0x044, 0x0001adb0,
+	0x045, 0x00056467,
+	0x046, 0x0008992c,
+	0x047, 0x0000452c,
+	0x048, 0x000c0443,
+	0x049, 0x00000730,
+	0x04a, 0x00050f0f,
+	0x04b, 0x000896ef,
+	0x04c, 0x0000ddee,
+	0x018, 0x00007401,
+	0x000, 0x00070000,
+	0x012, 0x000dc000,
+	0x012, 0x00090000,
+	0x012, 0x00051000,
+	0x012, 0x00012000,
+	0x013, 0x000287b7,
+	0x013, 0x000247ab,
+	0x013, 0x0002079f,
+	0x013, 0x0001c793,
+	0x013, 0x0001839b,
+	0x013, 0x00014392,
+	0x013, 0x0001019a,
+	0x013, 0x0000c191,
+	0x013, 0x00008194,
+	0x013, 0x000040a0,
+	0x013, 0x00000018,
+	0x015, 0x0000f424,
+	0x015, 0x0004f424,
+	0x015, 0x0008f424,
+	0x016, 0x000e1330,
+	0x016, 0x000a1330,
+	0x016, 0x00061330,
+	0x016, 0x00021330,
+	0x018, 0x00017524,
+	0x000, 0x00070000,
+	0x012, 0x000cf000,
+	0x012, 0x000bc000,
+	0x012, 0x00078000,
+	0x012, 0x00000000,
+	0x013, 0x000287bf,
+	0x013, 0x000247b3,
+	0x013, 0x000207a7,
+	0x013, 0x0001c79b,
+	0x013, 0x0001839f,
+	0x013, 0x00014393,
+	0x013, 0x00010399,
+	0x013, 0x0000c38d,
+	0x013, 0x00008199,
+	0x013, 0x0000418d,
+	0x013, 0x00000099,
+	0x015, 0x0000f495,
+	0x015, 0x0004f495,
+	0x015, 0x0008f495,
+	0x016, 0x000e1874,
+	0x016, 0x000a1874,
+	0x016, 0x00061874,
+	0x016, 0x00021874,
+	0x018, 0x00037564,
+	0x000, 0x00070000,
+	0x012, 0x000cf000,
+	0x012, 0x000bc000,
+	0x012, 0x00078000,
+	0x012, 0x00000000,
+	0x013, 0x000287bf,
+	0x013, 0x000247b3,
+	0x013, 0x000207a7,
+	0x013, 0x0001c79b,
+	0x013, 0x0001839f,
+	0x013, 0x00014393,
+	0x013, 0x00010399,
+	0x013, 0x0000c38d,
+	0x013, 0x00008199,
+	0x013, 0x0000418d,
+	0x013, 0x00000099,
+	0x015, 0x0000f495,
+	0x015, 0x0004f495,
+	0x015, 0x0008f495,
+	0x016, 0x000e1874,
+	0x016, 0x000a1874,
+	0x016, 0x00061874,
+	0x016, 0x00021874,
+	0x018, 0x00057595,
+	0x000, 0x00070000,
+	0x012, 0x000cf000,
+	0x012, 0x000bc000,
+	0x012, 0x00078000,
+	0x012, 0x00000000,
+	0x013, 0x000287bf,
+	0x013, 0x000247b3,
+	0x013, 0x000207a7,
+	0x013, 0x0001c79b,
+	0x013, 0x0001839f,
+	0x013, 0x00014393,
+	0x013, 0x00010399,
+	0x013, 0x0000c38d,
+	0x013, 0x00008199,
+	0x013, 0x0000418d,
+	0x013, 0x00000099,
+	0x015, 0x0000f495,
+	0x015, 0x0004f495,
+	0x015, 0x0008f495,
+	0x016, 0x000e1874,
+	0x016, 0x000a1874,
+	0x016, 0x00061874,
+	0x016, 0x00021874,
+	0x030, 0x0004470f,
+	0x031, 0x00044ff0,
+	0x032, 0x00000070,
+	0x033, 0x000dd480,
+	0x034, 0x000ffac0,
+	0x035, 0x000b80c0,
+	0x036, 0x00077000,
+	0x037, 0x00064ff2,
+	0x038, 0x000e7661,
+	0x039, 0x00000e90,
+	0x000, 0x00030000,
+	0x018, 0x0000f401,
+	0x0fe, 0x00000000,
+	0x0fe, 0x00000000,
+	0x01e, 0x00088009,
+	0x01f, 0x00080003,
+	0x0fe, 0x00000000,
+	0x01e, 0x00088001,
+	0x01f, 0x00080000,
+	0x0fe, 0x00000000,
+	0x018, 0x00087401,
+	0x0fe, 0x00000000,
+	0x0fe, 0x00000000,
+	0x0fe, 0x00000000,
+	0x02b, 0x00041289,
+	0x0fe, 0x00000000,
+	0x02d, 0x00066666,
+	0x02e, 0x00064001,
+	0x02d, 0x00091111,
+	0x02e, 0x00014002,
+	0x02d, 0x000bbbbb,
+	0x02e, 0x000b4003,
+	0x02d, 0x000e6666,
+	0x02e, 0x00064004,
+	0x02d, 0x00088888,
+	0x02e, 0x00084005,
+	0x02d, 0x0009dddd,
+	0x02e, 0x000d4006,
+	0x02d, 0x000b3333,
+	0x02e, 0x00034007,
+	0x02d, 0x00048888,
+	0x02e, 0x00084408,
+	0x02d, 0x000bbbbb,
+	0x02e, 0x000b4409,
+	0x02d, 0x000e6666,
+	0x02e, 0x0006440a,
+	0x02d, 0x00011111,
+	0x02e, 0x0001480b,
+	0x02d, 0x0003bbbb,
+	0x02e, 0x000b480c,
+	0x02d, 0x00066666,
+	0x02e, 0x0006480d,
+	0x02d, 0x000ccccc,
+	0x02e, 0x000c480e,
+};
+
+const u32 rtl8192du_mac_2tarray[MAC_2T_ARRAYLENGTH] = {
+	0x420, 0x00000080,
+	0x423, 0x00000000,
+	0x430, 0x00000000,
+	0x431, 0x00000000,
+	0x432, 0x00000000,
+	0x433, 0x00000001,
+	0x434, 0x00000004,
+	0x435, 0x00000005,
+	0x436, 0x00000006,
+	0x437, 0x00000007,
+	0x438, 0x00000000,
+	0x439, 0x00000000,
+	0x43a, 0x00000000,
+	0x43b, 0x00000001,
+	0x43c, 0x00000004,
+	0x43d, 0x00000005,
+	0x43e, 0x00000006,
+	0x43f, 0x00000007,
+	0x440, 0x00000050,
+	0x441, 0x00000001,
+	0x442, 0x00000000,
+	0x444, 0x00000015,
+	0x445, 0x000000f0,
+	0x446, 0x0000000f,
+	0x447, 0x00000000,
+	0x462, 0x00000008,
+	0x463, 0x00000003,
+	0x4c8, 0x000000ff,
+	0x4c9, 0x00000008,
+	0x4cc, 0x000000ff,
+	0x4cd, 0x000000ff,
+	0x4ce, 0x00000001,
+	0x500, 0x00000026,
+	0x501, 0x000000a2,
+	0x502, 0x0000002f,
+	0x503, 0x00000000,
+	0x504, 0x00000028,
+	0x505, 0x000000a3,
+	0x506, 0x0000005e,
+	0x507, 0x00000000,
+	0x508, 0x0000002b,
+	0x509, 0x000000a4,
+	0x50a, 0x0000005e,
+	0x50b, 0x00000000,
+	0x50c, 0x0000004f,
+	0x50d, 0x000000a4,
+	0x50e, 0x00000000,
+	0x50f, 0x00000000,
+	0x512, 0x0000001c,
+	0x514, 0x0000000a,
+	0x515, 0x00000010,
+	0x516, 0x0000000a,
+	0x517, 0x00000010,
+	0x51a, 0x00000016,
+	0x524, 0x0000000f,
+	0x525, 0x0000004f,
+	0x546, 0x00000040,
+	0x547, 0x00000000,
+	0x550, 0x00000010,
+	0x551, 0x00000010,
+	0x559, 0x00000002,
+	0x55a, 0x00000002,
+	0x55d, 0x000000ff,
+	0x605, 0x00000080,
+	0x608, 0x0000000e,
+	0x609, 0x0000002a,
+	0x652, 0x00000020,
+	0x63c, 0x0000000a,
+	0x63d, 0x0000000a,
+	0x63e, 0x0000000e,
+	0x63f, 0x0000000e,
+	0x66e, 0x00000005,
+	0x700, 0x00000021,
+	0x701, 0x00000043,
+	0x702, 0x00000065,
+	0x703, 0x00000087,
+	0x708, 0x00000021,
+	0x709, 0x00000043,
+	0x70a, 0x00000065,
+	0x70b, 0x00000087,
+	0x024, 0x0000000d,
+	0x025, 0x00000080,
+	0x026, 0x00000011,
+	0x027, 0x00000000,
+	0x028, 0x00000083,
+	0x029, 0x000000db,
+	0x02a, 0x000000ff,
+	0x02b, 0x00000000,
+	0x014, 0x00000055,
+	0x015, 0x000000a9,
+	0x016, 0x0000008b,
+	0x017, 0x00000008,
+	0x010, 0x00000003,
+	0x011, 0x0000002b,
+	0x012, 0x00000002,
+	0x013, 0x00000049,
+};
+
+const u32 rtl8192du_agctab_array[AGCTAB_ARRAYLENGTH] = {
+	0xc78, 0x7b000001,
+	0xc78, 0x7b010001,
+	0xc78, 0x7b020001,
+	0xc78, 0x7b030001,
+	0xc78, 0x7b040001,
+	0xc78, 0x7b050001,
+	0xc78, 0x7b060001,
+	0xc78, 0x7a070001,
+	0xc78, 0x79080001,
+	0xc78, 0x78090001,
+	0xc78, 0x770a0001,
+	0xc78, 0x760b0001,
+	0xc78, 0x750c0001,
+	0xc78, 0x740d0001,
+	0xc78, 0x730e0001,
+	0xc78, 0x720f0001,
+	0xc78, 0x71100001,
+	0xc78, 0x70110001,
+	0xc78, 0x6f120001,
+	0xc78, 0x6e130001,
+	0xc78, 0x6d140001,
+	0xc78, 0x6c150001,
+	0xc78, 0x6b160001,
+	0xc78, 0x6a170001,
+	0xc78, 0x69180001,
+	0xc78, 0x68190001,
+	0xc78, 0x671a0001,
+	0xc78, 0x661b0001,
+	0xc78, 0x651c0001,
+	0xc78, 0x641d0001,
+	0xc78, 0x631e0001,
+	0xc78, 0x621f0001,
+	0xc78, 0x61200001,
+	0xc78, 0x60210001,
+	0xc78, 0x49220001,
+	0xc78, 0x48230001,
+	0xc78, 0x47240001,
+	0xc78, 0x46250001,
+	0xc78, 0x45260001,
+	0xc78, 0x44270001,
+	0xc78, 0x43280001,
+	0xc78, 0x42290001,
+	0xc78, 0x412a0001,
+	0xc78, 0x402b0001,
+	0xc78, 0x262c0001,
+	0xc78, 0x252d0001,
+	0xc78, 0x242e0001,
+	0xc78, 0x232f0001,
+	0xc78, 0x22300001,
+	0xc78, 0x21310001,
+	0xc78, 0x20320001,
+	0xc78, 0x06330001,
+	0xc78, 0x05340001,
+	0xc78, 0x04350001,
+	0xc78, 0x03360001,
+	0xc78, 0x02370001,
+	0xc78, 0x01380001,
+	0xc78, 0x00390001,
+	0xc78, 0x003a0001,
+	0xc78, 0x003b0001,
+	0xc78, 0x003c0001,
+	0xc78, 0x003d0001,
+	0xc78, 0x003e0001,
+	0xc78, 0x003f0001,
+	0xc78, 0x7b400001,
+	0xc78, 0x7b410001,
+	0xc78, 0x7a420001,
+	0xc78, 0x79430001,
+	0xc78, 0x78440001,
+	0xc78, 0x77450001,
+	0xc78, 0x76460001,
+	0xc78, 0x75470001,
+	0xc78, 0x74480001,
+	0xc78, 0x73490001,
+	0xc78, 0x724a0001,
+	0xc78, 0x714b0001,
+	0xc78, 0x704c0001,
+	0xc78, 0x6f4d0001,
+	0xc78, 0x6e4e0001,
+	0xc78, 0x6d4f0001,
+	0xc78, 0x6c500001,
+	0xc78, 0x6b510001,
+	0xc78, 0x6a520001,
+	0xc78, 0x69530001,
+	0xc78, 0x68540001,
+	0xc78, 0x67550001,
+	0xc78, 0x66560001,
+	0xc78, 0x65570001,
+	0xc78, 0x64580001,
+	0xc78, 0x63590001,
+	0xc78, 0x625a0001,
+	0xc78, 0x615b0001,
+	0xc78, 0x605c0001,
+	0xc78, 0x485d0001,
+	0xc78, 0x475e0001,
+	0xc78, 0x465f0001,
+	0xc78, 0x45600001,
+	0xc78, 0x44610001,
+	0xc78, 0x43620001,
+	0xc78, 0x42630001,
+	0xc78, 0x41640001,
+	0xc78, 0x40650001,
+	0xc78, 0x27660001,
+	0xc78, 0x26670001,
+	0xc78, 0x25680001,
+	0xc78, 0x24690001,
+	0xc78, 0x236a0001,
+	0xc78, 0x226b0001,
+	0xc78, 0x216c0001,
+	0xc78, 0x206d0001,
+	0xc78, 0x206e0001,
+	0xc78, 0x206f0001,
+	0xc78, 0x20700001,
+	0xc78, 0x20710001,
+	0xc78, 0x20720001,
+	0xc78, 0x20730001,
+	0xc78, 0x20740001,
+	0xc78, 0x20750001,
+	0xc78, 0x20760001,
+	0xc78, 0x20770001,
+	0xc78, 0x20780001,
+	0xc78, 0x20790001,
+	0xc78, 0x207a0001,
+	0xc78, 0x207b0001,
+	0xc78, 0x207c0001,
+	0xc78, 0x207d0001,
+	0xc78, 0x207e0001,
+	0xc78, 0x207f0001,
+	0xc78, 0x38000002,
+	0xc78, 0x38010002,
+	0xc78, 0x38020002,
+	0xc78, 0x38030002,
+	0xc78, 0x38040002,
+	0xc78, 0x38050002,
+	0xc78, 0x38060002,
+	0xc78, 0x38070002,
+	0xc78, 0x38080002,
+	0xc78, 0x3c090002,
+	0xc78, 0x3e0a0002,
+	0xc78, 0x400b0002,
+	0xc78, 0x440c0002,
+	0xc78, 0x480d0002,
+	0xc78, 0x4c0e0002,
+	0xc78, 0x500f0002,
+	0xc78, 0x52100002,
+	0xc78, 0x56110002,
+	0xc78, 0x5a120002,
+	0xc78, 0x5e130002,
+	0xc78, 0x60140002,
+	0xc78, 0x60150002,
+	0xc78, 0x60160002,
+	0xc78, 0x62170002,
+	0xc78, 0x62180002,
+	0xc78, 0x62190002,
+	0xc78, 0x621a0002,
+	0xc78, 0x621b0002,
+	0xc78, 0x621c0002,
+	0xc78, 0x621d0002,
+	0xc78, 0x621e0002,
+	0xc78, 0x621f0002,
+	0xc78, 0x32000044,
+	0xc78, 0x32010044,
+	0xc78, 0x32020044,
+	0xc78, 0x32030044,
+	0xc78, 0x32040044,
+	0xc78, 0x32050044,
+	0xc78, 0x32060044,
+	0xc78, 0x34070044,
+	0xc78, 0x35080044,
+	0xc78, 0x36090044,
+	0xc78, 0x370a0044,
+	0xc78, 0x380b0044,
+	0xc78, 0x390c0044,
+	0xc78, 0x3a0d0044,
+	0xc78, 0x3e0e0044,
+	0xc78, 0x420f0044,
+	0xc78, 0x44100044,
+	0xc78, 0x46110044,
+	0xc78, 0x4a120044,
+	0xc78, 0x4e130044,
+	0xc78, 0x50140044,
+	0xc78, 0x55150044,
+	0xc78, 0x5a160044,
+	0xc78, 0x5e170044,
+	0xc78, 0x64180044,
+	0xc78, 0x6e190044,
+	0xc78, 0x6e1a0044,
+	0xc78, 0x6e1b0044,
+	0xc78, 0x6e1c0044,
+	0xc78, 0x6e1d0044,
+	0xc78, 0x6e1e0044,
+	0xc78, 0x6e1f0044,
+	0xc78, 0x6e1f0000,
+};
+
+const u32 rtl8192du_agctab_5garray[AGCTAB_5G_ARRAYLENGTH] = {
+	0xc78, 0x7b000001,
+	0xc78, 0x7b010001,
+	0xc78, 0x7a020001,
+	0xc78, 0x79030001,
+	0xc78, 0x78040001,
+	0xc78, 0x77050001,
+	0xc78, 0x76060001,
+	0xc78, 0x75070001,
+	0xc78, 0x74080001,
+	0xc78, 0x73090001,
+	0xc78, 0x720a0001,
+	0xc78, 0x710b0001,
+	0xc78, 0x700c0001,
+	0xc78, 0x6f0d0001,
+	0xc78, 0x6e0e0001,
+	0xc78, 0x6d0f0001,
+	0xc78, 0x6c100001,
+	0xc78, 0x6b110001,
+	0xc78, 0x6a120001,
+	0xc78, 0x69130001,
+	0xc78, 0x68140001,
+	0xc78, 0x67150001,
+	0xc78, 0x66160001,
+	0xc78, 0x65170001,
+	0xc78, 0x64180001,
+	0xc78, 0x63190001,
+	0xc78, 0x621a0001,
+	0xc78, 0x611b0001,
+	0xc78, 0x601c0001,
+	0xc78, 0x481d0001,
+	0xc78, 0x471e0001,
+	0xc78, 0x461f0001,
+	0xc78, 0x45200001,
+	0xc78, 0x44210001,
+	0xc78, 0x43220001,
+	0xc78, 0x42230001,
+	0xc78, 0x41240001,
+	0xc78, 0x40250001,
+	0xc78, 0x27260001,
+	0xc78, 0x26270001,
+	0xc78, 0x25280001,
+	0xc78, 0x24290001,
+	0xc78, 0x232a0001,
+	0xc78, 0x222b0001,
+	0xc78, 0x212c0001,
+	0xc78, 0x202d0001,
+	0xc78, 0x202e0001,
+	0xc78, 0x202f0001,
+	0xc78, 0x20300001,
+	0xc78, 0x20310001,
+	0xc78, 0x20320001,
+	0xc78, 0x20330001,
+	0xc78, 0x20340001,
+	0xc78, 0x20350001,
+	0xc78, 0x20360001,
+	0xc78, 0x20370001,
+	0xc78, 0x20380001,
+	0xc78, 0x20390001,
+	0xc78, 0x203a0001,
+	0xc78, 0x203b0001,
+	0xc78, 0x203c0001,
+	0xc78, 0x203d0001,
+	0xc78, 0x203e0001,
+	0xc78, 0x203f0001,
+	0xc78, 0x32000044,
+	0xc78, 0x32010044,
+	0xc78, 0x32020044,
+	0xc78, 0x32030044,
+	0xc78, 0x32040044,
+	0xc78, 0x32050044,
+	0xc78, 0x32060044,
+	0xc78, 0x34070044,
+	0xc78, 0x35080044,
+	0xc78, 0x36090044,
+	0xc78, 0x370a0044,
+	0xc78, 0x380b0044,
+	0xc78, 0x390c0044,
+	0xc78, 0x3a0d0044,
+	0xc78, 0x3e0e0044,
+	0xc78, 0x420f0044,
+	0xc78, 0x44100044,
+	0xc78, 0x46110044,
+	0xc78, 0x4a120044,
+	0xc78, 0x4e130044,
+	0xc78, 0x50140044,
+	0xc78, 0x55150044,
+	0xc78, 0x5a160044,
+	0xc78, 0x5e170044,
+	0xc78, 0x64180044,
+	0xc78, 0x6e190044,
+	0xc78, 0x6e1a0044,
+	0xc78, 0x6e1b0044,
+	0xc78, 0x6e1c0044,
+	0xc78, 0x6e1d0044,
+	0xc78, 0x6e1e0044,
+	0xc78, 0x6e1f0044,
+	0xc78, 0x6e1f0000,
+};
+
+const u32 rtl8192du_agctab_2garray[AGCTAB_2G_ARRAYLENGTH] = {
+	0xc78, 0x7b000001,
+	0xc78, 0x7b010001,
+	0xc78, 0x7b020001,
+	0xc78, 0x7b030001,
+	0xc78, 0x7b040001,
+	0xc78, 0x7b050001,
+	0xc78, 0x7b060001,
+	0xc78, 0x7a070001,
+	0xc78, 0x79080001,
+	0xc78, 0x78090001,
+	0xc78, 0x770a0001,
+	0xc78, 0x760b0001,
+	0xc78, 0x750c0001,
+	0xc78, 0x740d0001,
+	0xc78, 0x730e0001,
+	0xc78, 0x720f0001,
+	0xc78, 0x71100001,
+	0xc78, 0x70110001,
+	0xc78, 0x6f120001,
+	0xc78, 0x6e130001,
+	0xc78, 0x6d140001,
+	0xc78, 0x6c150001,
+	0xc78, 0x6b160001,
+	0xc78, 0x6a170001,
+	0xc78, 0x69180001,
+	0xc78, 0x68190001,
+	0xc78, 0x671a0001,
+	0xc78, 0x661b0001,
+	0xc78, 0x651c0001,
+	0xc78, 0x641d0001,
+	0xc78, 0x631e0001,
+	0xc78, 0x621f0001,
+	0xc78, 0x61200001,
+	0xc78, 0x60210001,
+	0xc78, 0x49220001,
+	0xc78, 0x48230001,
+	0xc78, 0x47240001,
+	0xc78, 0x46250001,
+	0xc78, 0x45260001,
+	0xc78, 0x44270001,
+	0xc78, 0x43280001,
+	0xc78, 0x42290001,
+	0xc78, 0x412a0001,
+	0xc78, 0x402b0001,
+	0xc78, 0x262c0001,
+	0xc78, 0x252d0001,
+	0xc78, 0x242e0001,
+	0xc78, 0x232f0001,
+	0xc78, 0x22300001,
+	0xc78, 0x21310001,
+	0xc78, 0x20320001,
+	0xc78, 0x06330001,
+	0xc78, 0x05340001,
+	0xc78, 0x04350001,
+	0xc78, 0x03360001,
+	0xc78, 0x02370001,
+	0xc78, 0x01380001,
+	0xc78, 0x00390001,
+	0xc78, 0x003a0001,
+	0xc78, 0x003b0001,
+	0xc78, 0x003c0001,
+	0xc78, 0x003d0001,
+	0xc78, 0x003e0001,
+	0xc78, 0x003f0001,
+	0xc78, 0x38000002,
+	0xc78, 0x38010002,
+	0xc78, 0x38020002,
+	0xc78, 0x38030002,
+	0xc78, 0x38040002,
+	0xc78, 0x38050002,
+	0xc78, 0x38060002,
+	0xc78, 0x38070002,
+	0xc78, 0x38080002,
+	0xc78, 0x3c090002,
+	0xc78, 0x3e0a0002,
+	0xc78, 0x400b0002,
+	0xc78, 0x440c0002,
+	0xc78, 0x480d0002,
+	0xc78, 0x4c0e0002,
+	0xc78, 0x500f0002,
+	0xc78, 0x52100002,
+	0xc78, 0x56110002,
+	0xc78, 0x5a120002,
+	0xc78, 0x5e130002,
+	0xc78, 0x60140002,
+	0xc78, 0x60150002,
+	0xc78, 0x60160002,
+	0xc78, 0x62170002,
+	0xc78, 0x62180002,
+	0xc78, 0x62190002,
+	0xc78, 0x621a0002,
+	0xc78, 0x621b0002,
+	0xc78, 0x621c0002,
+	0xc78, 0x621d0002,
+	0xc78, 0x621e0002,
+	0xc78, 0x621f0002,
+	0xc78, 0x6e1f0000,
+};
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192du/table.h b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/table.h
new file mode 100644
index 0000000000000..b809ba5113201
--- /dev/null
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/table.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2024  Realtek Corporation.*/
+
+#ifndef __RTL92DU_TABLE_H__
+#define __RTL92DU_TABLE_H__
+
+#define PHY_REG_2T_ARRAYLENGTH 372
+#define PHY_REG_ARRAY_PG_LENGTH 624
+#define RADIOA_2T_ARRAYLENGTH 378
+#define RADIOB_2T_ARRAYLENGTH 384
+#define RADIOA_2T_INT_PA_ARRAYLENGTH 378
+#define RADIOB_2T_INT_PA_ARRAYLENGTH 384
+#define MAC_2T_ARRAYLENGTH 192
+#define AGCTAB_ARRAYLENGTH 386
+#define AGCTAB_5G_ARRAYLENGTH 194
+#define AGCTAB_2G_ARRAYLENGTH 194
+
+extern const u32 rtl8192du_phy_reg_2tarray[PHY_REG_2T_ARRAYLENGTH];
+extern const u32 rtl8192du_phy_reg_array_pg[PHY_REG_ARRAY_PG_LENGTH];
+extern const u32 rtl8192du_radioa_2tarray[RADIOA_2T_ARRAYLENGTH];
+extern const u32 rtl8192du_radiob_2tarray[RADIOB_2T_ARRAYLENGTH];
+extern const u32 rtl8192du_radioa_2t_int_paarray[RADIOA_2T_INT_PA_ARRAYLENGTH];
+extern const u32 rtl8192du_radiob_2t_int_paarray[RADIOB_2T_INT_PA_ARRAYLENGTH];
+extern const u32 rtl8192du_mac_2tarray[MAC_2T_ARRAYLENGTH];
+extern const u32 rtl8192du_agctab_array[AGCTAB_ARRAYLENGTH];
+extern const u32 rtl8192du_agctab_5garray[AGCTAB_5G_ARRAYLENGTH];
+extern const u32 rtl8192du_agctab_2garray[AGCTAB_2G_ARRAYLENGTH];
+
+#endif
-- 
GitLab


From dc71f4e142df928747dc5b493faa2c841a400d88 Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Thu, 23 May 2024 17:44:39 +0300
Subject: [PATCH 542/950] wifi: rtlwifi: Add new members to struct rtl_priv for
 RTL8192DU

These are needed for the dual MAC version of RTL8192DU.

The two mutexes are used to avoid concurrent access to the hardware
from the two USB interfaces.

The two arrays are filled by one interface during LC calibration and
accessed by the other interface during channel switching.

Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://msgid.link/d1bf581b-de41-4d09-bf56-768c2fc29dd3@gmail.com
---
 drivers/net/wireless/realtek/rtlwifi/wifi.h | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/wireless/realtek/rtlwifi/wifi.h b/drivers/net/wireless/realtek/rtlwifi/wifi.h
index 442419568734b..6a8212fd36af6 100644
--- a/drivers/net/wireless/realtek/rtlwifi/wifi.h
+++ b/drivers/net/wireless/realtek/rtlwifi/wifi.h
@@ -2746,6 +2746,12 @@ struct rtl_priv {
 	 */
 	bool use_new_trx_flow;
 
+	/* For dual MAC RTL8192DU, things shared by the 2 USB interfaces */
+	u32 *curveindex_2g;
+	u32 *curveindex_5g;
+	struct mutex *mutex_for_power_on_off; /* for power on/off */
+	struct mutex *mutex_for_hw_init; /* for hardware init */
+
 #ifdef CONFIG_PM
 	struct wiphy_wowlan_support wowlan;
 #endif
-- 
GitLab


From e769c67105d35da254a62892111e7dcad93ff3a6 Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Thu, 23 May 2024 17:45:31 +0300
Subject: [PATCH 543/950] wifi: rtlwifi: Add rtl8192du/hw.{c,h}

These contain mostly hardware init/deinit routines for RTL8192DU.

Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://msgid.link/282afe18-f37d-45f7-9275-68c39d1fde09@gmail.com
---
 .../wireless/realtek/rtlwifi/rtl8192du/hw.c   | 1212 +++++++++++++++++
 .../wireless/realtek/rtlwifi/rtl8192du/hw.h   |   22 +
 2 files changed, 1234 insertions(+)
 create mode 100644 drivers/net/wireless/realtek/rtlwifi/rtl8192du/hw.c
 create mode 100644 drivers/net/wireless/realtek/rtlwifi/rtl8192du/hw.h

diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192du/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/hw.c
new file mode 100644
index 0000000000000..700c6e2bcad19
--- /dev/null
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/hw.c
@@ -0,0 +1,1212 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2024  Realtek Corporation.*/
+
+#include "../wifi.h"
+#include "../cam.h"
+#include "../usb.h"
+#include "../rtl8192d/reg.h"
+#include "../rtl8192d/def.h"
+#include "../rtl8192d/dm_common.h"
+#include "../rtl8192d/fw_common.h"
+#include "../rtl8192d/hw_common.h"
+#include "../rtl8192d/phy_common.h"
+#include "phy.h"
+#include "dm.h"
+#include "fw.h"
+#include "hw.h"
+#include "trx.h"
+
+static void _rtl92du_set_bcn_ctrl_reg(struct ieee80211_hw *hw,
+				      u8 set_bits, u8 clear_bits)
+{
+	struct rtl_usb *rtlusb = rtl_usbdev(rtl_usbpriv(hw));
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+
+	rtlusb->reg_bcn_ctrl_val |= set_bits;
+	rtlusb->reg_bcn_ctrl_val &= ~clear_bits;
+	rtl_write_byte(rtlpriv, REG_BCN_CTRL, (u8)rtlusb->reg_bcn_ctrl_val);
+}
+
+static void _rtl92du_enable_bcn_sub_func(struct ieee80211_hw *hw)
+{
+	_rtl92du_set_bcn_ctrl_reg(hw, 0, BIT(1));
+}
+
+static void _rtl92du_disable_bcn_sub_func(struct ieee80211_hw *hw)
+{
+	_rtl92du_set_bcn_ctrl_reg(hw, BIT(1), 0);
+}
+
+void rtl92du_get_hw_reg(struct ieee80211_hw *hw, u8 variable, u8 *val)
+{
+	struct rtl_mac *mac = rtl_mac(rtl_priv(hw));
+
+	switch (variable) {
+	case HW_VAR_RCR:
+		*((u32 *)val) = mac->rx_conf;
+		break;
+	default:
+		rtl92d_get_hw_reg(hw, variable, val);
+		break;
+	}
+}
+
+void rtl92du_set_hw_reg(struct ieee80211_hw *hw, u8 variable, u8 *val)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_mac *mac = rtl_mac(rtlpriv);
+
+	switch (variable) {
+	case HW_VAR_AC_PARAM:
+		rtl92d_dm_init_edca_turbo(hw);
+		break;
+	case HW_VAR_ACM_CTRL: {
+		u8 e_aci = *val;
+		union aci_aifsn *p_aci_aifsn =
+		    (union aci_aifsn *)(&mac->ac[0].aifs);
+		u8 acm = p_aci_aifsn->f.acm;
+		u8 acm_ctrl = rtl_read_byte(rtlpriv, REG_ACMHWCTRL);
+
+		if (acm) {
+			switch (e_aci) {
+			case AC0_BE:
+				acm_ctrl |= ACMHW_BEQEN;
+				break;
+			case AC2_VI:
+				acm_ctrl |= ACMHW_VIQEN;
+				break;
+			case AC3_VO:
+				acm_ctrl |= ACMHW_VOQEN;
+				break;
+			default:
+				rtl_dbg(rtlpriv, COMP_ERR, DBG_WARNING,
+					"HW_VAR_ACM_CTRL acm set failed: eACI is %d\n",
+					acm);
+				break;
+			}
+		} else {
+			switch (e_aci) {
+			case AC0_BE:
+				acm_ctrl &= (~ACMHW_BEQEN);
+				break;
+			case AC2_VI:
+				acm_ctrl &= (~ACMHW_VIQEN);
+				break;
+			case AC3_VO:
+				acm_ctrl &= (~ACMHW_VOQEN);
+				break;
+			default:
+				pr_err("%s:%d switch case %#x not processed\n",
+				       __func__, __LINE__, e_aci);
+				break;
+			}
+		}
+		rtl_dbg(rtlpriv, COMP_QOS, DBG_TRACE,
+			"SetHwReg8190pci(): [HW_VAR_ACM_CTRL] Write 0x%X\n",
+			acm_ctrl);
+		rtl_write_byte(rtlpriv, REG_ACMHWCTRL, acm_ctrl);
+		break;
+	}
+	case HW_VAR_RCR:
+		mac->rx_conf = ((u32 *)val)[0];
+		rtl_write_dword(rtlpriv, REG_RCR, mac->rx_conf);
+		break;
+	case HW_VAR_H2C_FW_JOINBSSRPT: {
+		u8 tmp_regcr, tmp_reg422;
+		bool recover = false;
+		u8 mstatus = *val;
+
+		if (mstatus == RT_MEDIA_CONNECT) {
+			rtlpriv->cfg->ops->set_hw_reg(hw,
+						      HW_VAR_AID, NULL);
+			tmp_regcr = rtl_read_byte(rtlpriv, REG_CR + 1);
+			rtl_write_byte(rtlpriv, REG_CR + 1,
+				       tmp_regcr | ENSWBCN);
+			_rtl92du_set_bcn_ctrl_reg(hw, 0, EN_BCN_FUNCTION);
+			_rtl92du_set_bcn_ctrl_reg(hw, DIS_TSF_UDT, 0);
+			tmp_reg422 = rtl_read_byte(rtlpriv,
+						   REG_FWHW_TXQ_CTRL + 2);
+			if (tmp_reg422 & (EN_BCNQ_DL >> 16))
+				recover = true;
+			rtl_write_byte(rtlpriv, REG_FWHW_TXQ_CTRL + 2,
+				       tmp_reg422 & ~(EN_BCNQ_DL >> 16));
+
+			/* We don't implement FW LPS so this is not needed. */
+			/* rtl92d_set_fw_rsvdpagepkt(hw, 0); */
+
+			_rtl92du_set_bcn_ctrl_reg(hw, EN_BCN_FUNCTION, 0);
+			_rtl92du_set_bcn_ctrl_reg(hw, 0, DIS_TSF_UDT);
+			if (recover)
+				rtl_write_byte(rtlpriv,
+					       REG_FWHW_TXQ_CTRL + 2,
+					       tmp_reg422);
+			rtl_write_byte(rtlpriv, REG_CR + 1,
+				       tmp_regcr & ~ENSWBCN);
+		}
+		rtl92d_set_fw_joinbss_report_cmd(hw, (*val));
+		break;
+	}
+	case HW_VAR_CORRECT_TSF: {
+		u8 btype_ibss = val[0];
+
+		if (btype_ibss)
+			rtl92d_stop_tx_beacon(hw);
+		_rtl92du_set_bcn_ctrl_reg(hw, 0, EN_BCN_FUNCTION);
+		rtl_write_dword(rtlpriv, REG_TSFTR,
+				(u32)(mac->tsf & 0xffffffff));
+		rtl_write_dword(rtlpriv, REG_TSFTR + 4,
+				(u32)((mac->tsf >> 32) & 0xffffffff));
+		_rtl92du_set_bcn_ctrl_reg(hw, EN_BCN_FUNCTION, 0);
+		if (btype_ibss)
+			rtl92d_resume_tx_beacon(hw);
+
+		break;
+	}
+	case HW_VAR_KEEP_ALIVE:
+		/* Avoid "switch case not processed" error. RTL8192DU doesn't
+		 * need to do anything here, maybe.
+		 */
+		break;
+	default:
+		rtl92d_set_hw_reg(hw, variable, val);
+		break;
+	}
+}
+
+static void _rtl92du_init_queue_reserved_page(struct ieee80211_hw *hw,
+					      u8 out_ep_num,
+					      u8 queue_sel)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_hal *rtlhal = rtl_hal(rtlpriv);
+	u32 txqpagenum, txqpageunit;
+	u32 txqremainingpage;
+	u32 numhq = 0;
+	u32 numlq = 0;
+	u32 numnq = 0;
+	u32 numpubq;
+	u32 value32;
+
+	if (rtlhal->macphymode != SINGLEMAC_SINGLEPHY) {
+		numpubq = NORMAL_PAGE_NUM_PUBQ_92D_DUAL_MAC;
+		txqpagenum = TX_TOTAL_PAGE_NUMBER_92D_DUAL_MAC - numpubq;
+	} else {
+		numpubq = TEST_PAGE_NUM_PUBQ_92DU;
+		txqpagenum = TX_TOTAL_PAGE_NUMBER_92DU - numpubq;
+	}
+
+	if (rtlhal->macphymode != SINGLEMAC_SINGLEPHY && out_ep_num == 3) {
+		numhq = NORMAL_PAGE_NUM_HPQ_92D_DUAL_MAC;
+		numlq = NORMAL_PAGE_NUM_LPQ_92D_DUAL_MAC;
+		numnq = NORMAL_PAGE_NUM_NORMALQ_92D_DUAL_MAC;
+	} else {
+		txqpageunit = txqpagenum / out_ep_num;
+		txqremainingpage = txqpagenum % out_ep_num;
+
+		if (queue_sel & TX_SELE_HQ)
+			numhq = txqpageunit;
+		if (queue_sel & TX_SELE_LQ)
+			numlq = txqpageunit;
+		if (queue_sel & TX_SELE_NQ)
+			numnq = txqpageunit;
+
+		/* HIGH priority queue always present in the
+		 * configuration of 2 or 3 out-ep. Remainder pages
+		 * assigned to High queue
+		 */
+		if (out_ep_num > 1 && txqremainingpage)
+			numhq += txqremainingpage;
+	}
+
+	/* NOTE: This step done before writing REG_RQPN. */
+	rtl_write_byte(rtlpriv, REG_RQPN_NPQ, (u8)numnq);
+
+	/* TX DMA */
+	u32p_replace_bits(&value32, numhq, HPQ_MASK);
+	u32p_replace_bits(&value32, numlq, LPQ_MASK);
+	u32p_replace_bits(&value32, numpubq, PUBQ_MASK);
+	value32 |= LD_RQPN;
+	rtl_write_dword(rtlpriv, REG_RQPN, value32);
+}
+
+static void _rtl92du_init_tx_buffer_boundary(struct ieee80211_hw *hw,
+					     u8 txpktbuf_bndy)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+
+	rtl_write_byte(rtlpriv, REG_TXPKTBUF_BCNQ_BDNY, txpktbuf_bndy);
+	rtl_write_byte(rtlpriv, REG_TXPKTBUF_MGQ_BDNY, txpktbuf_bndy);
+
+	rtl_write_byte(rtlpriv, REG_TXPKTBUF_WMAC_LBK_BF_HD, txpktbuf_bndy);
+
+	/* TXRKTBUG_PG_BNDY */
+	rtl_write_byte(rtlpriv, REG_TRXFF_BNDY, txpktbuf_bndy);
+
+	/* Beacon Head for TXDMA */
+	rtl_write_byte(rtlpriv, REG_TDECTRL + 1, txpktbuf_bndy);
+}
+
+static bool _rtl92du_llt_table_init(struct ieee80211_hw *hw, u8 txpktbuf_bndy)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	unsigned short i;
+	bool status;
+	u8 maxpage;
+
+	if (rtlpriv->rtlhal.macphymode == SINGLEMAC_SINGLEPHY)
+		maxpage = 255;
+	else
+		maxpage = 127;
+
+	for (i = 0; i < (txpktbuf_bndy - 1); i++) {
+		status = rtl92d_llt_write(hw, i, i + 1);
+		if (!status)
+			return status;
+	}
+
+	/* end of list */
+	status = rtl92d_llt_write(hw, txpktbuf_bndy - 1, 0xFF);
+	if (!status)
+		return status;
+
+	/* Make the other pages as ring buffer
+	 * This ring buffer is used as beacon buffer if we
+	 * config this MAC as two MAC transfer.
+	 * Otherwise used as local loopback buffer.
+	 */
+	for (i = txpktbuf_bndy; i < maxpage; i++) {
+		status = rtl92d_llt_write(hw, i, i + 1);
+		if (!status)
+			return status;
+	}
+
+	/* Let last entry point to the start entry of ring buffer */
+	status = rtl92d_llt_write(hw, maxpage, txpktbuf_bndy);
+	if (!status)
+		return status;
+
+	return true;
+}
+
+static void _rtl92du_init_chipn_reg_priority(struct ieee80211_hw *hw, u16 beq,
+					     u16 bkq, u16 viq, u16 voq,
+					     u16 mgtq, u16 hiq)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	u16 value16;
+
+	value16 = rtl_read_word(rtlpriv, REG_TRXDMA_CTRL) & 0x7;
+	u16p_replace_bits(&value16, beq, TXDMA_BEQ_MAP);
+	u16p_replace_bits(&value16, bkq, TXDMA_BKQ_MAP);
+	u16p_replace_bits(&value16, viq, TXDMA_VIQ_MAP);
+	u16p_replace_bits(&value16, voq, TXDMA_VOQ_MAP);
+	u16p_replace_bits(&value16, mgtq, TXDMA_MGQ_MAP);
+	u16p_replace_bits(&value16, hiq, TXDMA_HIQ_MAP);
+	rtl_write_word(rtlpriv,  REG_TRXDMA_CTRL, value16);
+}
+
+static void _rtl92du_init_chipn_one_out_ep_priority(struct ieee80211_hw *hw,
+						    u8 queue_sel)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	u16 value;
+
+	switch (queue_sel) {
+	case TX_SELE_HQ:
+		value = QUEUE_HIGH;
+		break;
+	case TX_SELE_LQ:
+		value = QUEUE_LOW;
+		break;
+	case TX_SELE_NQ:
+		value = QUEUE_NORMAL;
+		break;
+	default:
+		WARN_ON(1); /* Shall not reach here! */
+		return;
+	}
+	_rtl92du_init_chipn_reg_priority(hw, value, value, value, value,
+					 value, value);
+	rtl_dbg(rtlpriv, COMP_INIT, DBG_LOUD,
+		"Tx queue select: 0x%02x\n", queue_sel);
+}
+
+static void _rtl92du_init_chipn_two_out_ep_priority(struct ieee80211_hw *hw,
+						    u8 queue_sel)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	u16 beq, bkq, viq, voq, mgtq, hiq;
+	u16 valuehi, valuelow;
+
+	switch (queue_sel) {
+	default:
+		WARN_ON(1);
+		fallthrough;
+	case (TX_SELE_HQ | TX_SELE_LQ):
+		valuehi = QUEUE_HIGH;
+		valuelow = QUEUE_LOW;
+		break;
+	case (TX_SELE_NQ | TX_SELE_LQ):
+		valuehi = QUEUE_NORMAL;
+		valuelow = QUEUE_LOW;
+		break;
+	case (TX_SELE_HQ | TX_SELE_NQ):
+		valuehi = QUEUE_HIGH;
+		valuelow = QUEUE_NORMAL;
+		break;
+	}
+
+	beq = valuelow;
+	bkq = valuelow;
+	viq = valuehi;
+	voq = valuehi;
+	mgtq = valuehi;
+	hiq = valuehi;
+
+	_rtl92du_init_chipn_reg_priority(hw, beq, bkq, viq, voq, mgtq, hiq);
+	rtl_dbg(rtlpriv, COMP_INIT, DBG_LOUD,
+		"Tx queue select: 0x%02x\n", queue_sel);
+}
+
+static void _rtl92du_init_chipn_three_out_ep_priority(struct ieee80211_hw *hw,
+						      u8 queue_sel)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	u16 beq, bkq, viq, voq, mgtq, hiq;
+
+	beq = QUEUE_LOW;
+	bkq = QUEUE_LOW;
+	viq = QUEUE_NORMAL;
+	voq = QUEUE_HIGH;
+	mgtq = QUEUE_HIGH;
+	hiq = QUEUE_HIGH;
+
+	_rtl92du_init_chipn_reg_priority(hw, beq, bkq, viq, voq, mgtq, hiq);
+	rtl_dbg(rtlpriv, COMP_INIT, DBG_LOUD,
+		"Tx queue select: 0x%02x\n", queue_sel);
+}
+
+static void _rtl92du_init_queue_priority(struct ieee80211_hw *hw,
+					 u8 out_ep_num,
+					 u8 queue_sel)
+{
+	switch (out_ep_num) {
+	case 1:
+		_rtl92du_init_chipn_one_out_ep_priority(hw, queue_sel);
+		break;
+	case 2:
+		_rtl92du_init_chipn_two_out_ep_priority(hw, queue_sel);
+		break;
+	case 3:
+		_rtl92du_init_chipn_three_out_ep_priority(hw, queue_sel);
+		break;
+	default:
+		WARN_ON(1); /* Shall not reach here! */
+		break;
+	}
+}
+
+static void _rtl92du_init_wmac_setting(struct ieee80211_hw *hw)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_mac *mac = rtl_mac(rtlpriv);
+
+	mac->rx_conf = RCR_APM | RCR_AM | RCR_AB | RCR_ADF | RCR_APP_ICV |
+		       RCR_AMF | RCR_HTC_LOC_CTRL | RCR_APP_MIC |
+		       RCR_APP_PHYST_RXFF | RCR_APPFCS;
+
+	rtl_write_dword(rtlpriv, REG_RCR, mac->rx_conf);
+
+	/* Set Multicast Address. */
+	rtl_write_dword(rtlpriv, REG_MAR, 0xffffffff);
+	rtl_write_dword(rtlpriv, REG_MAR + 4, 0xffffffff);
+}
+
+static void _rtl92du_init_adaptive_ctrl(struct ieee80211_hw *hw)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	u32 val32;
+
+	val32 = rtl_read_dword(rtlpriv, REG_RRSR);
+	val32 &= ~0xfffff;
+	if (rtlpriv->rtlhal.current_bandtype == BAND_ON_5G)
+		val32 |= 0xffff0; /* No CCK */
+	else
+		val32 |= 0xffff1;
+	rtl_write_dword(rtlpriv, REG_RRSR, val32);
+
+	/* Set Spec SIFS (used in NAV) */
+	rtl_write_word(rtlpriv, REG_SPEC_SIFS, 0x1010);
+
+	/* Retry limit 0x30 */
+	rtl_write_word(rtlpriv, REG_RL, 0x3030);
+}
+
+static void _rtl92du_init_edca(struct ieee80211_hw *hw)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	u16 val16;
+
+	/* Disable EDCCA count down, to reduce collison and retry */
+	val16 = rtl_read_word(rtlpriv, REG_RD_CTRL);
+	val16 |= DIS_EDCA_CNT_DWN;
+	rtl_write_word(rtlpriv, REG_RD_CTRL, val16);
+
+	/* CCK SIFS shall always be 10us. */
+	rtl_write_word(rtlpriv, REG_SIFS_CTX, 0x0a0a);
+	/* Set SIFS for OFDM */
+	rtl_write_word(rtlpriv, REG_SIFS_TRX, 0x1010);
+
+	rtl_write_word(rtlpriv, REG_PROT_MODE_CTRL, 0x0204);
+
+	rtl_write_dword(rtlpriv, REG_BAR_MODE_CTRL, 0x014004);
+
+	/* TXOP */
+	rtl_write_dword(rtlpriv, REG_EDCA_BE_PARAM, 0x005EA42B);
+	rtl_write_dword(rtlpriv, REG_EDCA_BK_PARAM, 0x0000A44F);
+	rtl_write_dword(rtlpriv, REG_EDCA_VI_PARAM, 0x005EA324);
+	rtl_write_dword(rtlpriv, REG_EDCA_VO_PARAM, 0x002FA226);
+
+	rtl_write_byte(rtlpriv, REG_PIFS, 0x1C);
+
+	rtl_write_byte(rtlpriv, REG_AGGR_BREAK_TIME, 0x16);
+
+	rtl_write_word(rtlpriv, REG_NAV_PROT_LEN, 0x0040);
+
+	rtl_write_byte(rtlpriv, REG_BCNDMATIM, 0x2);
+	rtl_write_byte(rtlpriv, REG_ATIMWND, 0x2);
+}
+
+static void _rtl92du_init_retry_function(struct ieee80211_hw *hw)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	u8 val8;
+
+	val8 = rtl_read_byte(rtlpriv, REG_FWHW_TXQ_CTRL);
+	val8 |= EN_AMPDU_RTY_NEW;
+	rtl_write_byte(rtlpriv, REG_FWHW_TXQ_CTRL, val8);
+
+	rtl_write_byte(rtlpriv, REG_ACKTO, 0x40);
+}
+
+static void _rtl92du_init_operation_mode(struct ieee80211_hw *hw)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_hal *rtlhal = rtl_hal(rtlpriv);
+
+	rtl_write_byte(rtlpriv, REG_BWOPMODE, BW_OPMODE_20MHZ);
+
+	switch (rtlpriv->phy.rf_type) {
+	case RF_1T2R:
+	case RF_1T1R:
+		rtlhal->minspace_cfg = (MAX_MSS_DENSITY_1T << 3);
+		break;
+	case RF_2T2R:
+	case RF_2T2R_GREEN:
+		rtlhal->minspace_cfg = (MAX_MSS_DENSITY_2T << 3);
+		break;
+	}
+	rtl_write_byte(rtlpriv, REG_AMPDU_MIN_SPACE, rtlhal->minspace_cfg);
+}
+
+static void _rtl92du_init_beacon_parameters(struct ieee80211_hw *hw)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+
+	rtl_write_word(rtlpriv, REG_BCN_CTRL, 0x1010);
+
+	rtl_write_word(rtlpriv, REG_TBTT_PROHIBIT, 0x3c02);
+	rtl_write_byte(rtlpriv, REG_DRVERLYINT, 0x05);
+	rtl_write_byte(rtlpriv, REG_BCNDMATIM, 0x03);
+
+	rtl_write_word(rtlpriv, REG_BCNTCFG, 0x660f);
+}
+
+static void _rtl92du_init_ampdu_aggregation(struct ieee80211_hw *hw)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_hal *rtlhal = rtl_hal(rtlpriv);
+
+	/* Aggregation threshold */
+	if (rtlhal->macphymode == DUALMAC_DUALPHY)
+		rtl_write_dword(rtlpriv, REG_AGGLEN_LMT, 0x66525541);
+	else if (rtlhal->macphymode == DUALMAC_SINGLEPHY)
+		rtl_write_dword(rtlpriv, REG_AGGLEN_LMT, 0x44444441);
+	else
+		rtl_write_dword(rtlpriv, REG_AGGLEN_LMT, 0x88728841);
+
+	rtl_write_byte(rtlpriv, REG_AGGR_BREAK_TIME, 0x16);
+}
+
+static bool _rtl92du_init_power_on(struct ieee80211_hw *hw)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	unsigned short wordtmp;
+	unsigned char bytetmp;
+	u16 retry = 0;
+
+	do {
+		if (rtl_read_byte(rtlpriv, REG_APS_FSMCO) & PFM_ALDN)
+			break;
+
+		if (retry++ > 1000)
+			return false;
+	} while (true);
+
+	/* Unlock ISO/CLK/Power control register */
+	rtl_write_byte(rtlpriv, REG_RSV_CTRL, 0x00);
+
+	/* SPS0_CTRL 0x11[7:0] = 0x2b  enable SPS into PWM mode */
+	rtl_write_byte(rtlpriv, REG_SPS0_CTRL, 0x2b);
+
+	msleep(1);
+
+	bytetmp = rtl_read_byte(rtlpriv, REG_LDOV12D_CTRL);
+	if ((bytetmp & LDV12_EN) == 0) {
+		bytetmp |= LDV12_EN;
+		rtl_write_byte(rtlpriv, REG_LDOV12D_CTRL, bytetmp);
+
+		msleep(1);
+
+		bytetmp = rtl_read_byte(rtlpriv, REG_SYS_ISO_CTRL);
+		bytetmp &= ~ISO_MD2PP;
+		rtl_write_byte(rtlpriv, REG_SYS_ISO_CTRL, bytetmp);
+	}
+
+	/* Auto enable WLAN */
+	wordtmp = rtl_read_word(rtlpriv, REG_APS_FSMCO);
+	wordtmp |= APFM_ONMAC;
+	rtl_write_word(rtlpriv, REG_APS_FSMCO, wordtmp);
+
+	wordtmp = rtl_read_word(rtlpriv, REG_APS_FSMCO);
+	retry = 0;
+	while ((wordtmp & APFM_ONMAC) && retry < 1000) {
+		retry++;
+		wordtmp = rtl_read_word(rtlpriv, REG_APS_FSMCO);
+	}
+
+	/* Release RF digital isolation */
+	wordtmp = rtl_read_word(rtlpriv, REG_SYS_ISO_CTRL);
+	wordtmp &= ~ISO_DIOR;
+	rtl_write_word(rtlpriv, REG_SYS_ISO_CTRL, wordtmp);
+
+	/* Enable MAC DMA/WMAC/SCHEDULE/SEC block */
+	wordtmp = rtl_read_word(rtlpriv, REG_CR);
+	wordtmp |= HCI_TXDMA_EN | HCI_RXDMA_EN | TXDMA_EN | RXDMA_EN |
+		   PROTOCOL_EN | SCHEDULE_EN | MACTXEN | MACRXEN | ENSEC;
+	rtl_write_word(rtlpriv, REG_CR, wordtmp);
+
+	return true;
+}
+
+static bool _rtl92du_init_mac(struct ieee80211_hw *hw)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	u8 val8;
+
+	rtl_write_byte(rtlpriv, REG_RSV_CTRL, 0x00);
+
+	val8 = rtl_read_byte(rtlpriv, REG_SYS_FUNC_EN + 1);
+	val8 &= ~(FEN_MREGEN >> 8);
+	rtl_write_byte(rtlpriv, REG_SYS_FUNC_EN + 1, val8);
+
+	/* For s3/s4 may reset mac, Reg0xf8 may be set to 0,
+	 * so reset macphy control reg here.
+	 */
+	rtl92d_phy_config_macphymode(hw);
+
+	rtl92du_phy_set_poweron(hw);
+
+	if (!_rtl92du_init_power_on(hw)) {
+		pr_err("Failed to init power on!\n");
+		return false;
+	}
+
+	rtl92d_phy_config_maccoexist_rfpage(hw);
+
+	return true;
+}
+
+int rtl92du_hw_init(struct ieee80211_hw *hw)
+{
+	struct rtl_usb_priv *usb_priv = rtl_usbpriv(hw);
+	struct rtl_usb *rtlusb = rtl_usbdev(usb_priv);
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_ps_ctl *ppsc = rtl_psc(rtlpriv);
+	struct rtl_hal *rtlhal = rtl_hal(rtlpriv);
+	struct rtl_mac *mac = rtl_mac(rtlpriv);
+	struct rtl_phy *rtlphy = &rtlpriv->phy;
+	u8 val8, txpktbuf_bndy;
+	int err, i;
+	u32 val32;
+	u16 val16;
+
+	mutex_lock(rtlpriv->mutex_for_hw_init);
+
+	/* we should do iqk after disable/enable */
+	rtl92d_phy_reset_iqk_result(hw);
+
+	if (!_rtl92du_init_mac(hw)) {
+		pr_err("Init MAC failed\n");
+		mutex_unlock(rtlpriv->mutex_for_hw_init);
+		return 1;
+	}
+
+	if (rtlhal->macphymode == SINGLEMAC_SINGLEPHY)
+		txpktbuf_bndy = 249;
+	else
+		txpktbuf_bndy = 123;
+
+	if (!_rtl92du_llt_table_init(hw, txpktbuf_bndy)) {
+		pr_err("Init LLT failed\n");
+		mutex_unlock(rtlpriv->mutex_for_hw_init);
+		return 1;
+	}
+
+	err = rtl92du_download_fw(hw);
+
+	/* return fail only when part number check fail */
+	if (err && rtl_read_byte(rtlpriv, 0x1c5) == 0xe0) {
+		rtl_dbg(rtlpriv, COMP_ERR, DBG_WARNING,
+			"Failed to download FW. Init HW without FW..\n");
+		mutex_unlock(rtlpriv->mutex_for_hw_init);
+		return 1;
+	}
+	rtlhal->last_hmeboxnum = 0;
+	rtlpriv->psc.fw_current_inpsmode = false;
+
+	rtl92du_phy_mac_config(hw);
+
+	/* Set reserved page for each queue */
+	_rtl92du_init_queue_reserved_page(hw, rtlusb->out_ep_nums,
+					  rtlusb->out_queue_sel);
+
+	_rtl92du_init_tx_buffer_boundary(hw, txpktbuf_bndy);
+
+	_rtl92du_init_queue_priority(hw, rtlusb->out_ep_nums,
+				     rtlusb->out_queue_sel);
+
+	/* Set Tx/Rx page size (Tx must be 128 Bytes,
+	 * Rx can be 64, 128, 256, 512, 1024 bytes)
+	 */
+	rtl_write_byte(rtlpriv, REG_PBP, 0x11);
+
+	/* Get Rx PHY status in order to report RSSI and others. */
+	rtl_write_byte(rtlpriv, REG_RX_DRVINFO_SZ, 0x4);
+
+	rtl_write_dword(rtlpriv, REG_HISR, 0xffffffff);
+	rtl_write_dword(rtlpriv, REG_HIMR, 0xffffffff);
+
+	val8 = rtl_read_byte(rtlpriv, MSR);
+	val8 &= ~MSR_MASK;
+	val8 |= MSR_INFRA;
+	rtl_write_byte(rtlpriv, MSR, val8);
+
+	_rtl92du_init_wmac_setting(hw);
+	_rtl92du_init_adaptive_ctrl(hw);
+	_rtl92du_init_edca(hw);
+
+	rtl_write_dword(rtlpriv, REG_DARFRC, 0x00000000);
+	rtl_write_dword(rtlpriv, REG_DARFRC + 4, 0x10080404);
+	rtl_write_dword(rtlpriv, REG_RARFRC, 0x04030201);
+	rtl_write_dword(rtlpriv, REG_RARFRC + 4, 0x08070605);
+
+	_rtl92du_init_retry_function(hw);
+	/* _InitUsbAggregationSetting(padapter); no aggregation for now */
+	_rtl92du_init_operation_mode(hw);
+	_rtl92du_init_beacon_parameters(hw);
+	_rtl92du_init_ampdu_aggregation(hw);
+
+	rtl_write_byte(rtlpriv, REG_BCN_MAX_ERR, 0xff);
+
+	/* unit: 256us. 256ms */
+	rtl_write_word(rtlpriv, REG_PKT_VO_VI_LIFE_TIME, 0x0400);
+	rtl_write_word(rtlpriv, REG_PKT_BE_BK_LIFE_TIME, 0x0400);
+
+	/* Hardware-controlled blinking. */
+	rtl_write_word(rtlpriv, REG_LEDCFG0, 0x8282);
+	rtl_write_byte(rtlpriv, REG_LEDCFG2, 0x82);
+
+	val32 = rtl_read_dword(rtlpriv, REG_TXDMA_OFFSET_CHK);
+	val32 |= DROP_DATA_EN;
+	rtl_write_dword(rtlpriv, REG_TXDMA_OFFSET_CHK, val32);
+
+	if (mac->rdg_en) {
+		rtl_write_byte(rtlpriv, REG_RD_CTRL, 0xff);
+		rtl_write_word(rtlpriv, REG_RD_NAV_NXT, 0x200);
+		rtl_write_byte(rtlpriv, REG_RD_RESP_PKT_TH, 0x05);
+	}
+
+	for (i = 0; i < 4; i++)
+		rtl_write_dword(rtlpriv, REG_ARFR0 + i * 4, 0x1f8ffff0);
+
+	if (rtlhal->macphymode == SINGLEMAC_SINGLEPHY) {
+		if (rtlusb->out_ep_nums == 2)
+			rtl_write_dword(rtlpriv, REG_FAST_EDCA_CTRL, 0x03066666);
+		else
+			rtl_write_word(rtlpriv, REG_FAST_EDCA_CTRL, 0x8888);
+	} else {
+		rtl_write_word(rtlpriv, REG_FAST_EDCA_CTRL, 0x5555);
+	}
+
+	val8 = rtl_read_byte(rtlpriv, 0x605);
+	val8 |= 0xf0;
+	rtl_write_byte(rtlpriv, 0x605, val8);
+
+	rtl_write_byte(rtlpriv, REG_RXTSF_OFFSET_CCK, 0x30);
+	rtl_write_byte(rtlpriv, REG_RXTSF_OFFSET_OFDM, 0x30);
+	rtl_write_byte(rtlpriv, 0x606, 0x30);
+
+	/* temp for high queue and mgnt Queue corrupt in time; it may
+	 * cause hang when sw beacon use high_Q, other frame use mgnt_Q;
+	 * or, sw beacon use mgnt_Q, other frame use high_Q;
+	 */
+	rtl_write_byte(rtlpriv, REG_DIS_TXREQ_CLR, 0x10);
+	val16 = rtl_read_word(rtlpriv, REG_RD_CTRL);
+	val16 |= BIT(12);
+	rtl_write_word(rtlpriv, REG_RD_CTRL, val16);
+
+	rtl_write_byte(rtlpriv, REG_TXPAUSE, 0);
+
+	/* usb suspend idle time count for bitfile0927 */
+	val8 = rtl_read_byte(rtlpriv, 0xfe56);
+	val8 |= BIT(0) | BIT(1);
+	rtl_write_byte(rtlpriv, 0xfe56, val8);
+
+	if (rtlhal->earlymode_enable) {
+		rtl_dbg(rtlpriv, COMP_INIT, DBG_LOUD,
+			"EarlyMode Enabled!!!\n");
+
+		val8 = rtl_read_byte(rtlpriv, REG_EARLY_MODE_CONTROL);
+		val8 |= 0x1f;
+		rtl_write_byte(rtlpriv, REG_EARLY_MODE_CONTROL, val8);
+
+		rtl_write_byte(rtlpriv, REG_EARLY_MODE_CONTROL + 3, 0x80);
+
+		val8 = rtl_read_byte(rtlpriv, 0x605);
+		val8 |= 0x40;
+		rtl_write_byte(rtlpriv, 0x605, val8);
+	} else {
+		rtl_write_byte(rtlpriv, REG_EARLY_MODE_CONTROL, 0);
+	}
+
+	rtl92du_phy_bb_config(hw);
+
+	rtlphy->rf_mode = RF_OP_BY_SW_3WIRE;
+	/* set before initialize RF */
+	rtl_set_bbreg(hw, RFPGA0_ANALOGPARAMETER4, 0x00f00000, 0xf);
+
+	/* config RF */
+	rtl92du_phy_rf_config(hw);
+
+	/* set default value after initialize RF */
+	rtl_set_bbreg(hw, RFPGA0_ANALOGPARAMETER4, 0x00f00000, 0);
+
+	/* After load BB, RF params, we need to do more for 92D. */
+	rtl92du_update_bbrf_configuration(hw);
+
+	rtlphy->rfreg_chnlval[0] =
+		rtl_get_rfreg(hw, RF90_PATH_A, RF_CHNLBW, RFREG_OFFSET_MASK);
+	rtlphy->rfreg_chnlval[1] =
+		rtl_get_rfreg(hw, RF90_PATH_B, RF_CHNLBW, RFREG_OFFSET_MASK);
+
+	/*---- Set CCK and OFDM Block "ON"----*/
+	if (rtlhal->current_bandtype == BAND_ON_2_4G)
+		rtl_set_bbreg(hw, RFPGA0_RFMOD, BCCKEN, 0x1);
+	rtl_set_bbreg(hw, RFPGA0_RFMOD, BOFDMEN, 0x1);
+
+	/* reset hw sec */
+	rtl_cam_reset_all_entry(hw);
+	rtl92d_enable_hw_security_config(hw);
+
+	rtl_write_byte(rtlpriv, REG_HWSEQ_CTRL, 0xFF);
+
+	/* schmitt trigger, improve tx evm for 92du */
+	val8 = rtl_read_byte(rtlpriv, REG_AFE_XTAL_CTRL);
+	val8 |= BIT(1);
+	rtl_write_byte(rtlpriv, REG_AFE_XTAL_CTRL, val8);
+
+	/* Disable bar */
+	rtl_write_dword(rtlpriv, REG_BAR_MODE_CTRL, 0xffff);
+
+	/* Nav limit */
+	rtl_write_byte(rtlpriv, REG_NAV_CTRL + 2, 0);
+	rtl_write_byte(rtlpriv, ROFDM0_XATXAFE + 3, 0x50);
+
+	/* Read EEPROM TX power index and PHY_REG_PG.txt to capture correct
+	 * TX power index for different rate set.
+	 */
+	rtl92d_phy_get_hw_reg_originalvalue(hw);
+
+	ppsc->rfpwr_state = ERFON;
+
+	/* do IQK for 2.4G for better scan result */
+	if (rtlhal->current_bandtype == BAND_ON_2_4G)
+		rtl92du_phy_iq_calibrate(hw);
+
+	rtl92du_phy_lc_calibrate(hw, IS_92D_SINGLEPHY(rtlhal->version));
+
+	rtl92du_phy_init_pa_bias(hw);
+
+	mutex_unlock(rtlpriv->mutex_for_hw_init);
+
+	rtl92du_dm_init(hw);
+
+	/* For 2 PORT TSF SYNC */
+	rtl_write_word(rtlpriv, REG_BCN_CTRL, 0x1818);
+	rtlusb->reg_bcn_ctrl_val = 0x18;
+
+	udelay(500);
+
+	if (rtlhal->macphymode != DUALMAC_DUALPHY) {
+		rtl_write_dword(rtlpriv, RFPGA1_TXINFO,
+				rtl_read_dword(rtlpriv, RFPGA1_TXINFO) & ~BIT(30));
+
+		rtl_write_dword(rtlpriv, RFPGA0_TXGAINSTAGE,
+				rtl_read_dword(rtlpriv, RFPGA0_TXGAINSTAGE) & ~BIT(31));
+
+		rtl_write_dword(rtlpriv, ROFDM0_XBTXAFE, 0xa0e40000);
+	}
+
+	val32 = rtl_read_dword(rtlpriv, REG_FWHW_TXQ_CTRL);
+	val32 |= BIT(12);
+	rtl_write_dword(rtlpriv, REG_FWHW_TXQ_CTRL, val32);
+
+	return err;
+}
+
+static int _rtl92du_set_media_status(struct ieee80211_hw *hw,
+				     enum nl80211_iftype type)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	enum led_ctl_mode ledaction = LED_CTL_NO_LINK;
+	u8 bt_msr = rtl_read_byte(rtlpriv, MSR);
+
+	bt_msr &= 0xfc;
+
+	if (type == NL80211_IFTYPE_UNSPECIFIED ||
+	    type == NL80211_IFTYPE_STATION) {
+		rtl92d_stop_tx_beacon(hw);
+		_rtl92du_enable_bcn_sub_func(hw);
+	} else if (type == NL80211_IFTYPE_ADHOC ||
+		   type == NL80211_IFTYPE_AP) {
+		rtl92d_resume_tx_beacon(hw);
+		_rtl92du_disable_bcn_sub_func(hw);
+	} else {
+		rtl_dbg(rtlpriv, COMP_ERR, DBG_WARNING,
+			"Set HW_VAR_MEDIA_STATUS: No such media status(%x)\n",
+			type);
+	}
+
+	switch (type) {
+	case NL80211_IFTYPE_UNSPECIFIED:
+		bt_msr |= MSR_NOLINK;
+		ledaction = LED_CTL_LINK;
+		rtl_dbg(rtlpriv, COMP_INIT, DBG_TRACE,
+			"Set Network type to NO LINK!\n");
+		break;
+	case NL80211_IFTYPE_ADHOC:
+		bt_msr |= MSR_ADHOC;
+		rtl_dbg(rtlpriv, COMP_INIT, DBG_TRACE,
+			"Set Network type to Ad Hoc!\n");
+		break;
+	case NL80211_IFTYPE_STATION:
+		bt_msr |= MSR_INFRA;
+		ledaction = LED_CTL_LINK;
+		rtl_dbg(rtlpriv, COMP_INIT, DBG_TRACE,
+			"Set Network type to STA!\n");
+		break;
+	case NL80211_IFTYPE_AP:
+		bt_msr |= MSR_AP;
+		rtl_dbg(rtlpriv, COMP_INIT, DBG_TRACE,
+			"Set Network type to AP!\n");
+		break;
+	default:
+		pr_err("Network type %d not supported!\n", type);
+		return 1;
+	}
+	rtl_write_byte(rtlpriv, MSR, bt_msr);
+
+	rtlpriv->cfg->ops->led_control(hw, ledaction);
+
+	if ((bt_msr & MSR_MASK) == MSR_AP)
+		rtl_write_byte(rtlpriv, REG_BCNTCFG + 1, 0x00);
+	else
+		rtl_write_byte(rtlpriv, REG_BCNTCFG + 1, 0x66);
+
+	return 0;
+}
+
+void rtl92du_set_check_bssid(struct ieee80211_hw *hw, bool check_bssid)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	u32 reg_rcr;
+
+	if (rtlpriv->psc.rfpwr_state != ERFON)
+		return;
+
+	rtlpriv->cfg->ops->get_hw_reg(hw, HW_VAR_RCR, (u8 *)(&reg_rcr));
+
+	if (check_bssid) {
+		reg_rcr |= RCR_CBSSID_DATA | RCR_CBSSID_BCN;
+		rtlpriv->cfg->ops->set_hw_reg(hw, HW_VAR_RCR, (u8 *)&reg_rcr);
+		_rtl92du_set_bcn_ctrl_reg(hw, 0, DIS_TSF_UDT);
+	} else if (!check_bssid) {
+		reg_rcr &= ~(RCR_CBSSID_DATA | RCR_CBSSID_BCN);
+		_rtl92du_set_bcn_ctrl_reg(hw, DIS_TSF_UDT, 0);
+		rtlpriv->cfg->ops->set_hw_reg(hw, HW_VAR_RCR, (u8 *)&reg_rcr);
+	}
+}
+
+int rtl92du_set_network_type(struct ieee80211_hw *hw, enum nl80211_iftype type)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+
+	if (_rtl92du_set_media_status(hw, type))
+		return -EOPNOTSUPP;
+
+	/* check bssid */
+	if (rtlpriv->mac80211.link_state == MAC80211_LINKED) {
+		if (type != NL80211_IFTYPE_AP)
+			rtl92du_set_check_bssid(hw, true);
+	} else {
+		rtl92du_set_check_bssid(hw, false);
+	}
+
+	return 0;
+}
+
+/* do iqk or reload iqk */
+/* windows just rtl92d_phy_reload_iqk_setting in set channel,
+ * but it's very strict for time sequence so we add
+ * rtl92d_phy_reload_iqk_setting here
+ */
+void rtl92du_linked_set_reg(struct ieee80211_hw *hw)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_phy *rtlphy = &rtlpriv->phy;
+	u8 channel = rtlphy->current_channel;
+	u8 indexforchannel;
+
+	indexforchannel = rtl92d_get_rightchnlplace_for_iqk(channel);
+	if (!rtlphy->iqk_matrix[indexforchannel].iqk_done) {
+		rtl_dbg(rtlpriv, COMP_SCAN | COMP_INIT, DBG_DMESG,
+			"Do IQK for channel:%d\n", channel);
+		rtl92du_phy_iq_calibrate(hw);
+	}
+}
+
+void rtl92du_enable_interrupt(struct ieee80211_hw *hw)
+{
+	/* Nothing to do. */
+}
+
+void rtl92du_disable_interrupt(struct ieee80211_hw *hw)
+{
+	/* Nothing to do. */
+}
+
+static void _rtl92du_poweroff_adapter(struct ieee80211_hw *hw)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	u8 retry = 100;
+	u8 u1b_tmp;
+	u16 val16;
+	u32 val32;
+
+	rtl_write_byte(rtlpriv, REG_LDOA15_CTRL, 0x04);
+
+	rtl_write_byte(rtlpriv, REG_RF_CTRL, 0x00);
+
+	/* IF fw in RAM code, do reset */
+	if (rtl_read_byte(rtlpriv, REG_MCUFWDL) & MCUFWDL_RDY) {
+		rtl_write_byte(rtlpriv, REG_FSIMR, 0);
+
+		/* We need to disable other HRCV INT to influence 8051 reset. */
+		rtl_write_byte(rtlpriv, REG_FWIMR, 0x20);
+
+		/* Close mask to prevent incorrect FW write operation. */
+		rtl_write_byte(rtlpriv, REG_FTIMR, 0);
+
+		rtl_write_byte(rtlpriv, REG_MCUFWDL, 0);
+
+		/* Set (REG_HMETFR + 3) to 0x20 is reset 8051 */
+		rtl_write_byte(rtlpriv, REG_HMETFR + 3, 0x20);
+		val16 = rtl_read_word(rtlpriv, REG_SYS_FUNC_EN);
+		while (val16 & FEN_CPUEN) {
+			retry--;
+			if (retry == 0)
+				break;
+			udelay(50);
+			val16 = rtl_read_word(rtlpriv, REG_SYS_FUNC_EN);
+		}
+
+		if (retry == 0) {
+			rtl_write_byte(rtlpriv, REG_FWIMR, 0);
+
+			/* if 8051 reset fail, reset MAC directly. */
+			rtl_write_byte(rtlpriv, REG_SYS_FUNC_EN + 1, 0x50);
+
+			mdelay(10);
+		}
+	}
+
+	/* reset MCU, MAC register, DCORE */
+	rtl_write_byte(rtlpriv, REG_SYS_FUNC_EN + 1, 0x54);
+
+	/* reset MCU ready status */
+	rtl_write_byte(rtlpriv, REG_MCUFWDL, 0x00);
+
+	/* Pull GPIO PIN to balance level and LED control */
+
+	/* Disable GPIO[7:0] */
+	rtl_write_word(rtlpriv, REG_GPIO_PIN_CTRL + 2, 0x0000);
+	val32 = rtl_read_dword(rtlpriv, REG_GPIO_PIN_CTRL);
+	u32p_replace_bits(&val32, val32 & 0xff, 0x0000ff00);
+	u32p_replace_bits(&val32, 0xff, 0x00ff0000);
+	rtl_write_dword(rtlpriv, REG_GPIO_PIN_CTRL, val32);
+
+	/* Disable GPIO[10:8] */
+	rtl_write_byte(rtlpriv, REG_MAC_PINMUX_CFG, 0);
+	val16 = rtl_read_word(rtlpriv, REG_GPIO_IO_SEL);
+	u16p_replace_bits(&val16, val16 & 0xf, 0x00f0);
+	u16p_replace_bits(&val16, 0xf, 0x0780);
+	rtl_write_word(rtlpriv, REG_GPIO_IO_SEL, val16);
+
+	/* Disable LED 0, 1, and 2 */
+	rtl_write_word(rtlpriv, REG_LEDCFG0, 0x8888);
+	rtl_write_byte(rtlpriv, REG_LEDCFG2, 0x88);
+
+	/* Disable analog sequence */
+
+	/* enter PFM mode */
+	rtl_write_byte(rtlpriv, REG_SPS0_CTRL, 0x23);
+
+	rtl_write_word(rtlpriv, REG_APS_FSMCO,
+		       APDM_HOST | AFSM_HSUS | PFM_ALDN);
+
+	/* lock ISO/CLK/Power control register */
+	rtl_write_byte(rtlpriv, REG_RSV_CTRL, 0x0e);
+
+	rtl_dbg(rtlpriv, COMP_INIT, DBG_LOUD,
+		"In PowerOff,reg0x%x=%X\n",
+		REG_SPS0_CTRL, rtl_read_byte(rtlpriv, REG_SPS0_CTRL));
+
+	/* 0x17[7] 1b': power off in process  0b' : power off over */
+	if (rtlpriv->rtlhal.macphymode != SINGLEMAC_SINGLEPHY) {
+		mutex_lock(rtlpriv->mutex_for_power_on_off);
+		u1b_tmp = rtl_read_byte(rtlpriv, REG_POWER_OFF_IN_PROCESS);
+		u1b_tmp &= ~BIT(7);
+		rtl_write_byte(rtlpriv, REG_POWER_OFF_IN_PROCESS, u1b_tmp);
+		mutex_unlock(rtlpriv->mutex_for_power_on_off);
+	}
+
+	rtl_dbg(rtlpriv, COMP_INIT, DBG_LOUD, "<=======\n");
+}
+
+void rtl92du_card_disable(struct ieee80211_hw *hw)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_ps_ctl *ppsc = rtl_psc(rtl_priv(hw));
+	struct rtl_hal *rtlhal = rtl_hal(rtl_priv(hw));
+	struct rtl_mac *mac = rtl_mac(rtl_priv(hw));
+	enum nl80211_iftype opmode;
+	u32 val32;
+	u16 val16;
+	u8 val8;
+
+	mac->link_state = MAC80211_NOLINK;
+	opmode = NL80211_IFTYPE_UNSPECIFIED;
+	_rtl92du_set_media_status(hw, opmode);
+
+	RT_SET_PS_LEVEL(ppsc, RT_RF_OFF_LEVL_HALT_NIC);
+	/* Power sequence for each MAC. */
+	/* a. stop tx DMA  */
+	/* b. close RF */
+	/* c. clear rx buf */
+	/* d. stop rx DMA */
+	/* e. reset MAC */
+
+	val16 = rtl_read_word(rtlpriv, REG_GPIO_MUXCFG);
+	val16 &= ~BIT(12);
+	rtl_write_word(rtlpriv, REG_GPIO_MUXCFG, val16);
+
+	rtl_write_byte(rtlpriv, REG_TXPAUSE, 0xff);
+	udelay(500);
+	rtl_write_byte(rtlpriv, REG_CR, 0);
+
+	/* RF OFF sequence */
+	rtl_set_bbreg(hw, RFPGA0_ANALOGPARAMETER4, 0x00f00000, 0xf);
+	rtl_set_rfreg(hw, RF90_PATH_A, RF_AC, RFREG_OFFSET_MASK, 0x00);
+
+	rtl_write_byte(rtlpriv, REG_APSD_CTRL, 0x40);
+
+	val8 = FEN_USBD | FEN_USBA | FEN_BB_GLB_RSTN;
+	rtl_write_byte(rtlpriv, REG_SYS_FUNC_EN, val8);
+
+	/* Mac0 can not do Global reset. Mac1 can do. */
+	if (rtlhal->macphymode == SINGLEMAC_SINGLEPHY ||
+	    rtlhal->interfaceindex == 1) {
+		/* before BB reset should do clock gated */
+		val32 = rtl_read_dword(rtlpriv, RFPGA0_XCD_RFPARAMETER);
+		val32 |= BIT(31);
+		rtl_write_dword(rtlpriv, RFPGA0_XCD_RFPARAMETER, val32);
+
+		val8 &= ~FEN_BB_GLB_RSTN;
+		rtl_write_byte(rtlpriv, REG_SYS_FUNC_EN, val8);
+	}
+
+	rtl_dbg(rtlpriv, COMP_INIT, DBG_LOUD, "==> Do power off.......\n");
+	if (!rtl92du_phy_check_poweroff(hw))
+		return;
+
+	_rtl92du_poweroff_adapter(hw);
+}
+
+void rtl92du_set_beacon_related_registers(struct ieee80211_hw *hw)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_mac *mac = rtl_mac(rtlpriv);
+	u16 bcn_interval, atim_window;
+
+	bcn_interval = mac->beacon_interval;
+	atim_window = 2;
+	rtl92du_disable_interrupt(hw);
+	rtl_write_word(rtlpriv, REG_ATIMWND, atim_window);
+	rtl_write_word(rtlpriv, REG_BCN_INTERVAL, bcn_interval);
+	rtl_write_word(rtlpriv, REG_BCNTCFG, 0x660f);
+	rtl_write_byte(rtlpriv, REG_RXTSF_OFFSET_CCK, 0x20);
+	if (rtlpriv->rtlhal.current_bandtype == BAND_ON_5G)
+		rtl_write_byte(rtlpriv, REG_RXTSF_OFFSET_OFDM, 0x30);
+	else
+		rtl_write_byte(rtlpriv, REG_RXTSF_OFFSET_OFDM, 0x20);
+	rtl_write_byte(rtlpriv, 0x606, 0x30);
+}
+
+void rtl92du_set_beacon_interval(struct ieee80211_hw *hw)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_mac *mac = rtl_mac(rtl_priv(hw));
+	u16 bcn_interval = mac->beacon_interval;
+
+	rtl_dbg(rtlpriv, COMP_BEACON, DBG_DMESG,
+		"beacon_interval:%d\n", bcn_interval);
+	rtl92du_disable_interrupt(hw);
+	rtl_write_word(rtlpriv, REG_BCN_INTERVAL, bcn_interval);
+	rtl92du_enable_interrupt(hw);
+}
+
+void rtl92du_update_interrupt_mask(struct ieee80211_hw *hw,
+				   u32 add_msr, u32 rm_msr)
+{
+	/* Nothing to do here. */
+}
+
+void rtl92du_read_chip_version(struct ieee80211_hw *hw)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+
+	/* Chip version reading is done in rtl92d_read_eeprom_info. */
+
+	rtlpriv->rtlhal.hw_type = HARDWARE_TYPE_RTL8192DU;
+}
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192du/hw.h b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/hw.h
new file mode 100644
index 0000000000000..80ed00c90c169
--- /dev/null
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/hw.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2024  Realtek Corporation.*/
+
+#ifndef __RTL92DU_HW_H__
+#define __RTL92DU_HW_H__
+
+void rtl92du_get_hw_reg(struct ieee80211_hw *hw, u8 variable, u8 *val);
+void rtl92du_set_hw_reg(struct ieee80211_hw *hw, u8 variable, u8 *val);
+void rtl92du_read_chip_version(struct ieee80211_hw *hw);
+int rtl92du_hw_init(struct ieee80211_hw *hw);
+void rtl92du_card_disable(struct ieee80211_hw *hw);
+void rtl92du_enable_interrupt(struct ieee80211_hw *hw);
+void rtl92du_disable_interrupt(struct ieee80211_hw *hw);
+int rtl92du_set_network_type(struct ieee80211_hw *hw, enum nl80211_iftype type);
+void rtl92du_set_check_bssid(struct ieee80211_hw *hw, bool check_bssid);
+void rtl92du_set_beacon_related_registers(struct ieee80211_hw *hw);
+void rtl92du_set_beacon_interval(struct ieee80211_hw *hw);
+void rtl92du_update_interrupt_mask(struct ieee80211_hw *hw,
+				   u32 add_msr, u32 rm_msr);
+void rtl92du_linked_set_reg(struct ieee80211_hw *hw);
+
+#endif
-- 
GitLab


From af46caf0515281a30e119b53afb3083fcc5110a9 Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Thu, 23 May 2024 17:46:02 +0300
Subject: [PATCH 544/950] wifi: rtlwifi: Add rtl8192du/phy.{c,h}

These contain mostly the calibration and channel switching routines
for RTL8192DU.

Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://msgid.link/299a5ab7-46bf-410b-bbeb-e252eeeeb34c@gmail.com
---
 .../wireless/realtek/rtlwifi/rtl8192du/phy.c  | 3123 +++++++++++++++++
 .../wireless/realtek/rtlwifi/rtl8192du/phy.h  |   32 +
 2 files changed, 3155 insertions(+)
 create mode 100644 drivers/net/wireless/realtek/rtlwifi/rtl8192du/phy.c
 create mode 100644 drivers/net/wireless/realtek/rtlwifi/rtl8192du/phy.h

diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192du/phy.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/phy.c
new file mode 100644
index 0000000000000..289ec71ce3e56
--- /dev/null
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/phy.c
@@ -0,0 +1,3123 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2024  Realtek Corporation.*/
+
+#include "../wifi.h"
+#include "../ps.h"
+#include "../core.h"
+#include "../efuse.h"
+#include "../usb.h"
+#include "../rtl8192d/reg.h"
+#include "../rtl8192d/def.h"
+#include "../rtl8192d/phy_common.h"
+#include "../rtl8192d/rf_common.h"
+#include "phy.h"
+#include "rf.h"
+#include "table.h"
+
+#define MAX_RF_IMR_INDEX			12
+#define MAX_RF_IMR_INDEX_NORMAL			13
+#define RF_REG_NUM_FOR_C_CUT_5G			6
+#define RF_REG_NUM_FOR_C_CUT_5G_INTERNALPA	7
+#define RF_REG_NUM_FOR_C_CUT_2G			5
+#define RF_CHNL_NUM_5G				19
+#define RF_CHNL_NUM_5G_40M			17
+#define CV_CURVE_CNT				64
+
+static const u32 rf_reg_for_5g_swchnl_normal[MAX_RF_IMR_INDEX_NORMAL] = {
+	0, 0x2f, 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, 0x38, 0x39, 0x0
+};
+
+static const u8 rf_reg_for_c_cut_5g[RF_REG_NUM_FOR_C_CUT_5G] = {
+	RF_SYN_G1, RF_SYN_G2, RF_SYN_G3, RF_SYN_G4, RF_SYN_G5, RF_SYN_G6
+};
+
+static const u8 rf_reg_for_c_cut_2g[RF_REG_NUM_FOR_C_CUT_2G] = {
+	RF_SYN_G1, RF_SYN_G2, RF_SYN_G3, RF_SYN_G7, RF_SYN_G8
+};
+
+static const u8 rf_for_c_cut_5g_internal_pa[RF_REG_NUM_FOR_C_CUT_5G_INTERNALPA] = {
+	0x0B, 0x48, 0x49, 0x4B, 0x03, 0x04, 0x0E
+};
+
+static const u32 rf_reg_mask_for_c_cut_2g[RF_REG_NUM_FOR_C_CUT_2G] = {
+	BIT(19) | BIT(18) | BIT(17) | BIT(14) | BIT(1),
+	BIT(10) | BIT(9),
+	BIT(18) | BIT(17) | BIT(16) | BIT(1),
+	BIT(2) | BIT(1),
+	BIT(15) | BIT(14) | BIT(13) | BIT(12) | BIT(11)
+};
+
+static const u8 rf_chnl_5g[RF_CHNL_NUM_5G] = {
+	36, 40, 44, 48, 52, 56, 60, 64, 100, 104, 108,
+	112, 116, 120, 124, 128, 132, 136, 140
+};
+
+static const u8 rf_chnl_5g_40m[RF_CHNL_NUM_5G_40M] = {
+	38, 42, 46, 50, 54, 58, 62, 102, 106, 110, 114,
+	118, 122, 126, 130, 134, 138
+};
+
+static const u32 rf_reg_pram_c_5g[5][RF_REG_NUM_FOR_C_CUT_5G] = {
+	{0xE43BE, 0xFC638, 0x77C0A, 0xDE471, 0xd7110, 0x8EB04},
+	{0xE43BE, 0xFC078, 0xF7C1A, 0xE0C71, 0xD7550, 0xAEB04},
+	{0xE43BF, 0xFF038, 0xF7C0A, 0xDE471, 0xE5550, 0xAEB04},
+	{0xE43BF, 0xFF079, 0xF7C1A, 0xDE471, 0xE5550, 0xAEB04},
+	{0xE43BF, 0xFF038, 0xF7C1A, 0xDE471, 0xd7550, 0xAEB04}
+};
+
+static const u32 rf_reg_param_for_c_cut_2g[3][RF_REG_NUM_FOR_C_CUT_2G] = {
+	{0x643BC, 0xFC038, 0x77C1A, 0x41289, 0x01840},
+	{0x643BC, 0xFC038, 0x07C1A, 0x41289, 0x01840},
+	{0x243BC, 0xFC438, 0x07C1A, 0x4128B, 0x0FC41}
+};
+
+static const u32 rf_syn_g4_for_c_cut_2g = 0xD1C31 & 0x7FF;
+
+static const u32 rf_pram_c_5g_int_pa[3][RF_REG_NUM_FOR_C_CUT_5G_INTERNALPA] = {
+	{0x01a00, 0x40443, 0x00eb5, 0x89bec, 0x94a12, 0x94a12, 0x94a12},
+	{0x01800, 0xc0443, 0x00730, 0x896ee, 0x94a52, 0x94a52, 0x94a52},
+	{0x01800, 0xc0443, 0x00730, 0x896ee, 0x94a12, 0x94a12, 0x94a12}
+};
+
+/* [patha+b][reg] */
+static const u32 rf_imr_param_normal[3][MAX_RF_IMR_INDEX_NORMAL] = {
+	/* channels 1-14. */
+	{
+		0x70000, 0x00ff0, 0x4400f, 0x00ff0, 0x0, 0x0, 0x0,
+		0x0, 0x0, 0x64888, 0xe266c, 0x00090, 0x22fff
+	},
+	/* channels 36-64 */
+	{
+		0x70000, 0x22880, 0x4470f, 0x55880, 0x00070, 0x88000,
+		0x0, 0x88080, 0x70000, 0x64a82, 0xe466c, 0x00090,
+		0x32c9a
+	},
+	/* channels 100-165 */
+	{
+		0x70000, 0x44880, 0x4477f, 0x77880, 0x00070, 0x88000,
+		0x0, 0x880b0, 0x0, 0x64b82, 0xe466c, 0x00090, 0x32c9a
+	}
+};
+
+static const u32 targetchnl_5g[TARGET_CHNL_NUM_5G] = {
+	25141, 25116, 25091, 25066, 25041,
+	25016, 24991, 24966, 24941, 24917,
+	24892, 24867, 24843, 24818, 24794,
+	24770, 24765, 24721, 24697, 24672,
+	24648, 24624, 24600, 24576, 24552,
+	24528, 24504, 24480, 24457, 24433,
+	24409, 24385, 24362, 24338, 24315,
+	24291, 24268, 24245, 24221, 24198,
+	24175, 24151, 24128, 24105, 24082,
+	24059, 24036, 24013, 23990, 23967,
+	23945, 23922, 23899, 23876, 23854,
+	23831, 23809, 23786, 23764, 23741,
+	23719, 23697, 23674, 23652, 23630,
+	23608, 23586, 23564, 23541, 23519,
+	23498, 23476, 23454, 23432, 23410,
+	23388, 23367, 23345, 23323, 23302,
+	23280, 23259, 23237, 23216, 23194,
+	23173, 23152, 23130, 23109, 23088,
+	23067, 23046, 23025, 23003, 22982,
+	22962, 22941, 22920, 22899, 22878,
+	22857, 22837, 22816, 22795, 22775,
+	22754, 22733, 22713, 22692, 22672,
+	22652, 22631, 22611, 22591, 22570,
+	22550, 22530, 22510, 22490, 22469,
+	22449, 22429, 22409, 22390, 22370,
+	22350, 22336, 22310, 22290, 22271,
+	22251, 22231, 22212, 22192, 22173,
+	22153, 22134, 22114, 22095, 22075,
+	22056, 22037, 22017, 21998, 21979,
+	21960, 21941, 21921, 21902, 21883,
+	21864, 21845, 21826, 21807, 21789,
+	21770, 21751, 21732, 21713, 21695,
+	21676, 21657, 21639, 21620, 21602,
+	21583, 21565, 21546, 21528, 21509,
+	21491, 21473, 21454, 21436, 21418,
+	21400, 21381, 21363, 21345, 21327,
+	21309, 21291, 21273, 21255, 21237,
+	21219, 21201, 21183, 21166, 21148,
+	21130, 21112, 21095, 21077, 21059,
+	21042, 21024, 21007, 20989, 20972,
+	25679, 25653, 25627, 25601, 25575,
+	25549, 25523, 25497, 25471, 25446,
+	25420, 25394, 25369, 25343, 25318,
+	25292, 25267, 25242, 25216, 25191,
+	25166
+};
+
+/* channel 1~14 */
+static const u32 targetchnl_2g[TARGET_CHNL_NUM_2G] = {
+	26084, 26030, 25976, 25923, 25869, 25816, 25764,
+	25711, 25658, 25606, 25554, 25502, 25451, 25328
+};
+
+u32 rtl92du_phy_query_bb_reg(struct ieee80211_hw *hw, u32 regaddr, u32 bitmask)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_hal *rtlhal = rtl_hal(rtlpriv);
+	u32 returnvalue, originalvalue, bitshift;
+
+	rtl_dbg(rtlpriv, COMP_RF, DBG_TRACE, "regaddr(%#x), bitmask(%#x)\n",
+		regaddr, bitmask);
+
+	if (rtlhal->during_mac1init_radioa)
+		regaddr |= MAC1_ACCESS_PHY0;
+	else if (rtlhal->during_mac0init_radiob)
+		regaddr |= MAC0_ACCESS_PHY1;
+
+	originalvalue = rtl_read_dword(rtlpriv, regaddr);
+	bitshift = calculate_bit_shift(bitmask);
+	returnvalue = (originalvalue & bitmask) >> bitshift;
+	rtl_dbg(rtlpriv, COMP_RF, DBG_TRACE,
+		"BBR MASK=0x%x Addr[0x%x]=0x%x\n",
+		bitmask, regaddr, originalvalue);
+	return returnvalue;
+}
+
+void rtl92du_phy_set_bb_reg(struct ieee80211_hw *hw,
+			    u32 regaddr, u32 bitmask, u32 data)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_hal *rtlhal = rtl_hal(rtlpriv);
+	u32 originalvalue, bitshift;
+
+	rtl_dbg(rtlpriv, COMP_RF, DBG_TRACE,
+		"regaddr(%#x), bitmask(%#x), data(%#x)\n",
+		regaddr, bitmask, data);
+
+	if (rtlhal->during_mac1init_radioa)
+		regaddr |= MAC1_ACCESS_PHY0;
+	else if (rtlhal->during_mac0init_radiob)
+		regaddr |= MAC0_ACCESS_PHY1;
+
+	if (bitmask != MASKDWORD) {
+		originalvalue = rtl_read_dword(rtlpriv, regaddr);
+		bitshift = calculate_bit_shift(bitmask);
+		data = (originalvalue & (~bitmask)) |
+			((data << bitshift) & bitmask);
+	}
+
+	rtl_write_dword(rtlpriv, regaddr, data);
+	rtl_dbg(rtlpriv, COMP_RF, DBG_TRACE,
+		"regaddr(%#x), bitmask(%#x), data(%#x)\n",
+		regaddr, bitmask, data);
+}
+
+/* To avoid miswrite Reg0x800 for 92D */
+static void rtl92du_phy_set_bb_reg_1byte(struct ieee80211_hw *hw,
+					 u32 regaddr, u32 bitmask, u32 data)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	u32 originalvalue, bitshift, offset;
+	u8 value;
+
+	/* BitMask only support bit0~bit7 or bit8~bit15, bit16~bit23,
+	 * bit24~bit31, should be in 1 byte scale;
+	 */
+	bitshift = calculate_bit_shift(bitmask);
+	offset = bitshift / 8;
+
+	originalvalue = rtl_read_dword(rtlpriv, regaddr);
+	data = (originalvalue & (~bitmask)) | ((data << bitshift) & bitmask);
+
+	value = data >> (8 * offset);
+
+	rtl_write_byte(rtlpriv, regaddr + offset, value);
+}
+
+bool rtl92du_phy_mac_config(struct ieee80211_hw *hw)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	u32 arraylength;
+	const u32 *ptrarray;
+	u32 i;
+
+	rtl_dbg(rtlpriv, COMP_INIT, DBG_TRACE, "Read Rtl819XMACPHY_Array\n");
+
+	arraylength = MAC_2T_ARRAYLENGTH;
+	ptrarray = rtl8192du_mac_2tarray;
+
+	for (i = 0; i < arraylength; i = i + 2)
+		rtl_write_byte(rtlpriv, ptrarray[i], (u8)ptrarray[i + 1]);
+
+	if (rtlpriv->rtlhal.macphymode == SINGLEMAC_SINGLEPHY) {
+		/* improve 2-stream TX EVM */
+		/* rtl_write_byte(rtlpriv, 0x14,0x71); */
+		/* AMPDU aggregation number 9 */
+		/* rtl_write_word(rtlpriv, REG_MAX_AGGR_NUM, MAX_AGGR_NUM); */
+		rtl_write_byte(rtlpriv, REG_MAX_AGGR_NUM, 0x0B);
+	} else {
+		/* 92D need to test to decide the num. */
+		rtl_write_byte(rtlpriv, REG_MAX_AGGR_NUM, 0x07);
+	}
+
+	return true;
+}
+
+static bool _rtl92du_phy_config_bb(struct ieee80211_hw *hw, u8 configtype)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_hal *rtlhal = rtl_hal(rtlpriv);
+	u16 phy_reg_arraylen, agctab_arraylen = 0;
+	const u32 *agctab_array_table = NULL;
+	const u32 *phy_regarray_table;
+	int i;
+
+	/* Normal chip, Mac0 use AGC_TAB.txt for 2G and 5G band. */
+	if (rtlhal->interfaceindex == 0) {
+		agctab_arraylen = AGCTAB_ARRAYLENGTH;
+		agctab_array_table = rtl8192du_agctab_array;
+		rtl_dbg(rtlpriv, COMP_INIT, DBG_LOUD,
+			" ===> phy:MAC0, Rtl819XAGCTAB_Array\n");
+	} else {
+		if (rtlhal->current_bandtype == BAND_ON_2_4G) {
+			agctab_arraylen = AGCTAB_2G_ARRAYLENGTH;
+			agctab_array_table = rtl8192du_agctab_2garray;
+			rtl_dbg(rtlpriv, COMP_INIT, DBG_LOUD,
+				" ===> phy:MAC1, Rtl819XAGCTAB_2GArray\n");
+		} else {
+			agctab_arraylen = AGCTAB_5G_ARRAYLENGTH;
+			agctab_array_table = rtl8192du_agctab_5garray;
+			rtl_dbg(rtlpriv, COMP_INIT, DBG_LOUD,
+				" ===> phy:MAC1, Rtl819XAGCTAB_5GArray\n");
+		}
+	}
+	phy_reg_arraylen = PHY_REG_2T_ARRAYLENGTH;
+	phy_regarray_table = rtl8192du_phy_reg_2tarray;
+	rtl_dbg(rtlpriv, COMP_INIT, DBG_LOUD,
+		" ===> phy:Rtl819XPHY_REG_Array_PG\n");
+
+	if (configtype == BASEBAND_CONFIG_PHY_REG) {
+		for (i = 0; i < phy_reg_arraylen; i = i + 2) {
+			rtl_addr_delay(phy_regarray_table[i]);
+			rtl_set_bbreg(hw, phy_regarray_table[i], MASKDWORD,
+				      phy_regarray_table[i + 1]);
+			udelay(1);
+			rtl_dbg(rtlpriv, COMP_INIT, DBG_TRACE,
+				"The phy_regarray_table[0] is %x Rtl819XPHY_REGArray[1] is %x\n",
+				phy_regarray_table[i],
+				phy_regarray_table[i + 1]);
+		}
+	} else if (configtype == BASEBAND_CONFIG_AGC_TAB) {
+		for (i = 0; i < agctab_arraylen; i = i + 2) {
+			rtl_set_bbreg(hw, agctab_array_table[i],
+				      MASKDWORD, agctab_array_table[i + 1]);
+
+			/* Add 1us delay between BB/RF register setting. */
+			udelay(1);
+
+			rtl_dbg(rtlpriv, COMP_INIT, DBG_TRACE,
+				"AGC table %u %u\n",
+				agctab_array_table[i],
+				agctab_array_table[i + 1]);
+		}
+		rtl_dbg(rtlpriv, COMP_INIT, DBG_LOUD,
+			"Normal Chip, loaded AGC table\n");
+	}
+	return true;
+}
+
+static bool _rtl92du_phy_config_bb_pg(struct ieee80211_hw *hw, u8 configtype)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	const u32 *phy_regarray_table_pg;
+	u16 phy_regarray_pg_len;
+	int i;
+
+	phy_regarray_pg_len = PHY_REG_ARRAY_PG_LENGTH;
+	phy_regarray_table_pg = rtl8192du_phy_reg_array_pg;
+
+	if (configtype == BASEBAND_CONFIG_PHY_REG) {
+		for (i = 0; i < phy_regarray_pg_len; i = i + 3) {
+			rtl_addr_delay(phy_regarray_table_pg[i]);
+			rtl92d_store_pwrindex_diffrate_offset(hw,
+				phy_regarray_table_pg[i],
+				phy_regarray_table_pg[i + 1],
+				phy_regarray_table_pg[i + 2]);
+		}
+	} else {
+		rtl_dbg(rtlpriv, COMP_SEND, DBG_TRACE,
+			"configtype != BaseBand_Config_PHY_REG\n");
+	}
+	return true;
+}
+
+static bool _rtl92du_phy_bb_config(struct ieee80211_hw *hw)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_efuse *rtlefuse = rtl_efuse(rtlpriv);
+	struct rtl_phy *rtlphy = &rtlpriv->phy;
+	bool ret;
+
+	rtl_dbg(rtlpriv, COMP_INIT, DBG_TRACE, "==>\n");
+	ret = _rtl92du_phy_config_bb(hw, BASEBAND_CONFIG_PHY_REG);
+	if (!ret) {
+		pr_err("Write BB Reg Fail!!\n");
+		return false;
+	}
+
+	if (!rtlefuse->autoload_failflag) {
+		rtlphy->pwrgroup_cnt = 0;
+		ret = _rtl92du_phy_config_bb_pg(hw, BASEBAND_CONFIG_PHY_REG);
+	}
+	if (!ret) {
+		pr_err("BB_PG Reg Fail!!\n");
+		return false;
+	}
+
+	ret = _rtl92du_phy_config_bb(hw, BASEBAND_CONFIG_AGC_TAB);
+	if (!ret) {
+		pr_err("AGC Table Fail\n");
+		return false;
+	}
+
+	rtlphy->cck_high_power = (bool)rtl_get_bbreg(hw,
+						     RFPGA0_XA_HSSIPARAMETER2,
+						     0x200);
+
+	return true;
+}
+
+bool rtl92du_phy_bb_config(struct ieee80211_hw *hw)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_hal *rtlhal = rtl_hal(rtlpriv);
+	bool rtstatus;
+	u32 regvaldw;
+	u16 regval;
+	u8 value;
+
+	rtl92d_phy_init_bb_rf_register_definition(hw);
+
+	regval = rtl_read_word(rtlpriv, REG_SYS_FUNC_EN);
+	rtl_write_word(rtlpriv, REG_SYS_FUNC_EN,
+		       regval | BIT(13) | BIT(0) | BIT(1));
+
+	rtl_write_byte(rtlpriv, REG_AFE_PLL_CTRL, 0x83);
+	rtl_write_byte(rtlpriv, REG_AFE_PLL_CTRL + 1, 0xdb);
+
+	/* 0x1f bit7 bit6 represent for mac0/mac1 driver ready */
+	value = rtl_read_byte(rtlpriv, REG_RF_CTRL);
+	rtl_write_byte(rtlpriv, REG_RF_CTRL, value | RF_EN | RF_RSTB |
+		RF_SDMRSTB);
+
+	value = FEN_BB_GLB_RSTN | FEN_BBRSTB;
+	if (rtlhal->interface == INTF_PCI)
+		value |= FEN_PPLL | FEN_PCIEA | FEN_DIO_PCIE;
+	else if (rtlhal->interface == INTF_USB)
+		value |= FEN_USBA | FEN_USBD;
+	rtl_write_byte(rtlpriv, REG_SYS_FUNC_EN, value);
+
+	regvaldw = rtl_read_dword(rtlpriv, RFPGA0_XCD_RFPARAMETER);
+	regvaldw &= ~BIT(31);
+	rtl_write_dword(rtlpriv, RFPGA0_XCD_RFPARAMETER, regvaldw);
+
+	/* To Fix MAC loopback mode fail. */
+	rtl_write_byte(rtlpriv, REG_LDOHCI12_CTRL, 0x0f);
+	rtl_write_byte(rtlpriv, 0x15, 0xe9);
+
+	rtl_write_byte(rtlpriv, REG_AFE_XTAL_CTRL + 1, 0x80);
+	if (!(IS_92D_SINGLEPHY(rtlpriv->rtlhal.version)) &&
+	    rtlhal->interface == INTF_PCI) {
+		regvaldw = rtl_read_dword(rtlpriv, REG_LEDCFG0);
+		rtl_write_dword(rtlpriv, REG_LEDCFG0, regvaldw | BIT(23));
+	}
+
+	rtstatus = _rtl92du_phy_bb_config(hw);
+
+	/* Crystal calibration */
+	rtl_set_bbreg(hw, REG_AFE_XTAL_CTRL, 0xf0,
+		      rtlpriv->efuse.crystalcap & 0x0f);
+	rtl_set_bbreg(hw, REG_AFE_PLL_CTRL, 0xf0000000,
+		      (rtlpriv->efuse.crystalcap & 0xf0) >> 4);
+
+	return rtstatus;
+}
+
+bool rtl92du_phy_rf_config(struct ieee80211_hw *hw)
+{
+	return rtl92du_phy_rf6052_config(hw);
+}
+
+bool rtl92du_phy_config_rf_with_headerfile(struct ieee80211_hw *hw,
+					   enum rf_content content,
+					   enum radio_path rfpath)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	u16 radioa_arraylen, radiob_arraylen;
+	const u32 *radioa_array_table;
+	const u32 *radiob_array_table;
+	int i;
+
+	radioa_arraylen = RADIOA_2T_ARRAYLENGTH;
+	radioa_array_table = rtl8192du_radioa_2tarray;
+	radiob_arraylen = RADIOB_2T_ARRAYLENGTH;
+	radiob_array_table = rtl8192du_radiob_2tarray;
+	if (rtlpriv->efuse.internal_pa_5g[0]) {
+		radioa_arraylen = RADIOA_2T_INT_PA_ARRAYLENGTH;
+		radioa_array_table = rtl8192du_radioa_2t_int_paarray;
+	}
+	if (rtlpriv->efuse.internal_pa_5g[1]) {
+		radiob_arraylen = RADIOB_2T_INT_PA_ARRAYLENGTH;
+		radiob_array_table = rtl8192du_radiob_2t_int_paarray;
+	}
+	rtl_dbg(rtlpriv, COMP_INIT, DBG_LOUD,
+		"PHY_ConfigRFWithHeaderFile() Radio_A:Rtl819XRadioA_1TArray\n");
+	rtl_dbg(rtlpriv, COMP_INIT, DBG_LOUD,
+		"PHY_ConfigRFWithHeaderFile() Radio_B:Rtl819XRadioB_1TArray\n");
+	rtl_dbg(rtlpriv, COMP_INIT, DBG_TRACE, "Radio No %x\n", rfpath);
+
+	/* this only happens when DMDP, mac0 start on 2.4G,
+	 * mac1 start on 5G, mac 0 has to set phy0 & phy1
+	 * pathA or mac1 has to set phy0 & phy1 pathA
+	 */
+	if (content == radiob_txt && rfpath == RF90_PATH_A) {
+		rtl_dbg(rtlpriv, COMP_INIT, DBG_LOUD,
+			" ===> althougth Path A, we load radiob.txt\n");
+		radioa_arraylen = radiob_arraylen;
+		radioa_array_table = radiob_array_table;
+	}
+
+	switch (rfpath) {
+	case RF90_PATH_A:
+		for (i = 0; i < radioa_arraylen; i = i + 2) {
+			rtl_rfreg_delay(hw, rfpath, radioa_array_table[i],
+					RFREG_OFFSET_MASK,
+					radioa_array_table[i + 1]);
+		}
+		break;
+	case RF90_PATH_B:
+		for (i = 0; i < radiob_arraylen; i = i + 2) {
+			rtl_rfreg_delay(hw, rfpath, radiob_array_table[i],
+					RFREG_OFFSET_MASK,
+					radiob_array_table[i + 1]);
+		}
+		break;
+	case RF90_PATH_C:
+	case RF90_PATH_D:
+		pr_err("switch case %#x not processed\n", rfpath);
+		break;
+	}
+
+	return true;
+}
+
+void rtl92du_phy_set_bw_mode(struct ieee80211_hw *hw,
+			     enum nl80211_channel_type ch_type)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_hal *rtlhal = rtl_hal(rtlpriv);
+	struct rtl_phy *rtlphy = &rtlpriv->phy;
+	struct rtl_mac *mac = rtl_mac(rtlpriv);
+	u8 reg_bw_opmode;
+	u8 reg_prsr_rsc;
+
+	if (rtlphy->set_bwmode_inprogress)
+		return;
+
+	if ((is_hal_stop(rtlhal)) || (RT_CANNOT_IO(hw))) {
+		rtl_dbg(rtlpriv, COMP_ERR, DBG_WARNING,
+			"FALSE driver sleep or unload\n");
+		return;
+	}
+
+	rtlphy->set_bwmode_inprogress = true;
+
+	rtl_dbg(rtlpriv, COMP_SCAN, DBG_TRACE, "Switch to %s bandwidth\n",
+		rtlphy->current_chan_bw == HT_CHANNEL_WIDTH_20 ?
+		"20MHz" : "40MHz");
+
+	reg_bw_opmode = rtl_read_byte(rtlpriv, REG_BWOPMODE);
+	reg_prsr_rsc = rtl_read_byte(rtlpriv, REG_RRSR + 2);
+
+	switch (rtlphy->current_chan_bw) {
+	case HT_CHANNEL_WIDTH_20:
+		reg_bw_opmode |= BW_OPMODE_20MHZ;
+		rtl_write_byte(rtlpriv, REG_BWOPMODE, reg_bw_opmode);
+		break;
+	case HT_CHANNEL_WIDTH_20_40:
+		reg_bw_opmode &= ~BW_OPMODE_20MHZ;
+		rtl_write_byte(rtlpriv, REG_BWOPMODE, reg_bw_opmode);
+
+		reg_prsr_rsc = (reg_prsr_rsc & 0x90) |
+			       (mac->cur_40_prime_sc << 5);
+		rtl_write_byte(rtlpriv, REG_RRSR + 2, reg_prsr_rsc);
+		break;
+	default:
+		pr_err("unknown bandwidth: %#X\n",
+		       rtlphy->current_chan_bw);
+		break;
+	}
+
+	switch (rtlphy->current_chan_bw) {
+	case HT_CHANNEL_WIDTH_20:
+		rtl92du_phy_set_bb_reg_1byte(hw, RFPGA0_RFMOD, BRFMOD, 0x0);
+		rtl_set_bbreg(hw, RFPGA1_RFMOD, BRFMOD, 0x0);
+		/* SET BIT10 BIT11  for receive cck */
+		rtl_set_bbreg(hw, RFPGA0_ANALOGPARAMETER2, BIT(10) | BIT(11), 3);
+		break;
+	case HT_CHANNEL_WIDTH_20_40:
+		rtl92du_phy_set_bb_reg_1byte(hw, RFPGA0_RFMOD, BRFMOD, 0x1);
+		rtl_set_bbreg(hw, RFPGA1_RFMOD, BRFMOD, 0x1);
+		/* Set Control channel to upper or lower.
+		 * These settings are required only for 40MHz
+		 */
+		if (rtlhal->current_bandtype == BAND_ON_2_4G)
+			rtl_set_bbreg(hw, RCCK0_SYSTEM, BCCKSIDEBAND,
+				      mac->cur_40_prime_sc >> 1);
+		rtl_set_bbreg(hw, ROFDM1_LSTF, 0xC00, mac->cur_40_prime_sc);
+		/* SET BIT10 BIT11  for receive cck */
+		rtl_set_bbreg(hw, RFPGA0_ANALOGPARAMETER2,
+			      BIT(10) | BIT(11), 0);
+		rtl_set_bbreg(hw, 0x818, BIT(26) | BIT(27),
+			      mac->cur_40_prime_sc ==
+			      HAL_PRIME_CHNL_OFFSET_LOWER ? 2 : 1);
+		break;
+	default:
+		pr_err("unknown bandwidth: %#X\n",
+		       rtlphy->current_chan_bw);
+		break;
+	}
+
+	rtl92d_phy_rf6052_set_bandwidth(hw, rtlphy->current_chan_bw);
+
+	rtlphy->set_bwmode_inprogress = false;
+	rtl_dbg(rtlpriv, COMP_SCAN, DBG_TRACE, "<==\n");
+}
+
+static void _rtl92du_phy_stop_trx_before_changeband(struct ieee80211_hw *hw)
+{
+	rtl92du_phy_set_bb_reg_1byte(hw, RFPGA0_RFMOD, BCCKEN | BOFDMEN, 0);
+	rtl_set_bbreg(hw, ROFDM0_TRXPATHENABLE, MASKBYTE0, 0x00);
+	rtl_set_bbreg(hw, ROFDM1_TRXPATHENABLE, BDWORD, 0x0);
+}
+
+static void rtl92du_phy_switch_wirelessband(struct ieee80211_hw *hw, u8 band)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_hal *rtlhal = rtl_hal(rtlpriv);
+	u16 basic_rates;
+	u32 reg_mac;
+	u8 value8;
+
+	rtl_dbg(rtlpriv, COMP_INIT, DBG_LOUD, "==>\n");
+	rtlhal->bandset = band;
+	rtlhal->current_bandtype = band;
+	if (IS_92D_SINGLEPHY(rtlhal->version))
+		rtlhal->bandset = BAND_ON_BOTH;
+
+	/* stop RX/Tx */
+	_rtl92du_phy_stop_trx_before_changeband(hw);
+
+	/* reconfig BB/RF according to wireless mode */
+	if (rtlhal->current_bandtype == BAND_ON_2_4G)
+		/* BB & RF Config */
+		rtl_dbg(rtlpriv, COMP_CMD, DBG_DMESG, "====>2.4G\n");
+	else
+		/* 5G band */
+		rtl_dbg(rtlpriv, COMP_CMD, DBG_DMESG, "====>5G\n");
+
+	if (rtlhal->interfaceindex == 1)
+		_rtl92du_phy_config_bb(hw, BASEBAND_CONFIG_AGC_TAB);
+
+	rtl92du_update_bbrf_configuration(hw);
+
+	basic_rates = RRSR_6M | RRSR_12M | RRSR_24M;
+	if (rtlhal->current_bandtype == BAND_ON_2_4G)
+		basic_rates |= RRSR_1M | RRSR_2M | RRSR_5_5M | RRSR_11M;
+	rtlpriv->cfg->ops->set_hw_reg(hw, HW_VAR_BASIC_RATE,
+				      (u8 *)&basic_rates);
+
+	rtl92du_phy_set_bb_reg_1byte(hw, RFPGA0_RFMOD, BCCKEN | BOFDMEN, 0x3);
+
+	/* 20M BW. */
+	/* rtl_set_bbreg(hw, RFPGA0_ANALOGPARAMETER2, BIT(10), 1); */
+	rtlhal->reloadtxpowerindex = true;
+
+	reg_mac = rtlhal->interfaceindex == 0 ? REG_MAC0 : REG_MAC1;
+
+	/* notice fw know band status  0x81[1]/0x53[1] = 0: 5G, 1: 2G */
+	if (rtlhal->current_bandtype == BAND_ON_2_4G) {
+		value8 = rtl_read_byte(rtlpriv,	reg_mac);
+		value8 |= BIT(1);
+		rtl_write_byte(rtlpriv, reg_mac, value8);
+	} else {
+		value8 = rtl_read_byte(rtlpriv, reg_mac);
+		value8 &= ~BIT(1);
+		rtl_write_byte(rtlpriv, reg_mac, value8);
+	}
+	mdelay(1);
+	rtl_dbg(rtlpriv, COMP_INIT, DBG_LOUD, "<==Switch Band OK\n");
+}
+
+static void _rtl92du_phy_reload_imr_setting(struct ieee80211_hw *hw,
+					    u8 channel, u8 rfpath)
+{
+	struct rtl_usb *rtlusb = rtl_usbdev(rtl_usbpriv(hw));
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	u8 group, i;
+
+	if (rtlusb->udev->speed != USB_SPEED_HIGH)
+		return;
+
+	rtl_dbg(rtlpriv, COMP_CMD, DBG_LOUD, "====>path %d\n", rfpath);
+	if (rtlpriv->rtlhal.current_bandtype == BAND_ON_5G) {
+		rtl_dbg(rtlpriv, COMP_CMD, DBG_LOUD, "====>5G\n");
+		rtl92du_phy_set_bb_reg_1byte(hw, RFPGA0_RFMOD,
+					     BOFDMEN | BCCKEN, 0);
+		rtl_set_bbreg(hw, RFPGA0_ANALOGPARAMETER4, 0x00f00000, 0xf);
+
+		/* fc area 0xd2c */
+		if (channel >= 149)
+			rtl_set_bbreg(hw, ROFDM1_CFOTRACKING, BIT(13) |
+				      BIT(14), 2);
+		else
+			rtl_set_bbreg(hw, ROFDM1_CFOTRACKING, BIT(13) |
+				      BIT(14), 1);
+
+		/* leave 0 for channel1-14. */
+		group = channel <= 64 ? 1 : 2;
+		for (i = 0; i < MAX_RF_IMR_INDEX_NORMAL; i++)
+			rtl_set_rfreg(hw, (enum radio_path)rfpath,
+				      rf_reg_for_5g_swchnl_normal[i],
+				      RFREG_OFFSET_MASK,
+				      rf_imr_param_normal[group][i]);
+
+		rtl_set_bbreg(hw, RFPGA0_ANALOGPARAMETER4, 0x00f00000, 0);
+		rtl92du_phy_set_bb_reg_1byte(hw, RFPGA0_RFMOD,
+					     BOFDMEN | BCCKEN, 3);
+	} else {
+		/* G band. */
+		rtl_dbg(rtlpriv, COMP_SCAN, DBG_LOUD,
+			"Load RF IMR parameters for G band. IMR already setting %d\n",
+			rtlpriv->rtlhal.load_imrandiqk_setting_for2g);
+		rtl_dbg(rtlpriv, COMP_CMD, DBG_LOUD, "====>2.4G\n");
+
+		if (!rtlpriv->rtlhal.load_imrandiqk_setting_for2g) {
+			rtl_dbg(rtlpriv, COMP_SCAN, DBG_LOUD,
+				"Load RF IMR parameters for G band. %d\n",
+				rfpath);
+			rtl92du_phy_set_bb_reg_1byte(hw, RFPGA0_RFMOD,
+						     BOFDMEN | BCCKEN, 0);
+			rtl_set_bbreg(hw, RFPGA0_ANALOGPARAMETER4,
+				      0x00f00000, 0xf);
+
+			for (i = 0; i < MAX_RF_IMR_INDEX_NORMAL; i++) {
+				rtl_set_rfreg(hw, (enum radio_path)rfpath,
+					      rf_reg_for_5g_swchnl_normal[i],
+					      RFREG_OFFSET_MASK,
+					      rf_imr_param_normal[0][i]);
+			}
+
+			rtl_set_bbreg(hw, RFPGA0_ANALOGPARAMETER4,
+				      0x00f00000, 0);
+			rtl92du_phy_set_bb_reg_1byte(hw, RFPGA0_RFMOD,
+						     BOFDMEN | BCCKEN, 3);
+		}
+	}
+	rtl_dbg(rtlpriv, COMP_CMD, DBG_LOUD, "<====\n");
+}
+
+static void _rtl92du_phy_switch_rf_setting(struct ieee80211_hw *hw, u8 channel)
+{
+	struct rtl_usb *rtlusb = rtl_usbdev(rtl_usbpriv(hw));
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_hal *rtlhal = &rtlpriv->rtlhal;
+	struct rtl_phy *rtlphy = &rtlpriv->phy;
+	u8 path = rtlhal->current_bandtype == BAND_ON_5G ? RF90_PATH_A
+							 : RF90_PATH_B;
+	u32 u4regvalue, mask = 0x1C000, value = 0, u4tmp, u4tmp2;
+	bool need_pwr_down = false, internal_pa = false;
+	u32 regb30 = rtl_get_bbreg(hw, 0xb30, BIT(27));
+	u8 index = 0, i, rfpath;
+
+	if (rtlusb->udev->speed != USB_SPEED_HIGH)
+		return;
+
+	rtl_dbg(rtlpriv, COMP_CMD, DBG_LOUD, "====>\n");
+	/* config path A for 5G */
+	if (rtlhal->current_bandtype == BAND_ON_5G) {
+		rtl_dbg(rtlpriv, COMP_CMD, DBG_LOUD, "====>5G\n");
+		u4tmp = rtlpriv->curveindex_5g[channel - 1];
+		RTPRINT(rtlpriv, FINIT, INIT_IQK,
+			"ver 1 set RF-A, 5G, 0x28 = 0x%x !!\n", u4tmp);
+
+		for (i = 0; i < RF_CHNL_NUM_5G; i++) {
+			if (channel == rf_chnl_5g[i] && channel <= 140)
+				index = 0;
+		}
+		for (i = 0; i < RF_CHNL_NUM_5G_40M; i++) {
+			if (channel == rf_chnl_5g_40m[i] && channel <= 140)
+				index = 1;
+		}
+		if (channel == 149 || channel == 155 || channel == 161)
+			index = 2;
+		else if (channel == 151 || channel == 153 || channel == 163 ||
+			 channel == 165)
+			index = 3;
+		else if (channel == 157 || channel == 159)
+			index = 4;
+
+		if (rtlhal->macphymode == DUALMAC_DUALPHY &&
+		    rtlhal->interfaceindex == 1) {
+			need_pwr_down = rtl92du_phy_enable_anotherphy(hw, false);
+			rtlhal->during_mac1init_radioa = true;
+			/* asume no this case */
+			if (need_pwr_down)
+				rtl92d_phy_enable_rf_env(hw, path,
+							 &u4regvalue);
+		}
+
+		/* DMDP, if band = 5G, Mac0 need to set PHY1 when regB30[27]=1 */
+		if (regb30 && rtlhal->interfaceindex == 0) {
+			need_pwr_down = rtl92du_phy_enable_anotherphy(hw, true);
+			rtlhal->during_mac0init_radiob = true;
+			if (need_pwr_down)
+				rtl92d_phy_enable_rf_env(hw, path,
+							 &u4regvalue);
+		}
+
+		for (i = 0; i < RF_REG_NUM_FOR_C_CUT_5G; i++) {
+			if (i == 0 && rtlhal->macphymode == DUALMAC_DUALPHY) {
+				rtl_set_rfreg(hw, (enum radio_path)path,
+					      rf_reg_for_c_cut_5g[i],
+					      RFREG_OFFSET_MASK, 0xE439D);
+			} else if (rf_reg_for_c_cut_5g[i] == RF_SYN_G4) {
+				u4tmp2 = (rf_reg_pram_c_5g[index][i] &
+				     0x7FF) | (u4tmp << 11);
+				if (channel == 36)
+					u4tmp2 &= ~(BIT(7) | BIT(6));
+				rtl_set_rfreg(hw, (enum radio_path)path,
+					      rf_reg_for_c_cut_5g[i],
+					      RFREG_OFFSET_MASK, u4tmp2);
+			} else {
+				rtl_set_rfreg(hw, (enum radio_path)path,
+					      rf_reg_for_c_cut_5g[i],
+					      RFREG_OFFSET_MASK,
+					      rf_reg_pram_c_5g[index][i]);
+			}
+			rtl_dbg(rtlpriv, COMP_RF, DBG_TRACE,
+				"offset 0x%x value 0x%x path %d index %d readback 0x%x\n",
+				rf_reg_for_c_cut_5g[i],
+				rf_reg_pram_c_5g[index][i],
+				path, index,
+				rtl_get_rfreg(hw, (enum radio_path)path,
+					      rf_reg_for_c_cut_5g[i],
+					      RFREG_OFFSET_MASK));
+		}
+		if (rtlhal->macphymode == DUALMAC_DUALPHY &&
+		    rtlhal->interfaceindex == 1) {
+			if (need_pwr_down)
+				rtl92d_phy_restore_rf_env(hw, path, &u4regvalue);
+
+			rtl92du_phy_powerdown_anotherphy(hw, false);
+		}
+
+		if (regb30 && rtlhal->interfaceindex == 0) {
+			if (need_pwr_down)
+				rtl92d_phy_restore_rf_env(hw, path, &u4regvalue);
+
+			rtl92du_phy_powerdown_anotherphy(hw, true);
+		}
+
+		if (channel < 149)
+			value = 0x07;
+		else if (channel >= 149)
+			value = 0x02;
+		if (channel >= 36 && channel <= 64)
+			index = 0;
+		else if (channel >= 100 && channel <= 140)
+			index = 1;
+		else
+			index = 2;
+
+		for (rfpath = RF90_PATH_A; rfpath < rtlphy->num_total_rfpath;
+			rfpath++) {
+			if (rtlhal->macphymode == DUALMAC_DUALPHY &&
+			    rtlhal->interfaceindex == 1) /* MAC 1 5G */
+				internal_pa = rtlpriv->efuse.internal_pa_5g[1];
+			else
+				internal_pa =
+					 rtlpriv->efuse.internal_pa_5g[rfpath];
+
+			if (internal_pa) {
+				for (i = 0;
+				     i < RF_REG_NUM_FOR_C_CUT_5G_INTERNALPA;
+				     i++) {
+					if (rf_for_c_cut_5g_internal_pa[i] == 0x03 &&
+					    channel >= 36 && channel <= 64)
+						rtl_set_rfreg(hw, rfpath,
+							rf_for_c_cut_5g_internal_pa[i],
+							RFREG_OFFSET_MASK,
+							0x7bdef);
+					else
+						rtl_set_rfreg(hw, rfpath,
+							rf_for_c_cut_5g_internal_pa[i],
+							RFREG_OFFSET_MASK,
+							rf_pram_c_5g_int_pa[index][i]);
+					rtl_dbg(rtlpriv, COMP_RF, DBG_LOUD,
+						"offset 0x%x value 0x%x path %d index %d\n",
+						rf_for_c_cut_5g_internal_pa[i],
+						rf_pram_c_5g_int_pa[index][i],
+						rfpath, index);
+				}
+			} else {
+				rtl_set_rfreg(hw, (enum radio_path)rfpath, RF_TXPA_AG,
+					      mask, value);
+			}
+		}
+	} else if (rtlhal->current_bandtype == BAND_ON_2_4G) {
+		rtl_dbg(rtlpriv, COMP_CMD, DBG_LOUD, "====>2.4G\n");
+		u4tmp = rtlpriv->curveindex_2g[channel - 1];
+		RTPRINT(rtlpriv, FINIT, INIT_IQK,
+			"ver 3 set RF-B, 2G, 0x28 = 0x%x !!\n", u4tmp);
+
+		if (channel == 1 || channel == 2 || channel == 4 ||
+		    channel == 9 || channel == 10 || channel == 11 ||
+		    channel == 12)
+			index = 0;
+		else if (channel == 3 || channel == 13 || channel == 14)
+			index = 1;
+		else if (channel >= 5 && channel <= 8)
+			index = 2;
+
+		if (rtlhal->macphymode == DUALMAC_DUALPHY) {
+			path = RF90_PATH_A;
+			if (rtlhal->interfaceindex == 0) {
+				need_pwr_down =
+					 rtl92du_phy_enable_anotherphy(hw, true);
+				rtlhal->during_mac0init_radiob = true;
+
+				if (need_pwr_down)
+					rtl92d_phy_enable_rf_env(hw, path,
+								 &u4regvalue);
+			}
+
+			/* DMDP, if band = 2G, MAC1 need to set PHY0 when regB30[27]=1 */
+			if (regb30 && rtlhal->interfaceindex == 1) {
+				need_pwr_down =
+					 rtl92du_phy_enable_anotherphy(hw, false);
+				rtlhal->during_mac1init_radioa = true;
+
+				if (need_pwr_down)
+					rtl92d_phy_enable_rf_env(hw, path,
+								 &u4regvalue);
+			}
+		}
+
+		for (i = 0; i < RF_REG_NUM_FOR_C_CUT_2G; i++) {
+			if (rf_reg_for_c_cut_2g[i] == RF_SYN_G7)
+				rtl_set_rfreg(hw, (enum radio_path)path,
+					      rf_reg_for_c_cut_2g[i],
+					      RFREG_OFFSET_MASK,
+					      rf_reg_param_for_c_cut_2g[index][i] |
+					      BIT(17));
+			else
+				rtl_set_rfreg(hw, (enum radio_path)path,
+					      rf_reg_for_c_cut_2g[i],
+					      RFREG_OFFSET_MASK,
+					      rf_reg_param_for_c_cut_2g
+					      [index][i]);
+
+			rtl_dbg(rtlpriv, COMP_RF, DBG_TRACE,
+				"offset 0x%x value 0x%x mak 0x%x path %d index %d readback 0x%x\n",
+				rf_reg_for_c_cut_2g[i],
+				rf_reg_param_for_c_cut_2g[index][i],
+				rf_reg_mask_for_c_cut_2g[i], path, index,
+				rtl_get_rfreg(hw, (enum radio_path)path,
+					      rf_reg_for_c_cut_2g[i],
+					      RFREG_OFFSET_MASK));
+		}
+		RTPRINT(rtlpriv, FINIT, INIT_IQK,
+			"cosa ver 3 set RF-B, 2G, 0x28 = 0x%x !!\n",
+			rf_syn_g4_for_c_cut_2g | (u4tmp << 11));
+
+		rtl_set_rfreg(hw, (enum radio_path)path, RF_SYN_G4,
+			      RFREG_OFFSET_MASK,
+			      rf_syn_g4_for_c_cut_2g | (u4tmp << 11));
+
+		if (rtlhal->macphymode == DUALMAC_DUALPHY &&
+		    rtlhal->interfaceindex == 0) {
+			if (need_pwr_down)
+				rtl92d_phy_restore_rf_env(hw, path, &u4regvalue);
+
+			rtl92du_phy_powerdown_anotherphy(hw, true);
+		}
+
+		if (regb30 && rtlhal->interfaceindex == 1) {
+			if (need_pwr_down)
+				rtl92d_phy_restore_rf_env(hw, path, &u4regvalue);
+
+			rtl92du_phy_powerdown_anotherphy(hw, false);
+		}
+	}
+	rtl_dbg(rtlpriv, COMP_CMD, DBG_LOUD, "<====\n");
+}
+
+/* bit0 = 1 => Tx OK, bit1 = 1 => Rx OK */
+static u8 _rtl92du_phy_patha_iqk(struct ieee80211_hw *hw, bool configpathb)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_hal *rtlhal = rtl_hal(rtl_priv(hw));
+	u32 regeac, rege94, rege9c, regea4;
+	u8 result = 0;
+
+	RTPRINT(rtlpriv, FINIT, INIT_IQK,  "Path-A IQK setting!\n");
+
+	if (rtlhal->interfaceindex == 0) {
+		rtl_set_bbreg(hw, RTX_IQK_TONE_A, MASKDWORD, 0x10008c1f);
+		rtl_set_bbreg(hw, RRX_IQK_TONE_A, MASKDWORD, 0x10008c1f);
+	} else {
+		rtl_set_bbreg(hw, RTX_IQK_TONE_A, MASKDWORD, 0x10008c22);
+		rtl_set_bbreg(hw, RRX_IQK_TONE_A, MASKDWORD, 0x10008c22);
+	}
+	rtl_set_bbreg(hw, RTX_IQK_PI_A, MASKDWORD, 0x82140102);
+	rtl_set_bbreg(hw, RRX_IQK_PI_A, MASKDWORD,
+		      configpathb ? 0x28160202 : 0x28160502);
+	/* path-B IQK setting */
+	if (configpathb) {
+		rtl_set_bbreg(hw, RTX_IQK_TONE_B, MASKDWORD, 0x10008c22);
+		rtl_set_bbreg(hw, RRX_IQK_TONE_B, MASKDWORD, 0x10008c22);
+		rtl_set_bbreg(hw, RTX_IQK_PI_B, MASKDWORD, 0x82140102);
+		rtl_set_bbreg(hw, RRX_IQK_PI_B, MASKDWORD, 0x28160206);
+	}
+
+	/* LO calibration setting */
+	RTPRINT(rtlpriv, FINIT, INIT_IQK,  "LO calibration setting!\n");
+	rtl_set_bbreg(hw, RIQK_AGC_RSP, MASKDWORD, 0x00462911);
+
+	/* One shot, path A LOK & IQK */
+	RTPRINT(rtlpriv, FINIT, INIT_IQK,  "One shot, path A LOK & IQK!\n");
+	rtl_set_bbreg(hw, RIQK_AGC_PTS, MASKDWORD, 0xf9000000);
+	rtl_set_bbreg(hw, RIQK_AGC_PTS, MASKDWORD, 0xf8000000);
+
+	RTPRINT(rtlpriv, FINIT, INIT_IQK,
+		"Delay %d ms for One shot, path A LOK & IQK\n",
+		IQK_DELAY_TIME);
+	mdelay(IQK_DELAY_TIME);
+
+	/* Check failed */
+	regeac = rtl_get_bbreg(hw, RRX_POWER_AFTER_IQK_A_2, MASKDWORD);
+	RTPRINT(rtlpriv, FINIT, INIT_IQK,  "0xeac = 0x%x\n", regeac);
+	rege94 = rtl_get_bbreg(hw, RTX_POWER_BEFORE_IQK_A, MASKDWORD);
+	RTPRINT(rtlpriv, FINIT, INIT_IQK,  "0xe94 = 0x%x\n", rege94);
+	rege9c = rtl_get_bbreg(hw, RTX_POWER_AFTER_IQK_A, MASKDWORD);
+	RTPRINT(rtlpriv, FINIT, INIT_IQK,  "0xe9c = 0x%x\n", rege9c);
+	regea4 = rtl_get_bbreg(hw, RRX_POWER_BEFORE_IQK_A_2, MASKDWORD);
+	RTPRINT(rtlpriv, FINIT, INIT_IQK,  "0xea4 = 0x%x\n", regea4);
+
+	if (!(regeac & BIT(28)) &&
+	    (((rege94 & 0x03FF0000) >> 16) != 0x142) &&
+	    (((rege9c & 0x03FF0000) >> 16) != 0x42))
+		result |= 0x01;
+	else /* if Tx not OK, ignore Rx */
+		return result;
+
+	/* if Tx is OK, check whether Rx is OK */
+	if (!(regeac & BIT(27)) &&
+	    (((regea4 & 0x03FF0000) >> 16) != 0x132) &&
+	    (((regeac & 0x03FF0000) >> 16) != 0x36))
+		result |= 0x02;
+	else
+		RTPRINT(rtlpriv, FINIT, INIT_IQK,  "Path A Rx IQK fail!!\n");
+
+	return result;
+}
+
+/* bit0 = 1 => Tx OK, bit1 = 1 => Rx OK */
+static u8 _rtl92du_phy_patha_iqk_5g_normal(struct ieee80211_hw *hw,
+					   bool configpathb)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_hal *rtlhal = rtl_hal(rtlpriv);
+	struct rtl_phy *rtlphy = &rtlpriv->phy;
+	u32 TXOKBIT = BIT(28), RXOKBIT = BIT(27);
+	u32 regeac, rege94, rege9c, regea4;
+	u8 timeout = 20, timecount = 0;
+	u8 retrycount = 2;
+	u8 result = 0;
+	u8 i;
+
+	if (rtlhal->interfaceindex == 1) { /* PHY1 */
+		TXOKBIT = BIT(31);
+		RXOKBIT = BIT(30);
+	}
+
+	RTPRINT(rtlpriv, FINIT, INIT_IQK,  "Path-A IQK setting!\n");
+	rtl_set_bbreg(hw, RTX_IQK_TONE_A, MASKDWORD, 0x18008c1f);
+	rtl_set_bbreg(hw, RRX_IQK_TONE_A, MASKDWORD, 0x18008c1f);
+	rtl_set_bbreg(hw, RTX_IQK_PI_A, MASKDWORD, 0x82140307);
+	rtl_set_bbreg(hw, RRX_IQK_PI_A, MASKDWORD, 0x68160960);
+	/* path-B IQK setting */
+	if (configpathb) {
+		rtl_set_bbreg(hw, RTX_IQK_TONE_B, MASKDWORD, 0x18008c2f);
+		rtl_set_bbreg(hw, RRX_IQK_TONE_B, MASKDWORD, 0x18008c2f);
+		rtl_set_bbreg(hw, RTX_IQK_PI_B, MASKDWORD, 0x82110000);
+		rtl_set_bbreg(hw, RRX_IQK_PI_B, MASKDWORD, 0x68110000);
+	}
+
+	/* LO calibration setting */
+	RTPRINT(rtlpriv, FINIT, INIT_IQK,  "LO calibration setting!\n");
+	rtl_set_bbreg(hw, RIQK_AGC_RSP, MASKDWORD, 0x00462911);
+
+	/* path-A PA on */
+	rtl_set_bbreg(hw, RFPGA0_XAB_RFINTERFACESW, MASKDWORD, 0x07000f60);
+	rtl_set_bbreg(hw, RFPGA0_XA_RFINTERFACEOE, MASKDWORD, 0x66e60e30);
+
+	for (i = 0; i < retrycount; i++) {
+		/* One shot, path A LOK & IQK */
+		RTPRINT(rtlpriv, FINIT, INIT_IQK,
+			"One shot, path A LOK & IQK!\n");
+		rtl_set_bbreg(hw, RIQK_AGC_PTS, MASKDWORD, 0xf9000000);
+		rtl_set_bbreg(hw, RIQK_AGC_PTS, MASKDWORD, 0xf8000000);
+
+		RTPRINT(rtlpriv, FINIT, INIT_IQK,
+			"Delay %d ms for One shot, path A LOK & IQK.\n",
+			IQK_DELAY_TIME);
+		mdelay(IQK_DELAY_TIME * 10);
+
+		while (timecount < timeout &&
+		       rtl_get_bbreg(hw, RRX_POWER_AFTER_IQK_A_2, BIT(26)) == 0) {
+			udelay(IQK_DELAY_TIME * 1000 * 2);
+			timecount++;
+		}
+
+		timecount = 0;
+		while (timecount < timeout &&
+		       rtl_get_bbreg(hw, RRX_POWER_BEFORE_IQK_A_2, MASK_IQK_RESULT) == 0) {
+			udelay(IQK_DELAY_TIME * 1000 * 2);
+			timecount++;
+		}
+
+		/* Check failed */
+		regeac = rtl_get_bbreg(hw, RRX_POWER_AFTER_IQK_A_2, MASKDWORD);
+		RTPRINT(rtlpriv, FINIT, INIT_IQK,  "0xeac = 0x%x\n", regeac);
+		rege94 = rtl_get_bbreg(hw, RTX_POWER_BEFORE_IQK_A, MASKDWORD);
+		RTPRINT(rtlpriv, FINIT, INIT_IQK,  "0xe94 = 0x%x\n", rege94);
+		rege9c = rtl_get_bbreg(hw, RTX_POWER_AFTER_IQK_A, MASKDWORD);
+		RTPRINT(rtlpriv, FINIT, INIT_IQK,  "0xe9c = 0x%x\n", rege9c);
+		regea4 = rtl_get_bbreg(hw, RRX_POWER_BEFORE_IQK_A_2, MASKDWORD);
+		RTPRINT(rtlpriv, FINIT, INIT_IQK,  "0xea4 = 0x%x\n", regea4);
+
+		if (!(regeac & TXOKBIT) &&
+		    (((rege94 & 0x03FF0000) >> 16) != 0x142)) {
+			result |= 0x01;
+		} else { /* if Tx not OK, ignore Rx */
+			RTPRINT(rtlpriv, FINIT, INIT_IQK,
+				"Path A Tx IQK fail!!\n");
+			continue;
+		}
+
+		/* if Tx is OK, check whether Rx is OK */
+		if (!(regeac & RXOKBIT) &&
+		    (((regea4 & 0x03FF0000) >> 16) != 0x132)) {
+			result |= 0x02;
+			break;
+		}
+		RTPRINT(rtlpriv, FINIT, INIT_IQK, "Path A Rx IQK fail!!\n");
+	}
+
+	/* path A PA off */
+	rtl_set_bbreg(hw, RFPGA0_XAB_RFINTERFACESW, MASKDWORD,
+		      rtlphy->iqk_bb_backup[0]);
+	rtl_set_bbreg(hw, RFPGA0_XA_RFINTERFACEOE, MASKDWORD,
+		      rtlphy->iqk_bb_backup[1]);
+
+	if (!(result & 0x01)) /* Tx IQK fail */
+		rtl_set_bbreg(hw, RTX_IQK_TONE_A, MASKDWORD, 0x19008c00);
+
+	if (!(result & 0x02)) { /* Rx IQK fail */
+		rtl_set_bbreg(hw, ROFDM0_XARXIQIMBALANCE, MASKDWORD, 0x40000100);
+		rtl_set_bbreg(hw, RRX_IQK_TONE_A, MASKDWORD, 0x19008c00);
+
+		RTPRINT(rtlpriv, FINIT, INIT_IQK,
+			"Path A Rx IQK fail!! 0xe34 = %#x\n",
+			rtl_get_bbreg(hw, RRX_IQK_TONE_A, MASKDWORD));
+	}
+
+	return result;
+}
+
+/* bit0 = 1 => Tx OK, bit1 = 1 => Rx OK */
+static u8 _rtl92du_phy_pathb_iqk(struct ieee80211_hw *hw)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	u32 regeac, regeb4, regebc, regec4, regecc;
+	u8 result = 0;
+
+	RTPRINT(rtlpriv, FINIT, INIT_IQK,  "One shot, path B LOK & IQK!\n");
+	rtl_set_bbreg(hw, RIQK_AGC_CONT, MASKDWORD, 0x00000002);
+	rtl_set_bbreg(hw, RIQK_AGC_CONT, MASKDWORD, 0x00000000);
+
+	RTPRINT(rtlpriv, FINIT, INIT_IQK,
+		"Delay %d ms for One shot, path B LOK & IQK\n", IQK_DELAY_TIME);
+	mdelay(IQK_DELAY_TIME);
+
+	/* Check failed */
+	regeac = rtl_get_bbreg(hw, RRX_POWER_AFTER_IQK_A_2, MASKDWORD);
+	RTPRINT(rtlpriv, FINIT, INIT_IQK,  "0xeac = 0x%x\n", regeac);
+	regeb4 = rtl_get_bbreg(hw, RTX_POWER_BEFORE_IQK_B, MASKDWORD);
+	RTPRINT(rtlpriv, FINIT, INIT_IQK,  "0xeb4 = 0x%x\n", regeb4);
+	regebc = rtl_get_bbreg(hw, RTX_POWER_AFTER_IQK_B, MASKDWORD);
+	RTPRINT(rtlpriv, FINIT, INIT_IQK,  "0xebc = 0x%x\n", regebc);
+	regec4 = rtl_get_bbreg(hw, RRX_POWER_BEFORE_IQK_B_2, MASKDWORD);
+	RTPRINT(rtlpriv, FINIT, INIT_IQK,  "0xec4 = 0x%x\n", regec4);
+	regecc = rtl_get_bbreg(hw, RRX_POWER_AFTER_IQK_B_2, MASKDWORD);
+	RTPRINT(rtlpriv, FINIT, INIT_IQK,  "0xecc = 0x%x\n", regecc);
+
+	if (!(regeac & BIT(31)) &&
+	    (((regeb4 & 0x03FF0000) >> 16) != 0x142) &&
+	    (((regebc & 0x03FF0000) >> 16) != 0x42))
+		result |= 0x01;
+	else
+		return result;
+
+	if (!(regeac & BIT(30)) &&
+	    (((regec4 & 0x03FF0000) >> 16) != 0x132) &&
+	    (((regecc & 0x03FF0000) >> 16) != 0x36))
+		result |= 0x02;
+	else
+		RTPRINT(rtlpriv, FINIT, INIT_IQK,  "Path B Rx IQK fail!!\n");
+
+	return result;
+}
+
+/* bit0 = 1 => Tx OK, bit1 = 1 => Rx OK */
+static u8 _rtl92du_phy_pathb_iqk_5g_normal(struct ieee80211_hw *hw)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_phy *rtlphy = &rtlpriv->phy;
+	u32 regeac, regeb4, regebc, regec4, regecc;
+	u8 timeout = 20, timecount = 0;
+	u8 retrycount = 2;
+	u8 result = 0;
+	u8 i;
+
+	RTPRINT(rtlpriv, FINIT, INIT_IQK,  "Path-B IQK setting!\n");
+	rtl_set_bbreg(hw, RTX_IQK_TONE_A, MASKDWORD, 0x18008c1f);
+	rtl_set_bbreg(hw, RRX_IQK_TONE_A, MASKDWORD, 0x18008c1f);
+	rtl_set_bbreg(hw, RTX_IQK_PI_A, MASKDWORD, 0x82110000);
+	rtl_set_bbreg(hw, RRX_IQK_PI_A, MASKDWORD, 0x68110000);
+
+	/* path-B IQK setting */
+	rtl_set_bbreg(hw, RTX_IQK_TONE_B, MASKDWORD, 0x18008c2f);
+	rtl_set_bbreg(hw, RRX_IQK_TONE_B, MASKDWORD, 0x18008c2f);
+	rtl_set_bbreg(hw, RTX_IQK_PI_B, MASKDWORD, 0x82140307);
+	rtl_set_bbreg(hw, RRX_IQK_PI_B, MASKDWORD, 0x68160960);
+
+	/* LO calibration setting */
+	RTPRINT(rtlpriv, FINIT, INIT_IQK,  "LO calibration setting!\n");
+	rtl_set_bbreg(hw, RIQK_AGC_RSP, MASKDWORD, 0x00462911);
+
+	/* path-B PA on */
+	rtl_set_bbreg(hw, RFPGA0_XAB_RFINTERFACESW, MASKDWORD, 0x0f600700);
+	rtl_set_bbreg(hw, RFPGA0_XB_RFINTERFACEOE, MASKDWORD, 0x061f0d30);
+
+	for (i = 0; i < retrycount; i++) {
+		/* One shot, path B LOK & IQK */
+		RTPRINT(rtlpriv, FINIT, INIT_IQK,
+			"One shot, path A LOK & IQK!\n");
+		rtl_set_bbreg(hw, RIQK_AGC_PTS, MASKDWORD, 0xfa000000);
+		rtl_set_bbreg(hw, RIQK_AGC_PTS, MASKDWORD, 0xf8000000);
+
+		RTPRINT(rtlpriv, FINIT, INIT_IQK,
+			"Delay %d ms for One shot, path B LOK & IQK.\n", 10);
+		mdelay(IQK_DELAY_TIME * 10);
+
+		while (timecount < timeout &&
+		       rtl_get_bbreg(hw, RRX_POWER_AFTER_IQK_A_2, BIT(29)) == 0) {
+			udelay(IQK_DELAY_TIME * 1000 * 2);
+			timecount++;
+		}
+
+		timecount = 0;
+		while (timecount < timeout &&
+		       rtl_get_bbreg(hw, RRX_POWER_BEFORE_IQK_B_2, MASK_IQK_RESULT) == 0) {
+			udelay(IQK_DELAY_TIME * 1000 * 2);
+			timecount++;
+		}
+
+		/* Check failed */
+		regeac = rtl_get_bbreg(hw, RRX_POWER_AFTER_IQK_A_2, MASKDWORD);
+		RTPRINT(rtlpriv, FINIT, INIT_IQK,  "0xeac = 0x%x\n", regeac);
+		regeb4 = rtl_get_bbreg(hw, RTX_POWER_BEFORE_IQK_B, MASKDWORD);
+		RTPRINT(rtlpriv, FINIT, INIT_IQK,  "0xeb4 = 0x%x\n", regeb4);
+		regebc = rtl_get_bbreg(hw, RTX_POWER_AFTER_IQK_B, MASKDWORD);
+		RTPRINT(rtlpriv, FINIT, INIT_IQK,  "0xebc = 0x%x\n", regebc);
+		regec4 = rtl_get_bbreg(hw, RRX_POWER_BEFORE_IQK_B_2, MASKDWORD);
+		RTPRINT(rtlpriv, FINIT, INIT_IQK,  "0xec4 = 0x%x\n", regec4);
+		regecc = rtl_get_bbreg(hw, RRX_POWER_AFTER_IQK_B_2, MASKDWORD);
+		RTPRINT(rtlpriv, FINIT, INIT_IQK,  "0xecc = 0x%x\n", regecc);
+
+		if (!(regeac & BIT(31)) &&
+		    (((regeb4 & 0x03FF0000) >> 16) != 0x142))
+			result |= 0x01;
+		else
+			continue;
+
+		if (!(regeac & BIT(30)) &&
+		    (((regec4 & 0x03FF0000) >> 16) != 0x132)) {
+			result |= 0x02;
+			break;
+		}
+
+		RTPRINT(rtlpriv, FINIT, INIT_IQK, "Path B Rx IQK fail!!\n");
+	}
+
+	/* path B PA off */
+	rtl_set_bbreg(hw, RFPGA0_XAB_RFINTERFACESW, MASKDWORD,
+		      rtlphy->iqk_bb_backup[0]);
+	rtl_set_bbreg(hw, RFPGA0_XB_RFINTERFACEOE, MASKDWORD,
+		      rtlphy->iqk_bb_backup[2]);
+
+	if (!(result & 0x01))
+		rtl_set_bbreg(hw, RTX_IQK_TONE_B, MASKDWORD, 0x19008c00);
+
+	if (!(result & 0x02)) {
+		rtl_set_bbreg(hw, ROFDM0_XBRXIQIMBALANCE, MASKDWORD, 0x40000100);
+		rtl_set_bbreg(hw, RRX_IQK_TONE_B, MASKDWORD, 0x19008c00);
+
+		RTPRINT(rtlpriv, FINIT, INIT_IQK,
+			"Path B Rx IQK fail!! 0xe54 = %#x\n",
+			rtl_get_bbreg(hw, RRX_IQK_TONE_B, MASKDWORD));
+	}
+
+	return result;
+}
+
+static void _rtl92du_phy_reload_adda_registers(struct ieee80211_hw *hw,
+					       const u32 *adda_reg,
+					       u32 *adda_backup, u32 regnum)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	u32 i;
+
+	RTPRINT(rtlpriv, FINIT, INIT_IQK,
+		"Reload ADDA power saving parameters !\n");
+	for (i = 0; i < regnum; i++) {
+		/* path-A/B BB to initial gain */
+		if (adda_reg[i] == ROFDM0_XAAGCCORE1 ||
+		    adda_reg[i] == ROFDM0_XBAGCCORE1)
+			rtl_set_bbreg(hw, adda_reg[i], MASKDWORD, 0x50);
+
+		rtl_set_bbreg(hw, adda_reg[i], MASKDWORD, adda_backup[i]);
+	}
+}
+
+static void _rtl92du_phy_reload_mac_registers(struct ieee80211_hw *hw,
+					      const u32 *macreg, u32 *macbackup)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	u32 i;
+
+	RTPRINT(rtlpriv, FINIT, INIT_IQK, "Reload MAC parameters !\n");
+	for (i = 0; i < (IQK_MAC_REG_NUM - 1); i++)
+		rtl_write_byte(rtlpriv, macreg[i], (u8)macbackup[i]);
+	rtl_write_dword(rtlpriv, macreg[i], macbackup[i]);
+}
+
+static void _rtl92du_phy_patha_standby(struct ieee80211_hw *hw)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+
+	RTPRINT(rtlpriv, FINIT, INIT_IQK, "Path-A standby mode!\n");
+
+	rtl_set_bbreg(hw, RFPGA0_IQK, MASKH3BYTES, 0x0);
+	rtl_set_bbreg(hw, RFPGA0_XA_LSSIPARAMETER, MASKDWORD, 0x00010000);
+	rtl_set_bbreg(hw, RFPGA0_IQK, MASKH3BYTES, 0x808000);
+}
+
+static void _rtl92du_phy_pimode_switch(struct ieee80211_hw *hw, bool pi_mode)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	u32 mode;
+
+	RTPRINT(rtlpriv, FINIT, INIT_IQK,
+		"BB Switch to %s mode!\n", pi_mode ? "PI" : "SI");
+	mode = pi_mode ? 0x01000100 : 0x01000000;
+	rtl_set_bbreg(hw, RFPGA0_XA_HSSIPARAMETER1, MASKDWORD, mode);
+	rtl_set_bbreg(hw, RFPGA0_XB_HSSIPARAMETER1, MASKDWORD, mode);
+}
+
+static void _rtl92du_phy_iq_calibrate(struct ieee80211_hw *hw, long result[][8],
+				      u8 t, bool is2t)
+{
+	static const u32 adda_reg[IQK_ADDA_REG_NUM] = {
+		RFPGA0_XCD_SWITCHCONTROL, RBLUE_TOOTH, RRX_WAIT_CCA,
+		RTX_CCK_RFON, RTX_CCK_BBON, RTX_OFDM_RFON, RTX_OFDM_BBON,
+		RTX_TO_RX, RTX_TO_TX, RRX_CCK, RRX_OFDM, RRX_WAIT_RIFS,
+		RRX_TO_RX, RSTANDBY, RSLEEP, RPMPD_ANAEN
+	};
+	static const u32 iqk_mac_reg[IQK_MAC_REG_NUM] = {
+		REG_TXPAUSE, REG_BCN_CTRL, REG_BCN_CTRL_1, REG_GPIO_MUXCFG
+	};
+	static const u32 iqk_bb_reg[IQK_BB_REG_NUM] = {
+		RFPGA0_XAB_RFINTERFACESW, RFPGA0_XA_RFINTERFACEOE,
+		RFPGA0_XB_RFINTERFACEOE, ROFDM0_TRMUXPAR,
+		RFPGA0_XCD_RFINTERFACESW, ROFDM0_TRXPATHENABLE,
+		RFPGA0_RFMOD, RFPGA0_ANALOGPARAMETER4,
+		ROFDM0_XAAGCCORE1, ROFDM0_XBAGCCORE1
+	};
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_phy *rtlphy = &rtlpriv->phy;
+	const u32 retrycount = 2;
+	u8 patha_ok, pathb_ok;
+	u32 bbvalue;
+	u32 i;
+
+	RTPRINT(rtlpriv, FINIT, INIT_IQK,  "IQK for 2.4G :Start!!!\n");
+	if (t == 0) {
+		bbvalue = rtl_get_bbreg(hw, RFPGA0_RFMOD, MASKDWORD);
+		RTPRINT(rtlpriv, FINIT, INIT_IQK,  "==>0x%08x\n", bbvalue);
+		RTPRINT(rtlpriv, FINIT, INIT_IQK, "IQ Calibration for %s\n",
+			is2t ? "2T2R" : "1T1R");
+
+		/*  Save ADDA parameters, turn Path A ADDA on */
+		rtl92d_phy_save_adda_registers(hw, adda_reg,
+					       rtlphy->adda_backup,
+					       IQK_ADDA_REG_NUM);
+		rtl92d_phy_save_mac_registers(hw, iqk_mac_reg,
+					      rtlphy->iqk_mac_backup);
+		rtl92d_phy_save_adda_registers(hw, iqk_bb_reg,
+					       rtlphy->iqk_bb_backup,
+					       IQK_BB_REG_NUM);
+	}
+	rtl92d_phy_path_adda_on(hw, adda_reg, true, is2t);
+
+	rtl_set_bbreg(hw, RPDP_ANTA, MASKDWORD, 0x01017038);
+
+	if (t == 0)
+		rtlphy->rfpi_enable = (u8)rtl_get_bbreg(hw,
+				RFPGA0_XA_HSSIPARAMETER1, BIT(8));
+
+	/*  Switch BB to PI mode to do IQ Calibration. */
+	if (!rtlphy->rfpi_enable)
+		_rtl92du_phy_pimode_switch(hw, true);
+
+	rtl92du_phy_set_bb_reg_1byte(hw, RFPGA0_RFMOD, BCCKEN, 0x00);
+	rtl_set_bbreg(hw, ROFDM0_TRXPATHENABLE, MASKDWORD, 0x03a05600);
+	rtl_set_bbreg(hw, ROFDM0_TRMUXPAR, MASKDWORD, 0x000800e4);
+	rtl_set_bbreg(hw, RFPGA0_XCD_RFINTERFACESW, MASKDWORD, 0x22204000);
+	rtl_set_bbreg(hw, RFPGA0_ANALOGPARAMETER4, 0xf00000, 0x0f);
+	if (is2t) {
+		rtl_set_bbreg(hw, RFPGA0_XA_LSSIPARAMETER, MASKDWORD,
+			      0x00010000);
+		rtl_set_bbreg(hw, RFPGA0_XB_LSSIPARAMETER, MASKDWORD,
+			      0x00010000);
+	}
+
+	/* MAC settings */
+	rtl92d_phy_mac_setting_calibration(hw, iqk_mac_reg,
+					   rtlphy->iqk_mac_backup);
+
+	/* Page B init */
+	rtl_set_bbreg(hw, RCONFIG_ANTA, MASKDWORD, 0x0f600000);
+	if (is2t)
+		rtl_set_bbreg(hw, RCONFIG_ANTB, MASKDWORD, 0x0f600000);
+
+	/* IQ calibration setting */
+	RTPRINT(rtlpriv, FINIT, INIT_IQK,  "IQK setting!\n");
+	rtl_set_bbreg(hw, RFPGA0_IQK, MASKH3BYTES, 0x808000);
+	rtl_set_bbreg(hw, RTX_IQK, MASKDWORD, 0x01007c00);
+	rtl_set_bbreg(hw, RRX_IQK, MASKDWORD, 0x01004800);
+
+	for (i = 0; i < retrycount; i++) {
+		patha_ok = _rtl92du_phy_patha_iqk(hw, is2t);
+		if (patha_ok == 0x03) {
+			RTPRINT(rtlpriv, FINIT, INIT_IQK,
+				"Path A IQK Success!!\n");
+			result[t][0] = rtl_get_bbreg(hw, RTX_POWER_BEFORE_IQK_A,
+						     MASK_IQK_RESULT);
+			result[t][1] = rtl_get_bbreg(hw, RTX_POWER_AFTER_IQK_A,
+						     MASK_IQK_RESULT);
+			result[t][2] = rtl_get_bbreg(hw, RRX_POWER_BEFORE_IQK_A_2,
+						     MASK_IQK_RESULT);
+			result[t][3] = rtl_get_bbreg(hw, RRX_POWER_AFTER_IQK_A_2,
+						     MASK_IQK_RESULT);
+			break;
+		} else if (i == (retrycount - 1) && patha_ok == 0x01) {
+			/* Tx IQK OK */
+			RTPRINT(rtlpriv, FINIT, INIT_IQK,
+				"Path A IQK Only  Tx Success!!\n");
+
+			result[t][0] = rtl_get_bbreg(hw, RTX_POWER_BEFORE_IQK_A,
+						     MASK_IQK_RESULT);
+			result[t][1] = rtl_get_bbreg(hw, RTX_POWER_AFTER_IQK_A,
+						     MASK_IQK_RESULT);
+		}
+	}
+	if (patha_ok == 0x00)
+		RTPRINT(rtlpriv, FINIT, INIT_IQK, "Path A IQK failed!!\n");
+
+	if (is2t) {
+		_rtl92du_phy_patha_standby(hw);
+		/* Turn Path B ADDA on */
+		rtl92d_phy_path_adda_on(hw, adda_reg, false, is2t);
+
+		for (i = 0; i < retrycount; i++) {
+			pathb_ok = _rtl92du_phy_pathb_iqk(hw);
+			if (pathb_ok == 0x03) {
+				RTPRINT(rtlpriv, FINIT, INIT_IQK,
+					"Path B IQK Success!!\n");
+				result[t][4] = rtl_get_bbreg(hw, RTX_POWER_BEFORE_IQK_B,
+							     MASK_IQK_RESULT);
+				result[t][5] = rtl_get_bbreg(hw, RTX_POWER_AFTER_IQK_B,
+							     MASK_IQK_RESULT);
+				result[t][6] = rtl_get_bbreg(hw, RRX_POWER_BEFORE_IQK_B_2,
+							     MASK_IQK_RESULT);
+				result[t][7] = rtl_get_bbreg(hw, RRX_POWER_AFTER_IQK_B_2,
+							     MASK_IQK_RESULT);
+				break;
+			} else if (i == (retrycount - 1) && pathb_ok == 0x01) {
+				/* Tx IQK OK */
+				RTPRINT(rtlpriv, FINIT, INIT_IQK,
+					"Path B Only Tx IQK Success!!\n");
+				result[t][4] = rtl_get_bbreg(hw, RTX_POWER_BEFORE_IQK_B,
+							     MASK_IQK_RESULT);
+				result[t][5] = rtl_get_bbreg(hw, RTX_POWER_AFTER_IQK_B,
+							     MASK_IQK_RESULT);
+			}
+		}
+		if (pathb_ok == 0x00)
+			RTPRINT(rtlpriv, FINIT, INIT_IQK,
+				"Path B IQK failed!!\n");
+	}
+
+	/* Back to BB mode, load original value */
+	RTPRINT(rtlpriv, FINIT, INIT_IQK,
+		"IQK:Back to BB mode, load original value!\n");
+
+	rtl_set_bbreg(hw, RFPGA0_IQK, MASKH3BYTES, 0x000000);
+
+	if (t != 0) {
+		/* Switch back BB to SI mode after finish IQ Calibration. */
+		if (!rtlphy->rfpi_enable)
+			_rtl92du_phy_pimode_switch(hw, false);
+
+		/* Reload ADDA power saving parameters */
+		_rtl92du_phy_reload_adda_registers(hw, adda_reg,
+						   rtlphy->adda_backup,
+						   IQK_ADDA_REG_NUM);
+
+		/* Reload MAC parameters */
+		_rtl92du_phy_reload_mac_registers(hw, iqk_mac_reg,
+						  rtlphy->iqk_mac_backup);
+
+		if (is2t)
+			_rtl92du_phy_reload_adda_registers(hw, iqk_bb_reg,
+							   rtlphy->iqk_bb_backup,
+							   IQK_BB_REG_NUM);
+		else
+			_rtl92du_phy_reload_adda_registers(hw, iqk_bb_reg,
+							   rtlphy->iqk_bb_backup,
+							   IQK_BB_REG_NUM - 1);
+
+		/* load 0xe30 IQC default value */
+		rtl_set_bbreg(hw, RTX_IQK_TONE_A, MASKDWORD, 0x01008c00);
+		rtl_set_bbreg(hw, RRX_IQK_TONE_A, MASKDWORD, 0x01008c00);
+	}
+	RTPRINT(rtlpriv, FINIT, INIT_IQK,  "<==\n");
+}
+
+static void _rtl92du_phy_iq_calibrate_5g_normal(struct ieee80211_hw *hw,
+						long result[][8], u8 t)
+{
+	static const u32 adda_reg[IQK_ADDA_REG_NUM] = {
+		RFPGA0_XCD_SWITCHCONTROL, RBLUE_TOOTH, RRX_WAIT_CCA,
+		RTX_CCK_RFON, RTX_CCK_BBON, RTX_OFDM_RFON, RTX_OFDM_BBON,
+		RTX_TO_RX, RTX_TO_TX, RRX_CCK, RRX_OFDM, RRX_WAIT_RIFS,
+		RRX_TO_RX, RSTANDBY, RSLEEP, RPMPD_ANAEN
+	};
+	static const u32 iqk_mac_reg[IQK_MAC_REG_NUM] = {
+		REG_TXPAUSE, REG_BCN_CTRL, REG_BCN_CTRL_1, REG_GPIO_MUXCFG
+	};
+	static const u32 iqk_bb_reg[IQK_BB_REG_NUM] = {
+		RFPGA0_XAB_RFINTERFACESW, RFPGA0_XA_RFINTERFACEOE,
+		RFPGA0_XB_RFINTERFACEOE, ROFDM0_TRMUXPAR,
+		RFPGA0_XCD_RFINTERFACESW, ROFDM0_TRXPATHENABLE,
+		RFPGA0_RFMOD, RFPGA0_ANALOGPARAMETER4,
+		ROFDM0_XAAGCCORE1, ROFDM0_XBAGCCORE1
+	};
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_phy *rtlphy = &rtlpriv->phy;
+	struct rtl_hal *rtlhal = &rtlpriv->rtlhal;
+	bool is2t = IS_92D_SINGLEPHY(rtlhal->version);
+	u8 patha_ok, pathb_ok;
+	bool rf_path_div;
+	u32 bbvalue;
+
+	/* Note: IQ calibration must be performed after loading
+	 * PHY_REG.txt , and radio_a, radio_b.txt
+	 */
+
+	RTPRINT(rtlpriv, FINIT, INIT_IQK,  "IQK for 5G NORMAL:Start!!!\n");
+
+	mdelay(IQK_DELAY_TIME * 20);
+
+	if (t == 0) {
+		bbvalue = rtl_get_bbreg(hw, RFPGA0_RFMOD, MASKDWORD);
+		RTPRINT(rtlpriv, FINIT, INIT_IQK,  "==>0x%08x\n", bbvalue);
+		RTPRINT(rtlpriv, FINIT, INIT_IQK, "IQ Calibration for %s\n",
+			is2t ? "2T2R" : "1T1R");
+
+		/* Save ADDA parameters, turn Path A ADDA on */
+		rtl92d_phy_save_adda_registers(hw, adda_reg,
+					       rtlphy->adda_backup,
+					       IQK_ADDA_REG_NUM);
+		rtl92d_phy_save_mac_registers(hw, iqk_mac_reg,
+					      rtlphy->iqk_mac_backup);
+		if (is2t)
+			rtl92d_phy_save_adda_registers(hw, iqk_bb_reg,
+						       rtlphy->iqk_bb_backup,
+						       IQK_BB_REG_NUM);
+		else
+			rtl92d_phy_save_adda_registers(hw, iqk_bb_reg,
+						       rtlphy->iqk_bb_backup,
+						       IQK_BB_REG_NUM - 1);
+	}
+
+	rf_path_div = rtl_get_bbreg(hw, 0xb30, BIT(27));
+	rtl92d_phy_path_adda_on(hw, adda_reg, !rf_path_div, is2t);
+
+	if (t == 0)
+		rtlphy->rfpi_enable = rtl_get_bbreg(hw,
+						    RFPGA0_XA_HSSIPARAMETER1,
+						    BIT(8));
+
+	/*  Switch BB to PI mode to do IQ Calibration. */
+	if (!rtlphy->rfpi_enable)
+		_rtl92du_phy_pimode_switch(hw, true);
+
+	/* MAC settings */
+	rtl92d_phy_mac_setting_calibration(hw, iqk_mac_reg,
+					   rtlphy->iqk_mac_backup);
+
+	rtl92du_phy_set_bb_reg_1byte(hw, RFPGA0_RFMOD, BCCKEN, 0x00);
+	rtl_set_bbreg(hw, ROFDM0_TRXPATHENABLE, MASKDWORD, 0x03a05600);
+	rtl_set_bbreg(hw, ROFDM0_TRMUXPAR, MASKDWORD, 0x000800e4);
+	rtl_set_bbreg(hw, RFPGA0_XCD_RFINTERFACESW, MASKDWORD, 0x22208000);
+	rtl_set_bbreg(hw, RFPGA0_ANALOGPARAMETER4, 0xf00000, 0x0f);
+
+	/* Page A AP setting for IQK */
+	rtl_set_bbreg(hw, RPDP_ANTA, MASKDWORD, 0);
+	rtl_set_bbreg(hw, RCONFIG_ANTA, MASKDWORD, 0x20000000);
+	if (is2t) {
+		/* Page B AP setting for IQK */
+		rtl_set_bbreg(hw, RPDP_ANTB, MASKDWORD, 0);
+		rtl_set_bbreg(hw, RCONFIG_ANTB, MASKDWORD, 0x20000000);
+	}
+
+	/* IQ calibration setting  */
+	RTPRINT(rtlpriv, FINIT, INIT_IQK,  "IQK setting!\n");
+	rtl_set_bbreg(hw, RFPGA0_IQK, MASKH3BYTES, 0x808000);
+	rtl_set_bbreg(hw, RTX_IQK, MASKDWORD, 0x10007c00);
+	rtl_set_bbreg(hw, RRX_IQK, MASKDWORD, 0x01004800);
+
+	patha_ok = _rtl92du_phy_patha_iqk_5g_normal(hw, is2t);
+	if (patha_ok == 0x03) {
+		RTPRINT(rtlpriv, FINIT, INIT_IQK,  "Path A IQK Success!!\n");
+		result[t][0] = rtl_get_bbreg(hw, RTX_POWER_BEFORE_IQK_A,
+					     MASK_IQK_RESULT);
+		result[t][1] = rtl_get_bbreg(hw, RTX_POWER_AFTER_IQK_A,
+					     MASK_IQK_RESULT);
+		result[t][2] = rtl_get_bbreg(hw, RRX_POWER_BEFORE_IQK_A_2,
+					     MASK_IQK_RESULT);
+		result[t][3] = rtl_get_bbreg(hw, RRX_POWER_AFTER_IQK_A_2,
+					     MASK_IQK_RESULT);
+	} else if (patha_ok == 0x01) {	/* Tx IQK OK */
+		RTPRINT(rtlpriv, FINIT, INIT_IQK,
+			"Path A IQK Only  Tx Success!!\n");
+
+		result[t][0] = rtl_get_bbreg(hw, RTX_POWER_BEFORE_IQK_A,
+					     MASK_IQK_RESULT);
+		result[t][1] = rtl_get_bbreg(hw, RTX_POWER_AFTER_IQK_A,
+					     MASK_IQK_RESULT);
+	} else {
+		rtl_set_bbreg(hw, RFPGA0_IQK, MASKH3BYTES, 0x000000);
+		RTPRINT(rtlpriv, FINIT, INIT_IQK, "0xe70 = %#x\n",
+			rtl_get_bbreg(hw, RRX_WAIT_CCA, MASKDWORD));
+		RTPRINT(rtlpriv, FINIT, INIT_IQK, "RF path A 0x0 = %#x\n",
+			rtl_get_rfreg(hw, RF90_PATH_A, RF_AC, RFREG_OFFSET_MASK));
+		rtl_set_bbreg(hw, RFPGA0_IQK, MASKH3BYTES, 0x808000);
+		RTPRINT(rtlpriv, FINIT, INIT_IQK,  "Path A IQK Fail!!\n");
+	}
+
+	if (is2t) {
+		/* _rtl92d_phy_patha_standby(hw); */
+		/* Turn Path B ADDA on  */
+		rtl92d_phy_path_adda_on(hw, adda_reg, false, is2t);
+
+		pathb_ok = _rtl92du_phy_pathb_iqk_5g_normal(hw);
+		if (pathb_ok == 0x03) {
+			RTPRINT(rtlpriv, FINIT, INIT_IQK,
+				"Path B IQK Success!!\n");
+			result[t][4] = rtl_get_bbreg(hw, RTX_POWER_BEFORE_IQK_B,
+						     MASK_IQK_RESULT);
+			result[t][5] = rtl_get_bbreg(hw, RTX_POWER_AFTER_IQK_B,
+						     MASK_IQK_RESULT);
+			result[t][6] = rtl_get_bbreg(hw, RRX_POWER_BEFORE_IQK_B_2,
+						     MASK_IQK_RESULT);
+			result[t][7] = rtl_get_bbreg(hw, RRX_POWER_AFTER_IQK_B_2,
+						     MASK_IQK_RESULT);
+		} else if (pathb_ok == 0x01) { /* Tx IQK OK */
+			RTPRINT(rtlpriv, FINIT, INIT_IQK,
+				"Path B Only Tx IQK Success!!\n");
+			result[t][4] = rtl_get_bbreg(hw, RTX_POWER_BEFORE_IQK_B,
+						     MASK_IQK_RESULT);
+			result[t][5] = rtl_get_bbreg(hw, RTX_POWER_AFTER_IQK_B,
+						     MASK_IQK_RESULT);
+		} else {
+			RTPRINT(rtlpriv, FINIT, INIT_IQK,
+				"Path B IQK failed!!\n");
+		}
+	}
+
+	/* Back to BB mode, load original value */
+	RTPRINT(rtlpriv, FINIT, INIT_IQK,
+		"IQK:Back to BB mode, load original value!\n");
+	rtl_set_bbreg(hw, RFPGA0_IQK, MASKH3BYTES, 0);
+
+	if (is2t)
+		_rtl92du_phy_reload_adda_registers(hw, iqk_bb_reg,
+						   rtlphy->iqk_bb_backup,
+						   IQK_BB_REG_NUM);
+	else
+		_rtl92du_phy_reload_adda_registers(hw, iqk_bb_reg,
+						   rtlphy->iqk_bb_backup,
+						   IQK_BB_REG_NUM - 1);
+
+	/* path A IQ path to DP block */
+	rtl_set_bbreg(hw, RPDP_ANTA, MASKDWORD, 0x010170b8);
+	if (is2t) /* path B IQ path to DP block */
+		rtl_set_bbreg(hw, RPDP_ANTB, MASKDWORD, 0x010170b8);
+
+	/* Reload MAC parameters */
+	_rtl92du_phy_reload_mac_registers(hw, iqk_mac_reg,
+					  rtlphy->iqk_mac_backup);
+
+	/* Switch back BB to SI mode after finish IQ Calibration. */
+	if (!rtlphy->rfpi_enable)
+		_rtl92du_phy_pimode_switch(hw, false);
+
+	/* Reload ADDA power saving parameters */
+	_rtl92du_phy_reload_adda_registers(hw, adda_reg,
+					   rtlphy->adda_backup,
+					   IQK_ADDA_REG_NUM);
+
+	RTPRINT(rtlpriv, FINIT, INIT_IQK,  "<==\n");
+}
+
+static bool _rtl92du_phy_simularity_compare(struct ieee80211_hw *hw,
+					    long result[][8], u8 c1, u8 c2)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_hal *rtlhal = &rtlpriv->rtlhal;
+	u32 i, j, diff, sim_bitmap, bound, u4temp = 0;
+	u8 final_candidate[2] = {0xFF, 0xFF};	/* for path A and path B */
+	bool is2t = IS_92D_SINGLEPHY(rtlhal->version);
+	bool bresult = true;
+
+	if (is2t)
+		bound = 8;
+	else
+		bound = 4;
+
+	sim_bitmap = 0;
+
+	for (i = 0; i < bound; i++) {
+		diff = abs_diff(result[c1][i], result[c2][i]);
+
+		if (diff > MAX_TOLERANCE_92D) {
+			if ((i == 2 || i == 6) && !sim_bitmap) {
+				if (result[c1][i] + result[c1][i + 1] == 0)
+					final_candidate[(i / 4)] = c2;
+				else if (result[c2][i] + result[c2][i + 1] == 0)
+					final_candidate[(i / 4)] = c1;
+				else
+					sim_bitmap = sim_bitmap | (1 << i);
+			} else {
+				sim_bitmap = sim_bitmap | (1 << i);
+			}
+		}
+	}
+
+	if (sim_bitmap == 0) {
+		for (i = 0; i < (bound / 4); i++) {
+			if (final_candidate[i] != 0xFF) {
+				for (j = i * 4; j < (i + 1) * 4 - 2; j++)
+					result[3][j] =
+						 result[final_candidate[i]][j];
+				bresult = false;
+			}
+		}
+
+		for (i = 0; i < bound; i++)
+			u4temp += result[c1][i] + result[c2][i];
+
+		if (u4temp == 0) /* IQK fail for c1 & c2 */
+			bresult = false;
+
+		return bresult;
+	}
+
+	if (!(sim_bitmap & 0x0F)) { /* path A OK */
+		for (i = 0; i < 4; i++)
+			result[3][i] = result[c1][i];
+	} else if (!(sim_bitmap & 0x03)) { /* path A, Tx OK */
+		for (i = 0; i < 2; i++)
+			result[3][i] = result[c1][i];
+	}
+
+	if (!(sim_bitmap & 0xF0) && is2t) { /* path B OK */
+		for (i = 4; i < 8; i++)
+			result[3][i] = result[c1][i];
+	} else if (!(sim_bitmap & 0x30)) { /* path B, Tx OK */
+		for (i = 4; i < 6; i++)
+			result[3][i] = result[c1][i];
+	}
+
+	return false;
+}
+
+static void _rtl92du_phy_patha_fill_iqk_matrix_5g_normal(struct ieee80211_hw *hw,
+							 bool iqk_ok,
+							 long result[][8],
+							 u8 final_candidate,
+							 bool txonly)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_hal *rtlhal = &rtlpriv->rtlhal;
+	u32 val_x, reg;
+	int val_y;
+
+	RTPRINT(rtlpriv, FINIT, INIT_IQK,
+		"Path A IQ Calibration %s !\n", iqk_ok ? "Success" : "Failed");
+	if (iqk_ok && final_candidate != 0xFF) {
+		val_x = result[final_candidate][0];
+		if ((val_x & 0x00000200) != 0)
+			val_x = val_x | 0xFFFFFC00;
+
+		RTPRINT(rtlpriv, FINIT, INIT_IQK, "X = 0x%x\n", val_x);
+		rtl_set_bbreg(hw, RTX_IQK_TONE_A, 0x3FF0000, val_x);
+		rtl_set_bbreg(hw, ROFDM0_ECCATHRESHOLD, BIT(24), 0);
+
+		val_y = result[final_candidate][1];
+		if ((val_y & 0x00000200) != 0)
+			val_y = val_y | 0xFFFFFC00;
+
+		/* path B IQK result + 3 */
+		if (rtlhal->current_bandtype == BAND_ON_5G)
+			val_y += 3;
+
+		RTPRINT(rtlpriv, FINIT, INIT_IQK, "Y = 0x%x\n", val_y);
+
+		rtl_set_bbreg(hw, RTX_IQK_TONE_A, 0x3FF, val_y);
+		rtl_set_bbreg(hw, ROFDM0_ECCATHRESHOLD, BIT(26), 0);
+
+		RTPRINT(rtlpriv, FINIT, INIT_IQK, "0xe30 = 0x%x\n",
+			rtl_get_bbreg(hw, RTX_IQK_TONE_A, MASKDWORD));
+
+		if (txonly) {
+			RTPRINT(rtlpriv, FINIT, INIT_IQK, "only Tx OK\n");
+			return;
+		}
+
+		reg = result[final_candidate][2];
+		rtl_set_bbreg(hw, ROFDM0_XARXIQIMBALANCE, 0x3FF, reg);
+		reg = result[final_candidate][3] & 0x3F;
+		rtl_set_bbreg(hw, ROFDM0_XARXIQIMBALANCE, 0xFC00, reg);
+		reg = (result[final_candidate][3] >> 6) & 0xF;
+		rtl_set_bbreg(hw, ROFDM0_RXIQEXTANTA, 0xF0000000, reg);
+	} else {
+		RTPRINT(rtlpriv, FINIT, INIT_IQK,
+			"%s: Tx/Rx fail restore default value\n", __func__);
+
+		rtl_set_bbreg(hw, RTX_IQK_TONE_A, MASKDWORD, 0x19008c00);
+		rtl_set_bbreg(hw, ROFDM0_XARXIQIMBALANCE, MASKDWORD, 0x40000100);
+		rtl_set_bbreg(hw, RRX_IQK_TONE_A, MASKDWORD, 0x19008c00);
+	}
+}
+
+static void _rtl92du_phy_patha_fill_iqk_matrix(struct ieee80211_hw *hw,
+					       bool iqk_ok, long result[][8],
+					       u8 final_candidate, bool txonly)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_hal *rtlhal = &rtlpriv->rtlhal;
+	u32 oldval_0, val_x, tx0_a, reg;
+	long val_y, tx0_c;
+	bool is2t = IS_92D_SINGLEPHY(rtlhal->version) ||
+		    rtlhal->macphymode == DUALMAC_DUALPHY;
+
+	if (rtlhal->current_bandtype == BAND_ON_5G) {
+		_rtl92du_phy_patha_fill_iqk_matrix_5g_normal(hw, iqk_ok, result,
+							     final_candidate,
+							     txonly);
+		return;
+	}
+
+	RTPRINT(rtlpriv, FINIT, INIT_IQK,
+		"Path A IQ Calibration %s !\n", iqk_ok ? "Success" : "Failed");
+	if (final_candidate == 0xFF || !iqk_ok)
+		return;
+
+	/* OFDM0_D */
+	oldval_0 = rtl_get_bbreg(hw, ROFDM0_XATXIQIMBALANCE, 0xffc00000);
+
+	val_x = result[final_candidate][0];
+	if ((val_x & 0x00000200) != 0)
+		val_x = val_x | 0xFFFFFC00;
+
+	tx0_a = (val_x * oldval_0) >> 8;
+	RTPRINT(rtlpriv, FINIT, INIT_IQK,
+		"X = 0x%x, tx0_a = 0x%x, oldval_0 0x%x\n",
+		val_x, tx0_a, oldval_0);
+	rtl_set_bbreg(hw, ROFDM0_XATXIQIMBALANCE, 0x3FF, tx0_a);
+	rtl_set_bbreg(hw, ROFDM0_ECCATHRESHOLD, BIT(24),
+		      ((val_x * oldval_0 >> 7) & 0x1));
+
+	val_y = result[final_candidate][1];
+	if ((val_y & 0x00000200) != 0)
+		val_y = val_y | 0xFFFFFC00;
+
+	/* path B IQK result + 3 */
+	if (rtlhal->interfaceindex == 1 &&
+	    rtlhal->current_bandtype == BAND_ON_5G)
+		val_y += 3;
+
+	tx0_c = (val_y * oldval_0) >> 8;
+	RTPRINT(rtlpriv, FINIT, INIT_IQK,
+		"Y = 0x%lx, tx0_c = 0x%lx\n",
+		val_y, tx0_c);
+
+	rtl_set_bbreg(hw, ROFDM0_XCTXAFE, 0xF0000000, (tx0_c & 0x3C0) >> 6);
+	rtl_set_bbreg(hw, ROFDM0_XATXIQIMBALANCE, 0x003F0000, tx0_c & 0x3F);
+	if (is2t)
+		rtl_set_bbreg(hw, ROFDM0_ECCATHRESHOLD, BIT(26),
+			      (val_y * oldval_0 >> 7) & 0x1);
+
+	RTPRINT(rtlpriv, FINIT, INIT_IQK, "0xC80 = 0x%x\n",
+		rtl_get_bbreg(hw, ROFDM0_XATXIQIMBALANCE,
+			      MASKDWORD));
+
+	if (txonly) {
+		RTPRINT(rtlpriv, FINIT, INIT_IQK, "only Tx OK\n");
+		return;
+	}
+
+	reg = result[final_candidate][2];
+	rtl_set_bbreg(hw, ROFDM0_XARXIQIMBALANCE, 0x3FF, reg);
+	reg = result[final_candidate][3] & 0x3F;
+	rtl_set_bbreg(hw, ROFDM0_XARXIQIMBALANCE, 0xFC00, reg);
+	reg = (result[final_candidate][3] >> 6) & 0xF;
+	rtl_set_bbreg(hw, ROFDM0_RXIQEXTANTA, 0xF0000000, reg);
+}
+
+static void _rtl92du_phy_pathb_fill_iqk_matrix_5g_normal(struct ieee80211_hw *hw,
+							 bool iqk_ok,
+							 long result[][8],
+							 u8 final_candidate,
+							 bool txonly)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_hal *rtlhal = &rtlpriv->rtlhal;
+	u32 val_x, reg;
+	int val_y;
+
+	RTPRINT(rtlpriv, FINIT, INIT_IQK,
+		"Path B IQ Calibration %s !\n", iqk_ok ? "Success" : "Failed");
+	if (iqk_ok && final_candidate != 0xFF) {
+		val_x = result[final_candidate][4];
+		if ((val_x & 0x00000200) != 0)
+			val_x = val_x | 0xFFFFFC00;
+
+		RTPRINT(rtlpriv, FINIT, INIT_IQK, "X = 0x%x\n", val_x);
+		rtl_set_bbreg(hw, RTX_IQK_TONE_B, 0x3FF0000, val_x);
+		rtl_set_bbreg(hw, ROFDM0_ECCATHRESHOLD, BIT(28), 0);
+
+		val_y = result[final_candidate][5];
+		if ((val_y & 0x00000200) != 0)
+			val_y = val_y | 0xFFFFFC00;
+
+		/* path B IQK result + 3 */
+		if (rtlhal->current_bandtype == BAND_ON_5G)
+			val_y += 3;
+
+		RTPRINT(rtlpriv, FINIT, INIT_IQK, "Y = 0x%x\n", val_y);
+
+		rtl_set_bbreg(hw, RTX_IQK_TONE_B, 0x3FF, val_y);
+		rtl_set_bbreg(hw, ROFDM0_ECCATHRESHOLD, BIT(30), 0);
+
+		RTPRINT(rtlpriv, FINIT, INIT_IQK, "0xe50 = 0x%x\n",
+			rtl_get_bbreg(hw, RTX_IQK_TONE_B, MASKDWORD));
+
+		if (txonly) {
+			RTPRINT(rtlpriv, FINIT, INIT_IQK, "only Tx OK\n");
+			return;
+		}
+
+		reg = result[final_candidate][6];
+		rtl_set_bbreg(hw, ROFDM0_XBRXIQIMBALANCE, 0x3FF, reg);
+		reg = result[final_candidate][7] & 0x3F;
+		rtl_set_bbreg(hw, ROFDM0_XBRXIQIMBALANCE, 0xFC00, reg);
+		reg = (result[final_candidate][7] >> 6) & 0xF;
+		rtl_set_bbreg(hw, ROFDM0_AGCRSSITABLE, 0x0000F000, reg);
+	} else {
+		RTPRINT(rtlpriv, FINIT, INIT_IQK,
+			"%s: Tx/Rx fail restore default value\n", __func__);
+
+		rtl_set_bbreg(hw, RTX_IQK_TONE_B, MASKDWORD, 0x19008c00);
+		rtl_set_bbreg(hw, ROFDM0_XBRXIQIMBALANCE, MASKDWORD, 0x40000100);
+		rtl_set_bbreg(hw, RRX_IQK_TONE_B, MASKDWORD, 0x19008c00);
+	}
+}
+
+static void _rtl92du_phy_pathb_fill_iqk_matrix(struct ieee80211_hw *hw,
+					       bool iqk_ok, long result[][8],
+					       u8 final_candidate, bool txonly)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_hal *rtlhal = &rtlpriv->rtlhal;
+	u32 oldval_1, val_x, tx1_a, reg;
+	long val_y, tx1_c;
+
+	if (rtlhal->current_bandtype == BAND_ON_5G) {
+		_rtl92du_phy_pathb_fill_iqk_matrix_5g_normal(hw, iqk_ok, result,
+							     final_candidate,
+							     txonly);
+		return;
+	}
+
+	RTPRINT(rtlpriv, FINIT, INIT_IQK, "Path B IQ Calibration %s !\n",
+		iqk_ok ? "Success" : "Failed");
+
+	if (final_candidate == 0xFF || !iqk_ok)
+		return;
+
+	oldval_1 = rtl_get_bbreg(hw, ROFDM0_XBTXIQIMBALANCE, 0xffc00000);
+
+	val_x = result[final_candidate][4];
+	if ((val_x & 0x00000200) != 0)
+		val_x = val_x | 0xFFFFFC00;
+
+	tx1_a = (val_x * oldval_1) >> 8;
+	RTPRINT(rtlpriv, FINIT, INIT_IQK, "X = 0x%x, tx1_a = 0x%x\n",
+		val_x, tx1_a);
+	rtl_set_bbreg(hw, ROFDM0_XBTXIQIMBALANCE, 0x3FF, tx1_a);
+	rtl_set_bbreg(hw, ROFDM0_ECCATHRESHOLD, BIT(28),
+		      (val_x * oldval_1 >> 7) & 0x1);
+
+	val_y = result[final_candidate][5];
+	if ((val_y & 0x00000200) != 0)
+		val_y = val_y | 0xFFFFFC00;
+
+	if (rtlhal->current_bandtype == BAND_ON_5G)
+		val_y += 3;
+
+	tx1_c = (val_y * oldval_1) >> 8;
+	RTPRINT(rtlpriv, FINIT, INIT_IQK, "Y = 0x%lx, tx1_c = 0x%lx\n",
+		val_y, tx1_c);
+
+	rtl_set_bbreg(hw, ROFDM0_XDTXAFE, 0xF0000000, (tx1_c & 0x3C0) >> 6);
+	rtl_set_bbreg(hw, ROFDM0_XBTXIQIMBALANCE, 0x003F0000, tx1_c & 0x3F);
+	rtl_set_bbreg(hw, ROFDM0_ECCATHRESHOLD, BIT(30),
+		      (val_y * oldval_1 >> 7) & 0x1);
+
+	if (txonly)
+		return;
+
+	reg = result[final_candidate][6];
+	rtl_set_bbreg(hw, ROFDM0_XBRXIQIMBALANCE, 0x3FF, reg);
+	reg = result[final_candidate][7] & 0x3F;
+	rtl_set_bbreg(hw, ROFDM0_XBRXIQIMBALANCE, 0xFC00, reg);
+	reg = (result[final_candidate][7] >> 6) & 0xF;
+	rtl_set_bbreg(hw, ROFDM0_AGCRSSITABLE, 0x0000F000, reg);
+}
+
+void rtl92du_phy_iq_calibrate(struct ieee80211_hw *hw)
+{
+	long rege94, rege9c, regea4, regeac, regeb4;
+	bool is12simular, is13simular, is23simular;
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_hal *rtlhal = &rtlpriv->rtlhal;
+	long regebc, regec4, regecc, regtmp = 0;
+	struct rtl_phy *rtlphy = &rtlpriv->phy;
+	u8 i, final_candidate, indexforchannel;
+	bool patha_ok, pathb_ok;
+	long result[4][8] = {};
+
+	RTPRINT(rtlpriv, FINIT, INIT_IQK,
+		"IQK:Start!!!channel %d\n", rtlphy->current_channel);
+
+	final_candidate = 0xff;
+	patha_ok = false;
+	pathb_ok = false;
+	is12simular = false;
+	is23simular = false;
+	is13simular = false;
+	RTPRINT(rtlpriv, FINIT, INIT_IQK,
+		"IQK !!!currentband %d\n", rtlhal->current_bandtype);
+
+	for (i = 0; i < 3; i++) {
+		if (rtlhal->current_bandtype == BAND_ON_5G) {
+			_rtl92du_phy_iq_calibrate_5g_normal(hw, result, i);
+		} else if (rtlhal->current_bandtype == BAND_ON_2_4G) {
+			if (IS_92D_SINGLEPHY(rtlhal->version))
+				_rtl92du_phy_iq_calibrate(hw, result, i, true);
+			else
+				_rtl92du_phy_iq_calibrate(hw, result, i, false);
+		}
+
+		if (i == 1) {
+			is12simular = _rtl92du_phy_simularity_compare(hw, result,
+								      0, 1);
+			if (is12simular) {
+				final_candidate = 0;
+				break;
+			}
+		}
+
+		if (i == 2) {
+			is13simular = _rtl92du_phy_simularity_compare(hw, result,
+								      0, 2);
+			if (is13simular) {
+				final_candidate = 0;
+				break;
+			}
+
+			is23simular = _rtl92du_phy_simularity_compare(hw, result,
+								      1, 2);
+			if (is23simular) {
+				final_candidate = 1;
+			} else {
+				for (i = 0; i < 8; i++)
+					regtmp += result[3][i];
+
+				if (regtmp != 0)
+					final_candidate = 3;
+				else
+					final_candidate = 0xFF;
+			}
+		}
+	}
+
+	for (i = 0; i < 4; i++) {
+		rege94 = result[i][0];
+		rege9c = result[i][1];
+		regea4 = result[i][2];
+		regeac = result[i][3];
+		regeb4 = result[i][4];
+		regebc = result[i][5];
+		regec4 = result[i][6];
+		regecc = result[i][7];
+		RTPRINT(rtlpriv, FINIT, INIT_IQK,
+			"IQK: rege94=%lx rege9c=%lx regea4=%lx regeac=%lx regeb4=%lx regebc=%lx regec4=%lx regecc=%lx\n",
+			rege94, rege9c, regea4, regeac, regeb4, regebc, regec4,
+			regecc);
+	}
+
+	if (final_candidate != 0xff) {
+		rege94 = result[final_candidate][0];
+		rtlphy->reg_e94 = rege94;
+		rege9c = result[final_candidate][1];
+		rtlphy->reg_e9c = rege9c;
+		regea4 = result[final_candidate][2];
+		regeac = result[final_candidate][3];
+		regeb4 = result[final_candidate][4];
+		rtlphy->reg_eb4 = regeb4;
+		regebc = result[final_candidate][5];
+		rtlphy->reg_ebc = regebc;
+		regec4 = result[final_candidate][6];
+		regecc = result[final_candidate][7];
+
+		RTPRINT(rtlpriv, FINIT, INIT_IQK,
+			"IQK: final_candidate is %x\n", final_candidate);
+		RTPRINT(rtlpriv, FINIT, INIT_IQK,
+			"IQK: rege94=%lx rege9c=%lx regea4=%lx regeac=%lx regeb4=%lx regebc=%lx regec4=%lx regecc=%lx\n",
+			rege94, rege9c, regea4, regeac, regeb4, regebc, regec4,
+			regecc);
+
+		patha_ok = true;
+		pathb_ok = true;
+	} else {
+		rtlphy->reg_e94 = 0x100;
+		rtlphy->reg_eb4 = 0x100; /* X default value */
+		rtlphy->reg_e9c = 0x0;
+		rtlphy->reg_ebc = 0x0;   /* Y default value */
+	}
+	if (rege94 != 0 /*&& regea4 != 0*/)
+		_rtl92du_phy_patha_fill_iqk_matrix(hw, patha_ok, result,
+						   final_candidate,
+						   regea4 == 0);
+	if (IS_92D_SINGLEPHY(rtlhal->version) &&
+	    regeb4 != 0 /*&& regec4 != 0*/)
+		_rtl92du_phy_pathb_fill_iqk_matrix(hw, pathb_ok, result,
+						   final_candidate,
+						   regec4 == 0);
+
+	if (final_candidate != 0xFF) {
+		indexforchannel =
+			rtl92d_get_rightchnlplace_for_iqk(rtlphy->current_channel);
+
+		for (i = 0; i < IQK_MATRIX_REG_NUM; i++)
+			rtlphy->iqk_matrix[indexforchannel].value[0][i] =
+				result[final_candidate][i];
+
+		rtlphy->iqk_matrix[indexforchannel].iqk_done = true;
+
+		rtl_dbg(rtlpriv, COMP_SCAN | COMP_MLME, DBG_LOUD,
+			"IQK OK indexforchannel %d\n", indexforchannel);
+	}
+}
+
+void rtl92du_phy_reload_iqk_setting(struct ieee80211_hw *hw, u8 channel)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_hal *rtlhal = &rtlpriv->rtlhal;
+	struct rtl_phy *rtlphy = &rtlpriv->phy;
+	struct rtl_mac *mac = rtl_mac(rtlpriv);
+	u8 indexforchannel;
+	bool need_iqk;
+
+	rtl_dbg(rtlpriv, COMP_CMD, DBG_LOUD, "channel %d\n", channel);
+	/*------Do IQK for normal chip and test chip 5G band------- */
+
+	indexforchannel = rtl92d_get_rightchnlplace_for_iqk(channel);
+	rtl_dbg(rtlpriv, COMP_CMD, DBG_LOUD, "indexforchannel %d done %d\n",
+		indexforchannel,
+		rtlphy->iqk_matrix[indexforchannel].iqk_done);
+
+	/* We need to do IQK if we're about to connect to a network on 5 GHz.
+	 * On 5 GHz a channel switch outside of scanning happens only before
+	 * connecting.
+	 */
+	need_iqk = !mac->act_scanning;
+
+	if (!rtlphy->iqk_matrix[indexforchannel].iqk_done && need_iqk) {
+		rtl_dbg(rtlpriv, COMP_SCAN | COMP_INIT, DBG_LOUD,
+			"Do IQK Matrix reg for channel:%d....\n", channel);
+		rtl92du_phy_iq_calibrate(hw);
+		return;
+	}
+
+	/* Just load the value. */
+	/* 2G band just load once. */
+	if ((!rtlhal->load_imrandiqk_setting_for2g && indexforchannel == 0) ||
+	    indexforchannel > 0) {
+		rtl_dbg(rtlpriv, COMP_SCAN, DBG_LOUD,
+			"Just Read IQK Matrix reg for channel:%d....\n",
+			channel);
+
+		if (rtlphy->iqk_matrix[indexforchannel].value[0][0] != 0)
+			_rtl92du_phy_patha_fill_iqk_matrix(hw, true,
+				rtlphy->iqk_matrix[indexforchannel].value, 0,
+				rtlphy->iqk_matrix[indexforchannel].value[0][2] == 0);
+
+		if (IS_92D_SINGLEPHY(rtlhal->version) &&
+		    rtlphy->iqk_matrix[indexforchannel].value[0][4] != 0)
+			_rtl92du_phy_pathb_fill_iqk_matrix(hw, true,
+				rtlphy->iqk_matrix[indexforchannel].value, 0,
+				rtlphy->iqk_matrix[indexforchannel].value[0][6] == 0);
+	}
+	rtl_dbg(rtlpriv, COMP_CMD, DBG_LOUD, "<====\n");
+}
+
+static void _rtl92du_phy_reload_lck_setting(struct ieee80211_hw *hw, u8 channel)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_hal *rtlhal = &rtlpriv->rtlhal;
+	u8 erfpath = rtlhal->current_bandtype == BAND_ON_5G ? RF90_PATH_A :
+		IS_92D_SINGLEPHY(rtlhal->version) ? RF90_PATH_B : RF90_PATH_A;
+	bool bneed_powerdown_radio = false;
+	u32 u4tmp, u4regvalue;
+
+	rtl_dbg(rtlpriv, COMP_CMD, DBG_LOUD, "path %d\n", erfpath);
+	RTPRINT(rtlpriv, FINIT, INIT_IQK, "band type = %d\n",
+		rtlpriv->rtlhal.current_bandtype);
+	RTPRINT(rtlpriv, FINIT, INIT_IQK,  "channel = %d\n", channel);
+
+	if (rtlpriv->rtlhal.current_bandtype == BAND_ON_5G) {/* Path-A for 5G */
+		u4tmp = rtlpriv->curveindex_5g[channel - 1];
+		RTPRINT(rtlpriv, FINIT, INIT_IQK,
+			"ver 1 set RF-A, 5G,	0x28 = 0x%x !!\n", u4tmp);
+
+		if (rtlpriv->rtlhal.macphymode == DUALMAC_DUALPHY &&
+		    rtlpriv->rtlhal.interfaceindex == 1) {
+			bneed_powerdown_radio =
+				rtl92du_phy_enable_anotherphy(hw, false);
+			rtlpriv->rtlhal.during_mac1init_radioa = true;
+			/* asume no this case */
+			if (bneed_powerdown_radio)
+				rtl92d_phy_enable_rf_env(hw, erfpath,
+							 &u4regvalue);
+		}
+
+		rtl_set_rfreg(hw, erfpath, RF_SYN_G4, 0x3f800, u4tmp);
+
+		if (bneed_powerdown_radio) {
+			rtl92d_phy_restore_rf_env(hw, erfpath, &u4regvalue);
+			rtl92du_phy_powerdown_anotherphy(hw, false);
+		}
+	} else if (rtlpriv->rtlhal.current_bandtype == BAND_ON_2_4G) {
+		u4tmp = rtlpriv->curveindex_2g[channel - 1];
+		RTPRINT(rtlpriv, FINIT, INIT_IQK,
+			"ver 3 set RF-B, 2G, 0x28 = 0x%x !!\n", u4tmp);
+
+		if (rtlpriv->rtlhal.macphymode == DUALMAC_DUALPHY &&
+		    rtlpriv->rtlhal.interfaceindex == 0) {
+			bneed_powerdown_radio =
+				rtl92du_phy_enable_anotherphy(hw, true);
+			rtlpriv->rtlhal.during_mac0init_radiob = true;
+			if (bneed_powerdown_radio)
+				rtl92d_phy_enable_rf_env(hw, erfpath,
+							 &u4regvalue);
+		}
+
+		rtl_set_rfreg(hw, erfpath, RF_SYN_G4, 0x3f800, u4tmp);
+
+		RTPRINT(rtlpriv, FINIT, INIT_IQK,
+			"ver 3 set RF-B, 2G, 0x28 = 0x%x !!\n",
+			rtl_get_rfreg(hw,  erfpath, RF_SYN_G4, 0x3f800));
+
+		if (bneed_powerdown_radio) {
+			rtl92d_phy_restore_rf_env(hw, erfpath, &u4regvalue);
+			rtl92du_phy_powerdown_anotherphy(hw, true);
+		}
+	}
+	rtl_dbg(rtlpriv, COMP_CMD, DBG_LOUD, "<====\n");
+}
+
+static void _rtl92du_phy_lc_calibrate_sw(struct ieee80211_hw *hw, bool is2t)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_hal *rtlhal = &rtlpriv->rtlhal;
+	u32 curvecount_val[CV_CURVE_CNT * 2];
+	u16 timeout = 800, timecount = 0;
+	u32 u4tmp, offset, rf_syn_g4[2];
+	u8 tmpreg, index, rf_mode[2];
+	u8 path = is2t ? 2 : 1;
+	u8 i;
+
+	/* Check continuous TX and Packet TX */
+	tmpreg = rtl_read_byte(rtlpriv, 0xd03);
+	if ((tmpreg & 0x70) != 0)
+		/* if Deal with contisuous TX case, disable all continuous TX */
+		rtl_write_byte(rtlpriv, 0xd03, tmpreg & 0x8F);
+	else
+		/* if Deal with Packet TX case, block all queues */
+		rtl_write_byte(rtlpriv, REG_TXPAUSE, 0xFF);
+
+	rtl_set_bbreg(hw, RFPGA0_ANALOGPARAMETER4, 0xF00000, 0x0F);
+
+	for (index = 0; index < path; index++) {
+		/* 1. Read original RF mode */
+		offset = index == 0 ? ROFDM0_XAAGCCORE1 : ROFDM0_XBAGCCORE1;
+		rf_mode[index] = rtl_read_byte(rtlpriv, offset);
+
+		/* 2. Set RF mode = standby mode */
+		rtl_set_rfreg(hw, (enum radio_path)index, RF_AC,
+			      RFREG_OFFSET_MASK, 0x010000);
+
+		rf_syn_g4[index] = rtl_get_rfreg(hw, index, RF_SYN_G4,
+						 RFREG_OFFSET_MASK);
+		rtl_set_rfreg(hw, index, RF_SYN_G4, 0x700, 0x7);
+
+		/* switch CV-curve control by LC-calibration */
+		rtl_set_rfreg(hw, (enum radio_path)index, RF_SYN_G7,
+			      BIT(17), 0x0);
+
+		/* 4. Set LC calibration begin */
+		rtl_set_rfreg(hw, (enum radio_path)index, RF_CHNLBW,
+			      0x08000, 0x01);
+	}
+
+	for (index = 0; index < path; index++) {
+		u4tmp = rtl_get_rfreg(hw, (enum radio_path)index, RF_SYN_G6,
+				      RFREG_OFFSET_MASK);
+
+		while ((!(u4tmp & BIT(11))) && timecount <= timeout) {
+			mdelay(50);
+			timecount += 50;
+			u4tmp = rtl_get_rfreg(hw, (enum radio_path)index,
+					      RF_SYN_G6, RFREG_OFFSET_MASK);
+		}
+		RTPRINT(rtlpriv, FINIT, INIT_IQK,
+			"PHY_LCK finish delay for %d ms=2\n", timecount);
+	}
+
+	if ((tmpreg & 0x70) != 0)
+		rtl_write_byte(rtlpriv, 0xd03, tmpreg);
+	else /* Deal with Packet TX case */
+		rtl_write_byte(rtlpriv, REG_TXPAUSE, 0x00);
+
+	rtl_set_bbreg(hw, RFPGA0_ANALOGPARAMETER4, 0xF00000, 0x00);
+
+	for (index = 0; index < path; index++) {
+		rtl_get_rfreg(hw, index, RF_SYN_G4, RFREG_OFFSET_MASK);
+
+		if (index == 0 && rtlhal->interfaceindex == 0) {
+			RTPRINT(rtlpriv, FINIT, INIT_IQK,
+				"path-A / 5G LCK\n");
+		} else {
+			RTPRINT(rtlpriv, FINIT, INIT_IQK,
+				"path-B / 2.4G LCK\n");
+		}
+
+		memset(curvecount_val, 0, sizeof(curvecount_val));
+
+		/* Set LC calibration off */
+		rtl_set_rfreg(hw, (enum radio_path)index, RF_CHNLBW,
+			      0x08000, 0x0);
+
+		RTPRINT(rtlpriv, FINIT, INIT_IQK,  "set RF 0x18[15] = 0\n");
+
+		/* save Curve-counting number */
+		for (i = 0; i < CV_CURVE_CNT; i++) {
+			u32 readval = 0, readval2 = 0;
+
+			rtl_set_rfreg(hw, (enum radio_path)index, 0x3F,
+				      0x7f, i);
+
+			rtl_set_rfreg(hw, (enum radio_path)index, 0x4D,
+				      RFREG_OFFSET_MASK, 0x0);
+
+			readval = rtl_get_rfreg(hw, (enum radio_path)index,
+						0x4F, RFREG_OFFSET_MASK);
+			curvecount_val[2 * i + 1] = (readval & 0xfffe0) >> 5;
+
+			/* reg 0x4f [4:0] */
+			/* reg 0x50 [19:10] */
+			readval2 = rtl_get_rfreg(hw, (enum radio_path)index,
+						 0x50, 0xffc00);
+			curvecount_val[2 * i] = (((readval & 0x1F) << 10) |
+						 readval2);
+		}
+
+		if (index == 0 && rtlhal->interfaceindex == 0)
+			rtl92d_phy_calc_curvindex(hw, targetchnl_5g,
+						  curvecount_val,
+						  true, rtlpriv->curveindex_5g);
+		else
+			rtl92d_phy_calc_curvindex(hw, targetchnl_2g,
+						  curvecount_val,
+						  false, rtlpriv->curveindex_2g);
+
+		/* switch CV-curve control mode */
+		rtl_set_rfreg(hw, (enum radio_path)index, RF_SYN_G7,
+			      BIT(17), 0x1);
+	}
+
+	/* Restore original situation  */
+	for (index = 0; index < path; index++) {
+		rtl_set_rfreg(hw, index, RF_SYN_G4, RFREG_OFFSET_MASK,
+			      rf_syn_g4[index]);
+
+		offset = index == 0 ? ROFDM0_XAAGCCORE1 : ROFDM0_XBAGCCORE1;
+		rtl_write_byte(rtlpriv, offset, 0x50);
+		rtl_write_byte(rtlpriv, offset, rf_mode[index]);
+	}
+
+	_rtl92du_phy_reload_lck_setting(hw, rtlpriv->phy.current_channel);
+}
+
+void rtl92du_phy_lc_calibrate(struct ieee80211_hw *hw, bool is2t)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_hal *rtlhal = &rtlpriv->rtlhal;
+	struct rtl_phy *rtlphy = &rtlpriv->phy;
+	u32 timeout = 2000, timecount = 0;
+
+	while (rtlpriv->mac80211.act_scanning && timecount < timeout) {
+		udelay(50);
+		timecount += 50;
+	}
+
+	rtlphy->lck_inprogress = true;
+	RTPRINT(rtlpriv, FINIT, INIT_IQK,
+		"LCK:Start!!! currentband %x delay %d ms\n",
+		rtlhal->current_bandtype, timecount);
+
+	_rtl92du_phy_lc_calibrate_sw(hw, is2t);
+
+	rtlphy->lck_inprogress = false;
+	RTPRINT(rtlpriv, FINIT, INIT_IQK,  "LCK:Finish!!!\n");
+}
+
+void rtl92du_phy_ap_calibrate(struct ieee80211_hw *hw, s8 delta)
+{
+	/* Nothing to do. */
+}
+
+u8 rtl92du_phy_sw_chnl(struct ieee80211_hw *hw)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_hal *rtlhal = rtl_hal(rtlpriv);
+	struct rtl_phy *rtlphy = &rtlpriv->phy;
+	u8 num_total_rfpath = rtlphy->num_total_rfpath;
+	u8 channel = rtlphy->current_channel;
+	u32 timeout = 1000, timecount = 0;
+	u32 ret_value;
+	u8 rfpath;
+
+	if (rtlphy->sw_chnl_inprogress)
+		return 0;
+	if (rtlphy->set_bwmode_inprogress)
+		return 0;
+
+	if ((is_hal_stop(rtlhal)) || (RT_CANNOT_IO(hw))) {
+		rtl_dbg(rtlpriv, COMP_CHAN, DBG_LOUD,
+			"sw_chnl_inprogress false driver sleep or unload\n");
+		return 0;
+	}
+
+	while (rtlphy->lck_inprogress && timecount < timeout) {
+		mdelay(50);
+		timecount += 50;
+	}
+
+	if (rtlhal->macphymode == SINGLEMAC_SINGLEPHY &&
+	    rtlhal->bandset == BAND_ON_BOTH) {
+		ret_value = rtl_get_bbreg(hw, RFPGA0_XAB_RFPARAMETER,
+					  MASKDWORD);
+		if (rtlphy->current_channel > 14 && !(ret_value & BIT(0)))
+			rtl92du_phy_switch_wirelessband(hw, BAND_ON_5G);
+		else if (rtlphy->current_channel <= 14 && (ret_value & BIT(0)))
+			rtl92du_phy_switch_wirelessband(hw, BAND_ON_2_4G);
+	}
+
+	switch (rtlhal->current_bandtype) {
+	case BAND_ON_5G:
+		/* Get first channel error when change between
+		 * 5G and 2.4G band.
+		 */
+		if (WARN_ONCE(channel <= 14, "rtl8192du: 5G but channel<=14\n"))
+			return 0;
+		break;
+	case BAND_ON_2_4G:
+		/* Get first channel error when change between
+		 * 5G and 2.4G band.
+		 */
+		if (WARN_ONCE(channel > 14, "rtl8192du: 2G but channel>14\n"))
+			return 0;
+		break;
+	default:
+		WARN_ONCE(true, "rtl8192du: Invalid WirelessMode(%#x)!!\n",
+			  rtlpriv->mac80211.mode);
+		break;
+	}
+
+	rtlphy->sw_chnl_inprogress = true;
+
+	rtl_dbg(rtlpriv, COMP_SCAN, DBG_TRACE,
+		"switch to channel%d\n", rtlphy->current_channel);
+
+	rtl92d_phy_set_txpower_level(hw, channel);
+
+	for (rfpath = 0; rfpath < num_total_rfpath; rfpath++) {
+		u32p_replace_bits(&rtlphy->rfreg_chnlval[rfpath],
+				  channel, 0xff);
+
+		if (rtlpriv->rtlhal.current_bandtype == BAND_ON_5G) {
+			if (channel > 99)
+				rtlphy->rfreg_chnlval[rfpath] |= (BIT(18));
+			else
+				rtlphy->rfreg_chnlval[rfpath] &= ~BIT(18);
+			rtlphy->rfreg_chnlval[rfpath] |= (BIT(16) | BIT(8));
+		} else {
+			rtlphy->rfreg_chnlval[rfpath] &=
+				~(BIT(8) | BIT(16) | BIT(18));
+		}
+		rtl_set_rfreg(hw, rfpath, RF_CHNLBW, RFREG_OFFSET_MASK,
+			      rtlphy->rfreg_chnlval[rfpath]);
+
+		_rtl92du_phy_reload_imr_setting(hw, channel, rfpath);
+	}
+
+	_rtl92du_phy_switch_rf_setting(hw, channel);
+
+	/* do IQK when all parameters are ready */
+	rtl92du_phy_reload_iqk_setting(hw, channel);
+
+	rtl_dbg(rtlpriv, COMP_SCAN, DBG_TRACE, "<==\n");
+	rtlphy->sw_chnl_inprogress = false;
+	return 1;
+}
+
+static void _rtl92du_phy_set_rfon(struct ieee80211_hw *hw)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+
+	/* a.  SYS_CLKR 0x08[11] = 1  restore MAC clock */
+	/* b.  SPS_CTRL 0x11[7:0] = 0x2b */
+	if (rtlpriv->rtlhal.macphymode == SINGLEMAC_SINGLEPHY)
+		rtl_write_byte(rtlpriv, REG_SPS0_CTRL, 0x2b);
+
+	/* c.  For PCIE: SYS_FUNC_EN 0x02[7:0] = 0xE3 enable BB TRX function */
+	rtl_write_byte(rtlpriv, REG_SYS_FUNC_EN, 0xE3);
+
+	/* RF_ON_EXCEP(d~g): */
+	/* d.  APSD_CTRL 0x600[7:0] = 0x00 */
+	rtl_write_byte(rtlpriv, REG_APSD_CTRL, 0x00);
+
+	/* e.  SYS_FUNC_EN 0x02[7:0] = 0xE2  reset BB TRX function again */
+	/* f.  SYS_FUNC_EN 0x02[7:0] = 0xE3  enable BB TRX function*/
+	rtl_write_byte(rtlpriv, REG_SYS_FUNC_EN, 0xE2);
+	rtl_write_byte(rtlpriv, REG_SYS_FUNC_EN, 0xE3);
+
+	/* g.   txpause 0x522[7:0] = 0x00  enable mac tx queue */
+	rtl_write_byte(rtlpriv, REG_TXPAUSE, 0x00);
+}
+
+static void _rtl92du_phy_set_rfsleep(struct ieee80211_hw *hw)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	u32 u4btmp;
+	u8 retry = 5;
+
+	/* a.   TXPAUSE 0x522[7:0] = 0xFF  Pause MAC TX queue  */
+	rtl_write_byte(rtlpriv, REG_TXPAUSE, 0xFF);
+
+	/* b.   RF path 0 offset 0x00 = 0x00  disable RF  */
+	rtl_set_rfreg(hw, RF90_PATH_A, 0x00, RFREG_OFFSET_MASK, 0x00);
+
+	/* c.   APSD_CTRL 0x600[7:0] = 0x40 */
+	rtl_write_byte(rtlpriv, REG_APSD_CTRL, 0x40);
+
+	/* d. APSD_CTRL 0x600[7:0] = 0x00
+	 * APSD_CTRL 0x600[7:0] = 0x00
+	 * RF path 0 offset 0x00 = 0x00
+	 * APSD_CTRL 0x600[7:0] = 0x40
+	 */
+	u4btmp = rtl_get_rfreg(hw, RF90_PATH_A, 0, RFREG_OFFSET_MASK);
+	while (u4btmp != 0 && retry > 0) {
+		rtl_write_byte(rtlpriv, REG_APSD_CTRL, 0x0);
+		rtl_set_rfreg(hw, RF90_PATH_A, 0x00, RFREG_OFFSET_MASK, 0x00);
+		rtl_write_byte(rtlpriv, REG_APSD_CTRL, 0x40);
+		u4btmp = rtl_get_rfreg(hw, RF90_PATH_A, 0, RFREG_OFFSET_MASK);
+		retry--;
+	}
+	if (retry == 0) {
+		/* Jump out the LPS turn off sequence to RF_ON_EXCEP */
+		rtl_write_byte(rtlpriv, REG_APSD_CTRL, 0x00);
+
+		rtl_write_byte(rtlpriv, REG_SYS_FUNC_EN, 0xE2);
+		rtl_write_byte(rtlpriv, REG_SYS_FUNC_EN, 0xE3);
+		rtl_write_byte(rtlpriv, REG_TXPAUSE, 0x00);
+		rtl_dbg(rtlpriv, COMP_POWER, DBG_LOUD,
+			"Fail !!! Switch RF timeout\n");
+		return;
+	}
+
+	/* e.   For PCIE: SYS_FUNC_EN 0x02[7:0] = 0xE2 reset BB TRX function */
+	rtl_write_byte(rtlpriv, REG_SYS_FUNC_EN, 0xE2);
+
+	/* f.   SPS_CTRL 0x11[7:0] = 0x22 */
+	if (rtlpriv->rtlhal.macphymode == SINGLEMAC_SINGLEPHY)
+		rtl_write_byte(rtlpriv, REG_SPS0_CTRL, 0x22);
+}
+
+bool rtl92du_phy_set_rf_power_state(struct ieee80211_hw *hw,
+				    enum rf_pwrstate rfpwr_state)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_ps_ctl *ppsc = rtl_psc(rtlpriv);
+	struct rtl_mac *mac = rtl_mac(rtlpriv);
+	bool bresult = true;
+
+	if (rfpwr_state == ppsc->rfpwr_state)
+		return false;
+
+	switch (rfpwr_state) {
+	case ERFON:
+		if (ppsc->rfpwr_state == ERFOFF &&
+		    RT_IN_PS_LEVEL(ppsc, RT_RF_OFF_LEVL_HALT_NIC)) {
+			u32 initializecount = 0;
+			bool rtstatus;
+
+			do {
+				initializecount++;
+				rtl_dbg(rtlpriv, COMP_RF, DBG_DMESG,
+					"IPS Set eRf nic enable\n");
+				rtstatus = rtl_ps_enable_nic(hw);
+			} while (!rtstatus && (initializecount < 10));
+
+			RT_CLEAR_PS_LEVEL(ppsc,
+					  RT_RF_OFF_LEVL_HALT_NIC);
+		} else {
+			rtl_dbg(rtlpriv, COMP_POWER, DBG_DMESG,
+				"awake, slept:%d ms state_inap:%x\n",
+				jiffies_to_msecs(jiffies -
+						 ppsc->last_sleep_jiffies),
+				 rtlpriv->psc.state_inap);
+			ppsc->last_awake_jiffies = jiffies;
+			_rtl92du_phy_set_rfon(hw);
+		}
+
+		if (mac->link_state == MAC80211_LINKED)
+			rtlpriv->cfg->ops->led_control(hw, LED_CTL_LINK);
+		else
+			rtlpriv->cfg->ops->led_control(hw, LED_CTL_NO_LINK);
+		break;
+	case ERFOFF:
+		if (ppsc->reg_rfps_level & RT_RF_OFF_LEVL_HALT_NIC) {
+			rtl_dbg(rtlpriv, COMP_RF, DBG_DMESG,
+				"IPS Set eRf nic disable\n");
+			rtl_ps_disable_nic(hw);
+			RT_SET_PS_LEVEL(ppsc, RT_RF_OFF_LEVL_HALT_NIC);
+		} else {
+			if (ppsc->rfoff_reason == RF_CHANGE_BY_IPS)
+				rtlpriv->cfg->ops->led_control(hw, LED_CTL_NO_LINK);
+			else
+				rtlpriv->cfg->ops->led_control(hw, LED_CTL_POWER_OFF);
+		}
+		break;
+	case ERFSLEEP:
+		if (ppsc->rfpwr_state == ERFOFF)
+			return false;
+
+		rtl_dbg(rtlpriv, COMP_POWER, DBG_DMESG,
+			"sleep awakened:%d ms state_inap:%x\n",
+			jiffies_to_msecs(jiffies -
+					 ppsc->last_awake_jiffies),
+			rtlpriv->psc.state_inap);
+		ppsc->last_sleep_jiffies = jiffies;
+		_rtl92du_phy_set_rfsleep(hw);
+		break;
+	default:
+		pr_err("switch case %#x not processed\n",
+		       rfpwr_state);
+		return false;
+	}
+
+	if (bresult)
+		ppsc->rfpwr_state = rfpwr_state;
+
+	return bresult;
+}
+
+void rtl92du_phy_set_poweron(struct ieee80211_hw *hw)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_hal *rtlhal = rtl_hal(rtl_priv(hw));
+	u32 mac_reg = (rtlhal->interfaceindex == 0 ? REG_MAC0 : REG_MAC1);
+	u8 value8;
+	u16 i;
+
+	/* notice fw know band status  0x81[1]/0x53[1] = 0: 5G, 1: 2G */
+	if (rtlhal->current_bandtype == BAND_ON_2_4G) {
+		value8 = rtl_read_byte(rtlpriv, mac_reg);
+		value8 |= BIT(1);
+		rtl_write_byte(rtlpriv, mac_reg, value8);
+	} else {
+		value8 = rtl_read_byte(rtlpriv, mac_reg);
+		value8 &= ~BIT(1);
+		rtl_write_byte(rtlpriv, mac_reg, value8);
+	}
+
+	if (rtlhal->macphymode == SINGLEMAC_SINGLEPHY) {
+		value8 = rtl_read_byte(rtlpriv, REG_MAC0);
+		rtl_write_byte(rtlpriv, REG_MAC0, value8 | MAC0_ON);
+	} else {
+		mutex_lock(rtlpriv->mutex_for_power_on_off);
+		if (rtlhal->interfaceindex == 0) {
+			value8 = rtl_read_byte(rtlpriv, REG_MAC0);
+			rtl_write_byte(rtlpriv, REG_MAC0, value8 | MAC0_ON);
+		} else {
+			value8 = rtl_read_byte(rtlpriv, REG_MAC1);
+			rtl_write_byte(rtlpriv, REG_MAC1, value8 | MAC1_ON);
+		}
+		value8 = rtl_read_byte(rtlpriv, REG_POWER_OFF_IN_PROCESS);
+		mutex_unlock(rtlpriv->mutex_for_power_on_off);
+
+		for (i = 0; i < 200; i++) {
+			if ((value8 & BIT(7)) == 0)
+				break;
+
+			udelay(500);
+			mutex_lock(rtlpriv->mutex_for_power_on_off);
+			value8 = rtl_read_byte(rtlpriv,
+					       REG_POWER_OFF_IN_PROCESS);
+			mutex_unlock(rtlpriv->mutex_for_power_on_off);
+		}
+		if (i == 200)
+			WARN_ONCE(true, "rtl8192du: Another mac power off over time\n");
+	}
+}
+
+void rtl92du_update_bbrf_configuration(struct ieee80211_hw *hw)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_efuse *rtlefuse = rtl_efuse(rtlpriv);
+	struct rtl_hal *rtlhal = rtl_hal(rtlpriv);
+	struct rtl_phy *rtlphy = &rtlpriv->phy;
+	u8 rfpath, i;
+
+	rtl_dbg(rtlpriv, COMP_INIT, DBG_LOUD, "==>\n");
+	/* r_select_5G for path_A/B 0 for 2.4G, 1 for 5G */
+	if (rtlhal->current_bandtype == BAND_ON_2_4G) {
+		/* r_select_5G for path_A/B, 0x878 */
+		rtl_set_bbreg(hw, RFPGA0_XAB_RFPARAMETER, BIT(0), 0x0);
+		rtl_set_bbreg(hw, RFPGA0_XAB_RFPARAMETER, BIT(15), 0x0);
+		if (rtlhal->macphymode != DUALMAC_DUALPHY) {
+			rtl_set_bbreg(hw, RFPGA0_XAB_RFPARAMETER, BIT(16), 0x0);
+			rtl_set_bbreg(hw, RFPGA0_XAB_RFPARAMETER, BIT(31), 0x0);
+		}
+
+		/* rssi_table_select: index 0 for 2.4G. 1~3 for 5G, 0xc78 */
+		rtl_set_bbreg(hw, ROFDM0_AGCRSSITABLE, BIT(6) | BIT(7), 0x0);
+
+		/* fc_area  0xd2c */
+		rtl_set_bbreg(hw, ROFDM1_CFOTRACKING, BIT(14) | BIT(13), 0x0);
+
+		/* 5G LAN ON */
+		rtl_set_bbreg(hw, 0xB30, 0x00F00000, 0xa);
+
+		/* TX BB gain shift*1, Just for testchip, 0xc80, 0xc88 */
+		rtl_set_bbreg(hw, ROFDM0_XATXIQIMBALANCE, MASKDWORD, 0x40000100);
+		rtl_set_bbreg(hw, ROFDM0_XBTXIQIMBALANCE, MASKDWORD, 0x40000100);
+		if (rtlhal->macphymode == DUALMAC_DUALPHY) {
+			rtl_set_bbreg(hw, RFPGA0_XAB_RFINTERFACESW,
+				      BIT(10) | BIT(6) | BIT(5),
+				      ((rtlefuse->eeprom_c9 & BIT(3)) >> 3) |
+				      (rtlefuse->eeprom_c9 & BIT(1)) |
+				      ((rtlefuse->eeprom_cc & BIT(1)) << 4));
+			rtl_set_bbreg(hw, RFPGA0_XA_RFINTERFACEOE,
+				      BIT(10) | BIT(6) | BIT(5),
+				      ((rtlefuse->eeprom_c9 & BIT(2)) >> 2) |
+				      ((rtlefuse->eeprom_c9 & BIT(0)) << 1) |
+				      ((rtlefuse->eeprom_cc & BIT(0)) << 5));
+			rtl_set_bbreg(hw, RFPGA0_XAB_RFPARAMETER, BIT(15), 0);
+
+			rtl_set_bbreg(hw, RPDP_ANTA, MASKDWORD, 0x01017038);
+			rtl_set_bbreg(hw, RCONFIG_ANTA, MASKDWORD, 0x0f600000);
+		} else {
+			rtl_set_bbreg(hw, RFPGA0_XAB_RFINTERFACESW,
+				      BIT(26) | BIT(22) | BIT(21) | BIT(10) |
+				      BIT(6) | BIT(5),
+				      ((rtlefuse->eeprom_c9 & BIT(3)) >> 3) |
+				      (rtlefuse->eeprom_c9 & BIT(1)) |
+				      ((rtlefuse->eeprom_cc & BIT(1)) << 4) |
+				      ((rtlefuse->eeprom_c9 & BIT(7)) << 9) |
+				      ((rtlefuse->eeprom_c9 & BIT(5)) << 12) |
+				      ((rtlefuse->eeprom_cc & BIT(3)) << 18));
+			rtl_set_bbreg(hw, RFPGA0_XA_RFINTERFACEOE,
+				      BIT(10) | BIT(6) | BIT(5),
+				      ((rtlefuse->eeprom_c9 & BIT(2)) >> 2) |
+				      ((rtlefuse->eeprom_c9 & BIT(0)) << 1) |
+				      ((rtlefuse->eeprom_cc & BIT(0)) << 5));
+			rtl_set_bbreg(hw, RFPGA0_XB_RFINTERFACEOE,
+				      BIT(10) | BIT(6) | BIT(5),
+				      ((rtlefuse->eeprom_c9 & BIT(6)) >> 6) |
+				      ((rtlefuse->eeprom_c9 & BIT(4)) >> 3) |
+				      ((rtlefuse->eeprom_cc & BIT(2)) << 3));
+			rtl_set_bbreg(hw, RFPGA0_XAB_RFPARAMETER,
+				      BIT(31) | BIT(15), 0);
+
+			rtl_set_bbreg(hw, RPDP_ANTA, MASKDWORD, 0x01017038);
+			rtl_set_bbreg(hw, RPDP_ANTB, MASKDWORD, 0x01017038);
+			rtl_set_bbreg(hw, RCONFIG_ANTA, MASKDWORD, 0x0f600000);
+			rtl_set_bbreg(hw, RCONFIG_ANTB, MASKDWORD, 0x0f600000);
+		}
+		/* 1.5V_LDO */
+	} else {
+		/* r_select_5G for path_A/B */
+		rtl_set_bbreg(hw, RFPGA0_XAB_RFPARAMETER, BIT(0), 0x1);
+		rtl_set_bbreg(hw, RFPGA0_XAB_RFPARAMETER, BIT(15), 0x1);
+		if (rtlhal->macphymode != DUALMAC_DUALPHY) {
+			rtl_set_bbreg(hw, RFPGA0_XAB_RFPARAMETER, BIT(16), 0x1);
+			rtl_set_bbreg(hw, RFPGA0_XAB_RFPARAMETER, BIT(31), 0x1);
+		}
+
+		/* rssi_table_select: index 0 for 2.4G. 1~3 for 5G */
+		rtl_set_bbreg(hw, ROFDM0_AGCRSSITABLE, BIT(6) | BIT(7), 0x1);
+
+		/* fc_area */
+		rtl_set_bbreg(hw, ROFDM1_CFOTRACKING, BIT(14) | BIT(13), 0x1);
+
+		/* 5G LAN ON */
+		rtl_set_bbreg(hw, 0xB30, 0x00F00000, 0x0);
+
+		/* TX BB gain shift, Just for testchip, 0xc80, 0xc88 */
+		if (rtlefuse->internal_pa_5g[rtlhal->interfaceindex])
+			rtl_set_bbreg(hw, ROFDM0_XATXIQIMBALANCE, MASKDWORD,
+				      0x2d4000b5);
+		else
+			rtl_set_bbreg(hw, ROFDM0_XATXIQIMBALANCE, MASKDWORD,
+				      0x20000080);
+
+		if (rtlhal->macphymode != DUALMAC_DUALPHY) {
+			if (rtlefuse->internal_pa_5g[1])
+				rtl_set_bbreg(hw, ROFDM0_XBTXIQIMBALANCE,
+					      MASKDWORD, 0x2d4000b5);
+			else
+				rtl_set_bbreg(hw, ROFDM0_XBTXIQIMBALANCE,
+					      MASKDWORD, 0x20000080);
+		}
+
+		rtl_set_bbreg(hw, 0xB30, BIT(27), 0);
+
+		if (rtlhal->macphymode == DUALMAC_DUALPHY) {
+			rtl_set_bbreg(hw, RFPGA0_XAB_RFINTERFACESW,
+				      BIT(10) | BIT(6) | BIT(5),
+				      (rtlefuse->eeprom_cc & BIT(5)));
+			rtl_set_bbreg(hw, RFPGA0_XA_RFINTERFACEOE, BIT(10),
+				      ((rtlefuse->eeprom_cc & BIT(4)) >> 4));
+			rtl_set_bbreg(hw, RFPGA0_XAB_RFPARAMETER, BIT(15),
+				      (rtlefuse->eeprom_cc & BIT(4)) >> 4);
+
+			rtl_set_bbreg(hw, RPDP_ANTA, MASKDWORD, 0x01017098);
+			rtl_set_bbreg(hw, RCONFIG_ANTA, MASKDWORD, 0x20000000);
+		} else {
+			rtl_set_bbreg(hw, RFPGA0_XAB_RFINTERFACESW,
+				      BIT(26) | BIT(22) | BIT(21) | BIT(10) |
+				      BIT(6) | BIT(5),
+				      (rtlefuse->eeprom_cc & BIT(5)) |
+				      ((rtlefuse->eeprom_cc & BIT(7)) << 14));
+			rtl_set_bbreg(hw, RFPGA0_XA_RFINTERFACEOE, BIT(10),
+				      ((rtlefuse->eeprom_cc & BIT(4)) >> 4));
+			rtl_set_bbreg(hw, RFPGA0_XB_RFINTERFACEOE, BIT(10),
+				      ((rtlefuse->eeprom_cc & BIT(6)) >> 6));
+			rtl_set_bbreg(hw, RFPGA0_XAB_RFPARAMETER,
+				      BIT(31) | BIT(15),
+				      ((rtlefuse->eeprom_cc & BIT(4)) >> 4) |
+				      ((rtlefuse->eeprom_cc & BIT(6)) << 10));
+
+			rtl_set_bbreg(hw, RPDP_ANTA, MASKDWORD, 0x01017098);
+			rtl_set_bbreg(hw, RPDP_ANTB, MASKDWORD, 0x01017098);
+			rtl_set_bbreg(hw, RCONFIG_ANTA, MASKDWORD, 0x20000000);
+			rtl_set_bbreg(hw, RCONFIG_ANTB, MASKDWORD, 0x20000000);
+		}
+	}
+
+	/* update IQK related settings */
+	rtl_set_bbreg(hw, ROFDM0_XARXIQIMBALANCE, MASKDWORD, 0x40000100);
+	rtl_set_bbreg(hw, ROFDM0_XBRXIQIMBALANCE, MASKDWORD, 0x40000100);
+	rtl_set_bbreg(hw, ROFDM0_XCTXAFE, 0xF0000000, 0x00);
+	rtl_set_bbreg(hw, ROFDM0_ECCATHRESHOLD, BIT(30) | BIT(28) |
+		      BIT(26) | BIT(24), 0x00);
+	rtl_set_bbreg(hw, ROFDM0_XDTXAFE, 0xF0000000, 0x00);
+	rtl_set_bbreg(hw, ROFDM0_RXIQEXTANTA, 0xF0000000, 0x00);
+	rtl_set_bbreg(hw, ROFDM0_AGCRSSITABLE, 0x0000F000, 0x00);
+
+	/* Update RF */
+	for (rfpath = RF90_PATH_A; rfpath < rtlphy->num_total_rfpath;
+	     rfpath++) {
+		if (rtlhal->current_bandtype == BAND_ON_2_4G) {
+			/* MOD_AG for RF path_A 0x18 BIT8,BIT16 */
+			rtl_set_rfreg(hw, rfpath, RF_CHNLBW, BIT(8) | BIT(16) |
+				      BIT(18) | 0xff, 1);
+
+			/* RF0x0b[16:14] =3b'111 */
+			rtl_set_rfreg(hw, (enum radio_path)rfpath, 0x0B,
+				      0x1c000, 0x07);
+		} else {
+			/* MOD_AG for RF path_A 0x18 BIT8,BIT16 */
+			rtl_set_rfreg(hw, RF90_PATH_A, RF_CHNLBW, RFREG_OFFSET_MASK,
+				      0x97524);
+		}
+
+		/* Set right channel on RF reg0x18 for another mac. */
+		if (rtlhal->interfaceindex == 0 && rtlhal->bandset == BAND_ON_2_4G) {
+			/* Set MAC1 default channel if MAC1 not up. */
+			if (!(rtl_read_byte(rtlpriv, REG_MAC1) & MAC1_ON)) {
+				rtl92du_phy_enable_anotherphy(hw, true);
+				rtlhal->during_mac0init_radiob = true;
+				rtl_set_rfreg(hw, RF90_PATH_A, RF_CHNLBW,
+					      RFREG_OFFSET_MASK, 0x97524);
+				rtl92du_phy_powerdown_anotherphy(hw, true);
+			}
+		} else if (rtlhal->interfaceindex == 1 && rtlhal->bandset == BAND_ON_5G) {
+			/* Set MAC0 default channel */
+			if (!(rtl_read_byte(rtlpriv, REG_MAC0) & MAC0_ON)) {
+				rtl92du_phy_enable_anotherphy(hw, false);
+				rtlhal->during_mac1init_radioa = true;
+				rtl_set_rfreg(hw, RF90_PATH_A, RF_CHNLBW,
+					      RFREG_OFFSET_MASK, 0x87401);
+				rtl92du_phy_powerdown_anotherphy(hw, false);
+			}
+		}
+	}
+
+	/* Update for all band. */
+	/* DMDP */
+	if (rtlphy->rf_type == RF_1T1R) {
+		/* Use antenna 0, 0xc04, 0xd04 */
+		rtl_set_bbreg(hw, ROFDM0_TRXPATHENABLE, MASKBYTE0, 0x11);
+		rtl_set_bbreg(hw, ROFDM1_TRXPATHENABLE, BDWORD, 0x1);
+
+		/* enable ad/da clock1 for dual-phy reg0x888 */
+		if (rtlhal->interfaceindex == 0) {
+			rtl_set_bbreg(hw, RFPGA0_ADDALLOCKEN, BIT(12) |
+				      BIT(13), 0x3);
+		} else if (rtl92du_phy_enable_anotherphy(hw, false)) {
+			rtlhal->during_mac1init_radioa = true;
+			rtl_set_bbreg(hw, RFPGA0_ADDALLOCKEN,
+				      BIT(12) | BIT(13), 0x3);
+			rtl92du_phy_powerdown_anotherphy(hw, false);
+		}
+
+		rtl_set_bbreg(hw, ROFDM1_LSTF, BIT(19) | BIT(20), 0x0);
+	} else {
+		/* Single PHY */
+		/* Use antenna 0 & 1, 0xc04, 0xd04 */
+		rtl_set_bbreg(hw, ROFDM0_TRXPATHENABLE, MASKBYTE0, 0x33);
+		rtl_set_bbreg(hw, ROFDM1_TRXPATHENABLE, BDWORD, 0x3);
+		/* disable ad/da clock1,0x888 */
+		rtl_set_bbreg(hw, RFPGA0_ADDALLOCKEN, BIT(12) | BIT(13), 0);
+
+		rtl_set_bbreg(hw, ROFDM1_LSTF, BIT(19) | BIT(20), 0x1);
+	}
+
+	for (rfpath = RF90_PATH_A; rfpath < rtlphy->num_total_rfpath;
+	     rfpath++) {
+		rtlphy->rfreg_chnlval[rfpath] = rtl_get_rfreg(hw, rfpath,
+							      RF_CHNLBW,
+							      RFREG_OFFSET_MASK);
+		rtlphy->reg_rf3c[rfpath] = rtl_get_rfreg(hw, rfpath, 0x3C,
+							 RFREG_OFFSET_MASK);
+	}
+
+	for (i = 0; i < 2; i++)
+		rtl_dbg(rtlpriv, COMP_RF, DBG_LOUD, "RF 0x18 = 0x%x\n",
+			rtlphy->rfreg_chnlval[i]);
+
+	rtl_dbg(rtlpriv, COMP_INIT, DBG_LOUD, "<==\n");
+}
+
+bool rtl92du_phy_check_poweroff(struct ieee80211_hw *hw)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_hal *rtlhal = rtl_hal(rtl_priv(hw));
+	u8 u1btmp;
+
+	if (rtlhal->macphymode == SINGLEMAC_SINGLEPHY) {
+		u1btmp = rtl_read_byte(rtlpriv, REG_MAC0);
+		rtl_write_byte(rtlpriv, REG_MAC0, u1btmp & ~MAC0_ON);
+		return true;
+	}
+
+	mutex_lock(rtlpriv->mutex_for_power_on_off);
+	if (rtlhal->interfaceindex == 0) {
+		u1btmp = rtl_read_byte(rtlpriv, REG_MAC0);
+		rtl_write_byte(rtlpriv, REG_MAC0, u1btmp & ~MAC0_ON);
+		u1btmp = rtl_read_byte(rtlpriv, REG_MAC1);
+		u1btmp &= MAC1_ON;
+	} else {
+		u1btmp = rtl_read_byte(rtlpriv, REG_MAC1);
+		rtl_write_byte(rtlpriv, REG_MAC1, u1btmp & ~MAC1_ON);
+		u1btmp = rtl_read_byte(rtlpriv, REG_MAC0);
+		u1btmp &= MAC0_ON;
+	}
+	if (u1btmp) {
+		mutex_unlock(rtlpriv->mutex_for_power_on_off);
+		return false;
+	}
+	u1btmp = rtl_read_byte(rtlpriv, REG_POWER_OFF_IN_PROCESS);
+	u1btmp |= BIT(7);
+	rtl_write_byte(rtlpriv, REG_POWER_OFF_IN_PROCESS, u1btmp);
+	mutex_unlock(rtlpriv->mutex_for_power_on_off);
+
+	return true;
+}
+
+void rtl92du_phy_init_pa_bias(struct ieee80211_hw *hw)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_hal *rtlhal = rtl_hal(rtlpriv);
+	bool is_single_mac = rtlhal->macphymode == SINGLEMAC_SINGLEPHY;
+	enum radio_path rf_path;
+	u8 val8;
+
+	read_efuse_byte(hw, 0x3FA, &val8);
+
+	rtl_dbg(rtlpriv, COMP_RF, DBG_TRACE, "%s: 0x3FA %#x\n",
+		__func__, val8);
+
+	if (!(val8 & BIT(0)) && (is_single_mac || rtlhal->interfaceindex == 0)) {
+		rtl_set_rfreg(hw, RF90_PATH_A, RF_CHNLBW, RFREG_OFFSET_MASK, 0x07401);
+		rtl_set_rfreg(hw, RF90_PATH_A, RF_AC, RFREG_OFFSET_MASK, 0x70000);
+		rtl_set_rfreg(hw, RF90_PATH_A, RF_IPA, RFREG_OFFSET_MASK, 0x0F425);
+		rtl_set_rfreg(hw, RF90_PATH_A, RF_IPA, RFREG_OFFSET_MASK, 0x4F425);
+		rtl_set_rfreg(hw, RF90_PATH_A, RF_IPA, RFREG_OFFSET_MASK, 0x8F425);
+
+		/* Back to RX Mode */
+		rtl_set_rfreg(hw, RF90_PATH_A, RF_AC, RFREG_OFFSET_MASK, 0x30000);
+
+		rtl_dbg(rtlpriv, COMP_RF, DBG_TRACE, "2G PA BIAS path A\n");
+	}
+
+	if (!(val8 & BIT(1)) && (is_single_mac || rtlhal->interfaceindex == 1)) {
+		rf_path = rtlhal->interfaceindex == 1 ? RF90_PATH_A : RF90_PATH_B;
+
+		rtl_set_rfreg(hw, rf_path, RF_CHNLBW, RFREG_OFFSET_MASK, 0x07401);
+		rtl_set_rfreg(hw, rf_path, RF_AC, RFREG_OFFSET_MASK, 0x70000);
+		rtl_set_rfreg(hw, rf_path, RF_IPA, RFREG_OFFSET_MASK, 0x0F425);
+		rtl_set_rfreg(hw, rf_path, RF_IPA, RFREG_OFFSET_MASK, 0x4F425);
+		rtl_set_rfreg(hw, rf_path, RF_IPA, RFREG_OFFSET_MASK, 0x8F425);
+
+		/* Back to RX Mode */
+		rtl_set_rfreg(hw, rf_path, RF_AC, RFREG_OFFSET_MASK, 0x30000);
+
+		rtl_dbg(rtlpriv, COMP_RF, DBG_TRACE, "2G PA BIAS path B\n");
+	}
+
+	if (!(val8 & BIT(2)) && (is_single_mac || rtlhal->interfaceindex == 0)) {
+		/* 5GL_channel */
+		rtl_set_rfreg(hw, RF90_PATH_A, RF_CHNLBW, RFREG_OFFSET_MASK, 0x17524);
+		rtl_set_rfreg(hw, RF90_PATH_A, RF_AC, RFREG_OFFSET_MASK, 0x70000);
+		rtl_set_rfreg(hw, RF90_PATH_A, RF_IPA, RFREG_OFFSET_MASK, 0x0F496);
+		rtl_set_rfreg(hw, RF90_PATH_A, RF_IPA, RFREG_OFFSET_MASK, 0x4F496);
+		rtl_set_rfreg(hw, RF90_PATH_A, RF_IPA, RFREG_OFFSET_MASK, 0x8F496);
+
+		/* 5GM_channel */
+		rtl_set_rfreg(hw, RF90_PATH_A, RF_CHNLBW, RFREG_OFFSET_MASK, 0x37564);
+		rtl_set_rfreg(hw, RF90_PATH_A, RF_AC, RFREG_OFFSET_MASK, 0x70000);
+		rtl_set_rfreg(hw, RF90_PATH_A, RF_IPA, RFREG_OFFSET_MASK, 0x0F496);
+		rtl_set_rfreg(hw, RF90_PATH_A, RF_IPA, RFREG_OFFSET_MASK, 0x4F496);
+		rtl_set_rfreg(hw, RF90_PATH_A, RF_IPA, RFREG_OFFSET_MASK, 0x8F496);
+
+		/* 5GH_channel */
+		rtl_set_rfreg(hw, RF90_PATH_A, RF_CHNLBW, RFREG_OFFSET_MASK, 0x57595);
+		rtl_set_rfreg(hw, RF90_PATH_A, RF_AC, RFREG_OFFSET_MASK, 0x70000);
+		rtl_set_rfreg(hw, RF90_PATH_A, RF_IPA, RFREG_OFFSET_MASK, 0x0F496);
+		rtl_set_rfreg(hw, RF90_PATH_A, RF_IPA, RFREG_OFFSET_MASK, 0x4F496);
+		rtl_set_rfreg(hw, RF90_PATH_A, RF_IPA, RFREG_OFFSET_MASK, 0x8F496);
+
+		/* Back to RX Mode */
+		rtl_set_rfreg(hw, RF90_PATH_A, RF_AC, RFREG_OFFSET_MASK, 0x30000);
+
+		rtl_dbg(rtlpriv, COMP_RF, DBG_TRACE, "5G PA BIAS path A\n");
+	}
+
+	if (!(val8 & BIT(3)) && (is_single_mac || rtlhal->interfaceindex == 1)) {
+		rf_path = rtlhal->interfaceindex == 1 ? RF90_PATH_A : RF90_PATH_B;
+
+		/* 5GL_channel */
+		rtl_set_rfreg(hw, rf_path, RF_CHNLBW, RFREG_OFFSET_MASK, 0x17524);
+		rtl_set_rfreg(hw, rf_path, RF_AC, RFREG_OFFSET_MASK, 0x70000);
+		rtl_set_rfreg(hw, rf_path, RF_IPA, RFREG_OFFSET_MASK, 0x0F496);
+		rtl_set_rfreg(hw, rf_path, RF_IPA, RFREG_OFFSET_MASK, 0x4F496);
+		rtl_set_rfreg(hw, rf_path, RF_IPA, RFREG_OFFSET_MASK, 0x8F496);
+
+		/* 5GM_channel */
+		rtl_set_rfreg(hw, rf_path, RF_CHNLBW, RFREG_OFFSET_MASK, 0x37564);
+		rtl_set_rfreg(hw, rf_path, RF_AC, RFREG_OFFSET_MASK, 0x70000);
+		rtl_set_rfreg(hw, rf_path, RF_IPA, RFREG_OFFSET_MASK, 0x0F496);
+		rtl_set_rfreg(hw, rf_path, RF_IPA, RFREG_OFFSET_MASK, 0x4F496);
+		rtl_set_rfreg(hw, rf_path, RF_IPA, RFREG_OFFSET_MASK, 0x8F496);
+
+		/* 5GH_channel */
+		rtl_set_rfreg(hw, rf_path, RF_CHNLBW, RFREG_OFFSET_MASK, 0x57595);
+		rtl_set_rfreg(hw, rf_path, RF_AC, RFREG_OFFSET_MASK, 0x70000);
+		rtl_set_rfreg(hw, rf_path, RF_IPA, RFREG_OFFSET_MASK, 0x0F496);
+		rtl_set_rfreg(hw, rf_path, RF_IPA, RFREG_OFFSET_MASK, 0x4F496);
+		rtl_set_rfreg(hw, rf_path, RF_IPA, RFREG_OFFSET_MASK, 0x8F496);
+
+		/* Back to RX Mode */
+		rtl_set_rfreg(hw, rf_path, RF_AC, RFREG_OFFSET_MASK, 0x30000);
+
+		rtl_dbg(rtlpriv, COMP_RF, DBG_TRACE, "5G PA BIAS path B\n");
+	}
+}
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192du/phy.h b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/phy.h
new file mode 100644
index 0000000000000..090a6203db7ec
--- /dev/null
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/phy.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2024  Realtek Corporation.*/
+
+#ifndef __RTL92DU_PHY_H__
+#define __RTL92DU_PHY_H__
+
+u32 rtl92du_phy_query_bb_reg(struct ieee80211_hw *hw,
+			     u32 regaddr, u32 bitmask);
+void rtl92du_phy_set_bb_reg(struct ieee80211_hw *hw,
+			    u32 regaddr, u32 bitmask, u32 data);
+bool rtl92du_phy_mac_config(struct ieee80211_hw *hw);
+bool rtl92du_phy_bb_config(struct ieee80211_hw *hw);
+bool rtl92du_phy_rf_config(struct ieee80211_hw *hw);
+void rtl92du_phy_set_bw_mode(struct ieee80211_hw *hw,
+			     enum nl80211_channel_type ch_type);
+u8 rtl92du_phy_sw_chnl(struct ieee80211_hw *hw);
+bool rtl92du_phy_config_rf_with_headerfile(struct ieee80211_hw *hw,
+					   enum rf_content content,
+					   enum radio_path rfpath);
+bool rtl92du_phy_set_rf_power_state(struct ieee80211_hw *hw,
+				    enum rf_pwrstate rfpwr_state);
+
+void rtl92du_phy_set_poweron(struct ieee80211_hw *hw);
+bool rtl92du_phy_check_poweroff(struct ieee80211_hw *hw);
+void rtl92du_phy_lc_calibrate(struct ieee80211_hw *hw, bool is2t);
+void rtl92du_update_bbrf_configuration(struct ieee80211_hw *hw);
+void rtl92du_phy_ap_calibrate(struct ieee80211_hw *hw, s8 delta);
+void rtl92du_phy_iq_calibrate(struct ieee80211_hw *hw);
+void rtl92du_phy_reload_iqk_setting(struct ieee80211_hw *hw, u8 channel);
+void rtl92du_phy_init_pa_bias(struct ieee80211_hw *hw);
+
+#endif
-- 
GitLab


From 8321424134a400a5e3eb39f9acca6bc6946ff447 Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Thu, 23 May 2024 17:46:26 +0300
Subject: [PATCH 545/950] wifi: rtlwifi: Add rtl8192du/trx.{c,h}

These contain routines related to sending frames to the chip.

Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://msgid.link/bd2c24a0-a1fe-493a-8079-d83fda81a0d5@gmail.com
---
 .../wireless/realtek/rtlwifi/rtl8192du/trx.c  | 372 ++++++++++++++++++
 .../wireless/realtek/rtlwifi/rtl8192du/trx.h  |  60 +++
 2 files changed, 432 insertions(+)
 create mode 100644 drivers/net/wireless/realtek/rtlwifi/rtl8192du/trx.c
 create mode 100644 drivers/net/wireless/realtek/rtlwifi/rtl8192du/trx.h

diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192du/trx.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/trx.c
new file mode 100644
index 0000000000000..743ce0cfffe6d
--- /dev/null
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/trx.c
@@ -0,0 +1,372 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2024  Realtek Corporation.*/
+
+#include "../wifi.h"
+#include "../base.h"
+#include "../usb.h"
+#include "../rtl8192d/reg.h"
+#include "../rtl8192d/def.h"
+#include "../rtl8192d/trx_common.h"
+#include "trx.h"
+
+void rtl92du_tx_cleanup(struct ieee80211_hw *hw, struct sk_buff *skb)
+{
+}
+
+int rtl92du_tx_post_hdl(struct ieee80211_hw *hw, struct urb *urb,
+			struct sk_buff *skb)
+{
+	return 0;
+}
+
+struct sk_buff *rtl92du_tx_aggregate_hdl(struct ieee80211_hw *hw,
+					 struct sk_buff_head *list)
+{
+	return skb_dequeue(list);
+}
+
+static enum rtl_desc_qsel _rtl92du_hwq_to_descq(u16 queue_index)
+{
+	switch (queue_index) {
+	case RTL_TXQ_BCN:
+		return QSLT_BEACON;
+	case RTL_TXQ_MGT:
+		return QSLT_MGNT;
+	case RTL_TXQ_VO:
+		return QSLT_VO;
+	case RTL_TXQ_VI:
+		return QSLT_VI;
+	case RTL_TXQ_BK:
+		return QSLT_BK;
+	default:
+	case RTL_TXQ_BE:
+		return QSLT_BE;
+	}
+}
+
+/* For HW recovery information */
+static void _rtl92du_tx_desc_checksum(__le32 *txdesc)
+{
+	__le16 *ptr = (__le16 *)txdesc;
+	u16 checksum = 0;
+	u32 index;
+
+	/* Clear first */
+	set_tx_desc_tx_desc_checksum(txdesc, 0);
+	for (index = 0; index < 16; index++)
+		checksum = checksum ^ le16_to_cpu(*(ptr + index));
+	set_tx_desc_tx_desc_checksum(txdesc, checksum);
+}
+
+void rtl92du_tx_fill_desc(struct ieee80211_hw *hw,
+			  struct ieee80211_hdr *hdr, u8 *pdesc_tx,
+			  u8 *pbd_desc_tx, struct ieee80211_tx_info *info,
+			  struct ieee80211_sta *sta,
+			  struct sk_buff *skb,
+			  u8 queue_index,
+			  struct rtl_tcb_desc *tcb_desc)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_ps_ctl *ppsc = rtl_psc(rtlpriv);
+	struct rtl_hal *rtlhal = rtl_hal(rtlpriv);
+	struct rtl_mac *mac = rtl_mac(rtlpriv);
+	struct rtl_sta_info *sta_entry;
+	__le16 fc = hdr->frame_control;
+	u8 agg_state = RTL_AGG_STOP;
+	u16 pktlen = skb->len;
+	u32 rts_en, hw_rts_en;
+	u8 ampdu_density = 0;
+	u16 seq_number;
+	__le32 *txdesc;
+	u8 rate_flag;
+	u8 tid;
+
+	rtl_get_tcb_desc(hw, info, sta, skb, tcb_desc);
+
+	txdesc = (__le32 *)skb_push(skb, RTL_TX_HEADER_SIZE);
+	memset(txdesc, 0, RTL_TX_HEADER_SIZE);
+
+	set_tx_desc_pkt_size(txdesc, pktlen);
+	set_tx_desc_linip(txdesc, 0);
+	set_tx_desc_pkt_offset(txdesc, RTL_DUMMY_OFFSET);
+	set_tx_desc_offset(txdesc, RTL_TX_HEADER_SIZE);
+	/* 5G have no CCK rate */
+	if (rtlhal->current_bandtype == BAND_ON_5G)
+		if (tcb_desc->hw_rate < DESC_RATE6M)
+			tcb_desc->hw_rate = DESC_RATE6M;
+
+	set_tx_desc_tx_rate(txdesc, tcb_desc->hw_rate);
+	if (tcb_desc->use_shortgi || tcb_desc->use_shortpreamble)
+		set_tx_desc_data_shortgi(txdesc, 1);
+
+	if (rtlhal->macphymode == DUALMAC_DUALPHY &&
+	    tcb_desc->hw_rate == DESC_RATEMCS7)
+		set_tx_desc_data_shortgi(txdesc, 1);
+
+	if (sta) {
+		sta_entry = (struct rtl_sta_info *)sta->drv_priv;
+		tid = ieee80211_get_tid(hdr);
+		agg_state = sta_entry->tids[tid].agg.agg_state;
+		ampdu_density = sta->deflink.ht_cap.ampdu_density;
+	}
+
+	if (agg_state == RTL_AGG_OPERATIONAL &&
+	    info->flags & IEEE80211_TX_CTL_AMPDU) {
+		set_tx_desc_agg_enable(txdesc, 1);
+		set_tx_desc_max_agg_num(txdesc, 0x14);
+		set_tx_desc_ampdu_density(txdesc, ampdu_density);
+		tcb_desc->rts_enable = 1;
+		tcb_desc->rts_rate = DESC_RATE24M;
+	} else {
+		set_tx_desc_agg_break(txdesc, 1);
+	}
+	seq_number = (le16_to_cpu(hdr->seq_ctrl) & IEEE80211_SCTL_SEQ) >> 4;
+	set_tx_desc_seq(txdesc, seq_number);
+
+	rts_en = tcb_desc->rts_enable && !tcb_desc->cts_enable;
+	hw_rts_en = tcb_desc->rts_enable || tcb_desc->cts_enable;
+	set_tx_desc_rts_enable(txdesc, rts_en);
+	set_tx_desc_hw_rts_enable(txdesc, hw_rts_en);
+	set_tx_desc_cts2self(txdesc, tcb_desc->cts_enable);
+	set_tx_desc_rts_stbc(txdesc, tcb_desc->rts_stbc);
+	/* 5G have no CCK rate */
+	if (rtlhal->current_bandtype == BAND_ON_5G)
+		if (tcb_desc->rts_rate < DESC_RATE6M)
+			tcb_desc->rts_rate = DESC_RATE6M;
+	set_tx_desc_rts_rate(txdesc, tcb_desc->rts_rate);
+	set_tx_desc_rts_bw(txdesc, 0);
+	set_tx_desc_rts_sc(txdesc, tcb_desc->rts_sc);
+	set_tx_desc_rts_short(txdesc, tcb_desc->rts_use_shortpreamble);
+
+	rate_flag = info->control.rates[0].flags;
+	if (mac->bw_40) {
+		if (rate_flag & IEEE80211_TX_RC_DUP_DATA) {
+			set_tx_desc_data_bw(txdesc, 1);
+			set_tx_desc_tx_sub_carrier(txdesc, 3);
+		} else if (rate_flag & IEEE80211_TX_RC_40_MHZ_WIDTH) {
+			set_tx_desc_data_bw(txdesc, 1);
+			set_tx_desc_tx_sub_carrier(txdesc, mac->cur_40_prime_sc);
+		} else {
+			set_tx_desc_data_bw(txdesc, 0);
+			set_tx_desc_tx_sub_carrier(txdesc, 0);
+		}
+	} else {
+		set_tx_desc_data_bw(txdesc, 0);
+		set_tx_desc_tx_sub_carrier(txdesc, 0);
+	}
+
+	if (info->control.hw_key) {
+		struct ieee80211_key_conf *keyconf = info->control.hw_key;
+
+		switch (keyconf->cipher) {
+		case WLAN_CIPHER_SUITE_WEP40:
+		case WLAN_CIPHER_SUITE_WEP104:
+		case WLAN_CIPHER_SUITE_TKIP:
+			set_tx_desc_sec_type(txdesc, 0x1);
+			break;
+		case WLAN_CIPHER_SUITE_CCMP:
+			set_tx_desc_sec_type(txdesc, 0x3);
+			break;
+		default:
+			set_tx_desc_sec_type(txdesc, 0x0);
+			break;
+		}
+	}
+
+	set_tx_desc_pkt_id(txdesc, 0);
+	set_tx_desc_queue_sel(txdesc, _rtl92du_hwq_to_descq(queue_index));
+	set_tx_desc_data_rate_fb_limit(txdesc, 0x1F);
+	set_tx_desc_rts_rate_fb_limit(txdesc, 0xF);
+	set_tx_desc_disable_fb(txdesc, 0);
+	set_tx_desc_use_rate(txdesc, tcb_desc->use_driver_rate);
+
+	if (ieee80211_is_data_qos(fc)) {
+		if (mac->rdg_en) {
+			rtl_dbg(rtlpriv, COMP_SEND, DBG_TRACE,
+				"Enable RDG function\n");
+			set_tx_desc_rdg_enable(txdesc, 1);
+			set_tx_desc_htc(txdesc, 1);
+		}
+		set_tx_desc_qos(txdesc, 1);
+	}
+
+	if (rtlpriv->dm.useramask) {
+		set_tx_desc_rate_id(txdesc, tcb_desc->ratr_index);
+		set_tx_desc_macid(txdesc, tcb_desc->mac_id);
+	} else {
+		set_tx_desc_rate_id(txdesc, 0xC + tcb_desc->ratr_index);
+		set_tx_desc_macid(txdesc, tcb_desc->ratr_index);
+	}
+
+	if (!ieee80211_is_data_qos(fc) && ppsc->leisure_ps &&
+	    ppsc->fwctrl_lps) {
+		set_tx_desc_hwseq_en(txdesc, 1);
+		set_tx_desc_pkt_id(txdesc, 8);
+	}
+
+	if (ieee80211_has_morefrags(fc))
+		set_tx_desc_more_frag(txdesc, 1);
+	if (is_multicast_ether_addr(ieee80211_get_DA(hdr)) ||
+	    is_broadcast_ether_addr(ieee80211_get_DA(hdr)))
+		set_tx_desc_bmc(txdesc, 1);
+
+	set_tx_desc_own(txdesc, 1);
+	set_tx_desc_last_seg(txdesc, 1);
+	set_tx_desc_first_seg(txdesc, 1);
+	_rtl92du_tx_desc_checksum(txdesc);
+
+	rtl_dbg(rtlpriv, COMP_SEND, DBG_TRACE, "==>\n");
+}
+
+static void _rtl92du_config_out_ep(struct ieee80211_hw *hw, u8 num_out_pipe)
+{
+	struct rtl_usb *rtlusb = rtl_usbdev(rtl_usbpriv(hw));
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_hal *rtlhal = rtl_hal(rtlpriv);
+	u16 ep_cfg;
+
+	rtlusb->out_queue_sel = 0;
+	rtlusb->out_ep_nums = 0;
+
+	if (rtlhal->interfaceindex == 0)
+		ep_cfg = rtl_read_word(rtlpriv, REG_USB_Queue_Select_MAC0);
+	else
+		ep_cfg = rtl_read_word(rtlpriv, REG_USB_Queue_Select_MAC1);
+
+	if (ep_cfg & 0x00f) {
+		rtlusb->out_queue_sel |= TX_SELE_HQ;
+		rtlusb->out_ep_nums++;
+	}
+	if (ep_cfg & 0x0f0) {
+		rtlusb->out_queue_sel |= TX_SELE_NQ;
+		rtlusb->out_ep_nums++;
+	}
+	if (ep_cfg & 0xf00) {
+		rtlusb->out_queue_sel |= TX_SELE_LQ;
+		rtlusb->out_ep_nums++;
+	}
+
+	switch (num_out_pipe) {
+	case 3:
+		rtlusb->out_queue_sel = TX_SELE_HQ | TX_SELE_NQ | TX_SELE_LQ;
+		rtlusb->out_ep_nums = 3;
+		break;
+	case 2:
+		rtlusb->out_queue_sel = TX_SELE_HQ | TX_SELE_NQ;
+		rtlusb->out_ep_nums = 2;
+		break;
+	case 1:
+		rtlusb->out_queue_sel = TX_SELE_HQ;
+		rtlusb->out_ep_nums = 1;
+		break;
+	default:
+		break;
+	}
+}
+
+static void _rtl92du_one_out_ep_mapping(struct rtl_usb *rtlusb,
+					struct rtl_ep_map *ep_map)
+{
+	ep_map->ep_mapping[RTL_TXQ_BE] = rtlusb->out_eps[0];
+	ep_map->ep_mapping[RTL_TXQ_BK] = rtlusb->out_eps[0];
+	ep_map->ep_mapping[RTL_TXQ_VI] = rtlusb->out_eps[0];
+	ep_map->ep_mapping[RTL_TXQ_VO] = rtlusb->out_eps[0];
+	ep_map->ep_mapping[RTL_TXQ_MGT] = rtlusb->out_eps[0];
+	ep_map->ep_mapping[RTL_TXQ_BCN] = rtlusb->out_eps[0];
+	ep_map->ep_mapping[RTL_TXQ_HI] = rtlusb->out_eps[0];
+}
+
+static void _rtl92du_two_out_ep_mapping(struct rtl_usb *rtlusb,
+					struct rtl_ep_map *ep_map)
+{
+	ep_map->ep_mapping[RTL_TXQ_BE] = rtlusb->out_eps[1];
+	ep_map->ep_mapping[RTL_TXQ_BK] = rtlusb->out_eps[1];
+	ep_map->ep_mapping[RTL_TXQ_VI] = rtlusb->out_eps[0];
+	ep_map->ep_mapping[RTL_TXQ_VO] = rtlusb->out_eps[0];
+	ep_map->ep_mapping[RTL_TXQ_MGT] = rtlusb->out_eps[0];
+	ep_map->ep_mapping[RTL_TXQ_BCN] = rtlusb->out_eps[0];
+	ep_map->ep_mapping[RTL_TXQ_HI] = rtlusb->out_eps[0];
+}
+
+static void _rtl92du_three_out_ep_mapping(struct rtl_usb *rtlusb,
+					  struct rtl_ep_map *ep_map)
+{
+	ep_map->ep_mapping[RTL_TXQ_BE] = rtlusb->out_eps[2];
+	ep_map->ep_mapping[RTL_TXQ_BK] = rtlusb->out_eps[2];
+	ep_map->ep_mapping[RTL_TXQ_VI] = rtlusb->out_eps[1];
+	ep_map->ep_mapping[RTL_TXQ_VO] = rtlusb->out_eps[0];
+	ep_map->ep_mapping[RTL_TXQ_MGT] = rtlusb->out_eps[0];
+	ep_map->ep_mapping[RTL_TXQ_BCN] = rtlusb->out_eps[0];
+	ep_map->ep_mapping[RTL_TXQ_HI] = rtlusb->out_eps[0];
+}
+
+static int _rtl92du_out_ep_mapping(struct ieee80211_hw *hw)
+{
+	struct rtl_usb *rtlusb = rtl_usbdev(rtl_usbpriv(hw));
+	struct rtl_ep_map *ep_map = &rtlusb->ep_map;
+
+	switch (rtlusb->out_ep_nums) {
+	case 1:
+		_rtl92du_one_out_ep_mapping(rtlusb, ep_map);
+		break;
+	case 2:
+		_rtl92du_two_out_ep_mapping(rtlusb, ep_map);
+		break;
+	case 3:
+		_rtl92du_three_out_ep_mapping(rtlusb, ep_map);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int rtl92du_endpoint_mapping(struct ieee80211_hw *hw)
+{
+	struct rtl_usb *rtlusb = rtl_usbdev(rtl_usbpriv(hw));
+
+	_rtl92du_config_out_ep(hw, rtlusb->out_ep_nums);
+
+	/* Normal chip with one IN and one OUT doesn't have interrupt IN EP. */
+	if (rtlusb->out_ep_nums == 1 && rtlusb->in_ep_nums != 1)
+		return -EINVAL;
+
+	return _rtl92du_out_ep_mapping(hw);
+}
+
+u16 rtl92du_mq_to_hwq(__le16 fc, u16 mac80211_queue_index)
+{
+	u16 hw_queue_index;
+
+	if (unlikely(ieee80211_is_beacon(fc))) {
+		hw_queue_index = RTL_TXQ_BCN;
+		goto out;
+	}
+	if (ieee80211_is_mgmt(fc)) {
+		hw_queue_index = RTL_TXQ_MGT;
+		goto out;
+	}
+
+	switch (mac80211_queue_index) {
+	case 0:
+		hw_queue_index = RTL_TXQ_VO;
+		break;
+	case 1:
+		hw_queue_index = RTL_TXQ_VI;
+		break;
+	case 2:
+		hw_queue_index = RTL_TXQ_BE;
+		break;
+	case 3:
+		hw_queue_index = RTL_TXQ_BK;
+		break;
+	default:
+		hw_queue_index = RTL_TXQ_BE;
+		WARN_ONCE(true, "rtl8192du: QSLT_BE queue, skb_queue:%d\n",
+			  mac80211_queue_index);
+		break;
+	}
+out:
+	return hw_queue_index;
+}
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192du/trx.h b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/trx.h
new file mode 100644
index 0000000000000..8c3d24622fa7c
--- /dev/null
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/trx.h
@@ -0,0 +1,60 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2024  Realtek Corporation.*/
+
+#ifndef __RTL92DU_TRX_H__
+#define __RTL92DU_TRX_H__
+
+#define TX_SELE_HQ				BIT(0)	/* High Queue */
+#define TX_SELE_LQ				BIT(1)	/* Low Queue */
+#define TX_SELE_NQ				BIT(2)	/* Normal Queue */
+
+#define TX_TOTAL_PAGE_NUMBER_92DU			0xF8
+#define TEST_PAGE_NUM_PUBQ_92DU				0x89
+#define TX_TOTAL_PAGE_NUMBER_92D_DUAL_MAC		0x7A
+#define NORMAL_PAGE_NUM_PUBQ_92D_DUAL_MAC		0x5A
+#define NORMAL_PAGE_NUM_HPQ_92D_DUAL_MAC		0x10
+#define NORMAL_PAGE_NUM_LPQ_92D_DUAL_MAC		0x10
+#define NORMAL_PAGE_NUM_NORMALQ_92D_DUAL_MAC		0
+
+#define WMM_NORMAL_TX_TOTAL_PAGE_NUMBER			0xF5
+
+#define WMM_NORMAL_PAGE_NUM_PUBQ_92D			0x65
+#define WMM_NORMAL_PAGE_NUM_HPQ_92D			0x30
+#define WMM_NORMAL_PAGE_NUM_LPQ_92D			0x30
+#define WMM_NORMAL_PAGE_NUM_NPQ_92D			0x30
+
+#define WMM_NORMAL_PAGE_NUM_PUBQ_92D_DUAL_MAC		0x32
+#define WMM_NORMAL_PAGE_NUM_HPQ_92D_DUAL_MAC		0x18
+#define WMM_NORMAL_PAGE_NUM_LPQ_92D_DUAL_MAC		0x18
+#define WMM_NORMAL_PAGE_NUM_NPQ_92D_DUAL_MAC		0x18
+
+static inline void set_tx_desc_bmc(__le32 *__txdesc, u32 __value)
+{
+	le32p_replace_bits(__txdesc, __value, BIT(24));
+}
+
+static inline void set_tx_desc_agg_break(__le32 *__txdesc, u32 __value)
+{
+	le32p_replace_bits((__txdesc + 1), __value, BIT(6));
+}
+
+static inline void set_tx_desc_tx_desc_checksum(__le32 *__txdesc, u32 __value)
+{
+	le32p_replace_bits((__txdesc + 7), __value, GENMASK(15, 0));
+}
+
+void rtl92du_tx_fill_desc(struct ieee80211_hw *hw,
+			  struct ieee80211_hdr *hdr, u8 *pdesc,
+			  u8 *pbd_desc_tx, struct ieee80211_tx_info *info,
+			  struct ieee80211_sta *sta,
+			  struct sk_buff *skb, u8 hw_queue,
+			  struct rtl_tcb_desc *ptcb_desc);
+int rtl92du_endpoint_mapping(struct ieee80211_hw *hw);
+u16 rtl92du_mq_to_hwq(__le16 fc, u16 mac80211_queue_index);
+struct sk_buff *rtl92du_tx_aggregate_hdl(struct ieee80211_hw *hw,
+					 struct sk_buff_head *list);
+void rtl92du_tx_cleanup(struct ieee80211_hw *hw, struct sk_buff  *skb);
+int rtl92du_tx_post_hdl(struct ieee80211_hw *hw, struct urb *urb,
+			struct sk_buff *skb);
+
+#endif
-- 
GitLab


From c0e4ae46ffa20fa12f1748fffcd4c95590da80d4 Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Thu, 23 May 2024 17:46:51 +0300
Subject: [PATCH 546/950] wifi: rtlwifi: Add rtl8192du/rf.{c,h}

These contain one RF configuration function and some functions related
to dual MAC operation.

Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://msgid.link/36258d72-11fd-4f70-84c6-782972f706ed@gmail.com
---
 .../wireless/realtek/rtlwifi/rtl8192du/rf.c   | 240 ++++++++++++++++++
 .../wireless/realtek/rtlwifi/rtl8192du/rf.h   |  11 +
 2 files changed, 251 insertions(+)
 create mode 100644 drivers/net/wireless/realtek/rtlwifi/rtl8192du/rf.c
 create mode 100644 drivers/net/wireless/realtek/rtlwifi/rtl8192du/rf.h

diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192du/rf.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/rf.c
new file mode 100644
index 0000000000000..044dd65eafd04
--- /dev/null
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/rf.c
@@ -0,0 +1,240 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2024  Realtek Corporation.*/
+
+#include "../wifi.h"
+#include "../rtl8192d/reg.h"
+#include "../rtl8192d/phy_common.h"
+#include "phy.h"
+#include "rf.h"
+
+bool rtl92du_phy_enable_anotherphy(struct ieee80211_hw *hw, bool bmac0)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_hal *rtlhal = &rtlpriv->rtlhal;
+	u8 mac_on_bit = bmac0 ? MAC1_ON : MAC0_ON;
+	u8 mac_reg = bmac0 ? REG_MAC1 : REG_MAC0;
+	bool bresult = true; /* true: need to enable BB/RF power */
+	u32 maskforphyset = 0;
+	u16 val16;
+	u8 u1btmp;
+
+	rtlhal->during_mac0init_radiob = false;
+	rtlhal->during_mac1init_radioa = false;
+	rtl_dbg(rtlpriv, COMP_RF, DBG_LOUD, "===>\n");
+
+	/* MAC0 Need PHY1 load radio_b.txt . Driver use DBI to write. */
+	u1btmp = rtl_read_byte(rtlpriv, mac_reg);
+	if (!(u1btmp & mac_on_bit)) {
+		rtl_dbg(rtlpriv, COMP_INIT, DBG_LOUD, "enable BB & RF\n");
+		/* Enable BB and RF power */
+
+		maskforphyset = bmac0 ? MAC0_ACCESS_PHY1 : MAC1_ACCESS_PHY0;
+
+		val16 = rtl_read_word(rtlpriv, REG_SYS_FUNC_EN | maskforphyset);
+		val16 &= 0xfffc;
+		rtl_write_word(rtlpriv, REG_SYS_FUNC_EN | maskforphyset, val16);
+
+		val16 = rtl_read_word(rtlpriv, REG_SYS_FUNC_EN | maskforphyset);
+		val16 |= BIT(13) | BIT(0) | BIT(1);
+		rtl_write_word(rtlpriv, REG_SYS_FUNC_EN | maskforphyset, val16);
+	} else {
+		/* We think if MAC1 is ON,then radio_a.txt
+		 * and radio_b.txt has been load.
+		 */
+		bresult = false;
+	}
+	rtl_dbg(rtlpriv, COMP_RF, DBG_LOUD, "<===\n");
+	return bresult;
+}
+
+void rtl92du_phy_powerdown_anotherphy(struct ieee80211_hw *hw, bool bmac0)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_hal *rtlhal = &rtlpriv->rtlhal;
+	u8 mac_on_bit = bmac0 ? MAC1_ON : MAC0_ON;
+	u8 mac_reg = bmac0 ? REG_MAC1 : REG_MAC0;
+	u32 maskforphyset = 0;
+	u8 u1btmp;
+
+	rtlhal->during_mac0init_radiob = false;
+	rtlhal->during_mac1init_radioa = false;
+	rtl_dbg(rtlpriv, COMP_RF, DBG_LOUD, "====>\n");
+
+	/* check MAC0 enable or not again now, if
+	 * enabled, not power down radio A.
+	 */
+	u1btmp = rtl_read_byte(rtlpriv, mac_reg);
+	if (!(u1btmp & mac_on_bit)) {
+		rtl_dbg(rtlpriv, COMP_INIT, DBG_LOUD, "power down\n");
+		/* power down RF radio A according to YuNan's advice. */
+		maskforphyset = bmac0 ? MAC0_ACCESS_PHY1 : MAC1_ACCESS_PHY0;
+		rtl_write_dword(rtlpriv, RFPGA0_XA_LSSIPARAMETER | maskforphyset,
+				0x00000000);
+	}
+	rtl_dbg(rtlpriv, COMP_RF, DBG_LOUD, "<====\n");
+}
+
+bool rtl92du_phy_rf6052_config(struct ieee80211_hw *hw)
+{
+	bool mac1_initradioa_first = false, mac0_initradiob_first = false;
+	bool need_pwrdown_radioa = false, need_pwrdown_radiob = false;
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_hal *rtlhal = &rtlpriv->rtlhal;
+	struct rtl_phy *rtlphy = &rtlpriv->phy;
+	struct bb_reg_def *pphyreg;
+	bool true_bpath = false;
+	bool rtstatus = true;
+	u32 u4_regvalue = 0;
+	u8 rfpath;
+
+	if (rtlphy->rf_type == RF_1T1R)
+		rtlphy->num_total_rfpath = 1;
+	else
+		rtlphy->num_total_rfpath = 2;
+
+	/* Single phy mode: use radio_a radio_b config path_A path_B
+	 * separately by MAC0, and MAC1 needn't configure RF;
+	 * Dual PHY mode: MAC0 use radio_a config 1st phy path_A,
+	 * MAC1 use radio_b config 2nd PHY path_A.
+	 * DMDP, MAC0 on G band, MAC1 on A band.
+	 */
+	if (rtlhal->macphymode == DUALMAC_DUALPHY) {
+		if (rtlhal->current_bandtype == BAND_ON_2_4G &&
+		    rtlhal->interfaceindex == 0) {
+			/* MAC0 needs PHY1 load radio_b.txt. */
+			if (rtl92du_phy_enable_anotherphy(hw, true)) {
+				rtlphy->num_total_rfpath = 2;
+				mac0_initradiob_first = true;
+			} else {
+				/* We think if MAC1 is ON,then radio_a.txt and
+				 * radio_b.txt has been load.
+				 */
+				return rtstatus;
+			}
+		} else if (rtlhal->current_bandtype == BAND_ON_5G &&
+			   rtlhal->interfaceindex == 1) {
+			/* MAC1 needs PHY0 load radio_a.txt. */
+			if (rtl92du_phy_enable_anotherphy(hw, false)) {
+				rtlphy->num_total_rfpath = 2;
+				mac1_initradioa_first = true;
+			} else {
+				/* We think if MAC0 is ON, then radio_a.txt and
+				 * radio_b.txt has been load.
+				 */
+				return rtstatus;
+			}
+		} else if (rtlhal->interfaceindex == 1) {
+			/* MAC0 enabled, only init radia B.   */
+			true_bpath = true;
+		}
+	}
+
+	for (rfpath = 0; rfpath < rtlphy->num_total_rfpath; rfpath++) {
+		/* Mac1 use PHY0 write */
+		if (mac1_initradioa_first) {
+			if (rfpath == RF90_PATH_A) {
+				rtlhal->during_mac1init_radioa = true;
+				need_pwrdown_radioa = true;
+			} else if (rfpath == RF90_PATH_B) {
+				rtlhal->during_mac1init_radioa = false;
+				mac1_initradioa_first = false;
+				rfpath = RF90_PATH_A;
+				true_bpath = true;
+				rtlphy->num_total_rfpath = 1;
+			}
+		} else if (mac0_initradiob_first) {
+			/* Mac0 use PHY1 write */
+			if (rfpath == RF90_PATH_A)
+				rtlhal->during_mac0init_radiob = false;
+			if (rfpath == RF90_PATH_B) {
+				rtlhal->during_mac0init_radiob = true;
+				mac0_initradiob_first = false;
+				need_pwrdown_radiob = true;
+				rfpath = RF90_PATH_A;
+				true_bpath = true;
+				rtlphy->num_total_rfpath = 1;
+			}
+		}
+
+		pphyreg = &rtlphy->phyreg_def[rfpath];
+
+		switch (rfpath) {
+		case RF90_PATH_A:
+		case RF90_PATH_C:
+			u4_regvalue = rtl_get_bbreg(hw, pphyreg->rfintfs,
+						    BRFSI_RFENV);
+			break;
+		case RF90_PATH_B:
+		case RF90_PATH_D:
+			u4_regvalue = rtl_get_bbreg(hw, pphyreg->rfintfs,
+						    BRFSI_RFENV << 16);
+			break;
+		}
+
+		rtl_set_bbreg(hw, pphyreg->rfintfe, BRFSI_RFENV << 16, 0x1);
+		udelay(1);
+		rtl_set_bbreg(hw, pphyreg->rfintfo, BRFSI_RFENV, 0x1);
+		udelay(1);
+
+		/* Set bit number of Address and Data for RF register */
+		rtl_set_bbreg(hw, pphyreg->rfhssi_para2,
+			      B3WIREADDRESSLENGTH, 0x0);
+		udelay(1);
+		rtl_set_bbreg(hw, pphyreg->rfhssi_para2, B3WIREDATALENGTH, 0x0);
+		udelay(1);
+
+		switch (rfpath) {
+		case RF90_PATH_A:
+			if (true_bpath)
+				rtstatus = rtl92du_phy_config_rf_with_headerfile(
+						hw, radiob_txt,
+						(enum radio_path)rfpath);
+			else
+				rtstatus = rtl92du_phy_config_rf_with_headerfile(
+						hw, radioa_txt,
+						(enum radio_path)rfpath);
+			break;
+		case RF90_PATH_B:
+			rtstatus =
+			    rtl92du_phy_config_rf_with_headerfile(hw, radiob_txt,
+						(enum radio_path)rfpath);
+			break;
+		case RF90_PATH_C:
+			break;
+		case RF90_PATH_D:
+			break;
+		}
+
+		switch (rfpath) {
+		case RF90_PATH_A:
+		case RF90_PATH_C:
+			rtl_set_bbreg(hw, pphyreg->rfintfs, BRFSI_RFENV,
+				      u4_regvalue);
+			break;
+		case RF90_PATH_B:
+		case RF90_PATH_D:
+			rtl_set_bbreg(hw, pphyreg->rfintfs, BRFSI_RFENV << 16,
+				      u4_regvalue);
+			break;
+		}
+
+		if (!rtstatus) {
+			rtl_dbg(rtlpriv, COMP_INIT, DBG_TRACE,
+				"Radio[%d] Fail!!\n", rfpath);
+			return rtstatus;
+		}
+	}
+
+	/* check MAC0 enable or not again, if enabled,
+	 * not power down radio A.
+	 * check MAC1 enable or not again, if enabled,
+	 * not power down radio B.
+	 */
+	if (need_pwrdown_radioa)
+		rtl92du_phy_powerdown_anotherphy(hw, false);
+	else if (need_pwrdown_radiob)
+		rtl92du_phy_powerdown_anotherphy(hw, true);
+	rtl_dbg(rtlpriv, COMP_INIT, DBG_TRACE, "<---\n");
+
+	return rtstatus;
+}
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192du/rf.h b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/rf.h
new file mode 100644
index 0000000000000..4a92cbdd00c0e
--- /dev/null
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/rf.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2024  Realtek Corporation.*/
+
+#ifndef __RTL92DU_RF_H__
+#define __RTL92DU_RF_H__
+
+bool rtl92du_phy_rf6052_config(struct ieee80211_hw *hw);
+bool rtl92du_phy_enable_anotherphy(struct ieee80211_hw *hw, bool bmac0);
+void rtl92du_phy_powerdown_anotherphy(struct ieee80211_hw *hw, bool bmac0);
+
+#endif
-- 
GitLab


From 91f43aee0b1a5e8ba0ea7573e7473546b5cc7292 Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Thu, 23 May 2024 17:47:19 +0300
Subject: [PATCH 547/950] wifi: rtlwifi: Add rtl8192du/fw.{c,h} and
 rtl8192du/led.{c,h}

fw.c contains a function for loading the firmware.
led.c contains a function for controlling the LED.

Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://msgid.link/a52b8907-267c-4811-90ca-5eb852a2aa09@gmail.com
---
 .../wireless/realtek/rtlwifi/rtl8192du/fw.c   | 63 +++++++++++++++++++
 .../wireless/realtek/rtlwifi/rtl8192du/fw.h   |  9 +++
 .../wireless/realtek/rtlwifi/rtl8192du/led.c  | 10 +++
 .../wireless/realtek/rtlwifi/rtl8192du/led.h  |  9 +++
 4 files changed, 91 insertions(+)
 create mode 100644 drivers/net/wireless/realtek/rtlwifi/rtl8192du/fw.c
 create mode 100644 drivers/net/wireless/realtek/rtlwifi/rtl8192du/fw.h
 create mode 100644 drivers/net/wireless/realtek/rtlwifi/rtl8192du/led.c
 create mode 100644 drivers/net/wireless/realtek/rtlwifi/rtl8192du/led.h

diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192du/fw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/fw.c
new file mode 100644
index 0000000000000..f74e4e84fe391
--- /dev/null
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/fw.c
@@ -0,0 +1,63 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2024  Realtek Corporation.*/
+
+#include "../wifi.h"
+#include "../rtl8192d/reg.h"
+#include "../rtl8192d/def.h"
+#include "../rtl8192d/fw_common.h"
+#include "fw.h"
+
+int rtl92du_download_fw(struct ieee80211_hw *hw)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_hal *rtlhal = rtl_hal(rtlpriv);
+	enum version_8192d version = rtlhal->version;
+	u8 *pfwheader;
+	u8 *pfwdata;
+	u32 fwsize;
+	int err;
+
+	if (rtlpriv->max_fw_size == 0 || !rtlhal->pfirmware)
+		return 1;
+
+	fwsize = rtlhal->fwsize;
+	pfwheader = rtlhal->pfirmware;
+	pfwdata = rtlhal->pfirmware;
+	rtlhal->fw_version = (u16)GET_FIRMWARE_HDR_VERSION(pfwheader);
+	rtlhal->fw_subversion = (u16)GET_FIRMWARE_HDR_SUB_VER(pfwheader);
+
+	rtl_dbg(rtlpriv, COMP_INIT, DBG_LOUD,
+		"FirmwareVersion(%d), FirmwareSubVersion(%d), Signature(%#x)\n",
+		rtlhal->fw_version, rtlhal->fw_subversion,
+		GET_FIRMWARE_HDR_SIGNATURE(pfwheader));
+
+	if (IS_FW_HEADER_EXIST(pfwheader)) {
+		rtl_dbg(rtlpriv, COMP_INIT, DBG_LOUD,
+			"Shift 32 bytes for FW header!!\n");
+		pfwdata = pfwdata + 32;
+		fwsize = fwsize - 32;
+	}
+
+	if (rtl92d_is_fw_downloaded(rtlpriv))
+		goto exit;
+
+	/* If 8051 is running in RAM code, driver should
+	 * inform Fw to reset by itself, or it will cause
+	 * download Fw fail.
+	 */
+	if (rtl_read_byte(rtlpriv, REG_MCUFWDL) & BIT(7)) {
+		rtl92d_firmware_selfreset(hw);
+		rtl_write_byte(rtlpriv, REG_MCUFWDL, 0x00);
+	}
+
+	rtl92d_enable_fw_download(hw, true);
+	rtl92d_write_fw(hw, version, pfwdata, fwsize);
+	rtl92d_enable_fw_download(hw, false);
+
+	err = rtl92d_fw_free_to_go(hw);
+	if (err)
+		pr_err("fw is not ready to run!\n");
+exit:
+	err = rtl92d_fw_init(hw);
+	return err;
+}
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192du/fw.h b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/fw.h
new file mode 100644
index 0000000000000..7904bfbda4ba9
--- /dev/null
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/fw.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2024  Realtek Corporation.*/
+
+#ifndef __RTL92DU_FW_H__
+#define __RTL92DU_FW_H__
+
+int rtl92du_download_fw(struct ieee80211_hw *hw);
+
+#endif
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192du/led.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/led.c
new file mode 100644
index 0000000000000..6c12dfbd6367d
--- /dev/null
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/led.c
@@ -0,0 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2024  Realtek Corporation.*/
+
+#include "../wifi.h"
+#include "led.h"
+
+void rtl92du_led_control(struct ieee80211_hw *hw, enum led_ctl_mode ledaction)
+{
+	/* The hardware has control. */
+}
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192du/led.h b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/led.h
new file mode 100644
index 0000000000000..d7ebc8afcc7b1
--- /dev/null
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/led.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2024  Realtek Corporation.*/
+
+#ifndef __RTL92DU_LED_H__
+#define __RTL92DU_LED_H__
+
+void rtl92du_led_control(struct ieee80211_hw *hw, enum led_ctl_mode ledaction);
+
+#endif
-- 
GitLab


From 3f8b94dbff7ed9cbf07b397b08387da459085c6c Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Thu, 23 May 2024 17:47:40 +0300
Subject: [PATCH 548/950] wifi: rtlwifi: Add rtl8192du/dm.{c,h}

These contain functions related to the dynamic mechanism, which runs
every two seconds to adjust to changes in the environment.

Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://msgid.link/a010ed6d-efb0-456d-bd4a-dfc6da23e7aa@gmail.com
---
 .../wireless/realtek/rtlwifi/rtl8192du/dm.c   | 120 ++++++++++++++++++
 .../wireless/realtek/rtlwifi/rtl8192du/dm.h   |  10 ++
 2 files changed, 130 insertions(+)
 create mode 100644 drivers/net/wireless/realtek/rtlwifi/rtl8192du/dm.c
 create mode 100644 drivers/net/wireless/realtek/rtlwifi/rtl8192du/dm.h

diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192du/dm.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/dm.c
new file mode 100644
index 0000000000000..dd57707a9184b
--- /dev/null
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/dm.c
@@ -0,0 +1,120 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2024  Realtek Corporation.*/
+
+#include "../wifi.h"
+#include "../core.h"
+#include "../rtl8192d/reg.h"
+#include "../rtl8192d/def.h"
+#include "../rtl8192d/dm_common.h"
+#include "../rtl8192d/fw_common.h"
+#include "dm.h"
+
+static void rtl92du_dm_init_1r_cca(struct ieee80211_hw *hw)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct ps_t *dm_pstable = &rtlpriv->dm_pstable;
+
+	dm_pstable->pre_ccastate = CCA_MAX;
+	dm_pstable->cur_ccasate = CCA_MAX;
+}
+
+static void rtl92du_dm_1r_cca(struct ieee80211_hw *hw)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct ps_t *dm_pstable = &rtlpriv->dm_pstable;
+	struct rtl_hal *rtlhal = rtl_hal(rtlpriv);
+	int pwdb = rtlpriv->dm_digtable.min_undec_pwdb_for_dm;
+
+	if (rtlhal->macphymode != SINGLEMAC_SINGLEPHY ||
+	    rtlhal->current_bandtype != BAND_ON_5G)
+		return;
+
+	if (pwdb != 0) {
+		if (dm_pstable->pre_ccastate == CCA_2R ||
+		    dm_pstable->pre_ccastate == CCA_MAX)
+			dm_pstable->cur_ccasate = (pwdb >= 35) ? CCA_1R : CCA_2R;
+		else
+			dm_pstable->cur_ccasate = (pwdb <= 30) ? CCA_2R : CCA_1R;
+	} else {
+		dm_pstable->cur_ccasate = CCA_MAX;
+	}
+
+	if (dm_pstable->pre_ccastate == dm_pstable->cur_ccasate)
+		return;
+
+	rtl_dbg(rtlpriv, COMP_BB_POWERSAVING, DBG_TRACE,
+		"Old CCA state: %d new CCA state: %d\n",
+		dm_pstable->pre_ccastate, dm_pstable->cur_ccasate);
+
+	if (dm_pstable->cur_ccasate == CCA_1R) {
+		if (rtlpriv->phy.rf_type == RF_2T2R)
+			rtl_set_bbreg(hw, ROFDM0_TRXPATHENABLE, MASKBYTE0, 0x13);
+		else /* Is this branch reachable? */
+			rtl_set_bbreg(hw, ROFDM0_TRXPATHENABLE, MASKBYTE0, 0x23);
+	} else { /* CCA_2R or CCA_MAX */
+		rtl_set_bbreg(hw, ROFDM0_TRXPATHENABLE, MASKBYTE0, 0x33);
+	}
+}
+
+static void rtl92du_dm_pwdb_monitor(struct ieee80211_hw *hw)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	const u32 max_macid = 32;
+	u32 temp;
+
+	/* AP & ADHOC & MESH will return tmp */
+	if (rtlpriv->mac80211.opmode != NL80211_IFTYPE_STATION)
+		return;
+
+	/* Indicate Rx signal strength to FW. */
+	if (rtlpriv->dm.useramask) {
+		temp = rtlpriv->dm.undec_sm_pwdb << 16;
+		temp |= max_macid << 8;
+
+		rtl92d_fill_h2c_cmd(hw, H2C_RSSI_REPORT, 3, (u8 *)(&temp));
+	} else {
+		rtl_write_byte(rtlpriv, 0x4fe, (u8)rtlpriv->dm.undec_sm_pwdb);
+	}
+}
+
+void rtl92du_dm_init(struct ieee80211_hw *hw)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+
+	rtlpriv->dm.dm_type = DM_TYPE_BYDRIVER;
+	rtl_dm_diginit(hw, 0x20);
+	rtlpriv->dm_digtable.rx_gain_max = DM_DIG_FA_UPPER;
+	rtlpriv->dm_digtable.rx_gain_min = DM_DIG_FA_LOWER;
+	rtl92d_dm_init_edca_turbo(hw);
+	rtl92du_dm_init_1r_cca(hw);
+	rtl92d_dm_init_rate_adaptive_mask(hw);
+	rtl92d_dm_initialize_txpower_tracking(hw);
+}
+
+void rtl92du_dm_watchdog(struct ieee80211_hw *hw)
+{
+	struct rtl_ps_ctl *ppsc = rtl_psc(rtl_priv(hw));
+	bool fw_current_inpsmode = false;
+	bool fwps_awake = true;
+
+	/* 1. RF is OFF. (No need to do DM.)
+	 * 2. Fw is under power saving mode for FwLPS.
+	 *    (Prevent from SW/FW I/O racing.)
+	 * 3. IPS workitem is scheduled. (Prevent from IPS sequence
+	 *    to be swapped with DM.
+	 * 4. RFChangeInProgress is TRUE.
+	 *    (Prevent from broken by IPS/HW/SW Rf off.)
+	 */
+
+	if (ppsc->rfpwr_state != ERFON || fw_current_inpsmode ||
+	    !fwps_awake || ppsc->rfchange_inprogress)
+		return;
+
+	rtl92du_dm_pwdb_monitor(hw);
+	rtl92d_dm_false_alarm_counter_statistics(hw);
+	rtl92d_dm_find_minimum_rssi(hw);
+	rtl92d_dm_dig(hw);
+	rtl92d_dm_check_txpower_tracking_thermal_meter(hw);
+	rtl92d_dm_check_edca_turbo(hw);
+	rtl92du_dm_1r_cca(hw);
+}
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192du/dm.h b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/dm.h
new file mode 100644
index 0000000000000..2f283bf1e4d8d
--- /dev/null
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/dm.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2024  Realtek Corporation.*/
+
+#ifndef __RTL92DU_DM_H__
+#define __RTL92DU_DM_H__
+
+void rtl92du_dm_init(struct ieee80211_hw *hw);
+void rtl92du_dm_watchdog(struct ieee80211_hw *hw);
+
+#endif
-- 
GitLab


From 1d8b5003a55ccab64e865d2f34ab1fd7a4cfe3bb Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Thu, 23 May 2024 17:48:02 +0300
Subject: [PATCH 549/950] wifi: rtlwifi: Constify
 rtl_hal_cfg.{ops,usb_interface_cfg} and rtl_priv.cfg

This allows the drivers to declare the structs rtl_hal_cfg, rtl_hal_ops,
and rtl_hal_usbint_cfg as const.

Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://msgid.link/1b29994f-3d07-4297-875d-57c3a87a1ec6@gmail.com
---
 drivers/net/wireless/realtek/rtlwifi/base.c         | 2 +-
 drivers/net/wireless/realtek/rtlwifi/rtl8192cu/sw.c | 3 +--
 drivers/net/wireless/realtek/rtlwifi/usb.c          | 2 +-
 drivers/net/wireless/realtek/rtlwifi/usb.h          | 2 +-
 drivers/net/wireless/realtek/rtlwifi/wifi.h         | 6 +++---
 5 files changed, 7 insertions(+), 8 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtlwifi/base.c b/drivers/net/wireless/realtek/rtlwifi/base.c
index 1a8d715b7c070..aab4605de9c47 100644
--- a/drivers/net/wireless/realtek/rtlwifi/base.c
+++ b/drivers/net/wireless/realtek/rtlwifi/base.c
@@ -2272,7 +2272,7 @@ static void rtl_c2h_content_parsing(struct ieee80211_hw *hw,
 				    struct sk_buff *skb)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
-	struct rtl_hal_ops *hal_ops = rtlpriv->cfg->ops;
+	const struct rtl_hal_ops *hal_ops = rtlpriv->cfg->ops;
 	const struct rtl_btc_ops *btc_ops = rtlpriv->btcoexist.btc_ops;
 	u8 cmd_id, cmd_len;
 	u8 *cmd_buf = NULL;
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/sw.c
index 48be7e346efcc..c9b9e2bc90cc4 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/sw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/sw.c
@@ -53,8 +53,6 @@ static int rtl92cu_init_sw_vars(struct ieee80211_hw *hw)
 	} else {
 		fw_name = "rtlwifi/rtl8192cufw_TMSC.bin";
 	}
-	/* provide name of alternative file */
-	rtlpriv->cfg->alt_fw_name = "rtlwifi/rtl8192cufw.bin";
 	pr_info("Loading firmware %s\n", fw_name);
 	rtlpriv->max_fw_size = 0x4000;
 	err = request_firmware_nowait(THIS_MODULE, 1,
@@ -160,6 +158,7 @@ static struct rtl_hal_usbint_cfg rtl92cu_interface_cfg = {
 
 static struct rtl_hal_cfg rtl92cu_hal_cfg = {
 	.name = "rtl92c_usb",
+	.alt_fw_name = "rtlwifi/rtl8192cufw.bin",
 	.ops = &rtl8192cu_hal_ops,
 	.mod_params = &rtl92cu_mod_params,
 	.usb_interface_cfg = &rtl92cu_interface_cfg,
diff --git a/drivers/net/wireless/realtek/rtlwifi/usb.c b/drivers/net/wireless/realtek/rtlwifi/usb.c
index 2ea72d9e39577..b6d300bec1e9d 100644
--- a/drivers/net/wireless/realtek/rtlwifi/usb.c
+++ b/drivers/net/wireless/realtek/rtlwifi/usb.c
@@ -937,7 +937,7 @@ static const struct rtl_intf_ops rtl_usb_ops = {
 
 int rtl_usb_probe(struct usb_interface *intf,
 		  const struct usb_device_id *id,
-		  struct rtl_hal_cfg *rtl_hal_cfg)
+		  const struct rtl_hal_cfg *rtl_hal_cfg)
 {
 	int err;
 	struct ieee80211_hw *hw = NULL;
diff --git a/drivers/net/wireless/realtek/rtlwifi/usb.h b/drivers/net/wireless/realtek/rtlwifi/usb.h
index 12529afc0510b..b66d6f9ae564e 100644
--- a/drivers/net/wireless/realtek/rtlwifi/usb.h
+++ b/drivers/net/wireless/realtek/rtlwifi/usb.h
@@ -136,7 +136,7 @@ struct rtl_usb_priv {
 
 int rtl_usb_probe(struct usb_interface *intf,
 		  const struct usb_device_id *id,
-		  struct rtl_hal_cfg *rtl92cu_hal_cfg);
+		  const struct rtl_hal_cfg *rtl92cu_hal_cfg);
 void rtl_usb_disconnect(struct usb_interface *intf);
 int rtl_usb_suspend(struct usb_interface *pusb_intf, pm_message_t message);
 int rtl_usb_resume(struct usb_interface *pusb_intf);
diff --git a/drivers/net/wireless/realtek/rtlwifi/wifi.h b/drivers/net/wireless/realtek/rtlwifi/wifi.h
index 6a8212fd36af6..ae6e351bc83c9 100644
--- a/drivers/net/wireless/realtek/rtlwifi/wifi.h
+++ b/drivers/net/wireless/realtek/rtlwifi/wifi.h
@@ -2356,9 +2356,9 @@ struct rtl_hal_cfg {
 	bool write_readback;
 	char *name;
 	char *alt_fw_name;
-	struct rtl_hal_ops *ops;
+	const struct rtl_hal_ops *ops;
 	struct rtl_mod_params *mod_params;
-	struct rtl_hal_usbint_cfg *usb_interface_cfg;
+	const struct rtl_hal_usbint_cfg *usb_interface_cfg;
 	enum rtl_spec_ver spec_ver;
 
 	/*this map used for some registers or vars
@@ -2707,7 +2707,7 @@ struct rtl_priv {
 	/* hal_cfg : for diff cards
 	 * intf_ops : for diff interrface usb/pcie
 	 */
-	struct rtl_hal_cfg *cfg;
+	const struct rtl_hal_cfg *cfg;
 	const struct rtl_intf_ops *intf_ops;
 
 	/* this var will be set by set_bit,
-- 
GitLab


From b5dc8873b6ffebd331e46814e537179eac8b6aa4 Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Thu, 23 May 2024 17:48:32 +0300
Subject: [PATCH 550/950] wifi: rtlwifi: Add rtl8192du/sw.c

This contains the new module's entry point.

Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://msgid.link/1fdc83ac-4a6f-4645-8837-6e38683b6c84@gmail.com
---
 .../wireless/realtek/rtlwifi/rtl8192du/sw.c   | 395 ++++++++++++++++++
 1 file changed, 395 insertions(+)
 create mode 100644 drivers/net/wireless/realtek/rtlwifi/rtl8192du/sw.c

diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192du/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/sw.c
new file mode 100644
index 0000000000000..d069a81ac6175
--- /dev/null
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/sw.c
@@ -0,0 +1,395 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2024  Realtek Corporation.*/
+
+#include "../wifi.h"
+#include "../core.h"
+#include "../usb.h"
+#include "../base.h"
+#include "../rtl8192d/reg.h"
+#include "../rtl8192d/def.h"
+#include "../rtl8192d/fw_common.h"
+#include "../rtl8192d/hw_common.h"
+#include "../rtl8192d/phy_common.h"
+#include "../rtl8192d/trx_common.h"
+#include "phy.h"
+#include "dm.h"
+#include "hw.h"
+#include "trx.h"
+#include "led.h"
+
+#include <linux/module.h>
+
+static struct usb_interface *rtl92du_get_other_intf(struct ieee80211_hw *hw)
+{
+	struct usb_interface *intf;
+	struct usb_device *udev;
+	u8 other_interfaceindex;
+
+	/* See SET_IEEE80211_DEV(hw, &intf->dev); in usb.c */
+	intf = container_of_const(wiphy_dev(hw->wiphy), struct usb_interface, dev);
+
+	if (intf->altsetting[0].desc.bInterfaceNumber == 0)
+		other_interfaceindex = 1;
+	else
+		other_interfaceindex = 0;
+
+	udev = interface_to_usbdev(intf);
+
+	return usb_ifnum_to_if(udev, other_interfaceindex);
+}
+
+static int rtl92du_init_shared_data(struct ieee80211_hw *hw)
+{
+	struct usb_interface *other_intf = rtl92du_get_other_intf(hw);
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_priv *other_rtlpriv = NULL;
+	struct ieee80211_hw *other_hw = NULL;
+
+	if (other_intf)
+		other_hw = usb_get_intfdata(other_intf);
+
+	if (other_hw) {
+		/* The other interface was already probed. */
+		other_rtlpriv = rtl_priv(other_hw);
+		rtlpriv->curveindex_2g = other_rtlpriv->curveindex_2g;
+		rtlpriv->curveindex_5g = other_rtlpriv->curveindex_5g;
+		rtlpriv->mutex_for_power_on_off = other_rtlpriv->mutex_for_power_on_off;
+		rtlpriv->mutex_for_hw_init = other_rtlpriv->mutex_for_hw_init;
+
+		if (!rtlpriv->curveindex_2g || !rtlpriv->curveindex_5g ||
+		    !rtlpriv->mutex_for_power_on_off || !rtlpriv->mutex_for_hw_init)
+			return -ENOMEM;
+
+		return 0;
+	}
+
+	/* The other interface doesn't exist or was not probed yet. */
+	rtlpriv->curveindex_2g = kcalloc(TARGET_CHNL_NUM_2G,
+					 sizeof(*rtlpriv->curveindex_2g),
+					 GFP_KERNEL);
+	rtlpriv->curveindex_5g = kcalloc(TARGET_CHNL_NUM_5G,
+					 sizeof(*rtlpriv->curveindex_5g),
+					 GFP_KERNEL);
+	rtlpriv->mutex_for_power_on_off =
+		kzalloc(sizeof(*rtlpriv->mutex_for_power_on_off), GFP_KERNEL);
+	rtlpriv->mutex_for_hw_init =
+		kzalloc(sizeof(*rtlpriv->mutex_for_hw_init), GFP_KERNEL);
+
+	if (!rtlpriv->curveindex_2g || !rtlpriv->curveindex_5g ||
+	    !rtlpriv->mutex_for_power_on_off || !rtlpriv->mutex_for_hw_init) {
+		kfree(rtlpriv->curveindex_2g);
+		kfree(rtlpriv->curveindex_5g);
+		kfree(rtlpriv->mutex_for_power_on_off);
+		kfree(rtlpriv->mutex_for_hw_init);
+		rtlpriv->curveindex_2g = NULL;
+		rtlpriv->curveindex_5g = NULL;
+		rtlpriv->mutex_for_power_on_off = NULL;
+		rtlpriv->mutex_for_hw_init = NULL;
+		return -ENOMEM;
+	}
+
+	mutex_init(rtlpriv->mutex_for_power_on_off);
+	mutex_init(rtlpriv->mutex_for_hw_init);
+
+	return 0;
+}
+
+static void rtl92du_deinit_shared_data(struct ieee80211_hw *hw)
+{
+	struct usb_interface *other_intf = rtl92du_get_other_intf(hw);
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+
+	if (!other_intf || !usb_get_intfdata(other_intf)) {
+		/* The other interface doesn't exist or was already disconnected. */
+		kfree(rtlpriv->curveindex_2g);
+		kfree(rtlpriv->curveindex_5g);
+		if (rtlpriv->mutex_for_power_on_off)
+			mutex_destroy(rtlpriv->mutex_for_power_on_off);
+		if (rtlpriv->mutex_for_hw_init)
+			mutex_destroy(rtlpriv->mutex_for_hw_init);
+		kfree(rtlpriv->mutex_for_power_on_off);
+		kfree(rtlpriv->mutex_for_hw_init);
+	}
+}
+
+static int rtl92du_init_sw_vars(struct ieee80211_hw *hw)
+{
+	const char *fw_name = "rtlwifi/rtl8192dufw.bin";
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	int err;
+
+	err = rtl92du_init_shared_data(hw);
+	if (err)
+		return err;
+
+	rtlpriv->dm.dm_initialgain_enable = true;
+	rtlpriv->dm.dm_flag = 0;
+	rtlpriv->dm.disable_framebursting = false;
+	rtlpriv->dm.thermalvalue = 0;
+	rtlpriv->dm.useramask = true;
+
+	/* dual mac */
+	if (rtlpriv->rtlhal.current_bandtype == BAND_ON_5G)
+		rtlpriv->phy.current_channel = 36;
+	else
+		rtlpriv->phy.current_channel = 1;
+
+	if (rtlpriv->rtlhal.macphymode != SINGLEMAC_SINGLEPHY)
+		rtlpriv->rtlhal.disable_amsdu_8k = true;
+
+	/* for LPS & IPS */
+	rtlpriv->psc.inactiveps = rtlpriv->cfg->mod_params->inactiveps;
+	rtlpriv->psc.swctrl_lps = rtlpriv->cfg->mod_params->swctrl_lps;
+	rtlpriv->psc.fwctrl_lps = rtlpriv->cfg->mod_params->fwctrl_lps;
+
+	/* for early mode */
+	rtlpriv->rtlhal.earlymode_enable = false;
+
+	/* for firmware buf */
+	rtlpriv->rtlhal.pfirmware = kmalloc(0x8000, GFP_KERNEL);
+	if (!rtlpriv->rtlhal.pfirmware)
+		return -ENOMEM;
+
+	rtlpriv->max_fw_size = 0x8000;
+	pr_info("Driver for Realtek RTL8192DU WLAN interface\n");
+	pr_info("Loading firmware file %s\n", fw_name);
+
+	/* request fw */
+	err = request_firmware_nowait(THIS_MODULE, 1, fw_name,
+				      rtlpriv->io.dev, GFP_KERNEL, hw,
+				      rtl_fw_cb);
+	if (err) {
+		pr_err("Failed to request firmware!\n");
+		kfree(rtlpriv->rtlhal.pfirmware);
+		rtlpriv->rtlhal.pfirmware = NULL;
+		return err;
+	}
+
+	return 0;
+}
+
+static void rtl92du_deinit_sw_vars(struct ieee80211_hw *hw)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+
+	kfree(rtlpriv->rtlhal.pfirmware);
+	rtlpriv->rtlhal.pfirmware = NULL;
+
+	rtl92du_deinit_shared_data(hw);
+}
+
+static const struct rtl_hal_ops rtl8192du_hal_ops = {
+	.init_sw_vars = rtl92du_init_sw_vars,
+	.deinit_sw_vars = rtl92du_deinit_sw_vars,
+	.read_chip_version = rtl92du_read_chip_version,
+	.read_eeprom_info = rtl92d_read_eeprom_info,
+	.hw_init = rtl92du_hw_init,
+	.hw_disable = rtl92du_card_disable,
+	.enable_interrupt = rtl92du_enable_interrupt,
+	.disable_interrupt = rtl92du_disable_interrupt,
+	.set_network_type = rtl92du_set_network_type,
+	.set_chk_bssid = rtl92du_set_check_bssid,
+	.set_qos = rtl92d_set_qos,
+	.set_bcn_reg = rtl92du_set_beacon_related_registers,
+	.set_bcn_intv = rtl92du_set_beacon_interval,
+	.update_interrupt_mask = rtl92du_update_interrupt_mask,
+	.get_hw_reg = rtl92du_get_hw_reg,
+	.set_hw_reg = rtl92du_set_hw_reg,
+	.update_rate_tbl = rtl92d_update_hal_rate_tbl,
+	.fill_tx_desc = rtl92du_tx_fill_desc,
+	.query_rx_desc = rtl92d_rx_query_desc,
+	.set_channel_access = rtl92d_update_channel_access_setting,
+	.radio_onoff_checking = rtl92d_gpio_radio_on_off_checking,
+	.set_bw_mode = rtl92du_phy_set_bw_mode,
+	.switch_channel = rtl92du_phy_sw_chnl,
+	.dm_watchdog = rtl92du_dm_watchdog,
+	.scan_operation_backup = rtl_phy_scan_operation_backup,
+	.set_rf_power_state = rtl92du_phy_set_rf_power_state,
+	.led_control = rtl92du_led_control,
+	.set_desc = rtl92d_set_desc,
+	.get_desc = rtl92d_get_desc,
+	.enable_hw_sec = rtl92d_enable_hw_security_config,
+	.set_key = rtl92d_set_key,
+	.get_bbreg = rtl92du_phy_query_bb_reg,
+	.set_bbreg = rtl92du_phy_set_bb_reg,
+	.get_rfreg = rtl92d_phy_query_rf_reg,
+	.set_rfreg = rtl92d_phy_set_rf_reg,
+	.linked_set_reg = rtl92du_linked_set_reg,
+	.fill_h2c_cmd = rtl92d_fill_h2c_cmd,
+	.get_btc_status = rtl_btc_status_false,
+	.phy_iq_calibrate = rtl92du_phy_iq_calibrate,
+	.phy_lc_calibrate = rtl92du_phy_lc_calibrate,
+};
+
+static struct rtl_mod_params rtl92du_mod_params = {
+	.sw_crypto = false,
+	.inactiveps = false,
+	.swctrl_lps = false,
+	.debug_level = 0,
+	.debug_mask = 0,
+};
+
+static const struct rtl_hal_usbint_cfg rtl92du_interface_cfg = {
+	/* rx */
+	.rx_urb_num = 8,
+	.rx_max_size = 15360,
+	.usb_rx_hdl = NULL,
+	.usb_rx_segregate_hdl = NULL,
+	/* tx */
+	.usb_tx_cleanup = rtl92du_tx_cleanup,
+	.usb_tx_post_hdl = rtl92du_tx_post_hdl,
+	.usb_tx_aggregate_hdl = rtl92du_tx_aggregate_hdl,
+	.usb_endpoint_mapping = rtl92du_endpoint_mapping,
+	.usb_mq_to_hwq = rtl92du_mq_to_hwq,
+};
+
+static const struct rtl_hal_cfg rtl92du_hal_cfg = {
+	.name = "rtl8192du",
+	.ops = &rtl8192du_hal_ops,
+	.mod_params = &rtl92du_mod_params,
+	.usb_interface_cfg = &rtl92du_interface_cfg,
+
+	.maps[SYS_ISO_CTRL] = REG_SYS_ISO_CTRL,
+	.maps[SYS_FUNC_EN] = REG_SYS_FUNC_EN,
+	.maps[SYS_CLK] = REG_SYS_CLKR,
+	.maps[MAC_RCR_AM] = RCR_AM,
+	.maps[MAC_RCR_AB] = RCR_AB,
+	.maps[MAC_RCR_ACRC32] = RCR_ACRC32,
+	.maps[MAC_RCR_ACF] = RCR_ACF,
+	.maps[MAC_RCR_AAP] = RCR_AAP,
+
+	.maps[EFUSE_TEST] = REG_EFUSE_TEST,
+	.maps[EFUSE_ACCESS] = REG_EFUSE_ACCESS,
+	.maps[EFUSE_CTRL] = REG_EFUSE_CTRL,
+	.maps[EFUSE_CLK] = 0,	/* just for 92se */
+	.maps[EFUSE_CLK_CTRL] = REG_EFUSE_CTRL,
+	.maps[EFUSE_PWC_EV12V] = PWC_EV12V,
+	.maps[EFUSE_FEN_ELDR] = FEN_ELDR,
+	.maps[EFUSE_LOADER_CLK_EN] = 0,
+	.maps[EFUSE_ANA8M] = 0,	/* just for 92se */
+	.maps[EFUSE_HWSET_MAX_SIZE] = HWSET_MAX_SIZE,
+	.maps[EFUSE_MAX_SECTION_MAP] = EFUSE_MAX_SECTION,
+	.maps[EFUSE_REAL_CONTENT_SIZE] = EFUSE_REAL_CONTENT_LEN,
+
+	.maps[RWCAM] = REG_CAMCMD,
+	.maps[WCAMI] = REG_CAMWRITE,
+	.maps[RCAMO] = REG_CAMREAD,
+	.maps[CAMDBG] = REG_CAMDBG,
+	.maps[SECR] = REG_SECCFG,
+	.maps[SEC_CAM_NONE] = CAM_NONE,
+	.maps[SEC_CAM_WEP40] = CAM_WEP40,
+	.maps[SEC_CAM_TKIP] = CAM_TKIP,
+	.maps[SEC_CAM_AES] = CAM_AES,
+	.maps[SEC_CAM_WEP104] = CAM_WEP104,
+
+	.maps[RTL_IMR_BCNDMAINT6] = IMR_BCNDMAINT6,
+	.maps[RTL_IMR_BCNDMAINT5] = IMR_BCNDMAINT5,
+	.maps[RTL_IMR_BCNDMAINT4] = IMR_BCNDMAINT4,
+	.maps[RTL_IMR_BCNDMAINT3] = IMR_BCNDMAINT3,
+	.maps[RTL_IMR_BCNDMAINT2] = IMR_BCNDMAINT2,
+	.maps[RTL_IMR_BCNDMAINT1] = IMR_BCNDMAINT1,
+	.maps[RTL_IMR_BCNDOK8] = IMR_BCNDOK8,
+	.maps[RTL_IMR_BCNDOK7] = IMR_BCNDOK7,
+	.maps[RTL_IMR_BCNDOK6] = IMR_BCNDOK6,
+	.maps[RTL_IMR_BCNDOK5] = IMR_BCNDOK5,
+	.maps[RTL_IMR_BCNDOK4] = IMR_BCNDOK4,
+	.maps[RTL_IMR_BCNDOK3] = IMR_BCNDOK3,
+	.maps[RTL_IMR_BCNDOK2] = IMR_BCNDOK2,
+	.maps[RTL_IMR_BCNDOK1] = IMR_BCNDOK1,
+	.maps[RTL_IMR_TIMEOUT2] = IMR_TIMEOUT2,
+	.maps[RTL_IMR_TIMEOUT1] = IMR_TIMEOUT1,
+
+	.maps[RTL_IMR_TXFOVW] = IMR_TXFOVW,
+	.maps[RTL_IMR_PSTIMEOUT] = IMR_PSTIMEOUT,
+	.maps[RTL_IMR_BCNINT] = IMR_BCNINT,
+	.maps[RTL_IMR_RXFOVW] = IMR_RXFOVW,
+	.maps[RTL_IMR_RDU] = IMR_RDU,
+	.maps[RTL_IMR_ATIMEND] = IMR_ATIMEND,
+	.maps[RTL_IMR_BDOK] = IMR_BDOK,
+	.maps[RTL_IMR_MGNTDOK] = IMR_MGNTDOK,
+	.maps[RTL_IMR_TBDER] = IMR_TBDER,
+	.maps[RTL_IMR_HIGHDOK] = IMR_HIGHDOK,
+	.maps[RTL_IMR_TBDOK] = IMR_TBDOK,
+	.maps[RTL_IMR_BKDOK] = IMR_BKDOK,
+	.maps[RTL_IMR_BEDOK] = IMR_BEDOK,
+	.maps[RTL_IMR_VIDOK] = IMR_VIDOK,
+	.maps[RTL_IMR_VODOK] = IMR_VODOK,
+	.maps[RTL_IMR_ROK] = IMR_ROK,
+	.maps[RTL_IBSS_INT_MASKS] = (IMR_BCNINT | IMR_TBDOK | IMR_TBDER),
+
+	.maps[RTL_RC_CCK_RATE1M] = DESC_RATE1M,
+	.maps[RTL_RC_CCK_RATE2M] = DESC_RATE2M,
+	.maps[RTL_RC_CCK_RATE5_5M] = DESC_RATE5_5M,
+	.maps[RTL_RC_CCK_RATE11M] = DESC_RATE11M,
+	.maps[RTL_RC_OFDM_RATE6M] = DESC_RATE6M,
+	.maps[RTL_RC_OFDM_RATE9M] = DESC_RATE9M,
+	.maps[RTL_RC_OFDM_RATE12M] = DESC_RATE12M,
+	.maps[RTL_RC_OFDM_RATE18M] = DESC_RATE18M,
+	.maps[RTL_RC_OFDM_RATE24M] = DESC_RATE24M,
+	.maps[RTL_RC_OFDM_RATE36M] = DESC_RATE36M,
+	.maps[RTL_RC_OFDM_RATE48M] = DESC_RATE48M,
+	.maps[RTL_RC_OFDM_RATE54M] = DESC_RATE54M,
+
+	.maps[RTL_RC_HT_RATEMCS7] = DESC_RATEMCS7,
+	.maps[RTL_RC_HT_RATEMCS15] = DESC_RATEMCS15,
+};
+
+module_param_named(swenc, rtl92du_mod_params.sw_crypto, bool, 0444);
+module_param_named(debug_level, rtl92du_mod_params.debug_level, int, 0644);
+module_param_named(ips, rtl92du_mod_params.inactiveps, bool, 0444);
+module_param_named(swlps, rtl92du_mod_params.swctrl_lps, bool, 0444);
+module_param_named(debug_mask, rtl92du_mod_params.debug_mask, ullong, 0644);
+MODULE_PARM_DESC(swenc, "Set to 1 for software crypto (default 0)\n");
+MODULE_PARM_DESC(ips, "Set to 0 to not use link power save (default 0)\n");
+MODULE_PARM_DESC(swlps, "Set to 1 to use SW control power save (default 0)\n");
+MODULE_PARM_DESC(debug_level, "Set debug level (0-5) (default 0)");
+MODULE_PARM_DESC(debug_mask, "Set debug mask (default 0)");
+
+#define USB_VENDOR_ID_REALTEK		0x0bda
+
+static const struct usb_device_id rtl8192d_usb_ids[] = {
+	{RTL_USB_DEVICE(USB_VENDOR_ID_REALTEK, 0x8193, rtl92du_hal_cfg)},
+	{RTL_USB_DEVICE(USB_VENDOR_ID_REALTEK, 0x8194, rtl92du_hal_cfg)},
+	{RTL_USB_DEVICE(USB_VENDOR_ID_REALTEK, 0x8111, rtl92du_hal_cfg)},
+	{RTL_USB_DEVICE(USB_VENDOR_ID_REALTEK, 0x0193, rtl92du_hal_cfg)},
+	{RTL_USB_DEVICE(USB_VENDOR_ID_REALTEK, 0x8171, rtl92du_hal_cfg)},
+	{RTL_USB_DEVICE(USB_VENDOR_ID_REALTEK, 0xe194, rtl92du_hal_cfg)},
+	{RTL_USB_DEVICE(0x2019, 0xab2c, rtl92du_hal_cfg)},
+	{RTL_USB_DEVICE(0x2019, 0xab2d, rtl92du_hal_cfg)},
+	{RTL_USB_DEVICE(0x2019, 0x4903, rtl92du_hal_cfg)},
+	{RTL_USB_DEVICE(0x2019, 0x4904, rtl92du_hal_cfg)},
+	{RTL_USB_DEVICE(0x07b8, 0x8193, rtl92du_hal_cfg)},
+	{RTL_USB_DEVICE(0x20f4, 0x664b, rtl92du_hal_cfg)},
+	{RTL_USB_DEVICE(0x04dd, 0x954f, rtl92du_hal_cfg)},
+	{RTL_USB_DEVICE(0x04dd, 0x96a6, rtl92du_hal_cfg)},
+	{RTL_USB_DEVICE(0x050d, 0x110a, rtl92du_hal_cfg)},
+	{RTL_USB_DEVICE(0x050d, 0x1105, rtl92du_hal_cfg)},
+	{RTL_USB_DEVICE(0x050d, 0x120a, rtl92du_hal_cfg)},
+	{RTL_USB_DEVICE(0x1668, 0x8102, rtl92du_hal_cfg)},
+	{RTL_USB_DEVICE(0x0930, 0x0a0a, rtl92du_hal_cfg)},
+	{RTL_USB_DEVICE(0x2001, 0x330c, rtl92du_hal_cfg)},
+	{}
+};
+
+MODULE_DEVICE_TABLE(usb, rtl8192d_usb_ids);
+
+static int rtl8192du_probe(struct usb_interface *intf,
+			   const struct usb_device_id *id)
+{
+	return rtl_usb_probe(intf, id, &rtl92du_hal_cfg);
+}
+
+static struct usb_driver rtl8192du_driver = {
+	.name = "rtl8192du",
+	.probe = rtl8192du_probe,
+	.disconnect = rtl_usb_disconnect,
+	.id_table = rtl8192d_usb_ids,
+	.disable_hub_initiated_lpm = 1,
+};
+
+module_usb_driver(rtl8192du_driver);
+
+MODULE_AUTHOR("Bitterblue Smith	<rtl8821cerfe2@gmail.com>");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Realtek 8192DU 802.11n Dual Mac USB wireless");
+MODULE_FIRMWARE("rtlwifi/rtl8192dufw.bin");
-- 
GitLab


From 59ea089dcba3b51769280522fd62696d4d436cbc Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Thu, 23 May 2024 17:49:00 +0300
Subject: [PATCH 551/950] wifi: rtlwifi: Enable the new rtl8192du driver

The RTL8192DU is an older Wifi 4 dual band chip. It comes in two
flavours: single MAC single PHY (like most Realtek Wifi 4 USB devices),
and dual MAC dual PHY.

The single MAC single PHY version is 2T2R and can work either in the
2.4 GHz band or the 5 GHz band.

The dual MAC dual PHY version has two USB interfaces and appears to the
system as two separate 1T1R Wifi devices, one working in the 2.4 GHz
band, the other in the 5 GHz band.

This was tested only with a single MAC single PHY device, mostly in
station mode. The speeds in the 2.4 GHz band with 20 MHz channel width
are similar to the out-of-tree driver: 85/51 megabits/second.

Stefan Lippers-Hollmann tested the speed in the 5 GHz band with 40 MHz
channel width: 173/99 megabits/second.

It was also tested briefly in AP mode. It's emitting beacons and my
phone can connect to it.

Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Tested-by: Stefan Lippers-Hollmann <s.l-h@gmx.de>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://msgid.link/5f2da7ee-876a-42fc-8fec-ec5386fa8c26@gmail.com
---
 drivers/net/wireless/realtek/rtlwifi/Kconfig        | 12 ++++++++++++
 drivers/net/wireless/realtek/rtlwifi/Makefile       |  1 +
 .../net/wireless/realtek/rtlwifi/rtl8192du/Makefile | 13 +++++++++++++
 3 files changed, 26 insertions(+)
 create mode 100644 drivers/net/wireless/realtek/rtlwifi/rtl8192du/Makefile

diff --git a/drivers/net/wireless/realtek/rtlwifi/Kconfig b/drivers/net/wireless/realtek/rtlwifi/Kconfig
index cfe63f7b28d9a..1e66c1bf7c8bb 100644
--- a/drivers/net/wireless/realtek/rtlwifi/Kconfig
+++ b/drivers/net/wireless/realtek/rtlwifi/Kconfig
@@ -119,6 +119,18 @@ config RTL8192CU
 
 	If you choose to build it as a module, it will be called rtl8192cu
 
+config RTL8192DU
+	tristate "Realtek RTL8192DU USB Wireless Network Adapter"
+	depends on USB
+	select RTLWIFI
+	select RTLWIFI_USB
+	select RTL8192D_COMMON
+	help
+	This is the driver for Realtek RTL8192DU 802.11n USB
+	wireless network adapters.
+
+	If you choose to build it as a module, it will be called rtl8192du
+
 config RTLWIFI
 	tristate
 	select FW_LOADER
diff --git a/drivers/net/wireless/realtek/rtlwifi/Makefile b/drivers/net/wireless/realtek/rtlwifi/Makefile
index 423981b148df2..9cf32277c7f1b 100644
--- a/drivers/net/wireless/realtek/rtlwifi/Makefile
+++ b/drivers/net/wireless/realtek/rtlwifi/Makefile
@@ -25,6 +25,7 @@ obj-$(CONFIG_RTL8192CU)		+= rtl8192cu/
 obj-$(CONFIG_RTL8192SE)		+= rtl8192se/
 obj-$(CONFIG_RTL8192D_COMMON)	+= rtl8192d/
 obj-$(CONFIG_RTL8192DE)		+= rtl8192de/
+obj-$(CONFIG_RTL8192DU)		+= rtl8192du/
 obj-$(CONFIG_RTL8723AE)		+= rtl8723ae/
 obj-$(CONFIG_RTL8723BE)		+= rtl8723be/
 obj-$(CONFIG_RTL8188EE)		+= rtl8188ee/
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192du/Makefile b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/Makefile
new file mode 100644
index 0000000000000..569bfd3d50308
--- /dev/null
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/Makefile
@@ -0,0 +1,13 @@
+# SPDX-License-Identifier: GPL-2.0
+rtl8192du-objs :=		\
+		dm.o		\
+		fw.o		\
+		hw.o		\
+		led.o		\
+		phy.o		\
+		rf.o		\
+		sw.o		\
+		table.o		\
+		trx.o
+
+obj-$(CONFIG_RTL8192DU) += rtl8192du.o
-- 
GitLab


From 9c4fde42cce05719120cf892a44b76ff61d908c7 Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Fri, 24 May 2024 08:32:48 +0800
Subject: [PATCH 552/950] wifi: rtlwifi: handle return value of usb init TX/RX

Handle error code to cause failed to USB probe result from unexpected
USB EP number, otherwise when USB disconnect skb_dequeue() an uninitialized
skb list and cause warnings below.

usb 2-1: USB disconnect, device number 76
INFO: trying to register non-static key.
The code is fine but needs lockdep annotation, or maybe
you didn't initialize this object before use?
turning off the locking correctness validator.
CPU: 0 PID: 54060 Comm: kworker/0:1 Not tainted 6.9.0-rc7 #1
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.2-0-gea1b7a073390-prebuilt.qemu.org 04/01/2014
Workqueue: usb_hub_wq hub_event
Call Trace:
 <TASK>
 __dump_stack lib/dump_stack.c:88 [inline]
 dump_stack_lvl+0x116/0x1b0 lib/dump_stack.c:114
 assign_lock_key kernel/locking/lockdep.c:976 [inline]
 register_lock_class+0xc18/0xfa0 kernel/locking/lockdep.c:1289
 __lock_acquire+0x108/0x3bc0 kernel/locking/lockdep.c:5014
 lock_acquire kernel/locking/lockdep.c:5754 [inline]
 lock_acquire+0x1b0/0x550 kernel/locking/lockdep.c:5719
 __raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:110 [inline]
 _raw_spin_lock_irqsave+0x3d/0x60 kernel/locking/spinlock.c:162
 skb_dequeue+0x20/0x180 net/core/skbuff.c:3846
 rtl_usb_cleanup drivers/net/wireless/realtek/rtlwifi/usb.c:706 [inline]
 rtl_usb_deinit drivers/net/wireless/realtek/rtlwifi/usb.c:721 [inline]
 rtl_usb_disconnect+0x4a4/0x850 drivers/net/wireless/realtek/rtlwifi/usb.c:1051
 usb_unbind_interface+0x1e8/0x980 drivers/usb/core/driver.c:461
 device_remove drivers/base/dd.c:568 [inline]
 device_remove+0x122/0x170 drivers/base/dd.c:560
 __device_release_driver drivers/base/dd.c:1270 [inline]
 device_release_driver_internal+0x443/0x620 drivers/base/dd.c:1293
 bus_remove_device+0x22f/0x420 drivers/base/bus.c:574
 device_del+0x395/0x9f0 drivers/base/core.c:3909
 usb_disable_device+0x360/0x7b0 drivers/usb/core/message.c:1418
 usb_disconnect+0x2db/0x930 drivers/usb/core/hub.c:2305
 hub_port_connect drivers/usb/core/hub.c:5362 [inline]
 hub_port_connect_change drivers/usb/core/hub.c:5662 [inline]
 port_event drivers/usb/core/hub.c:5822 [inline]
 hub_event+0x1e39/0x4ce0 drivers/usb/core/hub.c:5904
 process_one_work+0x97b/0x1a90 kernel/workqueue.c:3267
 process_scheduled_works kernel/workqueue.c:3348 [inline]
 worker_thread+0x680/0xf00 kernel/workqueue.c:3429
 kthread+0x2c7/0x3b0 kernel/kthread.c:388
 ret_from_fork+0x45/0x80 arch/x86/kernel/process.c:147
 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244
 </TASK>

Reported-by: Shichao Lai <shichaorai@gmail.com>
Closes: https://lore.kernel.org/linux-wireless/CAEk6kZuuezkH1dVRJf3EAVZK-83=OpTz62qCugkpTkswj8JF6w@mail.gmail.com/T/#u
Tested-by: Shichao Lai <shichaorai@gmail.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://msgid.link/20240524003248.5952-1-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtlwifi/usb.c | 34 +++++++++++++++++-----
 1 file changed, 26 insertions(+), 8 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtlwifi/usb.c b/drivers/net/wireless/realtek/rtlwifi/usb.c
index b6d300bec1e9d..d37a017b2b814 100644
--- a/drivers/net/wireless/realtek/rtlwifi/usb.c
+++ b/drivers/net/wireless/realtek/rtlwifi/usb.c
@@ -23,6 +23,8 @@ MODULE_DESCRIPTION("USB basic driver for rtlwifi");
 
 #define MAX_USBCTRL_VENDORREQ_TIMES		10
 
+static void _rtl_usb_cleanup_tx(struct ieee80211_hw *hw);
+
 static void _usbctrl_vendorreq_sync(struct usb_device *udev, u8 reqtype,
 				   u16 value, void *pdata, u16 len)
 {
@@ -285,9 +287,23 @@ static int _rtl_usb_init(struct ieee80211_hw *hw)
 	}
 	/* usb endpoint mapping */
 	err = rtlpriv->cfg->usb_interface_cfg->usb_endpoint_mapping(hw);
-	rtlusb->usb_mq_to_hwq =  rtlpriv->cfg->usb_interface_cfg->usb_mq_to_hwq;
-	_rtl_usb_init_tx(hw);
-	_rtl_usb_init_rx(hw);
+	if (err)
+		return err;
+
+	rtlusb->usb_mq_to_hwq = rtlpriv->cfg->usb_interface_cfg->usb_mq_to_hwq;
+
+	err = _rtl_usb_init_tx(hw);
+	if (err)
+		return err;
+
+	err = _rtl_usb_init_rx(hw);
+	if (err)
+		goto err_out;
+
+	return 0;
+
+err_out:
+	_rtl_usb_cleanup_tx(hw);
 	return err;
 }
 
@@ -691,17 +707,13 @@ static int rtl_usb_start(struct ieee80211_hw *hw)
 }
 
 /*=======================  tx =========================================*/
-static void rtl_usb_cleanup(struct ieee80211_hw *hw)
+static void _rtl_usb_cleanup_tx(struct ieee80211_hw *hw)
 {
 	u32 i;
 	struct sk_buff *_skb;
 	struct rtl_usb *rtlusb = rtl_usbdev(rtl_usbpriv(hw));
 	struct ieee80211_tx_info *txinfo;
 
-	/* clean up rx stuff. */
-	_rtl_usb_cleanup_rx(hw);
-
-	/* clean up tx stuff */
 	for (i = 0; i < RTL_USB_MAX_EP_NUM; i++) {
 		while ((_skb = skb_dequeue(&rtlusb->tx_skb_queue[i]))) {
 			rtlusb->usb_tx_cleanup(hw, _skb);
@@ -715,6 +727,12 @@ static void rtl_usb_cleanup(struct ieee80211_hw *hw)
 	usb_kill_anchored_urbs(&rtlusb->tx_submitted);
 }
 
+static void rtl_usb_cleanup(struct ieee80211_hw *hw)
+{
+	_rtl_usb_cleanup_rx(hw);
+	_rtl_usb_cleanup_tx(hw);
+}
+
 /* We may add some struct into struct rtl_usb later. Do deinit here.  */
 static void rtl_usb_deinit(struct ieee80211_hw *hw)
 {
-- 
GitLab


From b3dc6e8003b500861fa307e9a3400c52e78e4d3a Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Wed, 29 May 2024 17:56:33 +0800
Subject: [PATCH 553/950] ipvlan: Dont Use skb->sk in
 ipvlan_process_v{4,6}_outbound

Raw packet from PF_PACKET socket ontop of an IPv6-backed ipvlan device will
hit WARN_ON_ONCE() in sk_mc_loop() through sch_direct_xmit() path.

WARNING: CPU: 2 PID: 0 at net/core/sock.c:775 sk_mc_loop+0x2d/0x70
Modules linked in: sch_netem ipvlan rfkill cirrus drm_shmem_helper sg drm_kms_helper
CPU: 2 PID: 0 Comm: swapper/2 Kdump: loaded Not tainted 6.9.0+ #279
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014
RIP: 0010:sk_mc_loop+0x2d/0x70
Code: fa 0f 1f 44 00 00 65 0f b7 15 f7 96 a3 4f 31 c0 66 85 d2 75 26 48 85 ff 74 1c
RSP: 0018:ffffa9584015cd78 EFLAGS: 00010212
RAX: 0000000000000011 RBX: ffff91e585793e00 RCX: 0000000002c6a001
RDX: 0000000000000000 RSI: 0000000000000040 RDI: ffff91e589c0f000
RBP: ffff91e5855bd100 R08: 0000000000000000 R09: 3d00545216f43d00
R10: ffff91e584fdcc50 R11: 00000060dd8616f4 R12: ffff91e58132d000
R13: ffff91e584fdcc68 R14: ffff91e5869ce800 R15: ffff91e589c0f000
FS:  0000000000000000(0000) GS:ffff91e898100000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f788f7c44c0 CR3: 0000000008e1a000 CR4: 00000000000006f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
<IRQ>
 ? __warn (kernel/panic.c:693)
 ? sk_mc_loop (net/core/sock.c:760)
 ? report_bug (lib/bug.c:201 lib/bug.c:219)
 ? handle_bug (arch/x86/kernel/traps.c:239)
 ? exc_invalid_op (arch/x86/kernel/traps.c:260 (discriminator 1))
 ? asm_exc_invalid_op (./arch/x86/include/asm/idtentry.h:621)
 ? sk_mc_loop (net/core/sock.c:760)
 ip6_finish_output2 (net/ipv6/ip6_output.c:83 (discriminator 1))
 ? nf_hook_slow (net/netfilter/core.c:626)
 ip6_finish_output (net/ipv6/ip6_output.c:222)
 ? __pfx_ip6_finish_output (net/ipv6/ip6_output.c:215)
 ipvlan_xmit_mode_l3 (drivers/net/ipvlan/ipvlan_core.c:602) ipvlan
 ipvlan_start_xmit (drivers/net/ipvlan/ipvlan_main.c:226) ipvlan
 dev_hard_start_xmit (net/core/dev.c:3594)
 sch_direct_xmit (net/sched/sch_generic.c:343)
 __qdisc_run (net/sched/sch_generic.c:416)
 net_tx_action (net/core/dev.c:5286)
 handle_softirqs (kernel/softirq.c:555)
 __irq_exit_rcu (kernel/softirq.c:589)
 sysvec_apic_timer_interrupt (arch/x86/kernel/apic/apic.c:1043)

The warning triggers as this:
packet_sendmsg
   packet_snd //skb->sk is packet sk
      __dev_queue_xmit
         __dev_xmit_skb //q->enqueue is not NULL
             __qdisc_run
               sch_direct_xmit
                 dev_hard_start_xmit
                   ipvlan_start_xmit
                      ipvlan_xmit_mode_l3 //l3 mode
                        ipvlan_process_outbound //vepa flag
                          ipvlan_process_v6_outbound
                            ip6_local_out
                                __ip6_finish_output
                                  ip6_finish_output2 //multicast packet
                                    sk_mc_loop //sk->sk_family is AF_PACKET

Call ip{6}_local_out() with NULL sk in ipvlan as other tunnels to fix this.

Fixes: 2ad7bf363841 ("ipvlan: Initial check-in of the IPVLAN driver.")
Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20240529095633.613103-1-yuehaibing@huawei.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ipvlan/ipvlan_core.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c
index 2d5b021b4ea60..fef4eff7753a7 100644
--- a/drivers/net/ipvlan/ipvlan_core.c
+++ b/drivers/net/ipvlan/ipvlan_core.c
@@ -439,7 +439,7 @@ static noinline_for_stack int ipvlan_process_v4_outbound(struct sk_buff *skb)
 
 	memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
 
-	err = ip_local_out(net, skb->sk, skb);
+	err = ip_local_out(net, NULL, skb);
 	if (unlikely(net_xmit_eval(err)))
 		DEV_STATS_INC(dev, tx_errors);
 	else
@@ -494,7 +494,7 @@ static int ipvlan_process_v6_outbound(struct sk_buff *skb)
 
 	memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
 
-	err = ip6_local_out(dev_net(dev), skb->sk, skb);
+	err = ip6_local_out(dev_net(dev), NULL, skb);
 	if (unlikely(net_xmit_eval(err)))
 		DEV_STATS_INC(dev, tx_errors);
 	else
-- 
GitLab


From 700fe6fd093d08c6da2bda8efe00479b0e617327 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Thu, 30 May 2024 12:10:43 +0200
Subject: [PATCH 554/950] ALSA: seq: Fix yet another spot for system message
 conversion

We fixed the incorrect UMP type for system messages in the recent
commit, but it missed one place in system_ev_to_ump_midi1().
Fix it now.

Fixes: e9e02819a98a ("ALSA: seq: Automatic conversion of UMP events")
Fixes: c2bb79613fed ("ALSA: seq: Fix incorrect UMP type for system messages")
Link: https://lore.kernel.org/r/20240530101044.17524-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/core/seq/seq_ump_convert.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/core/seq/seq_ump_convert.c b/sound/core/seq/seq_ump_convert.c
index add70b4c2885d..f0f332017e662 100644
--- a/sound/core/seq/seq_ump_convert.c
+++ b/sound/core/seq/seq_ump_convert.c
@@ -729,6 +729,7 @@ static int system_ev_to_ump_midi1(const struct snd_seq_event *event,
 				  union snd_ump_midi1_msg *data,
 				  unsigned char status)
 {
+	data->system.type = UMP_MSG_TYPE_SYSTEM; // override
 	data->system.status = status;
 	return 1;
 }
-- 
GitLab


From 13c7c941e72908b8cce5a84b45a7b5e485ca12ed Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 29 May 2024 09:35:47 -0700
Subject: [PATCH 555/950] netdev: add qstat for csum complete

Recent commit 0cfe71f45f42 ("netdev: add queue stats") added
a lot of useful stats, but only those immediately needed by virtio.
Presumably virtio does not support CHECKSUM_COMPLETE,
so statistic for that form of checksumming wasn't included.
Other drivers will definitely need it, in fact we expect it
to be needed in net-next soon (mlx5). So let's add the definition
of the counter for CHECKSUM_COMPLETE to uAPI in net already,
so that the counters are in a more natural order (all subsequent
counters have not been present in any released kernel, yet).

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Joe Damato <jdamato@fastly.com>
Fixes: 0cfe71f45f42 ("netdev: add queue stats")
Link: https://lore.kernel.org/r/20240529163547.3693194-1-kuba@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 Documentation/netlink/specs/netdev.yaml | 4 ++++
 include/uapi/linux/netdev.h             | 1 +
 tools/include/uapi/linux/netdev.h       | 1 +
 3 files changed, 6 insertions(+)

diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml
index 11a32373365ab..959755be4d7f9 100644
--- a/Documentation/netlink/specs/netdev.yaml
+++ b/Documentation/netlink/specs/netdev.yaml
@@ -349,6 +349,10 @@ attribute-sets:
           Number of packets dropped due to transient lack of resources, such as
           buffer space, host descriptors etc.
         type: uint
+      -
+        name: rx-csum-complete
+        doc: Number of packets that were marked as CHECKSUM_COMPLETE.
+        type: uint
       -
         name: rx-csum-unnecessary
         doc: Number of packets that were marked as CHECKSUM_UNNECESSARY.
diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
index a8188202413ec..43742ac5b00da 100644
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -148,6 +148,7 @@ enum {
 	NETDEV_A_QSTATS_RX_ALLOC_FAIL,
 	NETDEV_A_QSTATS_RX_HW_DROPS,
 	NETDEV_A_QSTATS_RX_HW_DROP_OVERRUNS,
+	NETDEV_A_QSTATS_RX_CSUM_COMPLETE,
 	NETDEV_A_QSTATS_RX_CSUM_UNNECESSARY,
 	NETDEV_A_QSTATS_RX_CSUM_NONE,
 	NETDEV_A_QSTATS_RX_CSUM_BAD,
diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h
index a8188202413ec..43742ac5b00da 100644
--- a/tools/include/uapi/linux/netdev.h
+++ b/tools/include/uapi/linux/netdev.h
@@ -148,6 +148,7 @@ enum {
 	NETDEV_A_QSTATS_RX_ALLOC_FAIL,
 	NETDEV_A_QSTATS_RX_HW_DROPS,
 	NETDEV_A_QSTATS_RX_HW_DROP_OVERRUNS,
+	NETDEV_A_QSTATS_RX_CSUM_COMPLETE,
 	NETDEV_A_QSTATS_RX_CSUM_UNNECESSARY,
 	NETDEV_A_QSTATS_RX_CSUM_NONE,
 	NETDEV_A_QSTATS_RX_CSUM_BAD,
-- 
GitLab


From 49cb894d567980235b6e64d5e69950ff77debd8c Mon Sep 17 00:00:00 2001
From: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Date: Thu, 30 May 2024 14:19:14 +0300
Subject: [PATCH 556/950] ASoC: SOF: ipc4-topology: Add support for NHLT with
 16-bit only DMIC blob

The ACPI NHLT table always had 32-bit DMIC blob even if 16-bit was also
present and taken as a 'rule' which obviously got broken and there is at
least one device on the market which ships with only 16-bit DMIC
configuration blob.
This corner case has never been supported and it is going to need topology
updates for DMIC copier to support multiple formats.

As for the kernel side: if the copier supports multiple formats and the
preferred 32-bit DMIC blob is not found then we will try to get a 16-bit
DMIC configuration and look for a 16-bit copier config.

Fixes: f9209644ae76 ("ASoC: SOF: ipc4-topology: Correct DAI copier config and NHLT blob request")
Link: https://github.com/thesofproject/linux/issues/4973
Signed-off-by: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Reviewed-by: Seppo Ingalsuo <seppo.ingalsuo@linux.intel.com>
Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Link: https://msgid.link/r/20240530111918.21974-2-peter.ujfalusi@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sof/ipc4-topology.c | 25 ++++++++++++++++++++++---
 1 file changed, 22 insertions(+), 3 deletions(-)

diff --git a/sound/soc/sof/ipc4-topology.c b/sound/soc/sof/ipc4-topology.c
index beff109893247..521b4dcba6012 100644
--- a/sound/soc/sof/ipc4-topology.c
+++ b/sound/soc/sof/ipc4-topology.c
@@ -1483,6 +1483,8 @@ snd_sof_get_nhlt_endpoint_data(struct snd_sof_dev *sdev, struct snd_sof_dai *dai
 					   dir, dev_type);
 
 	if (!cfg) {
+		bool get_new_blob = false;
+
 		if (format_change) {
 			/*
 			 * The 32-bit blob was not found in NHLT table, try to
@@ -1490,7 +1492,20 @@ snd_sof_get_nhlt_endpoint_data(struct snd_sof_dev *sdev, struct snd_sof_dai *dai
 			 */
 			bit_depth = params_width(params);
 			format_change = false;
+			get_new_blob = true;
+		} else if (linktype == SOF_DAI_INTEL_DMIC && !single_format) {
+			/*
+			 * The requested 32-bit blob (no format change for the
+			 * blob request) was not found in NHLT table, try to
+			 * look for 16-bit blob if the copier supports multiple
+			 * formats
+			 */
+			bit_depth = 16;
+			format_change = true;
+			get_new_blob = true;
+		}
 
+		if (get_new_blob) {
 			cfg = intel_nhlt_get_endpoint_blob(sdev->dev, ipc4_data->nhlt,
 							   dai_index, nhlt_type,
 							   bit_depth, bit_depth,
@@ -1513,8 +1528,8 @@ out:
 
 	if (format_change) {
 		/*
-		 * Update the params to reflect that we have loaded 32-bit blob
-		 * instead of the 16-bit.
+		 * Update the params to reflect that different blob was loaded
+		 * instead of the requested bit depth (16 -> 32 or 32 -> 16).
 		 * This information is going to be used by the caller to find
 		 * matching copier format on the dai side.
 		 */
@@ -1522,7 +1537,11 @@ out:
 
 		m = hw_param_mask(params, SNDRV_PCM_HW_PARAM_FORMAT);
 		snd_mask_none(m);
-		snd_mask_set_format(m, SNDRV_PCM_FORMAT_S32_LE);
+		if (bit_depth == 16)
+			snd_mask_set_format(m, SNDRV_PCM_FORMAT_S16_LE);
+		else
+			snd_mask_set_format(m, SNDRV_PCM_FORMAT_S32_LE);
+
 	}
 
 	return 0;
-- 
GitLab


From 2a865c9c3fb0289a95f1cb51b42d248736ff45cb Mon Sep 17 00:00:00 2001
From: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Date: Thu, 30 May 2024 14:19:15 +0300
Subject: [PATCH 557/950] ASoC: SOF: ipc4-topology: Print out the channel count
 in sof_ipc4_dbg_audio_format

Print out the number of channels for the format explicitly instead of
having the reader to understand how to interpret the ch_map and ch_cfg
values.

Signed-off-by: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Reviewed-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://msgid.link/r/20240530111918.21974-3-peter.ujfalusi@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sof/ipc4-topology.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/sound/soc/sof/ipc4-topology.c b/sound/soc/sof/ipc4-topology.c
index 521b4dcba6012..2e0234b865ad4 100644
--- a/sound/soc/sof/ipc4-topology.c
+++ b/sound/soc/sof/ipc4-topology.c
@@ -195,9 +195,10 @@ static void sof_ipc4_dbg_audio_format(struct device *dev, struct sof_ipc4_pin_fo
 	for (i = 0; i < num_formats; i++) {
 		struct sof_ipc4_audio_format *fmt = &pin_fmt[i].audio_fmt;
 		dev_dbg(dev,
-			"Pin index #%d: %uHz, %ubit (ch_map %#x ch_cfg %u interleaving_style %u fmt_cfg %#x) buffer size %d\n",
-			pin_fmt[i].pin_index, fmt->sampling_frequency, fmt->bit_depth, fmt->ch_map,
-			fmt->ch_cfg, fmt->interleaving_style, fmt->fmt_cfg,
+			"Pin index #%d: %uHz, %ubit, %luch (ch_map %#x ch_cfg %u interleaving_style %u fmt_cfg %#x) buffer size %d\n",
+			pin_fmt[i].pin_index, fmt->sampling_frequency, fmt->bit_depth,
+			SOF_IPC4_AUDIO_FORMAT_CFG_CHANNELS_COUNT(fmt->fmt_cfg),
+			fmt->ch_map, fmt->ch_cfg, fmt->interleaving_style, fmt->fmt_cfg,
 			pin_fmt[i].buffer_size);
 	}
 }
-- 
GitLab


From 3b64fd2f83f203f5a34faed3dadf6464313f827d Mon Sep 17 00:00:00 2001
From: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Date: Thu, 30 May 2024 14:19:16 +0300
Subject: [PATCH 558/950] ASoC: SOF: ipc4-topology/pcm: Rename
 sof_ipc4_copier_is_single_format()

Rename the sof_ipc4_copier_is_single_format() to
sof_ipc4_copier_is_single_bitdepth() to clear the confusion of the use of
'format' when we are querying information on the bit depth.
Format is used to describe a combination of parameters (rate, channels,
sample format / bit depth).
Rename the flags used to store the result at the same time.

Signed-off-by: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Reviewed-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Reviewed-by: Seppo Ingalsuo <seppo.ingalsuo@linux.intel.com>
Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Link: https://msgid.link/r/20240530111918.21974-4-peter.ujfalusi@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sof/ipc4-pcm.c      | 12 +++++------
 sound/soc/sof/ipc4-topology.c | 40 +++++++++++++++++------------------
 sound/soc/sof/ipc4-topology.h |  6 +++---
 3 files changed, 29 insertions(+), 29 deletions(-)

diff --git a/sound/soc/sof/ipc4-pcm.c b/sound/soc/sof/ipc4-pcm.c
index 307bee63756b5..4df2be3d39eba 100644
--- a/sound/soc/sof/ipc4-pcm.c
+++ b/sound/soc/sof/ipc4-pcm.c
@@ -650,7 +650,7 @@ static int sof_ipc4_pcm_dai_link_fixup(struct snd_soc_pcm_runtime *rtd,
 	struct snd_soc_dai *cpu_dai = snd_soc_rtd_to_cpu(rtd, 0);
 	struct sof_ipc4_audio_format *ipc4_fmt;
 	struct sof_ipc4_copier *ipc4_copier;
-	bool single_fmt = false;
+	bool single_bitdepth = false;
 	u32 valid_bits = 0;
 	int dir, ret;
 
@@ -682,18 +682,18 @@ static int sof_ipc4_pcm_dai_link_fixup(struct snd_soc_pcm_runtime *rtd,
 				return 0;
 
 			if (dir == SNDRV_PCM_STREAM_PLAYBACK) {
-				if (sof_ipc4_copier_is_single_format(sdev,
+				if (sof_ipc4_copier_is_single_bitdepth(sdev,
 					available_fmt->output_pin_fmts,
 					available_fmt->num_output_formats)) {
 					ipc4_fmt = &available_fmt->output_pin_fmts->audio_fmt;
-					single_fmt = true;
+					single_bitdepth = true;
 				}
 			} else {
-				if (sof_ipc4_copier_is_single_format(sdev,
+				if (sof_ipc4_copier_is_single_bitdepth(sdev,
 					available_fmt->input_pin_fmts,
 					available_fmt->num_input_formats)) {
 					ipc4_fmt = &available_fmt->input_pin_fmts->audio_fmt;
-					single_fmt = true;
+					single_bitdepth = true;
 				}
 			}
 		}
@@ -703,7 +703,7 @@ static int sof_ipc4_pcm_dai_link_fixup(struct snd_soc_pcm_runtime *rtd,
 	if (ret)
 		return ret;
 
-	if (single_fmt) {
+	if (single_bitdepth) {
 		snd_mask_none(fmt);
 		valid_bits = SOF_IPC4_AUDIO_FORMAT_CFG_V_BIT_DEPTH(ipc4_fmt->fmt_cfg);
 		dev_dbg(component->dev, "Set %s to %d bit format\n", dai->name, valid_bits);
diff --git a/sound/soc/sof/ipc4-topology.c b/sound/soc/sof/ipc4-topology.c
index 2e0234b865ad4..afb7908766a38 100644
--- a/sound/soc/sof/ipc4-topology.c
+++ b/sound/soc/sof/ipc4-topology.c
@@ -1423,7 +1423,7 @@ static int snd_sof_get_hw_config_params(struct snd_sof_dev *sdev, struct snd_sof
 
 static int
 snd_sof_get_nhlt_endpoint_data(struct snd_sof_dev *sdev, struct snd_sof_dai *dai,
-			       bool single_format,
+			       bool single_bitdepth,
 			       struct snd_pcm_hw_params *params, u32 dai_index,
 			       u32 linktype, u8 dir, u32 **dst, u32 *len)
 {
@@ -1446,7 +1446,7 @@ snd_sof_get_nhlt_endpoint_data(struct snd_sof_dev *sdev, struct snd_sof_dai *dai
 		 * Look for 32-bit blob first instead of 16-bit if copier
 		 * supports multiple formats
 		 */
-		if (bit_depth == 16 && !single_format) {
+		if (bit_depth == 16 && !single_bitdepth) {
 			dev_dbg(sdev->dev, "Looking for 32-bit blob first for DMIC\n");
 			format_change = true;
 			bit_depth = 32;
@@ -1494,7 +1494,7 @@ snd_sof_get_nhlt_endpoint_data(struct snd_sof_dev *sdev, struct snd_sof_dai *dai
 			bit_depth = params_width(params);
 			format_change = false;
 			get_new_blob = true;
-		} else if (linktype == SOF_DAI_INTEL_DMIC && !single_format) {
+		} else if (linktype == SOF_DAI_INTEL_DMIC && !single_bitdepth) {
 			/*
 			 * The requested 32-bit blob (no format change for the
 			 * blob request) was not found in NHLT table, try to
@@ -1550,7 +1550,7 @@ out:
 #else
 static int
 snd_sof_get_nhlt_endpoint_data(struct snd_sof_dev *sdev, struct snd_sof_dai *dai,
-			       bool single_format,
+			       bool single_bitdepth,
 			       struct snd_pcm_hw_params *params, u32 dai_index,
 			       u32 linktype, u8 dir, u32 **dst, u32 *len)
 {
@@ -1558,9 +1558,9 @@ snd_sof_get_nhlt_endpoint_data(struct snd_sof_dev *sdev, struct snd_sof_dai *dai
 }
 #endif
 
-bool sof_ipc4_copier_is_single_format(struct snd_sof_dev *sdev,
-				      struct sof_ipc4_pin_format *pin_fmts,
-				      u32 pin_fmts_size)
+bool sof_ipc4_copier_is_single_bitdepth(struct snd_sof_dev *sdev,
+					struct sof_ipc4_pin_format *pin_fmts,
+					u32 pin_fmts_size)
 {
 	struct sof_ipc4_audio_format *fmt;
 	u32 valid_bits;
@@ -1591,7 +1591,7 @@ sof_ipc4_prepare_dai_copier(struct snd_sof_dev *sdev, struct snd_sof_dai *dai,
 	struct snd_pcm_hw_params dai_params = *params;
 	struct sof_ipc4_copier_data *copier_data;
 	struct sof_ipc4_copier *ipc4_copier;
-	bool single_format;
+	bool single_bitdepth;
 	int ret;
 
 	ipc4_copier = dai->private;
@@ -1605,12 +1605,12 @@ sof_ipc4_prepare_dai_copier(struct snd_sof_dev *sdev, struct snd_sof_dai *dai,
 	 * format lookup
 	 */
 	if (dir == SNDRV_PCM_STREAM_PLAYBACK) {
-		single_format = sof_ipc4_copier_is_single_format(sdev,
+		single_bitdepth = sof_ipc4_copier_is_single_bitdepth(sdev,
 						available_fmt->output_pin_fmts,
 						available_fmt->num_output_formats);
 
 		/* Update the dai_params with the only supported format */
-		if (single_format) {
+		if (single_bitdepth) {
 			ret = sof_ipc4_update_hw_params(sdev, &dai_params,
 					&available_fmt->output_pin_fmts[0].audio_fmt,
 					BIT(SNDRV_PCM_HW_PARAM_FORMAT));
@@ -1618,12 +1618,12 @@ sof_ipc4_prepare_dai_copier(struct snd_sof_dev *sdev, struct snd_sof_dai *dai,
 				return ret;
 		}
 	} else {
-		single_format = sof_ipc4_copier_is_single_format(sdev,
+		single_bitdepth = sof_ipc4_copier_is_single_bitdepth(sdev,
 						available_fmt->input_pin_fmts,
 						available_fmt->num_input_formats);
 
 		/* Update the dai_params with the only supported format */
-		if (single_format) {
+		if (single_bitdepth) {
 			ret = sof_ipc4_update_hw_params(sdev, &dai_params,
 					&available_fmt->input_pin_fmts[0].audio_fmt,
 					BIT(SNDRV_PCM_HW_PARAM_FORMAT));
@@ -1632,7 +1632,7 @@ sof_ipc4_prepare_dai_copier(struct snd_sof_dev *sdev, struct snd_sof_dai *dai,
 		}
 	}
 
-	ret = snd_sof_get_nhlt_endpoint_data(sdev, dai, single_format,
+	ret = snd_sof_get_nhlt_endpoint_data(sdev, dai, single_bitdepth,
 					     &dai_params,
 					     ipc4_copier->dai_index,
 					     ipc4_copier->dai_type, dir,
@@ -1667,7 +1667,7 @@ sof_ipc4_prepare_copier_module(struct snd_sof_widget *swidget,
 	u32 out_ref_rate, out_ref_channels;
 	u32 deep_buffer_dma_ms = 0;
 	int output_fmt_index;
-	bool single_output_format;
+	bool single_output_bitdepth;
 	int i;
 
 	dev_dbg(sdev->dev, "copier %s, type %d", swidget->widget->name, swidget->id);
@@ -1804,9 +1804,9 @@ sof_ipc4_prepare_copier_module(struct snd_sof_widget *swidget,
 		return ret;
 
 	/* set the reference params for output format selection */
-	single_output_format = sof_ipc4_copier_is_single_format(sdev,
-								available_fmt->output_pin_fmts,
-								available_fmt->num_output_formats);
+	single_output_bitdepth = sof_ipc4_copier_is_single_bitdepth(sdev,
+					available_fmt->output_pin_fmts,
+					available_fmt->num_output_formats);
 	switch (swidget->id) {
 	case snd_soc_dapm_aif_in:
 	case snd_soc_dapm_dai_out:
@@ -1818,7 +1818,7 @@ sof_ipc4_prepare_copier_module(struct snd_sof_widget *swidget,
 		out_ref_rate = in_fmt->sampling_frequency;
 		out_ref_channels = SOF_IPC4_AUDIO_FORMAT_CFG_CHANNELS_COUNT(in_fmt->fmt_cfg);
 
-		if (!single_output_format)
+		if (!single_output_bitdepth)
 			out_ref_valid_bits =
 				SOF_IPC4_AUDIO_FORMAT_CFG_V_BIT_DEPTH(in_fmt->fmt_cfg);
 		break;
@@ -1827,7 +1827,7 @@ sof_ipc4_prepare_copier_module(struct snd_sof_widget *swidget,
 	case snd_soc_dapm_dai_in:
 		out_ref_rate = params_rate(fe_params);
 		out_ref_channels = params_channels(fe_params);
-		if (!single_output_format) {
+		if (!single_output_bitdepth) {
 			out_ref_valid_bits = sof_ipc4_get_valid_bits(sdev, fe_params);
 			if (out_ref_valid_bits < 0)
 				return out_ref_valid_bits;
@@ -1845,7 +1845,7 @@ sof_ipc4_prepare_copier_module(struct snd_sof_widget *swidget,
 	 * if the output format is the same across all available output formats, choose
 	 * that as the reference.
 	 */
-	if (single_output_format) {
+	if (single_output_bitdepth) {
 		struct sof_ipc4_audio_format *out_fmt;
 
 		out_fmt = &available_fmt->output_pin_fmts[0].audio_fmt;
diff --git a/sound/soc/sof/ipc4-topology.h b/sound/soc/sof/ipc4-topology.h
index 4488762f6a71b..f4dc499c0ffe5 100644
--- a/sound/soc/sof/ipc4-topology.h
+++ b/sound/soc/sof/ipc4-topology.h
@@ -476,7 +476,7 @@ struct sof_ipc4_process {
 	u32 init_config;
 };
 
-bool sof_ipc4_copier_is_single_format(struct snd_sof_dev *sdev,
-				      struct sof_ipc4_pin_format *pin_fmts,
-				      u32 pin_fmts_size);
+bool sof_ipc4_copier_is_single_bitdepth(struct snd_sof_dev *sdev,
+					struct sof_ipc4_pin_format *pin_fmts,
+					u32 pin_fmts_size);
 #endif
-- 
GitLab


From 2fcad03eaba1b86e6b829f73a9e75e681b7f3106 Mon Sep 17 00:00:00 2001
From: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Date: Thu, 30 May 2024 14:19:17 +0300
Subject: [PATCH 559/950] ASoC: SOF: ipc4-topology: Improve readability of
 sof_ipc4_prepare_dai_copier()

Remove the duplicated code paths to check for single bit depth and to
update the params with storing the parameters needed by the function and
have a single code section.

No functional change but the code is easier to follow.

Signed-off-by: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Reviewed-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Reviewed-by: Seppo Ingalsuo <seppo.ingalsuo@linux.intel.com>
Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Link: https://msgid.link/r/20240530111918.21974-5-peter.ujfalusi@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sof/ipc4-topology.c | 42 +++++++++++++++--------------------
 1 file changed, 18 insertions(+), 24 deletions(-)

diff --git a/sound/soc/sof/ipc4-topology.c b/sound/soc/sof/ipc4-topology.c
index afb7908766a38..645252789cfe5 100644
--- a/sound/soc/sof/ipc4-topology.c
+++ b/sound/soc/sof/ipc4-topology.c
@@ -1590,8 +1590,10 @@ sof_ipc4_prepare_dai_copier(struct snd_sof_dev *sdev, struct snd_sof_dai *dai,
 	struct sof_ipc4_available_audio_format *available_fmt;
 	struct snd_pcm_hw_params dai_params = *params;
 	struct sof_ipc4_copier_data *copier_data;
+	struct sof_ipc4_pin_format *pin_fmts;
 	struct sof_ipc4_copier *ipc4_copier;
 	bool single_bitdepth;
+	u32 num_pin_fmts;
 	int ret;
 
 	ipc4_copier = dai->private;
@@ -1605,31 +1607,23 @@ sof_ipc4_prepare_dai_copier(struct snd_sof_dev *sdev, struct snd_sof_dai *dai,
 	 * format lookup
 	 */
 	if (dir == SNDRV_PCM_STREAM_PLAYBACK) {
-		single_bitdepth = sof_ipc4_copier_is_single_bitdepth(sdev,
-						available_fmt->output_pin_fmts,
-						available_fmt->num_output_formats);
-
-		/* Update the dai_params with the only supported format */
-		if (single_bitdepth) {
-			ret = sof_ipc4_update_hw_params(sdev, &dai_params,
-					&available_fmt->output_pin_fmts[0].audio_fmt,
-					BIT(SNDRV_PCM_HW_PARAM_FORMAT));
-			if (ret)
-				return ret;
-		}
+		pin_fmts = available_fmt->output_pin_fmts;
+		num_pin_fmts = available_fmt->num_output_formats;
 	} else {
-		single_bitdepth = sof_ipc4_copier_is_single_bitdepth(sdev,
-						available_fmt->input_pin_fmts,
-						available_fmt->num_input_formats);
-
-		/* Update the dai_params with the only supported format */
-		if (single_bitdepth) {
-			ret = sof_ipc4_update_hw_params(sdev, &dai_params,
-					&available_fmt->input_pin_fmts[0].audio_fmt,
-					BIT(SNDRV_PCM_HW_PARAM_FORMAT));
-			if (ret)
-				return ret;
-		}
+		pin_fmts = available_fmt->input_pin_fmts;
+		num_pin_fmts = available_fmt->num_input_formats;
+	}
+
+	single_bitdepth = sof_ipc4_copier_is_single_bitdepth(sdev, pin_fmts,
+							     num_pin_fmts);
+
+	/* Update the dai_params with the only supported format */
+	if (single_bitdepth) {
+		ret = sof_ipc4_update_hw_params(sdev, &dai_params,
+						&pin_fmts[0].audio_fmt,
+						BIT(SNDRV_PCM_HW_PARAM_FORMAT));
+		if (ret)
+			return ret;
 	}
 
 	ret = snd_sof_get_nhlt_endpoint_data(sdev, dai, single_bitdepth,
-- 
GitLab


From b65456b7b379e20ab225a4e906dc4a0c98fddd7a Mon Sep 17 00:00:00 2001
From: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Date: Thu, 30 May 2024 14:19:18 +0300
Subject: [PATCH 560/950] ASoC: SOF: ipc4-topology: Adjust the params based on
 DAI formats

Currently we only check the bit depth value among to DAI formats, but other
parameters might be constant, like number of channels and/or rate.

In capture we use the fe params as a reference to find the format and blob
which should be used, but in the path we can have components which can
handle expanding/narrowing number of channels or do a resample.

In these cases the topology is expected to have 'fixed' parameter for
channels/rates/bit depth and the conversion to the fe format is going to
be done within the path.

In practice this patch fixes issues like:
All DMIC formats are fixed four channels
We have a component which converts the four channel to stereo
FE is opened with 2 channel

Even if we have the correct bit depth format and blob (for four channel) we
will still be looking for stereo configurations, which will fail.

Note: the adjustment of params have switched order with the checking of
single bit depth (needed for the NHLT blob fallback support). This change
is non function, just that if the sof_ipc4_narrow_params_to_format() would
fail, there is no point of checking the single bit depth.

Signed-off-by: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Reviewed-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Reviewed-by: Seppo Ingalsuo <seppo.ingalsuo@linux.intel.com>
Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Link: https://msgid.link/r/20240530111918.21974-6-peter.ujfalusi@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sof/ipc4-topology.c | 71 ++++++++++++++++++++++++++++-------
 1 file changed, 57 insertions(+), 14 deletions(-)

diff --git a/sound/soc/sof/ipc4-topology.c b/sound/soc/sof/ipc4-topology.c
index 645252789cfe5..1bea4bab958b8 100644
--- a/sound/soc/sof/ipc4-topology.c
+++ b/sound/soc/sof/ipc4-topology.c
@@ -1583,6 +1583,55 @@ bool sof_ipc4_copier_is_single_bitdepth(struct snd_sof_dev *sdev,
 	return true;
 }
 
+static int
+sof_ipc4_adjust_params_to_dai_format(struct snd_sof_dev *sdev,
+				     struct snd_pcm_hw_params *params,
+				     struct sof_ipc4_pin_format *pin_fmts,
+				     u32 pin_fmts_size)
+{
+	u32 params_mask = BIT(SNDRV_PCM_HW_PARAM_RATE) |
+			  BIT(SNDRV_PCM_HW_PARAM_CHANNELS) |
+			  BIT(SNDRV_PCM_HW_PARAM_FORMAT);
+	struct sof_ipc4_audio_format *fmt;
+	u32 rate, channels, valid_bits;
+	int i;
+
+	fmt = &pin_fmts[0].audio_fmt;
+	rate = fmt->sampling_frequency;
+	channels = SOF_IPC4_AUDIO_FORMAT_CFG_CHANNELS_COUNT(fmt->fmt_cfg);
+	valid_bits = SOF_IPC4_AUDIO_FORMAT_CFG_V_BIT_DEPTH(fmt->fmt_cfg);
+
+	/* check if parameters in topology defined formats are the same */
+	for (i = 1; i < pin_fmts_size; i++) {
+		u32 val;
+
+		fmt = &pin_fmts[i].audio_fmt;
+
+		if (params_mask & BIT(SNDRV_PCM_HW_PARAM_RATE)) {
+			val = fmt->sampling_frequency;
+			if (val != rate)
+				params_mask &= ~BIT(SNDRV_PCM_HW_PARAM_RATE);
+		}
+		if (params_mask & BIT(SNDRV_PCM_HW_PARAM_CHANNELS)) {
+			val = SOF_IPC4_AUDIO_FORMAT_CFG_CHANNELS_COUNT(fmt->fmt_cfg);
+			if (val != channels)
+				params_mask &= ~BIT(SNDRV_PCM_HW_PARAM_CHANNELS);
+		}
+		if (params_mask & BIT(SNDRV_PCM_HW_PARAM_FORMAT)) {
+			val = SOF_IPC4_AUDIO_FORMAT_CFG_V_BIT_DEPTH(fmt->fmt_cfg);
+			if (val != valid_bits)
+				params_mask &= ~BIT(SNDRV_PCM_HW_PARAM_FORMAT);
+		}
+	}
+
+	if (params_mask)
+		return sof_ipc4_update_hw_params(sdev, params,
+						 &pin_fmts[0].audio_fmt,
+						 params_mask);
+
+	return 0;
+}
+
 static int
 sof_ipc4_prepare_dai_copier(struct snd_sof_dev *sdev, struct snd_sof_dai *dai,
 			    struct snd_pcm_hw_params *params, int dir)
@@ -1601,10 +1650,9 @@ sof_ipc4_prepare_dai_copier(struct snd_sof_dev *sdev, struct snd_sof_dai *dai,
 	available_fmt = &ipc4_copier->available_fmt;
 
 	/*
-	 * If the copier on the DAI side supports only single bit depth then
-	 * this depth (format) should be used to look for the NHLT blob (if
-	 * needed) and in case of capture this should be used for the input
-	 * format lookup
+	 * Fixup the params based on the format parameters of the DAI. If any
+	 * of the RATE, CHANNELS, bit depth is static among the formats then
+	 * narrow the params to only allow that specific parameter value.
 	 */
 	if (dir == SNDRV_PCM_STREAM_PLAYBACK) {
 		pin_fmts = available_fmt->output_pin_fmts;
@@ -1614,18 +1662,13 @@ sof_ipc4_prepare_dai_copier(struct snd_sof_dev *sdev, struct snd_sof_dai *dai,
 		num_pin_fmts = available_fmt->num_input_formats;
 	}
 
+	ret = sof_ipc4_adjust_params_to_dai_format(sdev, &dai_params, pin_fmts,
+						   num_pin_fmts);
+	if (ret)
+		return ret;
+
 	single_bitdepth = sof_ipc4_copier_is_single_bitdepth(sdev, pin_fmts,
 							     num_pin_fmts);
-
-	/* Update the dai_params with the only supported format */
-	if (single_bitdepth) {
-		ret = sof_ipc4_update_hw_params(sdev, &dai_params,
-						&pin_fmts[0].audio_fmt,
-						BIT(SNDRV_PCM_HW_PARAM_FORMAT));
-		if (ret)
-			return ret;
-	}
-
 	ret = snd_sof_get_nhlt_endpoint_data(sdev, dai, single_bitdepth,
 					     &dai_params,
 					     ipc4_copier->dai_index,
-- 
GitLab


From 12870ae3818e39ea65bf710f645972277b634f72 Mon Sep 17 00:00:00 2001
From: Nathan Lynch <nathanl@linux.ibm.com>
Date: Fri, 24 May 2024 14:29:54 -0500
Subject: [PATCH 561/950] powerpc/pseries/lparcfg: drop error message from
 guest name lookup

It's not an error or exceptional situation when the hosting
environment does not expose a name for the LP/guest via RTAS or the
device tree. This happens with qemu when run without the '-name'
option. The message also lacks a newline. Remove it.

Signed-off-by: Nathan Lynch <nathanl@linux.ibm.com>
Fixes: eddaa9a40275 ("powerpc/pseries: read the lpar name from the firmware")
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://msgid.link/20240524-lparcfg-updates-v2-1-62e2e9d28724@linux.ibm.com
---
 arch/powerpc/platforms/pseries/lparcfg.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/platforms/pseries/lparcfg.c b/arch/powerpc/platforms/pseries/lparcfg.c
index 6e7029640c0ca..62da20f9700a9 100644
--- a/arch/powerpc/platforms/pseries/lparcfg.c
+++ b/arch/powerpc/platforms/pseries/lparcfg.c
@@ -371,8 +371,8 @@ static int read_dt_lpar_name(struct seq_file *m)
 
 static void read_lpar_name(struct seq_file *m)
 {
-	if (read_rtas_lpar_name(m) && read_dt_lpar_name(m))
-		pr_err_once("Error can't get the LPAR name");
+	if (read_rtas_lpar_name(m))
+		read_dt_lpar_name(m);
 }
 
 #define SPLPAR_MAXLENGTH 1026*(sizeof(char))
-- 
GitLab


From 2d43cc701b96f910f50915ac4c2a0cae5deb734c Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Wed, 29 May 2024 22:30:28 +1000
Subject: [PATCH 562/950] powerpc/uaccess: Fix build errors seen with GCC 13/14

Building ppc64le_defconfig with GCC 14 fails with assembler errors:

    CC      fs/readdir.o
  /tmp/ccdQn0mD.s: Assembler messages:
  /tmp/ccdQn0mD.s:212: Error: operand out of domain (18 is not a multiple of 4)
  /tmp/ccdQn0mD.s:226: Error: operand out of domain (18 is not a multiple of 4)
  ... [6 lines]
  /tmp/ccdQn0mD.s:1699: Error: operand out of domain (18 is not a multiple of 4)

A snippet of the asm shows:

  # ../fs/readdir.c:210:         unsafe_copy_dirent_name(dirent->d_name, name, namlen, efault_end);
         ld 9,0(29)       # MEM[(u64 *)name_38(D) + _88 * 1], MEM[(u64 *)name_38(D) + _88 * 1]
  # 210 "../fs/readdir.c" 1
         1:      std 9,18(8)     # put_user       # *__pus_addr_52, MEM[(u64 *)name_38(D) + _88 * 1]

The 'std' instruction requires a 4-byte aligned displacement because
it is a DS-form instruction, and as the assembler says, 18 is not a
multiple of 4.

A similar error is seen with GCC 13 and CONFIG_UBSAN_SIGNED_WRAP=y.

The fix is to change the constraint on the memory operand to put_user(),
from "m" which is a general memory reference to "YZ".

The "Z" constraint is documented in the GCC manual PowerPC machine
constraints, and specifies a "memory operand accessed with indexed or
indirect addressing". "Y" is not documented in the manual but specifies
a "memory operand for a DS-form instruction". Using both allows the
compiler to generate a DS-form "std" or X-form "stdx" as appropriate.

The change has to be conditional on CONFIG_PPC_KERNEL_PREFIXED because
the "Y" constraint does not guarantee 4-byte alignment when prefixed
instructions are enabled.

Unfortunately clang doesn't support the "Y" constraint so that has to be
behind an ifdef.

Although the build error is only seen with GCC 13/14, that appears
to just be luck. The constraint has been incorrect since it was first
added.

Fixes: c20beffeec3c ("powerpc/uaccess: Use flexible addressing with __put_user()/__get_user()")
Cc: stable@vger.kernel.org # v5.10+
Suggested-by: Kewen Lin <linkw@gcc.gnu.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://msgid.link/20240529123029.146953-1-mpe@ellerman.id.au
---
 arch/powerpc/include/asm/uaccess.h | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h
index de10437fd2065..4cba724c88991 100644
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -92,9 +92,25 @@ __pu_failed:							\
 		: label)
 #endif
 
+#ifdef CONFIG_CC_IS_CLANG
+#define DS_FORM_CONSTRAINT "Z<>"
+#else
+#define DS_FORM_CONSTRAINT "YZ<>"
+#endif
+
 #ifdef __powerpc64__
+#ifdef CONFIG_PPC_KERNEL_PREFIXED
 #define __put_user_asm2_goto(x, ptr, label)			\
 	__put_user_asm_goto(x, ptr, label, "std")
+#else
+#define __put_user_asm2_goto(x, addr, label)			\
+	asm goto ("1: std%U1%X1 %0,%1	# put_user\n"		\
+		EX_TABLE(1b, %l2)				\
+		:						\
+		: "r" (x), DS_FORM_CONSTRAINT (*addr)		\
+		:						\
+		: label)
+#endif // CONFIG_PPC_KERNEL_PREFIXED
 #else /* __powerpc64__ */
 #define __put_user_asm2_goto(x, addr, label)			\
 	asm goto(					\
-- 
GitLab


From 50934945d54238d2d6d8db4b7c1d4c90d2696c57 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Wed, 29 May 2024 22:30:29 +1000
Subject: [PATCH 563/950] powerpc/uaccess: Use YZ asm constraint for ld

The 'ld' instruction requires a 4-byte aligned displacement because it
is a DS-form instruction. But the "m" asm constraint doesn't enforce
that.

Add a special case of __get_user_asm2_goto() so that the "YZ" constraint
can be used for "ld".

The "Z" constraint is documented in the GCC manual PowerPC machine
constraints, and specifies a "memory operand accessed with indexed or
indirect addressing". "Y" is not documented in the manual but specifies
a "memory operand for a DS-form instruction". Using both allows the
compiler to generate a DS-form "ld" or X-form "ldx" as appropriate.

The change has to be conditional on CONFIG_PPC_KERNEL_PREFIXED because
the "Y" constraint does not guarantee 4-byte alignment when prefixed
instructions are enabled.

No build errors have been reported due to this, but the possibility is
there depending on compiler code generation decisions.

Fixes: c20beffeec3c ("powerpc/uaccess: Use flexible addressing with __put_user()/__get_user()")
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://msgid.link/20240529123029.146953-2-mpe@ellerman.id.au
---
 arch/powerpc/include/asm/uaccess.h | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h
index 4cba724c88991..fd594bf6c6a9c 100644
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -181,8 +181,19 @@ do {								\
 #endif
 
 #ifdef __powerpc64__
+#ifdef CONFIG_PPC_KERNEL_PREFIXED
 #define __get_user_asm2_goto(x, addr, label)			\
 	__get_user_asm_goto(x, addr, label, "ld")
+#else
+#define __get_user_asm2_goto(x, addr, label)			\
+	asm_goto_output(					\
+		"1:	ld%U1%X1 %0, %1	# get_user\n"		\
+		EX_TABLE(1b, %l2)				\
+		: "=r" (x)					\
+		: DS_FORM_CONSTRAINT (*addr)			\
+		:						\
+		: label)
+#endif // CONFIG_PPC_KERNEL_PREFIXED
 #else /* __powerpc64__ */
 #define __get_user_asm2_goto(x, addr, label)			\
 	asm_goto_output(					\
-- 
GitLab


From be2fc65d66e0406cc9d39d40becaecdf4ee765f3 Mon Sep 17 00:00:00 2001
From: Samuel Holland <samuel.holland@sifive.com>
Date: Wed, 29 May 2024 09:28:50 -0700
Subject: [PATCH 564/950] powerpc: Limit ARCH_HAS_KERNEL_FPU_SUPPORT to PPC64

When building a 32-bit kernel, some toolchains do not allow mixing soft
float and hard float object files:

    LD      vmlinux.o
  powerpc64le-unknown-linux-musl-ld: lib/test_fpu_impl.o uses hard float, arch/powerpc/kernel/udbg.o uses soft float
  powerpc64le-unknown-linux-musl-ld: failed to merge target specific data of file lib/test_fpu_impl.o
  make[2]: *** [scripts/Makefile.vmlinux_o:62: vmlinux.o] Error 1
  make[1]: *** [Makefile:1152: vmlinux_o] Error 2
  make: *** [Makefile:240: __sub-make] Error 2

This is not an issue when building a 64-bit kernel. To unbreak the
build, limit ARCH_HAS_KERNEL_FPU_SUPPORT to 64-bit kernels. This is okay
because the only real user of this option, amdgpu, was previously
limited to PPC64 anyway; see commit a28e4b672f04 ("drm/amd/display: use
ARCH_HAS_KERNEL_FPU_SUPPORT").

Fixes: 01db473e1aa3 ("powerpc: implement ARCH_HAS_KERNEL_FPU_SUPPORT")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202405250851.Z4daYSWG-lkp@intel.com/
Reported-by: Guenter Roeck <linux@roeck-us.net>
Closes: https://lore.kernel.org/lkml/eeffaec3-df63-4e55-ab7a-064a65c00efa@roeck-us.net/
Signed-off-by: Samuel Holland <samuel.holland@sifive.com>
Tested-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://msgid.link/20240529162852.1209-1-samuel.holland@sifive.com
---
 arch/powerpc/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 3c968f2f4ac44..c88c6d46a5bc0 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -137,7 +137,7 @@ config PPC
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_HAS_HUGEPD			if HUGETLB_PAGE
 	select ARCH_HAS_KCOV
-	select ARCH_HAS_KERNEL_FPU_SUPPORT	if PPC_FPU
+	select ARCH_HAS_KERNEL_FPU_SUPPORT	if PPC64 && PPC_FPU
 	select ARCH_HAS_MEMBARRIER_CALLBACKS
 	select ARCH_HAS_MEMBARRIER_SYNC_CORE
 	select ARCH_HAS_MEMREMAP_COMPAT_ALIGN	if PPC_64S_HASH_MMU
-- 
GitLab


From 0e5895ff7fab0fc05ec17daf9a568368828fa6ea Mon Sep 17 00:00:00 2001
From: Gerald Loacker <gerald.loacker@wolfvision.net>
Date: Wed, 29 May 2024 16:42:45 +0200
Subject: [PATCH 565/950] drm/panel: sitronix-st7789v: fix timing for
 jt240mhqs_hwt_ek_e3 panel

Flickering was observed when using partial mode. Moving the vsync to the
same position as used by the default sitronix-st7789v timing resolves this
issue.

Fixes: 0fbbe96bfa08 ("drm/panel: sitronix-st7789v: add jasonic jt240mhqs-hwt-ek-e3 support")
Acked-by: Jessica Zhang <quic_jesszhan@quicinc.com>
Signed-off-by: Gerald Loacker <gerald.loacker@wolfvision.net>
Link: https://lore.kernel.org/r/20240409-bugfix-jt240mhqs_hwt_ek_e3-timing-v2-1-e4821802443d@wolfvision.net
Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20240409-bugfix-jt240mhqs_hwt_ek_e3-timing-v2-1-e4821802443d@wolfvision.net
---
 drivers/gpu/drm/panel/panel-sitronix-st7789v.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/panel/panel-sitronix-st7789v.c b/drivers/gpu/drm/panel/panel-sitronix-st7789v.c
index 88e80fe98112d..32e5c03480381 100644
--- a/drivers/gpu/drm/panel/panel-sitronix-st7789v.c
+++ b/drivers/gpu/drm/panel/panel-sitronix-st7789v.c
@@ -286,9 +286,9 @@ static const struct drm_display_mode jt240mhqs_hwt_ek_e3_mode = {
 	.hsync_end = 240 + 28 + 10,
 	.htotal = 240 + 28 + 10 + 10,
 	.vdisplay = 280,
-	.vsync_start = 280 + 8,
-	.vsync_end = 280 + 8 + 4,
-	.vtotal = 280 + 8 + 4 + 4,
+	.vsync_start = 280 + 48,
+	.vsync_end = 280 + 48 + 4,
+	.vtotal = 280 + 48 + 4 + 4,
 	.width_mm = 43,
 	.height_mm = 37,
 	.flags = DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC,
-- 
GitLab


From 2ba50582634d0bfe3a333ab7575a7f0122a7cde8 Mon Sep 17 00:00:00 2001
From: Gerald Loacker <gerald.loacker@wolfvision.net>
Date: Wed, 29 May 2024 16:42:46 +0200
Subject: [PATCH 566/950] drm/panel: sitronix-st7789v: tweak timing for
 jt240mhqs_hwt_ek_e3 panel

Use the default timing parameters to get a refresh rate of about 60 Hz for
a clock of 6 MHz.

Fixes: 0fbbe96bfa08 ("drm/panel: sitronix-st7789v: add jasonic jt240mhqs-hwt-ek-e3 support")
Signed-off-by: Gerald Loacker <gerald.loacker@wolfvision.net>
Acked-by: Jessica Zhang <quic_jesszhan@quicinc.com>
Link: https://lore.kernel.org/r/20240409-bugfix-jt240mhqs_hwt_ek_e3-timing-v2-2-e4821802443d@wolfvision.net
Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20240409-bugfix-jt240mhqs_hwt_ek_e3-timing-v2-2-e4821802443d@wolfvision.net
---
 drivers/gpu/drm/panel/panel-sitronix-st7789v.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/panel/panel-sitronix-st7789v.c b/drivers/gpu/drm/panel/panel-sitronix-st7789v.c
index 32e5c03480381..c7e3f1280404d 100644
--- a/drivers/gpu/drm/panel/panel-sitronix-st7789v.c
+++ b/drivers/gpu/drm/panel/panel-sitronix-st7789v.c
@@ -282,9 +282,9 @@ static const struct drm_display_mode et028013dma_mode = {
 static const struct drm_display_mode jt240mhqs_hwt_ek_e3_mode = {
 	.clock = 6000,
 	.hdisplay = 240,
-	.hsync_start = 240 + 28,
-	.hsync_end = 240 + 28 + 10,
-	.htotal = 240 + 28 + 10 + 10,
+	.hsync_start = 240 + 38,
+	.hsync_end = 240 + 38 + 10,
+	.htotal = 240 + 38 + 10 + 10,
 	.vdisplay = 280,
 	.vsync_start = 280 + 48,
 	.vsync_end = 280 + 48 + 4,
-- 
GitLab


From b62c150c3bae72ac1910dcc588f360159eb0744a Mon Sep 17 00:00:00 2001
From: Gerald Loacker <gerald.loacker@wolfvision.net>
Date: Wed, 29 May 2024 16:42:47 +0200
Subject: [PATCH 567/950] drm/panel: sitronix-st7789v: fix display size for
 jt240mhqs_hwt_ek_e3 panel

This is a portrait mode display. Change the dimensions accordingly.

Fixes: 0fbbe96bfa08 ("drm/panel: sitronix-st7789v: add jasonic jt240mhqs-hwt-ek-e3 support")
Signed-off-by: Gerald Loacker <gerald.loacker@wolfvision.net>
Acked-by: Jessica Zhang <quic_jesszhan@quicinc.com>
Link: https://lore.kernel.org/r/20240409-bugfix-jt240mhqs_hwt_ek_e3-timing-v2-3-e4821802443d@wolfvision.net
Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20240409-bugfix-jt240mhqs_hwt_ek_e3-timing-v2-3-e4821802443d@wolfvision.net
---
 drivers/gpu/drm/panel/panel-sitronix-st7789v.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/panel/panel-sitronix-st7789v.c b/drivers/gpu/drm/panel/panel-sitronix-st7789v.c
index c7e3f1280404d..e8f385b9c6182 100644
--- a/drivers/gpu/drm/panel/panel-sitronix-st7789v.c
+++ b/drivers/gpu/drm/panel/panel-sitronix-st7789v.c
@@ -289,8 +289,8 @@ static const struct drm_display_mode jt240mhqs_hwt_ek_e3_mode = {
 	.vsync_start = 280 + 48,
 	.vsync_end = 280 + 48 + 4,
 	.vtotal = 280 + 48 + 4 + 4,
-	.width_mm = 43,
-	.height_mm = 37,
+	.width_mm = 37,
+	.height_mm = 43,
 	.flags = DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC,
 };
 
-- 
GitLab


From 487f7323f39a9d45a31c59e909de4a626f02d34f Mon Sep 17 00:00:00 2001
From: MD Danish Anwar <danishanwar@ti.com>
Date: Tue, 28 May 2024 17:07:32 +0530
Subject: [PATCH 568/950] net: ti: icssg-prueth: Add helper functions to
 configure FDB

Introduce helper functions to configure firmware FDB tables, VLAN tables
and Port VLAN ID settings to aid adding Switch mode support.

Signed-off-by: MD Danish Anwar <danishanwar@ti.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/ti/icssg/icssg_config.c | 170 +++++++++++++++++++
 drivers/net/ethernet/ti/icssg/icssg_config.h |  19 +++
 drivers/net/ethernet/ti/icssg/icssg_prueth.h |  12 ++
 3 files changed, 201 insertions(+)

diff --git a/drivers/net/ethernet/ti/icssg/icssg_config.c b/drivers/net/ethernet/ti/icssg/icssg_config.c
index 15f2235bf90fa..2213374d4d451 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_config.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_config.c
@@ -477,3 +477,173 @@ void icssg_config_set_speed(struct prueth_emac *emac)
 
 	writeb(fw_speed, emac->dram.va + PORT_LINK_SPEED_OFFSET);
 }
+
+int icssg_send_fdb_msg(struct prueth_emac *emac, struct mgmt_cmd *cmd,
+		       struct mgmt_cmd_rsp *rsp)
+{
+	struct prueth *prueth = emac->prueth;
+	int slice = prueth_emac_slice(emac);
+	int addr, ret;
+
+	addr = icssg_queue_pop(prueth, slice == 0 ?
+			       ICSSG_CMD_POP_SLICE0 : ICSSG_CMD_POP_SLICE1);
+	if (addr < 0)
+		return addr;
+
+	/* First 4 bytes have FW owned buffer linking info which should
+	 * not be touched
+	 */
+	memcpy_toio(prueth->shram.va + addr + 4, cmd, sizeof(*cmd));
+	icssg_queue_push(prueth, slice == 0 ?
+			 ICSSG_CMD_PUSH_SLICE0 : ICSSG_CMD_PUSH_SLICE1, addr);
+	ret = read_poll_timeout(icssg_queue_pop, addr, addr >= 0,
+				2000, 20000000, false, prueth, slice == 0 ?
+				ICSSG_RSP_POP_SLICE0 : ICSSG_RSP_POP_SLICE1);
+	if (ret) {
+		netdev_err(emac->ndev, "Timedout sending HWQ message\n");
+		return ret;
+	}
+
+	memcpy_fromio(rsp, prueth->shram.va + addr, sizeof(*rsp));
+	/* Return buffer back for to pool */
+	icssg_queue_push(prueth, slice == 0 ?
+			 ICSSG_RSP_PUSH_SLICE0 : ICSSG_RSP_PUSH_SLICE1, addr);
+
+	return 0;
+}
+
+static void icssg_fdb_setup(struct prueth_emac *emac, struct mgmt_cmd *fdb_cmd,
+			    const unsigned char *addr, u8 fid, int cmd)
+{
+	int slice = prueth_emac_slice(emac);
+	u8 mac_fid[ETH_ALEN + 2];
+	u16 fdb_slot;
+
+	ether_addr_copy(mac_fid, addr);
+
+	/* 1-1 VID-FID mapping is already setup */
+	mac_fid[ETH_ALEN] = fid;
+	mac_fid[ETH_ALEN + 1] = 0;
+
+	fdb_slot = bitrev32(crc32_le(0, mac_fid, 8)) & PRUETH_SWITCH_FDB_MASK;
+
+	fdb_cmd->header = ICSSG_FW_MGMT_CMD_HEADER;
+	fdb_cmd->type   = ICSSG_FW_MGMT_FDB_CMD_TYPE;
+	fdb_cmd->seqnum = ++(emac->prueth->icssg_hwcmdseq);
+	fdb_cmd->param  = cmd;
+	fdb_cmd->param |= (slice << 4);
+
+	memcpy(&fdb_cmd->cmd_args[0], addr, 4);
+	memcpy(&fdb_cmd->cmd_args[1], &addr[4], 2);
+	fdb_cmd->cmd_args[2] = fdb_slot;
+
+	netdev_dbg(emac->ndev, "MAC %pM slot %X FID %X\n", addr, fdb_slot, fid);
+}
+
+int icssg_fdb_add_del(struct prueth_emac *emac, const unsigned char *addr,
+		      u8 vid, u8 fid_c2, bool add)
+{
+	struct mgmt_cmd_rsp fdb_cmd_rsp = { 0 };
+	struct mgmt_cmd fdb_cmd = { 0 };
+	u8 fid = vid;
+	int ret;
+
+	icssg_fdb_setup(emac, &fdb_cmd, addr, fid, add ? ICSS_CMD_ADD_FDB : ICSS_CMD_DEL_FDB);
+
+	fid_c2 |= ICSSG_FDB_ENTRY_VALID;
+	fdb_cmd.cmd_args[1] |= ((fid << 16) | (fid_c2 << 24));
+
+	ret = icssg_send_fdb_msg(emac, &fdb_cmd, &fdb_cmd_rsp);
+	if (ret)
+		return ret;
+
+	WARN_ON(fdb_cmd.seqnum != fdb_cmd_rsp.seqnum);
+	if (fdb_cmd_rsp.status == 1)
+		return 0;
+
+	return -EINVAL;
+}
+
+int icssg_fdb_lookup(struct prueth_emac *emac, const unsigned char *addr,
+		     u8 vid)
+{
+	struct mgmt_cmd_rsp fdb_cmd_rsp = { 0 };
+	struct mgmt_cmd fdb_cmd = { 0 };
+	struct prueth_fdb_slot *slot;
+	u8 fid = vid;
+	int ret, i;
+
+	icssg_fdb_setup(emac, &fdb_cmd, addr, fid, ICSS_CMD_GET_FDB_SLOT);
+
+	fdb_cmd.cmd_args[1] |= fid << 16;
+
+	ret = icssg_send_fdb_msg(emac, &fdb_cmd, &fdb_cmd_rsp);
+	if (ret)
+		return ret;
+
+	WARN_ON(fdb_cmd.seqnum != fdb_cmd_rsp.seqnum);
+
+	slot = (struct prueth_fdb_slot __force *)(emac->dram.va + FDB_CMD_BUFFER);
+	for (i = 0; i < 4; i++) {
+		if (ether_addr_equal(addr, slot->mac) && vid == slot->fid)
+			return (slot->fid_c2 & ~ICSSG_FDB_ENTRY_VALID);
+		slot++;
+	}
+
+	return 0;
+}
+
+void icssg_vtbl_modify(struct prueth_emac *emac, u8 vid, u8 port_mask,
+		       u8 untag_mask, bool add)
+{
+	struct prueth *prueth = emac->prueth;
+	struct prueth_vlan_tbl *tbl;
+	u8 fid_c1;
+
+	tbl = prueth->vlan_tbl;
+	fid_c1 = tbl[vid].fid_c1;
+
+	/* FID_C1: bit0..2 port membership mask,
+	 * bit3..5 tagging mask for each port
+	 * bit6 Stream VID (not handled currently)
+	 * bit7 MC flood (not handled currently)
+	 */
+	if (add) {
+		fid_c1 |= (port_mask | port_mask << 3);
+		fid_c1 &= ~(untag_mask << 3);
+	} else {
+		fid_c1 &= ~(port_mask | port_mask << 3);
+	}
+
+	tbl[vid].fid_c1 = fid_c1;
+}
+
+u16 icssg_get_pvid(struct prueth_emac *emac)
+{
+	struct prueth *prueth = emac->prueth;
+	u32 pvid;
+
+	if (emac->port_id == PRUETH_PORT_MII0)
+		pvid = readl(prueth->shram.va + EMAC_ICSSG_SWITCH_PORT1_DEFAULT_VLAN_OFFSET);
+	else
+		pvid = readl(prueth->shram.va + EMAC_ICSSG_SWITCH_PORT2_DEFAULT_VLAN_OFFSET);
+
+	pvid = pvid >> 24;
+
+	return pvid;
+}
+
+void icssg_set_pvid(struct prueth *prueth, u8 vid, u8 port)
+{
+	u32 pvid;
+
+	/* only 256 VLANs are supported */
+	pvid = (u32 __force)cpu_to_be32((ETH_P_8021Q << 16) | (vid & 0xff));
+
+	if (port == PRUETH_PORT_MII0)
+		writel(pvid, prueth->shram.va + EMAC_ICSSG_SWITCH_PORT1_DEFAULT_VLAN_OFFSET);
+	else if (port == PRUETH_PORT_MII1)
+		writel(pvid, prueth->shram.va + EMAC_ICSSG_SWITCH_PORT2_DEFAULT_VLAN_OFFSET);
+	else
+		writel(pvid, prueth->shram.va + EMAC_ICSSG_SWITCH_PORT0_DEFAULT_VLAN_OFFSET);
+}
diff --git a/drivers/net/ethernet/ti/icssg/icssg_config.h b/drivers/net/ethernet/ti/icssg/icssg_config.h
index cf2ea4bd22a2d..4a9721aa60577 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_config.h
+++ b/drivers/net/ethernet/ti/icssg/icssg_config.h
@@ -35,6 +35,8 @@ struct icssg_flow_cfg {
 	(2 * (PRUETH_EMAC_BUF_POOL_SIZE * PRUETH_NUM_BUF_POOLS + \
 	 PRUETH_EMAC_RX_CTX_BUF_SIZE * 2))
 
+#define PRUETH_SWITCH_FDB_MASK ((SIZE_OF_FDB / NUMBER_OF_FDB_BUCKET_ENTRIES) - 1)
+
 struct icssg_rxq_ctx {
 	__le32 start[3];
 	__le32 end;
@@ -202,6 +204,23 @@ struct icssg_setclock_desc {
 #define ICSSG_TS_PUSH_SLICE0	40
 #define ICSSG_TS_PUSH_SLICE1	41
 
+struct mgmt_cmd {
+	u8 param;
+	u8 seqnum;
+	u8 type;
+	u8 header;
+	u32 cmd_args[3];
+};
+
+struct mgmt_cmd_rsp {
+	u32 reserved;
+	u8 status;
+	u8 seqnum;
+	u8 type;
+	u8 header;
+	u32 cmd_args[3];
+};
+
 /* FDB FID_C2 flag definitions */
 /* Indicates host port membership.*/
 #define ICSSG_FDB_ENTRY_P0_MEMBERSHIP         BIT(0)
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.h b/drivers/net/ethernet/ti/icssg/icssg_prueth.h
index a78c5eb75fb86..82bdad9702c3c 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.h
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.h
@@ -232,6 +232,7 @@ struct icssg_firmwares {
  * @emacs_initialized: num of EMACs/ext ports that are up/running
  * @iep0: pointer to IEP0 device
  * @iep1: pointer to IEP1 device
+ * @vlan_tbl: VLAN-FID table pointer
  */
 struct prueth {
 	struct device *dev;
@@ -256,6 +257,7 @@ struct prueth {
 	int emacs_initialized;
 	struct icss_iep *iep0;
 	struct icss_iep *iep1;
+	struct prueth_vlan_tbl *vlan_tbl;
 };
 
 struct emac_tx_ts_response {
@@ -313,6 +315,16 @@ int icssg_queue_pop(struct prueth *prueth, u8 queue);
 void icssg_queue_push(struct prueth *prueth, int queue, u16 addr);
 u32 icssg_queue_level(struct prueth *prueth, int queue);
 
+int icssg_send_fdb_msg(struct prueth_emac *emac, struct mgmt_cmd *cmd,
+		       struct mgmt_cmd_rsp *rsp);
+int icssg_fdb_add_del(struct prueth_emac *emac,  const unsigned char *addr,
+		      u8 vid, u8 fid_c2, bool add);
+int icssg_fdb_lookup(struct prueth_emac *emac, const unsigned char *addr,
+		     u8 vid);
+void icssg_vtbl_modify(struct prueth_emac *emac, u8 vid, u8 port_mask,
+		       u8 untag_mask, bool add);
+u16 icssg_get_pvid(struct prueth_emac *emac);
+void icssg_set_pvid(struct prueth *prueth, u8 vid, u8 port);
 #define prueth_napi_to_tx_chn(pnapi) \
 	container_of(pnapi, struct prueth_tx_chn, napi_tx)
 
-- 
GitLab


From 972383aecf43c3664750496d5395e669c35ba06e Mon Sep 17 00:00:00 2001
From: MD Danish Anwar <danishanwar@ti.com>
Date: Tue, 28 May 2024 17:07:33 +0530
Subject: [PATCH 569/950] net: ti: icssg-switch: Add switchdev based driver for
 ethernet switch support

ICSSG can operating in switch mode with 2 ext port and 1 host port with
VLAN/FDB/MDB and STP offloading. Add switchdev based driver to
support the same.

Driver itself will be integrated with icssg_prueth in future commits

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: MD Danish Anwar <danishanwar@ti.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/ti/icssg/icssg_prueth.c  |  12 +
 drivers/net/ethernet/ti/icssg/icssg_prueth.h  |  24 +
 .../net/ethernet/ti/icssg/icssg_switchdev.c   | 477 ++++++++++++++++++
 .../net/ethernet/ti/icssg/icssg_switchdev.h   |  13 +
 4 files changed, 526 insertions(+)
 create mode 100644 drivers/net/ethernet/ti/icssg/icssg_switchdev.c
 create mode 100644 drivers/net/ethernet/ti/icssg/icssg_switchdev.h

diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
index 1ea3fbd5e954e..1db67a8107cc1 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
@@ -30,6 +30,7 @@
 
 #include "icssg_prueth.h"
 #include "icssg_mii_rt.h"
+#include "icssg_switchdev.h"
 #include "../k3-cppi-desc-pool.h"
 
 #define PRUETH_MODULE_DESCRIPTION "PRUSS ICSSG Ethernet driver"
@@ -833,6 +834,17 @@ free_ndev:
 	return ret;
 }
 
+bool prueth_dev_check(const struct net_device *ndev)
+{
+	if (ndev->netdev_ops == &emac_netdev_ops && netif_running(ndev)) {
+		struct prueth_emac *emac = netdev_priv(ndev);
+
+		return emac->prueth->is_switch_mode;
+	}
+
+	return false;
+}
+
 static int prueth_probe(struct platform_device *pdev)
 {
 	struct device_node *eth_node, *eth_ports_node;
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.h b/drivers/net/ethernet/ti/icssg/icssg_prueth.h
index 82bdad9702c3c..5eeeccb736659 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.h
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.h
@@ -186,6 +186,9 @@ struct prueth_emac {
 
 	struct pruss_mem_region dram;
 
+	bool offload_fwd_mark;
+	int port_vlan;
+
 	struct delayed_work stats_work;
 	u64 stats[ICSSG_NUM_STATS];
 
@@ -198,10 +201,12 @@ struct prueth_emac {
  * struct prueth_pdata - PRUeth platform data
  * @fdqring_mode: Free desc queue mode
  * @quirk_10m_link_issue: 10M link detect errata
+ * @switch_mode: switch firmware support
  */
 struct prueth_pdata {
 	enum k3_ring_mode fdqring_mode;
 	u32	quirk_10m_link_issue:1;
+	u32	switch_mode:1;
 };
 
 struct icssg_firmwares {
@@ -233,6 +238,15 @@ struct icssg_firmwares {
  * @iep0: pointer to IEP0 device
  * @iep1: pointer to IEP1 device
  * @vlan_tbl: VLAN-FID table pointer
+ * @hw_bridge_dev: pointer to HW bridge net device
+ * @br_members: bitmask of bridge member ports
+ * @prueth_netdevice_nb: netdevice notifier block
+ * @prueth_switchdev_nb: switchdev notifier block
+ * @prueth_switchdev_bl_nb: switchdev blocking notifier block
+ * @is_switch_mode: flag to indicate if device is in Switch mode
+ * @is_switchmode_supported: indicates platform support for switch mode
+ * @switch_id: ID for mapping switch ports to bridge
+ * @default_vlan: Default VLAN for host
  */
 struct prueth {
 	struct device *dev;
@@ -258,6 +272,16 @@ struct prueth {
 	struct icss_iep *iep0;
 	struct icss_iep *iep1;
 	struct prueth_vlan_tbl *vlan_tbl;
+
+	struct net_device *hw_bridge_dev;
+	u8 br_members;
+	struct notifier_block prueth_netdevice_nb;
+	struct notifier_block prueth_switchdev_nb;
+	struct notifier_block prueth_switchdev_bl_nb;
+	bool is_switch_mode;
+	bool is_switchmode_supported;
+	unsigned char switch_id[MAX_PHYS_ITEM_ID_LEN];
+	int default_vlan;
 };
 
 struct emac_tx_ts_response {
diff --git a/drivers/net/ethernet/ti/icssg/icssg_switchdev.c b/drivers/net/ethernet/ti/icssg/icssg_switchdev.c
new file mode 100644
index 0000000000000..fceb8bb7d34ed
--- /dev/null
+++ b/drivers/net/ethernet/ti/icssg/icssg_switchdev.c
@@ -0,0 +1,477 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/* Texas Instruments K3 ICSSG Ethernet Switchdev Driver
+ *
+ * Copyright (C) 2021 Texas Instruments Incorporated - https://www.ti.com/
+ *
+ */
+
+#include <linux/etherdevice.h>
+#include <linux/if_bridge.h>
+#include <linux/netdevice.h>
+#include <linux/workqueue.h>
+#include <net/switchdev.h>
+
+#include "icssg_prueth.h"
+#include "icssg_switchdev.h"
+#include "icssg_mii_rt.h"
+
+struct prueth_switchdev_event_work {
+	struct work_struct work;
+	struct switchdev_notifier_fdb_info fdb_info;
+	struct prueth_emac *emac;
+	unsigned long event;
+};
+
+static int prueth_switchdev_stp_state_set(struct prueth_emac *emac,
+					  u8 state)
+{
+	enum icssg_port_state_cmd emac_state;
+	int ret = 0;
+
+	switch (state) {
+	case BR_STATE_FORWARDING:
+		emac_state = ICSSG_EMAC_PORT_FORWARD;
+		break;
+	case BR_STATE_DISABLED:
+		emac_state = ICSSG_EMAC_PORT_DISABLE;
+		break;
+	case BR_STATE_LISTENING:
+	case BR_STATE_BLOCKING:
+		emac_state = ICSSG_EMAC_PORT_BLOCK;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	emac_set_port_state(emac, emac_state);
+	netdev_dbg(emac->ndev, "STP state: %u\n", emac_state);
+
+	return ret;
+}
+
+static int prueth_switchdev_attr_br_flags_set(struct prueth_emac *emac,
+					      struct net_device *orig_dev,
+					      struct switchdev_brport_flags brport_flags)
+{
+	enum icssg_port_state_cmd emac_state;
+
+	if (brport_flags.mask & BR_MCAST_FLOOD)
+		emac_state = ICSSG_EMAC_PORT_MC_FLOODING_ENABLE;
+	else
+		emac_state = ICSSG_EMAC_PORT_MC_FLOODING_DISABLE;
+
+	netdev_dbg(emac->ndev, "BR_MCAST_FLOOD: %d port %u\n",
+		   emac_state, emac->port_id);
+
+	emac_set_port_state(emac, emac_state);
+
+	return 0;
+}
+
+static int prueth_switchdev_attr_br_flags_pre_set(struct net_device *netdev,
+						  struct switchdev_brport_flags brport_flags)
+{
+	if (brport_flags.mask & ~(BR_LEARNING | BR_MCAST_FLOOD))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int prueth_switchdev_attr_set(struct net_device *ndev, const void *ctx,
+				     const struct switchdev_attr *attr,
+				     struct netlink_ext_ack *extack)
+{
+	struct prueth_emac *emac = netdev_priv(ndev);
+	int ret;
+
+	netdev_dbg(ndev, "attr: id %u port: %u\n", attr->id, emac->port_id);
+
+	switch (attr->id) {
+	case SWITCHDEV_ATTR_ID_PORT_PRE_BRIDGE_FLAGS:
+		ret = prueth_switchdev_attr_br_flags_pre_set(ndev,
+							     attr->u.brport_flags);
+		break;
+	case SWITCHDEV_ATTR_ID_PORT_STP_STATE:
+		ret = prueth_switchdev_stp_state_set(emac,
+						     attr->u.stp_state);
+		netdev_dbg(ndev, "stp state: %u\n", attr->u.stp_state);
+		break;
+	case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS:
+		ret = prueth_switchdev_attr_br_flags_set(emac, attr->orig_dev,
+							 attr->u.brport_flags);
+		break;
+	default:
+		ret = -EOPNOTSUPP;
+		break;
+	}
+
+	return ret;
+}
+
+static void prueth_switchdev_fdb_offload_notify(struct net_device *ndev,
+						struct switchdev_notifier_fdb_info *rcv)
+{
+	struct switchdev_notifier_fdb_info info;
+
+	memset(&info, 0, sizeof(info));
+	info.addr = rcv->addr;
+	info.vid = rcv->vid;
+	info.offloaded = true;
+	call_switchdev_notifiers(SWITCHDEV_FDB_OFFLOADED,
+				 ndev, &info.info, NULL);
+}
+
+static void prueth_switchdev_event_work(struct work_struct *work)
+{
+	struct prueth_switchdev_event_work *switchdev_work =
+		container_of(work, struct prueth_switchdev_event_work, work);
+	struct prueth_emac *emac = switchdev_work->emac;
+	struct switchdev_notifier_fdb_info *fdb;
+	int port_id = emac->port_id;
+	int ret;
+
+	rtnl_lock();
+	switch (switchdev_work->event) {
+	case SWITCHDEV_FDB_ADD_TO_DEVICE:
+		fdb = &switchdev_work->fdb_info;
+
+		netdev_dbg(emac->ndev, "prueth_fdb_add: MACID = %pM vid = %u flags = %u %u -- port %d\n",
+			   fdb->addr, fdb->vid, fdb->added_by_user,
+			   fdb->offloaded, port_id);
+
+		if (!fdb->added_by_user)
+			break;
+		if (!ether_addr_equal(emac->mac_addr, fdb->addr))
+			break;
+
+		ret = icssg_fdb_add_del(emac, fdb->addr, fdb->vid,
+					BIT(port_id), true);
+		if (!ret)
+			prueth_switchdev_fdb_offload_notify(emac->ndev, fdb);
+		break;
+	case SWITCHDEV_FDB_DEL_TO_DEVICE:
+		fdb = &switchdev_work->fdb_info;
+
+		netdev_dbg(emac->ndev, "prueth_fdb_del: MACID = %pM vid = %u flags = %u %u -- port %d\n",
+			   fdb->addr, fdb->vid, fdb->added_by_user,
+			   fdb->offloaded, port_id);
+
+		if (!fdb->added_by_user)
+			break;
+		if (!ether_addr_equal(emac->mac_addr, fdb->addr))
+			break;
+		icssg_fdb_add_del(emac, fdb->addr, fdb->vid,
+				  BIT(port_id), false);
+		break;
+	default:
+		break;
+	}
+	rtnl_unlock();
+
+	kfree(switchdev_work->fdb_info.addr);
+	kfree(switchdev_work);
+	dev_put(emac->ndev);
+}
+
+static int prueth_switchdev_event(struct notifier_block *unused,
+				  unsigned long event, void *ptr)
+{
+	struct net_device *ndev = switchdev_notifier_info_to_dev(ptr);
+	struct prueth_switchdev_event_work *switchdev_work;
+	struct switchdev_notifier_fdb_info *fdb_info = ptr;
+	struct prueth_emac *emac = netdev_priv(ndev);
+	int err;
+
+	if (!prueth_dev_check(ndev))
+		return NOTIFY_DONE;
+
+	if (event == SWITCHDEV_PORT_ATTR_SET) {
+		err = switchdev_handle_port_attr_set(ndev, ptr,
+						     prueth_dev_check,
+						     prueth_switchdev_attr_set);
+		return notifier_from_errno(err);
+	}
+
+	switchdev_work = kzalloc(sizeof(*switchdev_work), GFP_ATOMIC);
+	if (WARN_ON(!switchdev_work))
+		return NOTIFY_BAD;
+
+	INIT_WORK(&switchdev_work->work, prueth_switchdev_event_work);
+	switchdev_work->emac = emac;
+	switchdev_work->event = event;
+
+	switch (event) {
+	case SWITCHDEV_FDB_ADD_TO_DEVICE:
+	case SWITCHDEV_FDB_DEL_TO_DEVICE:
+		memcpy(&switchdev_work->fdb_info, ptr,
+		       sizeof(switchdev_work->fdb_info));
+		switchdev_work->fdb_info.addr = kzalloc(ETH_ALEN, GFP_ATOMIC);
+		if (!switchdev_work->fdb_info.addr)
+			goto err_addr_alloc;
+		ether_addr_copy((u8 *)switchdev_work->fdb_info.addr,
+				fdb_info->addr);
+		dev_hold(ndev);
+		break;
+	default:
+		kfree(switchdev_work);
+		return NOTIFY_DONE;
+	}
+
+	queue_work(system_long_wq, &switchdev_work->work);
+
+	return NOTIFY_DONE;
+
+err_addr_alloc:
+	kfree(switchdev_work);
+	return NOTIFY_BAD;
+}
+
+static int prueth_switchdev_vlan_add(struct prueth_emac *emac, bool untag, bool pvid,
+				     u8 vid, struct net_device *orig_dev)
+{
+	bool cpu_port = netif_is_bridge_master(orig_dev);
+	int untag_mask = 0;
+	int port_mask;
+	int ret = 0;
+
+	if (cpu_port)
+		port_mask = BIT(PRUETH_PORT_HOST);
+	else
+		port_mask = BIT(emac->port_id);
+
+	if (untag)
+		untag_mask = port_mask;
+
+	icssg_vtbl_modify(emac, vid, port_mask, untag_mask, true);
+
+	netdev_dbg(emac->ndev, "VID add vid:%u port_mask:%X untag_mask %X PVID %d\n",
+		   vid, port_mask, untag_mask, pvid);
+
+	if (!pvid)
+		return ret;
+
+	icssg_set_pvid(emac->prueth, vid, emac->port_id);
+
+	return ret;
+}
+
+static int prueth_switchdev_vlan_del(struct prueth_emac *emac, u16 vid,
+				     struct net_device *orig_dev)
+{
+	bool cpu_port = netif_is_bridge_master(orig_dev);
+	int port_mask;
+	int ret = 0;
+
+	if (cpu_port)
+		port_mask = BIT(PRUETH_PORT_HOST);
+	else
+		port_mask = BIT(emac->port_id);
+
+	icssg_vtbl_modify(emac, vid, port_mask, 0, false);
+
+	if (cpu_port)
+		icssg_fdb_add_del(emac, emac->mac_addr, vid,
+				  BIT(PRUETH_PORT_HOST), false);
+
+	if (vid == icssg_get_pvid(emac))
+		icssg_set_pvid(emac->prueth, 0, emac->port_id);
+
+	netdev_dbg(emac->ndev, "VID del vid:%u port_mask:%X\n",
+		   vid, port_mask);
+
+	return ret;
+}
+
+static int prueth_switchdev_vlans_add(struct prueth_emac *emac,
+				      const struct switchdev_obj_port_vlan *vlan)
+{
+	bool untag = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED;
+	struct net_device *orig_dev = vlan->obj.orig_dev;
+	bool cpu_port = netif_is_bridge_master(orig_dev);
+	bool pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID;
+
+	netdev_dbg(emac->ndev, "VID add vid:%u flags:%X\n",
+		   vlan->vid, vlan->flags);
+
+	if (cpu_port && !(vlan->flags & BRIDGE_VLAN_INFO_BRENTRY))
+		return 0;
+
+	if (vlan->vid > 0xff)
+		return 0;
+
+	return prueth_switchdev_vlan_add(emac, untag, pvid, vlan->vid,
+					 orig_dev);
+}
+
+static int prueth_switchdev_vlans_del(struct prueth_emac *emac,
+				      const struct switchdev_obj_port_vlan *vlan)
+{
+	if (vlan->vid > 0xff)
+		return 0;
+
+	return prueth_switchdev_vlan_del(emac, vlan->vid,
+					 vlan->obj.orig_dev);
+}
+
+static int prueth_switchdev_mdb_add(struct prueth_emac *emac,
+				    struct switchdev_obj_port_mdb *mdb)
+{
+	struct net_device *orig_dev = mdb->obj.orig_dev;
+	u8 port_mask, fid_c2;
+	bool cpu_port;
+	int err;
+
+	cpu_port = netif_is_bridge_master(orig_dev);
+
+	if (cpu_port)
+		port_mask = BIT(PRUETH_PORT_HOST);
+	else
+		port_mask = BIT(emac->port_id);
+
+	fid_c2 = icssg_fdb_lookup(emac, mdb->addr, mdb->vid);
+
+	err = icssg_fdb_add_del(emac, mdb->addr, mdb->vid, fid_c2 | port_mask, true);
+	netdev_dbg(emac->ndev, "MDB add vid %u:%pM  ports: %X\n",
+		   mdb->vid, mdb->addr, port_mask);
+
+	return err;
+}
+
+static int prueth_switchdev_mdb_del(struct prueth_emac *emac,
+				    struct switchdev_obj_port_mdb *mdb)
+{
+	struct net_device *orig_dev = mdb->obj.orig_dev;
+	int del_mask, ret, fid_c2;
+	bool cpu_port;
+
+	cpu_port = netif_is_bridge_master(orig_dev);
+
+	if (cpu_port)
+		del_mask = BIT(PRUETH_PORT_HOST);
+	else
+		del_mask = BIT(emac->port_id);
+
+	fid_c2 = icssg_fdb_lookup(emac, mdb->addr, mdb->vid);
+
+	if (fid_c2 & ~del_mask)
+		ret = icssg_fdb_add_del(emac, mdb->addr, mdb->vid, fid_c2 & ~del_mask, true);
+	else
+		ret = icssg_fdb_add_del(emac, mdb->addr, mdb->vid, 0, false);
+
+	netdev_dbg(emac->ndev, "MDB del vid %u:%pM  ports: %X\n",
+		   mdb->vid, mdb->addr, del_mask);
+
+	return ret;
+}
+
+static int prueth_switchdev_obj_add(struct net_device *ndev, const void *ctx,
+				    const struct switchdev_obj *obj,
+				    struct netlink_ext_ack *extack)
+{
+	struct switchdev_obj_port_vlan *vlan = SWITCHDEV_OBJ_PORT_VLAN(obj);
+	struct switchdev_obj_port_mdb *mdb = SWITCHDEV_OBJ_PORT_MDB(obj);
+	struct prueth_emac *emac = netdev_priv(ndev);
+	int err = 0;
+
+	netdev_dbg(ndev, "obj_add: id %u port: %u\n", obj->id, emac->port_id);
+
+	switch (obj->id) {
+	case SWITCHDEV_OBJ_ID_PORT_VLAN:
+		err = prueth_switchdev_vlans_add(emac, vlan);
+		break;
+	case SWITCHDEV_OBJ_ID_PORT_MDB:
+	case SWITCHDEV_OBJ_ID_HOST_MDB:
+		err = prueth_switchdev_mdb_add(emac, mdb);
+		break;
+	default:
+		err = -EOPNOTSUPP;
+		break;
+	}
+
+	return err;
+}
+
+static int prueth_switchdev_obj_del(struct net_device *ndev, const void *ctx,
+				    const struct switchdev_obj *obj)
+{
+	struct switchdev_obj_port_vlan *vlan = SWITCHDEV_OBJ_PORT_VLAN(obj);
+	struct switchdev_obj_port_mdb *mdb = SWITCHDEV_OBJ_PORT_MDB(obj);
+	struct prueth_emac *emac = netdev_priv(ndev);
+	int err = 0;
+
+	netdev_dbg(ndev, "obj_del: id %u port: %u\n", obj->id, emac->port_id);
+
+	switch (obj->id) {
+	case SWITCHDEV_OBJ_ID_PORT_VLAN:
+		err = prueth_switchdev_vlans_del(emac, vlan);
+		break;
+	case SWITCHDEV_OBJ_ID_PORT_MDB:
+	case SWITCHDEV_OBJ_ID_HOST_MDB:
+		err = prueth_switchdev_mdb_del(emac, mdb);
+		break;
+	default:
+		err = -EOPNOTSUPP;
+		break;
+	}
+
+	return err;
+}
+
+static int prueth_switchdev_blocking_event(struct notifier_block *unused,
+					   unsigned long event, void *ptr)
+{
+	struct net_device *dev = switchdev_notifier_info_to_dev(ptr);
+	int err;
+
+	switch (event) {
+	case SWITCHDEV_PORT_OBJ_ADD:
+		err = switchdev_handle_port_obj_add(dev, ptr,
+						    prueth_dev_check,
+						    prueth_switchdev_obj_add);
+		return notifier_from_errno(err);
+	case SWITCHDEV_PORT_OBJ_DEL:
+		err = switchdev_handle_port_obj_del(dev, ptr,
+						    prueth_dev_check,
+						    prueth_switchdev_obj_del);
+		return notifier_from_errno(err);
+	case SWITCHDEV_PORT_ATTR_SET:
+		err = switchdev_handle_port_attr_set(dev, ptr,
+						     prueth_dev_check,
+						     prueth_switchdev_attr_set);
+		return notifier_from_errno(err);
+	default:
+		break;
+	}
+
+	return NOTIFY_DONE;
+}
+
+int prueth_switchdev_register_notifiers(struct prueth *prueth)
+{
+	int ret = 0;
+
+	prueth->prueth_switchdev_nb.notifier_call = &prueth_switchdev_event;
+	ret = register_switchdev_notifier(&prueth->prueth_switchdev_nb);
+	if (ret) {
+		dev_err(prueth->dev, "register switchdev notifier fail ret:%d\n",
+			ret);
+		return ret;
+	}
+
+	prueth->prueth_switchdev_bl_nb.notifier_call = &prueth_switchdev_blocking_event;
+	ret = register_switchdev_blocking_notifier(&prueth->prueth_switchdev_bl_nb);
+	if (ret) {
+		dev_err(prueth->dev, "register switchdev blocking notifier ret:%d\n",
+			ret);
+		unregister_switchdev_notifier(&prueth->prueth_switchdev_nb);
+	}
+
+	return ret;
+}
+
+void prueth_switchdev_unregister_notifiers(struct prueth *prueth)
+{
+	unregister_switchdev_blocking_notifier(&prueth->prueth_switchdev_bl_nb);
+	unregister_switchdev_notifier(&prueth->prueth_switchdev_nb);
+}
diff --git a/drivers/net/ethernet/ti/icssg/icssg_switchdev.h b/drivers/net/ethernet/ti/icssg/icssg_switchdev.h
new file mode 100644
index 0000000000000..0e64e7760a00a
--- /dev/null
+++ b/drivers/net/ethernet/ti/icssg/icssg_switchdev.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2021 Texas Instruments Incorporated - https://www.ti.com/
+ */
+#ifndef __NET_TI_ICSSG_SWITCHDEV_H
+#define __NET_TI_ICSSG_SWITCHDEV_H
+
+#include "icssg_prueth.h"
+
+int prueth_switchdev_register_notifiers(struct prueth *prueth);
+void prueth_switchdev_unregister_notifiers(struct prueth *prueth);
+bool prueth_dev_check(const struct net_device *ndev);
+
+#endif /* __NET_TI_ICSSG_SWITCHDEV_H */
-- 
GitLab


From abd5576b9c57fbf1ac2421463900061f4d67d96f Mon Sep 17 00:00:00 2001
From: MD Danish Anwar <danishanwar@ti.com>
Date: Tue, 28 May 2024 17:07:34 +0530
Subject: [PATCH 570/950] net: ti: icssg-prueth: Add support for ICSSG switch
 firmware

Add support for ICSSG switch firmware using existing Dual EMAC driver
with switchdev.

Limitations:
VLAN offloading is limited to 0-256 IDs.
MDB/FDB static entries are limited to 511 entries and different FDBs can
hash to same bucket and thus may not completely offloaded

Example assuming ETH1 and ETH2 as ICSSG2 interfaces:

Switch to ICSSG Switch mode:
 ip link add name br0 type bridge
 ip link set dev eth1 master br0
 ip link set dev eth2 master br0
 ip link set dev br0 up
 bridge vlan add dev br0 vid 1 pvid untagged self

Going back to Dual EMAC mode:

 ip link set dev br0 down
 ip link set dev eth1 nomaster
 ip link set dev eth2 nomaster
 ip link del name br0 type bridge

By default, Dual EMAC firmware is loaded, and can be changed to switch
mode by above steps

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: MD Danish Anwar <danishanwar@ti.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/ti/Kconfig               |   1 +
 drivers/net/ethernet/ti/Makefile              |   3 +-
 .../net/ethernet/ti/icssg/icssg_classifier.c  |   2 +-
 drivers/net/ethernet/ti/icssg/icssg_common.c  |   2 +
 drivers/net/ethernet/ti/icssg/icssg_config.c  | 152 +++++++++--
 drivers/net/ethernet/ti/icssg/icssg_config.h  |   7 +
 drivers/net/ethernet/ti/icssg/icssg_prueth.c  | 238 +++++++++++++++++-
 7 files changed, 386 insertions(+), 19 deletions(-)

diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig
index 1729eb0e0b410..f160a3b71499a 100644
--- a/drivers/net/ethernet/ti/Kconfig
+++ b/drivers/net/ethernet/ti/Kconfig
@@ -204,6 +204,7 @@ config TI_ICSSG_PRUETH_SR1
 	select TI_ICSS_IEP
 	select TI_K3_CPPI_DESC_POOL
 	depends on PRU_REMOTEPROC
+	depends on NET_SWITCHDEV
 	depends on ARCH_K3 && OF && TI_K3_UDMA_GLUE_LAYER
 	help
 	  Support dual Gigabit Ethernet ports over the ICSSG PRU Subsystem.
diff --git a/drivers/net/ethernet/ti/Makefile b/drivers/net/ethernet/ti/Makefile
index 6e086b4c0384a..59cd20a38267c 100644
--- a/drivers/net/ethernet/ti/Makefile
+++ b/drivers/net/ethernet/ti/Makefile
@@ -39,7 +39,8 @@ icssg-prueth-y := icssg/icssg_prueth.o \
 		  icssg/icssg_config.o \
 		  icssg/icssg_mii_cfg.o \
 		  icssg/icssg_stats.o \
-		  icssg/icssg_ethtool.o
+		  icssg/icssg_ethtool.o \
+		  icssg/icssg_switchdev.o
 obj-$(CONFIG_TI_ICSSG_PRUETH_SR1) += icssg-prueth-sr1.o
 icssg-prueth-sr1-y := icssg/icssg_prueth_sr1.o \
 		      icssg/icssg_common.o \
diff --git a/drivers/net/ethernet/ti/icssg/icssg_classifier.c b/drivers/net/ethernet/ti/icssg/icssg_classifier.c
index 79ba47bb3602e..8dee737639b60 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_classifier.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_classifier.c
@@ -455,7 +455,7 @@ void icssg_ft1_set_mac_addr(struct regmap *miig_rt, int slice, u8 *mac_addr)
 {
 	const u8 mask_addr[] = { 0, 0, 0, 0, 0, 0, };
 
-	rx_class_ft1_set_start_len(miig_rt, slice, 0, 6);
+	rx_class_ft1_set_start_len(miig_rt, slice, 6, 6);
 	rx_class_ft1_set_da(miig_rt, slice, 0, mac_addr);
 	rx_class_ft1_set_da_mask(miig_rt, slice, 0, mask_addr);
 	rx_class_ft1_cfg_set_type(miig_rt, slice, 0, FT1_CFG_TYPE_EQ);
diff --git a/drivers/net/ethernet/ti/icssg/icssg_common.c b/drivers/net/ethernet/ti/icssg/icssg_common.c
index 088ab8076db47..873126dfc1734 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_common.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_common.c
@@ -581,6 +581,8 @@ static int emac_rx_packet(struct prueth_emac *emac, u32 flow_id)
 	} else {
 		/* send the filled skb up the n/w stack */
 		skb_put(skb, pkt_len);
+		if (emac->prueth->is_switch_mode)
+			skb->offload_fwd_mark = emac->offload_fwd_mark;
 		skb->protocol = eth_type_trans(skb, ndev);
 		napi_gro_receive(&emac->napi_rx, skb);
 		ndev->stats.rx_bytes += pkt_len;
diff --git a/drivers/net/ethernet/ti/icssg/icssg_config.c b/drivers/net/ethernet/ti/icssg/icssg_config.c
index 2213374d4d451..9444e56b76729 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_config.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_config.c
@@ -107,28 +107,49 @@ static const struct map hwq_map[2][ICSSG_NUM_OTHER_QUEUES] = {
 	},
 };
 
+static void icssg_config_mii_init_switch(struct prueth_emac *emac)
+{
+	struct prueth *prueth = emac->prueth;
+	int mii = prueth_emac_slice(emac);
+	u32 txcfg_reg, pcnt_reg, txcfg;
+	struct regmap *mii_rt;
+
+	mii_rt = prueth->mii_rt;
+
+	txcfg_reg = (mii == ICSS_MII0) ? PRUSS_MII_RT_TXCFG0 :
+				       PRUSS_MII_RT_TXCFG1;
+	pcnt_reg = (mii == ICSS_MII0) ? PRUSS_MII_RT_RX_PCNT0 :
+				       PRUSS_MII_RT_RX_PCNT1;
+
+	txcfg = PRUSS_MII_RT_TXCFG_TX_ENABLE |
+		PRUSS_MII_RT_TXCFG_TX_AUTO_PREAMBLE |
+		PRUSS_MII_RT_TXCFG_TX_IPG_WIRE_CLK_EN;
+
+	if (emac->phy_if == PHY_INTERFACE_MODE_MII && mii == ICSS_MII1)
+		txcfg |= PRUSS_MII_RT_TXCFG_TX_MUX_SEL;
+	else if (emac->phy_if != PHY_INTERFACE_MODE_MII && mii == ICSS_MII0)
+		txcfg |= PRUSS_MII_RT_TXCFG_TX_MUX_SEL;
+
+	regmap_write(mii_rt, txcfg_reg, txcfg);
+	regmap_write(mii_rt, pcnt_reg, 0x1);
+}
+
 static void icssg_config_mii_init(struct prueth_emac *emac)
 {
-	u32 rxcfg, txcfg, rxcfg_reg, txcfg_reg, pcnt_reg;
 	struct prueth *prueth = emac->prueth;
 	int slice = prueth_emac_slice(emac);
+	u32 txcfg, txcfg_reg, pcnt_reg;
 	struct regmap *mii_rt;
 
 	mii_rt = prueth->mii_rt;
 
-	rxcfg_reg = (slice == ICSS_MII0) ? PRUSS_MII_RT_RXCFG0 :
-				       PRUSS_MII_RT_RXCFG1;
 	txcfg_reg = (slice == ICSS_MII0) ? PRUSS_MII_RT_TXCFG0 :
 				       PRUSS_MII_RT_TXCFG1;
 	pcnt_reg = (slice == ICSS_MII0) ? PRUSS_MII_RT_RX_PCNT0 :
 				       PRUSS_MII_RT_RX_PCNT1;
 
-	rxcfg = MII_RXCFG_DEFAULT;
 	txcfg = MII_TXCFG_DEFAULT;
 
-	if (slice == ICSS_MII1)
-		rxcfg |= PRUSS_MII_RT_RXCFG_RX_MUX_SEL;
-
 	/* In MII mode TX lines swapped inside ICSSG, so TX_MUX_SEL cfg need
 	 * to be swapped also comparing to RGMII mode.
 	 */
@@ -137,7 +158,6 @@ static void icssg_config_mii_init(struct prueth_emac *emac)
 	else if (emac->phy_if != PHY_INTERFACE_MODE_MII && slice == ICSS_MII1)
 		txcfg |= PRUSS_MII_RT_TXCFG_TX_MUX_SEL;
 
-	regmap_write(mii_rt, rxcfg_reg, rxcfg);
 	regmap_write(mii_rt, txcfg_reg, txcfg);
 	regmap_write(mii_rt, pcnt_reg, 0x1);
 }
@@ -257,6 +277,66 @@ static int emac_r30_is_done(struct prueth_emac *emac)
 	return 1;
 }
 
+static int prueth_switch_buffer_setup(struct prueth_emac *emac)
+{
+	struct icssg_buffer_pool_cfg __iomem *bpool_cfg;
+	struct icssg_rxq_ctx __iomem *rxq_ctx;
+	struct prueth *prueth = emac->prueth;
+	int slice = prueth_emac_slice(emac);
+	u32 addr;
+	int i;
+
+	addr = lower_32_bits(prueth->msmcram.pa);
+	if (slice)
+		addr += PRUETH_NUM_BUF_POOLS * PRUETH_EMAC_BUF_POOL_SIZE;
+
+	if (addr % SZ_64K) {
+		dev_warn(prueth->dev, "buffer pool needs to be 64KB aligned\n");
+		return -EINVAL;
+	}
+
+	bpool_cfg = emac->dram.va + BUFFER_POOL_0_ADDR_OFFSET;
+	/* workaround for f/w bug. bpool 0 needs to be initialized */
+	for (i = 0; i <  PRUETH_NUM_BUF_POOLS; i++) {
+		writel(addr, &bpool_cfg[i].addr);
+		writel(PRUETH_EMAC_BUF_POOL_SIZE, &bpool_cfg[i].len);
+		addr += PRUETH_EMAC_BUF_POOL_SIZE;
+	}
+
+	if (!slice)
+		addr += PRUETH_NUM_BUF_POOLS * PRUETH_EMAC_BUF_POOL_SIZE;
+	else
+		addr += PRUETH_SW_NUM_BUF_POOLS_HOST * PRUETH_SW_BUF_POOL_SIZE_HOST;
+
+	for (i = PRUETH_NUM_BUF_POOLS;
+	     i < 2 * PRUETH_SW_NUM_BUF_POOLS_HOST + PRUETH_NUM_BUF_POOLS;
+	     i++) {
+		/* The driver only uses first 4 queues per PRU so only initialize them */
+		if (i % PRUETH_SW_NUM_BUF_POOLS_HOST < PRUETH_SW_NUM_BUF_POOLS_PER_PRU) {
+			writel(addr, &bpool_cfg[i].addr);
+			writel(PRUETH_SW_BUF_POOL_SIZE_HOST, &bpool_cfg[i].len);
+			addr += PRUETH_SW_BUF_POOL_SIZE_HOST;
+		} else {
+			writel(0, &bpool_cfg[i].addr);
+			writel(0, &bpool_cfg[i].len);
+		}
+	}
+
+	if (!slice)
+		addr += PRUETH_SW_NUM_BUF_POOLS_HOST * PRUETH_SW_BUF_POOL_SIZE_HOST;
+	else
+		addr += PRUETH_EMAC_RX_CTX_BUF_SIZE;
+
+	rxq_ctx = emac->dram.va + HOST_RX_Q_PRE_CONTEXT_OFFSET;
+	for (i = 0; i < 3; i++)
+		writel(addr, &rxq_ctx->start[i]);
+
+	addr += PRUETH_EMAC_RX_CTX_BUF_SIZE;
+	writel(addr - SZ_2K, &rxq_ctx->end);
+
+	return 0;
+}
+
 static int prueth_emac_buffer_setup(struct prueth_emac *emac)
 {
 	struct icssg_buffer_pool_cfg __iomem *bpool_cfg;
@@ -321,25 +401,63 @@ static void icssg_init_emac_mode(struct prueth *prueth)
 	/* When the device is configured as a bridge and it is being brought
 	 * back to the emac mode, the host mac address has to be set as 0.
 	 */
+	u32 addr = prueth->shram.pa + EMAC_ICSSG_SWITCH_DEFAULT_VLAN_TABLE_OFFSET;
+	int i;
 	u8 mac[ETH_ALEN] = { 0 };
 
 	if (prueth->emacs_initialized)
 		return;
 
-	regmap_update_bits(prueth->miig_rt, FDB_GEN_CFG1,
-			   SMEM_VLAN_OFFSET_MASK, 0);
-	regmap_write(prueth->miig_rt, FDB_GEN_CFG2, 0);
+	/* Set VLAN TABLE address base */
+	regmap_update_bits(prueth->miig_rt, FDB_GEN_CFG1, SMEM_VLAN_OFFSET_MASK,
+			   addr <<  SMEM_VLAN_OFFSET);
+	/* Set enable VLAN aware mode, and FDBs for all PRUs */
+	regmap_write(prueth->miig_rt, FDB_GEN_CFG2, (FDB_PRU0_EN | FDB_PRU1_EN | FDB_HOST_EN));
+	prueth->vlan_tbl = (struct prueth_vlan_tbl __force *)(prueth->shram.va +
+			    EMAC_ICSSG_SWITCH_DEFAULT_VLAN_TABLE_OFFSET);
+	for (i = 0; i < SZ_4K - 1; i++) {
+		prueth->vlan_tbl[i].fid = i;
+		prueth->vlan_tbl[i].fid_c1 = 0;
+	}
 	/* Clear host MAC address */
 	icssg_class_set_host_mac_addr(prueth->miig_rt, mac);
 }
 
+static void icssg_init_switch_mode(struct prueth *prueth)
+{
+	u32 addr = prueth->shram.pa + EMAC_ICSSG_SWITCH_DEFAULT_VLAN_TABLE_OFFSET;
+	int i;
+
+	if (prueth->emacs_initialized)
+		return;
+
+	/* Set VLAN TABLE address base */
+	regmap_update_bits(prueth->miig_rt, FDB_GEN_CFG1, SMEM_VLAN_OFFSET_MASK,
+			   addr <<  SMEM_VLAN_OFFSET);
+	/* Set enable VLAN aware mode, and FDBs for all PRUs */
+	regmap_write(prueth->miig_rt, FDB_GEN_CFG2, FDB_EN_ALL);
+	prueth->vlan_tbl = (struct prueth_vlan_tbl __force *)(prueth->shram.va +
+			    EMAC_ICSSG_SWITCH_DEFAULT_VLAN_TABLE_OFFSET);
+	for (i = 0; i < SZ_4K - 1; i++) {
+		prueth->vlan_tbl[i].fid = i;
+		prueth->vlan_tbl[i].fid_c1 = 0;
+	}
+
+	if (prueth->hw_bridge_dev)
+		icssg_class_set_host_mac_addr(prueth->miig_rt, prueth->hw_bridge_dev->dev_addr);
+	icssg_set_pvid(prueth, prueth->default_vlan, PRUETH_PORT_HOST);
+}
+
 int icssg_config(struct prueth *prueth, struct prueth_emac *emac, int slice)
 {
 	void __iomem *config = emac->dram.va + ICSSG_CONFIG_OFFSET;
 	struct icssg_flow_cfg __iomem *flow_cfg;
 	int ret;
 
-	icssg_init_emac_mode(prueth);
+	if (prueth->is_switch_mode)
+		icssg_init_switch_mode(prueth);
+	else
+		icssg_init_emac_mode(prueth);
 
 	memset_io(config, 0, TAS_GATE_MASK_LIST0);
 	icssg_miig_queues_init(prueth, slice);
@@ -353,7 +471,10 @@ int icssg_config(struct prueth *prueth, struct prueth_emac *emac, int slice)
 	regmap_update_bits(prueth->miig_rt, ICSSG_CFG_OFFSET,
 			   ICSSG_CFG_DEFAULT, ICSSG_CFG_DEFAULT);
 	icssg_miig_set_interface_mode(prueth->miig_rt, slice, emac->phy_if);
-	icssg_config_mii_init(emac);
+	if (prueth->is_switch_mode)
+		icssg_config_mii_init_switch(emac);
+	else
+		icssg_config_mii_init(emac);
 	icssg_config_ipg(emac);
 	icssg_update_rgmii_cfg(prueth->miig_rt, emac);
 
@@ -376,7 +497,10 @@ int icssg_config(struct prueth *prueth, struct prueth_emac *emac, int slice)
 	writeb(0, config + SPL_PKT_DEFAULT_PRIORITY);
 	writeb(0, config + QUEUE_NUM_UNTAGGED);
 
-	ret = prueth_emac_buffer_setup(emac);
+	if (prueth->is_switch_mode)
+		ret = prueth_switch_buffer_setup(emac);
+	else
+		ret = prueth_emac_buffer_setup(emac);
 	if (ret)
 		return ret;
 
diff --git a/drivers/net/ethernet/ti/icssg/icssg_config.h b/drivers/net/ethernet/ti/icssg/icssg_config.h
index 4a9721aa60577..1ac60283923bd 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_config.h
+++ b/drivers/net/ethernet/ti/icssg/icssg_config.h
@@ -35,6 +35,13 @@ struct icssg_flow_cfg {
 	(2 * (PRUETH_EMAC_BUF_POOL_SIZE * PRUETH_NUM_BUF_POOLS + \
 	 PRUETH_EMAC_RX_CTX_BUF_SIZE * 2))
 
+#define PRUETH_SW_BUF_POOL_SIZE_HOST	SZ_4K
+#define PRUETH_SW_NUM_BUF_POOLS_HOST	8
+#define PRUETH_SW_NUM_BUF_POOLS_PER_PRU 4
+#define MSMC_RAM_SIZE_SWITCH_MODE \
+	(MSMC_RAM_SIZE + \
+	(2 * PRUETH_SW_BUF_POOL_SIZE_HOST * PRUETH_SW_NUM_BUF_POOLS_HOST))
+
 #define PRUETH_SWITCH_FDB_MASK ((SIZE_OF_FDB / NUMBER_OF_FDB_BUCKET_ENTRIES) - 1)
 
 struct icssg_rxq_ctx {
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
index 1db67a8107cc1..6e65aa0977d40 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
@@ -27,6 +27,7 @@
 #include <linux/remoteproc/pruss.h>
 #include <linux/regmap.h>
 #include <linux/remoteproc.h>
+#include <net/switchdev.h>
 
 #include "icssg_prueth.h"
 #include "icssg_mii_rt.h"
@@ -35,6 +36,10 @@
 
 #define PRUETH_MODULE_DESCRIPTION "PRUSS ICSSG Ethernet driver"
 
+#define DEFAULT_VID		1
+#define DEFAULT_PORT_MASK	1
+#define DEFAULT_UNTAG_MASK	1
+
 /* CTRLMMR_ICSSG_RGMII_CTRL register bits */
 #define ICSSG_CTRL_RGMII_ID_MODE                BIT(24)
 
@@ -113,6 +118,19 @@ static irqreturn_t prueth_tx_ts_irq(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
+static struct icssg_firmwares icssg_switch_firmwares[] = {
+	{
+		.pru = "ti-pruss/am65x-sr2-pru0-prusw-fw.elf",
+		.rtu = "ti-pruss/am65x-sr2-rtu0-prusw-fw.elf",
+		.txpru = "ti-pruss/am65x-sr2-txpru0-prusw-fw.elf",
+	},
+	{
+		.pru = "ti-pruss/am65x-sr2-pru1-prusw-fw.elf",
+		.rtu = "ti-pruss/am65x-sr2-rtu1-prusw-fw.elf",
+		.txpru = "ti-pruss/am65x-sr2-txpru1-prusw-fw.elf",
+	}
+};
+
 static struct icssg_firmwares icssg_emac_firmwares[] = {
 	{
 		.pru = "ti-pruss/am65x-sr2-pru0-prueth-fw.elf",
@@ -132,7 +150,10 @@ static int prueth_emac_start(struct prueth *prueth, struct prueth_emac *emac)
 	struct device *dev = prueth->dev;
 	int slice, ret;
 
-	firmwares = icssg_emac_firmwares;
+	if (prueth->is_switch_mode)
+		firmwares = icssg_switch_firmwares;
+	else
+		firmwares = icssg_emac_firmwares;
 
 	slice = prueth_emac_slice(emac);
 	if (slice < 0) {
@@ -446,9 +467,8 @@ static int emac_ndo_open(struct net_device *ndev)
 	ether_addr_copy(emac->mac_addr, ndev->dev_addr);
 
 	icssg_class_set_mac_addr(prueth->miig_rt, slice, emac->mac_addr);
-	icssg_ft1_set_mac_addr(prueth->miig_rt, slice, emac->mac_addr);
-
 	icssg_class_default(prueth->miig_rt, slice, 0, false);
+	icssg_ft1_set_mac_addr(prueth->miig_rt, slice, emac->mac_addr);
 
 	/* Notify the stack of the actual queue counts. */
 	ret = netif_set_real_num_tx_queues(ndev, num_data_chn);
@@ -845,6 +865,203 @@ bool prueth_dev_check(const struct net_device *ndev)
 	return false;
 }
 
+static void prueth_offload_fwd_mark_update(struct prueth *prueth)
+{
+	int set_val = 0;
+	int i;
+
+	if (prueth->br_members == (BIT(PRUETH_PORT_MII0) | BIT(PRUETH_PORT_MII1)))
+		set_val = 1;
+
+	dev_dbg(prueth->dev, "set offload_fwd_mark %d\n", set_val);
+
+	for (i = PRUETH_MAC0; i < PRUETH_NUM_MACS; i++) {
+		struct prueth_emac *emac = prueth->emac[i];
+
+		if (!emac || !emac->ndev)
+			continue;
+
+		emac->offload_fwd_mark = set_val;
+	}
+}
+
+static void prueth_emac_restart(struct prueth *prueth)
+{
+	struct prueth_emac *emac0 = prueth->emac[PRUETH_MAC0];
+	struct prueth_emac *emac1 = prueth->emac[PRUETH_MAC1];
+
+	/* Detach the net_device for both PRUeth ports*/
+	if (netif_running(emac0->ndev))
+		netif_device_detach(emac0->ndev);
+	if (netif_running(emac1->ndev))
+		netif_device_detach(emac1->ndev);
+
+	/* Disable both PRUeth ports */
+	emac_set_port_state(emac0, ICSSG_EMAC_PORT_DISABLE);
+	emac_set_port_state(emac1, ICSSG_EMAC_PORT_DISABLE);
+
+	/* Stop both pru cores for both PRUeth ports*/
+	prueth_emac_stop(emac0);
+	prueth->emacs_initialized--;
+	prueth_emac_stop(emac1);
+	prueth->emacs_initialized--;
+
+	/* Start both pru cores for both PRUeth ports */
+	prueth_emac_start(prueth, emac0);
+	prueth->emacs_initialized++;
+	prueth_emac_start(prueth, emac1);
+	prueth->emacs_initialized++;
+
+	/* Enable forwarding for both PRUeth ports */
+	emac_set_port_state(emac0, ICSSG_EMAC_PORT_FORWARD);
+	emac_set_port_state(emac1, ICSSG_EMAC_PORT_FORWARD);
+
+	/* Attache net_device for both PRUeth ports */
+	netif_device_attach(emac0->ndev);
+	netif_device_attach(emac1->ndev);
+}
+
+static void icssg_enable_switch_mode(struct prueth *prueth)
+{
+	struct prueth_emac *emac;
+	int mac;
+
+	prueth_emac_restart(prueth);
+
+	for (mac = PRUETH_MAC0; mac < PRUETH_NUM_MACS; mac++) {
+		emac = prueth->emac[mac];
+		if (netif_running(emac->ndev)) {
+			icssg_fdb_add_del(emac, eth_stp_addr, prueth->default_vlan,
+					  ICSSG_FDB_ENTRY_P0_MEMBERSHIP |
+					  ICSSG_FDB_ENTRY_P1_MEMBERSHIP |
+					  ICSSG_FDB_ENTRY_P2_MEMBERSHIP |
+					  ICSSG_FDB_ENTRY_BLOCK,
+					  true);
+			icssg_vtbl_modify(emac, emac->port_vlan | DEFAULT_VID,
+					  BIT(emac->port_id) | DEFAULT_PORT_MASK,
+					  BIT(emac->port_id) | DEFAULT_UNTAG_MASK,
+					  true);
+			icssg_set_pvid(prueth, emac->port_vlan, emac->port_id);
+			emac_set_port_state(emac, ICSSG_EMAC_PORT_VLAN_AWARE_ENABLE);
+		}
+	}
+}
+
+static int prueth_netdevice_port_link(struct net_device *ndev,
+				      struct net_device *br_ndev,
+				      struct netlink_ext_ack *extack)
+{
+	struct prueth_emac *emac = netdev_priv(ndev);
+	struct prueth *prueth = emac->prueth;
+	int err;
+
+	if (!prueth->br_members) {
+		prueth->hw_bridge_dev = br_ndev;
+	} else {
+		/* This is adding the port to a second bridge, this is
+		 * unsupported
+		 */
+		if (prueth->hw_bridge_dev != br_ndev)
+			return -EOPNOTSUPP;
+	}
+
+	err = switchdev_bridge_port_offload(br_ndev, ndev, emac,
+					    &prueth->prueth_switchdev_nb,
+					    &prueth->prueth_switchdev_bl_nb,
+					    false, extack);
+	if (err)
+		return err;
+
+	prueth->br_members |= BIT(emac->port_id);
+
+	if (!prueth->is_switch_mode) {
+		if (prueth->br_members & BIT(PRUETH_PORT_MII0) &&
+		    prueth->br_members & BIT(PRUETH_PORT_MII1)) {
+			prueth->is_switch_mode = true;
+			prueth->default_vlan = 1;
+			emac->port_vlan = prueth->default_vlan;
+			icssg_enable_switch_mode(prueth);
+		}
+	}
+
+	prueth_offload_fwd_mark_update(prueth);
+
+	return NOTIFY_DONE;
+}
+
+static void prueth_netdevice_port_unlink(struct net_device *ndev)
+{
+	struct prueth_emac *emac = netdev_priv(ndev);
+	struct prueth *prueth = emac->prueth;
+
+	prueth->br_members &= ~BIT(emac->port_id);
+
+	if (prueth->is_switch_mode) {
+		prueth->is_switch_mode = false;
+		emac->port_vlan = 0;
+		prueth_emac_restart(prueth);
+	}
+
+	prueth_offload_fwd_mark_update(prueth);
+
+	if (!prueth->br_members)
+		prueth->hw_bridge_dev = NULL;
+}
+
+/* netdev notifier */
+static int prueth_netdevice_event(struct notifier_block *unused,
+				  unsigned long event, void *ptr)
+{
+	struct netlink_ext_ack *extack = netdev_notifier_info_to_extack(ptr);
+	struct net_device *ndev = netdev_notifier_info_to_dev(ptr);
+	struct netdev_notifier_changeupper_info *info;
+	int ret = NOTIFY_DONE;
+
+	if (ndev->netdev_ops != &emac_netdev_ops)
+		return NOTIFY_DONE;
+
+	switch (event) {
+	case NETDEV_CHANGEUPPER:
+		info = ptr;
+
+		if (netif_is_bridge_master(info->upper_dev)) {
+			if (info->linking)
+				ret = prueth_netdevice_port_link(ndev, info->upper_dev, extack);
+			else
+				prueth_netdevice_port_unlink(ndev);
+		}
+		break;
+	default:
+		return NOTIFY_DONE;
+	}
+
+	return notifier_from_errno(ret);
+}
+
+static int prueth_register_notifiers(struct prueth *prueth)
+{
+	int ret = 0;
+
+	prueth->prueth_netdevice_nb.notifier_call = &prueth_netdevice_event;
+	ret = register_netdevice_notifier(&prueth->prueth_netdevice_nb);
+	if (ret) {
+		dev_err(prueth->dev, "can't register netdevice notifier\n");
+		return ret;
+	}
+
+	ret = prueth_switchdev_register_notifiers(prueth);
+	if (ret)
+		unregister_netdevice_notifier(&prueth->prueth_netdevice_nb);
+
+	return ret;
+}
+
+static void prueth_unregister_notifiers(struct prueth *prueth)
+{
+	prueth_switchdev_unregister_notifiers(prueth);
+	unregister_netdevice_notifier(&prueth->prueth_netdevice_nb);
+}
+
 static int prueth_probe(struct platform_device *pdev)
 {
 	struct device_node *eth_node, *eth_ports_node;
@@ -972,6 +1189,9 @@ static int prueth_probe(struct platform_device *pdev)
 	}
 
 	msmc_ram_size = MSMC_RAM_SIZE;
+	prueth->is_switchmode_supported = prueth->pdata.switch_mode;
+	if (prueth->is_switchmode_supported)
+		msmc_ram_size = MSMC_RAM_SIZE_SWITCH_MODE;
 
 	/* NOTE: FW bug needs buffer base to be 64KB aligned */
 	prueth->msmcram.va =
@@ -1077,6 +1297,14 @@ static int prueth_probe(struct platform_device *pdev)
 		phy_attached_info(prueth->emac[PRUETH_MAC1]->ndev->phydev);
 	}
 
+	if (prueth->is_switchmode_supported) {
+		ret = prueth_register_notifiers(prueth);
+		if (ret)
+			goto netdev_unregister;
+
+		sprintf(prueth->switch_id, "%s", dev_name(dev));
+	}
+
 	dev_info(dev, "TI PRU ethernet driver initialized: %s EMAC mode\n",
 		 (!eth0_node || !eth1_node) ? "single" : "dual");
 
@@ -1146,6 +1374,8 @@ static void prueth_remove(struct platform_device *pdev)
 	struct device_node *eth_node;
 	int i;
 
+	prueth_unregister_notifiers(prueth);
+
 	for (i = 0; i < PRUETH_NUM_MACS; i++) {
 		if (!prueth->registered_netdevs[i])
 			continue;
@@ -1187,10 +1417,12 @@ static void prueth_remove(struct platform_device *pdev)
 static const struct prueth_pdata am654_icssg_pdata = {
 	.fdqring_mode = K3_RINGACC_RING_MODE_MESSAGE,
 	.quirk_10m_link_issue = 1,
+	.switch_mode = 1,
 };
 
 static const struct prueth_pdata am64x_icssg_pdata = {
 	.fdqring_mode = K3_RINGACC_RING_MODE_RING,
+	.switch_mode = 1,
 };
 
 static const struct of_device_id prueth_dt_match[] = {
-- 
GitLab


From 34bf6bae3286a58762711cfbce2cf74ecd42e1b5 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 28 May 2024 22:21:31 +0200
Subject: [PATCH 571/950] x86/topology/amd: Evaluate SMT in CPUID leaf
 0x8000001e only on family 0x17 and greater

The new AMD/HYGON topology parser evaluates the SMT information in CPUID leaf
0x8000001e unconditionally while the original code restricted it to CPUs with
family 0x17 and greater.

This breaks family 0x15 CPUs which advertise that leaf and have a non-zero
value in the SMT section. The machine boots, but the scheduler complains loudly
about the mismatch of the core IDs:

  WARNING: CPU: 1 PID: 0 at kernel/sched/core.c:6482 sched_cpu_starting+0x183/0x250
  WARNING: CPU: 0 PID: 1 at kernel/sched/topology.c:2408 build_sched_domains+0x76b/0x12b0

Add the condition back to cure it.

  [ bp: Make it actually build because grandpa is not concerned with
    trivial stuff. :-P ]

Fixes: f7fb3b2dd92c ("x86/cpu: Provide an AMD/HYGON specific topology parser")
Closes: https://gitlab.archlinux.org/archlinux/packaging/packages/linux/-/issues/56
Reported-by: Tim Teichmann <teichmanntim@outlook.de>
Reported-by: Christian Heusel <christian@heusel.eu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Tested-by: Tim Teichmann <teichmanntim@outlook.de>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/7skhx6mwe4hxiul64v6azhlxnokheorksqsdbp7qw6g2jduf6c@7b5pvomauugk
---
 arch/x86/kernel/cpu/topology_amd.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/cpu/topology_amd.c b/arch/x86/kernel/cpu/topology_amd.c
index d419deed6a488..7d476fa697ca5 100644
--- a/arch/x86/kernel/cpu/topology_amd.c
+++ b/arch/x86/kernel/cpu/topology_amd.c
@@ -84,9 +84,9 @@ static bool parse_8000_001e(struct topo_scan *tscan, bool has_topoext)
 
 	/*
 	 * If leaf 0xb is available, then the domain shifts are set
-	 * already and nothing to do here.
+	 * already and nothing to do here. Only valid for family >= 0x17.
 	 */
-	if (!has_topoext) {
+	if (!has_topoext && tscan->c->x86 >= 0x17) {
 		/*
 		 * Leaf 0x80000008 set the CORE domain shift already.
 		 * Update the SMT domain, but do not propagate it.
-- 
GitLab


From e112311615a24e1618a591c73506571dc304eb8d Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Thu, 30 May 2024 07:23:39 -0700
Subject: [PATCH 572/950] io_uring/rw: Free iovec before cleaning async data

kmemleak shows that there is a memory leak in io_uring read operation,
where a buffer is allocated at iovec import, but never de-allocated.

The memory is allocated at io_async_rw->free_iovec, but, then
io_async_rw is kfreed, taking the allocated memory with it. I saw this
happening when the read operation fails with -11 (EAGAIN).

This is the kmemleak splat.

    unreferenced object 0xffff8881da591c00 (size 256):
...
      backtrace (crc 7a15bdee):
	[<00000000256f2de4>] __kmalloc+0x2d6/0x410
	[<000000007a9f5fc7>] iovec_from_user.part.0+0xc6/0x160
	[<00000000cecdf83a>] __import_iovec+0x50/0x220
	[<00000000d1d586a2>] __io_import_iovec+0x13d/0x220
	[<0000000054ee9bd2>] io_prep_rw+0x186/0x340
	[<00000000a9c0372d>] io_prep_rwv+0x31/0x120
	[<000000001d1170b9>] io_prep_readv+0xe/0x30
	[<0000000070b8eb67>] io_submit_sqes+0x1bd/0x780
	[<00000000812496d4>] __do_sys_io_uring_enter+0x3ed/0x5b0
	[<0000000081499602>] do_syscall_64+0x5d/0x170
	[<00000000de1c5a4d>] entry_SYSCALL_64_after_hwframe+0x76/0x7e

This occurs because the async data cleanup functions are not set for
read/write operations. As a result, the potentially allocated iovec in
the rw async data is not freed before the async data is released,
leading to a memory leak.

With this following patch, kmemleak does not show the leaked memory
anymore, and all liburing tests pass.

Fixes: a9165b83c193 ("io_uring/rw: always setup io_async_rw for read/write requests")
Signed-off-by: Breno Leitao <leitao@debian.org>
Link: https://lore.kernel.org/r/20240530142340.1248216-1-leitao@debian.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/opdef.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/io_uring/opdef.c b/io_uring/opdef.c
index 2de5cca9504eb..2e3b7b16effb3 100644
--- a/io_uring/opdef.c
+++ b/io_uring/opdef.c
@@ -516,10 +516,12 @@ const struct io_cold_def io_cold_defs[] = {
 	},
 	[IORING_OP_READ_FIXED] = {
 		.name			= "READ_FIXED",
+		.cleanup		= io_readv_writev_cleanup,
 		.fail			= io_rw_fail,
 	},
 	[IORING_OP_WRITE_FIXED] = {
 		.name			= "WRITE_FIXED",
+		.cleanup		= io_readv_writev_cleanup,
 		.fail			= io_rw_fail,
 	},
 	[IORING_OP_POLL_ADD] = {
@@ -582,10 +584,12 @@ const struct io_cold_def io_cold_defs[] = {
 	},
 	[IORING_OP_READ] = {
 		.name			= "READ",
+		.cleanup		= io_readv_writev_cleanup,
 		.fail			= io_rw_fail,
 	},
 	[IORING_OP_WRITE] = {
 		.name			= "WRITE",
+		.cleanup		= io_readv_writev_cleanup,
 		.fail			= io_rw_fail,
 	},
 	[IORING_OP_FADVISE] = {
@@ -692,6 +696,7 @@ const struct io_cold_def io_cold_defs[] = {
 	},
 	[IORING_OP_READ_MULTISHOT] = {
 		.name			= "READ_MULTISHOT",
+		.cleanup		= io_readv_writev_cleanup,
 	},
 	[IORING_OP_WAITID] = {
 		.name			= "WAITID",
-- 
GitLab


From 2a38e4ca302280fdcce370ba2bee79bac16c4587 Mon Sep 17 00:00:00 2001
From: Dave Hansen <dave.hansen@linux.intel.com>
Date: Fri, 17 May 2024 13:05:34 -0700
Subject: [PATCH 573/950] x86/cpu: Provide default cache line size if not
 enumerated
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

tl;dr: CPUs with CPUID.80000008H but without CPUID.01H:EDX[CLFSH]
will end up reporting cache_line_size()==0 and bad things happen.
Fill in a default on those to avoid the problem.

Long Story:

The kernel dies a horrible death if c->x86_cache_alignment (aka.
cache_line_size() is 0.  Normally, this value is populated from
c->x86_clflush_size.

Right now the code is set up to get c->x86_clflush_size from two
places.  First, modern CPUs get it from CPUID.  Old CPUs that don't
have leaf 0x80000008 (or CPUID at all) just get some sane defaults
from the kernel in get_cpu_address_sizes().

The vast majority of CPUs that have leaf 0x80000008 also get
->x86_clflush_size from CPUID.  But there are oddballs.

Intel Quark CPUs[1] and others[2] have leaf 0x80000008 but don't set
CPUID.01H:EDX[CLFSH], so they skip over filling in ->x86_clflush_size:

	cpuid(0x00000001, &tfms, &misc, &junk, &cap0);
	if (cap0 & (1<<19))
		c->x86_clflush_size = ((misc >> 8) & 0xff) * 8;

So they: land in get_cpu_address_sizes() and see that CPUID has level
0x80000008 and jump into the side of the if() that does not fill in
c->x86_clflush_size.  That assigns a 0 to c->x86_cache_alignment, and
hilarity ensues in code like:

        buffer = kzalloc(ALIGN(sizeof(*buffer), cache_line_size()),
                         GFP_KERNEL);

To fix this, always provide a sane value for ->x86_clflush_size.

Big thanks to Andy Shevchenko for finding and reporting this and also
providing a first pass at a fix. But his fix was only partial and only
worked on the Quark CPUs.  It would not, for instance, have worked on
the QEMU config.

1. https://raw.githubusercontent.com/InstLatx64/InstLatx64/master/GenuineIntel/GenuineIntel0000590_Clanton_03_CPUID.txt
2. You can also get this behavior if you use "-cpu 486,+clzero"
   in QEMU.

[ dhansen: remove 'vp_bits_from_cpuid' reference in changelog
	   because bpetkov brutally murdered it recently. ]

Fixes: fbf6449f84bf ("x86/sev-es: Set x86_virt_bits to the correct value straight away, instead of a two-phase approach")
Reported-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Tested-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Tested-by: Jörn Heusipp <osmanx@heusipp.de>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/all/20240516173928.3960193-1-andriy.shevchenko@linux.intel.com/
Link: https://lore.kernel.org/lkml/5e31cad3-ad4d-493e-ab07-724cfbfaba44@heusipp.de/
Link: https://lore.kernel.org/all/20240517200534.8EC5F33E%40davehans-spike.ostc.intel.com
---
 arch/x86/kernel/cpu/common.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 2b170da84f97f..e31293c9609f5 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1075,6 +1075,10 @@ void get_cpu_address_sizes(struct cpuinfo_x86 *c)
 
 		c->x86_virt_bits = (eax >> 8) & 0xff;
 		c->x86_phys_bits = eax & 0xff;
+
+		/* Provide a sane default if not enumerated: */
+		if (!c->x86_clflush_size)
+			c->x86_clflush_size = 32;
 	}
 
 	c->x86_cache_bits = c->x86_phys_bits;
-- 
GitLab


From 3d60041543189438cd1b03a1fa40ff6681c77970 Mon Sep 17 00:00:00 2001
From: Baochen Qiang <quic_bqiang@quicinc.com>
Date: Sun, 26 May 2024 20:42:26 +0800
Subject: [PATCH 574/950] wifi: ath12k: fix memory leak in
 ath12k_dp_rx_peer_frag_setup()

Currently the resource allocated by crypto_alloc_shash() is not
freed in case ath12k_peer_find() fails, resulting in memory leak.

Add crypto_free_shash() to fix it.

This is found during code review, compile tested only.

Signed-off-by: Baochen Qiang <quic_bqiang@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240526124226.24661-1-quic_bqiang@quicinc.com
---
 drivers/net/wireless/ath/ath12k/dp_rx.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/ath/ath12k/dp_rx.c b/drivers/net/wireless/ath/ath12k/dp_rx.c
index a52b7b273540f..cb1f308f096b1 100644
--- a/drivers/net/wireless/ath/ath12k/dp_rx.c
+++ b/drivers/net/wireless/ath/ath12k/dp_rx.c
@@ -2742,6 +2742,7 @@ int ath12k_dp_rx_peer_frag_setup(struct ath12k *ar, const u8 *peer_mac, int vdev
 	peer = ath12k_peer_find(ab, vdev_id, peer_mac);
 	if (!peer) {
 		spin_unlock_bh(&ab->base_lock);
+		crypto_free_shash(tfm);
 		ath12k_warn(ab, "failed to find the peer to set up fragment info\n");
 		return -ENOENT;
 	}
-- 
GitLab


From 43e934360d1d8fd3230d0c1ffa40f0d49deb4cf2 Mon Sep 17 00:00:00 2001
From: "Rob Herring (Arm)" <robh@kernel.org>
Date: Tue, 28 May 2024 08:46:09 -0500
Subject: [PATCH 575/950] dt-bindings: net: wireless: ath11k: Drop
 "qcom,ipq8074-wcss-pil" from example

Convention for examples is to only show what's covered by the binding,
so drop the provider "qcom,ipq8074-wcss-pil". It is also not documented
by a schema which caused a warning.

Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240528134610.4075204-1-robh@kernel.org
---
 .../devicetree/bindings/net/wireless/qcom,ath11k.yaml    | 9 ---------
 1 file changed, 9 deletions(-)

diff --git a/Documentation/devicetree/bindings/net/wireless/qcom,ath11k.yaml b/Documentation/devicetree/bindings/net/wireless/qcom,ath11k.yaml
index a2d55bf4c7a51..ff5763dc66a88 100644
--- a/Documentation/devicetree/bindings/net/wireless/qcom,ath11k.yaml
+++ b/Documentation/devicetree/bindings/net/wireless/qcom,ath11k.yaml
@@ -265,15 +265,6 @@ allOf:
 
 examples:
   - |
-
-    q6v5_wcss: remoteproc@cd00000 {
-        compatible = "qcom,ipq8074-wcss-pil";
-        reg = <0xcd00000 0x4040>,
-              <0x4ab000 0x20>;
-        reg-names = "qdsp6",
-                    "rmb";
-    };
-
     wifi0: wifi@c000000 {
         compatible = "qcom,ipq8074-wifi";
         reg = <0xc000000 0x2000000>;
-- 
GitLab


From 8233d2716570b66ab45b6d24e577ee6612002dc4 Mon Sep 17 00:00:00 2001
From: Baochen Qiang <quic_bqiang@quicinc.com>
Date: Wed, 29 May 2024 09:53:57 +0800
Subject: [PATCH 576/950] wifi: ath12k: do not process consecutive RDDM event

Currently we do reset for each RDDM event from MHI, however there are
cases, see below log, that we get two or more consecutive events, and
it is pointless to do reset for the subsequent ones. What's more, it
makes reset process more likely to fail.

[  103.289864] mhi mhi0: System error detected
[  103.289871] ath12k_pci 0000:03:00.0: mhi notify status reason MHI_CB_EE_RDDM
[  103.293144] mhi mhi0: System error detected
[  103.293150] ath12k_pci 0000:03:00.0: mhi notify status reason MHI_CB_EE_RDDM

Add a check to avoid reset again and again. This is done by tracking previous
MHI status: if we receive a new RDDM event while the previous event is
also the same, we treat it as duplicate and ignore it, because normally
we should at least receive a MHI_CB_EE_MISSION_MODE event between them.

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Signed-off-by: Baochen Qiang <quic_bqiang@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240529015357.9846-1-quic_bqiang@quicinc.com
---
 drivers/net/wireless/ath/ath12k/mhi.c | 11 +++++++++++
 drivers/net/wireless/ath/ath12k/pci.h |  1 +
 2 files changed, 12 insertions(+)

diff --git a/drivers/net/wireless/ath/ath12k/mhi.c b/drivers/net/wireless/ath/ath12k/mhi.c
index fef2f76220336..df96b0f91f54c 100644
--- a/drivers/net/wireless/ath/ath12k/mhi.c
+++ b/drivers/net/wireless/ath/ath12k/mhi.c
@@ -16,6 +16,7 @@
 #define MHI_TIMEOUT_DEFAULT_MS	90000
 #define OTP_INVALID_BOARD_ID	0xFFFF
 #define OTP_VALID_DUALMAC_BOARD_ID_MASK		0x1000
+#define MHI_CB_INVALID	0xff
 
 static const struct mhi_channel_config ath12k_mhi_channels_qcn9274[] = {
 	{
@@ -268,6 +269,7 @@ static void ath12k_mhi_op_status_cb(struct mhi_controller *mhi_cntrl,
 				    enum mhi_callback cb)
 {
 	struct ath12k_base *ab = dev_get_drvdata(mhi_cntrl->cntrl_dev);
+	struct ath12k_pci *ab_pci = ath12k_pci_priv(ab);
 
 	ath12k_dbg(ab, ATH12K_DBG_BOOT, "mhi notify status reason %s\n",
 		   ath12k_mhi_op_callback_to_str(cb));
@@ -277,12 +279,20 @@ static void ath12k_mhi_op_status_cb(struct mhi_controller *mhi_cntrl,
 		ath12k_warn(ab, "firmware crashed: MHI_CB_SYS_ERROR\n");
 		break;
 	case MHI_CB_EE_RDDM:
+		if (ab_pci->mhi_pre_cb == MHI_CB_EE_RDDM) {
+			ath12k_dbg(ab, ATH12K_DBG_BOOT,
+				   "do not queue again for consecutive RDDM event\n");
+			break;
+		}
+
 		if (!(test_bit(ATH12K_FLAG_UNREGISTERING, &ab->dev_flags)))
 			queue_work(ab->workqueue_aux, &ab->reset_work);
 		break;
 	default:
 		break;
 	}
+
+	ab_pci->mhi_pre_cb = cb;
 }
 
 static int ath12k_mhi_op_read_reg(struct mhi_controller *mhi_cntrl,
@@ -313,6 +323,7 @@ int ath12k_mhi_register(struct ath12k_pci *ab_pci)
 	if (!mhi_ctrl)
 		return -ENOMEM;
 
+	ab_pci->mhi_pre_cb = MHI_CB_INVALID;
 	ab_pci->mhi_ctrl = mhi_ctrl;
 	mhi_ctrl->cntrl_dev = ab->dev;
 	mhi_ctrl->regs = ab->mem;
diff --git a/drivers/net/wireless/ath/ath12k/pci.h b/drivers/net/wireless/ath/ath12k/pci.h
index 6186a78038cf6..31584a7ad80eb 100644
--- a/drivers/net/wireless/ath/ath12k/pci.h
+++ b/drivers/net/wireless/ath/ath12k/pci.h
@@ -104,6 +104,7 @@ struct ath12k_pci {
 	struct mhi_controller *mhi_ctrl;
 	const struct ath12k_msi_config *msi_config;
 	unsigned long mhi_state;
+	enum mhi_callback mhi_pre_cb;
 	u32 register_window;
 
 	/* protects register_window above */
-- 
GitLab


From 027a44fedd55fbdf1d45603894634acd960ad04b Mon Sep 17 00:00:00 2001
From: Peter Colberg <peter.colberg@intel.com>
Date: Tue, 21 May 2024 14:12:46 -0400
Subject: [PATCH 577/950] hwmon: (intel-m10-bmc-hwmon) Fix multiplier for N6000
 board power sensor

The Intel N6000 BMC outputs the board power value in milliwatt, whereas
the hwmon sysfs interface must provide power values in microwatt.

Fixes: e1983220ae14 ("hwmon: intel-m10-bmc-hwmon: Add N6000 sensors")
Signed-off-by: Peter Colberg <peter.colberg@intel.com>
Reviewed-by: Matthew Gerlach <matthew.gerlach@linux.intel.com>
Link: https://lore.kernel.org/r/20240521181246.683833-1-peter.colberg@intel.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/intel-m10-bmc-hwmon.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/hwmon/intel-m10-bmc-hwmon.c b/drivers/hwmon/intel-m10-bmc-hwmon.c
index 6500ca548f9c7..ca2dff1589251 100644
--- a/drivers/hwmon/intel-m10-bmc-hwmon.c
+++ b/drivers/hwmon/intel-m10-bmc-hwmon.c
@@ -429,7 +429,7 @@ static const struct m10bmc_sdata n6000bmc_curr_tbl[] = {
 };
 
 static const struct m10bmc_sdata n6000bmc_power_tbl[] = {
-	{ 0x724, 0x0, 0x0, 0x0, 0x0, 1, "Board Power" },
+	{ 0x724, 0x0, 0x0, 0x0, 0x0, 1000, "Board Power" },
 };
 
 static const struct hwmon_channel_info * const n6000bmc_hinfo[] = {
-- 
GitLab


From 52a2c70c3ec555e670a34dd1ab958986451d2dd2 Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Thu, 30 May 2024 08:20:14 -0700
Subject: [PATCH 578/950] hwmon: (shtc1) Fix property misspelling

The property name is "sensirion,low-precision", not
"sensicon,low-precision".

Cc: Chris Ruehl <chris.ruehl@gtsys.com.hk>
Fixes: be7373b60df5 ("hwmon: shtc1: add support for device tree bindings")
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/shtc1.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/hwmon/shtc1.c b/drivers/hwmon/shtc1.c
index 1f96e94967ee8..439dd3dba5fc8 100644
--- a/drivers/hwmon/shtc1.c
+++ b/drivers/hwmon/shtc1.c
@@ -238,7 +238,7 @@ static int shtc1_probe(struct i2c_client *client)
 
 	if (np) {
 		data->setup.blocking_io = of_property_read_bool(np, "sensirion,blocking-io");
-		data->setup.high_precision = !of_property_read_bool(np, "sensicon,low-precision");
+		data->setup.high_precision = !of_property_read_bool(np, "sensirion,low-precision");
 	} else {
 		if (client->dev.platform_data)
 			data->setup = *(struct shtc1_platform_data *)dev->platform_data;
-- 
GitLab


From 41011e2de3480f9adb6420b35b67628b2d903355 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 28 May 2024 11:06:31 +0100
Subject: [PATCH 579/950] KVM: arm64: nv: Fix relative priorities of exceptions
 generated by ERETAx

ERETAx can fail in multiple ways:

(1) ELR_EL2 points lalaland
(2) we get a PAC failure
(3) SPSR_EL2 has the wrong mode

(1) is easy, as we just let the CPU do its thing and deliver an
Instruction Abort. However, (2) and (3) are interesting, because
the PAC failure priority is way below that of the Illegal Execution
State exception.

Which means that if we have detected a PAC failure (and that we have
FPACCOMBINE), we must be careful to give priority to the Illegal
Execution State exception, should one be pending.

Solving this involves hoisting the SPSR calculation earlier and
testing for the IL bit before injecting the FPAC exception.

In the extreme case of a ERETAx returning to an invalid mode *and*
failing its PAC check, we end up with an Instruction Abort (due
to the new PC being mangled by the failed Auth) *and* PSTATE.IL
being set. Which matches the requirements of the architecture.

Whilst we're at it, remove a stale comment that states the obvious
and only confuses the reader.

Fixes: 213b3d1ea161 ("KVM: arm64: nv: Handle ERETA[AB] instructions")
Reviewed-by: Joey Gouly <joey.gouly@arm.com>
Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Link: https://lore.kernel.org/r/20240528100632.1831995-2-maz@kernel.org
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/emulate-nested.c | 21 +++++++++++----------
 1 file changed, 11 insertions(+), 10 deletions(-)

diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c
index 72d733c74a382..54090967a3356 100644
--- a/arch/arm64/kvm/emulate-nested.c
+++ b/arch/arm64/kvm/emulate-nested.c
@@ -2181,16 +2181,23 @@ void kvm_emulate_nested_eret(struct kvm_vcpu *vcpu)
 	if (forward_traps(vcpu, HCR_NV))
 		return;
 
+	spsr = vcpu_read_sys_reg(vcpu, SPSR_EL2);
+	spsr = kvm_check_illegal_exception_return(vcpu, spsr);
+
 	/* Check for an ERETAx */
 	esr = kvm_vcpu_get_esr(vcpu);
 	if (esr_iss_is_eretax(esr) && !kvm_auth_eretax(vcpu, &elr)) {
 		/*
-		 * Oh no, ERETAx failed to authenticate.  If we have
-		 * FPACCOMBINE, deliver an exception right away.  If we
-		 * don't, then let the mangled ELR value trickle down the
+		 * Oh no, ERETAx failed to authenticate.
+		 *
+		 * If we have FPACCOMBINE and we don't have a pending
+		 * Illegal Execution State exception (which has priority
+		 * over FPAC), deliver an exception right away.
+		 *
+		 * Otherwise, let the mangled ELR value trickle down the
 		 * ERET handling, and the guest will have a little surprise.
 		 */
-		if (kvm_has_pauth(vcpu->kvm, FPACCOMBINE)) {
+		if (kvm_has_pauth(vcpu->kvm, FPACCOMBINE) && !(spsr & PSR_IL_BIT)) {
 			esr &= ESR_ELx_ERET_ISS_ERETA;
 			esr |= FIELD_PREP(ESR_ELx_EC_MASK, ESR_ELx_EC_FPAC);
 			kvm_inject_nested_sync(vcpu, esr);
@@ -2201,17 +2208,11 @@ void kvm_emulate_nested_eret(struct kvm_vcpu *vcpu)
 	preempt_disable();
 	kvm_arch_vcpu_put(vcpu);
 
-	spsr = __vcpu_sys_reg(vcpu, SPSR_EL2);
-	spsr = kvm_check_illegal_exception_return(vcpu, spsr);
 	if (!esr_iss_is_eretax(esr))
 		elr = __vcpu_sys_reg(vcpu, ELR_EL2);
 
 	trace_kvm_nested_eret(vcpu, elr, spsr);
 
-	/*
-	 * Note that the current exception level is always the virtual EL2,
-	 * since we set HCR_EL2.NV bit only when entering the virtual EL2.
-	 */
 	*vcpu_pc(vcpu) = elr;
 	*vcpu_cpsr(vcpu) = spsr;
 
-- 
GitLab


From 47eb2d68d10208e6a9e89d10b66018e8d6ca0623 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 28 May 2024 11:06:32 +0100
Subject: [PATCH 580/950] KVM: arm64: nv: Expose BTI and CSV_frac to a guest
 hypervisor

Now that we expose PAC to NV guests, we can also expose BTI (as
the two as joined at the hip, due to some of the PAC instructions
being landing pads).

While we're at it, also propagate CSV_frac, which requires no
particular emulation.

Fixes: f4f6a95bac49 ("KVM: arm64: nv: Advertise support for PAuth")
Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Link: https://lore.kernel.org/r/20240528100632.1831995-3-maz@kernel.org
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/nested.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index 6813c7c7f00ab..bae8536cbf003 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -58,8 +58,10 @@ static u64 limit_nv_id_reg(u32 id, u64 val)
 		break;
 
 	case SYS_ID_AA64PFR1_EL1:
-		/* Only support SSBS */
-		val &= NV_FTR(PFR1, SSBS);
+		/* Only support BTI, SSBS, CSV2_frac */
+		val &= (NV_FTR(PFR1, BT)	|
+			NV_FTR(PFR1, SSBS)	|
+			NV_FTR(PFR1, CSV2_frac));
 		break;
 
 	case SYS_ID_AA64MMFR0_EL1:
-- 
GitLab


From a638b0461b58aa3205cd9d5f14d6f703d795b4af Mon Sep 17 00:00:00 2001
From: Sergey Matyukevich <sergey.matyukevich@syntacore.com>
Date: Thu, 23 May 2024 11:43:23 +0300
Subject: [PATCH 581/950] riscv: prevent pt_regs corruption for secondary idle
 threads

Top of the kernel thread stack should be reserved for pt_regs. However
this is not the case for the idle threads of the secondary boot harts.
Their stacks overlap with their pt_regs, so both may get corrupted.

Similar issue has been fixed for the primary hart, see c7cdd96eca28
("riscv: prevent stack corruption by reserving task_pt_regs(p) early").
However that fix was not propagated to the secondary harts. The problem
has been noticed in some CPU hotplug tests with V enabled. The function
smp_callin stored several registers on stack, corrupting top of pt_regs
structure including status field. As a result, kernel attempted to save
or restore inexistent V context.

Fixes: 9a2451f18663 ("RISC-V: Avoid using per cpu array for ordered booting")
Fixes: 2875fe056156 ("RISC-V: Add cpu_ops and modify default booting method")
Signed-off-by: Sergey Matyukevich <sergey.matyukevich@syntacore.com>
Reviewed-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Link: https://lore.kernel.org/r/20240523084327.2013211-1-geomatsi@gmail.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/kernel/cpu_ops_sbi.c      | 2 +-
 arch/riscv/kernel/cpu_ops_spinwait.c | 3 +--
 2 files changed, 2 insertions(+), 3 deletions(-)

diff --git a/arch/riscv/kernel/cpu_ops_sbi.c b/arch/riscv/kernel/cpu_ops_sbi.c
index 1cc7df740eddc..e6fbaaf549562 100644
--- a/arch/riscv/kernel/cpu_ops_sbi.c
+++ b/arch/riscv/kernel/cpu_ops_sbi.c
@@ -72,7 +72,7 @@ static int sbi_cpu_start(unsigned int cpuid, struct task_struct *tidle)
 	/* Make sure tidle is updated */
 	smp_mb();
 	bdata->task_ptr = tidle;
-	bdata->stack_ptr = task_stack_page(tidle) + THREAD_SIZE;
+	bdata->stack_ptr = task_pt_regs(tidle);
 	/* Make sure boot data is updated */
 	smp_mb();
 	hsm_data = __pa(bdata);
diff --git a/arch/riscv/kernel/cpu_ops_spinwait.c b/arch/riscv/kernel/cpu_ops_spinwait.c
index 613872b0a21ac..24869eb889085 100644
--- a/arch/riscv/kernel/cpu_ops_spinwait.c
+++ b/arch/riscv/kernel/cpu_ops_spinwait.c
@@ -34,8 +34,7 @@ static void cpu_update_secondary_bootdata(unsigned int cpuid,
 
 	/* Make sure tidle is updated */
 	smp_mb();
-	WRITE_ONCE(__cpu_spinwait_stack_pointer[hartid],
-		   task_stack_page(tidle) + THREAD_SIZE);
+	WRITE_ONCE(__cpu_spinwait_stack_pointer[hartid], task_pt_regs(tidle));
 	WRITE_ONCE(__cpu_spinwait_task_pointer[hartid], tidle);
 }
 
-- 
GitLab


From 7bed51617401dab2be930b13ed5aacf581f7c8ef Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Sun, 26 May 2024 13:01:04 +0200
Subject: [PATCH 582/950] riscv: enable HAVE_ARCH_HUGE_VMAP for XIP kernel

HAVE_ARCH_HUGE_VMAP also works on XIP kernel, so remove its dependency on
!XIP_KERNEL.

This also fixes a boot problem for XIP kernel introduced by the commit in
"Fixes:". This commit used huge page mapping for vmemmap, but huge page
vmap was not enabled for XIP kernel.

Fixes: ff172d4818ad ("riscv: Use hugepage mappings for vmemmap")
Signed-off-by: Nam Cao <namcao@linutronix.de>
Cc: <stable@vger.kernel.org>
Reviewed-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Link: https://lore.kernel.org/r/20240526110104.470429-1-namcao@linutronix.de
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index b94176e25be18..0525ee2d63c71 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -106,7 +106,7 @@ config RISCV
 	select HAS_IOPORT if MMU
 	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_ARCH_HUGE_VMALLOC if HAVE_ARCH_HUGE_VMAP
-	select HAVE_ARCH_HUGE_VMAP if MMU && 64BIT && !XIP_KERNEL
+	select HAVE_ARCH_HUGE_VMAP if MMU && 64BIT
 	select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL
 	select HAVE_ARCH_JUMP_LABEL_RELATIVE if !XIP_KERNEL
 	select HAVE_ARCH_KASAN if MMU && 64BIT
-- 
GitLab


From 982a7eb97be685d1129c06671aed4c26d6919af4 Mon Sep 17 00:00:00 2001
From: Palmer Dabbelt <palmer@rivosinc.com>
Date: Fri, 24 May 2024 11:56:00 -0700
Subject: [PATCH 583/950] Documentation: RISC-V: uabi: Only scalar misaligned
 loads are supported

We're stuck supporting scalar misaligned loads in userspace because they
were part of the ISA at the time we froze the uABI.  That wasn't the
case for vector misaligned accesses, so depending on them
unconditionally is a userspace bug.  All extant vector hardware traps on
these misaligned accesses.

Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20240524185600.5919-1-palmer@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 Documentation/arch/riscv/uabi.rst | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/Documentation/arch/riscv/uabi.rst b/Documentation/arch/riscv/uabi.rst
index 54d199dce78bf..2b420bab0527a 100644
--- a/Documentation/arch/riscv/uabi.rst
+++ b/Documentation/arch/riscv/uabi.rst
@@ -65,4 +65,6 @@ the extension, or may have deliberately removed it from the listing.
 Misaligned accesses
 -------------------
 
-Misaligned accesses are supported in userspace, but they may perform poorly.
+Misaligned scalar accesses are supported in userspace, but they may perform
+poorly.  Misaligned vector accesses are only supported if the Zicclsm extension
+is supported.
-- 
GitLab


From 1d84afaf02524d2558e8ca3ca169be2ef720380b Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Thu, 30 May 2024 16:55:46 +0200
Subject: [PATCH 584/950] riscv: Fix fully ordered LR/SC xchg[8|16]()
 implementations

The fully ordered versions of xchg[8|16]() using LR/SC lack the
necessary memory barriers to guarantee the order.

Fix this by matching what is already implemented in the fully ordered
versions of cmpxchg() using LR/SC.

Suggested-by: Andrea Parri <parri.andrea@gmail.com>
Reported-by: Andrea Parri <parri.andrea@gmail.com>
Closes: https://lore.kernel.org/linux-riscv/ZlYbupL5XgzgA0MX@andrea/T/#u
Fixes: a8ed2b7a2c13 ("riscv/cmpxchg: Implement xchg for variables of size 1 and 2")
Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Reviewed-by: Andrea Parri <parri.andrea@gmail.com>
Link: https://lore.kernel.org/r/20240530145546.394248-1-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/cmpxchg.h | 22 ++++++++++++----------
 1 file changed, 12 insertions(+), 10 deletions(-)

diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h
index ddb002ed89dea..808b4c78462e5 100644
--- a/arch/riscv/include/asm/cmpxchg.h
+++ b/arch/riscv/include/asm/cmpxchg.h
@@ -10,7 +10,7 @@
 
 #include <asm/fence.h>
 
-#define __arch_xchg_masked(prepend, append, r, p, n)			\
+#define __arch_xchg_masked(sc_sfx, prepend, append, r, p, n)		\
 ({									\
 	u32 *__ptr32b = (u32 *)((ulong)(p) & ~0x3);			\
 	ulong __s = ((ulong)(p) & (0x4 - sizeof(*p))) * BITS_PER_BYTE;	\
@@ -25,7 +25,7 @@
 	       "0:	lr.w %0, %2\n"					\
 	       "	and  %1, %0, %z4\n"				\
 	       "	or   %1, %1, %z3\n"				\
-	       "	sc.w %1, %1, %2\n"				\
+	       "	sc.w" sc_sfx " %1, %1, %2\n"			\
 	       "	bnez %1, 0b\n"					\
 	       append							\
 	       : "=&r" (__retx), "=&r" (__rc), "+A" (*(__ptr32b))	\
@@ -46,7 +46,8 @@
 		: "memory");						\
 })
 
-#define _arch_xchg(ptr, new, sfx, prepend, append)			\
+#define _arch_xchg(ptr, new, sc_sfx, swap_sfx, prepend,			\
+		   sc_append, swap_append)				\
 ({									\
 	__typeof__(ptr) __ptr = (ptr);					\
 	__typeof__(*(__ptr)) __new = (new);				\
@@ -55,15 +56,15 @@
 	switch (sizeof(*__ptr)) {					\
 	case 1:								\
 	case 2:								\
-		__arch_xchg_masked(prepend, append,			\
+		__arch_xchg_masked(sc_sfx, prepend, sc_append,		\
 				   __ret, __ptr, __new);		\
 		break;							\
 	case 4:								\
-		__arch_xchg(".w" sfx, prepend, append,			\
+		__arch_xchg(".w" swap_sfx, prepend, swap_append,	\
 			      __ret, __ptr, __new);			\
 		break;							\
 	case 8:								\
-		__arch_xchg(".d" sfx, prepend, append,			\
+		__arch_xchg(".d" swap_sfx, prepend, swap_append,	\
 			      __ret, __ptr, __new);			\
 		break;							\
 	default:							\
@@ -73,16 +74,17 @@
 })
 
 #define arch_xchg_relaxed(ptr, x)					\
-	_arch_xchg(ptr, x, "", "", "")
+	_arch_xchg(ptr, x, "", "", "", "", "")
 
 #define arch_xchg_acquire(ptr, x)					\
-	_arch_xchg(ptr, x, "", "", RISCV_ACQUIRE_BARRIER)
+	_arch_xchg(ptr, x, "", "", "",					\
+		   RISCV_ACQUIRE_BARRIER, RISCV_ACQUIRE_BARRIER)
 
 #define arch_xchg_release(ptr, x)					\
-	_arch_xchg(ptr, x, "", RISCV_RELEASE_BARRIER, "")
+	_arch_xchg(ptr, x, "", "", RISCV_RELEASE_BARRIER, "", "")
 
 #define arch_xchg(ptr, x)						\
-	_arch_xchg(ptr, x, ".aqrl", "", "")
+	_arch_xchg(ptr, x, ".rl", ".aqrl", "", RISCV_FULL_BARRIER, "")
 
 #define xchg32(ptr, x)							\
 ({									\
-- 
GitLab


From bb195358806847217efba98de62b7decec3b371f Mon Sep 17 00:00:00 2001
From: Abhinav Kumar <quic_abhinavk@quicinc.com>
Date: Tue, 7 May 2024 16:04:40 -0700
Subject: [PATCH 585/950] drm/msm: remove python 3.9 dependency for compiling
 msm

Since commit 5acf49119630 ("drm/msm: import gen_header.py script from Mesa"),
compilation is broken on machines having python versions older than 3.9
due to dependency on argparse.BooleanOptionalAction.

Switch to use simple bool for the validate flag to remove the dependency.

Fixes: 5acf49119630 ("drm/msm: import gen_header.py script from Mesa")
Signed-off-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
Tested-by: Douglas Anderson <dianders@chromium.org>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240507230440.3384949-1-quic_abhinavk@quicinc.com
---
 drivers/gpu/drm/msm/registers/gen_header.py | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/msm/registers/gen_header.py b/drivers/gpu/drm/msm/registers/gen_header.py
index fc3bfdc991d27..3926485bb197b 100644
--- a/drivers/gpu/drm/msm/registers/gen_header.py
+++ b/drivers/gpu/drm/msm/registers/gen_header.py
@@ -538,7 +538,7 @@ class Parser(object):
 		self.variants.add(reg.domain)
 
 	def do_validate(self, schemafile):
-		if self.validate == False:
+		if not self.validate:
 			return
 
 		try:
@@ -948,7 +948,8 @@ def main():
 	parser = argparse.ArgumentParser()
 	parser.add_argument('--rnn', type=str, required=True)
 	parser.add_argument('--xml', type=str, required=True)
-	parser.add_argument('--validate', action=argparse.BooleanOptionalAction)
+	parser.add_argument('--validate', default=False, action='store_true')
+	parser.add_argument('--no-validate', dest='validate', action='store_false')
 
 	subparsers = parser.add_subparsers()
 	subparsers.required = True
-- 
GitLab


From cb708ab9f584f159798b60853edcf0c8b67ce295 Mon Sep 17 00:00:00 2001
From: John Hubbard <jhubbard@nvidia.com>
Date: Tue, 28 May 2024 19:29:38 -0700
Subject: [PATCH 586/950] selftests/futex: pass _GNU_SOURCE without a value to
 the compiler

It's slightly better to set _GNU_SOURCE in the source code, but if one
must do it via the compiler invocation, then the best way to do so is
this:

    $(CC) -D_GNU_SOURCE=

...because otherwise, if this form is used:

    $(CC) -D_GNU_SOURCE

...then that leads the compiler to set a value, as if you had passed in:

    $(CC) -D_GNU_SOURCE=1

That, in turn, leads to warnings under both gcc and clang, like this:

    futex_requeue_pi.c:20: warning: "_GNU_SOURCE" redefined

Fix this by using the "-D_GNU_SOURCE=" form.

Reviewed-by: Edward Liaw <edliaw@google.com>
Reviewed-by: Davidlohr Bueso <dave@stgolabs.net>
Signed-off-by: John Hubbard <jhubbard@nvidia.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 tools/testing/selftests/futex/functional/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/futex/functional/Makefile b/tools/testing/selftests/futex/functional/Makefile
index a392d0917b4e5..994fa3468f170 100644
--- a/tools/testing/selftests/futex/functional/Makefile
+++ b/tools/testing/selftests/futex/functional/Makefile
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 INCLUDES := -I../include -I../../ $(KHDR_INCLUDES)
-CFLAGS := $(CFLAGS) -g -O2 -Wall -D_GNU_SOURCE -pthread $(INCLUDES) $(KHDR_INCLUDES)
+CFLAGS := $(CFLAGS) -g -O2 -Wall -D_GNU_SOURCE= -pthread $(INCLUDES) $(KHDR_INCLUDES)
 LDLIBS := -lpthread -lrt
 
 LOCAL_HDRS := \
-- 
GitLab


From 18414a4a2eabb0281d12d374c92874327e0e3fe3 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 30 May 2024 13:35:50 -0600
Subject: [PATCH 587/950] io_uring/net: assign kmsg inq/flags before buffer
 selection

syzbot reports that recv is using an uninitialized value:

=====================================================
BUG: KMSAN: uninit-value in io_req_cqe_overflow io_uring/io_uring.c:810 [inline]
BUG: KMSAN: uninit-value in io_req_complete_post io_uring/io_uring.c:937 [inline]
BUG: KMSAN: uninit-value in io_issue_sqe+0x1f1b/0x22c0 io_uring/io_uring.c:1763
 io_req_cqe_overflow io_uring/io_uring.c:810 [inline]
 io_req_complete_post io_uring/io_uring.c:937 [inline]
 io_issue_sqe+0x1f1b/0x22c0 io_uring/io_uring.c:1763
 io_wq_submit_work+0xa17/0xeb0 io_uring/io_uring.c:1860
 io_worker_handle_work+0xc04/0x2000 io_uring/io-wq.c:597
 io_wq_worker+0x447/0x1410 io_uring/io-wq.c:651
 ret_from_fork+0x6d/0x90 arch/x86/kernel/process.c:147
 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244

Uninit was stored to memory at:
 io_req_set_res io_uring/io_uring.h:215 [inline]
 io_recv_finish+0xf10/0x1560 io_uring/net.c:861
 io_recv+0x12ec/0x1ea0 io_uring/net.c:1175
 io_issue_sqe+0x429/0x22c0 io_uring/io_uring.c:1751
 io_wq_submit_work+0xa17/0xeb0 io_uring/io_uring.c:1860
 io_worker_handle_work+0xc04/0x2000 io_uring/io-wq.c:597
 io_wq_worker+0x447/0x1410 io_uring/io-wq.c:651
 ret_from_fork+0x6d/0x90 arch/x86/kernel/process.c:147
 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244

Uninit was created at:
 slab_post_alloc_hook mm/slub.c:3877 [inline]
 slab_alloc_node mm/slub.c:3918 [inline]
 __do_kmalloc_node mm/slub.c:4038 [inline]
 __kmalloc+0x6e4/0x1060 mm/slub.c:4052
 kmalloc include/linux/slab.h:632 [inline]
 io_alloc_async_data+0xc0/0x220 io_uring/io_uring.c:1662
 io_msg_alloc_async io_uring/net.c:166 [inline]
 io_recvmsg_prep_setup io_uring/net.c:725 [inline]
 io_recvmsg_prep+0xbe8/0x1a20 io_uring/net.c:806
 io_init_req io_uring/io_uring.c:2135 [inline]
 io_submit_sqe io_uring/io_uring.c:2182 [inline]
 io_submit_sqes+0x1135/0x2f10 io_uring/io_uring.c:2335
 __do_sys_io_uring_enter io_uring/io_uring.c:3246 [inline]
 __se_sys_io_uring_enter+0x40f/0x3c80 io_uring/io_uring.c:3183
 __x64_sys_io_uring_enter+0x11f/0x1a0 io_uring/io_uring.c:3183
 x64_sys_call+0x2c0/0x3b50 arch/x86/include/generated/asm/syscalls_64.h:427
 do_syscall_x64 arch/x86/entry/common.c:52 [inline]
 do_syscall_64+0xcf/0x1e0 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

which appears to be io_recv_finish() reading kmsg->msg.msg_inq to decide
if it needs to set IORING_CQE_F_SOCK_NONEMPTY or not. If the recv is
entered with buffer selection, but no buffer is available, then we jump
error path which calls io_recv_finish() without having assigned
kmsg->msg_inq. This might cause an errant setting of the NONEMPTY flag
for a request get gets errored with -ENOBUFS.

Reported-by: syzbot+b1647099e82b3b349fbf@syzkaller.appspotmail.com
Fixes: 4a3223f7bfda ("io_uring/net: switch io_recv() to using io_async_msghdr")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/net.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/io_uring/net.c b/io_uring/net.c
index 0a48596429d9f..7c98c4d509463 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -1127,6 +1127,9 @@ int io_recv(struct io_kiocb *req, unsigned int issue_flags)
 		flags |= MSG_DONTWAIT;
 
 retry_multishot:
+	kmsg->msg.msg_inq = -1;
+	kmsg->msg.msg_flags = 0;
+
 	if (io_do_buffer_select(req)) {
 		ret = io_recv_buf_select(req, kmsg, &len, issue_flags);
 		if (unlikely(ret))
@@ -1134,9 +1137,6 @@ retry_multishot:
 		sr->buf = NULL;
 	}
 
-	kmsg->msg.msg_inq = -1;
-	kmsg->msg.msg_flags = 0;
-
 	if (flags & MSG_WAITALL)
 		min_ret = iov_iter_count(&kmsg->msg.msg_iter);
 
-- 
GitLab


From b164316808ec5de391c3e7b0148ec937d32d280d Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Thu, 30 May 2024 14:40:32 +0900
Subject: [PATCH 588/950] null_blk: Do not allow runt zone with zone capacity
 smaller then zone size

A zoned device with a smaller last zone together with a zone capacity
smaller than the zone size does make any sense as that does not
correspond to any possible setup for a real device:
1) For ZNS and zoned UFS devices, all zones are always the same size.
2) For SMR HDDs, all zones always have the same capacity.
In other words, if we have a smaller last runt zone, then this zone
capacity should always be equal to the zone size.

Add a check in null_init_zoned_dev() to prevent a configuration to have
both a smaller zone size and a zone capacity smaller than the zone size.

Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Niklas Cassel <cassel@kernel.org>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20240530054035.491497-2-dlemoal@kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/null_blk/zoned.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/block/null_blk/zoned.c b/drivers/block/null_blk/zoned.c
index 79c8e5e99f7ff..f118d304f3108 100644
--- a/drivers/block/null_blk/zoned.c
+++ b/drivers/block/null_blk/zoned.c
@@ -74,6 +74,17 @@ int null_init_zoned_dev(struct nullb_device *dev,
 		return -EINVAL;
 	}
 
+	/*
+	 * If a smaller zone capacity was requested, do not allow a smaller last
+	 * zone at the same time as such zone configuration does not correspond
+	 * to any real zoned device.
+	 */
+	if (dev->zone_capacity != dev->zone_size &&
+	    dev->size & (dev->zone_size - 1)) {
+		pr_err("A smaller last zone is not allowed with zone capacity smaller than zone size.\n");
+		return -EINVAL;
+	}
+
 	zone_capacity_sects = mb_to_sects(dev->zone_capacity);
 	dev_capacity_sects = mb_to_sects(dev->size);
 	dev->zone_size_sects = mb_to_sects(dev->zone_size);
-- 
GitLab


From cd6399936869b4a042dd1270078cbf2bb871a407 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Thu, 30 May 2024 14:40:33 +0900
Subject: [PATCH 589/950] block: Fix validation of zoned device with a runt
 zone

Commit ecfe43b11b02 ("block: Remember zone capacity when revalidating
zones") introduced checks to ensure that the capacity of the zones of
a zoned device is constant for all zones. However, this check ignores
the possibility that a zoned device has a smaller last zone with a size
not equal to the capacity of other zones. Such device correspond in
practice to an SMR drive with a smaller last zone and all zones with a
capacity equal to the zone size, leading to the last zone capacity being
different than the capacity of other zones.

Correctly handle such device by fixing the check for the constant zone
capacity in blk_revalidate_seq_zone() using the new helper function
disk_zone_is_last(). This helper function is also used in
blk_revalidate_zone_cb() when checking the zone size.

Fixes: ecfe43b11b02 ("block: Remember zone capacity when revalidating zones")
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Niklas Cassel <cassel@kernel.org>
Link: https://lore.kernel.org/r/20240530054035.491497-3-dlemoal@kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-zoned.c | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)

diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index 03aa4eead39e7..402a50a1ac4d5 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -450,6 +450,11 @@ static inline bool disk_zone_is_conv(struct gendisk *disk, sector_t sector)
 	return test_bit(disk_zone_no(disk, sector), disk->conv_zones_bitmap);
 }
 
+static bool disk_zone_is_last(struct gendisk *disk, struct blk_zone *zone)
+{
+	return zone->start + zone->len >= get_capacity(disk);
+}
+
 static bool disk_insert_zone_wplug(struct gendisk *disk,
 				   struct blk_zone_wplug *zwplug)
 {
@@ -1693,11 +1698,13 @@ static int blk_revalidate_seq_zone(struct blk_zone *zone, unsigned int idx,
 
 	/*
 	 * Remember the capacity of the first sequential zone and check
-	 * if it is constant for all zones.
+	 * if it is constant for all zones, ignoring the last zone as it can be
+	 * smaller.
 	 */
 	if (!args->zone_capacity)
 		args->zone_capacity = zone->capacity;
-	if (zone->capacity != args->zone_capacity) {
+	if (!disk_zone_is_last(disk, zone) &&
+	    zone->capacity != args->zone_capacity) {
 		pr_warn("%s: Invalid variable zone capacity\n",
 			disk->disk_name);
 		return -ENODEV;
@@ -1732,7 +1739,6 @@ static int blk_revalidate_zone_cb(struct blk_zone *zone, unsigned int idx,
 {
 	struct blk_revalidate_zone_args *args = data;
 	struct gendisk *disk = args->disk;
-	sector_t capacity = get_capacity(disk);
 	sector_t zone_sectors = disk->queue->limits.chunk_sectors;
 	int ret;
 
@@ -1743,7 +1749,7 @@ static int blk_revalidate_zone_cb(struct blk_zone *zone, unsigned int idx,
 		return -ENODEV;
 	}
 
-	if (zone->start >= capacity || !zone->len) {
+	if (zone->start >= get_capacity(disk) || !zone->len) {
 		pr_warn("%s: Invalid zone start %llu, length %llu\n",
 			disk->disk_name, zone->start, zone->len);
 		return -ENODEV;
@@ -1753,7 +1759,7 @@ static int blk_revalidate_zone_cb(struct blk_zone *zone, unsigned int idx,
 	 * All zones must have the same size, with the exception on an eventual
 	 * smaller last zone.
 	 */
-	if (zone->start + zone->len < capacity) {
+	if (!disk_zone_is_last(disk, zone)) {
 		if (zone->len != zone_sectors) {
 			pr_warn("%s: Invalid zoned device with non constant zone size\n",
 				disk->disk_name);
-- 
GitLab


From 29459c3eaa5c6261fbe0dea7bdeb9b48d35d862a Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Thu, 30 May 2024 14:40:34 +0900
Subject: [PATCH 590/950] block: Fix zone write plugging handling of devices
 with a runt zone

A zoned device may have a last sequential write required zone that is
smaller than other zones. However, all tests to check if a zone write
plug write offset exceeds the zone capacity use the same capacity
value stored in the gendisk zone_capacity field. This is incorrect for a
zoned device with a last runt (smaller) zone.

Add the new field last_zone_capacity to struct gendisk to store the
capacity of the last zone of the device. blk_revalidate_seq_zone() and
blk_revalidate_conv_zone() are both modified to get this value when
disk_zone_is_last() returns true. Similarly to zone_capacity, the value
is first stored using the last_zone_capacity field of struct
blk_revalidate_zone_args. Once zone revalidation of all zones is done,
this is used to set the gendisk last_zone_capacity field.

The checks to determine if a zone is full or if a sector offset in a
zone exceeds the zone capacity in disk_should_remove_zone_wplug(),
disk_zone_wplug_abort_unaligned(), blk_zone_write_plug_init_request(),
and blk_zone_wplug_prepare_bio() are modified to use the new helper
functions disk_zone_is_full() and disk_zone_wplug_is_full().
disk_zone_is_full() uses the zone index to determine if the zone being
tested is the last one of the disk and uses the either the disk
zone_capacity or last_zone_capacity accordingly.

Fixes: dd291d77cc90 ("block: Introduce zone write plugging")
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Niklas Cassel <cassel@kernel.org>
Link: https://lore.kernel.org/r/20240530054035.491497-4-dlemoal@kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-zoned.c      | 35 +++++++++++++++++++++++++++--------
 include/linux/blkdev.h |  1 +
 2 files changed, 28 insertions(+), 8 deletions(-)

diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index 402a50a1ac4d5..52abebf56027a 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -455,6 +455,20 @@ static bool disk_zone_is_last(struct gendisk *disk, struct blk_zone *zone)
 	return zone->start + zone->len >= get_capacity(disk);
 }
 
+static bool disk_zone_is_full(struct gendisk *disk,
+			      unsigned int zno, unsigned int offset_in_zone)
+{
+	if (zno < disk->nr_zones - 1)
+		return offset_in_zone >= disk->zone_capacity;
+	return offset_in_zone >= disk->last_zone_capacity;
+}
+
+static bool disk_zone_wplug_is_full(struct gendisk *disk,
+				    struct blk_zone_wplug *zwplug)
+{
+	return disk_zone_is_full(disk, zwplug->zone_no, zwplug->wp_offset);
+}
+
 static bool disk_insert_zone_wplug(struct gendisk *disk,
 				   struct blk_zone_wplug *zwplug)
 {
@@ -548,7 +562,7 @@ static inline bool disk_should_remove_zone_wplug(struct gendisk *disk,
 		return false;
 
 	/* We can remove zone write plugs for zones that are empty or full. */
-	return !zwplug->wp_offset || zwplug->wp_offset >= disk->zone_capacity;
+	return !zwplug->wp_offset || disk_zone_wplug_is_full(disk, zwplug);
 }
 
 static void disk_remove_zone_wplug(struct gendisk *disk,
@@ -669,13 +683,12 @@ static void disk_zone_wplug_abort(struct blk_zone_wplug *zwplug)
 static void disk_zone_wplug_abort_unaligned(struct gendisk *disk,
 					    struct blk_zone_wplug *zwplug)
 {
-	unsigned int zone_capacity = disk->zone_capacity;
 	unsigned int wp_offset = zwplug->wp_offset;
 	struct bio_list bl = BIO_EMPTY_LIST;
 	struct bio *bio;
 
 	while ((bio = bio_list_pop(&zwplug->bio_list))) {
-		if (wp_offset >= zone_capacity ||
+		if (disk_zone_is_full(disk, zwplug->zone_no, wp_offset) ||
 		    (bio_op(bio) != REQ_OP_ZONE_APPEND &&
 		     bio_offset_from_zone_start(bio) != wp_offset)) {
 			blk_zone_wplug_bio_io_error(zwplug, bio);
@@ -914,7 +927,6 @@ void blk_zone_write_plug_init_request(struct request *req)
 	sector_t req_back_sector = blk_rq_pos(req) + blk_rq_sectors(req);
 	struct request_queue *q = req->q;
 	struct gendisk *disk = q->disk;
-	unsigned int zone_capacity = disk->zone_capacity;
 	struct blk_zone_wplug *zwplug =
 		disk_get_zone_wplug(disk, blk_rq_pos(req));
 	unsigned long flags;
@@ -938,7 +950,7 @@ void blk_zone_write_plug_init_request(struct request *req)
 	 * into the back of the request.
 	 */
 	spin_lock_irqsave(&zwplug->lock, flags);
-	while (zwplug->wp_offset < zone_capacity) {
+	while (!disk_zone_wplug_is_full(disk, zwplug)) {
 		bio = bio_list_peek(&zwplug->bio_list);
 		if (!bio)
 			break;
@@ -984,7 +996,7 @@ static bool blk_zone_wplug_prepare_bio(struct blk_zone_wplug *zwplug,
 	 * We know such BIO will fail, and that would potentially overflow our
 	 * write pointer offset beyond the end of the zone.
 	 */
-	if (zwplug->wp_offset >= disk->zone_capacity)
+	if (disk_zone_wplug_is_full(disk, zwplug))
 		goto err;
 
 	if (bio_op(bio) == REQ_OP_ZONE_APPEND) {
@@ -1561,6 +1573,7 @@ void disk_free_zone_resources(struct gendisk *disk)
 	kfree(disk->conv_zones_bitmap);
 	disk->conv_zones_bitmap = NULL;
 	disk->zone_capacity = 0;
+	disk->last_zone_capacity = 0;
 	disk->nr_zones = 0;
 }
 
@@ -1605,6 +1618,7 @@ struct blk_revalidate_zone_args {
 	unsigned long	*conv_zones_bitmap;
 	unsigned int	nr_zones;
 	unsigned int	zone_capacity;
+	unsigned int	last_zone_capacity;
 	sector_t	sector;
 };
 
@@ -1622,6 +1636,7 @@ static int disk_update_zone_resources(struct gendisk *disk,
 
 	disk->nr_zones = args->nr_zones;
 	disk->zone_capacity = args->zone_capacity;
+	disk->last_zone_capacity = args->last_zone_capacity;
 	swap(disk->conv_zones_bitmap, args->conv_zones_bitmap);
 	if (disk->conv_zones_bitmap)
 		nr_conv_zones = bitmap_weight(disk->conv_zones_bitmap,
@@ -1673,6 +1688,9 @@ static int blk_revalidate_conv_zone(struct blk_zone *zone, unsigned int idx,
 		return -ENODEV;
 	}
 
+	if (disk_zone_is_last(disk, zone))
+		args->last_zone_capacity = zone->capacity;
+
 	if (!disk_need_zone_resources(disk))
 		return 0;
 
@@ -1703,8 +1721,9 @@ static int blk_revalidate_seq_zone(struct blk_zone *zone, unsigned int idx,
 	 */
 	if (!args->zone_capacity)
 		args->zone_capacity = zone->capacity;
-	if (!disk_zone_is_last(disk, zone) &&
-	    zone->capacity != args->zone_capacity) {
+	if (disk_zone_is_last(disk, zone)) {
+		args->last_zone_capacity = zone->capacity;
+	} else if (zone->capacity != args->zone_capacity) {
 		pr_warn("%s: Invalid variable zone capacity\n",
 			disk->disk_name);
 		return -ENODEV;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index aefdda9f4ec71..24c36929920b7 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -186,6 +186,7 @@ struct gendisk {
 	 */
 	unsigned int		nr_zones;
 	unsigned int		zone_capacity;
+	unsigned int		last_zone_capacity;
 	unsigned long		*conv_zones_bitmap;
 	unsigned int            zone_wplugs_hash_bits;
 	spinlock_t              zone_wplugs_lock;
-- 
GitLab


From 46253c4ae96162a840ad65c1394de63796d7798a Mon Sep 17 00:00:00 2001
From: Jakub Sitnicki <jakub@cloudflare.com>
Date: Wed, 22 May 2024 10:09:36 +0200
Subject: [PATCH 591/950] selftests/bpf: use section names understood by libbpf
 in test_sockmap

libbpf can deduce program type and attach type from the ELF section name.
We don't need to pass it out-of-band if we switch to libbpf convention [1].

[1] https://docs.kernel.org/bpf/libbpf/program_types.html

Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20240522080936.2475833-1-jakub@cloudflare.com
---
 .../selftests/bpf/progs/test_sockmap_kern.h   | 17 +++++-----
 tools/testing/selftests/bpf/test_sockmap.c    | 31 -------------------
 2 files changed, 9 insertions(+), 39 deletions(-)

diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_kern.h b/tools/testing/selftests/bpf/progs/test_sockmap_kern.h
index 99d2ea9fb658f..3dff0813730b4 100644
--- a/tools/testing/selftests/bpf/progs/test_sockmap_kern.h
+++ b/tools/testing/selftests/bpf/progs/test_sockmap_kern.h
@@ -92,7 +92,7 @@ struct {
 	__uint(value_size, sizeof(int));
 } tls_sock_map SEC(".maps");
 
-SEC("sk_skb1")
+SEC("sk_skb/stream_parser")
 int bpf_prog1(struct __sk_buff *skb)
 {
 	int *f, two = 2;
@@ -104,7 +104,7 @@ int bpf_prog1(struct __sk_buff *skb)
 	return skb->len;
 }
 
-SEC("sk_skb2")
+SEC("sk_skb/stream_verdict")
 int bpf_prog2(struct __sk_buff *skb)
 {
 	__u32 lport = skb->local_port;
@@ -151,7 +151,7 @@ static inline void bpf_write_pass(struct __sk_buff *skb, int offset)
 		memcpy(c + offset, "PASS", 4);
 }
 
-SEC("sk_skb3")
+SEC("sk_skb/stream_verdict")
 int bpf_prog3(struct __sk_buff *skb)
 {
 	int err, *f, ret = SK_PASS;
@@ -233,7 +233,7 @@ int bpf_sockmap(struct bpf_sock_ops *skops)
 	return 0;
 }
 
-SEC("sk_msg1")
+SEC("sk_msg")
 int bpf_prog4(struct sk_msg_md *msg)
 {
 	int *bytes, zero = 0, one = 1, two = 2, three = 3, four = 4, five = 5;
@@ -263,7 +263,7 @@ int bpf_prog4(struct sk_msg_md *msg)
 	return SK_PASS;
 }
 
-SEC("sk_msg2")
+SEC("sk_msg")
 int bpf_prog6(struct sk_msg_md *msg)
 {
 	int zero = 0, one = 1, two = 2, three = 3, four = 4, five = 5, key = 0;
@@ -308,7 +308,7 @@ int bpf_prog6(struct sk_msg_md *msg)
 #endif
 }
 
-SEC("sk_msg3")
+SEC("sk_msg")
 int bpf_prog8(struct sk_msg_md *msg)
 {
 	void *data_end = (void *)(long) msg->data_end;
@@ -329,7 +329,8 @@ int bpf_prog8(struct sk_msg_md *msg)
 
 	return SK_PASS;
 }
-SEC("sk_msg4")
+
+SEC("sk_msg")
 int bpf_prog9(struct sk_msg_md *msg)
 {
 	void *data_end = (void *)(long) msg->data_end;
@@ -347,7 +348,7 @@ int bpf_prog9(struct sk_msg_md *msg)
 	return SK_PASS;
 }
 
-SEC("sk_msg5")
+SEC("sk_msg")
 int bpf_prog10(struct sk_msg_md *msg)
 {
 	int *bytes, *start, *end, *start_push, *end_push, *start_pop, *pop;
diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index 4499b3cfc3a68..ddc6a9cef36f9 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -1783,30 +1783,6 @@ char *map_names[] = {
 	"tls_sock_map",
 };
 
-int prog_attach_type[] = {
-	BPF_SK_SKB_STREAM_PARSER,
-	BPF_SK_SKB_STREAM_VERDICT,
-	BPF_SK_SKB_STREAM_VERDICT,
-	BPF_CGROUP_SOCK_OPS,
-	BPF_SK_MSG_VERDICT,
-	BPF_SK_MSG_VERDICT,
-	BPF_SK_MSG_VERDICT,
-	BPF_SK_MSG_VERDICT,
-	BPF_SK_MSG_VERDICT,
-};
-
-int prog_type[] = {
-	BPF_PROG_TYPE_SK_SKB,
-	BPF_PROG_TYPE_SK_SKB,
-	BPF_PROG_TYPE_SK_SKB,
-	BPF_PROG_TYPE_SOCK_OPS,
-	BPF_PROG_TYPE_SK_MSG,
-	BPF_PROG_TYPE_SK_MSG,
-	BPF_PROG_TYPE_SK_MSG,
-	BPF_PROG_TYPE_SK_MSG,
-	BPF_PROG_TYPE_SK_MSG,
-};
-
 static int populate_progs(char *bpf_file)
 {
 	struct bpf_program *prog;
@@ -1825,13 +1801,6 @@ static int populate_progs(char *bpf_file)
 		return -1;
 	}
 
-	bpf_object__for_each_program(prog, obj) {
-		bpf_program__set_type(prog, prog_type[i]);
-		bpf_program__set_expected_attach_type(prog,
-						      prog_attach_type[i]);
-		i++;
-	}
-
 	i = bpf_object__load(obj);
 	i = 0;
 	bpf_object__for_each_program(prog, obj) {
-- 
GitLab


From 73287fe228721b05690e671adbcccc6cf5435be6 Mon Sep 17 00:00:00 2001
From: Kui-Feng Lee <thinker.li@gmail.com>
Date: Wed, 29 May 2024 23:59:39 -0700
Subject: [PATCH 592/950] bpf: pass bpf_struct_ops_link to callbacks in
 bpf_struct_ops.

Pass an additional pointer of bpf_struct_ops_link to callback function reg,
unreg, and update provided by subsystems defined in bpf_struct_ops. A
bpf_struct_ops_map can be registered for multiple links. Passing a pointer
of bpf_struct_ops_link helps subsystems to distinguish them.

This pointer will be used in the later patches to let the subsystem
initiate a detachment on a link that was registered to it previously.

Signed-off-by: Kui-Feng Lee <thinker.li@gmail.com>
Link: https://lore.kernel.org/r/20240530065946.979330-2-thinker.li@gmail.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 include/linux/bpf.h                                    |  6 +++---
 kernel/bpf/bpf_struct_ops.c                            | 10 +++++-----
 net/bpf/bpf_dummy_struct_ops.c                         |  4 ++--
 net/ipv4/bpf_tcp_ca.c                                  |  6 +++---
 .../selftests/bpf/bpf_test_no_cfi/bpf_test_no_cfi.c    |  4 ++--
 tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c  |  6 +++---
 6 files changed, 18 insertions(+), 18 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 5e694a308081a..19f8836382fc4 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1730,9 +1730,9 @@ struct bpf_struct_ops {
 	int (*init_member)(const struct btf_type *t,
 			   const struct btf_member *member,
 			   void *kdata, const void *udata);
-	int (*reg)(void *kdata);
-	void (*unreg)(void *kdata);
-	int (*update)(void *kdata, void *old_kdata);
+	int (*reg)(void *kdata, struct bpf_link *link);
+	void (*unreg)(void *kdata, struct bpf_link *link);
+	int (*update)(void *kdata, void *old_kdata, struct bpf_link *link);
 	int (*validate)(void *kdata);
 	void *cfi_stubs;
 	struct module *owner;
diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
index 86c7884abaf87..1542dded7489b 100644
--- a/kernel/bpf/bpf_struct_ops.c
+++ b/kernel/bpf/bpf_struct_ops.c
@@ -757,7 +757,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 		goto unlock;
 	}
 
-	err = st_ops->reg(kdata);
+	err = st_ops->reg(kdata, NULL);
 	if (likely(!err)) {
 		/* This refcnt increment on the map here after
 		 * 'st_ops->reg()' is secure since the state of the
@@ -805,7 +805,7 @@ static long bpf_struct_ops_map_delete_elem(struct bpf_map *map, void *key)
 			     BPF_STRUCT_OPS_STATE_TOBEFREE);
 	switch (prev_state) {
 	case BPF_STRUCT_OPS_STATE_INUSE:
-		st_map->st_ops_desc->st_ops->unreg(&st_map->kvalue.data);
+		st_map->st_ops_desc->st_ops->unreg(&st_map->kvalue.data, NULL);
 		bpf_map_put(map);
 		return 0;
 	case BPF_STRUCT_OPS_STATE_TOBEFREE:
@@ -1060,7 +1060,7 @@ static void bpf_struct_ops_map_link_dealloc(struct bpf_link *link)
 		/* st_link->map can be NULL if
 		 * bpf_struct_ops_link_create() fails to register.
 		 */
-		st_map->st_ops_desc->st_ops->unreg(&st_map->kvalue.data);
+		st_map->st_ops_desc->st_ops->unreg(&st_map->kvalue.data, link);
 		bpf_map_put(&st_map->map);
 	}
 	kfree(st_link);
@@ -1125,7 +1125,7 @@ static int bpf_struct_ops_map_link_update(struct bpf_link *link, struct bpf_map
 		goto err_out;
 	}
 
-	err = st_map->st_ops_desc->st_ops->update(st_map->kvalue.data, old_st_map->kvalue.data);
+	err = st_map->st_ops_desc->st_ops->update(st_map->kvalue.data, old_st_map->kvalue.data, link);
 	if (err)
 		goto err_out;
 
@@ -1176,7 +1176,7 @@ int bpf_struct_ops_link_create(union bpf_attr *attr)
 	if (err)
 		goto err_out;
 
-	err = st_map->st_ops_desc->st_ops->reg(st_map->kvalue.data);
+	err = st_map->st_ops_desc->st_ops->reg(st_map->kvalue.data, &link->link);
 	if (err) {
 		bpf_link_cleanup(&link_primer);
 		link = NULL;
diff --git a/net/bpf/bpf_dummy_struct_ops.c b/net/bpf/bpf_dummy_struct_ops.c
index 891cdf61c65ae..3ea52b05adfbd 100644
--- a/net/bpf/bpf_dummy_struct_ops.c
+++ b/net/bpf/bpf_dummy_struct_ops.c
@@ -272,12 +272,12 @@ static int bpf_dummy_init_member(const struct btf_type *t,
 	return -EOPNOTSUPP;
 }
 
-static int bpf_dummy_reg(void *kdata)
+static int bpf_dummy_reg(void *kdata, struct bpf_link *link)
 {
 	return -EOPNOTSUPP;
 }
 
-static void bpf_dummy_unreg(void *kdata)
+static void bpf_dummy_unreg(void *kdata, struct bpf_link *link)
 {
 }
 
diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c
index 18227757ec0ce..3f88d0961e5b2 100644
--- a/net/ipv4/bpf_tcp_ca.c
+++ b/net/ipv4/bpf_tcp_ca.c
@@ -260,17 +260,17 @@ static int bpf_tcp_ca_check_member(const struct btf_type *t,
 	return 0;
 }
 
-static int bpf_tcp_ca_reg(void *kdata)
+static int bpf_tcp_ca_reg(void *kdata, struct bpf_link *link)
 {
 	return tcp_register_congestion_control(kdata);
 }
 
-static void bpf_tcp_ca_unreg(void *kdata)
+static void bpf_tcp_ca_unreg(void *kdata, struct bpf_link *link)
 {
 	tcp_unregister_congestion_control(kdata);
 }
 
-static int bpf_tcp_ca_update(void *kdata, void *old_kdata)
+static int bpf_tcp_ca_update(void *kdata, void *old_kdata, struct bpf_link *link)
 {
 	return tcp_update_congestion_control(kdata, old_kdata);
 }
diff --git a/tools/testing/selftests/bpf/bpf_test_no_cfi/bpf_test_no_cfi.c b/tools/testing/selftests/bpf/bpf_test_no_cfi/bpf_test_no_cfi.c
index b1dd889d5d7d0..948eb3962732d 100644
--- a/tools/testing/selftests/bpf/bpf_test_no_cfi/bpf_test_no_cfi.c
+++ b/tools/testing/selftests/bpf/bpf_test_no_cfi/bpf_test_no_cfi.c
@@ -22,12 +22,12 @@ static int dummy_init_member(const struct btf_type *t,
 	return 0;
 }
 
-static int dummy_reg(void *kdata)
+static int dummy_reg(void *kdata, struct bpf_link *link)
 {
 	return 0;
 }
 
-static void dummy_unreg(void *kdata)
+static void dummy_unreg(void *kdata, struct bpf_link *link)
 {
 }
 
diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
index 2a18bd320e922..0a09732cde4b7 100644
--- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
+++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
@@ -820,7 +820,7 @@ static const struct bpf_verifier_ops bpf_testmod_verifier_ops = {
 	.is_valid_access = bpf_testmod_ops_is_valid_access,
 };
 
-static int bpf_dummy_reg(void *kdata)
+static int bpf_dummy_reg(void *kdata, struct bpf_link *link)
 {
 	struct bpf_testmod_ops *ops = kdata;
 
@@ -835,7 +835,7 @@ static int bpf_dummy_reg(void *kdata)
 	return 0;
 }
 
-static void bpf_dummy_unreg(void *kdata)
+static void bpf_dummy_unreg(void *kdata, struct bpf_link *link)
 {
 }
 
@@ -871,7 +871,7 @@ struct bpf_struct_ops bpf_bpf_testmod_ops = {
 	.owner = THIS_MODULE,
 };
 
-static int bpf_dummy_reg2(void *kdata)
+static int bpf_dummy_reg2(void *kdata, struct bpf_link *link)
 {
 	struct bpf_testmod_ops2 *ops = kdata;
 
-- 
GitLab


From 6fb2544ea1493f52e50b753604791c01bd2cf897 Mon Sep 17 00:00:00 2001
From: Kui-Feng Lee <thinker.li@gmail.com>
Date: Wed, 29 May 2024 23:59:40 -0700
Subject: [PATCH 593/950] bpf: enable detaching links of struct_ops objects.

Implement the detach callback in bpf_link_ops for struct_ops so that user
programs can detach a struct_ops link. The subsystems that struct_ops
objects are registered to can also use this callback to detach the links
being passed to them.

Signed-off-by: Kui-Feng Lee <thinker.li@gmail.com>
Link: https://lore.kernel.org/r/20240530065946.979330-3-thinker.li@gmail.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 kernel/bpf/bpf_struct_ops.c | 48 +++++++++++++++++++++++++++++++++----
 1 file changed, 43 insertions(+), 5 deletions(-)

diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
index 1542dded7489b..58314b1fc39c7 100644
--- a/kernel/bpf/bpf_struct_ops.c
+++ b/kernel/bpf/bpf_struct_ops.c
@@ -1057,9 +1057,6 @@ static void bpf_struct_ops_map_link_dealloc(struct bpf_link *link)
 	st_map = (struct bpf_struct_ops_map *)
 		rcu_dereference_protected(st_link->map, true);
 	if (st_map) {
-		/* st_link->map can be NULL if
-		 * bpf_struct_ops_link_create() fails to register.
-		 */
 		st_map->st_ops_desc->st_ops->unreg(&st_map->kvalue.data, link);
 		bpf_map_put(&st_map->map);
 	}
@@ -1075,7 +1072,8 @@ static void bpf_struct_ops_map_link_show_fdinfo(const struct bpf_link *link,
 	st_link = container_of(link, struct bpf_struct_ops_link, link);
 	rcu_read_lock();
 	map = rcu_dereference(st_link->map);
-	seq_printf(seq, "map_id:\t%d\n", map->id);
+	if (map)
+		seq_printf(seq, "map_id:\t%d\n", map->id);
 	rcu_read_unlock();
 }
 
@@ -1088,7 +1086,8 @@ static int bpf_struct_ops_map_link_fill_link_info(const struct bpf_link *link,
 	st_link = container_of(link, struct bpf_struct_ops_link, link);
 	rcu_read_lock();
 	map = rcu_dereference(st_link->map);
-	info->struct_ops.map_id = map->id;
+	if (map)
+		info->struct_ops.map_id = map->id;
 	rcu_read_unlock();
 	return 0;
 }
@@ -1113,6 +1112,10 @@ static int bpf_struct_ops_map_link_update(struct bpf_link *link, struct bpf_map
 	mutex_lock(&update_mutex);
 
 	old_map = rcu_dereference_protected(st_link->map, lockdep_is_held(&update_mutex));
+	if (!old_map) {
+		err = -ENOLINK;
+		goto err_out;
+	}
 	if (expected_old_map && old_map != expected_old_map) {
 		err = -EPERM;
 		goto err_out;
@@ -1139,8 +1142,37 @@ err_out:
 	return err;
 }
 
+static int bpf_struct_ops_map_link_detach(struct bpf_link *link)
+{
+	struct bpf_struct_ops_link *st_link = container_of(link, struct bpf_struct_ops_link, link);
+	struct bpf_struct_ops_map *st_map;
+	struct bpf_map *map;
+
+	mutex_lock(&update_mutex);
+
+	map = rcu_dereference_protected(st_link->map, lockdep_is_held(&update_mutex));
+	if (!map) {
+		mutex_unlock(&update_mutex);
+		return 0;
+	}
+	st_map = container_of(map, struct bpf_struct_ops_map, map);
+
+	st_map->st_ops_desc->st_ops->unreg(&st_map->kvalue.data, link);
+
+	RCU_INIT_POINTER(st_link->map, NULL);
+	/* Pair with bpf_map_get() in bpf_struct_ops_link_create() or
+	 * bpf_map_inc() in bpf_struct_ops_map_link_update().
+	 */
+	bpf_map_put(&st_map->map);
+
+	mutex_unlock(&update_mutex);
+
+	return 0;
+}
+
 static const struct bpf_link_ops bpf_struct_ops_map_lops = {
 	.dealloc = bpf_struct_ops_map_link_dealloc,
+	.detach = bpf_struct_ops_map_link_detach,
 	.show_fdinfo = bpf_struct_ops_map_link_show_fdinfo,
 	.fill_link_info = bpf_struct_ops_map_link_fill_link_info,
 	.update_map = bpf_struct_ops_map_link_update,
@@ -1176,13 +1208,19 @@ int bpf_struct_ops_link_create(union bpf_attr *attr)
 	if (err)
 		goto err_out;
 
+	/* Hold the update_mutex such that the subsystem cannot
+	 * do link->ops->detach() before the link is fully initialized.
+	 */
+	mutex_lock(&update_mutex);
 	err = st_map->st_ops_desc->st_ops->reg(st_map->kvalue.data, &link->link);
 	if (err) {
+		mutex_unlock(&update_mutex);
 		bpf_link_cleanup(&link_primer);
 		link = NULL;
 		goto err_out;
 	}
 	RCU_INIT_POINTER(link->map, map);
+	mutex_unlock(&update_mutex);
 
 	return bpf_link_settle(&link_primer);
 
-- 
GitLab


From 1adddc97aa44c8783f9f0276ea70854d56f9f6df Mon Sep 17 00:00:00 2001
From: Kui-Feng Lee <thinker.li@gmail.com>
Date: Wed, 29 May 2024 23:59:41 -0700
Subject: [PATCH 594/950] bpf: support epoll from bpf struct_ops links.

Add epoll support to bpf struct_ops links to trigger EPOLLHUP event upon
detachment.

This patch implements the "poll" of the "struct file_operations" for BPF
links and introduces a new "poll" operator in the "struct bpf_link_ops". By
implementing "poll" of "struct bpf_link_ops" for the links of struct_ops,
the file descriptor of a struct_ops link can be added to an epoll file
descriptor to receive EPOLLHUP events.

Signed-off-by: Kui-Feng Lee <thinker.li@gmail.com>
Link: https://lore.kernel.org/r/20240530065946.979330-4-thinker.li@gmail.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 include/linux/bpf.h         |  1 +
 kernel/bpf/bpf_struct_ops.c | 17 +++++++++++++++++
 kernel/bpf/syscall.c        | 31 ++++++++++++++++++++++++++-----
 3 files changed, 44 insertions(+), 5 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 19f8836382fc4..5eb61120e4f56 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1612,6 +1612,7 @@ struct bpf_link_ops {
 			      struct bpf_link_info *info);
 	int (*update_map)(struct bpf_link *link, struct bpf_map *new_map,
 			  struct bpf_map *old_map);
+	__poll_t (*poll)(struct file *file, struct poll_table_struct *pts);
 };
 
 struct bpf_tramp_link {
diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
index 58314b1fc39c7..a2cf31b14be46 100644
--- a/kernel/bpf/bpf_struct_ops.c
+++ b/kernel/bpf/bpf_struct_ops.c
@@ -12,6 +12,7 @@
 #include <linux/mutex.h>
 #include <linux/btf_ids.h>
 #include <linux/rcupdate_wait.h>
+#include <linux/poll.h>
 
 struct bpf_struct_ops_value {
 	struct bpf_struct_ops_common_value common;
@@ -56,6 +57,7 @@ struct bpf_struct_ops_map {
 struct bpf_struct_ops_link {
 	struct bpf_link link;
 	struct bpf_map __rcu *map;
+	wait_queue_head_t wait_hup;
 };
 
 static DEFINE_MUTEX(update_mutex);
@@ -1167,15 +1169,28 @@ static int bpf_struct_ops_map_link_detach(struct bpf_link *link)
 
 	mutex_unlock(&update_mutex);
 
+	wake_up_interruptible_poll(&st_link->wait_hup, EPOLLHUP);
+
 	return 0;
 }
 
+static __poll_t bpf_struct_ops_map_link_poll(struct file *file,
+					     struct poll_table_struct *pts)
+{
+	struct bpf_struct_ops_link *st_link = file->private_data;
+
+	poll_wait(file, &st_link->wait_hup, pts);
+
+	return rcu_access_pointer(st_link->map) ? 0 : EPOLLHUP;
+}
+
 static const struct bpf_link_ops bpf_struct_ops_map_lops = {
 	.dealloc = bpf_struct_ops_map_link_dealloc,
 	.detach = bpf_struct_ops_map_link_detach,
 	.show_fdinfo = bpf_struct_ops_map_link_show_fdinfo,
 	.fill_link_info = bpf_struct_ops_map_link_fill_link_info,
 	.update_map = bpf_struct_ops_map_link_update,
+	.poll = bpf_struct_ops_map_link_poll,
 };
 
 int bpf_struct_ops_link_create(union bpf_attr *attr)
@@ -1208,6 +1223,8 @@ int bpf_struct_ops_link_create(union bpf_attr *attr)
 	if (err)
 		goto err_out;
 
+	init_waitqueue_head(&link->wait_hup);
+
 	/* Hold the update_mutex such that the subsystem cannot
 	 * do link->ops->detach() before the link is fully initialized.
 	 */
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 2222c3ff88e7f..81efa19449421 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -3150,6 +3150,13 @@ static void bpf_link_show_fdinfo(struct seq_file *m, struct file *filp)
 }
 #endif
 
+static __poll_t bpf_link_poll(struct file *file, struct poll_table_struct *pts)
+{
+	struct bpf_link *link = file->private_data;
+
+	return link->ops->poll(file, pts);
+}
+
 static const struct file_operations bpf_link_fops = {
 #ifdef CONFIG_PROC_FS
 	.show_fdinfo	= bpf_link_show_fdinfo,
@@ -3159,6 +3166,16 @@ static const struct file_operations bpf_link_fops = {
 	.write		= bpf_dummy_write,
 };
 
+static const struct file_operations bpf_link_fops_poll = {
+#ifdef CONFIG_PROC_FS
+	.show_fdinfo	= bpf_link_show_fdinfo,
+#endif
+	.release	= bpf_link_release,
+	.read		= bpf_dummy_read,
+	.write		= bpf_dummy_write,
+	.poll		= bpf_link_poll,
+};
+
 static int bpf_link_alloc_id(struct bpf_link *link)
 {
 	int id;
@@ -3201,7 +3218,9 @@ int bpf_link_prime(struct bpf_link *link, struct bpf_link_primer *primer)
 		return id;
 	}
 
-	file = anon_inode_getfile("bpf_link", &bpf_link_fops, link, O_CLOEXEC);
+	file = anon_inode_getfile("bpf_link",
+				  link->ops->poll ? &bpf_link_fops_poll : &bpf_link_fops,
+				  link, O_CLOEXEC);
 	if (IS_ERR(file)) {
 		bpf_link_free_id(id);
 		put_unused_fd(fd);
@@ -3229,7 +3248,9 @@ int bpf_link_settle(struct bpf_link_primer *primer)
 
 int bpf_link_new_fd(struct bpf_link *link)
 {
-	return anon_inode_getfd("bpf-link", &bpf_link_fops, link, O_CLOEXEC);
+	return anon_inode_getfd("bpf-link",
+				link->ops->poll ? &bpf_link_fops_poll : &bpf_link_fops,
+				link, O_CLOEXEC);
 }
 
 struct bpf_link *bpf_link_get_from_fd(u32 ufd)
@@ -3239,7 +3260,7 @@ struct bpf_link *bpf_link_get_from_fd(u32 ufd)
 
 	if (!f.file)
 		return ERR_PTR(-EBADF);
-	if (f.file->f_op != &bpf_link_fops) {
+	if (f.file->f_op != &bpf_link_fops && f.file->f_op != &bpf_link_fops_poll) {
 		fdput(f);
 		return ERR_PTR(-EINVAL);
 	}
@@ -4971,7 +4992,7 @@ static int bpf_obj_get_info_by_fd(const union bpf_attr *attr,
 					     uattr);
 	else if (f.file->f_op == &btf_fops)
 		err = bpf_btf_get_info_by_fd(f.file, f.file->private_data, attr, uattr);
-	else if (f.file->f_op == &bpf_link_fops)
+	else if (f.file->f_op == &bpf_link_fops || f.file->f_op == &bpf_link_fops_poll)
 		err = bpf_link_get_info_by_fd(f.file, f.file->private_data,
 					      attr, uattr);
 	else
@@ -5106,7 +5127,7 @@ static int bpf_task_fd_query(const union bpf_attr *attr,
 	if (!file)
 		return -EBADF;
 
-	if (file->f_op == &bpf_link_fops) {
+	if (file->f_op == &bpf_link_fops || file->f_op == &bpf_link_fops_poll) {
 		struct bpf_link *link = file->private_data;
 
 		if (link->ops == &bpf_raw_tp_link_lops) {
-- 
GitLab


From 67c3e8353f45c27800eecc46e00e8272f063f7d1 Mon Sep 17 00:00:00 2001
From: Kui-Feng Lee <thinker.li@gmail.com>
Date: Wed, 29 May 2024 23:59:42 -0700
Subject: [PATCH 595/950] bpf: export bpf_link_inc_not_zero.

bpf_link_inc_not_zero() will be used by kernel modules.  We will use it in
bpf_testmod.c later.

Signed-off-by: Kui-Feng Lee <thinker.li@gmail.com>
Link: https://lore.kernel.org/r/20240530065946.979330-5-thinker.li@gmail.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 include/linux/bpf.h  | 6 ++++++
 kernel/bpf/syscall.c | 3 ++-
 2 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 5eb61120e4f56..a834f4b761bc5 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -2334,6 +2334,7 @@ int bpf_link_prime(struct bpf_link *link, struct bpf_link_primer *primer);
 int bpf_link_settle(struct bpf_link_primer *primer);
 void bpf_link_cleanup(struct bpf_link_primer *primer);
 void bpf_link_inc(struct bpf_link *link);
+struct bpf_link *bpf_link_inc_not_zero(struct bpf_link *link);
 void bpf_link_put(struct bpf_link *link);
 int bpf_link_new_fd(struct bpf_link *link);
 struct bpf_link *bpf_link_get_from_fd(u32 ufd);
@@ -2705,6 +2706,11 @@ static inline void bpf_link_inc(struct bpf_link *link)
 {
 }
 
+static inline struct bpf_link *bpf_link_inc_not_zero(struct bpf_link *link)
+{
+	return NULL;
+}
+
 static inline void bpf_link_put(struct bpf_link *link)
 {
 }
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 81efa19449421..5070fa20d05c5 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -5437,10 +5437,11 @@ static int link_detach(union bpf_attr *attr)
 	return ret;
 }
 
-static struct bpf_link *bpf_link_inc_not_zero(struct bpf_link *link)
+struct bpf_link *bpf_link_inc_not_zero(struct bpf_link *link)
 {
 	return atomic64_fetch_add_unless(&link->refcnt, 1, 0) ? link : ERR_PTR(-ENOENT);
 }
+EXPORT_SYMBOL(bpf_link_inc_not_zero);
 
 struct bpf_link *bpf_link_by_id(u32 id)
 {
-- 
GitLab


From 1a4b858b6a045828de1b536cfab7819c50864ed6 Mon Sep 17 00:00:00 2001
From: Kui-Feng Lee <thinker.li@gmail.com>
Date: Wed, 29 May 2024 23:59:43 -0700
Subject: [PATCH 596/950] selftests/bpf: test struct_ops with epoll

Verify whether a user space program is informed through epoll with EPOLLHUP
when a struct_ops object is detached.

The BPF code in selftests/bpf/progs/struct_ops_module.c has become
complex. Therefore, struct_ops_detach.c has been added to segregate the BPF
code for detachment tests from the BPF code for other tests based on the
recommendation of Andrii Nakryiko.

Suggested-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Kui-Feng Lee <thinker.li@gmail.com>
Link: https://lore.kernel.org/r/20240530065946.979330-6-thinker.li@gmail.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 .../bpf/prog_tests/test_struct_ops_module.c   | 57 +++++++++++++++++++
 .../selftests/bpf/progs/struct_ops_detach.c   | 10 ++++
 2 files changed, 67 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/progs/struct_ops_detach.c

diff --git a/tools/testing/selftests/bpf/prog_tests/test_struct_ops_module.c b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_module.c
index 29e183a80f490..bbcf12696a6bc 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_struct_ops_module.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_module.c
@@ -3,9 +3,12 @@
 #include <test_progs.h>
 #include <time.h>
 
+#include <sys/epoll.h>
+
 #include "struct_ops_module.skel.h"
 #include "struct_ops_nulled_out_cb.skel.h"
 #include "struct_ops_forgotten_cb.skel.h"
+#include "struct_ops_detach.skel.h"
 
 static void check_map_info(struct bpf_map_info *info)
 {
@@ -242,6 +245,58 @@ cleanup:
 	struct_ops_forgotten_cb__destroy(skel);
 }
 
+/* Detach a link from a user space program */
+static void test_detach_link(void)
+{
+	struct epoll_event ev, events[2];
+	struct struct_ops_detach *skel;
+	struct bpf_link *link = NULL;
+	int fd, epollfd = -1, nfds;
+	int err;
+
+	skel = struct_ops_detach__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "struct_ops_detach__open_and_load"))
+		return;
+
+	link = bpf_map__attach_struct_ops(skel->maps.testmod_do_detach);
+	if (!ASSERT_OK_PTR(link, "attach_struct_ops"))
+		goto cleanup;
+
+	fd = bpf_link__fd(link);
+	if (!ASSERT_GE(fd, 0, "link_fd"))
+		goto cleanup;
+
+	epollfd = epoll_create1(0);
+	if (!ASSERT_GE(epollfd, 0, "epoll_create1"))
+		goto cleanup;
+
+	ev.events = EPOLLHUP;
+	ev.data.fd = fd;
+	err = epoll_ctl(epollfd, EPOLL_CTL_ADD, fd, &ev);
+	if (!ASSERT_OK(err, "epoll_ctl"))
+		goto cleanup;
+
+	err = bpf_link__detach(link);
+	if (!ASSERT_OK(err, "detach_link"))
+		goto cleanup;
+
+	/* Wait for EPOLLHUP */
+	nfds = epoll_wait(epollfd, events, 2, 500);
+	if (!ASSERT_EQ(nfds, 1, "epoll_wait"))
+		goto cleanup;
+
+	if (!ASSERT_EQ(events[0].data.fd, fd, "epoll_wait_fd"))
+		goto cleanup;
+	if (!ASSERT_TRUE(events[0].events & EPOLLHUP, "events[0].events"))
+		goto cleanup;
+
+cleanup:
+	if (epollfd >= 0)
+		close(epollfd);
+	bpf_link__destroy(link);
+	struct_ops_detach__destroy(skel);
+}
+
 void serial_test_struct_ops_module(void)
 {
 	if (test__start_subtest("struct_ops_load"))
@@ -254,5 +309,7 @@ void serial_test_struct_ops_module(void)
 		test_struct_ops_nulled_out_cb();
 	if (test__start_subtest("struct_ops_forgotten_cb"))
 		test_struct_ops_forgotten_cb();
+	if (test__start_subtest("test_detach_link"))
+		test_detach_link();
 }
 
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_detach.c b/tools/testing/selftests/bpf/progs/struct_ops_detach.c
new file mode 100644
index 0000000000000..56b787a898761
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/struct_ops_detach.c
@@ -0,0 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include "../bpf_testmod/bpf_testmod.h"
+
+char _license[] SEC("license") = "GPL";
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops testmod_do_detach;
-- 
GitLab


From d14c1fac0c9722c4ec79589921c9e798601ca9d5 Mon Sep 17 00:00:00 2001
From: Kui-Feng Lee <thinker.li@gmail.com>
Date: Wed, 29 May 2024 23:59:46 -0700
Subject: [PATCH 597/950] bpftool: Change pid_iter.bpf.c to comply with the
 change of bpf_link_fops.

To support epoll, a new instance of file_operations, bpf_link_fops_poll,
has been added for links that support epoll. The pid_iter.bpf.c checks
f_ops for links and other BPF objects. The check should fail for struct_ops
links without this patch.

Acked-by: Quentin Monnet <qmo@kernel.org>
Signed-off-by: Kui-Feng Lee <thinker.li@gmail.com>
Link: https://lore.kernel.org/r/20240530065946.979330-9-thinker.li@gmail.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/bpf/bpftool/skeleton/pid_iter.bpf.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/tools/bpf/bpftool/skeleton/pid_iter.bpf.c b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c
index 7bdbcac3cf628..948dde25034ef 100644
--- a/tools/bpf/bpftool/skeleton/pid_iter.bpf.c
+++ b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c
@@ -29,6 +29,7 @@ enum bpf_link_type___local {
 };
 
 extern const void bpf_link_fops __ksym;
+extern const void bpf_link_fops_poll __ksym __weak;
 extern const void bpf_map_fops __ksym;
 extern const void bpf_prog_fops __ksym;
 extern const void btf_fops __ksym;
@@ -84,7 +85,11 @@ int iter(struct bpf_iter__task_file *ctx)
 		fops = &btf_fops;
 		break;
 	case BPF_OBJ_LINK:
-		fops = &bpf_link_fops;
+		if (&bpf_link_fops_poll &&
+		    file->f_op == &bpf_link_fops_poll)
+			fops = &bpf_link_fops_poll;
+		else
+			fops = &bpf_link_fops;
 		break;
 	default:
 		return 0;
-- 
GitLab


From 6166bb0cacb62c388e4ed06167511a70591cc59a Mon Sep 17 00:00:00 2001
From: Joe Damato <jdamato@fastly.com>
Date: Tue, 28 May 2024 18:11:36 +0000
Subject: [PATCH 598/950] net/mlx4: Track RX allocation failures in a stat

mlx4_en_alloc_frags currently returns -ENOMEM when mlx4_alloc_page
fails but does not increment a stat field when this occurs.

A new field called alloc_fail has been added to struct mlx4_en_rx_ring
which is now incremented in mlx4_en_rx_ring when -ENOMEM occurs.

Signed-off-by: Joe Damato <jdamato@fastly.com>
Tested-by: Martin Karsten <mkarsten@uwaterloo.ca>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20240528181139.515070-2-jdamato@fastly.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 1 +
 drivers/net/ethernet/mellanox/mlx4/en_rx.c     | 4 +++-
 drivers/net/ethernet/mellanox/mlx4/mlx4_en.h   | 1 +
 3 files changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 4c089cfa027af..4d2f8c4583469 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -2073,6 +2073,7 @@ static void mlx4_en_clear_stats(struct net_device *dev)
 		priv->rx_ring[i]->csum_ok = 0;
 		priv->rx_ring[i]->csum_none = 0;
 		priv->rx_ring[i]->csum_complete = 0;
+		priv->rx_ring[i]->alloc_fail = 0;
 	}
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 8328df8645d50..15c57e9517e9a 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -82,8 +82,10 @@ static int mlx4_en_alloc_frags(struct mlx4_en_priv *priv,
 
 	for (i = 0; i < priv->num_frags; i++, frags++) {
 		if (!frags->page) {
-			if (mlx4_alloc_page(priv, frags, gfp))
+			if (mlx4_alloc_page(priv, frags, gfp)) {
+				ring->alloc_fail++;
 				return -ENOMEM;
+			}
 			ring->rx_alloc_pages++;
 		}
 		rx_desc->data[i].addr = cpu_to_be64(frags->dma +
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index efe3f97b874fe..cd70df22724bf 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -355,6 +355,7 @@ struct mlx4_en_rx_ring {
 	unsigned long xdp_tx;
 	unsigned long xdp_tx_full;
 	unsigned long dropped;
+	unsigned long alloc_fail;
 	int hwtstamp_rx_filter;
 	cpumask_var_t affinity_mask;
 	struct xdp_rxq_info xdp_rxq;
-- 
GitLab


From 64b62146ba9ee78c67e079b2ff09b106d8d6fd57 Mon Sep 17 00:00:00 2001
From: Joe Damato <jdamato@fastly.com>
Date: Tue, 28 May 2024 18:11:37 +0000
Subject: [PATCH 599/950] net/mlx4: link NAPI instances to queues and IRQs

Make mlx4 compatible with the newly added netlink queue GET APIs.

Signed-off-by: Joe Damato <jdamato@fastly.com>
Tested-by: Martin Karsten <mkarsten@uwaterloo.ca>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20240528181139.515070-3-jdamato@fastly.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx4/en_cq.c   | 14 ++++++++++++++
 drivers/net/ethernet/mellanox/mlx4/mlx4_en.h |  1 +
 2 files changed, 15 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_cq.c b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
index 1184ac5751e1b..461cc2c79c71f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
@@ -126,6 +126,7 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
 		cq_idx = cq_idx % priv->rx_ring_num;
 		rx_cq = priv->rx_cq[cq_idx];
 		cq->vector = rx_cq->vector;
+		irq = mlx4_eq_get_irq(mdev->dev, cq->vector);
 	}
 
 	if (cq->type == RX)
@@ -142,18 +143,23 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
 	if (err)
 		goto free_eq;
 
+	cq->cq_idx = cq_idx;
 	cq->mcq.event = mlx4_en_cq_event;
 
 	switch (cq->type) {
 	case TX:
 		cq->mcq.comp = mlx4_en_tx_irq;
 		netif_napi_add_tx(cq->dev, &cq->napi, mlx4_en_poll_tx_cq);
+		netif_napi_set_irq(&cq->napi, irq);
 		napi_enable(&cq->napi);
+		netif_queue_set_napi(cq->dev, cq_idx, NETDEV_QUEUE_TYPE_TX, &cq->napi);
 		break;
 	case RX:
 		cq->mcq.comp = mlx4_en_rx_irq;
 		netif_napi_add(cq->dev, &cq->napi, mlx4_en_poll_rx_cq);
+		netif_napi_set_irq(&cq->napi, irq);
 		napi_enable(&cq->napi);
+		netif_queue_set_napi(cq->dev, cq_idx, NETDEV_QUEUE_TYPE_RX, &cq->napi);
 		break;
 	case TX_XDP:
 		/* nothing regarding napi, it's shared with rx ring */
@@ -189,6 +195,14 @@ void mlx4_en_destroy_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq **pcq)
 void mlx4_en_deactivate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq)
 {
 	if (cq->type != TX_XDP) {
+		enum netdev_queue_type qtype;
+
+		if (cq->type == RX)
+			qtype = NETDEV_QUEUE_TYPE_RX;
+		else
+			qtype = NETDEV_QUEUE_TYPE_TX;
+
+		netif_queue_set_napi(cq->dev, cq->cq_idx, qtype, NULL);
 		napi_disable(&cq->napi);
 		netif_napi_del(&cq->napi);
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index cd70df22724bf..28b70dcc652e6 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -380,6 +380,7 @@ struct mlx4_en_cq {
 #define MLX4_EN_OPCODE_ERROR	0x1e
 
 	const struct cpumask *aff_mask;
+	int cq_idx;
 };
 
 struct mlx4_en_port_profile {
-- 
GitLab


From a5602c6edf7cbf5d69a32f089fb3938f42a3ff03 Mon Sep 17 00:00:00 2001
From: Joe Damato <jdamato@fastly.com>
Date: Tue, 28 May 2024 18:11:38 +0000
Subject: [PATCH 600/950] net/mlx4: support per-queue statistics via netlink

Make mlx4 compatible with the newly added netlink queue stats API.

Signed-off-by: Joe Damato <jdamato@fastly.com>
Tested-by: Martin Karsten <mkarsten@uwaterloo.ca>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20240528181139.515070-4-jdamato@fastly.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/mellanox/mlx4/en_netdev.c    | 73 +++++++++++++++++++
 1 file changed, 73 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 4d2f8c4583469..281b34af0bb48 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -43,6 +43,7 @@
 #include <net/vxlan.h>
 #include <net/devlink.h>
 #include <net/rps.h>
+#include <net/netdev_queues.h>
 
 #include <linux/mlx4/driver.h>
 #include <linux/mlx4/device.h>
@@ -3100,6 +3101,77 @@ void mlx4_en_set_stats_bitmap(struct mlx4_dev *dev,
 	last_i += NUM_PHY_STATS;
 }
 
+static void mlx4_get_queue_stats_rx(struct net_device *dev, int i,
+				    struct netdev_queue_stats_rx *stats)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+	const struct mlx4_en_rx_ring *ring;
+
+	spin_lock_bh(&priv->stats_lock);
+
+	if (!priv->port_up || mlx4_is_master(priv->mdev->dev))
+		goto out_unlock;
+
+	ring = priv->rx_ring[i];
+	stats->packets = READ_ONCE(ring->packets);
+	stats->bytes   = READ_ONCE(ring->bytes);
+	stats->alloc_fail = READ_ONCE(ring->alloc_fail);
+
+out_unlock:
+	spin_unlock_bh(&priv->stats_lock);
+}
+
+static void mlx4_get_queue_stats_tx(struct net_device *dev, int i,
+				    struct netdev_queue_stats_tx *stats)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+	const struct mlx4_en_tx_ring *ring;
+
+	spin_lock_bh(&priv->stats_lock);
+
+	if (!priv->port_up || mlx4_is_master(priv->mdev->dev))
+		goto out_unlock;
+
+	ring = priv->tx_ring[TX][i];
+	stats->packets = READ_ONCE(ring->packets);
+	stats->bytes   = READ_ONCE(ring->bytes);
+
+out_unlock:
+	spin_unlock_bh(&priv->stats_lock);
+}
+
+static void mlx4_get_base_stats(struct net_device *dev,
+				struct netdev_queue_stats_rx *rx,
+				struct netdev_queue_stats_tx *tx)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+
+	spin_lock_bh(&priv->stats_lock);
+
+	if (!priv->port_up || mlx4_is_master(priv->mdev->dev))
+		goto out_unlock;
+
+	if (priv->rx_ring_num) {
+		rx->packets = 0;
+		rx->bytes = 0;
+		rx->alloc_fail = 0;
+	}
+
+	if (priv->tx_ring_num[TX]) {
+		tx->packets = 0;
+		tx->bytes = 0;
+	}
+
+out_unlock:
+	spin_unlock_bh(&priv->stats_lock);
+}
+
+static const struct netdev_stat_ops mlx4_stat_ops = {
+	.get_queue_stats_rx     = mlx4_get_queue_stats_rx,
+	.get_queue_stats_tx     = mlx4_get_queue_stats_tx,
+	.get_base_stats         = mlx4_get_base_stats,
+};
+
 int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 			struct mlx4_en_port_profile *prof)
 {
@@ -3263,6 +3335,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 	netif_set_real_num_tx_queues(dev, priv->tx_ring_num[TX]);
 	netif_set_real_num_rx_queues(dev, priv->rx_ring_num);
 
+	dev->stat_ops = &mlx4_stat_ops;
 	dev->ethtool_ops = &mlx4_en_ethtool_ops;
 
 	/*
-- 
GitLab


From 935df1bd40d43c4ee91838c42a20e9af751885cc Mon Sep 17 00:00:00 2001
From: "Rob Herring (Arm)" <robh@kernel.org>
Date: Wed, 29 May 2024 14:59:20 -0500
Subject: [PATCH 601/950] of/irq: Factor out parsing of interrupt-map parent
 phandle+args from of_irq_parse_raw()

Factor out the parsing of interrupt-map interrupt parent phandle and its
arg cells to a separate function, of_irq_parse_imap_parent(), so that it
can be used in other parsing scenarios (e.g. fw_devlink).

There was a refcount leak on non-matching entries when iterating thru
"interrupt-map" which is fixed.

Tested-by: Marc Zyngier <maz@kernel.org>
Tested-by: Anup Patel <apatel@ventanamicro.com>
Link: https://lore.kernel.org/r/20240529-dt-interrupt-map-fix-v2-1-ef86dc5bcd2a@kernel.org
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
---
 drivers/of/irq.c        | 125 ++++++++++++++++++++++++----------------
 drivers/of/of_private.h |   3 +
 2 files changed, 77 insertions(+), 51 deletions(-)

diff --git a/drivers/of/irq.c b/drivers/of/irq.c
index 174900072c18c..462375b293e47 100644
--- a/drivers/of/irq.c
+++ b/drivers/of/irq.c
@@ -25,6 +25,8 @@
 #include <linux/string.h>
 #include <linux/slab.h>
 
+#include "of_private.h"
+
 /**
  * irq_of_parse_and_map - Parse and map an interrupt into linux virq space
  * @dev: Device node of the device whose interrupt is to be mapped
@@ -96,6 +98,57 @@ static const char * const of_irq_imap_abusers[] = {
 	NULL,
 };
 
+const __be32 *of_irq_parse_imap_parent(const __be32 *imap, int len, struct of_phandle_args *out_irq)
+{
+	u32 intsize, addrsize;
+	struct device_node *np;
+
+	/* Get the interrupt parent */
+	if (of_irq_workarounds & OF_IMAP_NO_PHANDLE)
+		np = of_node_get(of_irq_dflt_pic);
+	else
+		np = of_find_node_by_phandle(be32_to_cpup(imap));
+	imap++;
+
+	/* Check if not found */
+	if (!np) {
+		pr_debug(" -> imap parent not found !\n");
+		return NULL;
+	}
+
+	/* Get #interrupt-cells and #address-cells of new parent */
+	if (of_property_read_u32(np, "#interrupt-cells",
+					&intsize)) {
+		pr_debug(" -> parent lacks #interrupt-cells!\n");
+		of_node_put(np);
+		return NULL;
+	}
+	if (of_property_read_u32(np, "#address-cells",
+					&addrsize))
+		addrsize = 0;
+
+	pr_debug(" -> intsize=%d, addrsize=%d\n",
+		intsize, addrsize);
+
+	/* Check for malformed properties */
+	if (WARN_ON(addrsize + intsize > MAX_PHANDLE_ARGS)
+		|| (len < (addrsize + intsize))) {
+		of_node_put(np);
+		return NULL;
+	}
+
+	pr_debug(" -> imaplen=%d\n", len);
+
+	imap += addrsize + intsize;
+
+	out_irq->np = np;
+	for (int i = 0; i < intsize; i++)
+		out_irq->args[i] = be32_to_cpup(imap - intsize + i);
+	out_irq->args_count = intsize;
+
+	return imap;
+}
+
 /**
  * of_irq_parse_raw - Low level interrupt tree parsing
  * @addr:	address specifier (start of "reg" property of the device) in be32 format
@@ -112,12 +165,12 @@ static const char * const of_irq_imap_abusers[] = {
  */
 int of_irq_parse_raw(const __be32 *addr, struct of_phandle_args *out_irq)
 {
-	struct device_node *ipar, *tnode, *old = NULL, *newpar = NULL;
+	struct device_node *ipar, *tnode, *old = NULL;
 	__be32 initial_match_array[MAX_PHANDLE_ARGS];
 	const __be32 *match_array = initial_match_array;
-	const __be32 *tmp, *imap, *imask, dummy_imask[] = { [0 ... MAX_PHANDLE_ARGS] = cpu_to_be32(~0) };
-	u32 intsize = 1, addrsize, newintsize = 0, newaddrsize = 0;
-	int imaplen, match, i, rc = -EINVAL;
+	const __be32 *tmp, dummy_imask[] = { [0 ... MAX_PHANDLE_ARGS] = cpu_to_be32(~0) };
+	u32 intsize = 1, addrsize;
+	int i, rc = -EINVAL;
 
 #ifdef DEBUG
 	of_print_phandle_args("of_irq_parse_raw: ", out_irq);
@@ -176,6 +229,9 @@ int of_irq_parse_raw(const __be32 *addr, struct of_phandle_args *out_irq)
 
 	/* Now start the actual "proper" walk of the interrupt tree */
 	while (ipar != NULL) {
+		int imaplen, match;
+		const __be32 *imap, *oldimap, *imask;
+		struct device_node *newpar;
 		/*
 		 * Now check if cursor is an interrupt-controller and
 		 * if it is then we are done, unless there is an
@@ -216,7 +272,7 @@ int of_irq_parse_raw(const __be32 *addr, struct of_phandle_args *out_irq)
 
 		/* Parse interrupt-map */
 		match = 0;
-		while (imaplen > (addrsize + intsize + 1) && !match) {
+		while (imaplen > (addrsize + intsize + 1)) {
 			/* Compare specifiers */
 			match = 1;
 			for (i = 0; i < (addrsize + intsize); i++, imaplen--)
@@ -224,48 +280,17 @@ int of_irq_parse_raw(const __be32 *addr, struct of_phandle_args *out_irq)
 
 			pr_debug(" -> match=%d (imaplen=%d)\n", match, imaplen);
 
-			/* Get the interrupt parent */
-			if (of_irq_workarounds & OF_IMAP_NO_PHANDLE)
-				newpar = of_node_get(of_irq_dflt_pic);
-			else
-				newpar = of_find_node_by_phandle(be32_to_cpup(imap));
-			imap++;
-			--imaplen;
-
-			/* Check if not found */
-			if (newpar == NULL) {
-				pr_debug(" -> imap parent not found !\n");
-				goto fail;
-			}
-
-			if (!of_device_is_available(newpar))
-				match = 0;
-
-			/* Get #interrupt-cells and #address-cells of new
-			 * parent
-			 */
-			if (of_property_read_u32(newpar, "#interrupt-cells",
-						 &newintsize)) {
-				pr_debug(" -> parent lacks #interrupt-cells!\n");
-				goto fail;
-			}
-			if (of_property_read_u32(newpar, "#address-cells",
-						 &newaddrsize))
-				newaddrsize = 0;
-
-			pr_debug(" -> newintsize=%d, newaddrsize=%d\n",
-			    newintsize, newaddrsize);
-
-			/* Check for malformed properties */
-			if (WARN_ON(newaddrsize + newintsize > MAX_PHANDLE_ARGS)
-			    || (imaplen < (newaddrsize + newintsize))) {
-				rc = -EFAULT;
+			oldimap = imap;
+			imap = of_irq_parse_imap_parent(oldimap, imaplen, out_irq);
+			if (!imap)
 				goto fail;
-			}
 
-			imap += newaddrsize + newintsize;
-			imaplen -= newaddrsize + newintsize;
+			match &= of_device_is_available(out_irq->np);
+			if (match)
+				break;
 
+			of_node_put(out_irq->np);
+			imaplen -= imap - oldimap;
 			pr_debug(" -> imaplen=%d\n", imaplen);
 		}
 		if (!match) {
@@ -287,11 +312,11 @@ int of_irq_parse_raw(const __be32 *addr, struct of_phandle_args *out_irq)
 		 * Successfully parsed an interrupt-map translation; copy new
 		 * interrupt specifier into the out_irq structure
 		 */
-		match_array = imap - newaddrsize - newintsize;
-		for (i = 0; i < newintsize; i++)
-			out_irq->args[i] = be32_to_cpup(imap - newintsize + i);
-		out_irq->args_count = intsize = newintsize;
-		addrsize = newaddrsize;
+		match_array = oldimap + 1;
+
+		newpar = out_irq->np;
+		intsize = out_irq->args_count;
+		addrsize = (imap - match_array) - intsize;
 
 		if (ipar == newpar) {
 			pr_debug("%pOF interrupt-map entry to self\n", ipar);
@@ -300,7 +325,6 @@ int of_irq_parse_raw(const __be32 *addr, struct of_phandle_args *out_irq)
 
 	skiplevel:
 		/* Iterate again with new parent */
-		out_irq->np = newpar;
 		pr_debug(" -> new parent: %pOF\n", newpar);
 		of_node_put(ipar);
 		ipar = newpar;
@@ -310,7 +334,6 @@ int of_irq_parse_raw(const __be32 *addr, struct of_phandle_args *out_irq)
 
  fail:
 	of_node_put(ipar);
-	of_node_put(newpar);
 
 	return rc;
 }
diff --git a/drivers/of/of_private.h b/drivers/of/of_private.h
index 94fc0aa07af9e..04aa2a91f851a 100644
--- a/drivers/of/of_private.h
+++ b/drivers/of/of_private.h
@@ -159,6 +159,9 @@ extern void __of_sysfs_remove_bin_file(struct device_node *np,
 extern int of_bus_n_addr_cells(struct device_node *np);
 extern int of_bus_n_size_cells(struct device_node *np);
 
+const __be32 *of_irq_parse_imap_parent(const __be32 *imap, int len,
+				       struct of_phandle_args *out_irq);
+
 struct bus_dma_region;
 #if defined(CONFIG_OF_ADDRESS) && defined(CONFIG_HAS_DMA)
 int of_dma_get_range(struct device_node *np,
-- 
GitLab


From e7985f43609c782132f8f5794ee6cc4cdb66ca75 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Wed, 29 May 2024 14:59:21 -0500
Subject: [PATCH 602/950] of: property: Fix fw_devlink handling of
 interrupt-map

Commit d976c6f4b32c ("of: property: Add fw_devlink support for
interrupt-map property") tried to do what it says on the tin,
but failed on a couple of points:

- it confuses bytes and cells. Not a huge deal, except when it
  comes to pointer arithmetic

- it doesn't really handle anything but interrupt-maps that have
  their parent #address-cells set to 0

The combinations of the two leads to some serious fun on my M1
box, with plenty of WARN-ON() firing all over the shop, and
amusing values being generated for interrupt specifiers.

Having 2 versions of parsing code for "interrupt-map" was a bad
idea. Now that the common parsing parts have been refactored
into of_irq_parse_imap_parent(), rework the code here to use it
instead and fix the pointer arithmetic.

Note that the dependency will be a bit different than the original code
when the interrupt-map points to another interrupt-map. In this case,
the original code would resolve to the final interrupt controller. Now
the dependency is the parent interrupt-map (which itself should have a
dependency to the parent). It is possible that a node with an
interrupt-map has no driver.

Fixes: d976c6f4b32c ("of: property: Add fw_devlink support for interrupt-map property")
Signed-off-by: Marc Zyngier <maz@kernel.org>
Co-developed-by: Rob Herring (Arm) <robh@kernel.org>
Cc: Saravana Kannan <saravanak@google.com>
Tested-by: Marc Zyngier <maz@kernel.org>
Tested-by: Anup Patel <apatel@ventanamicro.com>
Link: https://lore.kernel.org/r/20240529-dt-interrupt-map-fix-v2-2-ef86dc5bcd2a@kernel.org
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
---
 drivers/of/property.c | 30 ++++++++++--------------------
 1 file changed, 10 insertions(+), 20 deletions(-)

diff --git a/drivers/of/property.c b/drivers/of/property.c
index 1c83e68f805ba..164d77cb94458 100644
--- a/drivers/of/property.c
+++ b/drivers/of/property.c
@@ -1306,10 +1306,10 @@ static struct device_node *parse_interrupts(struct device_node *np,
 static struct device_node *parse_interrupt_map(struct device_node *np,
 					       const char *prop_name, int index)
 {
-	const __be32 *imap, *imap_end, *addr;
+	const __be32 *imap, *imap_end;
 	struct of_phandle_args sup_args;
 	u32 addrcells, intcells;
-	int i, imaplen;
+	int imaplen;
 
 	if (!IS_ENABLED(CONFIG_OF_IRQ))
 		return NULL;
@@ -1322,33 +1322,23 @@ static struct device_node *parse_interrupt_map(struct device_node *np,
 	addrcells = of_bus_n_addr_cells(np);
 
 	imap = of_get_property(np, "interrupt-map", &imaplen);
-	if (!imap || imaplen <= (addrcells + intcells))
+	imaplen /= sizeof(*imap);
+	if (!imap)
 		return NULL;
-	imap_end = imap + imaplen;
 
-	while (imap < imap_end) {
-		addr = imap;
-		imap += addrcells;
+	imap_end = imap + imaplen;
 
-		sup_args.np = np;
-		sup_args.args_count = intcells;
-		for (i = 0; i < intcells; i++)
-			sup_args.args[i] = be32_to_cpu(imap[i]);
-		imap += intcells;
+	for (int i = 0; imap + addrcells + intcells + 1 < imap_end; i++) {
+		imap += addrcells + intcells;
 
-		/*
-		 * Upon success, the function of_irq_parse_raw() returns
-		 * interrupt controller DT node pointer in sup_args.np.
-		 */
-		if (of_irq_parse_raw(addr, &sup_args))
+		imap = of_irq_parse_imap_parent(imap, imap_end - imap, &sup_args);
+		if (!imap)
 			return NULL;
 
-		if (!index)
+		if (i == index)
 			return sup_args.np;
 
 		of_node_put(sup_args.np);
-		imap += sup_args.args_count + 1;
-		index--;
 	}
 
 	return NULL;
-- 
GitLab


From 727c94c9539aa8865cdbf6a783da6a6585f1fec2 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 28 May 2024 17:25:05 +0200
Subject: [PATCH 603/950] ethernet: octeontx2: avoid linking objects into
 multiple modules

Each object file contains information about which module it gets linked
into, so linking the same file into multiple modules now causes a warning:

scripts/Makefile.build:254: drivers/net/ethernet/marvell/octeontx2/nic/Makefile: otx2_devlink.o is added to multiple modules: rvu_nicpf rvu_nicvf

Change the way that octeontx2 ethernet is built by moving the common
file into a separate module with exported symbols instead.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20240528152527.2148092-1-arnd@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/marvell/octeontx2/nic/Makefile    | 14 ++++++++------
 .../ethernet/marvell/octeontx2/nic/otx2_dcbnl.c    | 11 +++++++++++
 .../ethernet/marvell/octeontx2/nic/otx2_devlink.c  |  6 ++++++
 3 files changed, 25 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/Makefile b/drivers/net/ethernet/marvell/octeontx2/nic/Makefile
index 5664f768cb0cd..e4c5dc46dd42d 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/Makefile
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/Makefile
@@ -3,16 +3,18 @@
 # Makefile for Marvell's RVU Ethernet device drivers
 #
 
-obj-$(CONFIG_OCTEONTX2_PF) += rvu_nicpf.o otx2_ptp.o
-obj-$(CONFIG_OCTEONTX2_VF) += rvu_nicvf.o otx2_ptp.o
+obj-$(CONFIG_OCTEONTX2_PF) += rvu_nicpf.o otx2_ptp.o otx2_devlink.o
+obj-$(CONFIG_OCTEONTX2_VF) += rvu_nicvf.o otx2_ptp.o otx2_devlink.o
 
 rvu_nicpf-y := otx2_pf.o otx2_common.o otx2_txrx.o otx2_ethtool.o \
                otx2_flows.o otx2_tc.o cn10k.o otx2_dmac_flt.o \
-               otx2_devlink.o qos_sq.o qos.o
-rvu_nicvf-y := otx2_vf.o otx2_devlink.o
+               qos_sq.o qos.o
+rvu_nicvf-y := otx2_vf.o
 
-rvu_nicpf-$(CONFIG_DCB) += otx2_dcbnl.o
-rvu_nicvf-$(CONFIG_DCB) += otx2_dcbnl.o
+ifdef CONFIG_DCB
+obj-$(CONFIG_OCTEONTX2_PF) += otx2_dcbnl.o
+obj-$(CONFIG_OCTEONTX2_VF) += otx2_dcbnl.o
+endif
 rvu_nicpf-$(CONFIG_MACSEC) += cn10k_macsec.o
 
 ccflags-y += -I$(srctree)/drivers/net/ethernet/marvell/octeontx2/af
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c
index 28fb643d2917f..0d7e611d9a05a 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c
@@ -54,6 +54,7 @@ int otx2_pfc_txschq_config(struct otx2_nic *pfvf)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(otx2_pfc_txschq_config);
 
 static int otx2_pfc_txschq_alloc_one(struct otx2_nic *pfvf, u8 prio)
 {
@@ -122,6 +123,7 @@ int otx2_pfc_txschq_alloc(struct otx2_nic *pfvf)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(otx2_pfc_txschq_alloc);
 
 static int otx2_pfc_txschq_stop_one(struct otx2_nic *pfvf, u8 prio)
 {
@@ -260,6 +262,7 @@ update_sq_smq_map:
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(otx2_pfc_txschq_update);
 
 int otx2_pfc_txschq_stop(struct otx2_nic *pfvf)
 {
@@ -282,6 +285,7 @@ int otx2_pfc_txschq_stop(struct otx2_nic *pfvf)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(otx2_pfc_txschq_stop);
 
 int otx2_config_priority_flow_ctrl(struct otx2_nic *pfvf)
 {
@@ -321,6 +325,7 @@ unlock:
 	mutex_unlock(&pfvf->mbox.lock);
 	return err;
 }
+EXPORT_SYMBOL_GPL(otx2_config_priority_flow_ctrl);
 
 void otx2_update_bpid_in_rqctx(struct otx2_nic *pfvf, int vlan_prio, int qidx,
 			       bool pfc_enable)
@@ -385,6 +390,7 @@ out:
 			 "Updating BPIDs in CQ and Aura contexts of RQ%d failed with err %d\n",
 			 qidx, err);
 }
+EXPORT_SYMBOL_GPL(otx2_update_bpid_in_rqctx);
 
 static int otx2_dcbnl_ieee_getpfc(struct net_device *dev, struct ieee_pfc *pfc)
 {
@@ -472,3 +478,8 @@ int otx2_dcbnl_set_ops(struct net_device *dev)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(otx2_dcbnl_set_ops);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Marvell RVU dcbnl");
+MODULE_AUTHOR("Sunil Goutham <sgoutham@marvell.com>");
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c
index 99ddf31269d96..440f574d11958 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c
@@ -113,6 +113,7 @@ err_dl:
 	devlink_free(dl);
 	return err;
 }
+EXPORT_SYMBOL_GPL(otx2_register_dl);
 
 void otx2_unregister_dl(struct otx2_nic *pfvf)
 {
@@ -124,3 +125,8 @@ void otx2_unregister_dl(struct otx2_nic *pfvf)
 				  ARRAY_SIZE(otx2_dl_params));
 	devlink_free(dl);
 }
+EXPORT_SYMBOL_GPL(otx2_unregister_dl);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Marvell RVU PF/VF Netdev Devlink");
+MODULE_AUTHOR("Sunil Goutham <sgoutham@marvell.com>");
-- 
GitLab


From e3bbb994a7e0ead1e028c5a8ec5f8526b4a9c5c9 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 28 May 2024 18:15:25 +0200
Subject: [PATCH 604/950] hns3: avoid linking objects into multiple modules

Each object file contains information about which module it gets linked
into, so linking the same file into multiple modules now causes a warning:

scripts/Makefile.build:254: drivers/net/ethernet/hisilicon/hns3/Makefile: hns3_common/hclge_comm_cmd.o is added to multiple modules: hclge hclgevf
scripts/Makefile.build:254: drivers/net/ethernet/hisilicon/hns3/Makefile: hns3_common/hclge_comm_rss.o is added to multiple modules: hclge hclgevf
scripts/Makefile.build:254: drivers/net/ethernet/hisilicon/hns3/Makefile: hns3_common/hclge_comm_tqp_stats.o is added to multiple modules: hclge hclgevf

Change the way that hns3 is built by moving the three common files into a
separate module with exported symbols instead.

Fixes: 5f20be4e90e6 ("net: hns3: refactor hns3 makefile to support hns3_common module")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20240528161603.2443125-1-arnd@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/hisilicon/hns3/Makefile       | 11 +++++------
 .../hisilicon/hns3/hns3_common/hclge_comm_cmd.c    | 11 +++++++++++
 .../hisilicon/hns3/hns3_common/hclge_comm_rss.c    | 14 ++++++++++++++
 .../hns3/hns3_common/hclge_comm_tqp_stats.c        |  5 +++++
 4 files changed, 35 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/Makefile b/drivers/net/ethernet/hisilicon/hns3/Makefile
index 8e9293e57bfd5..e8af26da1fc1e 100644
--- a/drivers/net/ethernet/hisilicon/hns3/Makefile
+++ b/drivers/net/ethernet/hisilicon/hns3/Makefile
@@ -15,15 +15,14 @@ hns3-objs = hns3_enet.o hns3_ethtool.o hns3_debugfs.o
 
 hns3-$(CONFIG_HNS3_DCB) += hns3_dcbnl.o
 
-obj-$(CONFIG_HNS3_HCLGEVF) += hclgevf.o
+obj-$(CONFIG_HNS3_HCLGEVF) += hclgevf.o hclge-common.o
 
-hclgevf-objs = hns3vf/hclgevf_main.o hns3vf/hclgevf_mbx.o  hns3vf/hclgevf_devlink.o hns3vf/hclgevf_regs.o \
-		hns3_common/hclge_comm_cmd.o hns3_common/hclge_comm_rss.o hns3_common/hclge_comm_tqp_stats.o
+hclge-common-objs += hns3_common/hclge_comm_cmd.o hns3_common/hclge_comm_rss.o hns3_common/hclge_comm_tqp_stats.o
 
-obj-$(CONFIG_HNS3_HCLGE) += hclge.o
+hclgevf-objs = hns3vf/hclgevf_main.o hns3vf/hclgevf_mbx.o  hns3vf/hclgevf_devlink.o hns3vf/hclgevf_regs.o
+
+obj-$(CONFIG_HNS3_HCLGE) += hclge.o hclge-common.o
 hclge-objs = hns3pf/hclge_main.o hns3pf/hclge_mdio.o hns3pf/hclge_tm.o hns3pf/hclge_regs.o \
 		hns3pf/hclge_mbx.o hns3pf/hclge_err.o  hns3pf/hclge_debugfs.o hns3pf/hclge_ptp.o hns3pf/hclge_devlink.o \
-		hns3_common/hclge_comm_cmd.o hns3_common/hclge_comm_rss.o hns3_common/hclge_comm_tqp_stats.o
-
 
 hclge-$(CONFIG_HNS3_DCB) += hns3pf/hclge_dcb.o
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.c
index ea40b594dbac7..4ad4e8ab2f1f3 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.c
@@ -48,6 +48,7 @@ void hclge_comm_cmd_reuse_desc(struct hclge_desc *desc, bool is_read)
 	else
 		desc->flag &= cpu_to_le16(~HCLGE_COMM_CMD_FLAG_WR);
 }
+EXPORT_SYMBOL_GPL(hclge_comm_cmd_reuse_desc);
 
 static void hclge_comm_set_default_capability(struct hnae3_ae_dev *ae_dev,
 					      bool is_pf)
@@ -72,6 +73,7 @@ void hclge_comm_cmd_setup_basic_desc(struct hclge_desc *desc,
 	if (is_read)
 		desc->flag |= cpu_to_le16(HCLGE_COMM_CMD_FLAG_WR);
 }
+EXPORT_SYMBOL_GPL(hclge_comm_cmd_setup_basic_desc);
 
 int hclge_comm_firmware_compat_config(struct hnae3_ae_dev *ae_dev,
 				      struct hclge_comm_hw *hw, bool en)
@@ -517,6 +519,7 @@ int hclge_comm_cmd_send(struct hclge_comm_hw *hw, struct hclge_desc *desc,
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(hclge_comm_cmd_send);
 
 static void hclge_comm_cmd_uninit_regs(struct hclge_comm_hw *hw)
 {
@@ -553,6 +556,7 @@ void hclge_comm_cmd_uninit(struct hnae3_ae_dev *ae_dev,
 	hclge_comm_free_cmd_desc(&cmdq->csq);
 	hclge_comm_free_cmd_desc(&cmdq->crq);
 }
+EXPORT_SYMBOL_GPL(hclge_comm_cmd_uninit);
 
 int hclge_comm_cmd_queue_init(struct pci_dev *pdev, struct hclge_comm_hw *hw)
 {
@@ -591,6 +595,7 @@ err_csq:
 	hclge_comm_free_cmd_desc(&hw->cmq.csq);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(hclge_comm_cmd_queue_init);
 
 void hclge_comm_cmd_init_ops(struct hclge_comm_hw *hw,
 			     const struct hclge_comm_cmq_ops *ops)
@@ -602,6 +607,7 @@ void hclge_comm_cmd_init_ops(struct hclge_comm_hw *hw,
 		cmdq->ops.trace_cmd_get = ops->trace_cmd_get;
 	}
 }
+EXPORT_SYMBOL_GPL(hclge_comm_cmd_init_ops);
 
 int hclge_comm_cmd_init(struct hnae3_ae_dev *ae_dev, struct hclge_comm_hw *hw,
 			u32 *fw_version, bool is_pf,
@@ -672,3 +678,8 @@ err_cmd_init:
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(hclge_comm_cmd_init);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("HNS3: Hisilicon Ethernet PF/VF Common Library");
+MODULE_AUTHOR("Huawei Tech. Co., Ltd.");
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_rss.c b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_rss.c
index b4ae2160aff4f..4e2bb6556b1ce 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_rss.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_rss.c
@@ -62,6 +62,7 @@ int hclge_comm_rss_init_cfg(struct hnae3_handle *nic,
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(hclge_comm_rss_init_cfg);
 
 void hclge_comm_get_rss_tc_info(u16 rss_size, u8 hw_tc_map, u16 *tc_offset,
 				u16 *tc_valid, u16 *tc_size)
@@ -78,6 +79,7 @@ void hclge_comm_get_rss_tc_info(u16 rss_size, u8 hw_tc_map, u16 *tc_offset,
 		tc_offset[i] = (hw_tc_map & BIT(i)) ? rss_size * i : 0;
 	}
 }
+EXPORT_SYMBOL_GPL(hclge_comm_get_rss_tc_info);
 
 int hclge_comm_set_rss_tc_mode(struct hclge_comm_hw *hw, u16 *tc_offset,
 			       u16 *tc_valid, u16 *tc_size)
@@ -113,6 +115,7 @@ int hclge_comm_set_rss_tc_mode(struct hclge_comm_hw *hw, u16 *tc_offset,
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(hclge_comm_set_rss_tc_mode);
 
 int hclge_comm_set_rss_hash_key(struct hclge_comm_rss_cfg *rss_cfg,
 				struct hclge_comm_hw *hw, const u8 *key,
@@ -143,6 +146,7 @@ int hclge_comm_set_rss_hash_key(struct hclge_comm_rss_cfg *rss_cfg,
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(hclge_comm_set_rss_hash_key);
 
 int hclge_comm_set_rss_tuple(struct hnae3_ae_dev *ae_dev,
 			     struct hclge_comm_hw *hw,
@@ -185,11 +189,13 @@ int hclge_comm_set_rss_tuple(struct hnae3_ae_dev *ae_dev,
 	rss_cfg->rss_tuple_sets.ipv6_fragment_en = req->ipv6_fragment_en;
 	return 0;
 }
+EXPORT_SYMBOL_GPL(hclge_comm_set_rss_tuple);
 
 u32 hclge_comm_get_rss_key_size(struct hnae3_handle *handle)
 {
 	return HCLGE_COMM_RSS_KEY_SIZE;
 }
+EXPORT_SYMBOL_GPL(hclge_comm_get_rss_key_size);
 
 int hclge_comm_parse_rss_hfunc(struct hclge_comm_rss_cfg *rss_cfg,
 			       const u8 hfunc, u8 *hash_algo)
@@ -217,6 +223,7 @@ void hclge_comm_rss_indir_init_cfg(struct hnae3_ae_dev *ae_dev,
 	for (i = 0; i < ae_dev->dev_specs.rss_ind_tbl_size; i++)
 		rss_cfg->rss_indirection_tbl[i] = i % rss_cfg->rss_size;
 }
+EXPORT_SYMBOL_GPL(hclge_comm_rss_indir_init_cfg);
 
 int hclge_comm_get_rss_tuple(struct hclge_comm_rss_cfg *rss_cfg, int flow_type,
 			     u8 *tuple_sets)
@@ -250,6 +257,7 @@ int hclge_comm_get_rss_tuple(struct hclge_comm_rss_cfg *rss_cfg, int flow_type,
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(hclge_comm_get_rss_tuple);
 
 static void
 hclge_comm_append_rss_msb_info(struct hclge_comm_rss_ind_tbl_cmd *req,
@@ -304,6 +312,7 @@ int hclge_comm_set_rss_indir_table(struct hnae3_ae_dev *ae_dev,
 	}
 	return 0;
 }
+EXPORT_SYMBOL_GPL(hclge_comm_set_rss_indir_table);
 
 int hclge_comm_set_rss_input_tuple(struct hclge_comm_hw *hw,
 				   struct hclge_comm_rss_cfg *rss_cfg)
@@ -332,6 +341,7 @@ int hclge_comm_set_rss_input_tuple(struct hclge_comm_hw *hw,
 			"failed to configure rss input, ret = %d.\n", ret);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(hclge_comm_set_rss_input_tuple);
 
 void hclge_comm_get_rss_hash_info(struct hclge_comm_rss_cfg *rss_cfg, u8 *key,
 				  u8 *hfunc)
@@ -355,6 +365,7 @@ void hclge_comm_get_rss_hash_info(struct hclge_comm_rss_cfg *rss_cfg, u8 *key,
 	if (key)
 		memcpy(key, rss_cfg->rss_hash_key, HCLGE_COMM_RSS_KEY_SIZE);
 }
+EXPORT_SYMBOL_GPL(hclge_comm_get_rss_hash_info);
 
 void hclge_comm_get_rss_indir_tbl(struct hclge_comm_rss_cfg *rss_cfg,
 				  u32 *indir, u16 rss_ind_tbl_size)
@@ -367,6 +378,7 @@ void hclge_comm_get_rss_indir_tbl(struct hclge_comm_rss_cfg *rss_cfg,
 	for (i = 0; i < rss_ind_tbl_size; i++)
 		indir[i] = rss_cfg->rss_indirection_tbl[i];
 }
+EXPORT_SYMBOL_GPL(hclge_comm_get_rss_indir_tbl);
 
 int hclge_comm_set_rss_algo_key(struct hclge_comm_hw *hw, const u8 hfunc,
 				const u8 *key)
@@ -408,6 +420,7 @@ int hclge_comm_set_rss_algo_key(struct hclge_comm_hw *hw, const u8 hfunc,
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(hclge_comm_set_rss_algo_key);
 
 static u8 hclge_comm_get_rss_hash_bits(struct ethtool_rxnfc *nfc)
 {
@@ -502,3 +515,4 @@ u64 hclge_comm_convert_rss_tuple(u8 tuple_sets)
 
 	return tuple_data;
 }
+EXPORT_SYMBOL_GPL(hclge_comm_convert_rss_tuple);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.c b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.c
index 618f66d9586b3..2b31188ff5558 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.c
@@ -26,6 +26,7 @@ u64 *hclge_comm_tqps_get_stats(struct hnae3_handle *handle, u64 *data)
 
 	return buff;
 }
+EXPORT_SYMBOL_GPL(hclge_comm_tqps_get_stats);
 
 int hclge_comm_tqps_get_sset_count(struct hnae3_handle *handle)
 {
@@ -33,6 +34,7 @@ int hclge_comm_tqps_get_sset_count(struct hnae3_handle *handle)
 
 	return kinfo->num_tqps * HCLGE_COMM_QUEUE_PAIR_SIZE;
 }
+EXPORT_SYMBOL_GPL(hclge_comm_tqps_get_sset_count);
 
 u8 *hclge_comm_tqps_get_strings(struct hnae3_handle *handle, u8 *data)
 {
@@ -56,6 +58,7 @@ u8 *hclge_comm_tqps_get_strings(struct hnae3_handle *handle, u8 *data)
 
 	return buff;
 }
+EXPORT_SYMBOL_GPL(hclge_comm_tqps_get_strings);
 
 int hclge_comm_tqps_update_stats(struct hnae3_handle *handle,
 				 struct hclge_comm_hw *hw)
@@ -99,6 +102,7 @@ int hclge_comm_tqps_update_stats(struct hnae3_handle *handle,
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(hclge_comm_tqps_update_stats);
 
 void hclge_comm_reset_tqp_stats(struct hnae3_handle *handle)
 {
@@ -113,3 +117,4 @@ void hclge_comm_reset_tqp_stats(struct hnae3_handle *handle)
 		memset(&tqp->tqp_stats, 0, sizeof(tqp->tqp_stats));
 	}
 }
+EXPORT_SYMBOL_GPL(hclge_comm_reset_tqp_stats);
-- 
GitLab


From 3eb76e71b16e8ba5277bf97617aef51f5e64dbe4 Mon Sep 17 00:00:00 2001
From: Shannon Nelson <shannon.nelson@amd.com>
Date: Tue, 28 May 2024 17:02:53 -0700
Subject: [PATCH 605/950] ionic: fix potential irq name truncation

Address a warning about potential string truncation based on the
string buffer sizes.  We can add some hints to the string format
specifier to set limits on the resulting possible string to
squelch the complaints.

Signed-off-by: Shannon Nelson <shannon.nelson@amd.com>
Link: https://lore.kernel.org/r/20240529000259.25775-2-shannon.nelson@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/pensando/ionic/ionic_lif.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
index 24870da3f4848..12fda3b860b94 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@@ -242,7 +242,7 @@ static int ionic_request_irq(struct ionic_lif *lif, struct ionic_qcq *qcq)
 		name = dev_name(dev);
 
 	snprintf(intr->name, sizeof(intr->name),
-		 "%s-%s-%s", IONIC_DRV_NAME, name, q->name);
+		 "%.5s-%.16s-%.8s", IONIC_DRV_NAME, name, q->name);
 
 	return devm_request_irq(dev, intr->vector, ionic_isr,
 				0, intr->name, &qcq->napi);
-- 
GitLab


From 8097a2f3d21a672c772ca1919f253e611f2f0bad Mon Sep 17 00:00:00 2001
From: Shannon Nelson <shannon.nelson@amd.com>
Date: Tue, 28 May 2024 17:02:54 -0700
Subject: [PATCH 606/950] ionic: Reset LIF device while restarting LIF

Recovery from broken states can be hard.  If the LIF reset in
the fw_down path didn't work because the PCI link was broken,
the FW won't be in the right state for proper restart.  We can
fire another LIF reset in the fw_up path to be sure things
are clean on restart.

Signed-off-by: Shannon Nelson <shannon.nelson@amd.com>
Link: https://lore.kernel.org/r/20240529000259.25775-3-shannon.nelson@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/pensando/ionic/ionic_lif.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
index 12fda3b860b94..101cbc088853e 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@@ -3388,6 +3388,7 @@ static void ionic_lif_handle_fw_up(struct ionic_lif *lif)
 	 * just need to reanimate it.
 	 */
 	ionic_init_devinfo(ionic);
+	ionic_reset(ionic);
 	err = ionic_identify(ionic);
 	if (err)
 		goto err_out;
-- 
GitLab


From 4dde9588c54d1d86a415a5ed7dc6d8a605fe11ce Mon Sep 17 00:00:00 2001
From: Brett Creeley <brett.creeley@amd.com>
Date: Tue, 28 May 2024 17:02:55 -0700
Subject: [PATCH 607/950] ionic: Pass ionic_txq_desc to ionic_tx_tso_post

Pass the ionic_txq_desc instead of re-referencing it from the q->txq
array since the caller to ionic_tx_tso_post will always have the
current ionic_txq_desc pointer already.

Signed-off-by: Brett Creeley <brett.creeley@amd.com>
Signed-off-by: Shannon Nelson <shannon.nelson@amd.com>
Link: https://lore.kernel.org/r/20240529000259.25775-4-shannon.nelson@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/pensando/ionic/ionic_txrx.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
index 5dba6d2d633cb..c6aa8fb743be0 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
@@ -1357,7 +1357,7 @@ static int ionic_tx_tcp_pseudo_csum(struct sk_buff *skb)
 }
 
 static void ionic_tx_tso_post(struct net_device *netdev, struct ionic_queue *q,
-			      struct ionic_tx_desc_info *desc_info,
+			      struct ionic_txq_desc *desc,
 			      struct sk_buff *skb,
 			      dma_addr_t addr, u8 nsge, u16 len,
 			      unsigned int hdrlen, unsigned int mss,
@@ -1365,7 +1365,6 @@ static void ionic_tx_tso_post(struct net_device *netdev, struct ionic_queue *q,
 			      u16 vlan_tci, bool has_vlan,
 			      bool start, bool done)
 {
-	struct ionic_txq_desc *desc = &q->txq[q->head_idx];
 	u8 flags = 0;
 	u64 cmd;
 
@@ -1503,10 +1502,9 @@ static int ionic_tx_tso(struct net_device *netdev, struct ionic_queue *q,
 		seg_rem = min(tso_rem, mss);
 		done = (tso_rem == 0);
 		/* post descriptor */
-		ionic_tx_tso_post(netdev, q, desc_info, skb,
-				  desc_addr, desc_nsge, desc_len,
-				  hdrlen, mss, outer_csum, vlan_tci, has_vlan,
-				  start, done);
+		ionic_tx_tso_post(netdev, q, desc, skb, desc_addr, desc_nsge,
+				  desc_len, hdrlen, mss, outer_csum, vlan_tci,
+				  has_vlan, start, done);
 		start = false;
 		/* Buffer information is stored with the first tso descriptor */
 		desc_info = &q->tx_info[q->head_idx];
-- 
GitLab


From d9c04209990be6c03a354b124e012293273e05d5 Mon Sep 17 00:00:00 2001
From: Brett Creeley <brett.creeley@amd.com>
Date: Tue, 28 May 2024 17:02:56 -0700
Subject: [PATCH 608/950] ionic: Mark error paths in the data path as unlikely

As the title states, mark unlikely error paths in the data path as
unlikely.

Signed-off-by: Brett Creeley <brett.creeley@amd.com>
Signed-off-by: Shannon Nelson <shannon.nelson@amd.com>
Link: https://lore.kernel.org/r/20240529000259.25775-5-shannon.nelson@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/pensando/ionic/ionic_txrx.c  | 20 +++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
index c6aa8fb743be0..14aa3844b6999 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
@@ -582,7 +582,7 @@ static bool ionic_run_xdp(struct ionic_rx_stats *stats,
 					   buf_info->page_offset,
 					   true);
 		__netif_tx_unlock(nq);
-		if (err) {
+		if (unlikely(err)) {
 			netdev_dbg(netdev, "tx ionic_xdp_post_frame err %d\n", err);
 			goto out_xdp_abort;
 		}
@@ -597,7 +597,7 @@ static bool ionic_run_xdp(struct ionic_rx_stats *stats,
 			       IONIC_PAGE_SIZE, DMA_FROM_DEVICE);
 
 		err = xdp_do_redirect(netdev, &xdp_buf, xdp_prog);
-		if (err) {
+		if (unlikely(err)) {
 			netdev_dbg(netdev, "xdp_do_redirect err %d\n", err);
 			goto out_xdp_abort;
 		}
@@ -1058,7 +1058,7 @@ static dma_addr_t ionic_tx_map_single(struct ionic_queue *q,
 	dma_addr_t dma_addr;
 
 	dma_addr = dma_map_single(dev, data, len, DMA_TO_DEVICE);
-	if (dma_mapping_error(dev, dma_addr)) {
+	if (unlikely(dma_mapping_error(dev, dma_addr))) {
 		net_warn_ratelimited("%s: DMA single map failed on %s!\n",
 				     dev_name(dev), q->name);
 		q_to_tx_stats(q)->dma_map_err++;
@@ -1075,7 +1075,7 @@ static dma_addr_t ionic_tx_map_frag(struct ionic_queue *q,
 	dma_addr_t dma_addr;
 
 	dma_addr = skb_frag_dma_map(dev, frag, offset, len, DMA_TO_DEVICE);
-	if (dma_mapping_error(dev, dma_addr)) {
+	if (unlikely(dma_mapping_error(dev, dma_addr))) {
 		net_warn_ratelimited("%s: DMA frag map failed on %s!\n",
 				     dev_name(dev), q->name);
 		q_to_tx_stats(q)->dma_map_err++;
@@ -1316,7 +1316,7 @@ static int ionic_tx_tcp_inner_pseudo_csum(struct sk_buff *skb)
 	int err;
 
 	err = skb_cow_head(skb, 0);
-	if (err)
+	if (unlikely(err))
 		return err;
 
 	if (skb->protocol == cpu_to_be16(ETH_P_IP)) {
@@ -1340,7 +1340,7 @@ static int ionic_tx_tcp_pseudo_csum(struct sk_buff *skb)
 	int err;
 
 	err = skb_cow_head(skb, 0);
-	if (err)
+	if (unlikely(err))
 		return err;
 
 	if (skb->protocol == cpu_to_be16(ETH_P_IP)) {
@@ -1444,7 +1444,7 @@ static int ionic_tx_tso(struct net_device *netdev, struct ionic_queue *q,
 		err = ionic_tx_tcp_inner_pseudo_csum(skb);
 	else
 		err = ionic_tx_tcp_pseudo_csum(skb);
-	if (err) {
+	if (unlikely(err)) {
 		/* clean up mapping from ionic_tx_map_skb */
 		ionic_tx_desc_unmap_bufs(q, desc_info);
 		return err;
@@ -1729,7 +1729,7 @@ static int ionic_tx_descs_needed(struct ionic_queue *q, struct sk_buff *skb)
 linearize:
 	if (too_many_frags) {
 		err = skb_linearize(skb);
-		if (err)
+		if (unlikely(err))
 			return err;
 		q_to_tx_stats(q)->linearize++;
 	}
@@ -1763,7 +1763,7 @@ static netdev_tx_t ionic_start_hwstamp_xmit(struct sk_buff *skb,
 	else
 		err = ionic_tx(netdev, q, skb);
 
-	if (err)
+	if (unlikely(err))
 		goto err_out_drop;
 
 	return NETDEV_TX_OK;
@@ -1809,7 +1809,7 @@ netdev_tx_t ionic_start_xmit(struct sk_buff *skb, struct net_device *netdev)
 	else
 		err = ionic_tx(netdev, q, skb);
 
-	if (err)
+	if (unlikely(err))
 		goto err_out_drop;
 
 	return NETDEV_TX_OK;
-- 
GitLab


From fc53d46524480a732a233bc9d6cdf6155205d9eb Mon Sep 17 00:00:00 2001
From: Brett Creeley <brett.creeley@amd.com>
Date: Tue, 28 May 2024 17:02:57 -0700
Subject: [PATCH 609/950] ionic: Use netdev_name() function instead of
 netdev->name

There is no reason not to use netdev_name() in these places, so do just
as the title states.

Signed-off-by: Brett Creeley <brett.creeley@amd.com>
Signed-off-by: Shannon Nelson <shannon.nelson@amd.com>
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Link: https://lore.kernel.org/r/20240529000259.25775-6-shannon.nelson@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/pensando/ionic/ionic_debugfs.c | 2 +-
 drivers/net/ethernet/pensando/ionic/ionic_lif.c     | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c b/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c
index c3ae11a480242..59e5a9f211052 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c
@@ -220,7 +220,7 @@ static int netdev_show(struct seq_file *seq, void *v)
 {
 	struct net_device *netdev = seq->private;
 
-	seq_printf(seq, "%s\n", netdev->name);
+	seq_printf(seq, "%s\n", netdev_name(netdev));
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
index 101cbc088853e..23e1f6638b38f 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@@ -237,7 +237,7 @@ static int ionic_request_irq(struct ionic_lif *lif, struct ionic_qcq *qcq)
 	const char *name;
 
 	if (lif->registered)
-		name = lif->netdev->name;
+		name = netdev_name(lif->netdev);
 	else
 		name = dev_name(dev);
 
@@ -3732,7 +3732,7 @@ static void ionic_lif_set_netdev_info(struct ionic_lif *lif)
 		},
 	};
 
-	strscpy(ctx.cmd.lif_setattr.name, lif->netdev->name,
+	strscpy(ctx.cmd.lif_setattr.name, netdev_name(lif->netdev),
 		sizeof(ctx.cmd.lif_setattr.name));
 
 	ionic_adminq_post_wait(lif, &ctx);
-- 
GitLab


From 488da00479d50ec5970b3f84e9fad2c5fda2d78c Mon Sep 17 00:00:00 2001
From: Shannon Nelson <shannon.nelson@amd.com>
Date: Tue, 28 May 2024 17:02:58 -0700
Subject: [PATCH 610/950] ionic: only sync frag_len in first buffer of xdp

We don't want to try to sync more length than might be
in the first frag of an Rx skb, so make sure to use
the frag_len rather than the full len.

Signed-off-by: Shannon Nelson <shannon.nelson@amd.com>
Link: https://lore.kernel.org/r/20240529000259.25775-7-shannon.nelson@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/pensando/ionic/ionic_txrx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
index 14aa3844b6999..c3a6c4af52f11 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
@@ -502,7 +502,7 @@ static bool ionic_run_xdp(struct ionic_rx_stats *stats,
 			 XDP_PACKET_HEADROOM, frag_len, false);
 
 	dma_sync_single_range_for_cpu(rxq->dev, ionic_rx_buf_pa(buf_info),
-				      XDP_PACKET_HEADROOM, len,
+				      XDP_PACKET_HEADROOM, frag_len,
 				      DMA_FROM_DEVICE);
 
 	prefetchw(&xdp_buf.data_hard_start);
-- 
GitLab


From a54e2a36b68c30822d3571b969e24aa429b3d1a5 Mon Sep 17 00:00:00 2001
From: Shannon Nelson <shannon.nelson@amd.com>
Date: Tue, 28 May 2024 17:02:59 -0700
Subject: [PATCH 611/950] ionic: fix up ionic_if.h kernel-doc issues

All the changes here are whitespace and comments, no code
or definitions changed.  Not all issues were addressed, but
it is much better than it was.  Mostly fixed was a lot
of "Excess union member" and ''rsvd' not described' warnings.

Signed-off-by: Shannon Nelson <shannon.nelson@amd.com>
Link: https://lore.kernel.org/r/20240529000259.25775-8-shannon.nelson@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/pensando/ionic/ionic_if.h    | 237 +++++++++++++-----
 1 file changed, 181 insertions(+), 56 deletions(-)

diff --git a/drivers/net/ethernet/pensando/ionic/ionic_if.h b/drivers/net/ethernet/pensando/ionic/ionic_if.h
index 9a1825edf0d04..9c85c0706c6e1 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_if.h
+++ b/drivers/net/ethernet/pensando/ionic/ionic_if.h
@@ -71,7 +71,7 @@ enum ionic_cmd_opcode {
 	IONIC_CMD_FW_CONTROL_V1		        = 255,
 };
 
-/**
+/*
  * enum ionic_status_code - Device command return codes
  */
 enum ionic_status_code {
@@ -112,6 +112,7 @@ enum ionic_notifyq_opcode {
 /**
  * struct ionic_admin_cmd - General admin command format
  * @opcode:     Opcode for the command
+ * @rsvd:       reserved byte(s)
  * @lif_index:  LIF index
  * @cmd_data:   Opcode-specific command bytes
  */
@@ -125,6 +126,7 @@ struct ionic_admin_cmd {
 /**
  * struct ionic_admin_comp - General admin command completion format
  * @status:     Status of the command (enum ionic_status_code)
+ * @rsvd:       reserved byte(s)
  * @comp_index: Index in the descriptor ring for which this is the completion
  * @cmd_data:   Command-specific bytes
  * @color:      Color bit (Always 0 for commands issued to the
@@ -147,6 +149,7 @@ static inline u8 color_match(u8 color, u8 done_color)
 /**
  * struct ionic_nop_cmd - NOP command
  * @opcode: opcode
+ * @rsvd:   reserved byte(s)
  */
 struct ionic_nop_cmd {
 	u8 opcode;
@@ -156,6 +159,7 @@ struct ionic_nop_cmd {
 /**
  * struct ionic_nop_comp - NOP command completion
  * @status: Status of the command (enum ionic_status_code)
+ * @rsvd:   reserved byte(s)
  */
 struct ionic_nop_comp {
 	u8 status;
@@ -166,6 +170,7 @@ struct ionic_nop_comp {
  * struct ionic_dev_init_cmd - Device init command
  * @opcode:    opcode
  * @type:      Device type
+ * @rsvd:      reserved byte(s)
  */
 struct ionic_dev_init_cmd {
 	u8     opcode;
@@ -176,6 +181,7 @@ struct ionic_dev_init_cmd {
 /**
  * struct ionic_dev_init_comp - Device init command completion
  * @status: Status of the command (enum ionic_status_code)
+ * @rsvd:   reserved byte(s)
  */
 struct ionic_dev_init_comp {
 	u8 status;
@@ -185,6 +191,7 @@ struct ionic_dev_init_comp {
 /**
  * struct ionic_dev_reset_cmd - Device reset command
  * @opcode: opcode
+ * @rsvd:   reserved byte(s)
  */
 struct ionic_dev_reset_cmd {
 	u8 opcode;
@@ -194,6 +201,7 @@ struct ionic_dev_reset_cmd {
 /**
  * struct ionic_dev_reset_comp - Reset command completion
  * @status: Status of the command (enum ionic_status_code)
+ * @rsvd:   reserved byte(s)
  */
 struct ionic_dev_reset_comp {
 	u8 status;
@@ -207,6 +215,7 @@ struct ionic_dev_reset_comp {
  * struct ionic_dev_identify_cmd - Driver/device identify command
  * @opcode:  opcode
  * @ver:     Highest version of identify supported by driver
+ * @rsvd:    reserved byte(s)
  */
 struct ionic_dev_identify_cmd {
 	u8 opcode;
@@ -218,6 +227,7 @@ struct ionic_dev_identify_cmd {
  * struct ionic_dev_identify_comp - Driver/device identify command completion
  * @status: Status of the command (enum ionic_status_code)
  * @ver:    Version of identify returned by device
+ * @rsvd:   reserved byte(s)
  */
 struct ionic_dev_identify_comp {
 	u8 status;
@@ -242,6 +252,7 @@ enum ionic_os_type {
  * @kernel_ver:       Kernel version, numeric format
  * @kernel_ver_str:   Kernel version, string format
  * @driver_ver_str:   Driver version, string format
+ * @words:            word access to struct contents
  */
 union ionic_drv_identity {
 	struct {
@@ -267,7 +278,9 @@ enum ionic_dev_capability {
  * union ionic_dev_identity - device identity information
  * @version:          Version of device identify
  * @type:             Identify type (0 for now)
+ * @rsvd:             reserved byte(s)
  * @nports:           Number of ports provisioned
+ * @rsvd2:            reserved byte(s)
  * @nlifs:            Number of LIFs provisioned
  * @nintrs:           Number of interrupts provisioned
  * @ndbpgs_per_lif:   Number of doorbell pages per LIF
@@ -284,6 +297,7 @@ enum ionic_dev_capability {
  * @hwstamp_mult:     Hardware tick to nanosecond multiplier.
  * @hwstamp_shift:    Hardware tick to nanosecond divisor (power of two).
  * @capabilities:     Device capabilities
+ * @words:            word access to struct contents
  */
 union ionic_dev_identity {
 	struct {
@@ -317,6 +331,7 @@ enum ionic_lif_type {
  * @opcode:  opcode
  * @type:    LIF type (enum ionic_lif_type)
  * @ver:     Version of identify returned by device
+ * @rsvd:    reserved byte(s)
  */
 struct ionic_lif_identify_cmd {
 	u8 opcode;
@@ -329,6 +344,7 @@ struct ionic_lif_identify_cmd {
  * struct ionic_lif_identify_comp - LIF identify command completion
  * @status:  Status of the command (enum ionic_status_code)
  * @ver:     Version of identify returned by device
+ * @rsvd2:   reserved byte(s)
  */
 struct ionic_lif_identify_comp {
 	u8 status;
@@ -416,7 +432,7 @@ enum ionic_txq_feature {
 };
 
 /**
- * struct ionic_hwstamp_bits - Hardware timestamp decoding bits
+ * enum ionic_hwstamp_bits - Hardware timestamp decoding bits
  * @IONIC_HWSTAMP_INVALID:          Invalid hardware timestamp value
  * @IONIC_HWSTAMP_CQ_NEGOFFSET:     Timestamp field negative offset
  *                                  from the base cq descriptor.
@@ -429,6 +445,7 @@ enum ionic_hwstamp_bits {
 /**
  * struct ionic_lif_logical_qtype - Descriptor of logical to HW queue type
  * @qtype:          Hardware Queue Type
+ * @rsvd:           reserved byte(s)
  * @qid_count:      Number of Queue IDs of the logical type
  * @qid_base:       Minimum Queue ID of the logical type
  */
@@ -454,12 +471,14 @@ enum ionic_lif_state {
 /**
  * union ionic_lif_config - LIF configuration
  * @state:          LIF state (enum ionic_lif_state)
+ * @rsvd:           reserved byte(s)
  * @name:           LIF name
  * @mtu:            MTU
  * @mac:            Station MAC address
  * @vlan:           Default Vlan ID
  * @features:       Features (enum ionic_eth_hw_features)
  * @queue_count:    Queue counts per queue-type
+ * @words:          word access to struct contents
  */
 union ionic_lif_config {
 	struct {
@@ -481,33 +500,39 @@ union ionic_lif_config {
  * @capabilities:        LIF capabilities
  *
  * @eth:                    Ethernet identify structure
- *     @version:            Ethernet identify structure version
- *     @max_ucast_filters:  Number of perfect unicast addresses supported
- *     @max_mcast_filters:  Number of perfect multicast addresses supported
- *     @min_frame_size:     Minimum size of frames to be sent
- *     @max_frame_size:     Maximum size of frames to be sent
- *     @hwstamp_tx_modes:   Bitmask of BIT_ULL(enum ionic_txstamp_mode)
- *     @hwstamp_rx_filters: Bitmask of enum ionic_pkt_class
- *     @config:             LIF config struct with features, mtu, mac, q counts
+ *	@eth.version:            Ethernet identify structure version
+ *	@eth.rsvd:               reserved byte(s)
+ *	@eth.max_ucast_filters:  Number of perfect unicast addresses supported
+ *	@eth.max_mcast_filters:  Number of perfect multicast addresses supported
+ *	@eth.min_frame_size:     Minimum size of frames to be sent
+ *	@eth.max_frame_size:     Maximum size of frames to be sent
+ *	@eth.rsvd2:              reserved byte(s)
+ *	@eth.hwstamp_tx_modes:   Bitmask of BIT_ULL(enum ionic_txstamp_mode)
+ *	@eth.hwstamp_rx_filters: Bitmask of enum ionic_pkt_class
+ *	@eth.rsvd3:              reserved byte(s)
+ *	@eth.config:             LIF config struct with features, mtu, mac, q counts
  *
  * @rdma:                RDMA identify structure
- *     @version:         RDMA version of opcodes and queue descriptors
- *     @qp_opcodes:      Number of RDMA queue pair opcodes supported
- *     @admin_opcodes:   Number of RDMA admin opcodes supported
- *     @npts_per_lif:    Page table size per LIF
- *     @nmrs_per_lif:    Number of memory regions per LIF
- *     @nahs_per_lif:    Number of address handles per LIF
- *     @max_stride:      Max work request stride
- *     @cl_stride:       Cache line stride
- *     @pte_stride:      Page table entry stride
- *     @rrq_stride:      Remote RQ work request stride
- *     @rsq_stride:      Remote SQ work request stride
- *     @dcqcn_profiles:  Number of DCQCN profiles
- *     @aq_qtype:        RDMA Admin Qtype
- *     @sq_qtype:        RDMA Send Qtype
- *     @rq_qtype:        RDMA Receive Qtype
- *     @cq_qtype:        RDMA Completion Qtype
- *     @eq_qtype:        RDMA Event Qtype
+ *	@rdma.version:         RDMA version of opcodes and queue descriptors
+ *	@rdma.qp_opcodes:      Number of RDMA queue pair opcodes supported
+ *	@rdma.admin_opcodes:   Number of RDMA admin opcodes supported
+ *	@rdma.rsvd:            reserved byte(s)
+ *	@rdma.npts_per_lif:    Page table size per LIF
+ *	@rdma.nmrs_per_lif:    Number of memory regions per LIF
+ *	@rdma.nahs_per_lif:    Number of address handles per LIF
+ *	@rdma.max_stride:      Max work request stride
+ *	@rdma.cl_stride:       Cache line stride
+ *	@rdma.pte_stride:      Page table entry stride
+ *	@rdma.rrq_stride:      Remote RQ work request stride
+ *	@rdma.rsq_stride:      Remote SQ work request stride
+ *	@rdma.dcqcn_profiles:  Number of DCQCN profiles
+ *	@rdma.rsvd_dimensions: reserved byte(s)
+ *	@rdma.aq_qtype:        RDMA Admin Qtype
+ *	@rdma.sq_qtype:        RDMA Send Qtype
+ *	@rdma.rq_qtype:        RDMA Receive Qtype
+ *	@rdma.cq_qtype:        RDMA Completion Qtype
+ *	@rdma.eq_qtype:        RDMA Event Qtype
+ * @words:               word access to struct contents
  */
 union ionic_lif_identity {
 	struct {
@@ -558,7 +583,9 @@ union ionic_lif_identity {
  * @opcode:       Opcode
  * @type:         LIF type (enum ionic_lif_type)
  * @index:        LIF index
+ * @rsvd:         reserved byte(s)
  * @info_pa:      Destination address for LIF info (struct ionic_lif_info)
+ * @rsvd2:        reserved byte(s)
  */
 struct ionic_lif_init_cmd {
 	u8     opcode;
@@ -572,7 +599,9 @@ struct ionic_lif_init_cmd {
 /**
  * struct ionic_lif_init_comp - LIF init command completion
  * @status:	Status of the command (enum ionic_status_code)
+ * @rsvd:	reserved byte(s)
  * @hw_index:	Hardware index of the initialized LIF
+ * @rsvd2:	reserved byte(s)
  */
 struct ionic_lif_init_comp {
 	u8 status;
@@ -584,9 +613,11 @@ struct ionic_lif_init_comp {
 /**
  * struct ionic_q_identify_cmd - queue identify command
  * @opcode:     opcode
+ * @rsvd:       reserved byte(s)
  * @lif_type:   LIF type (enum ionic_lif_type)
  * @type:       Logical queue type (enum ionic_logical_qtype)
  * @ver:        Highest queue type version that the driver supports
+ * @rsvd2:      reserved byte(s)
  */
 struct ionic_q_identify_cmd {
 	u8     opcode;
@@ -600,8 +631,10 @@ struct ionic_q_identify_cmd {
 /**
  * struct ionic_q_identify_comp - queue identify command completion
  * @status:     Status of the command (enum ionic_status_code)
+ * @rsvd:       reserved byte(s)
  * @comp_index: Index in the descriptor ring for which this is the completion
  * @ver:        Queue type version that can be used with FW
+ * @rsvd2:      reserved byte(s)
  */
 struct ionic_q_identify_comp {
 	u8     status;
@@ -615,12 +648,14 @@ struct ionic_q_identify_comp {
  * union ionic_q_identity - queue identity information
  *     @version:        Queue type version that can be used with FW
  *     @supported:      Bitfield of queue versions, first bit = ver 0
+ *     @rsvd:           reserved byte(s)
  *     @features:       Queue features (enum ionic_q_feature, etc)
  *     @desc_sz:        Descriptor size
  *     @comp_sz:        Completion descriptor size
  *     @sg_desc_sz:     Scatter/Gather descriptor size
  *     @max_sg_elems:   Maximum number of Scatter/Gather elements
  *     @sg_desc_stride: Number of Scatter/Gather elements per descriptor
+ *     @words:          word access to struct contents
  */
 union ionic_q_identity {
 	struct {
@@ -640,8 +675,10 @@ union ionic_q_identity {
 /**
  * struct ionic_q_init_cmd - Queue init command
  * @opcode:       opcode
+ * @rsvd:         reserved byte(s)
  * @type:         Logical queue type
  * @ver:          Queue type version
+ * @rsvd1:        reserved byte(s)
  * @lif_index:    LIF index
  * @index:        (LIF, qtype) relative admin queue index
  * @intr_index:   Interrupt control register index, or Event queue index
@@ -667,6 +704,7 @@ union ionic_q_identity {
  * @ring_base:    Queue ring base address
  * @cq_ring_base: Completion queue ring base address
  * @sg_ring_base: Scatter/Gather ring base address
+ * @rsvd2:        reserved byte(s)
  * @features:     Mask of queue features to enable, if not in the flags above.
  */
 struct ionic_q_init_cmd {
@@ -698,9 +736,11 @@ struct ionic_q_init_cmd {
 /**
  * struct ionic_q_init_comp - Queue init command completion
  * @status:     Status of the command (enum ionic_status_code)
+ * @rsvd:       reserved byte(s)
  * @comp_index: Index in the descriptor ring for which this is the completion
  * @hw_index:   Hardware Queue ID
  * @hw_type:    Hardware Queue type
+ * @rsvd2:      reserved byte(s)
  * @color:      Color
  */
 struct ionic_q_init_comp {
@@ -800,7 +840,7 @@ enum ionic_txq_desc_opcode {
  *                      will set CWR flag in the first segment if
  *                      CWR is set in the template header, and
  *                      clear CWR in remaining segments.
- * @flags:
+ *    flags:
  *                vlan:
  *                    Insert an L2 VLAN header using @vlan_tci
  *                encap:
@@ -813,13 +853,14 @@ enum ionic_txq_desc_opcode {
  *                    TSO start
  *                tso_eot:
  *                    TSO end
- * @num_sg_elems: Number of scatter-gather elements in SG
+ *    num_sg_elems: Number of scatter-gather elements in SG
  *                descriptor
- * @addr:         First data buffer's DMA address
+ *    addr:       First data buffer's DMA address
  *                (Subsequent data buffers are on txq_sg_desc)
  * @len:          First data buffer's length, in bytes
  * @vlan_tci:     VLAN tag to insert in the packet (if requested
  *                by @V-bit).  Includes .1p and .1q tags
+ * @hword0:       half word padding
  * @hdr_len:      Length of packet headers, including
  *                encapsulating outer header, if applicable
  *                Valid for opcodes IONIC_TXQ_DESC_OPCODE_CALC_CSUM and
@@ -830,10 +871,12 @@ enum ionic_txq_desc_opcode {
  *                IONIC_TXQ_DESC_OPCODE_TSO, @hdr_len is up to
  *                inner-most L4 payload, so inclusive of
  *                inner-most L4 header.
+ * @hword1:       half word padding
  * @mss:          Desired MSS value for TSO; only applicable for
  *                IONIC_TXQ_DESC_OPCODE_TSO
  * @csum_start:   Offset from packet to first byte checked in L4 checksum
  * @csum_offset:  Offset from csum_start to L4 checksum field
+ * @hword2:       half word padding
  */
 struct ionic_txq_desc {
 	__le64  cmd;
@@ -901,6 +944,7 @@ static inline void decode_txq_desc_cmd(u64 cmd, u8 *opcode, u8 *flags,
  * struct ionic_txq_sg_elem - Transmit scatter-gather (SG) descriptor element
  * @addr:      DMA address of SG element data buffer
  * @len:       Length of SG element data buffer, in bytes
+ * @rsvd:      reserved byte(s)
  */
 struct ionic_txq_sg_elem {
 	__le64 addr;
@@ -927,7 +971,9 @@ struct ionic_txq_sg_desc_v1 {
 /**
  * struct ionic_txq_comp - Ethernet transmit queue completion descriptor
  * @status:     Status of the command (enum ionic_status_code)
+ * @rsvd:       reserved byte(s)
  * @comp_index: Index in the descriptor ring for which this is the completion
+ * @rsvd2:      reserved byte(s)
  * @color:      Color bit
  */
 struct ionic_txq_comp {
@@ -953,6 +999,7 @@ enum ionic_rxq_desc_opcode {
  *                      receive, including actual bytes received,
  *                      are recorded in Rx completion descriptor.
  *
+ * @rsvd:         reserved byte(s)
  * @len:          Data buffer's length, in bytes
  * @addr:         Data buffer's DMA address
  */
@@ -967,6 +1014,7 @@ struct ionic_rxq_desc {
  * struct ionic_rxq_sg_elem - Receive scatter-gather (SG) descriptor element
  * @addr:      DMA address of SG element data buffer
  * @len:       Length of SG element data buffer, in bytes
+ * @rsvd:      reserved byte(s)
  */
 struct ionic_rxq_sg_elem {
 	__le64 addr;
@@ -1170,6 +1218,7 @@ enum ionic_pkt_class {
  * @lif_index:  LIF index
  * @index:      Queue index
  * @oper:       Operation (enum ionic_q_control_oper)
+ * @rsvd:       reserved byte(s)
  */
 struct ionic_q_control_cmd {
 	u8     opcode;
@@ -1182,7 +1231,7 @@ struct ionic_q_control_cmd {
 
 typedef struct ionic_admin_comp ionic_q_control_comp;
 
-enum q_control_oper {
+enum ionic_q_control_oper {
 	IONIC_Q_DISABLE		= 0,
 	IONIC_Q_ENABLE		= 1,
 	IONIC_Q_HANG_RESET	= 2,
@@ -1216,7 +1265,7 @@ enum ionic_xcvr_state {
 	IONIC_XCVR_STATE_SPROM_READ_ERR	 = 4,
 };
 
-/**
+/*
  * enum ionic_xcvr_pid - Supported link modes
  */
 enum ionic_xcvr_pid {
@@ -1351,6 +1400,7 @@ struct ionic_xcvr_status {
  * @fec_type:           fec type (enum ionic_port_fec_type)
  * @pause_type:         pause type (enum ionic_port_pause_type)
  * @loopback_mode:      loopback mode (enum ionic_port_loopback_mode)
+ * @words:              word access to struct contents
  */
 union ionic_port_config {
 	struct {
@@ -1382,6 +1432,7 @@ union ionic_port_config {
  * @speed:              link speed (in Mbps)
  * @link_down_count:    number of times link went from up to down
  * @fec_type:           fec type (enum ionic_port_fec_type)
+ * @rsvd:               reserved byte(s)
  * @xcvr:               transceiver status
  */
 struct ionic_port_status {
@@ -1399,6 +1450,7 @@ struct ionic_port_status {
  * @opcode:     opcode
  * @index:      port index
  * @ver:        Highest version of identify supported by driver
+ * @rsvd:       reserved byte(s)
  */
 struct ionic_port_identify_cmd {
 	u8 opcode;
@@ -1411,6 +1463,7 @@ struct ionic_port_identify_cmd {
  * struct ionic_port_identify_comp - Port identify command completion
  * @status: Status of the command (enum ionic_status_code)
  * @ver:    Version of identify returned by device
+ * @rsvd:   reserved byte(s)
  */
 struct ionic_port_identify_comp {
 	u8 status;
@@ -1422,7 +1475,9 @@ struct ionic_port_identify_comp {
  * struct ionic_port_init_cmd - Port initialization command
  * @opcode:     opcode
  * @index:      port index
+ * @rsvd:       reserved byte(s)
  * @info_pa:    destination address for port info (struct ionic_port_info)
+ * @rsvd2:      reserved byte(s)
  */
 struct ionic_port_init_cmd {
 	u8     opcode;
@@ -1435,6 +1490,7 @@ struct ionic_port_init_cmd {
 /**
  * struct ionic_port_init_comp - Port initialization command completion
  * @status: Status of the command (enum ionic_status_code)
+ * @rsvd:   reserved byte(s)
  */
 struct ionic_port_init_comp {
 	u8 status;
@@ -1445,6 +1501,7 @@ struct ionic_port_init_comp {
  * struct ionic_port_reset_cmd - Port reset command
  * @opcode:     opcode
  * @index:      port index
+ * @rsvd:       reserved byte(s)
  */
 struct ionic_port_reset_cmd {
 	u8 opcode;
@@ -1455,6 +1512,7 @@ struct ionic_port_reset_cmd {
 /**
  * struct ionic_port_reset_comp - Port reset command completion
  * @status: Status of the command (enum ionic_status_code)
+ * @rsvd:   reserved byte(s)
  */
 struct ionic_port_reset_comp {
 	u8 status;
@@ -1510,6 +1568,7 @@ enum ionic_port_attr {
  * @opcode:         Opcode
  * @index:          Port index
  * @attr:           Attribute type (enum ionic_port_attr)
+ * @rsvd:           reserved byte(s)
  * @state:          Port state
  * @speed:          Port speed
  * @mtu:            Port MTU
@@ -1518,6 +1577,7 @@ enum ionic_port_attr {
  * @pause_type:     Port pause type setting
  * @loopback_mode:  Port loopback mode
  * @stats_ctl:      Port stats setting
+ * @rsvd2:          reserved byte(s)
  */
 struct ionic_port_setattr_cmd {
 	u8     opcode;
@@ -1540,6 +1600,7 @@ struct ionic_port_setattr_cmd {
 /**
  * struct ionic_port_setattr_comp - Port set attr command completion
  * @status:     Status of the command (enum ionic_status_code)
+ * @rsvd:       reserved byte(s)
  * @color:      Color bit
  */
 struct ionic_port_setattr_comp {
@@ -1553,6 +1614,7 @@ struct ionic_port_setattr_comp {
  * @opcode:     Opcode
  * @index:      port index
  * @attr:       Attribute type (enum ionic_port_attr)
+ * @rsvd:       reserved byte(s)
  */
 struct ionic_port_getattr_cmd {
 	u8     opcode;
@@ -1564,6 +1626,7 @@ struct ionic_port_getattr_cmd {
 /**
  * struct ionic_port_getattr_comp - Port get attr command completion
  * @status:         Status of the command (enum ionic_status_code)
+ * @rsvd:           reserved byte(s)
  * @state:          Port state
  * @speed:          Port speed
  * @mtu:            Port MTU
@@ -1571,6 +1634,7 @@ struct ionic_port_getattr_cmd {
  * @fec_type:       Port FEC type setting
  * @pause_type:     Port pause type setting
  * @loopback_mode:  Port loopback mode
+ * @rsvd2:          reserved byte(s)
  * @color:          Color bit
  */
 struct ionic_port_getattr_comp {
@@ -1593,9 +1657,11 @@ struct ionic_port_getattr_comp {
  * struct ionic_lif_status - LIF status register
  * @eid:             most recent NotifyQ event id
  * @port_num:        port the LIF is connected to
+ * @rsvd:            reserved byte(s)
  * @link_status:     port status (enum ionic_port_oper_status)
  * @link_speed:      speed of link in Mbps
  * @link_down_count: number of times link went from up to down
+ * @rsvd2:           reserved byte(s)
  */
 struct ionic_lif_status {
 	__le64 eid;
@@ -1610,7 +1676,9 @@ struct ionic_lif_status {
 /**
  * struct ionic_lif_reset_cmd - LIF reset command
  * @opcode:    opcode
+ * @rsvd:      reserved byte(s)
  * @index:     LIF index
+ * @rsvd2:     reserved byte(s)
  */
 struct ionic_lif_reset_cmd {
 	u8     opcode;
@@ -1643,9 +1711,11 @@ enum ionic_dev_attr {
  * struct ionic_dev_setattr_cmd - Set Device attributes on the NIC
  * @opcode:     Opcode
  * @attr:       Attribute type (enum ionic_dev_attr)
+ * @rsvd:       reserved byte(s)
  * @state:      Device state (enum ionic_dev_state)
  * @name:       The bus info, e.g. PCI slot-device-function, 0 terminated
  * @features:   Device features
+ * @rsvd2:      reserved byte(s)
  */
 struct ionic_dev_setattr_cmd {
 	u8     opcode;
@@ -1662,7 +1732,9 @@ struct ionic_dev_setattr_cmd {
 /**
  * struct ionic_dev_setattr_comp - Device set attr command completion
  * @status:     Status of the command (enum ionic_status_code)
+ * @rsvd:       reserved byte(s)
  * @features:   Device features
+ * @rsvd2:      reserved byte(s)
  * @color:      Color bit
  */
 struct ionic_dev_setattr_comp {
@@ -1679,6 +1751,7 @@ struct ionic_dev_setattr_comp {
  * struct ionic_dev_getattr_cmd - Get Device attributes from the NIC
  * @opcode:     opcode
  * @attr:       Attribute type (enum ionic_dev_attr)
+ * @rsvd:       reserved byte(s)
  */
 struct ionic_dev_getattr_cmd {
 	u8     opcode;
@@ -1687,9 +1760,11 @@ struct ionic_dev_getattr_cmd {
 };
 
 /**
- * struct ionic_dev_setattr_comp - Device set attr command completion
+ * struct ionic_dev_getattr_comp - Device set attr command completion
  * @status:     Status of the command (enum ionic_status_code)
+ * @rsvd:       reserved byte(s)
  * @features:   Device features
+ * @rsvd2:      reserved byte(s)
  * @color:      Color bit
  */
 struct ionic_dev_getattr_comp {
@@ -1702,7 +1777,7 @@ struct ionic_dev_getattr_comp {
 	u8     color;
 };
 
-/**
+/*
  * RSS parameters
  */
 #define IONIC_RSS_HASH_KEY_SIZE		40
@@ -1726,6 +1801,7 @@ enum ionic_rss_hash_types {
  * @IONIC_LIF_ATTR_RSS:         LIF RSS attribute
  * @IONIC_LIF_ATTR_STATS_CTRL:  LIF statistics control attribute
  * @IONIC_LIF_ATTR_TXSTAMP:     LIF TX timestamping mode
+ * @IONIC_LIF_ATTR_MAX:         maximum attribute value
  */
 enum ionic_lif_attr {
 	IONIC_LIF_ATTR_STATE        = 0,
@@ -1736,6 +1812,7 @@ enum ionic_lif_attr {
 	IONIC_LIF_ATTR_RSS          = 5,
 	IONIC_LIF_ATTR_STATS_CTRL   = 6,
 	IONIC_LIF_ATTR_TXSTAMP      = 7,
+	IONIC_LIF_ATTR_MAX          = 255,
 };
 
 /**
@@ -1749,11 +1826,13 @@ enum ionic_lif_attr {
  * @mac:        Station mac
  * @features:   Features (enum ionic_eth_hw_features)
  * @rss:        RSS properties
- *              @types:     The hash types to enable (see rss_hash_types)
- *              @key:       The hash secret key
- *              @addr:      Address for the indirection table shared memory
+ *	@rss.types:     The hash types to enable (see rss_hash_types)
+ *	@rss.key:       The hash secret key
+ *	@rss.rsvd:      reserved byte(s)
+ *	@rss.addr:      Address for the indirection table shared memory
  * @stats_ctl:  stats control commands (enum ionic_stats_ctl_cmd)
- * @txstamp:    TX Timestamping Mode (enum ionic_txstamp_mode)
+ * @txstamp_mode:    TX Timestamping Mode (enum ionic_txstamp_mode)
+ * @rsvd:        reserved byte(s)
  */
 struct ionic_lif_setattr_cmd {
 	u8     opcode;
@@ -1772,7 +1851,7 @@ struct ionic_lif_setattr_cmd {
 			__le64 addr;
 		} rss;
 		u8      stats_ctl;
-		__le16 txstamp_mode;
+		__le16  txstamp_mode;
 		u8      rsvd[60];
 	} __packed;
 };
@@ -1780,8 +1859,10 @@ struct ionic_lif_setattr_cmd {
 /**
  * struct ionic_lif_setattr_comp - LIF set attr command completion
  * @status:     Status of the command (enum ionic_status_code)
+ * @rsvd:       reserved byte(s)
  * @comp_index: Index in the descriptor ring for which this is the completion
  * @features:   features (enum ionic_eth_hw_features)
+ * @rsvd2:      reserved byte(s)
  * @color:      Color bit
  */
 struct ionic_lif_setattr_comp {
@@ -1800,6 +1881,7 @@ struct ionic_lif_setattr_comp {
  * @opcode:     Opcode
  * @attr:       Attribute type (enum ionic_lif_attr)
  * @index:      LIF index
+ * @rsvd:       reserved byte(s)
  */
 struct ionic_lif_getattr_cmd {
 	u8     opcode;
@@ -1811,13 +1893,14 @@ struct ionic_lif_getattr_cmd {
 /**
  * struct ionic_lif_getattr_comp - LIF get attr command completion
  * @status:     Status of the command (enum ionic_status_code)
+ * @rsvd:       reserved byte(s)
  * @comp_index: Index in the descriptor ring for which this is the completion
  * @state:      LIF state (enum ionic_lif_state)
- * @name:       The netdev name string, 0 terminated
  * @mtu:        Mtu
  * @mac:        Station mac
  * @features:   Features (enum ionic_eth_hw_features)
- * @txstamp:    TX Timestamping Mode (enum ionic_txstamp_mode)
+ * @txstamp_mode:    TX Timestamping Mode (enum ionic_txstamp_mode)
+ * @rsvd2:      reserved byte(s)
  * @color:      Color bit
  */
 struct ionic_lif_getattr_comp {
@@ -1838,12 +1921,15 @@ struct ionic_lif_getattr_comp {
 /**
  * struct ionic_lif_setphc_cmd - Set LIF PTP Hardware Clock
  * @opcode:     Opcode
+ * @rsvd1:      reserved byte(s)
  * @lif_index:  LIF index
+ * @rsvd2:      reserved byte(s)
  * @tick:       Hardware stamp tick of an instant in time.
  * @nsec:       Nanosecond stamp of the same instant.
  * @frac:       Fractional nanoseconds at the same instant.
  * @mult:       Cycle to nanosecond multiplier.
  * @shift:      Cycle to nanosecond divisor (power of two).
+ * @rsvd3:      reserved byte(s)
  */
 struct ionic_lif_setphc_cmd {
 	u8	opcode;
@@ -1870,6 +1956,7 @@ enum ionic_rx_mode {
 /**
  * struct ionic_rx_mode_set_cmd - Set LIF's Rx mode command
  * @opcode:     opcode
+ * @rsvd:       reserved byte(s)
  * @lif_index:  LIF index
  * @rx_mode:    Rx mode flags:
  *                  IONIC_RX_MODE_F_UNICAST: Accept known unicast packets
@@ -1878,6 +1965,7 @@ enum ionic_rx_mode {
  *                  IONIC_RX_MODE_F_PROMISC: Accept any packets
  *                  IONIC_RX_MODE_F_ALLMULTI: Accept any multicast packets
  *                  IONIC_RX_MODE_F_RDMA_SNIFFER: Sniff RDMA packets
+ * @rsvd2:      reserved byte(s)
  */
 struct ionic_rx_mode_set_cmd {
 	u8     opcode;
@@ -1904,13 +1992,14 @@ enum ionic_rx_filter_match_type {
  * @qid:        Queue ID
  * @match:      Rx filter match type (see IONIC_RX_FILTER_MATCH_xxx)
  * @vlan:       VLAN filter
- *              @vlan:  VLAN ID
+ *	@vlan.vlan:  VLAN ID
  * @mac:        MAC filter
- *              @addr:  MAC address (network-byte order)
+ *	@mac.addr:  MAC address (network-byte order)
  * @mac_vlan:   MACVLAN filter
- *              @vlan:  VLAN ID
- *              @addr:  MAC address (network-byte order)
+ *	@mac_vlan.vlan:  VLAN ID
+ *	@mac_vlan.addr:  MAC address (network-byte order)
  * @pkt_class:  Packet classification filter
+ * @rsvd:       reserved byte(s)
  */
 struct ionic_rx_filter_add_cmd {
 	u8     opcode;
@@ -1937,8 +2026,10 @@ struct ionic_rx_filter_add_cmd {
 /**
  * struct ionic_rx_filter_add_comp - Add LIF Rx filter command completion
  * @status:     Status of the command (enum ionic_status_code)
+ * @rsvd:       reserved byte(s)
  * @comp_index: Index in the descriptor ring for which this is the completion
  * @filter_id:  Filter ID
+ * @rsvd2:      reserved byte(s)
  * @color:      Color bit
  */
 struct ionic_rx_filter_add_comp {
@@ -1953,8 +2044,10 @@ struct ionic_rx_filter_add_comp {
 /**
  * struct ionic_rx_filter_del_cmd - Delete LIF Rx filter command
  * @opcode:     opcode
+ * @rsvd:       reserved byte(s)
  * @lif_index:  LIF index
  * @filter_id:  Filter ID
+ * @rsvd2:      reserved byte(s)
  */
 struct ionic_rx_filter_del_cmd {
 	u8     opcode;
@@ -2000,6 +2093,7 @@ enum ionic_vf_link_status {
  *	@trust:		enable VF trust
  *	@linkstate:	set link up or down
  *	@stats_pa:	set DMA address for VF stats
+ *	@pad:           reserved byte(s)
  */
 struct ionic_vf_setattr_cmd {
 	u8     opcode;
@@ -2031,6 +2125,7 @@ struct ionic_vf_setattr_comp {
  * @opcode:     Opcode
  * @attr:       Attribute type (enum ionic_vf_attr)
  * @vf_index:   VF index
+ * @rsvd:       reserved byte(s)
  */
 struct ionic_vf_getattr_cmd {
 	u8     opcode;
@@ -2064,8 +2159,8 @@ enum ionic_vf_ctrl_opcode {
 /**
  * struct ionic_vf_ctrl_cmd - VF control command
  * @opcode:         Opcode for the command
- * @vf_index:       VF Index. It is unused if op START_ALL is used.
  * @ctrl_opcode:    VF control operation type
+ * @vf_index:       VF Index. It is unused if op START_ALL is used.
  */
 struct ionic_vf_ctrl_cmd {
 	u8	opcode;
@@ -2089,7 +2184,7 @@ struct ionic_vf_ctrl_comp {
  * struct ionic_qos_identify_cmd - QoS identify command
  * @opcode:  opcode
  * @ver:     Highest version of identify supported by driver
- *
+ * @rsvd:    reserved byte(s)
  */
 struct ionic_qos_identify_cmd {
 	u8 opcode;
@@ -2101,6 +2196,7 @@ struct ionic_qos_identify_cmd {
  * struct ionic_qos_identify_comp - QoS identify command completion
  * @status: Status of the command (enum ionic_status_code)
  * @ver:    Version of identify returned by device
+ * @rsvd:   reserved byte(s)
  */
 struct ionic_qos_identify_comp {
 	u8 status;
@@ -2118,7 +2214,7 @@ struct ionic_qos_identify_comp {
 #define IONIC_QOS_ALL_PCP		0xFF
 #define IONIC_DSCP_BLOCK_SIZE		8
 
-/**
+/*
  * enum ionic_qos_class
  */
 enum ionic_qos_class {
@@ -2174,6 +2270,7 @@ enum ionic_qos_sched_type {
  * @dot1q_pcp:		Dot1q pcp value
  * @ndscp:		Number of valid dscp values in the ip_dscp field
  * @ip_dscp:		IP dscp values
+ * @words:		word access to struct contents
  */
 union ionic_qos_config {
 	struct {
@@ -2219,8 +2316,9 @@ union ionic_qos_config {
  * union ionic_qos_identity - QoS identity structure
  * @version:	Version of the identify structure
  * @type:	QoS system type
- * @nclasses:	Number of usable QoS classes
+ * @rsvd:	reserved byte(s)
  * @config:	Current configuration of classes
+ * @words:	word access to struct contents
  */
 union ionic_qos_identity {
 	struct {
@@ -2236,7 +2334,9 @@ union ionic_qos_identity {
  * struct ionic_qos_init_cmd - QoS config init command
  * @opcode:	Opcode
  * @group:	QoS class id
+ * @rsvd:	reserved byte(s)
  * @info_pa:	destination address for qos info
+ * @rsvd1:	reserved byte(s)
  */
 struct ionic_qos_init_cmd {
 	u8     opcode;
@@ -2252,6 +2352,7 @@ typedef struct ionic_admin_comp ionic_qos_init_comp;
  * struct ionic_qos_reset_cmd - QoS config reset command
  * @opcode:	Opcode
  * @group:	QoS class id
+ * @rsvd:	reserved byte(s)
  */
 struct ionic_qos_reset_cmd {
 	u8    opcode;
@@ -2260,8 +2361,10 @@ struct ionic_qos_reset_cmd {
 };
 
 /**
- * struct ionic_qos_clear_port_stats_cmd - Qos config reset command
+ * struct ionic_qos_clear_stats_cmd - Qos config reset command
  * @opcode:	Opcode
+ * @group_bitmap: bitmap of groups to be cleared
+ * @rsvd:	reserved byte(s)
  */
 struct ionic_qos_clear_stats_cmd {
 	u8    opcode;
@@ -2274,6 +2377,7 @@ typedef struct ionic_admin_comp ionic_qos_reset_comp;
 /**
  * struct ionic_fw_download_cmd - Firmware download command
  * @opcode:	opcode
+ * @rsvd:	reserved byte(s)
  * @addr:	dma address of the firmware buffer
  * @offset:	offset of the firmware buffer within the full image
  * @length:	number of valid bytes in the firmware buffer
@@ -2297,6 +2401,7 @@ typedef struct ionic_admin_comp ionic_fw_download_comp;
  * @IONIC_FW_INSTALL_STATUS:	Firmware installation status
  * @IONIC_FW_ACTIVATE_ASYNC:	Activate firmware asynchronously
  * @IONIC_FW_ACTIVATE_STATUS:	Firmware activate status
+ * @IONIC_FW_UPDATE_CLEANUP:	Clean up after an interrupted fw update
  */
 enum ionic_fw_control_oper {
 	IONIC_FW_RESET			= 0,
@@ -2312,8 +2417,10 @@ enum ionic_fw_control_oper {
 /**
  * struct ionic_fw_control_cmd - Firmware control command
  * @opcode:    opcode
+ * @rsvd:      reserved byte(s)
  * @oper:      firmware control operation (enum ionic_fw_control_oper)
  * @slot:      slot to activate
+ * @rsvd1:     reserved byte(s)
  */
 struct ionic_fw_control_cmd {
 	u8  opcode;
@@ -2326,8 +2433,10 @@ struct ionic_fw_control_cmd {
 /**
  * struct ionic_fw_control_comp - Firmware control copletion
  * @status:     Status of the command (enum ionic_status_code)
+ * @rsvd:       reserved byte(s)
  * @comp_index: Index in the descriptor ring for which this is the completion
  * @slot:       Slot where the firmware was installed
+ * @rsvd1:      reserved byte(s)
  * @color:      Color bit
  */
 struct ionic_fw_control_comp {
@@ -2346,7 +2455,9 @@ struct ionic_fw_control_comp {
 /**
  * struct ionic_rdma_reset_cmd - Reset RDMA LIF cmd
  * @opcode:        opcode
+ * @rsvd:          reserved byte(s)
  * @lif_index:     LIF index
+ * @rsvd2:         reserved byte(s)
  *
  * There is no RDMA specific dev command completion struct.  Completion uses
  * the common struct ionic_admin_comp.  Only the status is indicated.
@@ -2362,6 +2473,7 @@ struct ionic_rdma_reset_cmd {
 /**
  * struct ionic_rdma_queue_cmd - Create RDMA Queue command
  * @opcode:        opcode, 52, 53
+ * @rsvd:          reserved byte(s)
  * @lif_index:     LIF index
  * @qid_ver:       (qid | (RDMA version << 24))
  * @cid:           intr, eq_id, or cq_id
@@ -2369,6 +2481,7 @@ struct ionic_rdma_reset_cmd {
  * @depth_log2:    log base two of queue depth
  * @stride_log2:   log base two of queue stride
  * @dma_addr:      address of the queue memory
+ * @rsvd2:         reserved byte(s)
  *
  * The same command struct is used to create an RDMA event queue, completion
  * queue, or RDMA admin queue.  The cid is an interrupt number for an event
@@ -2425,6 +2538,7 @@ struct ionic_notifyq_event {
  * @ecode:		event code = IONIC_EVENT_LINK_CHANGE
  * @link_status:	link up/down, with error bits (enum ionic_port_status)
  * @link_speed:		speed of the network link
+ * @rsvd:		reserved byte(s)
  *
  * Sent when the network link state changes between UP and DOWN
  */
@@ -2442,6 +2556,7 @@ struct ionic_link_change_event {
  * @ecode:		event code = IONIC_EVENT_RESET
  * @reset_code:		reset type
  * @state:		0=pending, 1=complete, 2=error
+ * @rsvd:		reserved byte(s)
  *
  * Sent when the NIC or some subsystem is going to be or
  * has been reset.
@@ -2458,6 +2573,7 @@ struct ionic_reset_event {
  * struct ionic_heartbeat_event - Sent periodically by NIC to indicate health
  * @eid:	event number
  * @ecode:	event code = IONIC_EVENT_HEARTBEAT
+ * @rsvd:	reserved byte(s)
  */
 struct ionic_heartbeat_event {
 	__le64 eid;
@@ -2481,6 +2597,7 @@ struct ionic_log_event {
  * struct ionic_xcvr_event - Transceiver change event
  * @eid:	event number
  * @ecode:	event code = IONIC_EVENT_XCVR
+ * @rsvd:	reserved byte(s)
  */
 struct ionic_xcvr_event {
 	__le64 eid;
@@ -2488,7 +2605,7 @@ struct ionic_xcvr_event {
 	u8     rsvd[54];
 };
 
-/**
+/*
  * struct ionic_port_stats - Port statistics structure
  */
 struct ionic_port_stats {
@@ -2646,8 +2763,7 @@ enum ionic_oflow_drop_stats {
 	IONIC_OFLOW_DROP_MAX,
 };
 
-/**
- * struct port_pb_stats - packet buffers system stats
+/* struct ionic_port_pb_stats - packet buffers system stats
  * uses ionic_pb_buffer_drop_stats for drop_counts[]
  */
 struct ionic_port_pb_stats {
@@ -2681,7 +2797,9 @@ struct ionic_port_pb_stats {
  * @pause_type:     supported pause types
  * @loopback_mode:  supported loopback mode
  * @speeds:         supported speeds
+ * @rsvd2:          reserved byte(s)
  * @config:         current port configuration
+ * @words:          word access to struct contents
  */
 union ionic_port_identity {
 	struct {
@@ -2707,7 +2825,8 @@ union ionic_port_identity {
  * @status:          Port status data
  * @stats:           Port statistics data
  * @mgmt_stats:      Port management statistics data
- * @port_pb_drop_stats:   uplink pb drop stats
+ * @rsvd:            reserved byte(s)
+ * @pb_stats:        uplink pb drop stats
  */
 struct ionic_port_info {
 	union ionic_port_config config;
@@ -2721,7 +2840,7 @@ struct ionic_port_info {
 	struct ionic_port_pb_stats  pb_stats;
 };
 
-/**
+/*
  * struct ionic_lif_stats - LIF statistics structure
  */
 struct ionic_lif_stats {
@@ -2983,8 +3102,10 @@ struct ionic_hwstamp_regs {
  *			bit 4-7 - 4 bit generation number, changes on fw restart
  * @fw_heartbeat:    Firmware heartbeat counter
  * @serial_num:      Serial number
+ * @rsvd_pad1024:    reserved byte(s)
  * @fw_version:      Firmware version
- * @hwstamp_regs:    Hardware current timestamp registers
+ * @hwstamp:         Hardware current timestamp registers
+ * @words:           word access to struct contents
  */
 union ionic_dev_info_regs {
 #define IONIC_DEVINFO_FWVERS_BUFLEN 32
@@ -3014,7 +3135,9 @@ union ionic_dev_info_regs {
  * @done:            Done indicator, bit 0 == 1 when command is complete
  * @cmd:             Opcode-specific command bytes
  * @comp:            Opcode-specific response bytes
+ * @rsvd:            reserved byte(s)
  * @data:            Opcode-specific side-data
+ * @words:           word access to struct contents
  */
 union ionic_dev_cmd_regs {
 	struct {
@@ -3032,6 +3155,7 @@ union ionic_dev_cmd_regs {
  * union ionic_dev_regs - Device register format for bar 0 page 0
  * @info:            Device info registers
  * @devcmd:          Device command registers
+ * @words:           word access to struct contents
  */
 union ionic_dev_regs {
 	struct {
@@ -3098,6 +3222,7 @@ union ionic_adminq_comp {
  *              interrupts when armed.
  * @qid_lo:  Queue destination for the producer index and flags (low bits)
  * @qid_hi:  Queue destination for the producer index and flags (high bits)
+ * @rsvd2:   reserved byte(s)
  */
 struct ionic_doorbell {
 	__le16 p_index;
-- 
GitLab


From 57e3c5af2befaf54cbae326fe800c148852e67a1 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 28 May 2024 19:33:22 -0700
Subject: [PATCH 612/950] net: fjes: correct TRACE_INCLUDE_PATH
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

A comment in define_trace.h clearly states:

 TRACE_INCLUDE_PATH if the path is something other than core kernel
                                                           vvvvvvvvvvvvvv
 include/trace then this macro can define the path to use. Note, the path
 is relative to define_trace.h, not the file including it. Full path names
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 for out of tree modules must be used.

fjes uses path relative to itself. Which (somehow) works most of
the time. Except when the kernel tree is "nested" in another
kernel tree, and ../drivers/net/fjes actually exists. In which
case build will use the header file from the wrong directory.

I've been trying to figure out why net NIPA builder is constantly
failing for the last 5 days, with:

include/trace/../../../drivers/net/fjes/fjes_trace.h:88:17: error: ‘__assign_str’ undeclared (first use in this function)
   88 |                 __assign_str(err, err);
      |                 ^~~~~~~~~~~~

when the line in the tree clearly has only one "err". NIPA does
indeed have "nested" trees, because it uses git work-trees and
the tree on the "outside" is not very up to date.

Link: https://lore.kernel.org/r/20240529023322.3467755-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/fjes/fjes_trace.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/fjes/fjes_trace.h b/drivers/net/fjes/fjes_trace.h
index 166ef015262be..37c6071cb333e 100644
--- a/drivers/net/fjes/fjes_trace.h
+++ b/drivers/net/fjes/fjes_trace.h
@@ -358,7 +358,7 @@ TRACE_EVENT(fjes_stop_req_irq_post,
 
 #undef TRACE_INCLUDE_PATH
 #undef TRACE_INCLUDE_FILE
-#define TRACE_INCLUDE_PATH ../../../drivers/net/fjes
+#define TRACE_INCLUDE_PATH ../../drivers/net/fjes
 #define TRACE_INCLUDE_FILE fjes_trace
 
 /* This part must be outside protection */
-- 
GitLab


From a79d8fe2ff8e78e549dc86cc853a61b029404871 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Wed, 29 May 2024 12:09:08 +0800
Subject: [PATCH 613/950] ipv6: sr: restruct ifdefines

There are too many ifdef in IPv6 segment routing code that may cause logic
problems. like commit 160e9d275218 ("ipv6: sr: fix invalid unregister error
path"). To avoid this, the init functions are redefined for both cases. The
code could be more clear after all fidefs are removed.

Suggested-by: Simon Horman <horms@kernel.org>
Suggested-by: David Ahern <dsahern@kernel.org>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20240529040908.3472952-1-liuhangbin@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/seg6.h      |  7 +++++++
 include/net/seg6_hmac.h |  7 +++++++
 net/ipv6/seg6.c         | 33 +++++----------------------------
 3 files changed, 19 insertions(+), 28 deletions(-)

diff --git a/include/net/seg6.h b/include/net/seg6.h
index af668f17b3988..82b3fbbcbb935 100644
--- a/include/net/seg6.h
+++ b/include/net/seg6.h
@@ -52,10 +52,17 @@ static inline struct seg6_pernet_data *seg6_pernet(struct net *net)
 
 extern int seg6_init(void);
 extern void seg6_exit(void);
+#ifdef CONFIG_IPV6_SEG6_LWTUNNEL
 extern int seg6_iptunnel_init(void);
 extern void seg6_iptunnel_exit(void);
 extern int seg6_local_init(void);
 extern void seg6_local_exit(void);
+#else
+static inline int seg6_iptunnel_init(void) { return 0; }
+static inline void seg6_iptunnel_exit(void) {}
+static inline int seg6_local_init(void) { return 0; }
+static inline void seg6_local_exit(void) {}
+#endif
 
 extern bool seg6_validate_srh(struct ipv6_sr_hdr *srh, int len, bool reduced);
 extern struct ipv6_sr_hdr *seg6_get_srh(struct sk_buff *skb, int flags);
diff --git a/include/net/seg6_hmac.h b/include/net/seg6_hmac.h
index 2b5d2ee5613e8..24f733b3e3fe9 100644
--- a/include/net/seg6_hmac.h
+++ b/include/net/seg6_hmac.h
@@ -49,9 +49,16 @@ extern int seg6_hmac_info_del(struct net *net, u32 key);
 extern int seg6_push_hmac(struct net *net, struct in6_addr *saddr,
 			  struct ipv6_sr_hdr *srh);
 extern bool seg6_hmac_validate_skb(struct sk_buff *skb);
+#ifdef CONFIG_IPV6_SEG6_HMAC
 extern int seg6_hmac_init(void);
 extern void seg6_hmac_exit(void);
 extern int seg6_hmac_net_init(struct net *net);
 extern void seg6_hmac_net_exit(struct net *net);
+#else
+static inline int seg6_hmac_init(void) { return 0; }
+static inline void seg6_hmac_exit(void) {}
+static inline int seg6_hmac_net_init(struct net *net) { return 0; }
+static inline void seg6_hmac_net_exit(struct net *net) {}
+#endif
 
 #endif
diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c
index a31521e270f78..180da19c148c1 100644
--- a/net/ipv6/seg6.c
+++ b/net/ipv6/seg6.c
@@ -21,9 +21,7 @@
 #include <net/genetlink.h>
 #include <linux/seg6.h>
 #include <linux/seg6_genl.h>
-#ifdef CONFIG_IPV6_SEG6_HMAC
 #include <net/seg6_hmac.h>
-#endif
 
 bool seg6_validate_srh(struct ipv6_sr_hdr *srh, int len, bool reduced)
 {
@@ -437,13 +435,11 @@ static int __net_init seg6_net_init(struct net *net)
 
 	net->ipv6.seg6_data = sdata;
 
-#ifdef CONFIG_IPV6_SEG6_HMAC
 	if (seg6_hmac_net_init(net)) {
 		kfree(rcu_dereference_raw(sdata->tun_src));
 		kfree(sdata);
 		return -ENOMEM;
 	}
-#endif
 
 	return 0;
 }
@@ -452,9 +448,7 @@ static void __net_exit seg6_net_exit(struct net *net)
 {
 	struct seg6_pernet_data *sdata = seg6_pernet(net);
 
-#ifdef CONFIG_IPV6_SEG6_HMAC
 	seg6_hmac_net_exit(net);
-#endif
 
 	kfree(rcu_dereference_raw(sdata->tun_src));
 	kfree(sdata);
@@ -520,41 +514,28 @@ int __init seg6_init(void)
 	if (err)
 		goto out_unregister_pernet;
 
-#ifdef CONFIG_IPV6_SEG6_LWTUNNEL
 	err = seg6_iptunnel_init();
 	if (err)
 		goto out_unregister_genl;
 
 	err = seg6_local_init();
-	if (err) {
-		seg6_iptunnel_exit();
-		goto out_unregister_genl;
-	}
-#endif
+	if (err)
+		goto out_unregister_iptun;
 
-#ifdef CONFIG_IPV6_SEG6_HMAC
 	err = seg6_hmac_init();
 	if (err)
-		goto out_unregister_iptun;
-#endif
+		goto out_unregister_seg6;
 
 	pr_info("Segment Routing with IPv6\n");
 
 out:
 	return err;
-#ifdef CONFIG_IPV6_SEG6_HMAC
-out_unregister_iptun:
-#ifdef CONFIG_IPV6_SEG6_LWTUNNEL
+out_unregister_seg6:
 	seg6_local_exit();
+out_unregister_iptun:
 	seg6_iptunnel_exit();
-#endif
-#endif
-#ifdef CONFIG_IPV6_SEG6_LWTUNNEL
 out_unregister_genl:
-#endif
-#if IS_ENABLED(CONFIG_IPV6_SEG6_LWTUNNEL) || IS_ENABLED(CONFIG_IPV6_SEG6_HMAC)
 	genl_unregister_family(&seg6_genl_family);
-#endif
 out_unregister_pernet:
 	unregister_pernet_subsys(&ip6_segments_ops);
 	goto out;
@@ -562,13 +543,9 @@ out_unregister_pernet:
 
 void seg6_exit(void)
 {
-#ifdef CONFIG_IPV6_SEG6_HMAC
 	seg6_hmac_exit();
-#endif
-#ifdef CONFIG_IPV6_SEG6_LWTUNNEL
 	seg6_local_exit();
 	seg6_iptunnel_exit();
-#endif
 	genl_unregister_family(&seg6_genl_family);
 	unregister_pernet_subsys(&ip6_segments_ops);
 }
-- 
GitLab


From 482b3c3ba757f8fb7368f208b411d2bad3004702 Mon Sep 17 00:00:00 2001
From: Serge Semin <fancer.lancer@gmail.com>
Date: Wed, 29 May 2024 09:40:34 +0100
Subject: [PATCH 614/950] net: stmmac: Drop TBI/RTBI PCS flags

First of all the flags are never set by any of the driver parts. If nobody
have them set then the respective statements will always have the same
result. Thus the statements can be simplified or even dropped with no risk
to break things.

Secondly shall any of the TBI or RTBI flag is set the MDIO-bus
registration will be bypassed. Why? It really seems weird. It's perfectly
fine to have a TBI/RTBI-capable PHY configured over the MDIO bus
interface.

Based on the notes above the TBI/RTBI PCS flags can be freely dropped thus
simplifying the driver code.

Reviewed-by: Andrew Halaney <ahalaney@redhat.com>
Signed-off-by: Serge Semin <fancer.lancer@gmail.com>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Serge Semin <fancer.lancer@gmail.com>
Link: https://lore.kernel.org/r/E1sCErK-00EOPf-EP@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/common.h  |  2 --
 .../net/ethernet/stmicro/stmmac/stmmac_main.c | 35 +++++--------------
 2 files changed, 9 insertions(+), 28 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index 9cd62b2110a14..cd36ff4da68c6 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -271,8 +271,6 @@ struct stmmac_safety_stats {
 /* PCS defines */
 #define STMMAC_PCS_RGMII	(1 << 0)
 #define STMMAC_PCS_SGMII	(1 << 1)
-#define STMMAC_PCS_TBI		(1 << 2)
-#define STMMAC_PCS_RTBI		(1 << 3)
 
 #define SF_DMA_MODE 1		/* DMA STORE-AND-FORWARD Operation Mode */
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index b3afc7cb7d72d..3ab93f89be906 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -471,13 +471,6 @@ bool stmmac_eee_init(struct stmmac_priv *priv)
 {
 	int eee_tw_timer = priv->eee_tw_timer;
 
-	/* Using PCS we cannot dial with the phy registers at this stage
-	 * so we do not support extra feature like EEE.
-	 */
-	if (priv->hw->pcs == STMMAC_PCS_TBI ||
-	    priv->hw->pcs == STMMAC_PCS_RTBI)
-		return false;
-
 	/* Check if MAC core supports the EEE feature. */
 	if (!priv->dma_cap.eee)
 		return false;
@@ -3953,9 +3946,7 @@ static int __stmmac_open(struct net_device *dev,
 	if (ret < 0)
 		return ret;
 
-	if (priv->hw->pcs != STMMAC_PCS_TBI &&
-	    priv->hw->pcs != STMMAC_PCS_RTBI &&
-	    (!priv->hw->xpcs ||
+	if ((!priv->hw->xpcs ||
 	     xpcs_get_an_mode(priv->hw->xpcs, mode) != DW_AN_C73)) {
 		ret = stmmac_init_phy(dev);
 		if (ret) {
@@ -7739,16 +7730,12 @@ int stmmac_dvr_probe(struct device *device,
 	if (!pm_runtime_enabled(device))
 		pm_runtime_enable(device);
 
-	if (priv->hw->pcs != STMMAC_PCS_TBI &&
-	    priv->hw->pcs != STMMAC_PCS_RTBI) {
-		/* MDIO bus Registration */
-		ret = stmmac_mdio_register(ndev);
-		if (ret < 0) {
-			dev_err_probe(priv->device, ret,
-				      "%s: MDIO bus (id: %d) registration failed\n",
-				      __func__, priv->plat->bus_id);
-			goto error_mdio_register;
-		}
+	ret = stmmac_mdio_register(ndev);
+	if (ret < 0) {
+		dev_err_probe(priv->device, ret,
+			      "MDIO bus (id: %d) registration failed\n",
+			      priv->plat->bus_id);
+		goto error_mdio_register;
 	}
 
 	if (priv->plat->speed_mode_2500)
@@ -7790,9 +7777,7 @@ error_netdev_register:
 error_phy_setup:
 	stmmac_pcs_clean(ndev);
 error_pcs_setup:
-	if (priv->hw->pcs != STMMAC_PCS_TBI &&
-	    priv->hw->pcs != STMMAC_PCS_RTBI)
-		stmmac_mdio_unregister(ndev);
+	stmmac_mdio_unregister(ndev);
 error_mdio_register:
 	stmmac_napi_del(ndev);
 error_hw_init:
@@ -7833,10 +7818,8 @@ void stmmac_dvr_remove(struct device *dev)
 	reset_control_assert(priv->plat->stmmac_ahb_rst);
 
 	stmmac_pcs_clean(ndev);
+	stmmac_mdio_unregister(ndev);
 
-	if (priv->hw->pcs != STMMAC_PCS_TBI &&
-	    priv->hw->pcs != STMMAC_PCS_RTBI)
-		stmmac_mdio_unregister(ndev);
 	destroy_workqueue(priv->wq);
 	mutex_destroy(&priv->lock);
 	bitmap_free(priv->af_xdp_zc_qps);
-- 
GitLab


From 4af90c0f484491a1bdccc7c3bfe9b7411868b139 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Wed, 29 May 2024 09:40:39 +0100
Subject: [PATCH 615/950] net: stmmac: dwxgmac2: remove useless NULL pointer
 initialisations

Remove useless NULL pointer initialisations for "PCS" methods from the
dwxgmac2 code.

Reviewed-by: Andrew Halaney <ahalaney@redhat.com>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Serge Semin <fancer.lancer@gmail.com>
Link: https://lore.kernel.org/r/E1sCErP-00EOPl-IT@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
index f8e7775bb6336..6a987cf598e4f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
@@ -1554,9 +1554,6 @@ const struct stmmac_ops dwxgmac210_ops = {
 	.reset_eee_mode = dwxgmac2_reset_eee_mode,
 	.set_eee_timer = dwxgmac2_set_eee_timer,
 	.set_eee_pls = dwxgmac2_set_eee_pls,
-	.pcs_ctrl_ane = NULL,
-	.pcs_rane = NULL,
-	.pcs_get_adv_lp = NULL,
 	.debug = NULL,
 	.set_filter = dwxgmac2_set_filter,
 	.safety_feat_config = dwxgmac3_safety_feat_config,
@@ -1614,9 +1611,6 @@ const struct stmmac_ops dwxlgmac2_ops = {
 	.reset_eee_mode = dwxgmac2_reset_eee_mode,
 	.set_eee_timer = dwxgmac2_set_eee_timer,
 	.set_eee_pls = dwxgmac2_set_eee_pls,
-	.pcs_ctrl_ane = NULL,
-	.pcs_rane = NULL,
-	.pcs_get_adv_lp = NULL,
 	.debug = NULL,
 	.set_filter = dwxgmac2_set_filter,
 	.safety_feat_config = dwxgmac3_safety_feat_config,
-- 
GitLab


From 3277407e5e8217cb7550453fe3184d0de511f377 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Wed, 29 May 2024 09:40:44 +0100
Subject: [PATCH 616/950] net: stmmac: remove pcs_rane() method

The pcs_rane() method is not called, so lets just remove this
redundant code.

Reviewed-by: Andrew Halaney <ahalaney@redhat.com>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Serge Semin <fancer.lancer@gmail.com>
Link: https://lore.kernel.org/r/E1sCErU-00EOPr-MC@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../ethernet/stmicro/stmmac/dwmac1000_core.c    |  6 ------
 .../net/ethernet/stmicro/stmmac/dwmac4_core.c   |  8 --------
 drivers/net/ethernet/stmicro/stmmac/hwif.h      |  3 ---
 .../net/ethernet/stmicro/stmmac/stmmac_pcs.h    | 17 -----------------
 4 files changed, 34 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
index 8555299443f4e..d0c7c2320d8d5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
@@ -404,11 +404,6 @@ static void dwmac1000_ctrl_ane(void __iomem *ioaddr, bool ane, bool srgmi_ral,
 	dwmac_ctrl_ane(ioaddr, GMAC_PCS_BASE, ane, srgmi_ral, loopback);
 }
 
-static void dwmac1000_rane(void __iomem *ioaddr, bool restart)
-{
-	dwmac_rane(ioaddr, GMAC_PCS_BASE, restart);
-}
-
 static void dwmac1000_get_adv_lp(void __iomem *ioaddr, struct rgmii_adv *adv)
 {
 	dwmac_get_adv_lp(ioaddr, GMAC_PCS_BASE, adv);
@@ -519,7 +514,6 @@ const struct stmmac_ops dwmac1000_ops = {
 	.set_eee_pls = dwmac1000_set_eee_pls,
 	.debug = dwmac1000_debug,
 	.pcs_ctrl_ane = dwmac1000_ctrl_ane,
-	.pcs_rane = dwmac1000_rane,
 	.pcs_get_adv_lp = dwmac1000_get_adv_lp,
 	.set_mac_loopback = dwmac1000_set_mac_loopback,
 };
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
index b25774d691957..dbd9f93b2460f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
@@ -758,11 +758,6 @@ static void dwmac4_ctrl_ane(void __iomem *ioaddr, bool ane, bool srgmi_ral,
 	dwmac_ctrl_ane(ioaddr, GMAC_PCS_BASE, ane, srgmi_ral, loopback);
 }
 
-static void dwmac4_rane(void __iomem *ioaddr, bool restart)
-{
-	dwmac_rane(ioaddr, GMAC_PCS_BASE, restart);
-}
-
 static void dwmac4_get_adv_lp(void __iomem *ioaddr, struct rgmii_adv *adv)
 {
 	dwmac_get_adv_lp(ioaddr, GMAC_PCS_BASE, adv);
@@ -1215,7 +1210,6 @@ const struct stmmac_ops dwmac4_ops = {
 	.set_eee_timer = dwmac4_set_eee_timer,
 	.set_eee_pls = dwmac4_set_eee_pls,
 	.pcs_ctrl_ane = dwmac4_ctrl_ane,
-	.pcs_rane = dwmac4_rane,
 	.pcs_get_adv_lp = dwmac4_get_adv_lp,
 	.debug = dwmac4_debug,
 	.set_filter = dwmac4_set_filter,
@@ -1260,7 +1254,6 @@ const struct stmmac_ops dwmac410_ops = {
 	.set_eee_timer = dwmac4_set_eee_timer,
 	.set_eee_pls = dwmac4_set_eee_pls,
 	.pcs_ctrl_ane = dwmac4_ctrl_ane,
-	.pcs_rane = dwmac4_rane,
 	.pcs_get_adv_lp = dwmac4_get_adv_lp,
 	.debug = dwmac4_debug,
 	.set_filter = dwmac4_set_filter,
@@ -1309,7 +1302,6 @@ const struct stmmac_ops dwmac510_ops = {
 	.set_eee_timer = dwmac4_set_eee_timer,
 	.set_eee_pls = dwmac4_set_eee_pls,
 	.pcs_ctrl_ane = dwmac4_ctrl_ane,
-	.pcs_rane = dwmac4_rane,
 	.pcs_get_adv_lp = dwmac4_get_adv_lp,
 	.debug = dwmac4_debug,
 	.set_filter = dwmac4_set_filter,
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h
index 90384db228b5c..97934ccba5b1a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.h
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h
@@ -370,7 +370,6 @@ struct stmmac_ops {
 	/* PCS calls */
 	void (*pcs_ctrl_ane)(void __iomem *ioaddr, bool ane, bool srgmi_ral,
 			     bool loopback);
-	void (*pcs_rane)(void __iomem *ioaddr, bool restart);
 	void (*pcs_get_adv_lp)(void __iomem *ioaddr, struct rgmii_adv *adv);
 	/* Safety Features */
 	int (*safety_feat_config)(void __iomem *ioaddr, unsigned int asp,
@@ -484,8 +483,6 @@ struct stmmac_ops {
 	stmmac_do_void_callback(__priv, mac, debug, __priv, __args)
 #define stmmac_pcs_ctrl_ane(__priv, __args...) \
 	stmmac_do_void_callback(__priv, mac, pcs_ctrl_ane, __args)
-#define stmmac_pcs_rane(__priv, __args...) \
-	stmmac_do_void_callback(__priv, mac, pcs_rane, __priv, __args)
 #define stmmac_pcs_get_adv_lp(__priv, __args...) \
 	stmmac_do_void_callback(__priv, mac, pcs_get_adv_lp, __args)
 #define stmmac_safety_feat_config(__priv, __args...) \
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pcs.h b/drivers/net/ethernet/stmicro/stmmac/stmmac_pcs.h
index 13a30e6df4c15..1bdf87b237c4e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pcs.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pcs.h
@@ -74,23 +74,6 @@ static inline void dwmac_pcs_isr(void __iomem *ioaddr, u32 reg,
 	}
 }
 
-/**
- * dwmac_rane - To restart ANE
- * @ioaddr: IO registers pointer
- * @reg: Base address of the AN Control Register.
- * @restart: to restart ANE
- * Description: this is to just restart the Auto-Negotiation.
- */
-static inline void dwmac_rane(void __iomem *ioaddr, u32 reg, bool restart)
-{
-	u32 value = readl(ioaddr + GMAC_AN_CTRL(reg));
-
-	if (restart)
-		value |= GMAC_AN_CTRL_RAN;
-
-	writel(value, ioaddr + GMAC_AN_CTRL(reg));
-}
-
 /**
  * dwmac_ctrl_ane - To program the AN Control Register.
  * @ioaddr: IO registers pointer
-- 
GitLab


From aee04f4bb44d47205f4db9e84384116bb213160e Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Wed, 29 May 2024 09:40:49 +0100
Subject: [PATCH 617/950] net: stmmac: remove unnecessary netif_carrier_off()

It is incorrect to call netif_carrier_off(), or in fact any driver
teardown, before unregister_netdev() has been called.

unregister_netdev() unpublishes the network device from userspace, and
takes the interface down if it was up prior to returning. Therefore,
once the call has returned, we are guaranteed that .ndo_stop() will
have been called for an interface that was up. Phylink will take the
carrier down via phylink_stop(), making any manipulation of the carrier
in the remove path unnecessary.

In the stmmac_release() path, the netif_carrier_off() call follows the
call to phylink_stop(), so this call is redundant.

Reviewed-by: Andrew Halaney <ahalaney@redhat.com>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Serge Semin <fancer.lancer@gmail.com>
Link: https://lore.kernel.org/r/E1sCErZ-00EOPx-PF@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 3ab93f89be906..ca19b232431a5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -4088,8 +4088,6 @@ static int stmmac_release(struct net_device *dev)
 	if (priv->plat->serdes_powerdown)
 		priv->plat->serdes_powerdown(dev, priv->plat->bsp_priv);
 
-	netif_carrier_off(dev);
-
 	stmmac_release_ptp(priv);
 
 	pm_runtime_put(priv->device);
@@ -7806,7 +7804,6 @@ void stmmac_dvr_remove(struct device *dev)
 
 	stmmac_stop_all_dma(priv);
 	stmmac_mac_set(priv, priv->ioaddr, false);
-	netif_carrier_off(ndev);
 	unregister_netdev(ndev);
 
 #ifdef CONFIG_DEBUG_FS
-- 
GitLab


From cd56ff75ccfc37aab4b35b17b84d3ba08f33b933 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Wed, 29 May 2024 09:40:54 +0100
Subject: [PATCH 618/950] net: stmmac: include linux/io.h rather than asm/io.h

Include linux/io.h instead of asm/io.h since linux/ includes are
preferred.

Reviewed-by: Andrew Halaney <ahalaney@redhat.com>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Serge Semin <fancer.lancer@gmail.com>
Link: https://lore.kernel.org/r/E1sCEre-00EOQ3-SR@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c | 2 +-
 drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c  | 2 +-
 drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c  | 2 +-
 drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c   | 2 +-
 drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c | 2 +-
 5 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
index d0c7c2320d8d5..d413d76a89368 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
@@ -15,7 +15,7 @@
 #include <linux/crc32.h>
 #include <linux/slab.h>
 #include <linux/ethtool.h>
-#include <asm/io.h>
+#include <linux/io.h>
 #include "stmmac.h"
 #include "stmmac_pcs.h"
 #include "dwmac1000.h"
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c
index daf79cdbd3ecf..adccdd816ea91 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c
@@ -12,7 +12,7 @@
   Author: Giuseppe Cavallaro <peppe.cavallaro@st.com>
 *******************************************************************************/
 
-#include <asm/io.h>
+#include <linux/io.h>
 #include "dwmac1000.h"
 #include "dwmac_dma.h"
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c
index 7667d103cd0eb..14e847c0e1a91 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c
@@ -15,7 +15,7 @@
 *******************************************************************************/
 
 #include <linux/crc32.h>
-#include <asm/io.h>
+#include <linux/io.h>
 #include "stmmac.h"
 #include "dwmac100.h"
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c
index dea270f60cc3e..b402fb54f6131 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c
@@ -14,7 +14,7 @@
   Author: Giuseppe Cavallaro <peppe.cavallaro@st.com>
 *******************************************************************************/
 
-#include <asm/io.h>
+#include <linux/io.h>
 #include "dwmac100.h"
 #include "dwmac_dma.h"
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index 542e2633a6f52..18468c0228f0b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -11,10 +11,10 @@
 #include <linux/etherdevice.h>
 #include <linux/ethtool.h>
 #include <linux/interrupt.h>
+#include <linux/io.h>
 #include <linux/mii.h>
 #include <linux/phylink.h>
 #include <linux/net_tstamp.h>
-#include <asm/io.h>
 
 #include "stmmac.h"
 #include "dwmac_dma.h"
-- 
GitLab


From 7efc706577046a8dd2a11ba7942e3a52a30c8b68 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Wed, 29 May 2024 09:40:59 +0100
Subject: [PATCH 619/950] net: stmmac: ethqos: clean up setting serdes speed

There are four repititions of the same sequence of code, three of which
are identical. Pull these out into a separate function to improve
readability.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Andrew Halaney <ahalaney@redhat.com>
Reviewed-by: Serge Semin <fancer.lancer@gmail.com>
Link: https://lore.kernel.org/r/E1sCErj-00EOQ9-Vh@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../stmicro/stmmac/dwmac-qcom-ethqos.c        | 24 +++++++++----------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
index e254b21fdb598..d9eed415b0b7b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
@@ -605,6 +605,14 @@ static int ethqos_configure_rgmii(struct qcom_ethqos *ethqos)
 	return 0;
 }
 
+static void ethqos_set_serdes_speed(struct qcom_ethqos *ethqos, int speed)
+{
+	if (ethqos->serdes_speed != speed) {
+		phy_set_speed(ethqos->serdes_phy, speed);
+		ethqos->serdes_speed = speed;
+	}
+}
+
 /* On interface toggle MAC registers gets reset.
  * Configure MAC block for SGMII on ethernet phy link up
  */
@@ -622,9 +630,7 @@ static int ethqos_configure_sgmii(struct qcom_ethqos *ethqos)
 		rgmii_updatel(ethqos, RGMII_CONFIG2_RGMII_CLK_SEL_CFG,
 			      RGMII_CONFIG2_RGMII_CLK_SEL_CFG,
 			      RGMII_IO_MACRO_CONFIG2);
-		if (ethqos->serdes_speed != SPEED_2500)
-			phy_set_speed(ethqos->serdes_phy, SPEED_2500);
-		ethqos->serdes_speed = SPEED_2500;
+		ethqos_set_serdes_speed(ethqos, SPEED_2500);
 		stmmac_pcs_ctrl_ane(priv, priv->ioaddr, 0, 0, 0);
 		break;
 	case SPEED_1000:
@@ -632,16 +638,12 @@ static int ethqos_configure_sgmii(struct qcom_ethqos *ethqos)
 		rgmii_updatel(ethqos, RGMII_CONFIG2_RGMII_CLK_SEL_CFG,
 			      RGMII_CONFIG2_RGMII_CLK_SEL_CFG,
 			      RGMII_IO_MACRO_CONFIG2);
-		if (ethqos->serdes_speed != SPEED_1000)
-			phy_set_speed(ethqos->serdes_phy, SPEED_1000);
-		ethqos->serdes_speed = SPEED_1000;
+		ethqos_set_serdes_speed(ethqos, SPEED_1000);
 		stmmac_pcs_ctrl_ane(priv, priv->ioaddr, 1, 0, 0);
 		break;
 	case SPEED_100:
 		val |= ETHQOS_MAC_CTRL_PORT_SEL | ETHQOS_MAC_CTRL_SPEED_MODE;
-		if (ethqos->serdes_speed != SPEED_1000)
-			phy_set_speed(ethqos->serdes_phy, SPEED_1000);
-		ethqos->serdes_speed = SPEED_1000;
+		ethqos_set_serdes_speed(ethqos, SPEED_1000);
 		stmmac_pcs_ctrl_ane(priv, priv->ioaddr, 1, 0, 0);
 		break;
 	case SPEED_10:
@@ -651,9 +653,7 @@ static int ethqos_configure_sgmii(struct qcom_ethqos *ethqos)
 			      FIELD_PREP(RGMII_CONFIG_SGMII_CLK_DVDR,
 					 SGMII_10M_RX_CLK_DVDR),
 			      RGMII_IO_MACRO_CONFIG);
-		if (ethqos->serdes_speed != SPEED_1000)
-			phy_set_speed(ethqos->serdes_phy, ethqos->speed);
-		ethqos->serdes_speed = SPEED_1000;
+		ethqos_set_serdes_speed(ethqos, SPEED_1000);
 		stmmac_pcs_ctrl_ane(priv, priv->ioaddr, 1, 0, 0);
 		break;
 	}
-- 
GitLab


From 2f19a795e1f9c722b182f9a3d3dedd80f90a0715 Mon Sep 17 00:00:00 2001
From: MD Danish Anwar <danishanwar@ti.com>
Date: Wed, 29 May 2024 17:22:25 +0530
Subject: [PATCH 620/950] dt-bindings: net: ti: icssg_prueth: Add documentation
 for PA_STATS support

Add documentation for ti,pa-stats property which is syscon regmap for
PA_STATS registers. This will be used to dump statistics maintained by
ICSSG firmware.

Signed-off-by: MD Danish Anwar <danishanwar@ti.com>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20240529115225.630535-1-danishanwar@ti.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../devicetree/bindings/net/ti,icssg-prueth.yaml         | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/Documentation/devicetree/bindings/net/ti,icssg-prueth.yaml b/Documentation/devicetree/bindings/net/ti,icssg-prueth.yaml
index e253fa7860922..c296e57118484 100644
--- a/Documentation/devicetree/bindings/net/ti,icssg-prueth.yaml
+++ b/Documentation/devicetree/bindings/net/ti,icssg-prueth.yaml
@@ -55,6 +55,14 @@ properties:
     description:
       phandle to MII_RT module's syscon regmap
 
+  ti,pa-stats:
+    $ref: /schemas/types.yaml#/definitions/phandle
+    description:
+      phandle to PA_STATS module's syscon regmap. PA_STATS is a set of
+      registers where different statistics related to ICSSG, are dumped by
+      ICSSG firmware. PA_STATS module's syscon regmap will help the device to
+      access/read/write those statistics.
+
   ti,iep:
     $ref: /schemas/types.yaml#/definitions/phandle-array
     maxItems: 2
@@ -194,6 +202,7 @@ examples:
                     "tx1-0", "tx1-1", "tx1-2", "tx1-3",
                     "rx0", "rx1";
         ti,mii-g-rt = <&icssg2_mii_g_rt>;
+        ti,pa-stats = <&icssg2_pa_stats>;
         ti,iep = <&icssg2_iep0>, <&icssg2_iep1>;
         interrupt-parent = <&icssg2_intc>;
         interrupts = <24 0 2>, <25 1 3>;
-- 
GitLab


From 75518b0dc9d602bdd0e0ee4e04806dff53cb761a Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Wed, 29 May 2024 14:29:19 +0100
Subject: [PATCH 621/950] net: phylink: rearrange phylink_parse_mode()

Of the two users of phylink_config->ovr_an_inband, both manually check
for a fixed link before setting this flag (or clearing it if they find
a fixed link.) This is unnecessary complication.

Rearrange phylink_parse_mode() a little so we can change how
phylink_config->ovr_an_inband works. This will allow the flag to be
tested before checking for the fixed link properties in the next patch.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Andrew Halaney <ahalaney@redhat.com>
Link: https://lore.kernel.org/r/E1sCJMl-00Ecqp-K0@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/phylink.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 994471fad833f..5abd127135986 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -899,12 +899,15 @@ static int phylink_parse_mode(struct phylink *pl,
 			return -EINVAL;
 		}
 
+		pl->cfg_link_an_mode = MLO_AN_INBAND;
+	}
+
+	if (pl->cfg_link_an_mode == MLO_AN_INBAND) {
 		linkmode_zero(pl->supported);
 		phylink_set(pl->supported, MII);
 		phylink_set(pl->supported, Autoneg);
 		phylink_set(pl->supported, Asym_Pause);
 		phylink_set(pl->supported, Pause);
-		pl->cfg_link_an_mode = MLO_AN_INBAND;
 
 		switch (pl->link_config.interface) {
 		case PHY_INTERFACE_MODE_SGMII:
-- 
GitLab


From fea49f065c1cff71a86e7629094f912531edf035 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Wed, 29 May 2024 14:29:24 +0100
Subject: [PATCH 622/950] net: phylink: move test for ovr_an_inband

Of the two users of phylink_config->ovr_an_inband, both manually check
for a fixed link before setting this flag (or clearing it if they find
a fixed link.) This is unnecessary complication.

Test ovr_an_inband before checking for the fixed-link properties, which
will allow ovr_an_inband to be overriden by a fixed link specification.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Andrew Halaney <ahalaney@redhat.com>
Link: https://lore.kernel.org/r/E1sCJMq-00Ecqv-P8@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/phylink.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 5abd127135986..c81f1c1ee6750 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -885,14 +885,16 @@ static int phylink_parse_mode(struct phylink *pl,
 	const char *managed;
 	unsigned long caps;
 
+	if (pl->config->ovr_an_inband)
+		pl->cfg_link_an_mode = MLO_AN_INBAND;
+
 	dn = fwnode_get_named_child_node(fwnode, "fixed-link");
 	if (dn || fwnode_property_present(fwnode, "fixed-link"))
 		pl->cfg_link_an_mode = MLO_AN_FIXED;
 	fwnode_handle_put(dn);
 
 	if ((fwnode_property_read_string(fwnode, "managed", &managed) == 0 &&
-	     strcmp(managed, "in-band-status") == 0) ||
-	    pl->config->ovr_an_inband) {
+	     strcmp(managed, "in-band-status") == 0)) {
 		if (pl->cfg_link_an_mode == MLO_AN_FIXED) {
 			phylink_err(pl,
 				    "can't use both fixed-link and in-band-status\n");
-- 
GitLab


From 02d00dc73d8d0613f82063ed53d67912a422c21e Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Wed, 29 May 2024 14:29:29 +0100
Subject: [PATCH 623/950] net: phylink: rename ovr_an_inband to
 default_an_inband

Since ovr_an_inband no longer overrides every MLO_AN_xxx mode, rename
it to reflect what it now does - it changes the default mode from
MLO_AN_PHY to MLO_AN_INBAND. Fix up the two users of this.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Andrew Halaney <ahalaney@redhat.com>
Link: https://lore.kernel.org/r/E1sCJMv-00Ecr1-Sk@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/fman/fman_memac.c  | 2 +-
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 2 +-
 drivers/net/phy/phylink.c                         | 2 +-
 include/linux/phylink.h                           | 5 +++--
 4 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.c b/drivers/net/ethernet/freescale/fman/fman_memac.c
index 92b8f4ab26f1d..9c44a3581950b 100644
--- a/drivers/net/ethernet/freescale/fman/fman_memac.c
+++ b/drivers/net/ethernet/freescale/fman/fman_memac.c
@@ -1232,7 +1232,7 @@ int memac_initialization(struct mac_device *mac_dev,
 	    !of_property_read_bool(mac_node, "managed") &&
 	    mac_dev->phy_if != PHY_INTERFACE_MODE_MII &&
 	    !phy_interface_mode_is_rgmii(mac_dev->phy_if))
-		mac_dev->phylink_config.ovr_an_inband = true;
+		mac_dev->phylink_config.default_an_inband = true;
 	of_node_put(fixed);
 
 	err = memac_init(mac_dev->fman_mac);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index ca19b232431a5..488b2fd2349cb 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1221,7 +1221,7 @@ static int stmmac_phy_setup(struct stmmac_priv *priv)
 
 	mdio_bus_data = priv->plat->mdio_bus_data;
 	if (mdio_bus_data)
-		priv->phylink_config.ovr_an_inband =
+		priv->phylink_config.default_an_inband =
 			mdio_bus_data->xpcs_an_inband;
 
 	/* Set the platform/firmware specified interface mode. Note, phylink
diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index c81f1c1ee6750..02427378acfda 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -885,7 +885,7 @@ static int phylink_parse_mode(struct phylink *pl,
 	const char *managed;
 	unsigned long caps;
 
-	if (pl->config->ovr_an_inband)
+	if (pl->config->default_an_inband)
 		pl->cfg_link_an_mode = MLO_AN_INBAND;
 
 	dn = fwnode_get_named_child_node(fwnode, "fixed-link");
diff --git a/include/linux/phylink.h b/include/linux/phylink.h
index 5ea6b2ad23963..a30a692acc327 100644
--- a/include/linux/phylink.h
+++ b/include/linux/phylink.h
@@ -141,7 +141,8 @@ enum phylink_op_type {
  * @mac_requires_rxc: if true, the MAC always requires a receive clock from PHY.
  *                    The PHY driver should start the clock signal as soon as
  *                    possible and avoid stopping it during suspend events.
- * @ovr_an_inband: if true, override PCS to MLO_AN_INBAND
+ * @default_an_inband: if true, defaults to MLO_AN_INBAND rather than
+ *		       MLO_AN_PHY. A fixed-link specification will override.
  * @get_fixed_state: callback to execute to determine the fixed link state,
  *		     if MAC link is at %MLO_AN_FIXED mode.
  * @supported_interfaces: bitmap describing which PHY_INTERFACE_MODE_xxx
@@ -154,7 +155,7 @@ struct phylink_config {
 	bool poll_fixed_state;
 	bool mac_managed_pm;
 	bool mac_requires_rxc;
-	bool ovr_an_inband;
+	bool default_an_inband;
 	void (*get_fixed_state)(struct phylink_config *config,
 				struct phylink_link_state *state);
 	DECLARE_PHY_INTERFACE_MASK(supported_interfaces);
-- 
GitLab


From 5e332954e7609acc9a265fcd9df53a3102206c8d Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Wed, 29 May 2024 14:29:35 +0100
Subject: [PATCH 624/950] net: fman_memac: remove the now unnecessary checking
 for fixed-link

Since default_an_inband can be overriden by a fixed-link specification,
there is no need for memac to be checking for this before setting
default_an_inband. Remove this code and update the comment.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Sean Anderson <sean.anderson@seco.com>
Reviewed-by: Andrew Halaney <ahalaney@redhat.com>
Link: https://lore.kernel.org/r/E1sCJN1-00Ecr7-02@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/fman/fman_memac.c | 14 +++++---------
 1 file changed, 5 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.c b/drivers/net/ethernet/freescale/fman/fman_memac.c
index 9c44a3581950b..796e6f4e583d1 100644
--- a/drivers/net/ethernet/freescale/fman/fman_memac.c
+++ b/drivers/net/ethernet/freescale/fman/fman_memac.c
@@ -1066,7 +1066,6 @@ int memac_initialization(struct mac_device *mac_dev,
 			 struct fman_mac_params *params)
 {
 	int			 err;
-	struct device_node      *fixed;
 	struct phylink_pcs	*pcs;
 	struct fman_mac		*memac;
 	unsigned long		 capabilities;
@@ -1222,18 +1221,15 @@ int memac_initialization(struct mac_device *mac_dev,
 		memac->rgmii_no_half_duplex = true;
 
 	/* Most boards should use MLO_AN_INBAND, but existing boards don't have
-	 * a managed property. Default to MLO_AN_INBAND if nothing else is
-	 * specified. We need to be careful and not enable this if we have a
-	 * fixed link or if we are using MII or RGMII, since those
-	 * configurations modes don't use in-band autonegotiation.
+	 * a managed property. Default to MLO_AN_INBAND rather than MLO_AN_PHY.
+	 * Phylink will allow this to be overriden by a fixed link. We need to
+	 * be careful and not enable this if we are using MII or RGMII, since
+	 * those configurations modes don't use in-band autonegotiation.
 	 */
-	fixed = of_get_child_by_name(mac_node, "fixed-link");
-	if (!fixed && !of_property_read_bool(mac_node, "fixed-link") &&
-	    !of_property_read_bool(mac_node, "managed") &&
+	if (!of_property_read_bool(mac_node, "managed") &&
 	    mac_dev->phy_if != PHY_INTERFACE_MODE_MII &&
 	    !phy_interface_mode_is_rgmii(mac_dev->phy_if))
 		mac_dev->phylink_config.default_an_inband = true;
-	of_node_put(fixed);
 
 	err = memac_init(mac_dev->fman_mac);
 	if (err < 0)
-- 
GitLab


From 83f55b01dd903040d6ab64f4f9d78a27391a5916 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Wed, 29 May 2024 14:29:40 +0100
Subject: [PATCH 625/950] net: stmmac: rename xpcs_an_inband to
 default_an_inband

Rename xpcs_an_inband to default_an_inband to reflect the change in
phylink and its changed functionality.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Andrew Halaney <ahalaney@redhat.com>
Link: https://lore.kernel.org/r/E1sCJN6-00EcrD-43@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c | 8 ++++----
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 2 +-
 include/linux/stmmac.h                            | 2 +-
 3 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
index 60283543ffc88..5e96146b8bd93 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
@@ -248,7 +248,7 @@ static void intel_speed_mode_2500(struct net_device *ndev, void *intel_data)
 		dev_info(priv->device, "Link Speed Mode: 2.5Gbps\n");
 		priv->plat->max_speed = 2500;
 		priv->plat->phy_interface = PHY_INTERFACE_MODE_2500BASEX;
-		priv->plat->mdio_bus_data->xpcs_an_inband = false;
+		priv->plat->mdio_bus_data->default_an_inband = false;
 	} else {
 		priv->plat->max_speed = 1000;
 	}
@@ -586,16 +586,16 @@ static int intel_mgbe_common_data(struct pci_dev *pdev,
 	if (plat->phy_interface == PHY_INTERFACE_MODE_SGMII ||
 	    plat->phy_interface == PHY_INTERFACE_MODE_1000BASEX) {
 		plat->mdio_bus_data->has_xpcs = true;
-		plat->mdio_bus_data->xpcs_an_inband = true;
+		plat->mdio_bus_data->default_an_inband = true;
 	}
 
-	/* For fixed-link setup, we clear xpcs_an_inband */
+	/* For fixed-link setup, we clear default_an_inband */
 	if (fwnode) {
 		struct fwnode_handle *fixed_node;
 
 		fixed_node = fwnode_get_named_child_node(fwnode, "fixed-link");
 		if (fixed_node)
-			plat->mdio_bus_data->xpcs_an_inband = false;
+			plat->mdio_bus_data->default_an_inband = false;
 
 		fwnode_handle_put(fixed_node);
 	}
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 488b2fd2349cb..bbedf2a8c60f2 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1222,7 +1222,7 @@ static int stmmac_phy_setup(struct stmmac_priv *priv)
 	mdio_bus_data = priv->plat->mdio_bus_data;
 	if (mdio_bus_data)
 		priv->phylink_config.default_an_inband =
-			mdio_bus_data->xpcs_an_inband;
+			mdio_bus_data->default_an_inband;
 
 	/* Set the platform/firmware specified interface mode. Note, phylink
 	 * deals with the PHY interface mode, not the MAC interface mode.
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index f92c195c76ed2..8f0f156d50d35 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -83,7 +83,7 @@ struct stmmac_priv;
 struct stmmac_mdio_bus_data {
 	unsigned int phy_mask;
 	unsigned int has_xpcs;
-	unsigned int xpcs_an_inband;
+	unsigned int default_an_inband;
 	int *irqs;
 	int probed_phy_irq;
 	bool needs_reset;
-- 
GitLab


From ab77c7aa9388ccc82102c9e448112ab478bba80c Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Wed, 29 May 2024 14:29:45 +0100
Subject: [PATCH 626/950] net: stmmac: dwmac-intel: remove checking for fixed
 link

With the new default_an_inband functionality in phylink, there is no
need to check for a fixed link when this flag is set, since a fixed
link will now override default_an_inband.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Andrew Halaney <ahalaney@redhat.com>
Link: https://lore.kernel.org/r/E1sCJNB-00EcrJ-7L@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c | 11 -----------
 1 file changed, 11 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
index 5e96146b8bd93..56649edb18cd5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
@@ -589,17 +589,6 @@ static int intel_mgbe_common_data(struct pci_dev *pdev,
 		plat->mdio_bus_data->default_an_inband = true;
 	}
 
-	/* For fixed-link setup, we clear default_an_inband */
-	if (fwnode) {
-		struct fwnode_handle *fixed_node;
-
-		fixed_node = fwnode_get_named_child_node(fwnode, "fixed-link");
-		if (fixed_node)
-			plat->mdio_bus_data->default_an_inband = false;
-
-		fwnode_handle_put(fixed_node);
-	}
-
 	/* Ensure mdio bus scan skips intel serdes and pcs-xpcs */
 	plat->mdio_bus_data->phy_mask = 1 << INTEL_MGBE_ADHOC_ADDR;
 	plat->mdio_bus_data->phy_mask |= 1 << INTEL_MGBE_XPCS_ADDR;
-- 
GitLab


From ccf23c916ca35239a924ec8649cc88b1ef25d3d9 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 29 May 2024 12:20:31 -0700
Subject: [PATCH 627/950] tools: ynl: make the attr and msg helpers more C++
 friendly

Folks working on a C++ codegen would like to reuse the attribute
helpers directly. Add the few necessary casts, it's not too ugly.

Reviewed-by: Donald Hunter <donald.hunter@gmail.com>
Reviewed-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Link: https://lore.kernel.org/r/20240529192031.3785761-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/net/ynl/lib/ynl-priv.h | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/tools/net/ynl/lib/ynl-priv.h b/tools/net/ynl/lib/ynl-priv.h
index 6cf890080dc09..80791c34730c9 100644
--- a/tools/net/ynl/lib/ynl-priv.h
+++ b/tools/net/ynl/lib/ynl-priv.h
@@ -79,7 +79,7 @@ static inline void *ynl_dump_obj_next(void *obj)
 	struct ynl_dump_list_type *list;
 
 	uptr -= offsetof(struct ynl_dump_list_type, data);
-	list = (void *)uptr;
+	list = (struct ynl_dump_list_type *)uptr;
 	uptr = (unsigned long)list->next;
 	uptr += offsetof(struct ynl_dump_list_type, data);
 
@@ -139,7 +139,7 @@ int ynl_error_parse(struct ynl_parse_arg *yarg, const char *msg);
 
 static inline struct nlmsghdr *ynl_nlmsg_put_header(void *buf)
 {
-	struct nlmsghdr *nlh = buf;
+	struct nlmsghdr *nlh = (struct nlmsghdr *)buf;
 
 	memset(nlh, 0, sizeof(*nlh));
 	nlh->nlmsg_len = NLMSG_HDRLEN;
@@ -196,7 +196,7 @@ static inline void *ynl_attr_data(const struct nlattr *attr)
 
 static inline void *ynl_attr_data_end(const struct nlattr *attr)
 {
-	return ynl_attr_data(attr) + ynl_attr_data_len(attr);
+	return (char *)ynl_attr_data(attr) + ynl_attr_data_len(attr);
 }
 
 #define ynl_attr_for_each(attr, nlh, fixed_hdr_sz)			\
@@ -228,7 +228,7 @@ ynl_attr_next(const void *end, const struct nlattr *prev)
 {
 	struct nlattr *attr;
 
-	attr = (void *)((char *)prev + NLA_ALIGN(prev->nla_len));
+	attr = (struct nlattr *)((char *)prev + NLA_ALIGN(prev->nla_len));
 	return ynl_attr_if_good(end, attr);
 }
 
@@ -237,8 +237,8 @@ ynl_attr_first(const void *start, size_t len, size_t skip)
 {
 	struct nlattr *attr;
 
-	attr = (void *)((char *)start + NLMSG_ALIGN(skip));
-	return ynl_attr_if_good(start + len, attr);
+	attr = (struct nlattr *)((char *)start + NLMSG_ALIGN(skip));
+	return ynl_attr_if_good((char *)start + len, attr);
 }
 
 static inline bool
@@ -262,9 +262,9 @@ ynl_attr_nest_start(struct nlmsghdr *nlh, unsigned int attr_type)
 	struct nlattr *attr;
 
 	if (__ynl_attr_put_overflow(nlh, 0))
-		return ynl_nlmsg_end_addr(nlh) - NLA_HDRLEN;
+		return (struct nlattr *)ynl_nlmsg_end_addr(nlh) - 1;
 
-	attr = ynl_nlmsg_end_addr(nlh);
+	attr = (struct nlattr *)ynl_nlmsg_end_addr(nlh);
 	attr->nla_type = attr_type | NLA_F_NESTED;
 	nlh->nlmsg_len += NLA_HDRLEN;
 
@@ -286,7 +286,7 @@ ynl_attr_put(struct nlmsghdr *nlh, unsigned int attr_type,
 	if (__ynl_attr_put_overflow(nlh, size))
 		return;
 
-	attr = ynl_nlmsg_end_addr(nlh);
+	attr = (struct nlattr *)ynl_nlmsg_end_addr(nlh);
 	attr->nla_type = attr_type;
 	attr->nla_len = NLA_HDRLEN + size;
 
@@ -305,10 +305,10 @@ ynl_attr_put_str(struct nlmsghdr *nlh, unsigned int attr_type, const char *str)
 	if (__ynl_attr_put_overflow(nlh, len))
 		return;
 
-	attr = ynl_nlmsg_end_addr(nlh);
+	attr = (struct nlattr *)ynl_nlmsg_end_addr(nlh);
 	attr->nla_type = attr_type;
 
-	strcpy(ynl_attr_data(attr), str);
+	strcpy((char *)ynl_attr_data(attr), str);
 	attr->nla_len = NLA_HDRLEN + NLA_ALIGN(len);
 
 	nlh->nlmsg_len += NLMSG_ALIGN(attr->nla_len);
-- 
GitLab


From 0a751df4566c86e5a24f2a03290dad3d0f215692 Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Thu, 30 May 2024 09:45:47 -0400
Subject: [PATCH 628/950] blk-throttle: Fix incorrect display of io.max

Commit bf20ab538c81 ("blk-throttle: remove CONFIG_BLK_DEV_THROTTLING_LOW")
attempts to revert the code change introduced by commit cd5ab1b0fcb4
("blk-throttle: add .low interface").  However, it leaves behind the
bps_conf[] and iops_conf[] fields in the throtl_grp structure which
aren't set anywhere in the new blk-throttle.c code but are still being
used by tg_prfill_limit() to display the limits in io.max. Now io.max
always displays the following values if a block queue is used:

	<m>:<n> rbps=0 wbps=0 riops=0 wiops=0

Fix this problem by removing bps_conf[] and iops_conf[] and use bps[]
and iops[] instead to complete the revert.

Fixes: bf20ab538c81 ("blk-throttle: remove CONFIG_BLK_DEV_THROTTLING_LOW")
Reported-by: Justin Forbes <jforbes@redhat.com>
Closes: https://github.com/containers/podman/issues/22701#issuecomment-2120627789
Signed-off-by: Waiman Long <longman@redhat.com>
Acked-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Yu Kuai <yukuai3@huawei.com>
Link: https://lore.kernel.org/r/20240530134547.970075-1-longman@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-throttle.c | 24 ++++++++++++------------
 block/blk-throttle.h |  8 ++------
 2 files changed, 14 insertions(+), 18 deletions(-)

diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 0be180f9a7899..c1bf73f8c75d9 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -1399,32 +1399,32 @@ static u64 tg_prfill_limit(struct seq_file *sf, struct blkg_policy_data *pd,
 	bps_dft = U64_MAX;
 	iops_dft = UINT_MAX;
 
-	if (tg->bps_conf[READ] == bps_dft &&
-	    tg->bps_conf[WRITE] == bps_dft &&
-	    tg->iops_conf[READ] == iops_dft &&
-	    tg->iops_conf[WRITE] == iops_dft)
+	if (tg->bps[READ] == bps_dft &&
+	    tg->bps[WRITE] == bps_dft &&
+	    tg->iops[READ] == iops_dft &&
+	    tg->iops[WRITE] == iops_dft)
 		return 0;
 
 	seq_printf(sf, "%s", dname);
-	if (tg->bps_conf[READ] == U64_MAX)
+	if (tg->bps[READ] == U64_MAX)
 		seq_printf(sf, " rbps=max");
 	else
-		seq_printf(sf, " rbps=%llu", tg->bps_conf[READ]);
+		seq_printf(sf, " rbps=%llu", tg->bps[READ]);
 
-	if (tg->bps_conf[WRITE] == U64_MAX)
+	if (tg->bps[WRITE] == U64_MAX)
 		seq_printf(sf, " wbps=max");
 	else
-		seq_printf(sf, " wbps=%llu", tg->bps_conf[WRITE]);
+		seq_printf(sf, " wbps=%llu", tg->bps[WRITE]);
 
-	if (tg->iops_conf[READ] == UINT_MAX)
+	if (tg->iops[READ] == UINT_MAX)
 		seq_printf(sf, " riops=max");
 	else
-		seq_printf(sf, " riops=%u", tg->iops_conf[READ]);
+		seq_printf(sf, " riops=%u", tg->iops[READ]);
 
-	if (tg->iops_conf[WRITE] == UINT_MAX)
+	if (tg->iops[WRITE] == UINT_MAX)
 		seq_printf(sf, " wiops=max");
 	else
-		seq_printf(sf, " wiops=%u", tg->iops_conf[WRITE]);
+		seq_printf(sf, " wiops=%u", tg->iops[WRITE]);
 
 	seq_printf(sf, "\n");
 	return 0;
diff --git a/block/blk-throttle.h b/block/blk-throttle.h
index 393c3d134b967..4d9ef5abdf21c 100644
--- a/block/blk-throttle.h
+++ b/block/blk-throttle.h
@@ -95,15 +95,11 @@ struct throtl_grp {
 	bool has_rules_bps[2];
 	bool has_rules_iops[2];
 
-	/* internally used bytes per second rate limits */
+	/* bytes per second rate limits */
 	uint64_t bps[2];
-	/* user configured bps limits */
-	uint64_t bps_conf[2];
 
-	/* internally used IOPS limits */
+	/* IOPS limits */
 	unsigned int iops[2];
-	/* user configured IOPS limits */
-	unsigned int iops_conf[2];
 
 	/* Number of bytes dispatched in current slice */
 	uint64_t bytes_disp[2];
-- 
GitLab


From 2d707b4e37f9b0c37b8b2392f91b04c5b63ea538 Mon Sep 17 00:00:00 2001
From: Yong-Xuan Wang <yongxuan.wang@sifive.com>
Date: Mon, 15 Apr 2024 14:49:04 +0800
Subject: [PATCH 629/950] RISC-V: KVM: No need to use mask when hart-index-bit
 is 0

When the maximum hart number within groups is 1, hart-index-bit is set to
0. Consequently, there is no need to restore the hart ID from IMSIC
addresses and hart-index-bit settings. Currently, QEMU and kvmtool do not
pass correct hart-index-bit values when the maximum hart number is a
power of 2, thereby avoiding this issue. Corresponding patches for QEMU
and kvmtool will also be dispatched.

Fixes: 89d01306e34d ("RISC-V: KVM: Implement device interface for AIA irqchip")
Signed-off-by: Yong-Xuan Wang <yongxuan.wang@sifive.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Link: https://lore.kernel.org/r/20240415064905.25184-1-yongxuan.wang@sifive.com
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/aia_device.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/arch/riscv/kvm/aia_device.c b/arch/riscv/kvm/aia_device.c
index 0eb689351b7d0..5cd407c6a8e4f 100644
--- a/arch/riscv/kvm/aia_device.c
+++ b/arch/riscv/kvm/aia_device.c
@@ -237,10 +237,11 @@ static gpa_t aia_imsic_ppn(struct kvm_aia *aia, gpa_t addr)
 
 static u32 aia_imsic_hart_index(struct kvm_aia *aia, gpa_t addr)
 {
-	u32 hart, group = 0;
+	u32 hart = 0, group = 0;
 
-	hart = (addr >> (aia->nr_guest_bits + IMSIC_MMIO_PAGE_SHIFT)) &
-		GENMASK_ULL(aia->nr_hart_bits - 1, 0);
+	if (aia->nr_hart_bits)
+		hart = (addr >> (aia->nr_guest_bits + IMSIC_MMIO_PAGE_SHIFT)) &
+		       GENMASK_ULL(aia->nr_hart_bits - 1, 0);
 	if (aia->nr_group_bits)
 		group = (addr >> aia->nr_group_shift) &
 			GENMASK_ULL(aia->nr_group_bits - 1, 0);
-- 
GitLab


From c66f3b40b17d3dfc4b6abb5efde8e71c46971821 Mon Sep 17 00:00:00 2001
From: Quan Zhou <zhouquan@iscas.ac.cn>
Date: Thu, 23 May 2024 10:13:34 +0800
Subject: [PATCH 630/950] RISC-V: KVM: Fix incorrect reg_subtype labels in
 kvm_riscv_vcpu_set_reg_isa_ext function

In the function kvm_riscv_vcpu_set_reg_isa_ext, the original code
used incorrect reg_subtype labels KVM_REG_RISCV_SBI_MULTI_EN/DIS.
These have been corrected to KVM_REG_RISCV_ISA_MULTI_EN/DIS respectively.
Although they are numerically equivalent, the actual processing
will not result in errors, but it may lead to ambiguous code semantics.

Fixes: 613029442a4b ("RISC-V: KVM: Extend ONE_REG to enable/disable multiple ISA extensions")
Signed-off-by: Quan Zhou <zhouquan@iscas.ac.cn>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Link: https://lore.kernel.org/r/ff1c6771a67d660db94372ac9aaa40f51e5e0090.1716429371.git.zhouquan@iscas.ac.cn
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/vcpu_onereg.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index c676275ea0a01..62874fbca29ff 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -724,9 +724,9 @@ static int kvm_riscv_vcpu_set_reg_isa_ext(struct kvm_vcpu *vcpu,
 	switch (reg_subtype) {
 	case KVM_REG_RISCV_ISA_SINGLE:
 		return riscv_vcpu_set_isa_ext_single(vcpu, reg_num, reg_val);
-	case KVM_REG_RISCV_SBI_MULTI_EN:
+	case KVM_REG_RISCV_ISA_MULTI_EN:
 		return riscv_vcpu_set_isa_ext_multi(vcpu, reg_num, reg_val, true);
-	case KVM_REG_RISCV_SBI_MULTI_DIS:
+	case KVM_REG_RISCV_ISA_MULTI_DIS:
 		return riscv_vcpu_set_isa_ext_multi(vcpu, reg_num, reg_val, false);
 	default:
 		return -ENOENT;
-- 
GitLab


From 310fa3ec2859f1c094e6e9b5d2e1ca51738c409a Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Fri, 31 May 2024 09:51:07 +0200
Subject: [PATCH 631/950] ALSA: seq: ump: Fix swapped song position pointer
 data

At converting between the legacy event and UMP, the parameters for
MIDI Song Position Pointer are incorrectly stored.  It should have
been LSB -> MSB order while it stored in MSB -> LSB order.
This patch corrects the ordering.

Fixes: e9e02819a98a ("ALSA: seq: Automatic conversion of UMP events")
Link: https://lore.kernel.org/r/20240531075110.3250-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/core/seq/seq_ump_convert.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/sound/core/seq/seq_ump_convert.c b/sound/core/seq/seq_ump_convert.c
index f0f332017e662..171fb75267afa 100644
--- a/sound/core/seq/seq_ump_convert.c
+++ b/sound/core/seq/seq_ump_convert.c
@@ -157,7 +157,7 @@ static void ump_system_to_one_param_ev(const union snd_ump_midi1_msg *val,
 static void ump_system_to_songpos_ev(const union snd_ump_midi1_msg *val,
 				     struct snd_seq_event *ev)
 {
-	ev->data.control.value = (val->system.parm1 << 7) | val->system.parm2;
+	ev->data.control.value = (val->system.parm2 << 7) | val->system.parm1;
 }
 
 /* Encoders for 0xf0 - 0xff */
@@ -754,8 +754,8 @@ static int system_2p_ev_to_ump_midi1(const struct snd_seq_event *event,
 {
 	data->system.type = UMP_MSG_TYPE_SYSTEM; // override
 	data->system.status = status;
-	data->system.parm1 = (event->data.control.value >> 7) & 0x7f;
-	data->system.parm2 = event->data.control.value & 0x7f;
+	data->system.parm1 = event->data.control.value & 0x7f;
+	data->system.parm2 = (event->data.control.value >> 7) & 0x7f;
 	return 1;
 }
 
-- 
GitLab


From 0a44078f2b72abcdda47581c942bd5d0468ec50b Mon Sep 17 00:00:00 2001
From: Jeff Johnson <quic_jjohnson@quicinc.com>
Date: Thu, 30 May 2024 13:12:03 -0700
Subject: [PATCH 632/950] perf/x86/rapl: Add missing MODULE_DESCRIPTION() line

Fix the warning from 'make C=1 W=1':

  WARNING: modpost: missing MODULE_DESCRIPTION() in arch/x86/events/rapl.o

Signed-off-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Link: https://lore.kernel.org/r/20240530-md-arch-x86-events-v1-1-e45ffa8af99f@quicinc.com
---
 arch/x86/events/rapl.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c
index 46e6735855603..0c5e7a7c43ac0 100644
--- a/arch/x86/events/rapl.c
+++ b/arch/x86/events/rapl.c
@@ -64,6 +64,7 @@
 #include "perf_event.h"
 #include "probe.h"
 
+MODULE_DESCRIPTION("Support Intel/AMD RAPL energy consumption counters");
 MODULE_LICENSE("GPL");
 
 /*
-- 
GitLab


From dc8e5dfb52d56e955ad09174330252710845b8d2 Mon Sep 17 00:00:00 2001
From: Jeff Johnson <quic_jjohnson@quicinc.com>
Date: Thu, 30 May 2024 13:42:51 -0700
Subject: [PATCH 633/950] perf/x86/intel: Add missing MODULE_DESCRIPTION()
 lines

Fix the 'make W=1 C=1' warnings:

  WARNING: modpost: missing MODULE_DESCRIPTION() in arch/x86/events/intel/intel-uncore.o
  WARNING: modpost: missing MODULE_DESCRIPTION() in arch/x86/events/intel/intel-cstate.o

Signed-off-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Link: https://lore.kernel.org/r/20240530-md-arch-x86-events-intel-v1-1-8252194ed20a@quicinc.com
---
 arch/x86/events/intel/cstate.c | 1 +
 arch/x86/events/intel/uncore.c | 1 +
 2 files changed, 2 insertions(+)

diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index e64eaa8dda5a4..9d6e8f13d13a7 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -114,6 +114,7 @@
 #include "../perf_event.h"
 #include "../probe.h"
 
+MODULE_DESCRIPTION("Support for Intel cstate performance events");
 MODULE_LICENSE("GPL");
 
 #define DEFINE_CSTATE_FORMAT_ATTR(_var, _name, _format)		\
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 419c517b8594f..c68f5b39952b0 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -34,6 +34,7 @@ static struct event_constraint uncore_constraint_fixed =
 struct event_constraint uncore_constraint_empty =
 	EVENT_CONSTRAINT(0, 0, 0);
 
+MODULE_DESCRIPTION("Support for Intel uncore performance events");
 MODULE_LICENSE("GPL");
 
 int uncore_pcibus_to_dieid(struct pci_bus *bus)
-- 
GitLab


From d40605a6823577a6c40fad6fb1f10a40ea0389d7 Mon Sep 17 00:00:00 2001
From: Phil Auld <pauld@redhat.com>
Date: Thu, 30 May 2024 14:15:48 -0400
Subject: [PATCH 634/950] sched/x86: Export 'percpu arch_freq_scale'

Commit:

  7bc263840bc3 ("sched/topology: Consolidate and clean up access to a CPU's max compute capacity")

removed rq->cpu_capacity_orig in favor of using arch_scale_freq_capacity()
calls. Export the underlying percpu symbol on x86 so that external trace
point helper modules can be made to work again.

Signed-off-by: Phil Auld <pauld@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20240530181548.2039216-1-pauld@redhat.com
---
 arch/x86/kernel/cpu/aperfmperf.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c
index f9a8c7b7943fb..b3fa61d45352e 100644
--- a/arch/x86/kernel/cpu/aperfmperf.c
+++ b/arch/x86/kernel/cpu/aperfmperf.c
@@ -345,6 +345,7 @@ static DECLARE_WORK(disable_freq_invariance_work,
 		    disable_freq_invariance_workfn);
 
 DEFINE_PER_CPU(unsigned long, arch_freq_scale) = SCHED_CAPACITY_SCALE;
+EXPORT_PER_CPU_SYMBOL_GPL(arch_freq_scale);
 
 static void scale_freq_tick(u64 acnt, u64 mcnt)
 {
-- 
GitLab


From 86aaa7e9d641c1ad1035ed2df88b8d0b48c86b30 Mon Sep 17 00:00:00 2001
From: Niklas Cassel <cassel@kernel.org>
Date: Thu, 30 May 2024 23:28:17 +0200
Subject: [PATCH 635/950] ata: libata-core: Add ATA_HORKAGE_NOLPM for Crucial
 CT240BX500SSD1

Commit 7627a0edef54 ("ata: ahci: Drop low power policy board type")
dropped the board_ahci_low_power board type, and instead enables LPM if:
-The AHCI controller reports that it supports LPM (Partial/Slumber), and
-CONFIG_SATA_MOBILE_LPM_POLICY != 0, and
-The port is not defined as external in the per port PxCMD register, and
-The port is not defined as hotplug capable in the per port PxCMD
 register.

Partial and Slumber LPM states can either be initiated by HIPM or DIPM.

For HIPM (host initiated power management) to get enabled, both the AHCI
controller and the drive have to report that they support HIPM.

For DIPM (device initiated power management) to get enabled, only the
drive has to report that it supports DIPM. However, the HBA will reject
device requests to enter LPM states which the HBA does not support.

The problem is that Crucial CT240BX500SSD1 drives do not handle low power
modes correctly. The problem was most likely not seen before because no
one had used this drive with a AHCI controller with LPM enabled.

Add a quirk so that we do not enable LPM for this drive, since we see
command timeouts if we do (even though the drive claims to support DIPM).

Fixes: 7627a0edef54 ("ata: ahci: Drop low power policy board type")
Cc: stable@vger.kernel.org
Reported-by: Aarrayy <lp610mh@gmail.com>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=218832
Reviewed-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Niklas Cassel <cassel@kernel.org>
---
 drivers/ata/libata-core.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 4f35aab81a0a3..b0ce621fe2a11 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -4136,8 +4136,9 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = {
 	{ "PIONEER BD-RW   BDR-207M",	NULL,	ATA_HORKAGE_NOLPM },
 	{ "PIONEER BD-RW   BDR-205",	NULL,	ATA_HORKAGE_NOLPM },
 
-	/* Crucial BX100 SSD 500GB has broken LPM support */
+	/* Crucial devices with broken LPM support */
 	{ "CT500BX100SSD1",		NULL,	ATA_HORKAGE_NOLPM },
+	{ "CT240BX500SSD1",		NULL,	ATA_HORKAGE_NOLPM },
 
 	/* 512GB MX100 with MU01 firmware has both queued TRIM and LPM issues */
 	{ "Crucial_CT512MX100*",	"MU01",	ATA_HORKAGE_NO_NCQ_TRIM |
-- 
GitLab


From 473880369304cfd4445720cdd8bae4c6f1e16e60 Mon Sep 17 00:00:00 2001
From: Niklas Cassel <cassel@kernel.org>
Date: Thu, 30 May 2024 23:32:44 +0200
Subject: [PATCH 636/950] ata: libata-core: Add ATA_HORKAGE_NOLPM for AMD
 Radeon S3 SSD

Commit 7627a0edef54 ("ata: ahci: Drop low power policy board type")
dropped the board_ahci_low_power board type, and instead enables LPM if:
-The AHCI controller reports that it supports LPM (Partial/Slumber), and
-CONFIG_SATA_MOBILE_LPM_POLICY != 0, and
-The port is not defined as external in the per port PxCMD register, and
-The port is not defined as hotplug capable in the per port PxCMD
 register.

Partial and Slumber LPM states can either be initiated by HIPM or DIPM.

For HIPM (host initiated power management) to get enabled, both the AHCI
controller and the drive have to report that they support HIPM.

For DIPM (device initiated power management) to get enabled, only the
drive has to report that it supports DIPM. However, the HBA will reject
device requests to enter LPM states which the HBA does not support.

The problem is that AMD Radeon S3 SSD drives do not handle low power modes
correctly. The problem was most likely not seen before because no one
had used this drive with a AHCI controller with LPM enabled.

Add a quirk so that we do not enable LPM for this drive, since we see
command timeouts if we do (even though the drive claims to support both
HIPM and DIPM).

Fixes: 7627a0edef54 ("ata: ahci: Drop low power policy board type")
Cc: stable@vger.kernel.org
Reported-by: Doru Iorgulescu <doru.iorgulescu1@gmail.com>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=218832
Reviewed-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Niklas Cassel <cassel@kernel.org>
---
 drivers/ata/libata-core.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index b0ce621fe2a11..4ea859dc381aa 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -4156,6 +4156,9 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = {
 						ATA_HORKAGE_ZERO_AFTER_TRIM |
 						ATA_HORKAGE_NOLPM },
 
+	/* AMD Radeon devices with broken LPM support */
+	{ "R3SL240G",			NULL,	ATA_HORKAGE_NOLPM },
+
 	/* These specific Samsung models/firmware-revs do not handle LPM well */
 	{ "SAMSUNG MZMPC128HBFU-000MV", "CXM14M1Q", ATA_HORKAGE_NOLPM },
 	{ "SAMSUNG SSD PM830 mSATA *",  "CXM13D1Q", ATA_HORKAGE_NOLPM },
-- 
GitLab


From 3cb648c4dd3e8dde800fb3659250ed11f2d9efa5 Mon Sep 17 00:00:00 2001
From: Niklas Cassel <cassel@kernel.org>
Date: Thu, 30 May 2024 23:27:04 +0200
Subject: [PATCH 637/950] ata: libata-core: Add ATA_HORKAGE_NOLPM for Apacer
 AS340

Commit 7627a0edef54 ("ata: ahci: Drop low power policy board type")
dropped the board_ahci_low_power board type, and instead enables LPM if:
-The AHCI controller reports that it supports LPM (Partial/Slumber), and
-CONFIG_SATA_MOBILE_LPM_POLICY != 0, and
-The port is not defined as external in the per port PxCMD register, and
-The port is not defined as hotplug capable in the per port PxCMD
 register.

Partial and Slumber LPM states can either be initiated by HIPM or DIPM.

For HIPM (host initiated power management) to get enabled, both the AHCI
controller and the drive have to report that they support HIPM.

For DIPM (device initiated power management) to get enabled, only the
drive has to report that it supports DIPM. However, the HBA will reject
device requests to enter LPM states which the HBA does not support.

The problem is that Apacer AS340 drives do not handle low power modes
correctly. The problem was most likely not seen before because no one
had used this drive with a AHCI controller with LPM enabled.

Add a quirk so that we do not enable LPM for this drive, since we see
command timeouts if we do (even though the drive claims to support DIPM).

Fixes: 7627a0edef54 ("ata: ahci: Drop low power policy board type")
Cc: stable@vger.kernel.org
Reported-by: Tim Teichmann <teichmanntim@outlook.de>
Closes: https://lore.kernel.org/linux-ide/87bk4pbve8.ffs@tglx/
Reviewed-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Niklas Cassel <cassel@kernel.org>
---
 drivers/ata/libata-core.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 4ea859dc381aa..e1bf8a19b3c89 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -4159,6 +4159,9 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = {
 	/* AMD Radeon devices with broken LPM support */
 	{ "R3SL240G",			NULL,	ATA_HORKAGE_NOLPM },
 
+	/* Apacer models with LPM issues */
+	{ "Apacer AS340*",		NULL,	ATA_HORKAGE_NOLPM },
+
 	/* These specific Samsung models/firmware-revs do not handle LPM well */
 	{ "SAMSUNG MZMPC128HBFU-000MV", "CXM14M1Q", ATA_HORKAGE_NOLPM },
 	{ "SAMSUNG SSD PM830 mSATA *",  "CXM13D1Q", ATA_HORKAGE_NOLPM },
-- 
GitLab


From 0f42bdf59b4e428485aa922bef871bfa6cc505e0 Mon Sep 17 00:00:00 2001
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Date: Fri, 31 May 2024 18:43:37 +0900
Subject: [PATCH 638/950] selftests/tracing: Fix event filter test to retry up
 to 10 times

Commit eb50d0f250e9 ("selftests/ftrace: Choose target function for filter
test from samples") choose the target function from samples, but sometimes
this test failes randomly because the target function does not hit at the
next time. So retry getting samples up to 10 times.

Fixes: eb50d0f250e9 ("selftests/ftrace: Choose target function for filter test from samples")
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 .../test.d/filter/event-filter-function.tc    | 20 ++++++++++++++++++-
 1 file changed, 19 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc b/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc
index 3f74c09c56b62..118247b8dd84d 100644
--- a/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc
+++ b/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc
@@ -10,7 +10,6 @@ fail() { #msg
 }
 
 sample_events() {
-    echo > trace
     echo 1 > events/kmem/kmem_cache_free/enable
     echo 1 > tracing_on
     ls > /dev/null
@@ -22,6 +21,7 @@ echo 0 > tracing_on
 echo 0 > events/enable
 
 echo "Get the most frequently calling function"
+echo > trace
 sample_events
 
 target_func=`cat trace | grep -o 'call_site=\([^+]*\)' | sed 's/call_site=//' | sort | uniq -c | sort | tail -n 1 | sed 's/^[ 0-9]*//'`
@@ -32,7 +32,16 @@ echo > trace
 
 echo "Test event filter function name"
 echo "call_site.function == $target_func" > events/kmem/kmem_cache_free/filter
+
+sample_events
+max_retry=10
+while [ `grep kmem_cache_free trace| wc -l` -eq 0 ]; do
 sample_events
+max_retry=$((max_retry - 1))
+if [ $max_retry -eq 0 ]; then
+	exit_fail
+fi
+done
 
 hitcnt=`grep kmem_cache_free trace| grep $target_func | wc -l`
 misscnt=`grep kmem_cache_free trace| grep -v $target_func | wc -l`
@@ -49,7 +58,16 @@ address=`grep " ${target_func}\$" /proc/kallsyms | cut -d' ' -f1`
 
 echo "Test event filter function address"
 echo "call_site.function == 0x$address" > events/kmem/kmem_cache_free/filter
+echo > trace
+sample_events
+max_retry=10
+while [ `grep kmem_cache_free trace| wc -l` -eq 0 ]; do
 sample_events
+max_retry=$((max_retry - 1))
+if [ $max_retry -eq 0 ]; then
+	exit_fail
+fi
+done
 
 hitcnt=`grep kmem_cache_free trace| grep $target_func | wc -l`
 misscnt=`grep kmem_cache_free trace| grep -v $target_func | wc -l`
-- 
GitLab


From 88da52ccd66e65f2e63a6c35c9dff55d448ef4dc Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Micka=C3=ABl=20Sala=C3=BCn?= <mic@digikod.net>
Date: Thu, 16 May 2024 20:19:34 +0200
Subject: [PATCH 639/950] landlock: Fix d_parent walk
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The WARN_ON_ONCE() in collect_domain_accesses() can be triggered when
trying to link a root mount point.  This cannot work in practice because
this directory is mounted, but the VFS check is done after the call to
security_path_link().

Do not use source directory's d_parent when the source directory is the
mount point.

Cc: Günther Noack <gnoack@google.com>
Cc: Paul Moore <paul@paul-moore.com>
Cc: stable@vger.kernel.org
Reported-by: syzbot+bf4903dc7e12b18ebc87@syzkaller.appspotmail.com
Fixes: b91c3e4ea756 ("landlock: Add support for file reparenting with LANDLOCK_ACCESS_FS_REFER")
Closes: https://lore.kernel.org/r/000000000000553d3f0618198200@google.com
Link: https://lore.kernel.org/r/20240516181935.1645983-2-mic@digikod.net
[mic: Fix commit message]
Signed-off-by: Mickaël Salaün <mic@digikod.net>
---
 security/landlock/fs.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/security/landlock/fs.c b/security/landlock/fs.c
index 22d8b7c28074e..7877a64cc6b87 100644
--- a/security/landlock/fs.c
+++ b/security/landlock/fs.c
@@ -1110,6 +1110,7 @@ static int current_check_refer_path(struct dentry *const old_dentry,
 	bool allow_parent1, allow_parent2;
 	access_mask_t access_request_parent1, access_request_parent2;
 	struct path mnt_dir;
+	struct dentry *old_parent;
 	layer_mask_t layer_masks_parent1[LANDLOCK_NUM_ACCESS_FS] = {},
 		     layer_masks_parent2[LANDLOCK_NUM_ACCESS_FS] = {};
 
@@ -1157,9 +1158,17 @@ static int current_check_refer_path(struct dentry *const old_dentry,
 	mnt_dir.mnt = new_dir->mnt;
 	mnt_dir.dentry = new_dir->mnt->mnt_root;
 
+	/*
+	 * old_dentry may be the root of the common mount point and
+	 * !IS_ROOT(old_dentry) at the same time (e.g. with open_tree() and
+	 * OPEN_TREE_CLONE).  We do not need to call dget(old_parent) because
+	 * we keep a reference to old_dentry.
+	 */
+	old_parent = (old_dentry == mnt_dir.dentry) ? old_dentry :
+						      old_dentry->d_parent;
+
 	/* new_dir->dentry is equal to new_dentry->d_parent */
-	allow_parent1 = collect_domain_accesses(dom, mnt_dir.dentry,
-						old_dentry->d_parent,
+	allow_parent1 = collect_domain_accesses(dom, mnt_dir.dentry, old_parent,
 						&layer_masks_parent1);
 	allow_parent2 = collect_domain_accesses(
 		dom, mnt_dir.dentry, new_dir->dentry, &layer_masks_parent2);
-- 
GitLab


From 0055f53aac80fd938bf7cdfad7ad414ca6c0e198 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Micka=C3=ABl=20Sala=C3=BCn?= <mic@digikod.net>
Date: Thu, 16 May 2024 20:19:35 +0200
Subject: [PATCH 640/950] selftests/landlock: Add layout1.refer_mount_root
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add tests to check error codes when linking or renaming a mount root
directory.  This previously triggered a kernel warning, but it is fixed
with the previous commit.

Cc: Günther Noack <gnoack@google.com>
Cc: Paul Moore <paul@paul-moore.com>
Link: https://lore.kernel.org/r/20240516181935.1645983-3-mic@digikod.net
Signed-off-by: Mickaël Salaün <mic@digikod.net>
---
 tools/testing/selftests/landlock/fs_test.c | 45 ++++++++++++++++++++++
 1 file changed, 45 insertions(+)

diff --git a/tools/testing/selftests/landlock/fs_test.c b/tools/testing/selftests/landlock/fs_test.c
index 6b5a9ff88c3d7..7d063c652be16 100644
--- a/tools/testing/selftests/landlock/fs_test.c
+++ b/tools/testing/selftests/landlock/fs_test.c
@@ -35,6 +35,7 @@
  * See https://sourceware.org/glibc/wiki/Synchronizing_Headers.
  */
 #include <linux/fs.h>
+#include <linux/mount.h>
 
 #include "common.h"
 
@@ -47,6 +48,13 @@ int renameat2(int olddirfd, const char *oldpath, int newdirfd,
 }
 #endif
 
+#ifndef open_tree
+int open_tree(int dfd, const char *filename, unsigned int flags)
+{
+	return syscall(__NR_open_tree, dfd, filename, flags);
+}
+#endif
+
 #ifndef RENAME_EXCHANGE
 #define RENAME_EXCHANGE (1 << 1)
 #endif
@@ -2400,6 +2408,43 @@ TEST_F_FORK(layout1, refer_denied_by_default4)
 				layer_dir_s1d1_refer);
 }
 
+/*
+ * Tests walking through a denied root mount.
+ */
+TEST_F_FORK(layout1, refer_mount_root_deny)
+{
+	const struct landlock_ruleset_attr ruleset_attr = {
+		.handled_access_fs = LANDLOCK_ACCESS_FS_MAKE_DIR,
+	};
+	int root_fd, ruleset_fd;
+
+	/* Creates a mount object from a non-mount point. */
+	set_cap(_metadata, CAP_SYS_ADMIN);
+	root_fd =
+		open_tree(AT_FDCWD, dir_s1d1,
+			  AT_EMPTY_PATH | OPEN_TREE_CLONE | OPEN_TREE_CLOEXEC);
+	clear_cap(_metadata, CAP_SYS_ADMIN);
+	ASSERT_LE(0, root_fd);
+
+	ruleset_fd =
+		landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0);
+	ASSERT_LE(0, ruleset_fd);
+
+	ASSERT_EQ(0, prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0));
+	ASSERT_EQ(0, landlock_restrict_self(ruleset_fd, 0));
+	EXPECT_EQ(0, close(ruleset_fd));
+
+	/* Link denied by Landlock: EACCES. */
+	EXPECT_EQ(-1, linkat(root_fd, ".", root_fd, "does_not_exist", 0));
+	EXPECT_EQ(EACCES, errno);
+
+	/* renameat2() always returns EBUSY. */
+	EXPECT_EQ(-1, renameat2(root_fd, ".", root_fd, "does_not_exist", 0));
+	EXPECT_EQ(EBUSY, errno);
+
+	EXPECT_EQ(0, close(root_fd));
+}
+
 TEST_F_FORK(layout1, reparent_link)
 {
 	const struct rule layer1[] = {
-- 
GitLab


From 518549c120e671c4906f77d1802b97e9b23f673a Mon Sep 17 00:00:00 2001
From: Steve French <stfrench@microsoft.com>
Date: Wed, 29 May 2024 18:16:56 -0500
Subject: [PATCH 641/950] cifs: fix creating sockets when using sfu mount
 options

When running fstest generic/423 with sfu mount option, it
was being skipped due to inability to create sockets:

  generic/423  [not run] cifs does not support mknod/mkfifo

which can also be easily reproduced with their af_unix tool:

  ./src/af_unix /mnt1/socket-two bind: Operation not permitted

Fix sfu mount option to allow creating and reporting sockets.

Cc: stable@vger.kernel.org
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cifspdu.h | 2 +-
 fs/smb/client/inode.c   | 4 ++++
 fs/smb/client/smb2ops.c | 3 +++
 3 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/fs/smb/client/cifspdu.h b/fs/smb/client/cifspdu.h
index c46d418c1c0c3..a2072ab9e586d 100644
--- a/fs/smb/client/cifspdu.h
+++ b/fs/smb/client/cifspdu.h
@@ -2574,7 +2574,7 @@ typedef struct {
 
 
 struct win_dev {
-	unsigned char type[8]; /* IntxCHR or IntxBLK or LnxFIFO*/
+	unsigned char type[8]; /* IntxCHR or IntxBLK or LnxFIFO or LnxSOCK */
 	__le64 major;
 	__le64 minor;
 } __attribute__((packed));
diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c
index 262576573eb51..4a8aa1de95223 100644
--- a/fs/smb/client/inode.c
+++ b/fs/smb/client/inode.c
@@ -606,6 +606,10 @@ cifs_sfu_type(struct cifs_fattr *fattr, const char *path,
 				mnr = le64_to_cpu(*(__le64 *)(pbuf+16));
 				fattr->cf_rdev = MKDEV(mjr, mnr);
 			}
+		} else if (memcmp("LnxSOCK", pbuf, 8) == 0) {
+			cifs_dbg(FYI, "Socket\n");
+			fattr->cf_mode |= S_IFSOCK;
+			fattr->cf_dtype = DT_SOCK;
 		} else if (memcmp("IntxLNK", pbuf, 7) == 0) {
 			cifs_dbg(FYI, "Symlink\n");
 			fattr->cf_mode |= S_IFLNK;
diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index 4ce6c3121a7ef..c8e536540895a 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -4997,6 +4997,9 @@ static int __cifs_sfu_make_node(unsigned int xid, struct inode *inode,
 		pdev.major = cpu_to_le64(MAJOR(dev));
 		pdev.minor = cpu_to_le64(MINOR(dev));
 		break;
+	case S_IFSOCK:
+		strscpy(pdev.type, "LnxSOCK");
+		break;
 	case S_IFIFO:
 		strscpy(pdev.type, "LnxFIFO");
 		break;
-- 
GitLab


From adb77bba9c664f5d120e0ffb1387e9d7408e1529 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Tue, 9 Apr 2024 19:31:52 -0700
Subject: [PATCH 642/950] scsi: mpt3sas: Avoid possible run-time warning with
 long manufacturer strings

The prior strscpy() replacement of strncpy() here expected the
manufacture_reply strings to be NUL-terminated, but it is possible
they are not, as the code pattern here shows, e.g., edev->vendor_id
being exactly 1 character larger than manufacture_reply->vendor_id,
and the replaced strncpy() was copying only up to the size of the
source character array. Replace this with memtostr(), which is the
unambiguous way to convert a maybe not-NUL-terminated character array
into a NUL-terminated string.

Fixes: b7e9712a02e8 ("scsi: mpt3sas: Replace deprecated strncpy() with strscpy()")
Signed-off-by: Kees Cook <keescook@chromium.org>
Tested-by: Marco Patalano <mpatalan@redhat.com>
Reviewed-by: Ewan D. Milne <emilne@redhat.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Link: https://lore.kernel.org/r/20240410023155.2100422-3-keescook@chromium.org
Signed-off-by: Kees Cook <kees@kernel.org>
---
 drivers/scsi/mpt3sas/mpt3sas_base.c      |  2 +-
 drivers/scsi/mpt3sas/mpt3sas_transport.c | 14 +++++---------
 2 files changed, 6 insertions(+), 10 deletions(-)

diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index 258647fc6bddb..1320e06727df1 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -4774,7 +4774,7 @@ _base_display_ioc_capabilities(struct MPT3SAS_ADAPTER *ioc)
 	char desc[17] = {0};
 	u32 iounit_pg1_flags;
 
-	strscpy(desc, ioc->manu_pg0.ChipName, sizeof(desc));
+	memtostr(desc, ioc->manu_pg0.ChipName);
 	ioc_info(ioc, "%s: FWVersion(%02d.%02d.%02d.%02d), ChipRevision(0x%02x)\n",
 		 desc,
 		 (ioc->facts.FWVersion.Word & 0xFF000000) >> 24,
diff --git a/drivers/scsi/mpt3sas/mpt3sas_transport.c b/drivers/scsi/mpt3sas/mpt3sas_transport.c
index 76f9a91771985..d84413b77d849 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_transport.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_transport.c
@@ -458,17 +458,13 @@ _transport_expander_report_manufacture(struct MPT3SAS_ADAPTER *ioc,
 			goto out;
 
 		manufacture_reply = data_out + sizeof(struct rep_manu_request);
-		strscpy(edev->vendor_id, manufacture_reply->vendor_id,
-			sizeof(edev->vendor_id));
-		strscpy(edev->product_id, manufacture_reply->product_id,
-			sizeof(edev->product_id));
-		strscpy(edev->product_rev, manufacture_reply->product_rev,
-			sizeof(edev->product_rev));
+		memtostr(edev->vendor_id, manufacture_reply->vendor_id);
+		memtostr(edev->product_id, manufacture_reply->product_id);
+		memtostr(edev->product_rev, manufacture_reply->product_rev);
 		edev->level = manufacture_reply->sas_format & 1;
 		if (edev->level) {
-			strscpy(edev->component_vendor_id,
-				manufacture_reply->component_vendor_id,
-				sizeof(edev->component_vendor_id));
+			memtostr(edev->component_vendor_id,
+				 manufacture_reply->component_vendor_id);
 			tmp = (u8 *)&manufacture_reply->component_id;
 			edev->component_id = tmp[0] << 8 | tmp[1];
 			edev->component_revision_id =
-- 
GitLab


From 4e173c825b1914d5b118bbf26f0168102d56ae95 Mon Sep 17 00:00:00 2001
From: Kees Cook <kees@kernel.org>
Date: Fri, 31 May 2024 08:54:52 -0700
Subject: [PATCH 643/950] mailmap: update entry for Kees Cook

I'm tired of gmail breaking DKIM. Switch everything over to my
@kernel.org alias instead.

Signed-off-by: Kees Cook <kees@kernel.org>
---
 .mailmap | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/.mailmap b/.mailmap
index 43cd2995dbc29..efd9fa867a8ec 100644
--- a/.mailmap
+++ b/.mailmap
@@ -337,10 +337,11 @@ Kalyan Thota <quic_kalyant@quicinc.com> <kalyan_t@codeaurora.org>
 Karthikeyan Periyasamy <quic_periyasa@quicinc.com> <periyasa@codeaurora.org>
 Kathiravan T <quic_kathirav@quicinc.com> <kathirav@codeaurora.org>
 Kay Sievers <kay.sievers@vrfy.org>
-Kees Cook <keescook@chromium.org> <kees.cook@canonical.com>
-Kees Cook <keescook@chromium.org> <keescook@google.com>
-Kees Cook <keescook@chromium.org> <kees@outflux.net>
-Kees Cook <keescook@chromium.org> <kees@ubuntu.com>
+Kees Cook <kees@kernel.org> <kees.cook@canonical.com>
+Kees Cook <kees@kernel.org> <keescook@chromium.org>
+Kees Cook <kees@kernel.org> <keescook@google.com>
+Kees Cook <kees@kernel.org> <kees@outflux.net>
+Kees Cook <kees@kernel.org> <kees@ubuntu.com>
 Keith Busch <kbusch@kernel.org> <keith.busch@intel.com>
 Keith Busch <kbusch@kernel.org> <keith.busch@linux.intel.com>
 Kenneth W Chen <kenneth.w.chen@intel.com>
-- 
GitLab


From d551ce15d08114514d489fad63bd275de2aca862 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 28 May 2024 14:02:35 +0200
Subject: [PATCH 644/950] mailbox: zynqmp-ipi: drop irq_to_desc() call

irq_to_desc() is not exported to loadable modules, so this driver now
fails to link in some configurations:

ERROR: modpost: "irq_to_desc" [drivers/mailbox/zynqmp-ipi-mailbox.ko] undefined!

I can't see a purpose for this call, since the return value is unused
and probably left over from some code refactoring.

Address the link failure by just removing the line.

Fixes: 6ffb1635341b ("mailbox: zynqmp: handle SGI for shared IPI")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Tested-by: Tanmay Shah <tanmay.shah@amd.com>
Signed-off-by: Jassi Brar <jassisinghbrar@gmail.com>
---
 drivers/mailbox/zynqmp-ipi-mailbox.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/mailbox/zynqmp-ipi-mailbox.c b/drivers/mailbox/zynqmp-ipi-mailbox.c
index 7c90bac3de216..4acf5612487cf 100644
--- a/drivers/mailbox/zynqmp-ipi-mailbox.c
+++ b/drivers/mailbox/zynqmp-ipi-mailbox.c
@@ -850,7 +850,6 @@ static int xlnx_mbox_init_sgi(struct platform_device *pdev,
 		return ret;
 	}
 
-	irq_to_desc(pdata->virq_sgi);
 	irq_set_status_flags(pdata->virq_sgi, IRQ_PER_CPU);
 
 	/* Setup function for the CPU hot-plug cases */
-- 
GitLab


From 0c2f6d04619ec2b53ad4b0b591eafc9389786e86 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Thu, 30 May 2024 17:29:18 +0200
Subject: [PATCH 645/950] x86/topology/intel: Unlock CPUID before evaluating
 anything

Intel CPUs have a MSR bit to limit CPUID enumeration to leaf two. If
this bit is set by the BIOS then CPUID evaluation including topology
enumeration does not work correctly as the evaluation code does not try
to analyze any leaf greater than two.

This went unnoticed before because the original topology code just
repeated evaluation several times and managed to overwrite the initial
limited information with the correct one later. The new evaluation code
does it once and therefore ends up with the limited and wrong
information.

Cure this by unlocking CPUID right before evaluating anything which
depends on the maximum CPUID leaf being greater than two instead of
rereading stuff after unlock.

Fixes: 22d63660c35e ("x86/cpu: Use common topology code for Intel")
Reported-by: Peter Schneider <pschneider1968@googlemail.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Tested-by: Peter Schneider <pschneider1968@googlemail.com>
Cc: <stable@kernel.org>
Link: https://lore.kernel.org/r/fd3f73dc-a86f-4bcf-9c60-43556a21eb42@googlemail.com
---
 arch/x86/kernel/cpu/common.c |  3 ++-
 arch/x86/kernel/cpu/cpu.h    |  2 ++
 arch/x86/kernel/cpu/intel.c  | 25 ++++++++++++++++---------
 3 files changed, 20 insertions(+), 10 deletions(-)

diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index e31293c9609f5..d4e539d4e158c 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1589,6 +1589,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 	if (have_cpuid_p()) {
 		cpu_detect(c);
 		get_cpu_vendor(c);
+		intel_unlock_cpuid_leafs(c);
 		get_cpu_cap(c);
 		setup_force_cpu_cap(X86_FEATURE_CPUID);
 		get_cpu_address_sizes(c);
@@ -1748,7 +1749,7 @@ static void generic_identify(struct cpuinfo_x86 *c)
 	cpu_detect(c);
 
 	get_cpu_vendor(c);
-
+	intel_unlock_cpuid_leafs(c);
 	get_cpu_cap(c);
 
 	get_cpu_address_sizes(c);
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index ea9e07d57c8dd..1beccefbaff9a 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -61,9 +61,11 @@ extern __ro_after_init enum tsx_ctrl_states tsx_ctrl_state;
 
 extern void __init tsx_init(void);
 void tsx_ap_init(void);
+void intel_unlock_cpuid_leafs(struct cpuinfo_x86 *c);
 #else
 static inline void tsx_init(void) { }
 static inline void tsx_ap_init(void) { }
+static inline void intel_unlock_cpuid_leafs(struct cpuinfo_x86 *c) { }
 #endif /* CONFIG_CPU_SUP_INTEL */
 
 extern void init_spectral_chicken(struct cpuinfo_x86 *c);
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 3c3e7e5695ba4..fdf3489d92a49 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -269,19 +269,26 @@ detect_keyid_bits:
 	c->x86_phys_bits -= keyid_bits;
 }
 
+void intel_unlock_cpuid_leafs(struct cpuinfo_x86 *c)
+{
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+		return;
+
+	if (c->x86 < 6 || (c->x86 == 6 && c->x86_model < 0xd))
+		return;
+
+	/*
+	 * The BIOS can have limited CPUID to leaf 2, which breaks feature
+	 * enumeration. Unlock it and update the maximum leaf info.
+	 */
+	if (msr_clear_bit(MSR_IA32_MISC_ENABLE, MSR_IA32_MISC_ENABLE_LIMIT_CPUID_BIT) > 0)
+		c->cpuid_level = cpuid_eax(0);
+}
+
 static void early_init_intel(struct cpuinfo_x86 *c)
 {
 	u64 misc_enable;
 
-	/* Unmask CPUID levels if masked: */
-	if (c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xd)) {
-		if (msr_clear_bit(MSR_IA32_MISC_ENABLE,
-				  MSR_IA32_MISC_ENABLE_LIMIT_CPUID_BIT) > 0) {
-			c->cpuid_level = cpuid_eax(0);
-			get_cpu_cap(c);
-		}
-	}
-
 	if ((c->x86 == 0xf && c->x86_model >= 0x03) ||
 		(c->x86 == 0x6 && c->x86_model >= 0x0e))
 		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
-- 
GitLab


From 32c75ad4a79259609ee19f749832bc2d99bbdd13 Mon Sep 17 00:00:00 2001
From: John Hubbard <jhubbard@nvidia.com>
Date: Fri, 31 May 2024 13:07:53 -0700
Subject: [PATCH 646/950] selftests/futex: don't redefine .PHONY targets (all,
 clean)

The .PHONY targets "all" and "clean"  are both already defined in the
file that is included in the very next line:

    ../lib.mk.

Remove this duplicate code.

Reviewed-by: Davidlohr Bueso <dave@stgolabs.net>
Signed-off-by: John Hubbard <jhubbard@nvidia.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 tools/testing/selftests/futex/Makefile | 2 --
 1 file changed, 2 deletions(-)

diff --git a/tools/testing/selftests/futex/Makefile b/tools/testing/selftests/futex/Makefile
index 11e157d7533b8..78ab2cd111f60 100644
--- a/tools/testing/selftests/futex/Makefile
+++ b/tools/testing/selftests/futex/Makefile
@@ -3,8 +3,6 @@ SUBDIRS := functional
 
 TEST_PROGS := run.sh
 
-.PHONY: all clean
-
 include ../lib.mk
 
 all:
-- 
GitLab


From 4bf15b1c657d22d1d70173e43264e4606dfe75ff Mon Sep 17 00:00:00 2001
From: John Hubbard <jhubbard@nvidia.com>
Date: Fri, 31 May 2024 13:07:54 -0700
Subject: [PATCH 647/950] selftests/futex: don't pass a const char* to
 asprintf(3)

When building with clang, via:

    make LLVM=1 -C tools/testing/selftests

...clang issues this warning:

futex_requeue_pi.c:403:17: warning: passing 'const char **' to parameter
of type 'char **' discards qualifiers in nested pointer types
[-Wincompatible-pointer-types-discards-qualifiers]

This warning fires because test_name is passed into asprintf(3), which
then changes it.

Fix this by simply removing the const qualifier. This is a local
automatic variable in a very short function, so there is not much need
to use the compiler to enforce const-ness at this scope.

[1] https://lore.kernel.org/all/20240329-selftests-libmk-llvm-rfc-v1-1-2f9ed7d1c49f@valentinobst.de/

Fixes: f17d8a87ecb5 ("selftests: fuxex: Report a unique test name per run of futex_requeue_pi")
Reviewed-by: Davidlohr Bueso <dave@stgolabs.net>
Signed-off-by: John Hubbard <jhubbard@nvidia.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 tools/testing/selftests/futex/functional/futex_requeue_pi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/futex/functional/futex_requeue_pi.c b/tools/testing/selftests/futex/functional/futex_requeue_pi.c
index 7f3ca5c78df12..215c6cb539b4a 100644
--- a/tools/testing/selftests/futex/functional/futex_requeue_pi.c
+++ b/tools/testing/selftests/futex/functional/futex_requeue_pi.c
@@ -360,7 +360,7 @@ out:
 
 int main(int argc, char *argv[])
 {
-	const char *test_name;
+	char *test_name;
 	int c, ret;
 
 	while ((c = getopt(argc, argv, "bchlot:v:")) != -1) {
-- 
GitLab


From 99a6087dfdc65303d26ab5fba2dacd8931b82b08 Mon Sep 17 00:00:00 2001
From: Kees Cook <kees@kernel.org>
Date: Fri, 31 May 2024 11:57:07 -0700
Subject: [PATCH 648/950] kunit/fortify: Remove __kmalloc_node() test

__kmalloc_node() is considered an "internal" function to the Slab, so
drop it from explicit testing.

Link: https://lore.kernel.org/r/20240531185703.work.588-kees@kernel.org
Signed-off-by: Kees Cook <kees@kernel.org>
---
 lib/fortify_kunit.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/lib/fortify_kunit.c b/lib/fortify_kunit.c
index 39da5b3bc649c..f9cc467334ce3 100644
--- a/lib/fortify_kunit.c
+++ b/lib/fortify_kunit.c
@@ -235,9 +235,6 @@ static void fortify_test_alloc_size_##allocator##_dynamic(struct kunit *test) \
 		kmalloc_array_node(alloc_size, 1, gfp, NUMA_NO_NODE),	\
 		kfree(p));						\
 	checker(expected_size, __kmalloc(alloc_size, gfp),		\
-		kfree(p));						\
-	checker(expected_size,						\
-		__kmalloc_node(alloc_size, gfp, NUMA_NO_NODE),		\
 		kfree(p));						\
 									\
 	orig = kmalloc(alloc_size, gfp);				\
-- 
GitLab


From 62da3acd28955e7299babebdfcb14243b789e773 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Tue, 28 May 2024 15:32:18 -0700
Subject: [PATCH 649/950] selftests/bpf: fix inet_csk_accept prototype in
 test_sk_storage_tracing.c

Recent kernel change ([0]) changed inet_csk_accept() prototype. Adapt
progs/test_sk_storage_tracing.c to take that into account.

  [0] 92ef0fd55ac8 ("net: change proto and proto_ops accept type")

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20240528223218.3445297-1-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/progs/test_sk_storage_tracing.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/progs/test_sk_storage_tracing.c b/tools/testing/selftests/bpf/progs/test_sk_storage_tracing.c
index 02e718f06e0f5..40531e56776e4 100644
--- a/tools/testing/selftests/bpf/progs/test_sk_storage_tracing.c
+++ b/tools/testing/selftests/bpf/progs/test_sk_storage_tracing.c
@@ -84,7 +84,7 @@ int BPF_PROG(trace_tcp_connect, struct sock *sk)
 }
 
 SEC("fexit/inet_csk_accept")
-int BPF_PROG(inet_csk_accept, struct sock *sk, int flags, int *err, bool kern,
+int BPF_PROG(inet_csk_accept, struct sock *sk, struct proto_accept_arg *arg,
 	     struct sock *accepted_sk)
 {
 	set_task_info(accepted_sk);
-- 
GitLab


From aeb8fe0283d4d3b0f27a87c5f5c938e7324f7d8f Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Fri, 31 May 2024 21:45:00 +0200
Subject: [PATCH 650/950] bpf: Fix bpf_session_cookie BTF_ID in
 special_kfunc_set list

The bpf_session_cookie is unavailable for !CONFIG_FPROBE as reported
by Sebastian [1].

To fix that we remove CONFIG_FPROBE ifdef for session kfuncs, which
is fine, because there's filter for session programs.

Then based on bpf_trace.o dependency:
  obj-$(CONFIG_BPF_EVENTS) += bpf_trace.o

we add bpf_session_cookie BTF_ID in special_kfunc_set list dependency
on CONFIG_BPF_EVENTS.

[1] https://lore.kernel.org/bpf/20240531071557.MvfIqkn7@linutronix.de/T/#m71c6d5ec71db2967288cb79acedc15cc5dbfeec5
Reported-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Tested-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Suggested-by: Alexei Starovoitov <ast@kernel.org>
Fixes: 5c919acef8514 ("bpf: Add support for kprobe session cookie")
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20240531194500.2967187-1-jolsa@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/verifier.c    | 4 ++++
 kernel/trace/bpf_trace.c | 2 --
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 48f3a9acdef3d..36ef8e96787ed 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -11128,7 +11128,11 @@ BTF_ID(func, bpf_iter_css_task_new)
 #else
 BTF_ID_UNUSED
 #endif
+#ifdef CONFIG_BPF_EVENTS
 BTF_ID(func, bpf_session_cookie)
+#else
+BTF_ID_UNUSED
+#endif
 
 static bool is_kfunc_ret_null(struct bpf_kfunc_call_arg_meta *meta)
 {
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 6249dac617018..d1daeab1bbc14 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -3517,7 +3517,6 @@ static u64 bpf_uprobe_multi_entry_ip(struct bpf_run_ctx *ctx)
 }
 #endif /* CONFIG_UPROBES */
 
-#ifdef CONFIG_FPROBE
 __bpf_kfunc_start_defs();
 
 __bpf_kfunc bool bpf_session_is_return(void)
@@ -3566,4 +3565,3 @@ static int __init bpf_kprobe_multi_kfuncs_init(void)
 }
 
 late_initcall(bpf_kprobe_multi_kfuncs_init);
-#endif
-- 
GitLab


From 7d0b3953f6d832daec10a0d76e2d4db405768a8b Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Wed, 29 May 2024 16:12:12 -0700
Subject: [PATCH 651/950] libbpf: don't close(-1) in multi-uprobe feature
 detector

Guard close(link_fd) with extra link_fd >= 0 check to prevent close(-1).

Detected by Coverity static analysis.

Fixes: 04d939a2ab22 ("libbpf: detect broken PID filtering logic for multi-uprobe")
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20240529231212.768828-1-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/features.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/lib/bpf/features.c b/tools/lib/bpf/features.c
index 3df0125ed5fa7..50befe125ddc5 100644
--- a/tools/lib/bpf/features.c
+++ b/tools/lib/bpf/features.c
@@ -393,7 +393,8 @@ static int probe_uprobe_multi_link(int token_fd)
 	err = -errno; /* close() can clobber errno */
 
 	if (link_fd >= 0 || err != -EBADF) {
-		close(link_fd);
+		if (link_fd >= 0)
+			close(link_fd);
 		close(prog_fd);
 		return 0;
 	}
-- 
GitLab


From 531876c80004ecff7bfdbd8ba6c6b48835ef5e22 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Wed, 29 May 2024 15:32:39 -0700
Subject: [PATCH 652/950] libbpf: keep FD_CLOEXEC flag when dup()'ing FD

Make sure to preserve and/or enforce FD_CLOEXEC flag on duped FDs.
Use dup3() with O_CLOEXEC flag for that.

Without this fix libbpf effectively clears FD_CLOEXEC flag on each of BPF
map/prog FD, which is definitely not the right or expected behavior.

Reported-by: Lennart Poettering <lennart@poettering.net>
Fixes: bc308d011ab8 ("libbpf: call dup2() syscall directly")
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20240529223239.504241-1-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/libbpf_internal.h | 10 +++-------
 1 file changed, 3 insertions(+), 7 deletions(-)

diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index a0dcfb82e455d..7e7e686008c62 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -597,13 +597,9 @@ static inline int ensure_good_fd(int fd)
 	return fd;
 }
 
-static inline int sys_dup2(int oldfd, int newfd)
+static inline int sys_dup3(int oldfd, int newfd, int flags)
 {
-#ifdef __NR_dup2
-	return syscall(__NR_dup2, oldfd, newfd);
-#else
-	return syscall(__NR_dup3, oldfd, newfd, 0);
-#endif
+	return syscall(__NR_dup3, oldfd, newfd, flags);
 }
 
 /* Point *fixed_fd* to the same file that *tmp_fd* points to.
@@ -614,7 +610,7 @@ static inline int reuse_fd(int fixed_fd, int tmp_fd)
 {
 	int err;
 
-	err = sys_dup2(tmp_fd, fixed_fd);
+	err = sys_dup3(tmp_fd, fixed_fd, O_CLOEXEC);
 	err = err < 0 ? -errno : 0;
 	close(tmp_fd); /* clean up temporary FD */
 	return err;
-- 
GitLab


From 7bc4244c882a7d7d79f4afefc50893244eb11d07 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Sat, 1 Jun 2024 07:28:21 +0200
Subject: [PATCH 653/950] Revert "VT: Use macros to define ioctls"

This reverts commit 8c467f3300591a206fa8dcc6988d768910799872.

Turns out this breaks many architectures as the vt ioctls do not all
match up everywhere due to historical reasons, so the original commit is
invalid for many values.

Reported-by: Nick Bowler <nbowler@draconx.ca>
Reported-by: Arnd Bergmann <arnd@kernel.org>
Reported-by: Jiri Slaby <jirislaby@kernel.org>
Reported-by: Christian Zigotzky <chzigotzky@xenosoft.de>
Reported-by: Michael Ellerman <mpe@ellerman.id.au>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Alexey Gladkov <legion@kernel.org>
Link: https://lore.kernel.org/r/ad4e561c-1d49-4f25-882c-7a36c6b1b5c0@draconx.ca
Link: https://lore.kernel.org/r/0da9785e-ba44-4718-9d08-4e96c1ba7ab2@kernel.org
Link: https://lore.kernel.org/all/34d848f4-670b-4493-bf21-130ef862521b@xenosoft.de/
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/uapi/linux/kd.h | 96 ++++++++++++++++++++---------------------
 1 file changed, 47 insertions(+), 49 deletions(-)

diff --git a/include/uapi/linux/kd.h b/include/uapi/linux/kd.h
index 8ddb2219a84bd..6b384065c0135 100644
--- a/include/uapi/linux/kd.h
+++ b/include/uapi/linux/kd.h
@@ -5,61 +5,60 @@
 #include <linux/compiler.h>
 
 /* 0x4B is 'K', to avoid collision with termios and vt */
-#define KD_IOCTL_BASE	'K'
 
-#define GIO_FONT	_IO(KD_IOCTL_BASE, 0x60)	/* gets font in expanded form */
-#define PIO_FONT	_IO(KD_IOCTL_BASE, 0x61)	/* use font in expanded form */
+#define GIO_FONT	0x4B60	/* gets font in expanded form */
+#define PIO_FONT	0x4B61	/* use font in expanded form */
 
-#define GIO_FONTX	_IO(KD_IOCTL_BASE, 0x6B)	/* get font using struct consolefontdesc */
-#define PIO_FONTX	_IO(KD_IOCTL_BASE, 0x6C)	/* set font using struct consolefontdesc */
+#define GIO_FONTX	0x4B6B	/* get font using struct consolefontdesc */
+#define PIO_FONTX	0x4B6C	/* set font using struct consolefontdesc */
 struct consolefontdesc {
 	unsigned short charcount;	/* characters in font (256 or 512) */
 	unsigned short charheight;	/* scan lines per character (1-32) */
 	char __user *chardata;		/* font data in expanded form */
 };
 
-#define PIO_FONTRESET	_IO(KD_IOCTL_BASE, 0x6D)	/* reset to default font */
+#define PIO_FONTRESET   0x4B6D	/* reset to default font */
 
-#define GIO_CMAP	_IO(KD_IOCTL_BASE, 0x70)	/* gets colour palette on VGA+ */
-#define PIO_CMAP	_IO(KD_IOCTL_BASE, 0x71)	/* sets colour palette on VGA+ */
+#define GIO_CMAP	0x4B70	/* gets colour palette on VGA+ */
+#define PIO_CMAP	0x4B71	/* sets colour palette on VGA+ */
 
-#define KIOCSOUND	_IO(KD_IOCTL_BASE, 0x2F)	/* start sound generation (0 for off) */
-#define KDMKTONE	_IO(KD_IOCTL_BASE, 0x30)	/* generate tone */
+#define KIOCSOUND	0x4B2F	/* start sound generation (0 for off) */
+#define KDMKTONE	0x4B30	/* generate tone */
 
-#define KDGETLED	_IO(KD_IOCTL_BASE, 0x31)	/* return current led state */
-#define KDSETLED	_IO(KD_IOCTL_BASE, 0x32)	/* set led state [lights, not flags] */
+#define KDGETLED	0x4B31	/* return current led state */
+#define KDSETLED	0x4B32	/* set led state [lights, not flags] */
 #define 	LED_SCR		0x01	/* scroll lock led */
 #define 	LED_NUM		0x02	/* num lock led */
 #define 	LED_CAP		0x04	/* caps lock led */
 
-#define KDGKBTYPE	_IO(KD_IOCTL_BASE, 0x33)	/* get keyboard type */
+#define KDGKBTYPE	0x4B33	/* get keyboard type */
 #define 	KB_84		0x01
 #define 	KB_101		0x02 	/* this is what we always answer */
 #define 	KB_OTHER	0x03
 
-#define KDADDIO		_IO(KD_IOCTL_BASE, 0x34)	/* add i/o port as valid */
-#define KDDELIO		_IO(KD_IOCTL_BASE, 0x35)	/* del i/o port as valid */
-#define KDENABIO	_IO(KD_IOCTL_BASE, 0x36)	/* enable i/o to video board */
-#define KDDISABIO	_IO(KD_IOCTL_BASE, 0x37)	/* disable i/o to video board */
+#define KDADDIO		0x4B34	/* add i/o port as valid */
+#define KDDELIO		0x4B35	/* del i/o port as valid */
+#define KDENABIO	0x4B36	/* enable i/o to video board */
+#define KDDISABIO	0x4B37	/* disable i/o to video board */
 
-#define KDSETMODE	_IO(KD_IOCTL_BASE, 0x3A)	/* set text/graphics mode */
+#define KDSETMODE	0x4B3A	/* set text/graphics mode */
 #define		KD_TEXT		0x00
 #define		KD_GRAPHICS	0x01
 #define		KD_TEXT0	0x02	/* obsolete */
 #define		KD_TEXT1	0x03	/* obsolete */
-#define KDGETMODE	_IO(KD_IOCTL_BASE, 0x3B)	/* get current mode */
+#define KDGETMODE	0x4B3B	/* get current mode */
 
-#define KDMAPDISP	_IO(KD_IOCTL_BASE, 0x3C)	/* map display into address space */
-#define KDUNMAPDISP	_IO(KD_IOCTL_BASE, 0x3D)	/* unmap display from address space */
+#define KDMAPDISP	0x4B3C	/* map display into address space */
+#define KDUNMAPDISP	0x4B3D	/* unmap display from address space */
 
 typedef char scrnmap_t;
 #define		E_TABSZ		256
-#define GIO_SCRNMAP	_IO(KD_IOCTL_BASE, 0x40)	/* get screen mapping from kernel */
-#define PIO_SCRNMAP	_IO(KD_IOCTL_BASE, 0x41)	/* put screen mapping table in kernel */
-#define GIO_UNISCRNMAP	_IO(KD_IOCTL_BASE, 0x69)	/* get full Unicode screen mapping */
-#define PIO_UNISCRNMAP	_IO(KD_IOCTL_BASE, 0x6A)	/* set full Unicode screen mapping */
+#define GIO_SCRNMAP	0x4B40	/* get screen mapping from kernel */
+#define PIO_SCRNMAP	0x4B41	/* put screen mapping table in kernel */
+#define GIO_UNISCRNMAP  0x4B69	/* get full Unicode screen mapping */
+#define PIO_UNISCRNMAP  0x4B6A  /* set full Unicode screen mapping */
 
-#define GIO_UNIMAP	_IO(KD_IOCTL_BASE, 0x66)	/* get unicode-to-font mapping from kernel */
+#define GIO_UNIMAP	0x4B66	/* get unicode-to-font mapping from kernel */
 struct unipair {
 	unsigned short unicode;
 	unsigned short fontpos;
@@ -68,8 +67,8 @@ struct unimapdesc {
 	unsigned short entry_ct;
 	struct unipair __user *entries;
 };
-#define PIO_UNIMAP	_IO(KD_IOCTL_BASE, 0x67)	/* put unicode-to-font mapping in kernel */
-#define PIO_UNIMAPCLR	_IO(KD_IOCTL_BASE, 0x68)	/* clear table, possibly advise hash algorithm */
+#define PIO_UNIMAP	0x4B67	/* put unicode-to-font mapping in kernel */
+#define PIO_UNIMAPCLR	0x4B68	/* clear table, possibly advise hash algorithm */
 struct unimapinit {
 	unsigned short advised_hashsize;  /* 0 if no opinion */
 	unsigned short advised_hashstep;  /* 0 if no opinion */
@@ -84,19 +83,19 @@ struct unimapinit {
 #define		K_MEDIUMRAW	0x02
 #define		K_UNICODE	0x03
 #define		K_OFF		0x04
-#define KDGKBMODE	_IO(KD_IOCTL_BASE, 0x44)	/* gets current keyboard mode */
-#define KDSKBMODE	_IO(KD_IOCTL_BASE, 0x45)	/* sets current keyboard mode */
+#define KDGKBMODE	0x4B44	/* gets current keyboard mode */
+#define KDSKBMODE	0x4B45	/* sets current keyboard mode */
 
 #define		K_METABIT	0x03
 #define		K_ESCPREFIX	0x04
-#define KDGKBMETA	_IO(KD_IOCTL_BASE, 0x62)	/* gets meta key handling mode */
-#define KDSKBMETA	_IO(KD_IOCTL_BASE, 0x63)	/* sets meta key handling mode */
+#define KDGKBMETA	0x4B62	/* gets meta key handling mode */
+#define KDSKBMETA	0x4B63	/* sets meta key handling mode */
 
 #define		K_SCROLLLOCK	0x01
 #define		K_NUMLOCK	0x02
 #define		K_CAPSLOCK	0x04
-#define	KDGKBLED	_IO(KD_IOCTL_BASE, 0x64)	/* get led flags (not lights) */
-#define	KDSKBLED	_IO(KD_IOCTL_BASE, 0x65)	/* set led flags (not lights) */
+#define	KDGKBLED	0x4B64	/* get led flags (not lights) */
+#define	KDSKBLED	0x4B65	/* set led flags (not lights) */
 
 struct kbentry {
 	unsigned char kb_table;
@@ -108,15 +107,15 @@ struct kbentry {
 #define		K_ALTTAB	0x02
 #define		K_ALTSHIFTTAB	0x03
 
-#define KDGKBENT	_IO(KD_IOCTL_BASE, 0x46)	/* gets one entry in translation table */
-#define KDSKBENT	_IO(KD_IOCTL_BASE, 0x47)	/* sets one entry in translation table */
+#define KDGKBENT	0x4B46	/* gets one entry in translation table */
+#define KDSKBENT	0x4B47	/* sets one entry in translation table */
 
 struct kbsentry {
 	unsigned char kb_func;
 	unsigned char kb_string[512];
 };
-#define KDGKBSENT	_IO(KD_IOCTL_BASE, 0x48)	/* gets one function key string entry */
-#define KDSKBSENT	_IO(KD_IOCTL_BASE, 0x49)	/* sets one function key string entry */
+#define KDGKBSENT	0x4B48	/* gets one function key string entry */
+#define KDSKBSENT	0x4B49	/* sets one function key string entry */
 
 struct kbdiacr {
         unsigned char diacr, base, result;
@@ -125,8 +124,8 @@ struct kbdiacrs {
         unsigned int kb_cnt;    /* number of entries in following array */
 	struct kbdiacr kbdiacr[256];    /* MAX_DIACR from keyboard.h */
 };
-#define KDGKBDIACR	_IO(KD_IOCTL_BASE, 0x4A)  /* read kernel accent table */
-#define KDSKBDIACR	_IO(KD_IOCTL_BASE, 0x4B)  /* write kernel accent table */
+#define KDGKBDIACR      0x4B4A  /* read kernel accent table */
+#define KDSKBDIACR      0x4B4B  /* write kernel accent table */
 
 struct kbdiacruc {
 	unsigned int diacr, base, result;
@@ -135,16 +134,16 @@ struct kbdiacrsuc {
         unsigned int kb_cnt;    /* number of entries in following array */
 	struct kbdiacruc kbdiacruc[256];    /* MAX_DIACR from keyboard.h */
 };
-#define KDGKBDIACRUC	_IO(KD_IOCTL_BASE, 0xFA)  /* read kernel accent table - UCS */
-#define KDSKBDIACRUC	_IO(KD_IOCTL_BASE, 0xFB)  /* write kernel accent table - UCS */
+#define KDGKBDIACRUC    0x4BFA  /* read kernel accent table - UCS */
+#define KDSKBDIACRUC    0x4BFB  /* write kernel accent table - UCS */
 
 struct kbkeycode {
 	unsigned int scancode, keycode;
 };
-#define KDGETKEYCODE	_IO(KD_IOCTL_BASE, 0x4C)	/* read kernel keycode table entry */
-#define KDSETKEYCODE	_IO(KD_IOCTL_BASE, 0x4D)	/* write kernel keycode table entry */
+#define KDGETKEYCODE	0x4B4C	/* read kernel keycode table entry */
+#define KDSETKEYCODE	0x4B4D	/* write kernel keycode table entry */
 
-#define KDSIGACCEPT	_IO(KD_IOCTL_BASE, 0x4E)	/* accept kbd generated signals */
+#define KDSIGACCEPT	0x4B4E	/* accept kbd generated signals */
 
 struct kbd_repeat {
 	int delay;	/* in msec; <= 0: don't change */
@@ -152,11 +151,10 @@ struct kbd_repeat {
 			/* earlier this field was misnamed "rate" */
 };
 
-#define KDKBDREP	_IO(KD_IOCTL_BASE, 0x52)	/* set keyboard delay/repeat rate;
-							 * actually used values are returned
-							 */
+#define KDKBDREP        0x4B52  /* set keyboard delay/repeat rate;
+				 * actually used values are returned */
 
-#define KDFONTOP	_IO(KD_IOCTL_BASE, 0x72)	/* font operations */
+#define KDFONTOP	0x4B72	/* font operations */
 
 struct console_font_op {
 	unsigned int op;	/* operation code KD_FONT_OP_* */
-- 
GitLab


From ebfb5e8fc8b45040b979f4bf0012a01d0abac8d4 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Alexis=20Lothor=C3=A9?= <alexis.lothore@bootlin.com>
Date: Tue, 28 May 2024 16:20:28 +0200
Subject: [PATCH 654/950] Revert "wifi: wilc1000: convert list management to
 RCU"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This reverts commit f236464f1db7bea80075e6e31ac70dc6eb80547f

Commit f236464f1db7 ("wifi: wilc1000: convert list management to RCU")
replaced SRCU with RCU, aiming to simplify RCU usage in the driver. No
documentation or commit history hinted about why SRCU has been preferred
in original design, so it has been assumed to be safe to do this
conversion.
Unfortunately, some static analyzers raised warnings, confirmed by runtime
checker, not long after the merge. At least three different issues arose
when switching to RCU:
- wilc_wlan_txq_filter_dup_tcp_ack is executed in a RCU read critical
  section yet calls wait_for_completion_timeout
- wilc_wfi_init_mon_interface calls kmalloc and register_netdevice while
  manipulating a vif retrieved from vif list
- set_channel sends command to chip (and so, also waits for a completion)
  while holding a vif retrieved from vif list (so, in RCU read critical
  section)

Some of those issues are not trivial to fix and would need bigger driver
rework. Fix those issues by reverting the SRCU to RCU conversion commit

Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Closes: https://lore.kernel.org/linux-wireless/3b46ec7c-baee-49fd-b760-3bc12fb12eaf@moroto.mountain/
Fixes: f236464f1db7 ("wifi: wilc1000: convert list management to RCU")
Signed-off-by: Alexis Lothoré <alexis.lothore@bootlin.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://msgid.link/20240528-wilc_revert_srcu_to_rcu-v1-1-bce096e0798c@bootlin.com
---
 .../wireless/microchip/wilc1000/cfg80211.c    | 41 ++++++++++--------
 drivers/net/wireless/microchip/wilc1000/hif.c | 15 ++++---
 .../net/wireless/microchip/wilc1000/netdev.c  | 43 +++++++++++--------
 .../net/wireless/microchip/wilc1000/netdev.h  |  5 ++-
 .../net/wireless/microchip/wilc1000/wlan.c    |  5 ++-
 5 files changed, 64 insertions(+), 45 deletions(-)

diff --git a/drivers/net/wireless/microchip/wilc1000/cfg80211.c b/drivers/net/wireless/microchip/wilc1000/cfg80211.c
index 7d9fb9f2d5279..089102ed9ae51 100644
--- a/drivers/net/wireless/microchip/wilc1000/cfg80211.c
+++ b/drivers/net/wireless/microchip/wilc1000/cfg80211.c
@@ -237,11 +237,12 @@ static int set_channel(struct wiphy *wiphy,
 	struct wilc_vif *vif;
 	u32 channelnum;
 	int result;
+	int srcu_idx;
 
-	rcu_read_lock();
+	srcu_idx = srcu_read_lock(&wl->srcu);
 	vif = wilc_get_wl_to_vif(wl);
 	if (IS_ERR(vif)) {
-		rcu_read_unlock();
+		srcu_read_unlock(&wl->srcu, srcu_idx);
 		return PTR_ERR(vif);
 	}
 
@@ -252,7 +253,7 @@ static int set_channel(struct wiphy *wiphy,
 	if (result)
 		netdev_err(vif->ndev, "Error in setting channel\n");
 
-	rcu_read_unlock();
+	srcu_read_unlock(&wl->srcu, srcu_idx);
 	return result;
 }
 
@@ -805,8 +806,9 @@ static int set_wiphy_params(struct wiphy *wiphy, u32 changed)
 	struct wilc *wl = wiphy_priv(wiphy);
 	struct wilc_vif *vif;
 	struct wilc_priv *priv;
+	int srcu_idx;
 
-	rcu_read_lock();
+	srcu_idx = srcu_read_lock(&wl->srcu);
 	vif = wilc_get_wl_to_vif(wl);
 	if (IS_ERR(vif))
 		goto out;
@@ -861,7 +863,7 @@ static int set_wiphy_params(struct wiphy *wiphy, u32 changed)
 		netdev_err(priv->dev, "Error in setting WIPHY PARAMS\n");
 
 out:
-	rcu_read_unlock();
+	srcu_read_unlock(&wl->srcu, srcu_idx);
 	return ret;
 }
 
@@ -1537,19 +1539,20 @@ static struct wireless_dev *add_virtual_intf(struct wiphy *wiphy,
 
 	if (type == NL80211_IFTYPE_MONITOR) {
 		struct net_device *ndev;
+		int srcu_idx;
 
-		rcu_read_lock();
+		srcu_idx = srcu_read_lock(&wl->srcu);
 		vif = wilc_get_vif_from_type(wl, WILC_AP_MODE);
 		if (!vif) {
 			vif = wilc_get_vif_from_type(wl, WILC_GO_MODE);
 			if (!vif) {
-				rcu_read_unlock();
+				srcu_read_unlock(&wl->srcu, srcu_idx);
 				goto validate_interface;
 			}
 		}
 
 		if (vif->monitor_flag) {
-			rcu_read_unlock();
+			srcu_read_unlock(&wl->srcu, srcu_idx);
 			goto validate_interface;
 		}
 
@@ -1557,12 +1560,12 @@ static struct wireless_dev *add_virtual_intf(struct wiphy *wiphy,
 		if (ndev) {
 			vif->monitor_flag = 1;
 		} else {
-			rcu_read_unlock();
+			srcu_read_unlock(&wl->srcu, srcu_idx);
 			return ERR_PTR(-EINVAL);
 		}
 
 		wdev = &vif->priv.wdev;
-		rcu_read_unlock();
+		srcu_read_unlock(&wl->srcu, srcu_idx);
 		return wdev;
 	}
 
@@ -1610,7 +1613,7 @@ static int del_virtual_intf(struct wiphy *wiphy, struct wireless_dev *wdev)
 	list_del_rcu(&vif->list);
 	wl->vif_num--;
 	mutex_unlock(&wl->vif_mutex);
-	synchronize_rcu();
+	synchronize_srcu(&wl->srcu);
 	return 0;
 }
 
@@ -1635,23 +1638,25 @@ static void wilc_set_wakeup(struct wiphy *wiphy, bool enabled)
 {
 	struct wilc *wl = wiphy_priv(wiphy);
 	struct wilc_vif *vif;
+	int srcu_idx;
 
-	rcu_read_lock();
+	srcu_idx = srcu_read_lock(&wl->srcu);
 	vif = wilc_get_wl_to_vif(wl);
 	if (IS_ERR(vif)) {
-		rcu_read_unlock();
+		srcu_read_unlock(&wl->srcu, srcu_idx);
 		return;
 	}
 
 	netdev_info(vif->ndev, "cfg set wake up = %d\n", enabled);
 	wilc_set_wowlan_trigger(vif, enabled);
-	rcu_read_unlock();
+	srcu_read_unlock(&wl->srcu, srcu_idx);
 }
 
 static int set_tx_power(struct wiphy *wiphy, struct wireless_dev *wdev,
 			enum nl80211_tx_power_setting type, int mbm)
 {
 	int ret;
+	int srcu_idx;
 	s32 tx_power = MBM_TO_DBM(mbm);
 	struct wilc *wl = wiphy_priv(wiphy);
 	struct wilc_vif *vif;
@@ -1659,10 +1664,10 @@ static int set_tx_power(struct wiphy *wiphy, struct wireless_dev *wdev,
 	if (!wl->initialized)
 		return -EIO;
 
-	rcu_read_lock();
+	srcu_idx = srcu_read_lock(&wl->srcu);
 	vif = wilc_get_wl_to_vif(wl);
 	if (IS_ERR(vif)) {
-		rcu_read_unlock();
+		srcu_read_unlock(&wl->srcu, srcu_idx);
 		return -EINVAL;
 	}
 
@@ -1674,7 +1679,7 @@ static int set_tx_power(struct wiphy *wiphy, struct wireless_dev *wdev,
 	ret = wilc_set_tx_power(vif, tx_power);
 	if (ret)
 		netdev_err(vif->ndev, "Failed to set tx power\n");
-	rcu_read_unlock();
+	srcu_read_unlock(&wl->srcu, srcu_idx);
 
 	return ret;
 }
@@ -1757,6 +1762,7 @@ static void wlan_init_locks(struct wilc *wl)
 	init_completion(&wl->cfg_event);
 	init_completion(&wl->sync_event);
 	init_completion(&wl->txq_thread_started);
+	init_srcu_struct(&wl->srcu);
 }
 
 void wlan_deinit_locks(struct wilc *wilc)
@@ -1767,6 +1773,7 @@ void wlan_deinit_locks(struct wilc *wilc)
 	mutex_destroy(&wilc->txq_add_to_head_cs);
 	mutex_destroy(&wilc->vif_mutex);
 	mutex_destroy(&wilc->deinit_lock);
+	cleanup_srcu_struct(&wilc->srcu);
 }
 
 int wilc_cfg80211_init(struct wilc **wilc, struct device *dev, int io_type,
diff --git a/drivers/net/wireless/microchip/wilc1000/hif.c b/drivers/net/wireless/microchip/wilc1000/hif.c
index 919de6ffb8217..3925ca653e807 100644
--- a/drivers/net/wireless/microchip/wilc1000/hif.c
+++ b/drivers/net/wireless/microchip/wilc1000/hif.c
@@ -1570,11 +1570,12 @@ void wilc_network_info_received(struct wilc *wilc, u8 *buffer, u32 length)
 	struct host_if_drv *hif_drv;
 	struct host_if_msg *msg;
 	struct wilc_vif *vif;
+	int srcu_idx;
 	int result;
 	int id;
 
 	id = get_unaligned_le32(&buffer[length - 4]);
-	rcu_read_lock();
+	srcu_idx = srcu_read_lock(&wilc->srcu);
 	vif = wilc_get_vif_from_idx(wilc, id);
 	if (!vif)
 		goto out;
@@ -1606,7 +1607,7 @@ void wilc_network_info_received(struct wilc *wilc, u8 *buffer, u32 length)
 		kfree(msg);
 	}
 out:
-	rcu_read_unlock();
+	srcu_read_unlock(&wilc->srcu, srcu_idx);
 }
 
 void wilc_gnrl_async_info_received(struct wilc *wilc, u8 *buffer, u32 length)
@@ -1614,13 +1615,14 @@ void wilc_gnrl_async_info_received(struct wilc *wilc, u8 *buffer, u32 length)
 	struct host_if_drv *hif_drv;
 	struct host_if_msg *msg;
 	struct wilc_vif *vif;
+	int srcu_idx;
 	int result;
 	int id;
 
 	mutex_lock(&wilc->deinit_lock);
 
 	id = get_unaligned_le32(&buffer[length - 4]);
-	rcu_read_lock();
+	srcu_idx = srcu_read_lock(&wilc->srcu);
 	vif = wilc_get_vif_from_idx(wilc, id);
 	if (!vif)
 		goto out;
@@ -1647,7 +1649,7 @@ void wilc_gnrl_async_info_received(struct wilc *wilc, u8 *buffer, u32 length)
 		kfree(msg);
 	}
 out:
-	rcu_read_unlock();
+	srcu_read_unlock(&wilc->srcu, srcu_idx);
 	mutex_unlock(&wilc->deinit_lock);
 }
 
@@ -1655,11 +1657,12 @@ void wilc_scan_complete_received(struct wilc *wilc, u8 *buffer, u32 length)
 {
 	struct host_if_drv *hif_drv;
 	struct wilc_vif *vif;
+	int srcu_idx;
 	int result;
 	int id;
 
 	id = get_unaligned_le32(&buffer[length - 4]);
-	rcu_read_lock();
+	srcu_idx = srcu_read_lock(&wilc->srcu);
 	vif = wilc_get_vif_from_idx(wilc, id);
 	if (!vif)
 		goto out;
@@ -1684,7 +1687,7 @@ void wilc_scan_complete_received(struct wilc *wilc, u8 *buffer, u32 length)
 		}
 	}
 out:
-	rcu_read_unlock();
+	srcu_read_unlock(&wilc->srcu, srcu_idx);
 }
 
 int wilc_remain_on_channel(struct wilc_vif *vif, u64 cookie, u16 chan,
diff --git a/drivers/net/wireless/microchip/wilc1000/netdev.c b/drivers/net/wireless/microchip/wilc1000/netdev.c
index 73f56f7b002bf..710e29bea5605 100644
--- a/drivers/net/wireless/microchip/wilc1000/netdev.c
+++ b/drivers/net/wireless/microchip/wilc1000/netdev.c
@@ -127,28 +127,30 @@ void wilc_wlan_set_bssid(struct net_device *wilc_netdev, const u8 *bssid,
 
 int wilc_wlan_get_num_conn_ifcs(struct wilc *wilc)
 {
+	int srcu_idx;
 	u8 ret_val = 0;
 	struct wilc_vif *vif;
 
-	rcu_read_lock();
+	srcu_idx = srcu_read_lock(&wilc->srcu);
 	wilc_for_each_vif(wilc, vif) {
 		if (!is_zero_ether_addr(vif->bssid))
 			ret_val++;
 	}
-	rcu_read_unlock();
+	srcu_read_unlock(&wilc->srcu, srcu_idx);
 	return ret_val;
 }
 
 static void wilc_wake_tx_queues(struct wilc *wl)
 {
+	int srcu_idx;
 	struct wilc_vif *ifc;
 
-	rcu_read_lock();
+	srcu_idx = srcu_read_lock(&wl->srcu);
 	wilc_for_each_vif(wl, ifc) {
 		if (ifc->mac_opened && netif_queue_stopped(ifc->ndev))
 			netif_wake_queue(ifc->ndev);
 	}
-	rcu_read_unlock();
+	srcu_read_unlock(&wl->srcu, srcu_idx);
 }
 
 static int wilc_txq_task(void *vp)
@@ -653,6 +655,7 @@ static int wilc_set_mac_addr(struct net_device *dev, void *p)
 	struct sockaddr *addr = (struct sockaddr *)p;
 	unsigned char mac_addr[ETH_ALEN];
 	struct wilc_vif *tmp_vif;
+	int srcu_idx;
 
 	if (!is_valid_ether_addr(addr->sa_data))
 		return -EADDRNOTAVAIL;
@@ -664,19 +667,19 @@ static int wilc_set_mac_addr(struct net_device *dev, void *p)
 
 	/* Verify MAC Address is not already in use: */
 
-	rcu_read_lock();
+	srcu_idx = srcu_read_lock(&wilc->srcu);
 	wilc_for_each_vif(wilc, tmp_vif) {
 		wilc_get_mac_address(tmp_vif, mac_addr);
 		if (ether_addr_equal(addr->sa_data, mac_addr)) {
 			if (vif != tmp_vif) {
-				rcu_read_unlock();
+				srcu_read_unlock(&wilc->srcu, srcu_idx);
 				return -EADDRNOTAVAIL;
 			}
-			rcu_read_unlock();
+			srcu_read_unlock(&wilc->srcu, srcu_idx);
 			return 0;
 		}
 	}
-	rcu_read_unlock();
+	srcu_read_unlock(&wilc->srcu, srcu_idx);
 
 	result = wilc_set_mac_address(vif, (u8 *)addr->sa_data);
 	if (result)
@@ -764,14 +767,15 @@ netdev_tx_t wilc_mac_xmit(struct sk_buff *skb, struct net_device *ndev)
 						wilc_tx_complete);
 
 	if (queue_count > FLOW_CONTROL_UPPER_THRESHOLD) {
+		int srcu_idx;
 		struct wilc_vif *vif;
 
-		rcu_read_lock();
+		srcu_idx = srcu_read_lock(&wilc->srcu);
 		wilc_for_each_vif(wilc, vif) {
 			if (vif->mac_opened)
 				netif_stop_queue(vif->ndev);
 		}
-		rcu_read_unlock();
+		srcu_read_unlock(&wilc->srcu, srcu_idx);
 	}
 
 	return NETDEV_TX_OK;
@@ -815,12 +819,13 @@ void wilc_frmw_to_host(struct wilc *wilc, u8 *buff, u32 size,
 	unsigned int frame_len = 0;
 	struct wilc_vif *vif;
 	struct sk_buff *skb;
+	int srcu_idx;
 	int stats;
 
 	if (!wilc)
 		return;
 
-	rcu_read_lock();
+	srcu_idx = srcu_read_lock(&wilc->srcu);
 	wilc_netdev = get_if_handler(wilc, buff);
 	if (!wilc_netdev)
 		goto out;
@@ -848,14 +853,15 @@ void wilc_frmw_to_host(struct wilc *wilc, u8 *buff, u32 size,
 		netdev_dbg(wilc_netdev, "netif_rx ret value is: %d\n", stats);
 	}
 out:
-	rcu_read_unlock();
+	srcu_read_unlock(&wilc->srcu, srcu_idx);
 }
 
 void wilc_wfi_mgmt_rx(struct wilc *wilc, u8 *buff, u32 size, bool is_auth)
 {
+	int srcu_idx;
 	struct wilc_vif *vif;
 
-	rcu_read_lock();
+	srcu_idx = srcu_read_lock(&wilc->srcu);
 	wilc_for_each_vif(wilc, vif) {
 		struct ieee80211_mgmt *mgmt = (struct ieee80211_mgmt *)buff;
 		u16 type = le16_to_cpup((__le16 *)buff);
@@ -876,7 +882,7 @@ void wilc_wfi_mgmt_rx(struct wilc *wilc, u8 *buff, u32 size, bool is_auth)
 		if (vif->monitor_flag)
 			wilc_wfi_monitor_rx(wilc->monitor_dev, buff, size);
 	}
-	rcu_read_unlock();
+	srcu_read_unlock(&wilc->srcu, srcu_idx);
 }
 
 static const struct net_device_ops wilc_netdev_ops = {
@@ -906,7 +912,7 @@ void wilc_netdev_cleanup(struct wilc *wilc)
 		list_del_rcu(&vif->list);
 		wilc->vif_num--;
 		mutex_unlock(&wilc->vif_mutex);
-		synchronize_rcu();
+		synchronize_srcu(&wilc->srcu);
 		if (vif->ndev)
 			unregister_netdev(vif->ndev);
 	}
@@ -925,15 +931,16 @@ static u8 wilc_get_available_idx(struct wilc *wl)
 {
 	int idx = 0;
 	struct wilc_vif *vif;
+	int srcu_idx;
 
-	rcu_read_lock();
+	srcu_idx = srcu_read_lock(&wl->srcu);
 	wilc_for_each_vif(wl, vif) {
 		if (vif->idx == 0)
 			idx = 1;
 		else
 			idx = 0;
 	}
-	rcu_read_unlock();
+	srcu_read_unlock(&wl->srcu, srcu_idx);
 	return idx;
 }
 
@@ -983,7 +990,7 @@ struct wilc_vif *wilc_netdev_ifc_init(struct wilc *wl, const char *name,
 	list_add_tail_rcu(&vif->list, &wl->vif_list);
 	wl->vif_num += 1;
 	mutex_unlock(&wl->vif_mutex);
-	synchronize_rcu();
+	synchronize_srcu(&wl->srcu);
 
 	return vif;
 
diff --git a/drivers/net/wireless/microchip/wilc1000/netdev.h b/drivers/net/wireless/microchip/wilc1000/netdev.h
index eecee3973d6a4..5937d6d45695f 100644
--- a/drivers/net/wireless/microchip/wilc1000/netdev.h
+++ b/drivers/net/wireless/microchip/wilc1000/netdev.h
@@ -32,8 +32,8 @@
 
 #define wilc_for_each_vif(w, v) \
 	struct wilc *_w = w; \
-	list_for_each_entry_rcu(v, &_w->vif_list, list, \
-				 rcu_read_lock_held())
+	list_for_each_entry_srcu(v, &_w->vif_list, list, \
+				 srcu_read_lock_held(&_w->srcu))
 
 struct wilc_wfi_stats {
 	unsigned long rx_packets;
@@ -220,6 +220,7 @@ struct wilc {
 
 	/* protect vif list */
 	struct mutex vif_mutex;
+	struct srcu_struct srcu;
 	u8 open_ifcs;
 
 	/* protect head of transmit queue */
diff --git a/drivers/net/wireless/microchip/wilc1000/wlan.c b/drivers/net/wireless/microchip/wilc1000/wlan.c
index 37c32d17856ea..a9e872a7b2c38 100644
--- a/drivers/net/wireless/microchip/wilc1000/wlan.c
+++ b/drivers/net/wireless/microchip/wilc1000/wlan.c
@@ -712,6 +712,7 @@ int wilc_wlan_handle_txq(struct wilc *wilc, u32 *txq_count)
 	u32 *vmm_table = wilc->vmm_table;
 	u8 ac_pkt_num_to_chip[NQUEUES] = {0, 0, 0, 0};
 	const struct wilc_hif_func *func;
+	int srcu_idx;
 	u8 *txb = wilc->tx_buffer;
 	struct wilc_vif *vif;
 
@@ -723,10 +724,10 @@ int wilc_wlan_handle_txq(struct wilc *wilc, u32 *txq_count)
 
 	mutex_lock(&wilc->txq_add_to_head_cs);
 
-	rcu_read_lock();
+	srcu_idx = srcu_read_lock(&wilc->srcu);
 	wilc_for_each_vif(wilc, vif)
 		wilc_wlan_txq_filter_dup_tcp_ack(vif->ndev);
-	rcu_read_unlock();
+	srcu_read_unlock(&wilc->srcu, srcu_idx);
 
 	for (ac = 0; ac < NQUEUES; ac++)
 		tqe_q[ac] = wilc_wlan_txq_get_first(wilc, ac);
-- 
GitLab


From 3596717a6fbd54c64e97e085a9f77ed511ff59f9 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Alexis=20Lothor=C3=A9?= <alexis.lothore@bootlin.com>
Date: Tue, 28 May 2024 16:20:29 +0200
Subject: [PATCH 655/950] Revert "wifi: wilc1000: set atomic flag on kmemdup in
 srcu critical section"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This reverts commit 35aee01ff43d7eb6c2caa0b94e7cc6c45baeeab7

Commit 35aee01ff43d ("wifi: wilc1000: set atomic flag on kmemdup in srcu
critical section") was preparatory to the SRCU to RCU conversion done by
commit f236464f1db7 ("wifi: wilc1000: convert list management to RCU").
This conversion brought issues and so has been reverted, so the atomic flag
is not needed anymore.

Signed-off-by: Alexis Lothoré <alexis.lothore@bootlin.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://msgid.link/20240528-wilc_revert_srcu_to_rcu-v1-2-bce096e0798c@bootlin.com
---
 drivers/net/wireless/microchip/wilc1000/hif.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/microchip/wilc1000/hif.c b/drivers/net/wireless/microchip/wilc1000/hif.c
index 3925ca653e807..f1085ccb7eedc 100644
--- a/drivers/net/wireless/microchip/wilc1000/hif.c
+++ b/drivers/net/wireless/microchip/wilc1000/hif.c
@@ -1594,7 +1594,7 @@ void wilc_network_info_received(struct wilc *wilc, u8 *buffer, u32 length)
 	msg->body.net_info.rssi = buffer[8];
 	msg->body.net_info.mgmt = kmemdup(&buffer[9],
 					  msg->body.net_info.frame_len,
-					  GFP_ATOMIC);
+					  GFP_KERNEL);
 	if (!msg->body.net_info.mgmt) {
 		kfree(msg);
 		goto out;
-- 
GitLab


From 596c195680dceb34e6b994ff5571331d5dba8299 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Alexis=20Lothor=C3=A9?= <alexis.lothore@bootlin.com>
Date: Tue, 28 May 2024 16:20:30 +0200
Subject: [PATCH 656/950] wifi: wilc1000: document SRCU usage instead of SRCU
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit f236464f1db7 ("wifi: wilc1000: convert list management to RCU")
attempted to convert SRCU to RCU usage, assuming it was not really needed.
The runtime issues that arose after merging it showed that there are code
paths involving sleeping functions, and removing those would need some
heavier driver rework.

Add some documentation about SRCU need to make sure that any future
developer do not miss some use cases if tempted to convert back again to
RCU.

Signed-off-by: Alexis Lothoré <alexis.lothore@bootlin.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://msgid.link/20240528-wilc_revert_srcu_to_rcu-v1-3-bce096e0798c@bootlin.com
---
 drivers/net/wireless/microchip/wilc1000/netdev.h | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/wireless/microchip/wilc1000/netdev.h b/drivers/net/wireless/microchip/wilc1000/netdev.h
index 5937d6d45695f..fde8610a9c84b 100644
--- a/drivers/net/wireless/microchip/wilc1000/netdev.h
+++ b/drivers/net/wireless/microchip/wilc1000/netdev.h
@@ -220,6 +220,13 @@ struct wilc {
 
 	/* protect vif list */
 	struct mutex vif_mutex;
+	/* Sleepable RCU struct to manipulate vif list. Sleepable version is
+	 * needed over the classic RCU version because the driver's current
+	 * design involves some sleeping code while manipulating a vif
+	 * retrieved from vif list (so in a SRCU critical section), like:
+	 * - sending commands to the chip, using info from retrieved vif
+	 * - registering a new monitoring net device
+	 */
 	struct srcu_struct srcu;
 	u8 open_ifcs;
 
-- 
GitLab


From 40cecacabc460f5074398753feb9ed7d43e8dfa6 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 28 May 2024 14:23:08 +0200
Subject: [PATCH 657/950] wifi: mt76: mt7615: add missing chanctx ops

Here's another one I missed during the initial conversion,
fix that.

Cc: stable@vger.kernel.org
Reported-by: Rene Petersen <renepetersen@posteo.de>
Fixes: 0a44dfc07074 ("wifi: mac80211: simplify non-chanctx drivers")
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=218895
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://msgid.link/20240528142308.3f7db1821e68.I531135d7ad76331a50244d6d5288e14aa9668390@changeid
---
 drivers/net/wireless/mediatek/mt76/mt7615/main.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/main.c b/drivers/net/wireless/mediatek/mt76/mt7615/main.c
index 0971c164b57e9..c27acaf0eb1cf 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/main.c
@@ -1326,6 +1326,10 @@ static void mt7615_set_rekey_data(struct ieee80211_hw *hw,
 #endif /* CONFIG_PM */
 
 const struct ieee80211_ops mt7615_ops = {
+	.add_chanctx = ieee80211_emulate_add_chanctx,
+	.remove_chanctx = ieee80211_emulate_remove_chanctx,
+	.change_chanctx = ieee80211_emulate_change_chanctx,
+	.switch_vif_chanctx = ieee80211_emulate_switch_vif_chanctx,
 	.tx = mt7615_tx,
 	.start = mt7615_start,
 	.stop = mt7615_stop,
-- 
GitLab


From dcb77f854ae086bf32596fae02c88665393a13e8 Mon Sep 17 00:00:00 2001
From: Erick Archer <erick.archer@outlook.com>
Date: Mon, 27 May 2024 19:34:25 +0200
Subject: [PATCH 658/950] wifi: brcm80211: use sizeof(*pointer) instead of
 sizeof(type)

It is preferred to use sizeof(*pointer) instead of sizeof(type)
due to the type of the variable can change and one needs not
change the former (unlike the latter). This patch has no effect
on runtime behavior.

At the same time remove some redundant NULL initializations.

Acked-by: Arend van Spriel <arend.vanspriel@broadcom.com>
Signed-off-by: Erick Archer <erick.archer@outlook.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://msgid.link/AS8PR02MB7237FF1C2E880D1231684D708BF02@AS8PR02MB7237.eurprd02.prod.outlook.com
---
 .../broadcom/brcm80211/brcmfmac/bcmsdh.c      |  4 ++--
 .../broadcom/brcm80211/brcmfmac/btcoex.c      |  4 ++--
 .../broadcom/brcm80211/brcmfmac/sdio.c        |  2 +-
 .../broadcom/brcm80211/brcmfmac/usb.c         |  6 ++---
 .../broadcom/brcm80211/brcmsmac/aiutils.c     |  2 +-
 .../broadcom/brcm80211/brcmsmac/ampdu.c       |  2 +-
 .../broadcom/brcm80211/brcmsmac/antsel.c      |  2 +-
 .../broadcom/brcm80211/brcmsmac/channel.c     |  2 +-
 .../broadcom/brcm80211/brcmsmac/dma.c         |  2 +-
 .../broadcom/brcm80211/brcmsmac/mac80211_if.c |  2 +-
 .../broadcom/brcm80211/brcmsmac/main.c        | 23 +++++++++----------
 .../broadcom/brcm80211/brcmsmac/phy/phy_cmn.c |  4 ++--
 .../broadcom/brcm80211/brcmsmac/phy/phy_lcn.c |  6 ++---
 .../broadcom/brcm80211/brcmsmac/phy_shim.c    |  4 ++--
 14 files changed, 32 insertions(+), 33 deletions(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c
index 00679a990e3da..32f6b9d419d42 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c
@@ -1061,10 +1061,10 @@ static int brcmf_ops_sdio_probe(struct sdio_func *func,
 	if (func->num != 2)
 		return -ENODEV;
 
-	bus_if = kzalloc(sizeof(struct brcmf_bus), GFP_KERNEL);
+	bus_if = kzalloc(sizeof(*bus_if), GFP_KERNEL);
 	if (!bus_if)
 		return -ENOMEM;
-	sdiodev = kzalloc(sizeof(struct brcmf_sdio_dev), GFP_KERNEL);
+	sdiodev = kzalloc(sizeof(*sdiodev), GFP_KERNEL);
 	if (!sdiodev) {
 		kfree(bus_if);
 		return -ENOMEM;
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/btcoex.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/btcoex.c
index 7ea2631b80692..0c3d119d12199 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/btcoex.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/btcoex.c
@@ -358,10 +358,10 @@ idle:
  */
 int brcmf_btcoex_attach(struct brcmf_cfg80211_info *cfg)
 {
-	struct brcmf_btcoex_info *btci = NULL;
+	struct brcmf_btcoex_info *btci;
 	brcmf_dbg(TRACE, "enter\n");
 
-	btci = kmalloc(sizeof(struct brcmf_btcoex_info), GFP_KERNEL);
+	btci = kmalloc(sizeof(*btci), GFP_KERNEL);
 	if (!btci)
 		return -ENOMEM;
 
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
index 6b38d9de71af6..1461dc453ac22 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
@@ -4450,7 +4450,7 @@ struct brcmf_sdio *brcmf_sdio_probe(struct brcmf_sdio_dev *sdiodev)
 	brcmf_dbg(TRACE, "Enter\n");
 
 	/* Allocate private bus interface state */
-	bus = kzalloc(sizeof(struct brcmf_sdio), GFP_ATOMIC);
+	bus = kzalloc(sizeof(*bus), GFP_ATOMIC);
 	if (!bus)
 		goto fail;
 
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c
index 9a105e6debe1f..8afbf529c7450 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c
@@ -1236,8 +1236,8 @@ brcmf_usb_prepare_fw_request(struct brcmf_usbdev_info *devinfo)
 static int brcmf_usb_probe_cb(struct brcmf_usbdev_info *devinfo,
 			      enum brcmf_fwvendor fwvid)
 {
-	struct brcmf_bus *bus = NULL;
-	struct brcmf_usbdev *bus_pub = NULL;
+	struct brcmf_bus *bus;
+	struct brcmf_usbdev *bus_pub;
 	struct device *dev = devinfo->dev;
 	struct brcmf_fw_request *fwreq;
 	int ret;
@@ -1247,7 +1247,7 @@ static int brcmf_usb_probe_cb(struct brcmf_usbdev_info *devinfo,
 	if (!bus_pub)
 		return -ENODEV;
 
-	bus = kzalloc(sizeof(struct brcmf_bus), GFP_ATOMIC);
+	bus = kzalloc(sizeof(*bus), GFP_ATOMIC);
 	if (!bus) {
 		ret = -ENOMEM;
 		goto fail;
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/aiutils.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/aiutils.c
index 2084b506a4500..50d817485cf9f 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/aiutils.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/aiutils.c
@@ -512,7 +512,7 @@ ai_attach(struct bcma_bus *pbus)
 	struct si_info *sii;
 
 	/* alloc struct si_info */
-	sii = kzalloc(sizeof(struct si_info), GFP_ATOMIC);
+	sii = kzalloc(sizeof(*sii), GFP_ATOMIC);
 	if (sii == NULL)
 		return NULL;
 
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/ampdu.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/ampdu.c
index c3376f887114a..33d17b779201d 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/ampdu.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/ampdu.c
@@ -219,7 +219,7 @@ struct ampdu_info *brcms_c_ampdu_attach(struct brcms_c_info *wlc)
 	struct ampdu_info *ampdu;
 	int i;
 
-	ampdu = kzalloc(sizeof(struct ampdu_info), GFP_ATOMIC);
+	ampdu = kzalloc(sizeof(*ampdu), GFP_ATOMIC);
 	if (!ampdu)
 		return NULL;
 
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/antsel.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/antsel.c
index 54c616919590d..f411bc6d795d6 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/antsel.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/antsel.c
@@ -111,7 +111,7 @@ struct antsel_info *brcms_c_antsel_attach(struct brcms_c_info *wlc)
 	struct antsel_info *asi;
 	struct ssb_sprom *sprom = &wlc->hw->d11core->bus->sprom;
 
-	asi = kzalloc(sizeof(struct antsel_info), GFP_ATOMIC);
+	asi = kzalloc(sizeof(*asi), GFP_ATOMIC);
 	if (!asi)
 		return NULL;
 
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/channel.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/channel.c
index f6962e558d7c7..d1b9a18d03740 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/channel.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/channel.c
@@ -331,7 +331,7 @@ struct brcms_cm_info *brcms_c_channel_mgr_attach(struct brcms_c_info *wlc)
 	const char *ccode = sprom->alpha2;
 	int ccode_len = sizeof(sprom->alpha2);
 
-	wlc_cm = kzalloc(sizeof(struct brcms_cm_info), GFP_ATOMIC);
+	wlc_cm = kzalloc(sizeof(*wlc_cm), GFP_ATOMIC);
 	if (wlc_cm == NULL)
 		return NULL;
 	wlc_cm->pub = pub;
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/dma.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/dma.c
index 3d5c1ef8f7f25..bd480239368a4 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/dma.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/dma.c
@@ -558,7 +558,7 @@ struct dma_pub *dma_attach(char *name, struct brcms_c_info *wlc,
 	struct si_info *sii = container_of(sih, struct si_info, pub);
 
 	/* allocate private info structure */
-	di = kzalloc(sizeof(struct dma_info), GFP_ATOMIC);
+	di = kzalloc(sizeof(*di), GFP_ATOMIC);
 	if (di == NULL)
 		return NULL;
 
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c
index 92860dc0a92eb..860ef9c11c46d 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c
@@ -1496,7 +1496,7 @@ struct brcms_timer *brcms_init_timer(struct brcms_info *wl,
 {
 	struct brcms_timer *t;
 
-	t = kzalloc(sizeof(struct brcms_timer), GFP_ATOMIC);
+	t = kzalloc(sizeof(*t), GFP_ATOMIC);
 	if (!t)
 		return NULL;
 
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/main.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/main.c
index 34460b5815d02..d3c74440381fb 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/main.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/main.c
@@ -463,11 +463,11 @@ static struct brcms_bss_cfg *brcms_c_bsscfg_malloc(uint unit)
 {
 	struct brcms_bss_cfg *cfg;
 
-	cfg = kzalloc(sizeof(struct brcms_bss_cfg), GFP_ATOMIC);
+	cfg = kzalloc(sizeof(*cfg), GFP_ATOMIC);
 	if (cfg == NULL)
 		goto fail;
 
-	cfg->current_bss = kzalloc(sizeof(struct brcms_bss_info), GFP_ATOMIC);
+	cfg->current_bss = kzalloc(sizeof(*cfg->current_bss), GFP_ATOMIC);
 	if (cfg->current_bss == NULL)
 		goto fail;
 
@@ -483,14 +483,14 @@ brcms_c_attach_malloc(uint unit, uint *err, uint devid)
 {
 	struct brcms_c_info *wlc;
 
-	wlc = kzalloc(sizeof(struct brcms_c_info), GFP_ATOMIC);
+	wlc = kzalloc(sizeof(*wlc), GFP_ATOMIC);
 	if (wlc == NULL) {
 		*err = 1002;
 		goto fail;
 	}
 
 	/* allocate struct brcms_c_pub state structure */
-	wlc->pub = kzalloc(sizeof(struct brcms_pub), GFP_ATOMIC);
+	wlc->pub = kzalloc(sizeof(*wlc->pub), GFP_ATOMIC);
 	if (wlc->pub == NULL) {
 		*err = 1003;
 		goto fail;
@@ -499,7 +499,7 @@ brcms_c_attach_malloc(uint unit, uint *err, uint devid)
 
 	/* allocate struct brcms_hardware state structure */
 
-	wlc->hw = kzalloc(sizeof(struct brcms_hardware), GFP_ATOMIC);
+	wlc->hw = kzalloc(sizeof(*wlc->hw), GFP_ATOMIC);
 	if (wlc->hw == NULL) {
 		*err = 1005;
 		goto fail;
@@ -528,7 +528,7 @@ brcms_c_attach_malloc(uint unit, uint *err, uint devid)
 		goto fail;
 	}
 
-	wlc->default_bss = kzalloc(sizeof(struct brcms_bss_info), GFP_ATOMIC);
+	wlc->default_bss = kzalloc(sizeof(*wlc->default_bss), GFP_ATOMIC);
 	if (wlc->default_bss == NULL) {
 		*err = 1010;
 		goto fail;
@@ -540,21 +540,20 @@ brcms_c_attach_malloc(uint unit, uint *err, uint devid)
 		goto fail;
 	}
 
-	wlc->protection = kzalloc(sizeof(struct brcms_protection),
-				  GFP_ATOMIC);
+	wlc->protection = kzalloc(sizeof(*wlc->protection), GFP_ATOMIC);
 	if (wlc->protection == NULL) {
 		*err = 1016;
 		goto fail;
 	}
 
-	wlc->stf = kzalloc(sizeof(struct brcms_stf), GFP_ATOMIC);
+	wlc->stf = kzalloc(sizeof(*wlc->stf), GFP_ATOMIC);
 	if (wlc->stf == NULL) {
 		*err = 1017;
 		goto fail;
 	}
 
 	wlc->bandstate[0] =
-		kcalloc(MAXBANDS, sizeof(struct brcms_band), GFP_ATOMIC);
+		kcalloc(MAXBANDS, sizeof(*wlc->bandstate[0]), GFP_ATOMIC);
 	if (wlc->bandstate[0] == NULL) {
 		*err = 1025;
 		goto fail;
@@ -567,14 +566,14 @@ brcms_c_attach_malloc(uint unit, uint *err, uint devid)
 				+ (sizeof(struct brcms_band)*i));
 	}
 
-	wlc->corestate = kzalloc(sizeof(struct brcms_core), GFP_ATOMIC);
+	wlc->corestate = kzalloc(sizeof(*wlc->corestate), GFP_ATOMIC);
 	if (wlc->corestate == NULL) {
 		*err = 1026;
 		goto fail;
 	}
 
 	wlc->corestate->macstat_snapshot =
-		kzalloc(sizeof(struct macstat), GFP_ATOMIC);
+		kzalloc(sizeof(*wlc->corestate->macstat_snapshot), GFP_ATOMIC);
 	if (wlc->corestate->macstat_snapshot == NULL) {
 		*err = 1027;
 		goto fail;
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_cmn.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_cmn.c
index a27d6f0b88191..c3d7aa570b4e2 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_cmn.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_cmn.c
@@ -355,7 +355,7 @@ struct shared_phy *wlc_phy_shared_attach(struct shared_phy_params *shp)
 {
 	struct shared_phy *sh;
 
-	sh = kzalloc(sizeof(struct shared_phy), GFP_ATOMIC);
+	sh = kzalloc(sizeof(*sh), GFP_ATOMIC);
 	if (sh == NULL)
 		return NULL;
 
@@ -442,7 +442,7 @@ wlc_phy_attach(struct shared_phy *sh, struct bcma_device *d11core,
 		return &pi->pubpi_ro;
 	}
 
-	pi = kzalloc(sizeof(struct brcms_phy), GFP_ATOMIC);
+	pi = kzalloc(sizeof(*pi), GFP_ATOMIC);
 	if (pi == NULL)
 		return NULL;
 	pi->wiphy = wiphy;
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_lcn.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_lcn.c
index e472591f321bd..d0faba2405610 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_lcn.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_lcn.c
@@ -4968,11 +4968,11 @@ bool wlc_phy_attach_lcnphy(struct brcms_phy *pi)
 {
 	struct brcms_phy_lcnphy *pi_lcn;
 
-	pi->u.pi_lcnphy = kzalloc(sizeof(struct brcms_phy_lcnphy), GFP_ATOMIC);
-	if (pi->u.pi_lcnphy == NULL)
+	pi_lcn = kzalloc(sizeof(*pi_lcn), GFP_ATOMIC);
+	if (!pi_lcn)
 		return false;
 
-	pi_lcn = pi->u.pi_lcnphy;
+	pi->u.pi_lcnphy = pi_lcn;
 
 	if (0 == (pi->sh->boardflags & BFL_NOPA)) {
 		pi->hwpwrctrl = true;
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy_shim.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy_shim.c
index b723817915365..8b852581c4e47 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy_shim.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy_shim.c
@@ -38,9 +38,9 @@ struct phy_shim_info {
 struct phy_shim_info *wlc_phy_shim_attach(struct brcms_hardware *wlc_hw,
 					  struct brcms_info *wl,
 					  struct brcms_c_info *wlc) {
-	struct phy_shim_info *physhim = NULL;
+	struct phy_shim_info *physhim;
 
-	physhim = kzalloc(sizeof(struct phy_shim_info), GFP_ATOMIC);
+	physhim = kzalloc(sizeof(*physhim), GFP_ATOMIC);
 	if (!physhim)
 		return NULL;
 
-- 
GitLab


From 5bcd9a0a59953b5ff55ac226f903397319bf7f40 Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Mon, 27 May 2024 00:45:53 +0100
Subject: [PATCH 659/950] wifi: brcm80211: remove unused structs

'brcmf_pcie_core_info' was added in
commit 9e37f045d5e7 ("brcmfmac: Adding PCIe bus layer support.")
but never used.

'brcms_c_bit_desc' last use was removed in
commit cdf4352f5c59 ("brcmsmac: Improve tx trace and debug support").

Remove them.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Acked-by: Arend van Spriel <arend.vanspriel@broadcom.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://msgid.link/20240526234553.286773-1-linux@treblig.org
---
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c | 5 -----
 drivers/net/wireless/broadcom/brcm80211/brcmsmac/main.c | 6 ------
 2 files changed, 11 deletions(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c
index 06698a714b523..ce482a3877e90 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c
@@ -313,11 +313,6 @@ struct brcmf_pcie_shared_info {
 	u8 version;
 };
 
-struct brcmf_pcie_core_info {
-	u32 base;
-	u32 wrapbase;
-};
-
 #define BRCMF_OTP_MAX_PARAM_LEN 16
 
 struct brcmf_otp_params {
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/main.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/main.c
index d3c74440381fb..2738d4d6c60a9 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/main.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/main.c
@@ -234,12 +234,6 @@
 /* max # tx status to process in wlc_txstatus() */
 #define TXSBND				8
 
-/* brcmu_format_flags() bit description structure */
-struct brcms_c_bit_desc {
-	u32 bit;
-	const char *name;
-};
-
 /*
  * The following table lists the buffer memory allocated to xmt fifos in HW.
  * the size is in units of 256bytes(one block), total size is HW dependent
-- 
GitLab


From 819bda58e77bb67974f94dc1aa11b0556b6f6889 Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Wed, 29 May 2024 20:19:47 +0300
Subject: [PATCH 660/950] wifi: rtlwifi: Ignore
 IEEE80211_CONF_CHANGE_RETRY_LIMITS

Since commit 0a44dfc07074 ("wifi: mac80211: simplify non-chanctx
drivers") ieee80211_hw_config() is no longer called with changed = ~0.
rtlwifi relied on ~0 in order to ignore the default retry limits of
4/7, preferring 48/48 in station mode and 7/7 in AP/IBSS.

RTL8192DU has a lot of packet loss with the default limits from
mac80211. Fix it by ignoring IEEE80211_CONF_CHANGE_RETRY_LIMITS
completely, because it's the simplest solution.

Link: https://lore.kernel.org/linux-wireless/cedd13d7691f4692b2a2fa5a24d44a22@realtek.com/
Cc: stable@vger.kernel.org # 6.9.x
Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Acked-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://msgid.link/1fabb8e4-adf3-47ae-8462-8aea963bc2a5@gmail.com
---
 drivers/net/wireless/realtek/rtlwifi/core.c | 15 ---------------
 1 file changed, 15 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtlwifi/core.c b/drivers/net/wireless/realtek/rtlwifi/core.c
index 2e60a6991ca16..42b7db12b1bd4 100644
--- a/drivers/net/wireless/realtek/rtlwifi/core.c
+++ b/drivers/net/wireless/realtek/rtlwifi/core.c
@@ -633,21 +633,6 @@ static int rtl_op_config(struct ieee80211_hw *hw, u32 changed)
 		}
 	}
 
-	if (changed & IEEE80211_CONF_CHANGE_RETRY_LIMITS) {
-		rtl_dbg(rtlpriv, COMP_MAC80211, DBG_LOUD,
-			"IEEE80211_CONF_CHANGE_RETRY_LIMITS %x\n",
-			hw->conf.long_frame_max_tx_count);
-		/* brought up everything changes (changed == ~0) indicates first
-		 * open, so use our default value instead of that of wiphy.
-		 */
-		if (changed != ~0) {
-			mac->retry_long = hw->conf.long_frame_max_tx_count;
-			mac->retry_short = hw->conf.long_frame_max_tx_count;
-			rtlpriv->cfg->ops->set_hw_reg(hw, HW_VAR_RETRY_LIMIT,
-				(u8 *)(&hw->conf.long_frame_max_tx_count));
-		}
-	}
-
 	if (changed & IEEE80211_CONF_CHANGE_CHANNEL &&
 	    !rtlpriv->proximity.proxim_on) {
 		struct ieee80211_channel *channel = hw->conf.chandef.chan;
-- 
GitLab


From 30636258a7c9174be44ddb2318bae4f66d4beab0 Mon Sep 17 00:00:00 2001
From: Heng Qi <hengqi@linux.alibaba.com>
Date: Thu, 30 May 2024 11:41:43 +0800
Subject: [PATCH 661/950] virtio_net: fix missing lock protection on
 control_buf access

Refactored the handling of control_buf to be within the cvq_lock
critical section, mitigating race conditions between reading device
responses and new command submissions.

Fixes: 6f45ab3e0409 ("virtio_net: Add a lock for the command VQ.")
Signed-off-by: Heng Qi <hengqi@linux.alibaba.com>
Reviewed-by: Hariprasad Kelam <hkelam@marvell.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Reviewed-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Link: https://lore.kernel.org/r/20240530034143.19579-1-hengqi@linux.alibaba.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/virtio_net.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 4a802c0ea2cbc..1ea8e6a24286e 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -2686,6 +2686,7 @@ static bool virtnet_send_command_reply(struct virtnet_info *vi, u8 class, u8 cmd
 {
 	struct scatterlist *sgs[5], hdr, stat;
 	u32 out_num = 0, tmp, in_num = 0;
+	bool ok;
 	int ret;
 
 	/* Caller should know better */
@@ -2731,8 +2732,9 @@ static bool virtnet_send_command_reply(struct virtnet_info *vi, u8 class, u8 cmd
 	}
 
 unlock:
+	ok = vi->ctrl->status == VIRTIO_NET_OK;
 	mutex_unlock(&vi->cvq_lock);
-	return vi->ctrl->status == VIRTIO_NET_OK;
+	return ok;
 }
 
 static bool virtnet_send_command(struct virtnet_info *vi, u8 class, u8 cmd,
-- 
GitLab


From 7679935b8bdf8d2bc298b04ed579d1ed78e81907 Mon Sep 17 00:00:00 2001
From: Peter Geis <pgwipeout@gmail.com>
Date: Wed, 29 May 2024 14:56:35 -0400
Subject: [PATCH 662/950] MAINTAINERS: remove Peter Geis

The Motorcomm PHY driver is now maintained by the OEM. The driver has
expanded far beyond my original purpose, and I do not have the hardware
to test against the new portions of it. Therefore I am removing myself as
a maintainer of the driver.

Signed-off-by: Peter Geis <pgwipeout@gmail.com>
Link: https://lore.kernel.org/r/20240529185635.538072-1-pgwipeout@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 1 -
 1 file changed, 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index ba231d2f3a4e5..f7b8025e3c27c 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15239,7 +15239,6 @@ F:	drivers/staging/most/
 F:	include/linux/most.h
 
 MOTORCOMM PHY DRIVER
-M:	Peter Geis <pgwipeout@gmail.com>
 M:	Frank <Frank.Sae@motor-comm.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
-- 
GitLab


From 89e281ebff72e6d37dce2df0e142b2909dafb267 Mon Sep 17 00:00:00 2001
From: Vadim Fedorenko <vadfed@meta.com>
Date: Wed, 29 May 2024 21:08:14 -0700
Subject: [PATCH 663/950] ethtool: init tsinfo stats if requested

Statistic values should be set to ETHTOOL_STAT_NOT_SET even if the
device doesn't support statistics. Otherwise zeros will be returned as
if they are proper values:

host# ethtool -I -T lo
Time stamping parameters for lo:
Capabilities:
	software-transmit
	software-receive
	software-system-clock
PTP Hardware Clock: none
Hardware Transmit Timestamp Modes: none
Hardware Receive Filter Modes: none
Statistics:
  tx_pkts: 0
  tx_lost: 0
  tx_err: 0

Fixes: 0e9c127729be ("ethtool: add interface to read Tx hardware timestamping statistics")
Suggested-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Vadim Fedorenko <vadfed@meta.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Link: https://lore.kernel.org/r/20240530040814.1014446-1-vadfed@meta.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ethtool/tsinfo.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/ethtool/tsinfo.c b/net/ethtool/tsinfo.c
index be2755c8d8fde..57d496287e523 100644
--- a/net/ethtool/tsinfo.c
+++ b/net/ethtool/tsinfo.c
@@ -38,11 +38,11 @@ static int tsinfo_prepare_data(const struct ethnl_req_info *req_base,
 	ret = ethnl_ops_begin(dev);
 	if (ret < 0)
 		return ret;
-	if (req_base->flags & ETHTOOL_FLAG_STATS &&
-	    dev->ethtool_ops->get_ts_stats) {
+	if (req_base->flags & ETHTOOL_FLAG_STATS) {
 		ethtool_stats_init((u64 *)&data->stats,
 				   sizeof(data->stats) / sizeof(u64));
-		dev->ethtool_ops->get_ts_stats(dev, &data->stats);
+		if (dev->ethtool_ops->get_ts_stats)
+			dev->ethtool_ops->get_ts_stats(dev, &data->stats);
 	}
 	ret = __ethtool_get_ts_info(dev, &data->ts_info);
 	ethnl_ops_complete(dev);
-- 
GitLab


From 69c8b998717c03adeada070882512ebeae11d71f Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 29 May 2024 09:29:22 -0700
Subject: [PATCH 664/950] net: qstat: extend kdoc about get_base_stats

mlx5 has a dedicated queue for PTP packets. Clarify that
this sort of queues can also be accounted towards the base.

Reviewed-by: Joe Damato <jdamato@fastly.com>
Link: https://lore.kernel.org/r/20240529162922.3690698-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/netdev_queues.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/include/net/netdev_queues.h b/include/net/netdev_queues.h
index a8a7e48dfa6ca..5ca019d294ca3 100644
--- a/include/net/netdev_queues.h
+++ b/include/net/netdev_queues.h
@@ -62,6 +62,8 @@ struct netdev_queue_stats_tx {
  * statistics will not generally add up to the total number of events for
  * the device. The @get_base_stats callback allows filling in the delta
  * between events for currently live queues and overall device history.
+ * @get_base_stats can also be used to report any miscellaneous packets
+ * transferred outside of the main set of queues used by the networking stack.
  * When the statistics for the entire device are queried, first @get_base_stats
  * is issued to collect the delta, and then a series of per-queue callbacks.
  * Only statistics which are set in @get_base_stats will be reported
-- 
GitLab


From 9e0945b1901c9eed4fbee3b8a3870487b2bdc936 Mon Sep 17 00:00:00 2001
From: Heng Qi <hengqi@linux.alibaba.com>
Date: Tue, 28 May 2024 21:41:15 +0800
Subject: [PATCH 665/950] virtio_net: fix possible dim status unrecoverable

When the dim worker is scheduled, if it no longer needs to issue
commands, dim may not be able to return to the working state later.

For example, the following single queue scenario:
  1. The dim worker of rxq0 is scheduled, and the dim status is
     changed to DIM_APPLY_NEW_PROFILE;
  2. dim is disabled or parameters have not been modified;
  3. virtnet_rx_dim_work exits directly;

Then, even if net_dim is invoked again, it cannot work because the
state is not restored to DIM_START_MEASURE.

Fixes: 6208799553a8 ("virtio-net: support rx netdim")
Signed-off-by: Heng Qi <hengqi@linux.alibaba.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Link: https://lore.kernel.org/r/20240528134116.117426-2-hengqi@linux.alibaba.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/virtio_net.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 1ea8e6a24286e..774a292a60906 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -4419,9 +4419,9 @@ static void virtnet_rx_dim_work(struct work_struct *work)
 		if (err)
 			pr_debug("%s: Failed to send dim parameters on rxq%d\n",
 				 dev->name, qnum);
-		dim->state = DIM_START_MEASURE;
 	}
 out:
+	dim->state = DIM_START_MEASURE;
 	mutex_unlock(&rq->dim_lock);
 }
 
-- 
GitLab


From d1f0bd01bc58f35b5353ad9dbe5f7249a8f3368e Mon Sep 17 00:00:00 2001
From: Heng Qi <hengqi@linux.alibaba.com>
Date: Tue, 28 May 2024 21:41:16 +0800
Subject: [PATCH 666/950] virtio_net: fix a spurious deadlock issue

When the following snippet is run, lockdep will report a deadlock[1].

  /* Acquire all queues dim_locks */
  for (i = 0; i < vi->max_queue_pairs; i++)
          mutex_lock(&vi->rq[i].dim_lock);

There's no deadlock here because the vq locks are always taken
in the same order, but lockdep can not figure it out. So refactoring
the code to alleviate the problem.

[1]
========================================================
WARNING: possible recursive locking detected
6.9.0-rc7+ #319 Not tainted
--------------------------------------------
ethtool/962 is trying to acquire lock:

but task is already holding lock:

other info that might help us debug this:
Possible unsafe locking scenario:

      CPU0
      ----
 lock(&vi->rq[i].dim_lock);
 lock(&vi->rq[i].dim_lock);

*** DEADLOCK ***

 May be due to missing lock nesting notation

3 locks held by ethtool/962:
 #0: ffffffff82dbaab0 (cb_lock){++++}-{3:3}, at: genl_rcv+0x19/0x40
 #1: ffffffff82dad0a8 (rtnl_mutex){+.+.}-{3:3}, at:
				ethnl_default_set_doit+0xbe/0x1e0

stack backtrace:
CPU: 6 PID: 962 Comm: ethtool Not tainted 6.9.0-rc7+ #319
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS
	   rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014
Call Trace:
 <TASK>
 dump_stack_lvl+0x79/0xb0
 check_deadlock+0x130/0x220
 __lock_acquire+0x861/0x990
 lock_acquire.part.0+0x72/0x1d0
 ? lock_acquire+0xf8/0x130
 __mutex_lock+0x71/0xd50
 virtnet_set_coalesce+0x151/0x190
 __ethnl_set_coalesce.isra.0+0x3f8/0x4d0
 ethnl_set_coalesce+0x34/0x90
 ethnl_default_set_doit+0xdd/0x1e0
 genl_family_rcv_msg_doit+0xdc/0x130
 genl_family_rcv_msg+0x154/0x230
 ? __pfx_ethnl_default_set_doit+0x10/0x10
 genl_rcv_msg+0x4b/0xa0
 ? __pfx_genl_rcv_msg+0x10/0x10
 netlink_rcv_skb+0x5a/0x110
 genl_rcv+0x28/0x40
 netlink_unicast+0x1af/0x280
 netlink_sendmsg+0x20e/0x460
 __sys_sendto+0x1fe/0x210
 ? find_held_lock+0x2b/0x80
 ? do_user_addr_fault+0x3a2/0x8a0
 ? __lock_release+0x5e/0x160
 ? do_user_addr_fault+0x3a2/0x8a0
 ? lock_release+0x72/0x140
 ? do_user_addr_fault+0x3a7/0x8a0
 __x64_sys_sendto+0x29/0x30
 do_syscall_64+0x78/0x180
 entry_SYSCALL_64_after_hwframe+0x76/0x7e

Fixes: 4d4ac2ececd3 ("virtio_net: Add a lock for per queue RX coalesce")
Signed-off-by: Heng Qi <hengqi@linux.alibaba.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Link: https://lore.kernel.org/r/20240528134116.117426-3-hengqi@linux.alibaba.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/virtio_net.c | 36 ++++++++++++++++--------------------
 1 file changed, 16 insertions(+), 20 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 774a292a60906..61a57d134544f 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -4259,7 +4259,6 @@ static int virtnet_send_rx_notf_coal_cmds(struct virtnet_info *vi,
 	struct virtio_net_ctrl_coal_rx *coal_rx __free(kfree) = NULL;
 	bool rx_ctrl_dim_on = !!ec->use_adaptive_rx_coalesce;
 	struct scatterlist sgs_rx;
-	int ret = 0;
 	int i;
 
 	if (rx_ctrl_dim_on && !virtio_has_feature(vi->vdev, VIRTIO_NET_F_VQ_NOTF_COAL))
@@ -4269,27 +4268,27 @@ static int virtnet_send_rx_notf_coal_cmds(struct virtnet_info *vi,
 			       ec->rx_max_coalesced_frames != vi->intr_coal_rx.max_packets))
 		return -EINVAL;
 
-	/* Acquire all queues dim_locks */
-	for (i = 0; i < vi->max_queue_pairs; i++)
-		mutex_lock(&vi->rq[i].dim_lock);
-
 	if (rx_ctrl_dim_on && !vi->rx_dim_enabled) {
 		vi->rx_dim_enabled = true;
-		for (i = 0; i < vi->max_queue_pairs; i++)
+		for (i = 0; i < vi->max_queue_pairs; i++) {
+			mutex_lock(&vi->rq[i].dim_lock);
 			vi->rq[i].dim_enabled = true;
-		goto unlock;
+			mutex_unlock(&vi->rq[i].dim_lock);
+		}
+		return 0;
 	}
 
 	coal_rx = kzalloc(sizeof(*coal_rx), GFP_KERNEL);
-	if (!coal_rx) {
-		ret = -ENOMEM;
-		goto unlock;
-	}
+	if (!coal_rx)
+		return -ENOMEM;
 
 	if (!rx_ctrl_dim_on && vi->rx_dim_enabled) {
 		vi->rx_dim_enabled = false;
-		for (i = 0; i < vi->max_queue_pairs; i++)
+		for (i = 0; i < vi->max_queue_pairs; i++) {
+			mutex_lock(&vi->rq[i].dim_lock);
 			vi->rq[i].dim_enabled = false;
+			mutex_unlock(&vi->rq[i].dim_lock);
+		}
 	}
 
 	/* Since the per-queue coalescing params can be set,
@@ -4302,22 +4301,19 @@ static int virtnet_send_rx_notf_coal_cmds(struct virtnet_info *vi,
 
 	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_NOTF_COAL,
 				  VIRTIO_NET_CTRL_NOTF_COAL_RX_SET,
-				  &sgs_rx)) {
-		ret = -EINVAL;
-		goto unlock;
-	}
+				  &sgs_rx))
+		return -EINVAL;
 
 	vi->intr_coal_rx.max_usecs = ec->rx_coalesce_usecs;
 	vi->intr_coal_rx.max_packets = ec->rx_max_coalesced_frames;
 	for (i = 0; i < vi->max_queue_pairs; i++) {
+		mutex_lock(&vi->rq[i].dim_lock);
 		vi->rq[i].intr_coal.max_usecs = ec->rx_coalesce_usecs;
 		vi->rq[i].intr_coal.max_packets = ec->rx_max_coalesced_frames;
-	}
-unlock:
-	for (i = vi->max_queue_pairs - 1; i >= 0; i--)
 		mutex_unlock(&vi->rq[i].dim_lock);
+	}
 
-	return ret;
+	return 0;
 }
 
 static int virtnet_send_notf_coal_cmds(struct virtnet_info *vi,
-- 
GitLab


From 6d9e9c36e1a6407818ec8ef9785ae47150d7ddc3 Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@toblux.com>
Date: Wed, 29 May 2024 16:39:02 +0200
Subject: [PATCH 667/950] net: smc91x: Fix pointer types

Use void __iomem pointers as parameters for mcf_insw() and mcf_outsw()
to align with the parameter types of readw() and writew() to fix the
following warnings reported by kernel test robot:

drivers/net/ethernet/smsc/smc91x.c:590:9: sparse: warning: incorrect type in argument 1 (different address spaces)
drivers/net/ethernet/smsc/smc91x.c:590:9: sparse:    expected void *a
drivers/net/ethernet/smsc/smc91x.c:590:9: sparse:    got void [noderef] __iomem *
drivers/net/ethernet/smsc/smc91x.c:590:9: sparse: warning: incorrect type in argument 1 (different address spaces)
drivers/net/ethernet/smsc/smc91x.c:590:9: sparse:    expected void *a
drivers/net/ethernet/smsc/smc91x.c:590:9: sparse:    got void [noderef] __iomem *
drivers/net/ethernet/smsc/smc91x.c:590:9: sparse: warning: incorrect type in argument 1 (different address spaces)
drivers/net/ethernet/smsc/smc91x.c:590:9: sparse:    expected void *a
drivers/net/ethernet/smsc/smc91x.c:590:9: sparse:    got void [noderef] __iomem *
drivers/net/ethernet/smsc/smc91x.c:483:17: sparse: warning: incorrect type in argument 1 (different address spaces)
drivers/net/ethernet/smsc/smc91x.c:483:17: sparse:    expected void *a
drivers/net/ethernet/smsc/smc91x.c:483:17: sparse:    got void [noderef] __iomem *

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202405160853.3qyaSj8w-lkp@intel.com/
Acked-by: Nicolas Pitre <nico@fluxnic.net>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Thorsten Blum <thorsten.blum@toblux.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Link: https://lore.kernel.org/r/20240529143859.108201-4-thorsten.blum@toblux.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/smsc/smc91x.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/smsc/smc91x.h b/drivers/net/ethernet/smsc/smc91x.h
index 45ef5ac0788a8..38aa4374e813a 100644
--- a/drivers/net/ethernet/smsc/smc91x.h
+++ b/drivers/net/ethernet/smsc/smc91x.h
@@ -142,14 +142,14 @@ static inline void _SMC_outw_align4(u16 val, void __iomem *ioaddr, int reg,
 #define SMC_CAN_USE_32BIT	0
 #define SMC_NOWAIT		1
 
-static inline void mcf_insw(void *a, unsigned char *p, int l)
+static inline void mcf_insw(void __iomem *a, unsigned char *p, int l)
 {
 	u16 *wp = (u16 *) p;
 	while (l-- > 0)
 		*wp++ = readw(a);
 }
 
-static inline void mcf_outsw(void *a, unsigned char *p, int l)
+static inline void mcf_outsw(void __iomem *a, unsigned char *p, int l)
 {
 	u16 *wp = (u16 *) p;
 	while (l-- > 0)
-- 
GitLab


From ccf45c92d746e8eac2cb1e60243d38a479e8dc0a Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Thu, 30 May 2024 16:07:30 +0200
Subject: [PATCH 668/950] doc: mptcp: add missing 'available_schedulers' entry

This sysctl knob has been added recently, but the documentation has not
been updated.

This knob is used to show the available schedulers choices that are
registered, similar to 'net.ipv4.tcp_available_congestion_control'.

Fixes: 73c900aa3660 ("mptcp: add net.mptcp.available_schedulers")
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://lore.kernel.org/r/20240530-upstream-net-20240520-mptcp-doc-v3-1-e94cdd9f2673@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/networking/mptcp-sysctl.rst | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/Documentation/networking/mptcp-sysctl.rst b/Documentation/networking/mptcp-sysctl.rst
index 69975ce25a029..102a45e7bfa8a 100644
--- a/Documentation/networking/mptcp-sysctl.rst
+++ b/Documentation/networking/mptcp-sysctl.rst
@@ -93,3 +93,7 @@ scheduler - STRING
 	sysctl.
 
 	Default: "default"
+
+available_schedulers - STRING
+	Shows the available schedulers choices that are registered. More packet
+	schedulers may be available, but not loaded.
-- 
GitLab


From a32c6966b23d987520f7c5ac12d153eaff425553 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Thu, 30 May 2024 16:07:31 +0200
Subject: [PATCH 669/950] doc: mptcp: alphabetical order

Similar to what is done in other 'sysctl' pages: it looks clearer from a
readability perspective.

This might cause troubles in the short/mid-term with the backports, but
by not putting new entries at the end, this can help to reduce conflicts
in case of backports in the long term. We don't change the information
here too often, so it looks OK to do that.

Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://lore.kernel.org/r/20240530-upstream-net-20240520-mptcp-doc-v3-2-e94cdd9f2673@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/networking/mptcp-sysctl.rst | 74 +++++++++++------------
 1 file changed, 37 insertions(+), 37 deletions(-)

diff --git a/Documentation/networking/mptcp-sysctl.rst b/Documentation/networking/mptcp-sysctl.rst
index 102a45e7bfa8a..fd514bba8c431 100644
--- a/Documentation/networking/mptcp-sysctl.rst
+++ b/Documentation/networking/mptcp-sysctl.rst
@@ -7,14 +7,6 @@ MPTCP Sysfs variables
 /proc/sys/net/mptcp/* Variables
 ===============================
 
-enabled - BOOLEAN
-	Control whether MPTCP sockets can be created.
-
-	MPTCP sockets can be created if the value is 1. This is a
-	per-namespace sysctl.
-
-	Default: 1 (enabled)
-
 add_addr_timeout - INTEGER (seconds)
 	Set the timeout after which an ADD_ADDR control message will be
 	resent to an MPTCP peer that has not acknowledged a previous
@@ -25,16 +17,22 @@ add_addr_timeout - INTEGER (seconds)
 
 	Default: 120
 
-close_timeout - INTEGER (seconds)
-	Set the make-after-break timeout: in absence of any close or
-	shutdown syscall, MPTCP sockets will maintain the status
-	unchanged for such time, after the last subflow removal, before
-	moving to TCP_CLOSE.
+allow_join_initial_addr_port - BOOLEAN
+	Allow peers to send join requests to the IP address and port number used
+	by the initial subflow if the value is 1. This controls a flag that is
+	sent to the peer at connection time, and whether such join requests are
+	accepted or denied.
 
-	The default value matches TCP_TIMEWAIT_LEN. This is a per-namespace
-	sysctl.
+	Joins to addresses advertised with ADD_ADDR are not affected by this
+	value.
 
-	Default: 60
+	This is a per-namespace sysctl.
+
+	Default: 1
+
+available_schedulers - STRING
+	Shows the available schedulers choices that are registered. More packet
+	schedulers may be available, but not loaded.
 
 checksum_enabled - BOOLEAN
 	Control whether DSS checksum can be enabled.
@@ -44,18 +42,24 @@ checksum_enabled - BOOLEAN
 
 	Default: 0
 
-allow_join_initial_addr_port - BOOLEAN
-	Allow peers to send join requests to the IP address and port number used
-	by the initial subflow if the value is 1. This controls a flag that is
-	sent to the peer at connection time, and whether such join requests are
-	accepted or denied.
+close_timeout - INTEGER (seconds)
+	Set the make-after-break timeout: in absence of any close or
+	shutdown syscall, MPTCP sockets will maintain the status
+	unchanged for such time, after the last subflow removal, before
+	moving to TCP_CLOSE.
 
-	Joins to addresses advertised with ADD_ADDR are not affected by this
-	value.
+	The default value matches TCP_TIMEWAIT_LEN. This is a per-namespace
+	sysctl.
 
-	This is a per-namespace sysctl.
+	Default: 60
 
-	Default: 1
+enabled - BOOLEAN
+	Control whether MPTCP sockets can be created.
+
+	MPTCP sockets can be created if the value is 1. This is a
+	per-namespace sysctl.
+
+	Default: 1 (enabled)
 
 pm_type - INTEGER
 	Set the default path manager type to use for each new MPTCP
@@ -74,6 +78,14 @@ pm_type - INTEGER
 
 	Default: 0
 
+scheduler - STRING
+	Select the scheduler of your choice.
+
+	Support for selection of different schedulers. This is a per-namespace
+	sysctl.
+
+	Default: "default"
+
 stale_loss_cnt - INTEGER
 	The number of MPTCP-level retransmission intervals with no traffic and
 	pending outstanding data on a given subflow required to declare it stale.
@@ -85,15 +97,3 @@ stale_loss_cnt - INTEGER
 	This is a per-namespace sysctl.
 
 	Default: 4
-
-scheduler - STRING
-	Select the scheduler of your choice.
-
-	Support for selection of different schedulers. This is a per-namespace
-	sysctl.
-
-	Default: "default"
-
-available_schedulers - STRING
-	Shows the available schedulers choices that are registered. More packet
-	schedulers may be available, but not loaded.
-- 
GitLab


From c049275f24de70edd43e521f5a549c9e63165906 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Thu, 30 May 2024 16:07:32 +0200
Subject: [PATCH 670/950] doc: new 'mptcp' page in 'networking'

A general documentation about MPTCP was missing since its introduction
in v5.6.

Most of what is there comes from our recently updated mptcp.dev website,
with additional links to resources from the kernel documentation.

This is a first version, mainly targeting app developers and users.

Link: https://www.mptcp.dev
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://lore.kernel.org/r/20240530-upstream-net-20240520-mptcp-doc-v3-3-e94cdd9f2673@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/networking/index.rst |   1 +
 Documentation/networking/mptcp.rst | 156 +++++++++++++++++++++++++++++
 MAINTAINERS                        |   2 +-
 3 files changed, 158 insertions(+), 1 deletion(-)
 create mode 100644 Documentation/networking/mptcp.rst

diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst
index 7664c0bfe461c..a6443851a1424 100644
--- a/Documentation/networking/index.rst
+++ b/Documentation/networking/index.rst
@@ -72,6 +72,7 @@ Contents:
    mac80211-injection
    mctp
    mpls-sysctl
+   mptcp
    mptcp-sysctl
    multiqueue
    multi-pf-netdev
diff --git a/Documentation/networking/mptcp.rst b/Documentation/networking/mptcp.rst
new file mode 100644
index 0000000000000..17f2bab611644
--- /dev/null
+++ b/Documentation/networking/mptcp.rst
@@ -0,0 +1,156 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=====================
+Multipath TCP (MPTCP)
+=====================
+
+Introduction
+============
+
+Multipath TCP or MPTCP is an extension to the standard TCP and is described in
+`RFC 8684 (MPTCPv1) <https://www.rfc-editor.org/rfc/rfc8684.html>`_. It allows a
+device to make use of multiple interfaces at once to send and receive TCP
+packets over a single MPTCP connection. MPTCP can aggregate the bandwidth of
+multiple interfaces or prefer the one with the lowest latency. It also allows a
+fail-over if one path is down, and the traffic is seamlessly reinjected on other
+paths.
+
+For more details about Multipath TCP in the Linux kernel, please see the
+official website: `mptcp.dev <https://www.mptcp.dev>`_.
+
+
+Use cases
+=========
+
+Thanks to MPTCP, being able to use multiple paths in parallel or simultaneously
+brings new use-cases, compared to TCP:
+
+- Seamless handovers: switching from one path to another while preserving
+  established connections, e.g. to be used in mobility use-cases, like on
+  smartphones.
+- Best network selection: using the "best" available path depending on some
+  conditions, e.g. latency, losses, cost, bandwidth, etc.
+- Network aggregation: using multiple paths at the same time to have a higher
+  throughput, e.g. to combine fixed and mobile networks to send files faster.
+
+
+Concepts
+========
+
+Technically, when a new socket is created with the ``IPPROTO_MPTCP`` protocol
+(Linux-specific), a *subflow* (or *path*) is created. This *subflow* consists of
+a regular TCP connection that is used to transmit data through one interface.
+Additional *subflows* can be negotiated later between the hosts. For the remote
+host to be able to detect the use of MPTCP, a new field is added to the TCP
+*option* field of the underlying TCP *subflow*. This field contains, amongst
+other things, a ``MP_CAPABLE`` option that tells the other host to use MPTCP if
+it is supported. If the remote host or any middlebox in between does not support
+it, the returned ``SYN+ACK`` packet will not contain MPTCP options in the TCP
+*option* field. In that case, the connection will be "downgraded" to plain TCP,
+and it will continue with a single path.
+
+This behavior is made possible by two internal components: the path manager, and
+the packet scheduler.
+
+Path Manager
+------------
+
+The Path Manager is in charge of *subflows*, from creation to deletion, and also
+address announcements. Typically, it is the client side that initiates subflows,
+and the server side that announces additional addresses via the ``ADD_ADDR`` and
+``REMOVE_ADDR`` options.
+
+Path managers are controlled by the ``net.mptcp.pm_type`` sysctl knob -- see
+mptcp-sysctl.rst. There are two types: the in-kernel one (type ``0``) where the
+same rules are applied for all the connections (see: ``ip mptcp``) ; and the
+userspace one (type ``1``), controlled by a userspace daemon (i.e. `mptcpd
+<https://mptcpd.mptcp.dev/>`_) where different rules can be applied for each
+connection. The path managers can be controlled via a Netlink API; see
+netlink_spec/mptcp_pm.rst.
+
+To be able to use multiple IP addresses on a host to create multiple *subflows*
+(paths), the default in-kernel MPTCP path-manager needs to know which IP
+addresses can be used. This can be configured with ``ip mptcp endpoint`` for
+example.
+
+Packet Scheduler
+----------------
+
+The Packet Scheduler is in charge of selecting which available *subflow(s)* to
+use to send the next data packet. It can decide to maximize the use of the
+available bandwidth, only to pick the path with the lower latency, or any other
+policy depending on the configuration.
+
+Packet schedulers are controlled by the ``net.mptcp.scheduler`` sysctl knob --
+see mptcp-sysctl.rst.
+
+
+Sockets API
+===========
+
+Creating MPTCP sockets
+----------------------
+
+On Linux, MPTCP can be used by selecting MPTCP instead of TCP when creating the
+``socket``:
+
+.. code-block:: C
+
+    int sd = socket(AF_INET(6), SOCK_STREAM, IPPROTO_MPTCP);
+
+Note that ``IPPROTO_MPTCP`` is defined as ``262``.
+
+If MPTCP is not supported, ``errno`` will be set to:
+
+- ``EINVAL``: (*Invalid argument*): MPTCP is not available, on kernels < 5.6.
+- ``EPROTONOSUPPORT`` (*Protocol not supported*): MPTCP has not been compiled,
+  on kernels >= v5.6.
+- ``ENOPROTOOPT`` (*Protocol not available*): MPTCP has been disabled using
+  ``net.mptcp.enabled`` sysctl knob; see mptcp-sysctl.rst.
+
+MPTCP is then opt-in: applications need to explicitly request it. Note that
+applications can be forced to use MPTCP with different techniques, e.g.
+``LD_PRELOAD`` (see ``mptcpize``), eBPF (see ``mptcpify``), SystemTAP,
+``GODEBUG`` (``GODEBUG=multipathtcp=1``), etc.
+
+Switching to ``IPPROTO_MPTCP`` instead of ``IPPROTO_TCP`` should be as
+transparent as possible for the userspace applications.
+
+Socket options
+--------------
+
+MPTCP supports most socket options handled by TCP. It is possible some less
+common options are not supported, but contributions are welcome.
+
+Generally, the same value is propagated to all subflows, including the ones
+created after the calls to ``setsockopt()``. eBPF can be used to set different
+values per subflow.
+
+There are some MPTCP specific socket options at the ``SOL_MPTCP`` (284) level to
+retrieve info. They fill the ``optval`` buffer of the ``getsockopt()`` system
+call:
+
+- ``MPTCP_INFO``: Uses ``struct mptcp_info``.
+- ``MPTCP_TCPINFO``: Uses ``struct mptcp_subflow_data``, followed by an array of
+  ``struct tcp_info``.
+- ``MPTCP_SUBFLOW_ADDRS``: Uses ``struct mptcp_subflow_data``, followed by an
+  array of ``mptcp_subflow_addrs``.
+- ``MPTCP_FULL_INFO``: Uses ``struct mptcp_full_info``, with one pointer to an
+  array of ``struct mptcp_subflow_info`` (including the
+  ``struct mptcp_subflow_addrs``), and one pointer to an array of
+  ``struct tcp_info``, followed by the content of ``struct mptcp_info``.
+
+Note that at the TCP level, ``TCP_IS_MPTCP`` socket option can be used to know
+if MPTCP is currently being used: the value will be set to 1 if it is.
+
+
+Design choices
+==============
+
+A new socket type has been added for MPTCP for the userspace-facing socket. The
+kernel is in charge of creating subflow sockets: they are TCP sockets where the
+behavior is modified using TCP-ULP.
+
+MPTCP listen sockets will create "plain" *accepted* TCP sockets if the
+connection request from the client didn't ask for MPTCP, making the performance
+impact minimal when MPTCP is enabled by default.
diff --git a/MAINTAINERS b/MAINTAINERS
index ba231d2f3a4e5..7538152be2f1a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15753,7 +15753,7 @@ B:	https://github.com/multipath-tcp/mptcp_net-next/issues
 T:	git https://github.com/multipath-tcp/mptcp_net-next.git export-net
 T:	git https://github.com/multipath-tcp/mptcp_net-next.git export
 F:	Documentation/netlink/specs/mptcp_pm.yaml
-F:	Documentation/networking/mptcp-sysctl.rst
+F:	Documentation/networking/mptcp*.rst
 F:	include/net/mptcp.h
 F:	include/trace/events/mptcp.h
 F:	include/uapi/linux/mptcp*.h
-- 
GitLab


From 73451e9aaa24e8e44cb91e5fd6b59bf53e069c1f Mon Sep 17 00:00:00 2001
From: Abhishek Chauhan <quic_abchauha@quicinc.com>
Date: Wed, 29 May 2024 11:31:30 -0700
Subject: [PATCH 671/950] net: validate SO_TXTIME clockid coming from userspace

Currently there are no strict checks while setting SO_TXTIME
from userspace. With the recent development in skb->tstamp_type
clockid with unsupported clocks results in warn_on_once, which causes
unnecessary aborts in some systems which enables panic on warns.

Add validation in setsockopt to support only CLOCK_REALTIME,
CLOCK_MONOTONIC and CLOCK_TAI to be set from userspace.

Link: https://lore.kernel.org/netdev/bc037db4-58bb-4861-ac31-a361a93841d3@linux.dev/
Link: https://lore.kernel.org/lkml/6bdba7b6-fd22-4ea5-a356-12268674def1@quicinc.com/
Fixes: 1693c5db6ab8 ("net: Add additional bit to support clockid_t timestamp type")
Reported-by: syzbot+d7b227731ec589e7f4f0@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=d7b227731ec589e7f4f0
Reported-by: syzbot+30a35a2e9c5067cc43fa@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=30a35a2e9c5067cc43fa
Signed-off-by: Abhishek Chauhan <quic_abchauha@quicinc.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://lore.kernel.org/r/20240529183130.1717083-1-quic_abchauha@quicinc.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/sock.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/net/core/sock.c b/net/core/sock.c
index 521e6373d4f73..69baddcfbd8c1 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1083,6 +1083,17 @@ bool sockopt_capable(int cap)
 }
 EXPORT_SYMBOL(sockopt_capable);
 
+static int sockopt_validate_clockid(__kernel_clockid_t value)
+{
+	switch (value) {
+	case CLOCK_REALTIME:
+	case CLOCK_MONOTONIC:
+	case CLOCK_TAI:
+		return 0;
+	}
+	return -EINVAL;
+}
+
 /*
  *	This is meant for all protocols to use and covers goings on
  *	at the socket level. Everything here is generic.
@@ -1497,6 +1508,11 @@ set_sndbuf:
 			ret = -EPERM;
 			break;
 		}
+
+		ret = sockopt_validate_clockid(sk_txtime.clockid);
+		if (ret)
+			break;
+
 		sock_valbool_flag(sk, SOCK_TXTIME, true);
 		sk->sk_clockid = sk_txtime.clockid;
 		sk->sk_txtime_deadline_mode =
-- 
GitLab


From 3c34fb0bd4a4237592c5ecb5b2e2531900c55774 Mon Sep 17 00:00:00 2001
From: Lars Kellogg-Stedman <lars@oddbit.com>
Date: Wed, 29 May 2024 17:02:43 -0400
Subject: [PATCH 672/950] ax25: Fix refcount imbalance on inbound connections

When releasing a socket in ax25_release(), we call netdev_put() to
decrease the refcount on the associated ax.25 device. However, the
execution path for accepting an incoming connection never calls
netdev_hold(). This imbalance leads to refcount errors, and ultimately
to kernel crashes.

A typical call trace for the above situation will start with one of the
following errors:

    refcount_t: decrement hit 0; leaking memory.
    refcount_t: underflow; use-after-free.

And will then have a trace like:

    Call Trace:
    <TASK>
    ? show_regs+0x64/0x70
    ? __warn+0x83/0x120
    ? refcount_warn_saturate+0xb2/0x100
    ? report_bug+0x158/0x190
    ? prb_read_valid+0x20/0x30
    ? handle_bug+0x3e/0x70
    ? exc_invalid_op+0x1c/0x70
    ? asm_exc_invalid_op+0x1f/0x30
    ? refcount_warn_saturate+0xb2/0x100
    ? refcount_warn_saturate+0xb2/0x100
    ax25_release+0x2ad/0x360
    __sock_release+0x35/0xa0
    sock_close+0x19/0x20
    [...]

On reboot (or any attempt to remove the interface), the kernel gets
stuck in an infinite loop:

    unregister_netdevice: waiting for ax0 to become free. Usage count = 0

This patch corrects these issues by ensuring that we call netdev_hold()
and ax25_dev_hold() for new connections in ax25_accept(). This makes the
logic leading to ax25_accept() match the logic for ax25_bind(): in both
cases we increment the refcount, which is ultimately decremented in
ax25_release().

Fixes: 9fd75b66b8f6 ("ax25: Fix refcount leaks caused by ax25_cb_del()")
Signed-off-by: Lars Kellogg-Stedman <lars@oddbit.com>
Tested-by: Duoming Zhou <duoming@zju.edu.cn>
Tested-by: Dan Cross <crossd@gmail.com>
Tested-by: Chris Maness <christopher.maness@gmail.com>
Reviewed-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://lore.kernel.org/r/20240529210242.3346844-2-lars@oddbit.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ax25/af_ax25.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index 8077cf2ee4480..d6f9fae06a9d8 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -1378,8 +1378,10 @@ static int ax25_accept(struct socket *sock, struct socket *newsock,
 {
 	struct sk_buff *skb;
 	struct sock *newsk;
+	ax25_dev *ax25_dev;
 	DEFINE_WAIT(wait);
 	struct sock *sk;
+	ax25_cb *ax25;
 	int err = 0;
 
 	if (sock->state != SS_UNCONNECTED)
@@ -1434,6 +1436,10 @@ static int ax25_accept(struct socket *sock, struct socket *newsock,
 	kfree_skb(skb);
 	sk_acceptq_removed(sk);
 	newsock->state = SS_CONNECTED;
+	ax25 = sk_to_ax25(newsk);
+	ax25_dev = ax25->ax25_dev;
+	netdev_hold(ax25_dev->dev, &ax25->dev_tracker, GFP_ATOMIC);
+	ax25_dev_hold(ax25_dev);
 
 out:
 	release_sock(sk);
-- 
GitLab


From 166fcf86cd34e15c7f383eda4642d7a212393008 Mon Sep 17 00:00:00 2001
From: Duoming Zhou <duoming@zju.edu.cn>
Date: Thu, 30 May 2024 13:17:33 +0800
Subject: [PATCH 673/950] ax25: Replace kfree() in ax25_dev_free() with
 ax25_dev_put()

The object "ax25_dev" is managed by reference counting. Thus it should
not be directly released by kfree(), replace with ax25_dev_put().

Fixes: d01ffb9eee4a ("ax25: add refcount in ax25_dev to avoid UAF bugs")
Suggested-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Duoming Zhou <duoming@zju.edu.cn>
Reviewed-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://lore.kernel.org/r/20240530051733.11416-1-duoming@zju.edu.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ax25/ax25_dev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ax25/ax25_dev.c b/net/ax25/ax25_dev.c
index 742d7c68e7e7e..9efd6690b3443 100644
--- a/net/ax25/ax25_dev.c
+++ b/net/ax25/ax25_dev.c
@@ -196,7 +196,7 @@ void __exit ax25_dev_free(void)
 	list_for_each_entry_safe(s, n, &ax25_dev_list, list) {
 		netdev_put(s->dev, &s->dev_tracker);
 		list_del(&s->list);
-		kfree(s);
+		ax25_dev_put(s);
 	}
 	spin_unlock_bh(&ax25_dev_lock);
 }
-- 
GitLab


From d551d075b043821880b8afc0010ef70d050716d0 Mon Sep 17 00:00:00 2001
From: Karol Kolacinski <karol.kolacinski@intel.com>
Date: Tue, 28 May 2024 16:03:51 -0700
Subject: [PATCH 674/950] ice: Introduce ice_ptp_hw struct

Create new ice_ptp_hw struct and use it for all HW and PTP-related
fields from struct ice_hw.
Replace definitions with struct fields, which values are set accordingly
to a specific device.

Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Arkadiusz Kubalewski <arkadiusz.kubalewski@intel.com>
Signed-off-by: Karol Kolacinski <karol.kolacinski@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20240528-next-2024-05-28-ptp-refactors-v1-1-c082739bb6f6@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/ice/ice_common.c |  24 ++++
 drivers/net/ethernet/intel/ice/ice_common.h |   1 +
 drivers/net/ethernet/intel/ice/ice_ptp.c    |  22 ++--
 drivers/net/ethernet/intel/ice/ice_ptp_hw.c | 134 ++++++++++++--------
 drivers/net/ethernet/intel/ice/ice_ptp_hw.h |   4 +-
 drivers/net/ethernet/intel/ice/ice_type.h   |  17 ++-
 6 files changed, 126 insertions(+), 76 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index 24716a3b494cd..61eb6af37f8e2 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -239,6 +239,30 @@ bool ice_is_e810t(struct ice_hw *hw)
 	return false;
 }
 
+/**
+ * ice_is_e822 - Check if a device is E822 family device
+ * @hw: pointer to the hardware structure
+ *
+ * Return: true if the device is E822 based, false if not.
+ */
+bool ice_is_e822(struct ice_hw *hw)
+{
+	switch (hw->device_id) {
+	case ICE_DEV_ID_E822C_BACKPLANE:
+	case ICE_DEV_ID_E822C_QSFP:
+	case ICE_DEV_ID_E822C_SFP:
+	case ICE_DEV_ID_E822C_10G_BASE_T:
+	case ICE_DEV_ID_E822C_SGMII:
+	case ICE_DEV_ID_E822L_BACKPLANE:
+	case ICE_DEV_ID_E822L_SFP:
+	case ICE_DEV_ID_E822L_10G_BASE_T:
+	case ICE_DEV_ID_E822L_SGMII:
+		return true;
+	default:
+		return false;
+	}
+}
+
 /**
  * ice_is_e823
  * @hw: pointer to the hardware structure
diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h
index ffb22c7ce28b7..70f57340eb0df 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.h
+++ b/drivers/net/ethernet/intel/ice/ice_common.h
@@ -249,6 +249,7 @@ void
 ice_stat_update32(struct ice_hw *hw, u32 reg, bool prev_stat_loaded,
 		  u64 *prev_stat, u64 *cur_stat);
 bool ice_is_e810t(struct ice_hw *hw);
+bool ice_is_e822(struct ice_hw *hw);
 bool ice_is_e823(struct ice_hw *hw);
 bool ice_is_e825c(struct ice_hw *hw);
 int
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c
index 0f17fc1181d28..cca9d09b2d61f 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.c
@@ -813,7 +813,7 @@ static enum ice_tx_tstamp_work ice_ptp_tx_tstamp_owner(struct ice_pf *pf)
 	}
 	mutex_unlock(&pf->ptp.ports_owner.lock);
 
-	for (i = 0; i < ICE_MAX_QUAD; i++) {
+	for (i = 0; i < ICE_GET_QUAD_NUM(pf->hw.ptp.num_lports); i++) {
 		u64 tstamp_ready;
 		int err;
 
@@ -1027,7 +1027,7 @@ ice_ptp_release_tx_tracker(struct ice_pf *pf, struct ice_ptp_tx *tx)
 static int
 ice_ptp_init_tx_e82x(struct ice_pf *pf, struct ice_ptp_tx *tx, u8 port)
 {
-	tx->block = port / ICE_PORTS_PER_QUAD;
+	tx->block = ICE_GET_QUAD_NUM(port);
 	tx->offset = (port % ICE_PORTS_PER_QUAD) * INDEX_PER_PORT_E82X;
 	tx->len = INDEX_PER_PORT_E82X;
 	tx->has_ready_bitmap = 1;
@@ -1229,8 +1229,8 @@ static u64 ice_base_incval(struct ice_pf *pf)
  */
 static int ice_ptp_check_tx_fifo(struct ice_ptp_port *port)
 {
-	int quad = port->port_num / ICE_PORTS_PER_QUAD;
 	int offs = port->port_num % ICE_PORTS_PER_QUAD;
+	int quad = ICE_GET_QUAD_NUM(port->port_num);
 	struct ice_pf *pf;
 	struct ice_hw *hw;
 	u32 val, phy_sts;
@@ -1429,7 +1429,7 @@ void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup)
 	if (pf->ptp.state != ICE_PTP_READY)
 		return;
 
-	if (WARN_ON_ONCE(port >= ICE_NUM_EXTERNAL_PORTS))
+	if (WARN_ON_ONCE(port >= hw->ptp.num_lports))
 		return;
 
 	ptp_port = &pf->ptp.port;
@@ -1439,7 +1439,7 @@ void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup)
 	/* Update cached link status for this port immediately */
 	ptp_port->link_up = linkup;
 
-	switch (hw->phy_model) {
+	switch (hw->ptp.phy_model) {
 	case ICE_PHY_E810:
 		/* Do not reconfigure E810 PHY */
 		return;
@@ -1468,7 +1468,7 @@ static int ice_ptp_cfg_phy_interrupt(struct ice_pf *pf, bool ena, u32 threshold)
 
 	ice_ptp_reset_ts_memory(hw);
 
-	for (quad = 0; quad < ICE_MAX_QUAD; quad++) {
+	for (quad = 0; quad < ICE_GET_QUAD_NUM(hw->ptp.num_lports); quad++) {
 		err = ice_read_quad_reg_e82x(hw, quad, Q_REG_TX_MEM_GBL_CFG,
 					     &val);
 		if (err)
@@ -1953,7 +1953,7 @@ ice_ptp_settime64(struct ptp_clock_info *info, const struct timespec64 *ts)
 	ice_ptp_enable_all_clkout(pf);
 
 	/* Recalibrate and re-enable timestamp blocks for E822/E823 */
-	if (hw->phy_model == ICE_PHY_E82X)
+	if (hw->ptp.phy_model == ICE_PHY_E82X)
 		ice_ptp_restart_all_phy(pf);
 exit:
 	if (err) {
@@ -2578,7 +2578,7 @@ static void ice_ptp_maybe_trigger_tx_interrupt(struct ice_pf *pf)
 	if (!ice_pf_src_tmr_owned(pf))
 		return;
 
-	for (i = 0; i < ICE_MAX_QUAD; i++) {
+	for (i = 0; i < ICE_GET_QUAD_NUM(hw->ptp.num_lports); i++) {
 		u64 tstamp_ready;
 		int err;
 
@@ -3076,7 +3076,7 @@ static int ice_ptp_init_port(struct ice_pf *pf, struct ice_ptp_port *ptp_port)
 
 	mutex_init(&ptp_port->ps_lock);
 
-	switch (hw->phy_model) {
+	switch (hw->ptp.phy_model) {
 	case ICE_PHY_E810:
 		return ice_ptp_init_tx_e810(pf, &ptp_port->tx);
 	case ICE_PHY_E82X:
@@ -3171,7 +3171,7 @@ static void ice_ptp_remove_auxbus_device(struct ice_pf *pf)
  */
 static void ice_ptp_init_tx_interrupt_mode(struct ice_pf *pf)
 {
-	switch (pf->hw.phy_model) {
+	switch (pf->hw.ptp.phy_model) {
 	case ICE_PHY_E82X:
 		/* E822 based PHY has the clock owner process the interrupt
 		 * for all ports.
@@ -3207,7 +3207,7 @@ void ice_ptp_init(struct ice_pf *pf)
 
 	ptp->state = ICE_PTP_INITIALIZING;
 
-	ice_ptp_init_phy_model(hw);
+	ice_ptp_init_hw(hw);
 
 	ice_ptp_init_tx_interrupt_mode(pf);
 
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
index 2b9423a173bba..22fca17a5a3cb 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
@@ -288,18 +288,21 @@ static void ice_ptp_exec_tmr_cmd(struct ice_hw *hw)
 
 /**
  * ice_fill_phy_msg_e82x - Fill message data for a PHY register access
+ * @hw: pointer to the HW struct
  * @msg: the PHY message buffer to fill in
  * @port: the port to access
  * @offset: the register offset
  */
-static void
-ice_fill_phy_msg_e82x(struct ice_sbq_msg_input *msg, u8 port, u16 offset)
+static void ice_fill_phy_msg_e82x(struct ice_hw *hw,
+				  struct ice_sbq_msg_input *msg, u8 port,
+				  u16 offset)
 {
 	int phy_port, phy, quadtype;
 
-	phy_port = port % ICE_PORTS_PER_PHY_E82X;
-	phy = port / ICE_PORTS_PER_PHY_E82X;
-	quadtype = (port / ICE_PORTS_PER_QUAD) % ICE_QUADS_PER_PHY_E82X;
+	phy_port = port % hw->ptp.ports_per_phy;
+	phy = port / hw->ptp.ports_per_phy;
+	quadtype = ICE_GET_QUAD_NUM(port) %
+		   ICE_GET_QUAD_NUM(hw->ptp.ports_per_phy);
 
 	if (quadtype == 0) {
 		msg->msg_addr_low = P_Q0_L(P_0_BASE + offset, phy_port);
@@ -430,7 +433,7 @@ ice_read_phy_reg_e82x(struct ice_hw *hw, u8 port, u16 offset, u32 *val)
 	struct ice_sbq_msg_input msg = {0};
 	int err;
 
-	ice_fill_phy_msg_e82x(&msg, port, offset);
+	ice_fill_phy_msg_e82x(hw, &msg, port, offset);
 	msg.opcode = ice_sbq_msg_rd;
 
 	err = ice_sbq_rw_reg(hw, &msg);
@@ -507,7 +510,7 @@ ice_write_phy_reg_e82x(struct ice_hw *hw, u8 port, u16 offset, u32 val)
 	struct ice_sbq_msg_input msg = {0};
 	int err;
 
-	ice_fill_phy_msg_e82x(&msg, port, offset);
+	ice_fill_phy_msg_e82x(hw, &msg, port, offset);
 	msg.opcode = ice_sbq_msg_wr;
 	msg.data = val;
 
@@ -617,24 +620,30 @@ ice_write_64b_phy_reg_e82x(struct ice_hw *hw, u8 port, u16 low_addr, u64 val)
 
 /**
  * ice_fill_quad_msg_e82x - Fill message data for quad register access
+ * @hw: pointer to the HW struct
  * @msg: the PHY message buffer to fill in
  * @quad: the quad to access
  * @offset: the register offset
  *
  * Fill a message buffer for accessing a register in a quad shared between
  * multiple PHYs.
+ *
+ * Return:
+ * * %0       - OK
+ * * %-EINVAL - invalid quad number
  */
-static int
-ice_fill_quad_msg_e82x(struct ice_sbq_msg_input *msg, u8 quad, u16 offset)
+static int ice_fill_quad_msg_e82x(struct ice_hw *hw,
+				  struct ice_sbq_msg_input *msg, u8 quad,
+				  u16 offset)
 {
 	u32 addr;
 
-	if (quad >= ICE_MAX_QUAD)
+	if (quad >= ICE_GET_QUAD_NUM(hw->ptp.num_lports))
 		return -EINVAL;
 
 	msg->dest_dev = rmn_0;
 
-	if ((quad % ICE_QUADS_PER_PHY_E82X) == 0)
+	if (!(quad % ICE_GET_QUAD_NUM(hw->ptp.ports_per_phy)))
 		addr = Q_0_BASE + offset;
 	else
 		addr = Q_1_BASE + offset;
@@ -661,7 +670,7 @@ ice_read_quad_reg_e82x(struct ice_hw *hw, u8 quad, u16 offset, u32 *val)
 	struct ice_sbq_msg_input msg = {0};
 	int err;
 
-	err = ice_fill_quad_msg_e82x(&msg, quad, offset);
+	err = ice_fill_quad_msg_e82x(hw, &msg, quad, offset);
 	if (err)
 		return err;
 
@@ -695,7 +704,7 @@ ice_write_quad_reg_e82x(struct ice_hw *hw, u8 quad, u16 offset, u32 val)
 	struct ice_sbq_msg_input msg = {0};
 	int err;
 
-	err = ice_fill_quad_msg_e82x(&msg, quad, offset);
+	err = ice_fill_quad_msg_e82x(hw, &msg, quad, offset);
 	if (err)
 		return err;
 
@@ -816,7 +825,7 @@ static void ice_ptp_reset_ts_memory_e82x(struct ice_hw *hw)
 {
 	unsigned int quad;
 
-	for (quad = 0; quad < ICE_MAX_QUAD; quad++)
+	for (quad = 0; quad < ICE_GET_QUAD_NUM(hw->ptp.num_lports); quad++)
 		ice_ptp_reset_ts_memory_quad_e82x(hw, quad);
 }
 
@@ -1113,7 +1122,7 @@ static int ice_ptp_set_vernier_wl(struct ice_hw *hw)
 {
 	u8 port;
 
-	for (port = 0; port < ICE_NUM_EXTERNAL_PORTS; port++) {
+	for (port = 0; port < hw->ptp.num_lports; port++) {
 		int err;
 
 		err = ice_write_phy_reg_e82x(hw, port, P_REG_WL,
@@ -1178,7 +1187,7 @@ ice_ptp_prep_phy_time_e82x(struct ice_hw *hw, u32 time)
 	 */
 	phy_time = (u64)time << 32;
 
-	for (port = 0; port < ICE_NUM_EXTERNAL_PORTS; port++) {
+	for (port = 0; port < hw->ptp.num_lports; port++) {
 		/* Tx case */
 		err = ice_write_64b_phy_reg_e82x(hw, port,
 						 P_REG_TX_TIMER_INC_PRE_L,
@@ -1281,7 +1290,7 @@ ice_ptp_prep_phy_adj_e82x(struct ice_hw *hw, s32 adj)
 	else
 		cycles = -(((s64)-adj) << 32);
 
-	for (port = 0; port < ICE_NUM_EXTERNAL_PORTS; port++) {
+	for (port = 0; port < hw->ptp.num_lports; port++) {
 		int err;
 
 		err = ice_ptp_prep_port_adj_e82x(hw, port, cycles);
@@ -1307,7 +1316,7 @@ ice_ptp_prep_phy_incval_e82x(struct ice_hw *hw, u64 incval)
 	int err;
 	u8 port;
 
-	for (port = 0; port < ICE_NUM_EXTERNAL_PORTS; port++) {
+	for (port = 0; port < hw->ptp.num_lports; port++) {
 		err = ice_write_40b_phy_reg_e82x(hw, port, P_REG_TIMETUS_L,
 						 incval);
 		if (err)
@@ -1463,7 +1472,7 @@ ice_ptp_one_port_cmd(struct ice_hw *hw, u8 configured_port,
 {
 	u8 port;
 
-	for (port = 0; port < ICE_NUM_EXTERNAL_PORTS; port++) {
+	for (port = 0; port < hw->ptp.num_lports; port++) {
 		enum ice_ptp_tmr_cmd cmd;
 		int err;
 
@@ -1493,7 +1502,7 @@ ice_ptp_port_cmd_e82x(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd)
 {
 	u8 port;
 
-	for (port = 0; port < ICE_NUM_EXTERNAL_PORTS; port++) {
+	for (port = 0; port < hw->ptp.num_lports; port++) {
 		int err;
 
 		err = ice_ptp_write_port_cmd_e82x(hw, port, cmd);
@@ -1606,7 +1615,7 @@ static void ice_phy_cfg_lane_e82x(struct ice_hw *hw, u8 port)
 		return;
 	}
 
-	quad = port / ICE_PORTS_PER_QUAD;
+	quad = ICE_GET_QUAD_NUM(port);
 
 	err = ice_read_quad_reg_e82x(hw, quad, Q_REG_TX_MEM_GBL_CFG, &val);
 	if (err) {
@@ -2636,6 +2645,17 @@ ice_get_phy_tx_tstamp_ready_e82x(struct ice_hw *hw, u8 quad, u64 *tstamp_ready)
 	return 0;
 }
 
+/**
+ * ice_ptp_init_phy_e82x - initialize PHY parameters
+ * @ptp: pointer to the PTP HW struct
+ */
+static void ice_ptp_init_phy_e82x(struct ice_ptp_hw *ptp)
+{
+	ptp->phy_model = ICE_PHY_E82X;
+	ptp->num_lports = 8;
+	ptp->ports_per_phy = 8;
+}
+
 /* E810 functions
  *
  * The following functions operate on the E810 series devices which use
@@ -2863,17 +2883,21 @@ static int ice_clear_phy_tstamp_e810(struct ice_hw *hw, u8 lport, u8 idx)
 }
 
 /**
- * ice_ptp_init_phy_e810 - Enable PTP function on the external PHY
+ * ice_ptp_init_phc_e810 - Perform E810 specific PHC initialization
  * @hw: pointer to HW struct
  *
- * Enable the timesync PTP functionality for the external PHY connected to
- * this function.
+ * Perform E810-specific PTP hardware clock initialization steps.
+ *
+ * Return: 0 on success, other error codes when failed to initialize TimeSync
  */
-int ice_ptp_init_phy_e810(struct ice_hw *hw)
+static int ice_ptp_init_phc_e810(struct ice_hw *hw)
 {
 	u8 tmr_idx;
 	int err;
 
+	/* Ensure synchronization delay is zero */
+	wr32(hw, GLTSYN_SYNC_DLAY, 0);
+
 	tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned;
 	err = ice_write_phy_reg_e810(hw, ETH_GLTSYN_ENA(tmr_idx),
 				     GLTSYN_ENA_TSYN_ENA_M);
@@ -2884,21 +2908,6 @@ int ice_ptp_init_phy_e810(struct ice_hw *hw)
 	return err;
 }
 
-/**
- * ice_ptp_init_phc_e810 - Perform E810 specific PHC initialization
- * @hw: pointer to HW struct
- *
- * Perform E810-specific PTP hardware clock initialization steps.
- */
-static int ice_ptp_init_phc_e810(struct ice_hw *hw)
-{
-	/* Ensure synchronization delay is zero */
-	wr32(hw, GLTSYN_SYNC_DLAY, 0);
-
-	/* Initialize the PHY */
-	return ice_ptp_init_phy_e810(hw);
-}
-
 /**
  * ice_ptp_prep_phy_time_e810 - Prepare PHY port with initial time
  * @hw: Board private structure
@@ -3242,6 +3251,17 @@ int ice_read_pca9575_reg_e810t(struct ice_hw *hw, u8 offset, u8 *data)
 	return ice_aq_read_i2c(hw, link_topo, 0, addr, 1, data, NULL);
 }
 
+/**
+ * ice_ptp_init_phy_e810 - initialize PHY parameters
+ * @ptp: pointer to the PTP HW struct
+ */
+static void ice_ptp_init_phy_e810(struct ice_ptp_hw *ptp)
+{
+	ptp->phy_model = ICE_PHY_E810;
+	ptp->num_lports = 8;
+	ptp->ports_per_phy = 4;
+}
+
 /* Device agnostic functions
  *
  * The following functions implement shared behavior common to both E822 and
@@ -3299,18 +3319,22 @@ void ice_ptp_unlock(struct ice_hw *hw)
 }
 
 /**
- * ice_ptp_init_phy_model - Initialize hw->phy_model based on device type
+ * ice_ptp_init_hw - Initialize hw based on device type
  * @hw: pointer to the HW structure
  *
- * Determine the PHY model for the device, and initialize hw->phy_model
+ * Determine the PHY model for the device, and initialize hw
  * for use by other functions.
  */
-void ice_ptp_init_phy_model(struct ice_hw *hw)
+void ice_ptp_init_hw(struct ice_hw *hw)
 {
-	if (ice_is_e810(hw))
-		hw->phy_model = ICE_PHY_E810;
+	struct ice_ptp_hw *ptp = &hw->ptp;
+
+	if (ice_is_e822(hw) || ice_is_e823(hw))
+		ice_ptp_init_phy_e82x(ptp);
+	else if (ice_is_e810(hw))
+		ice_ptp_init_phy_e810(ptp);
 	else
-		hw->phy_model = ICE_PHY_E82X;
+		ptp->phy_model = ICE_PHY_UNSUP;
 }
 
 /**
@@ -3331,7 +3355,7 @@ static int ice_ptp_tmr_cmd(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd)
 	ice_ptp_src_cmd(hw, cmd);
 
 	/* Next, prepare the ports */
-	switch (hw->phy_model) {
+	switch (hw->ptp.phy_model) {
 	case ICE_PHY_E810:
 		err = ice_ptp_port_cmd_e810(hw, cmd);
 		break;
@@ -3383,7 +3407,7 @@ int ice_ptp_init_time(struct ice_hw *hw, u64 time)
 
 	/* PHY timers */
 	/* Fill Rx and Tx ports and send msg to PHY */
-	switch (hw->phy_model) {
+	switch (hw->ptp.phy_model) {
 	case ICE_PHY_E810:
 		err = ice_ptp_prep_phy_time_e810(hw, time & 0xFFFFFFFF);
 		break;
@@ -3425,7 +3449,7 @@ int ice_ptp_write_incval(struct ice_hw *hw, u64 incval)
 	wr32(hw, GLTSYN_SHADJ_L(tmr_idx), lower_32_bits(incval));
 	wr32(hw, GLTSYN_SHADJ_H(tmr_idx), upper_32_bits(incval));
 
-	switch (hw->phy_model) {
+	switch (hw->ptp.phy_model) {
 	case ICE_PHY_E810:
 		err = ice_ptp_prep_phy_incval_e810(hw, incval);
 		break;
@@ -3491,7 +3515,7 @@ int ice_ptp_adj_clock(struct ice_hw *hw, s32 adj)
 	wr32(hw, GLTSYN_SHADJ_L(tmr_idx), 0);
 	wr32(hw, GLTSYN_SHADJ_H(tmr_idx), adj);
 
-	switch (hw->phy_model) {
+	switch (hw->ptp.phy_model) {
 	case ICE_PHY_E810:
 		err = ice_ptp_prep_phy_adj_e810(hw, adj);
 		break;
@@ -3521,7 +3545,7 @@ int ice_ptp_adj_clock(struct ice_hw *hw, s32 adj)
  */
 int ice_read_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx, u64 *tstamp)
 {
-	switch (hw->phy_model) {
+	switch (hw->ptp.phy_model) {
 	case ICE_PHY_E810:
 		return ice_read_phy_tstamp_e810(hw, block, idx, tstamp);
 	case ICE_PHY_E82X:
@@ -3549,7 +3573,7 @@ int ice_read_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx, u64 *tstamp)
  */
 int ice_clear_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx)
 {
-	switch (hw->phy_model) {
+	switch (hw->ptp.phy_model) {
 	case ICE_PHY_E810:
 		return ice_clear_phy_tstamp_e810(hw, block, idx);
 	case ICE_PHY_E82X:
@@ -3610,7 +3634,7 @@ static int ice_get_pf_c827_idx(struct ice_hw *hw, u8 *idx)
  */
 void ice_ptp_reset_ts_memory(struct ice_hw *hw)
 {
-	switch (hw->phy_model) {
+	switch (hw->ptp.phy_model) {
 	case ICE_PHY_E82X:
 		ice_ptp_reset_ts_memory_e82x(hw);
 		break;
@@ -3636,7 +3660,7 @@ int ice_ptp_init_phc(struct ice_hw *hw)
 	/* Clear event err indications for auxiliary pins */
 	(void)rd32(hw, GLTSYN_STAT(src_idx));
 
-	switch (hw->phy_model) {
+	switch (hw->ptp.phy_model) {
 	case ICE_PHY_E810:
 		return ice_ptp_init_phc_e810(hw);
 	case ICE_PHY_E82X:
@@ -3659,7 +3683,7 @@ int ice_ptp_init_phc(struct ice_hw *hw)
  */
 int ice_get_phy_tx_tstamp_ready(struct ice_hw *hw, u8 block, u64 *tstamp_ready)
 {
-	switch (hw->phy_model) {
+	switch (hw->ptp.phy_model) {
 	case ICE_PHY_E810:
 		return ice_get_phy_tx_tstamp_ready_e810(hw, block,
 							tstamp_ready);
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
index 1f3e031244308..3dce09af0d78a 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
@@ -212,6 +212,7 @@ int ice_read_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx, u64 *tstamp);
 int ice_clear_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx);
 void ice_ptp_reset_ts_memory(struct ice_hw *hw);
 int ice_ptp_init_phc(struct ice_hw *hw);
+void ice_ptp_init_hw(struct ice_hw *hw);
 int ice_get_phy_tx_tstamp_ready(struct ice_hw *hw, u8 block, u64 *tstamp_ready);
 
 /* E822 family functions */
@@ -266,7 +267,6 @@ int ice_phy_cfg_tx_offset_e82x(struct ice_hw *hw, u8 port);
 int ice_phy_cfg_rx_offset_e82x(struct ice_hw *hw, u8 port);
 
 /* E810 family functions */
-int ice_ptp_init_phy_e810(struct ice_hw *hw);
 int ice_read_sma_ctrl_e810t(struct ice_hw *hw, u8 *data);
 int ice_write_sma_ctrl_e810t(struct ice_hw *hw, u8 data);
 int ice_read_pca9575_reg_e810t(struct ice_hw *hw, u8 offset, u8 *data);
@@ -280,8 +280,6 @@ int ice_get_cgu_state(struct ice_hw *hw, u8 dpll_idx,
 		      u8 *ref_state, u8 *eec_mode, s64 *phase_offset,
 		      enum dpll_lock_status *dpll_state);
 int ice_get_cgu_rclk_pin_info(struct ice_hw *hw, u8 *base_idx, u8 *pin_num);
-
-void ice_ptp_init_phy_model(struct ice_hw *hw);
 int ice_cgu_get_output_pin_state_caps(struct ice_hw *hw, u8 pin_id,
 				      unsigned long *caps);
 
diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h
index f0796a93f4287..2d2af80a65a9d 100644
--- a/drivers/net/ethernet/intel/ice/ice_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_type.h
@@ -818,6 +818,9 @@ struct ice_mbx_data {
 	u16 async_watermark_val;
 };
 
+#define ICE_PORTS_PER_QUAD	4
+#define ICE_GET_QUAD_NUM(port) ((port) / ICE_PORTS_PER_QUAD)
+
 /* PHY model */
 enum ice_phy_model {
 	ICE_PHY_UNSUP = -1,
@@ -825,6 +828,12 @@ enum ice_phy_model {
 	ICE_PHY_E82X,
 };
 
+struct ice_ptp_hw {
+	enum ice_phy_model phy_model;
+	u8 num_lports;
+	u8 ports_per_phy;
+};
+
 /* Port hardware description */
 struct ice_hw {
 	u8 __iomem *hw_addr;
@@ -846,7 +855,6 @@ struct ice_hw {
 	u8 revision_id;
 
 	u8 pf_id;		/* device profile info */
-	enum ice_phy_model phy_model;
 
 	u16 max_burst_size;	/* driver sets this value */
 
@@ -909,12 +917,7 @@ struct ice_hw {
 	/* INTRL granularity in 1 us */
 	u8 intrl_gran;
 
-#define ICE_MAX_QUAD			2
-#define ICE_QUADS_PER_PHY_E82X		2
-#define ICE_PORTS_PER_PHY_E82X		8
-#define ICE_PORTS_PER_QUAD		4
-#define ICE_PORTS_PER_PHY_E810		4
-#define ICE_NUM_EXTERNAL_PORTS		(ICE_MAX_QUAD * ICE_PORTS_PER_QUAD)
+	struct ice_ptp_hw ptp;
 
 	/* Active package version (currently active) */
 	struct ice_pkg_ver active_pkg_ver;
-- 
GitLab


From 579a2302bd16277918f862a1dd9f3f904264fa1a Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Tue, 28 May 2024 16:03:52 -0700
Subject: [PATCH 675/950] ice: Introduce helper to get tmr_cmd_reg values

Multiple places in the driver code need to convert enum ice_ptp_tmr_cmd
values into register bits for both the main timer and the PHY port
timers. The main MAC register has one bit scheme for timer commands,
while the PHY commands use a different scheme.

The E810 and E830 devices use the same scheme for port commands as used
for the main timer. However, E822 and ETH56G hardware has a separate
scheme used by the PHY.

Introduce helper functions to convert the timer command enumeration into
the register values, reducing some code duplication, and making it
easier to later refactor the individual port write commands.

Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Arkadiusz Kubalewski <arkadiusz.kubalewski@intel.com>
Signed-off-by: Karol Kolacinski <karol.kolacinski@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20240528-next-2024-05-28-ptp-refactors-v1-2-c082739bb6f6@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/ice/ice_ptp_hw.c | 140 ++++++++++++--------
 drivers/net/ethernet/intel/ice/ice_ptp_hw.h |   2 +-
 2 files changed, 89 insertions(+), 53 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
index 22fca17a5a3cb..43aa83bc54c2e 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
@@ -227,40 +227,114 @@ static u64 ice_ptp_read_src_incval(struct ice_hw *hw)
 }
 
 /**
- * ice_ptp_src_cmd - Prepare source timer for a timer command
- * @hw: pointer to HW structure
+ * ice_ptp_tmr_cmd_to_src_reg - Convert to source timer command value
+ * @hw: pointer to HW struct
  * @cmd: Timer command
  *
- * Prepare the source timer for an upcoming timer sync command.
+ * Return: the source timer command register value for the given PTP timer
+ * command.
  */
-void ice_ptp_src_cmd(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd)
+static u32 ice_ptp_tmr_cmd_to_src_reg(struct ice_hw *hw,
+				      enum ice_ptp_tmr_cmd cmd)
 {
-	u32 cmd_val;
-	u8 tmr_idx;
+	u32 cmd_val, tmr_idx;
+
+	switch (cmd) {
+	case ICE_PTP_INIT_TIME:
+		cmd_val = GLTSYN_CMD_INIT_TIME;
+		break;
+	case ICE_PTP_INIT_INCVAL:
+		cmd_val = GLTSYN_CMD_INIT_INCVAL;
+		break;
+	case ICE_PTP_ADJ_TIME:
+		cmd_val = GLTSYN_CMD_ADJ_TIME;
+		break;
+	case ICE_PTP_ADJ_TIME_AT_TIME:
+		cmd_val = GLTSYN_CMD_ADJ_INIT_TIME;
+		break;
+	case ICE_PTP_NOP:
+	case ICE_PTP_READ_TIME:
+		cmd_val = GLTSYN_CMD_READ_TIME;
+		break;
+	default:
+		dev_warn(ice_hw_to_dev(hw),
+			 "Ignoring unrecognized timer command %u\n", cmd);
+		cmd_val = 0;
+	}
 
 	tmr_idx = ice_get_ptp_src_clock_index(hw);
-	cmd_val = tmr_idx << SEL_CPK_SRC;
+
+	return tmr_idx << SEL_CPK_SRC | cmd_val;
+}
+
+/**
+ * ice_ptp_tmr_cmd_to_port_reg- Convert to port timer command value
+ * @hw: pointer to HW struct
+ * @cmd: Timer command
+ *
+ * Note that some hardware families use a different command register value for
+ * the PHY ports, while other hardware families use the same register values
+ * as the source timer.
+ *
+ * Return: the PHY port timer command register value for the given PTP timer
+ * command.
+ */
+static u32 ice_ptp_tmr_cmd_to_port_reg(struct ice_hw *hw,
+				       enum ice_ptp_tmr_cmd cmd)
+{
+	u32 cmd_val, tmr_idx;
+
+	/* Certain hardware families share the same register values for the
+	 * port register and source timer register.
+	 */
+	switch (hw->ptp.phy_model) {
+	case ICE_PHY_E810:
+		return ice_ptp_tmr_cmd_to_src_reg(hw, cmd) & TS_CMD_MASK_E810;
+	default:
+		break;
+	}
 
 	switch (cmd) {
 	case ICE_PTP_INIT_TIME:
-		cmd_val |= GLTSYN_CMD_INIT_TIME;
+		cmd_val = PHY_CMD_INIT_TIME;
 		break;
 	case ICE_PTP_INIT_INCVAL:
-		cmd_val |= GLTSYN_CMD_INIT_INCVAL;
+		cmd_val = PHY_CMD_INIT_INCVAL;
 		break;
 	case ICE_PTP_ADJ_TIME:
-		cmd_val |= GLTSYN_CMD_ADJ_TIME;
+		cmd_val = PHY_CMD_ADJ_TIME;
 		break;
 	case ICE_PTP_ADJ_TIME_AT_TIME:
-		cmd_val |= GLTSYN_CMD_ADJ_INIT_TIME;
+		cmd_val = PHY_CMD_ADJ_TIME_AT_TIME;
 		break;
 	case ICE_PTP_READ_TIME:
-		cmd_val |= GLTSYN_CMD_READ_TIME;
+		cmd_val = PHY_CMD_READ_TIME;
 		break;
 	case ICE_PTP_NOP:
+		cmd_val = 0;
 		break;
+	default:
+		dev_warn(ice_hw_to_dev(hw),
+			 "Ignoring unrecognized timer command %u\n", cmd);
+		cmd_val = 0;
 	}
 
+	tmr_idx = ice_get_ptp_src_clock_index(hw);
+
+	return tmr_idx << SEL_PHY_SRC | cmd_val;
+}
+
+/**
+ * ice_ptp_src_cmd - Prepare source timer for a timer command
+ * @hw: pointer to HW structure
+ * @cmd: Timer command
+ *
+ * Prepare the source timer for an upcoming timer sync command.
+ */
+void ice_ptp_src_cmd(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd)
+{
+	u32 cmd_val = ice_ptp_tmr_cmd_to_src_reg(hw, cmd);
+
 	wr32(hw, GLTSYN_CMD, cmd_val);
 }
 
@@ -3029,47 +3103,9 @@ static int ice_ptp_prep_phy_incval_e810(struct ice_hw *hw, u64 incval)
  */
 static int ice_ptp_port_cmd_e810(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd)
 {
-	u32 cmd_val, val;
-	int err;
+	u32 val = ice_ptp_tmr_cmd_to_port_reg(hw, cmd);
 
-	switch (cmd) {
-	case ICE_PTP_INIT_TIME:
-		cmd_val = GLTSYN_CMD_INIT_TIME;
-		break;
-	case ICE_PTP_INIT_INCVAL:
-		cmd_val = GLTSYN_CMD_INIT_INCVAL;
-		break;
-	case ICE_PTP_ADJ_TIME:
-		cmd_val = GLTSYN_CMD_ADJ_TIME;
-		break;
-	case ICE_PTP_READ_TIME:
-		cmd_val = GLTSYN_CMD_READ_TIME;
-		break;
-	case ICE_PTP_ADJ_TIME_AT_TIME:
-		cmd_val = GLTSYN_CMD_ADJ_INIT_TIME;
-		break;
-	case ICE_PTP_NOP:
-		return 0;
-	}
-
-	/* Read, modify, write */
-	err = ice_read_phy_reg_e810(hw, ETH_GLTSYN_CMD, &val);
-	if (err) {
-		ice_debug(hw, ICE_DBG_PTP, "Failed to read GLTSYN_CMD, err %d\n", err);
-		return err;
-	}
-
-	/* Modify necessary bits only and perform write */
-	val &= ~TS_CMD_MASK_E810;
-	val |= cmd_val;
-
-	err = ice_write_phy_reg_e810(hw, ETH_GLTSYN_CMD, val);
-	if (err) {
-		ice_debug(hw, ICE_DBG_PTP, "Failed to write back GLTSYN_CMD, err %d\n", err);
-		return err;
-	}
-
-	return 0;
+	return ice_write_phy_reg_e810(hw, E810_ETH_GLTSYN_CMD, val);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
index 3dce09af0d78a..6246de3bacf3c 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
@@ -485,7 +485,7 @@ int ice_cgu_get_output_pin_state_caps(struct ice_hw *hw, u8 pin_id,
 #define ETH_GLTSYN_SHADJ_H(_i)		(0x0300037C + ((_i) * 32))
 
 /* E810 timer command register */
-#define ETH_GLTSYN_CMD			0x03000344
+#define E810_ETH_GLTSYN_CMD		0x03000344
 
 /* Source timer incval macros */
 #define INCVAL_HIGH_M			0xFF
-- 
GitLab


From 0d80bbe254198ab20982d5c508c55518d32c033b Mon Sep 17 00:00:00 2001
From: Sergey Temerkhanov <sergey.temerkhanov@intel.com>
Date: Tue, 28 May 2024 16:03:53 -0700
Subject: [PATCH 676/950] ice: Implement Tx interrupt enablement functions

Introduce functions enabling/disabling Tx TS interrupts
for the E822 and ETH56G PHYs

Signed-off-by: Sergey Temerkhanov <sergey.temerkhanov@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Arkadiusz Kubalewski <arkadiusz.kubalewski@intel.com>
Signed-off-by: Karol Kolacinski <karol.kolacinski@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20240528-next-2024-05-28-ptp-refactors-v1-3-c082739bb6f6@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/ice/ice_ptp.c    | 66 +++++++++++----------
 drivers/net/ethernet/intel/ice/ice_ptp_hw.c | 31 ++++++++++
 drivers/net/ethernet/intel/ice/ice_ptp_hw.h |  4 +-
 3 files changed, 66 insertions(+), 35 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c
index cca9d09b2d61f..412555194c97f 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.c
@@ -1457,42 +1457,46 @@ void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup)
  * @ena: bool value to enable or disable interrupt
  * @threshold: Minimum number of packets at which intr is triggered
  *
- * Utility function to enable or disable Tx timestamp interrupt and threshold
+ * Utility function to configure all the PHY interrupt settings, including
+ * whether the PHY interrupt is enabled, and what threshold to use. Also
+ * configures The E82X timestamp owner to react to interrupts from all PHYs.
+ *
+ * Return: 0 on success, -EOPNOTSUPP when PHY model incorrect, other error codes
+ * when failed to configure PHY interrupt for E82X
  */
 static int ice_ptp_cfg_phy_interrupt(struct ice_pf *pf, bool ena, u32 threshold)
 {
+	struct device *dev = ice_pf_to_dev(pf);
 	struct ice_hw *hw = &pf->hw;
-	int err = 0;
-	int quad;
-	u32 val;
 
 	ice_ptp_reset_ts_memory(hw);
 
-	for (quad = 0; quad < ICE_GET_QUAD_NUM(hw->ptp.num_lports); quad++) {
-		err = ice_read_quad_reg_e82x(hw, quad, Q_REG_TX_MEM_GBL_CFG,
-					     &val);
-		if (err)
-			break;
-
-		if (ena) {
-			val |= Q_REG_TX_MEM_GBL_CFG_INTR_ENA_M;
-			val &= ~Q_REG_TX_MEM_GBL_CFG_INTR_THR_M;
-			val |= FIELD_PREP(Q_REG_TX_MEM_GBL_CFG_INTR_THR_M,
-					  threshold);
-		} else {
-			val &= ~Q_REG_TX_MEM_GBL_CFG_INTR_ENA_M;
+	switch (hw->ptp.phy_model) {
+	case ICE_PHY_E82X: {
+		int quad;
+
+		for (quad = 0; quad < ICE_GET_QUAD_NUM(hw->ptp.num_lports);
+		     quad++) {
+			int err;
+
+			err = ice_phy_cfg_intr_e82x(hw, quad, ena, threshold);
+			if (err) {
+				dev_err(dev, "Failed to configure PHY interrupt for quad %d, err %d\n",
+					quad, err);
+				return err;
+			}
 		}
 
-		err = ice_write_quad_reg_e82x(hw, quad, Q_REG_TX_MEM_GBL_CFG,
-					      val);
-		if (err)
-			break;
+		return 0;
+	}
+	case ICE_PHY_E810:
+		return 0;
+	case ICE_PHY_UNSUP:
+	default:
+		dev_warn(dev, "%s: Unexpected PHY model %d\n", __func__,
+			 hw->ptp.phy_model);
+		return -EOPNOTSUPP;
 	}
-
-	if (err)
-		dev_err(ice_pf_to_dev(pf), "PTP failed in intr ena, err %d\n",
-			err);
-	return err;
 }
 
 /**
@@ -3010,12 +3014,10 @@ static int ice_ptp_init_owner(struct ice_pf *pf)
 	/* Release the global hardware lock */
 	ice_ptp_unlock(hw);
 
-	if (!ice_is_e810(hw)) {
-		/* Enable quad interrupts */
-		err = ice_ptp_cfg_phy_interrupt(pf, true, 1);
-		if (err)
-			goto err_exit;
-	}
+	/* Configure PHY interrupt settings */
+	err = ice_ptp_cfg_phy_interrupt(pf, true, 1);
+	if (err)
+		goto err_exit;
 
 	/* Ensure we have a clock device */
 	err = ice_ptp_create_clock(pf);
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
index 43aa83bc54c2e..0a4026c8a3ba5 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
@@ -2719,6 +2719,37 @@ ice_get_phy_tx_tstamp_ready_e82x(struct ice_hw *hw, u8 quad, u64 *tstamp_ready)
 	return 0;
 }
 
+/**
+ * ice_phy_cfg_intr_e82x - Configure TX timestamp interrupt
+ * @hw: pointer to the HW struct
+ * @quad: the timestamp quad
+ * @ena: enable or disable interrupt
+ * @threshold: interrupt threshold
+ *
+ * Configure TX timestamp interrupt for the specified quad
+ *
+ * Return: 0 on success, other error codes when failed to read/write quad
+ */
+
+int ice_phy_cfg_intr_e82x(struct ice_hw *hw, u8 quad, bool ena, u8 threshold)
+{
+	int err;
+	u32 val;
+
+	err = ice_read_quad_reg_e82x(hw, quad, Q_REG_TX_MEM_GBL_CFG, &val);
+	if (err)
+		return err;
+
+	val &= ~Q_REG_TX_MEM_GBL_CFG_INTR_ENA_M;
+	if (ena) {
+		val |= Q_REG_TX_MEM_GBL_CFG_INTR_ENA_M;
+		val &= ~Q_REG_TX_MEM_GBL_CFG_INTR_THR_M;
+		val |= FIELD_PREP(Q_REG_TX_MEM_GBL_CFG_INTR_THR_M, threshold);
+	}
+
+	return ice_write_quad_reg_e82x(hw, quad, Q_REG_TX_MEM_GBL_CFG, val);
+}
+
 /**
  * ice_ptp_init_phy_e82x - initialize PHY parameters
  * @ptp: pointer to the PTP HW struct
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
index 6246de3bacf3c..5645b20a9f87c 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
@@ -265,6 +265,7 @@ int ice_stop_phy_timer_e82x(struct ice_hw *hw, u8 port, bool soft_reset);
 int ice_start_phy_timer_e82x(struct ice_hw *hw, u8 port);
 int ice_phy_cfg_tx_offset_e82x(struct ice_hw *hw, u8 port);
 int ice_phy_cfg_rx_offset_e82x(struct ice_hw *hw, u8 port);
+int ice_phy_cfg_intr_e82x(struct ice_hw *hw, u8 quad, bool ena, u8 threshold);
 
 /* E810 family functions */
 int ice_read_sma_ctrl_e810t(struct ice_hw *hw, u8 *data);
@@ -342,11 +343,8 @@ int ice_cgu_get_output_pin_state_caps(struct ice_hw *hw, u8 pin_id,
 #define Q_REG_TX_MEM_GBL_CFG		0xC08
 #define Q_REG_TX_MEM_GBL_CFG_LANE_TYPE_S	0
 #define Q_REG_TX_MEM_GBL_CFG_LANE_TYPE_M	BIT(0)
-#define Q_REG_TX_MEM_GBL_CFG_TX_TYPE_S	1
 #define Q_REG_TX_MEM_GBL_CFG_TX_TYPE_M	ICE_M(0xFF, 1)
-#define Q_REG_TX_MEM_GBL_CFG_INTR_THR_S	9
 #define Q_REG_TX_MEM_GBL_CFG_INTR_THR_M ICE_M(0x3F, 9)
-#define Q_REG_TX_MEM_GBL_CFG_INTR_ENA_S	15
 #define Q_REG_TX_MEM_GBL_CFG_INTR_ENA_M	BIT(15)
 
 /* Tx Timestamp data registers */
-- 
GitLab


From c199b31a043c4fe6500b13c486fd06430f464b40 Mon Sep 17 00:00:00 2001
From: Karol Kolacinski <karol.kolacinski@intel.com>
Date: Tue, 28 May 2024 16:03:54 -0700
Subject: [PATCH 677/950] ice: Add PHY OFFSET_READY register clearing

Add a possibility to mark all transmitted/received timestamps as invalid
by clearing PHY OFFSET_READY registers.

Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Arkadiusz Kubalewski <arkadiusz.kubalewski@intel.com>
Signed-off-by: Karol Kolacinski <karol.kolacinski@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20240528-next-2024-05-28-ptp-refactors-v1-4-c082739bb6f6@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/ice/ice_ptp.c    | 11 ++++---
 drivers/net/ethernet/intel/ice/ice_ptp_hw.c | 34 +++++++++++++++++++++
 drivers/net/ethernet/intel/ice/ice_ptp_hw.h |  1 +
 3 files changed, 42 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c
index 412555194c97f..4ed2213247f72 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.c
@@ -1933,11 +1933,14 @@ ice_ptp_settime64(struct ptp_clock_info *info, const struct timespec64 *ts)
 	struct ice_hw *hw = &pf->hw;
 	int err;
 
-	/* For Vernier mode, we need to recalibrate after new settime
-	 * Start with disabling timestamp block
+	/* For Vernier mode on E82X, we need to recalibrate after new settime.
+	 * Start with marking timestamps as invalid.
 	 */
-	if (pf->ptp.port.link_up)
-		ice_ptp_port_phy_stop(&pf->ptp.port);
+	if (hw->ptp.phy_model == ICE_PHY_E82X) {
+		err = ice_ptp_clear_phy_offset_ready_e82x(hw);
+		if (err)
+			dev_warn(ice_pf_to_dev(pf), "Failed to mark timestamps as invalid before settime\n");
+	}
 
 	if (!ice_ptp_lock(hw)) {
 		err = -EBUSY;
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
index 0a4026c8a3ba5..25b3544c48627 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
@@ -2409,6 +2409,40 @@ int ice_phy_cfg_rx_offset_e82x(struct ice_hw *hw, u8 port)
 	return 0;
 }
 
+/**
+ * ice_ptp_clear_phy_offset_ready_e82x - Clear PHY TX_/RX_OFFSET_READY registers
+ * @hw: pointer to the HW struct
+ *
+ * Clear PHY TX_/RX_OFFSET_READY registers, effectively marking all transmitted
+ * and received timestamps as invalid.
+ *
+ * Return: 0 on success, other error codes when failed to write to PHY
+ */
+int ice_ptp_clear_phy_offset_ready_e82x(struct ice_hw *hw)
+{
+	u8 port;
+
+	for (port = 0; port < hw->ptp.num_lports; port++) {
+		int err;
+
+		err = ice_write_phy_reg_e82x(hw, port, P_REG_TX_OR, 0);
+		if (err) {
+			dev_warn(ice_hw_to_dev(hw),
+				 "Failed to clear PHY TX_OFFSET_READY register\n");
+			return err;
+		}
+
+		err = ice_write_phy_reg_e82x(hw, port, P_REG_RX_OR, 0);
+		if (err) {
+			dev_warn(ice_hw_to_dev(hw),
+				 "Failed to clear PHY RX_OFFSET_READY register\n");
+			return err;
+		}
+	}
+
+	return 0;
+}
+
 /**
  * ice_read_phy_and_phc_time_e82x - Simultaneously capture PHC and PHY time
  * @hw: pointer to the HW struct
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
index 5645b20a9f87c..5223e17d28063 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
@@ -208,6 +208,7 @@ int ice_ptp_init_time(struct ice_hw *hw, u64 time);
 int ice_ptp_write_incval(struct ice_hw *hw, u64 incval);
 int ice_ptp_write_incval_locked(struct ice_hw *hw, u64 incval);
 int ice_ptp_adj_clock(struct ice_hw *hw, s32 adj);
+int ice_ptp_clear_phy_offset_ready_e82x(struct ice_hw *hw);
 int ice_read_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx, u64 *tstamp);
 int ice_clear_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx);
 void ice_ptp_reset_ts_memory(struct ice_hw *hw);
-- 
GitLab


From 39ecb29df855ce46f70456996c518789445f2a46 Mon Sep 17 00:00:00 2001
From: Sergey Temerkhanov <sergey.temerkhanov@intel.com>
Date: Tue, 28 May 2024 16:03:55 -0700
Subject: [PATCH 678/950] ice: Move CGU block

Move CGU block to the beginning of ice_ptp_hw.c

Signed-off-by: Sergey Temerkhanov <sergey.temerkhanov@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Arkadiusz Kubalewski <arkadiusz.kubalewski@intel.com>
Signed-off-by: Karol Kolacinski <karol.kolacinski@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20240528-next-2024-05-28-ptp-refactors-v1-5-c082739bb6f6@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/ice/ice_ptp_hw.c | 1409 ++++++++++---------
 drivers/net/ethernet/intel/ice/ice_ptp_hw.h |    2 +-
 2 files changed, 707 insertions(+), 704 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
index 25b3544c48627..7224bce7aa28b 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
@@ -227,563 +227,575 @@ static u64 ice_ptp_read_src_incval(struct ice_hw *hw)
 }
 
 /**
- * ice_ptp_tmr_cmd_to_src_reg - Convert to source timer command value
- * @hw: pointer to HW struct
- * @cmd: Timer command
+ * ice_read_cgu_reg_e82x - Read a CGU register
+ * @hw: pointer to the HW struct
+ * @addr: Register address to read
+ * @val: storage for register value read
  *
- * Return: the source timer command register value for the given PTP timer
- * command.
+ * Read the contents of a register of the Clock Generation Unit. Only
+ * applicable to E822 devices.
+ *
+ * Return: 0 on success, other error codes when failed to read from CGU
  */
-static u32 ice_ptp_tmr_cmd_to_src_reg(struct ice_hw *hw,
-				      enum ice_ptp_tmr_cmd cmd)
+static int ice_read_cgu_reg_e82x(struct ice_hw *hw, u32 addr, u32 *val)
 {
-	u32 cmd_val, tmr_idx;
+	struct ice_sbq_msg_input cgu_msg = {
+		.opcode = ice_sbq_msg_rd,
+		.dest_dev = cgu,
+		.msg_addr_low = addr
+	};
+	int err;
 
-	switch (cmd) {
-	case ICE_PTP_INIT_TIME:
-		cmd_val = GLTSYN_CMD_INIT_TIME;
-		break;
-	case ICE_PTP_INIT_INCVAL:
-		cmd_val = GLTSYN_CMD_INIT_INCVAL;
-		break;
-	case ICE_PTP_ADJ_TIME:
-		cmd_val = GLTSYN_CMD_ADJ_TIME;
-		break;
-	case ICE_PTP_ADJ_TIME_AT_TIME:
-		cmd_val = GLTSYN_CMD_ADJ_INIT_TIME;
-		break;
-	case ICE_PTP_NOP:
-	case ICE_PTP_READ_TIME:
-		cmd_val = GLTSYN_CMD_READ_TIME;
-		break;
-	default:
-		dev_warn(ice_hw_to_dev(hw),
-			 "Ignoring unrecognized timer command %u\n", cmd);
-		cmd_val = 0;
+	err = ice_sbq_rw_reg(hw, &cgu_msg);
+	if (err) {
+		ice_debug(hw, ICE_DBG_PTP, "Failed to read CGU register 0x%04x, err %d\n",
+			  addr, err);
+		return err;
 	}
 
-	tmr_idx = ice_get_ptp_src_clock_index(hw);
+	*val = cgu_msg.data;
 
-	return tmr_idx << SEL_CPK_SRC | cmd_val;
+	return 0;
 }
 
 /**
- * ice_ptp_tmr_cmd_to_port_reg- Convert to port timer command value
- * @hw: pointer to HW struct
- * @cmd: Timer command
+ * ice_write_cgu_reg_e82x - Write a CGU register
+ * @hw: pointer to the HW struct
+ * @addr: Register address to write
+ * @val: value to write into the register
  *
- * Note that some hardware families use a different command register value for
- * the PHY ports, while other hardware families use the same register values
- * as the source timer.
+ * Write the specified value to a register of the Clock Generation Unit. Only
+ * applicable to E822 devices.
  *
- * Return: the PHY port timer command register value for the given PTP timer
- * command.
+ * Return: 0 on success, other error codes when failed to write to CGU
  */
-static u32 ice_ptp_tmr_cmd_to_port_reg(struct ice_hw *hw,
-				       enum ice_ptp_tmr_cmd cmd)
+static int ice_write_cgu_reg_e82x(struct ice_hw *hw, u32 addr, u32 val)
 {
-	u32 cmd_val, tmr_idx;
-
-	/* Certain hardware families share the same register values for the
-	 * port register and source timer register.
-	 */
-	switch (hw->ptp.phy_model) {
-	case ICE_PHY_E810:
-		return ice_ptp_tmr_cmd_to_src_reg(hw, cmd) & TS_CMD_MASK_E810;
-	default:
-		break;
-	}
+	struct ice_sbq_msg_input cgu_msg = {
+		.opcode = ice_sbq_msg_wr,
+		.dest_dev = cgu,
+		.msg_addr_low = addr,
+		.data = val
+	};
+	int err;
 
-	switch (cmd) {
-	case ICE_PTP_INIT_TIME:
-		cmd_val = PHY_CMD_INIT_TIME;
-		break;
-	case ICE_PTP_INIT_INCVAL:
-		cmd_val = PHY_CMD_INIT_INCVAL;
-		break;
-	case ICE_PTP_ADJ_TIME:
-		cmd_val = PHY_CMD_ADJ_TIME;
-		break;
-	case ICE_PTP_ADJ_TIME_AT_TIME:
-		cmd_val = PHY_CMD_ADJ_TIME_AT_TIME;
-		break;
-	case ICE_PTP_READ_TIME:
-		cmd_val = PHY_CMD_READ_TIME;
-		break;
-	case ICE_PTP_NOP:
-		cmd_val = 0;
-		break;
-	default:
-		dev_warn(ice_hw_to_dev(hw),
-			 "Ignoring unrecognized timer command %u\n", cmd);
-		cmd_val = 0;
+	err = ice_sbq_rw_reg(hw, &cgu_msg);
+	if (err) {
+		ice_debug(hw, ICE_DBG_PTP, "Failed to write CGU register 0x%04x, err %d\n",
+			  addr, err);
+		return err;
 	}
 
-	tmr_idx = ice_get_ptp_src_clock_index(hw);
-
-	return tmr_idx << SEL_PHY_SRC | cmd_val;
+	return err;
 }
 
 /**
- * ice_ptp_src_cmd - Prepare source timer for a timer command
- * @hw: pointer to HW structure
- * @cmd: Timer command
+ * ice_clk_freq_str - Convert time_ref_freq to string
+ * @clk_freq: Clock frequency
  *
- * Prepare the source timer for an upcoming timer sync command.
+ * Return: specified TIME_REF clock frequency converted to a string
  */
-void ice_ptp_src_cmd(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd)
+static const char *ice_clk_freq_str(enum ice_time_ref_freq clk_freq)
 {
-	u32 cmd_val = ice_ptp_tmr_cmd_to_src_reg(hw, cmd);
-
-	wr32(hw, GLTSYN_CMD, cmd_val);
+	switch (clk_freq) {
+	case ICE_TIME_REF_FREQ_25_000:
+		return "25 MHz";
+	case ICE_TIME_REF_FREQ_122_880:
+		return "122.88 MHz";
+	case ICE_TIME_REF_FREQ_125_000:
+		return "125 MHz";
+	case ICE_TIME_REF_FREQ_153_600:
+		return "153.6 MHz";
+	case ICE_TIME_REF_FREQ_156_250:
+		return "156.25 MHz";
+	case ICE_TIME_REF_FREQ_245_760:
+		return "245.76 MHz";
+	default:
+		return "Unknown";
+	}
 }
 
 /**
- * ice_ptp_exec_tmr_cmd - Execute all prepared timer commands
- * @hw: pointer to HW struct
+ * ice_clk_src_str - Convert time_ref_src to string
+ * @clk_src: Clock source
  *
- * Write the SYNC_EXEC_CMD bit to the GLTSYN_CMD_SYNC register, and flush the
- * write immediately. This triggers the hardware to begin executing all of the
- * source and PHY timer commands synchronously.
+ * Return: specified clock source converted to its string name
  */
-static void ice_ptp_exec_tmr_cmd(struct ice_hw *hw)
+static const char *ice_clk_src_str(enum ice_clk_src clk_src)
 {
-	struct ice_pf *pf = container_of(hw, struct ice_pf, hw);
-
-	guard(spinlock)(&pf->adapter->ptp_gltsyn_time_lock);
-	wr32(hw, GLTSYN_CMD_SYNC, SYNC_EXEC_CMD);
-	ice_flush(hw);
+	switch (clk_src) {
+	case ICE_CLK_SRC_TCX0:
+		return "TCX0";
+	case ICE_CLK_SRC_TIME_REF:
+		return "TIME_REF";
+	default:
+		return "Unknown";
+	}
 }
 
-/* E822 family functions
- *
- * The following functions operate on the E822 family of devices.
- */
-
 /**
- * ice_fill_phy_msg_e82x - Fill message data for a PHY register access
+ * ice_cfg_cgu_pll_e82x - Configure the Clock Generation Unit
  * @hw: pointer to the HW struct
- * @msg: the PHY message buffer to fill in
- * @port: the port to access
- * @offset: the register offset
+ * @clk_freq: Clock frequency to program
+ * @clk_src: Clock source to select (TIME_REF, or TCX0)
+ *
+ * Configure the Clock Generation Unit with the desired clock frequency and
+ * time reference, enabling the PLL which drives the PTP hardware clock.
+ *
+ * Return:
+ * * %0       - success
+ * * %-EINVAL - input parameters are incorrect
+ * * %-EBUSY  - failed to lock TS PLL
+ * * %other   - CGU read/write failure
  */
-static void ice_fill_phy_msg_e82x(struct ice_hw *hw,
-				  struct ice_sbq_msg_input *msg, u8 port,
-				  u16 offset)
+static int ice_cfg_cgu_pll_e82x(struct ice_hw *hw,
+				enum ice_time_ref_freq clk_freq,
+				enum ice_clk_src clk_src)
 {
-	int phy_port, phy, quadtype;
-
-	phy_port = port % hw->ptp.ports_per_phy;
-	phy = port / hw->ptp.ports_per_phy;
-	quadtype = ICE_GET_QUAD_NUM(port) %
-		   ICE_GET_QUAD_NUM(hw->ptp.ports_per_phy);
+	union tspll_ro_bwm_lf bwm_lf;
+	union nac_cgu_dword19 dw19;
+	union nac_cgu_dword22 dw22;
+	union nac_cgu_dword24 dw24;
+	union nac_cgu_dword9 dw9;
+	int err;
 
-	if (quadtype == 0) {
-		msg->msg_addr_low = P_Q0_L(P_0_BASE + offset, phy_port);
-		msg->msg_addr_high = P_Q0_H(P_0_BASE + offset, phy_port);
-	} else {
-		msg->msg_addr_low = P_Q1_L(P_4_BASE + offset, phy_port);
-		msg->msg_addr_high = P_Q1_H(P_4_BASE + offset, phy_port);
+	if (clk_freq >= NUM_ICE_TIME_REF_FREQ) {
+		dev_warn(ice_hw_to_dev(hw), "Invalid TIME_REF frequency %u\n",
+			 clk_freq);
+		return -EINVAL;
 	}
 
-	if (phy == 0)
-		msg->dest_dev = rmn_0;
-	else if (phy == 1)
-		msg->dest_dev = rmn_1;
-	else
-		msg->dest_dev = rmn_2;
-}
-
-/**
- * ice_is_64b_phy_reg_e82x - Check if this is a 64bit PHY register
- * @low_addr: the low address to check
- * @high_addr: on return, contains the high address of the 64bit register
- *
- * Checks if the provided low address is one of the known 64bit PHY values
- * represented as two 32bit registers. If it is, return the appropriate high
- * register offset to use.
- */
-static bool ice_is_64b_phy_reg_e82x(u16 low_addr, u16 *high_addr)
-{
-	switch (low_addr) {
-	case P_REG_PAR_PCS_TX_OFFSET_L:
-		*high_addr = P_REG_PAR_PCS_TX_OFFSET_U;
-		return true;
-	case P_REG_PAR_PCS_RX_OFFSET_L:
-		*high_addr = P_REG_PAR_PCS_RX_OFFSET_U;
-		return true;
-	case P_REG_PAR_TX_TIME_L:
-		*high_addr = P_REG_PAR_TX_TIME_U;
-		return true;
-	case P_REG_PAR_RX_TIME_L:
-		*high_addr = P_REG_PAR_RX_TIME_U;
-		return true;
-	case P_REG_TOTAL_TX_OFFSET_L:
-		*high_addr = P_REG_TOTAL_TX_OFFSET_U;
-		return true;
-	case P_REG_TOTAL_RX_OFFSET_L:
-		*high_addr = P_REG_TOTAL_RX_OFFSET_U;
-		return true;
-	case P_REG_UIX66_10G_40G_L:
-		*high_addr = P_REG_UIX66_10G_40G_U;
-		return true;
-	case P_REG_UIX66_25G_100G_L:
-		*high_addr = P_REG_UIX66_25G_100G_U;
-		return true;
-	case P_REG_TX_CAPTURE_L:
-		*high_addr = P_REG_TX_CAPTURE_U;
-		return true;
-	case P_REG_RX_CAPTURE_L:
-		*high_addr = P_REG_RX_CAPTURE_U;
-		return true;
-	case P_REG_TX_TIMER_INC_PRE_L:
-		*high_addr = P_REG_TX_TIMER_INC_PRE_U;
-		return true;
-	case P_REG_RX_TIMER_INC_PRE_L:
-		*high_addr = P_REG_RX_TIMER_INC_PRE_U;
-		return true;
-	default:
-		return false;
+	if (clk_src >= NUM_ICE_CLK_SRC) {
+		dev_warn(ice_hw_to_dev(hw), "Invalid clock source %u\n",
+			 clk_src);
+		return -EINVAL;
 	}
-}
 
-/**
- * ice_is_40b_phy_reg_e82x - Check if this is a 40bit PHY register
- * @low_addr: the low address to check
- * @high_addr: on return, contains the high address of the 40bit value
- *
- * Checks if the provided low address is one of the known 40bit PHY values
- * split into two registers with the lower 8 bits in the low register and the
- * upper 32 bits in the high register. If it is, return the appropriate high
- * register offset to use.
- */
-static bool ice_is_40b_phy_reg_e82x(u16 low_addr, u16 *high_addr)
-{
-	switch (low_addr) {
-	case P_REG_TIMETUS_L:
-		*high_addr = P_REG_TIMETUS_U;
-		return true;
-	case P_REG_PAR_RX_TUS_L:
-		*high_addr = P_REG_PAR_RX_TUS_U;
-		return true;
-	case P_REG_PAR_TX_TUS_L:
-		*high_addr = P_REG_PAR_TX_TUS_U;
-		return true;
-	case P_REG_PCS_RX_TUS_L:
-		*high_addr = P_REG_PCS_RX_TUS_U;
-		return true;
-	case P_REG_PCS_TX_TUS_L:
-		*high_addr = P_REG_PCS_TX_TUS_U;
-		return true;
-	case P_REG_DESK_PAR_RX_TUS_L:
-		*high_addr = P_REG_DESK_PAR_RX_TUS_U;
-		return true;
-	case P_REG_DESK_PAR_TX_TUS_L:
-		*high_addr = P_REG_DESK_PAR_TX_TUS_U;
-		return true;
-	case P_REG_DESK_PCS_RX_TUS_L:
-		*high_addr = P_REG_DESK_PCS_RX_TUS_U;
-		return true;
-	case P_REG_DESK_PCS_TX_TUS_L:
-		*high_addr = P_REG_DESK_PCS_TX_TUS_U;
-		return true;
-	default:
-		return false;
+	if (clk_src == ICE_CLK_SRC_TCX0 &&
+	    clk_freq != ICE_TIME_REF_FREQ_25_000) {
+		dev_warn(ice_hw_to_dev(hw),
+			 "TCX0 only supports 25 MHz frequency\n");
+		return -EINVAL;
 	}
-}
 
-/**
- * ice_read_phy_reg_e82x - Read a PHY register
- * @hw: pointer to the HW struct
- * @port: PHY port to read from
- * @offset: PHY register offset to read
- * @val: on return, the contents read from the PHY
- *
- * Read a PHY register for the given port over the device sideband queue.
- */
-static int
-ice_read_phy_reg_e82x(struct ice_hw *hw, u8 port, u16 offset, u32 *val)
-{
-	struct ice_sbq_msg_input msg = {0};
-	int err;
+	err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD9, &dw9.val);
+	if (err)
+		return err;
 
-	ice_fill_phy_msg_e82x(hw, &msg, port, offset);
-	msg.opcode = ice_sbq_msg_rd;
+	err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD24, &dw24.val);
+	if (err)
+		return err;
 
-	err = ice_sbq_rw_reg(hw, &msg);
-	if (err) {
-		ice_debug(hw, ICE_DBG_PTP, "Failed to send message to PHY, err %d\n",
-			  err);
+	err = ice_read_cgu_reg_e82x(hw, TSPLL_RO_BWM_LF, &bwm_lf.val);
+	if (err)
 		return err;
+
+	/* Log the current clock configuration */
+	ice_debug(hw, ICE_DBG_PTP, "Current CGU configuration -- %s, clk_src %s, clk_freq %s, PLL %s\n",
+		  dw24.field.ts_pll_enable ? "enabled" : "disabled",
+		  ice_clk_src_str(dw24.field.time_ref_sel),
+		  ice_clk_freq_str(dw9.field.time_ref_freq_sel),
+		  bwm_lf.field.plllock_true_lock_cri ? "locked" : "unlocked");
+
+	/* Disable the PLL before changing the clock source or frequency */
+	if (dw24.field.ts_pll_enable) {
+		dw24.field.ts_pll_enable = 0;
+
+		err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD24, dw24.val);
+		if (err)
+			return err;
 	}
 
-	*val = msg.data;
+	/* Set the frequency */
+	dw9.field.time_ref_freq_sel = clk_freq;
+	err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD9, dw9.val);
+	if (err)
+		return err;
 
-	return 0;
-}
+	/* Configure the TS PLL feedback divisor */
+	err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD19, &dw19.val);
+	if (err)
+		return err;
 
-/**
- * ice_read_64b_phy_reg_e82x - Read a 64bit value from PHY registers
- * @hw: pointer to the HW struct
- * @port: PHY port to read from
- * @low_addr: offset of the lower register to read from
- * @val: on return, the contents of the 64bit value from the PHY registers
- *
- * Reads the two registers associated with a 64bit value and returns it in the
- * val pointer. The offset always specifies the lower register offset to use.
- * The high offset is looked up. This function only operates on registers
- * known to be two parts of a 64bit value.
- */
-static int
-ice_read_64b_phy_reg_e82x(struct ice_hw *hw, u8 port, u16 low_addr, u64 *val)
-{
-	u32 low, high;
-	u16 high_addr;
-	int err;
+	dw19.field.tspll_fbdiv_intgr = e822_cgu_params[clk_freq].feedback_div;
+	dw19.field.tspll_ndivratio = 1;
 
-	/* Only operate on registers known to be split into two 32bit
-	 * registers.
-	 */
-	if (!ice_is_64b_phy_reg_e82x(low_addr, &high_addr)) {
-		ice_debug(hw, ICE_DBG_PTP, "Invalid 64b register addr 0x%08x\n",
-			  low_addr);
-		return -EINVAL;
-	}
+	err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD19, dw19.val);
+	if (err)
+		return err;
 
-	err = ice_read_phy_reg_e82x(hw, port, low_addr, &low);
-	if (err) {
-		ice_debug(hw, ICE_DBG_PTP, "Failed to read from low register 0x%08x\n, err %d",
-			  low_addr, err);
+	/* Configure the TS PLL post divisor */
+	err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD22, &dw22.val);
+	if (err)
 		return err;
-	}
 
-	err = ice_read_phy_reg_e82x(hw, port, high_addr, &high);
-	if (err) {
-		ice_debug(hw, ICE_DBG_PTP, "Failed to read from high register 0x%08x\n, err %d",
-			  high_addr, err);
+	dw22.field.time1588clk_div = e822_cgu_params[clk_freq].post_pll_div;
+	dw22.field.time1588clk_sel_div2 = 0;
+
+	err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD22, dw22.val);
+	if (err)
+		return err;
+
+	/* Configure the TS PLL pre divisor and clock source */
+	err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD24, &dw24.val);
+	if (err)
+		return err;
+
+	dw24.field.ref1588_ck_div = e822_cgu_params[clk_freq].refclk_pre_div;
+	dw24.field.tspll_fbdiv_frac = e822_cgu_params[clk_freq].frac_n_div;
+	dw24.field.time_ref_sel = clk_src;
+
+	err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD24, dw24.val);
+	if (err)
 		return err;
+
+	/* Finally, enable the PLL */
+	dw24.field.ts_pll_enable = 1;
+
+	err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD24, dw24.val);
+	if (err)
+		return err;
+
+	/* Wait to verify if the PLL locks */
+	usleep_range(1000, 5000);
+
+	err = ice_read_cgu_reg_e82x(hw, TSPLL_RO_BWM_LF, &bwm_lf.val);
+	if (err)
+		return err;
+
+	if (!bwm_lf.field.plllock_true_lock_cri) {
+		dev_warn(ice_hw_to_dev(hw), "CGU PLL failed to lock\n");
+		return -EBUSY;
 	}
 
-	*val = (u64)high << 32 | low;
+	/* Log the current clock configuration */
+	ice_debug(hw, ICE_DBG_PTP, "New CGU configuration -- %s, clk_src %s, clk_freq %s, PLL %s\n",
+		  dw24.field.ts_pll_enable ? "enabled" : "disabled",
+		  ice_clk_src_str(dw24.field.time_ref_sel),
+		  ice_clk_freq_str(dw9.field.time_ref_freq_sel),
+		  bwm_lf.field.plllock_true_lock_cri ? "locked" : "unlocked");
 
 	return 0;
 }
 
 /**
- * ice_write_phy_reg_e82x - Write a PHY register
- * @hw: pointer to the HW struct
- * @port: PHY port to write to
- * @offset: PHY register offset to write
- * @val: The value to write to the register
+ * ice_init_cgu_e82x - Initialize CGU with settings from firmware
+ * @hw: pointer to the HW structure
  *
- * Write a PHY register for the given port over the device sideband queue.
+ * Initialize the Clock Generation Unit of the E822 device.
+ *
+ * Return: 0 on success, other error codes when failed to read/write/cfg CGU
  */
-static int
-ice_write_phy_reg_e82x(struct ice_hw *hw, u8 port, u16 offset, u32 val)
+static int ice_init_cgu_e82x(struct ice_hw *hw)
 {
-	struct ice_sbq_msg_input msg = {0};
+	struct ice_ts_func_info *ts_info = &hw->func_caps.ts_func_info;
+	union tspll_cntr_bist_settings cntr_bist;
 	int err;
 
-	ice_fill_phy_msg_e82x(hw, &msg, port, offset);
-	msg.opcode = ice_sbq_msg_wr;
-	msg.data = val;
+	err = ice_read_cgu_reg_e82x(hw, TSPLL_CNTR_BIST_SETTINGS,
+				    &cntr_bist.val);
+	if (err)
+		return err;
 
-	err = ice_sbq_rw_reg(hw, &msg);
-	if (err) {
-		ice_debug(hw, ICE_DBG_PTP, "Failed to send message to PHY, err %d\n",
-			  err);
+	/* Disable sticky lock detection so lock err reported is accurate */
+	cntr_bist.field.i_plllock_sel_0 = 0;
+	cntr_bist.field.i_plllock_sel_1 = 0;
+
+	err = ice_write_cgu_reg_e82x(hw, TSPLL_CNTR_BIST_SETTINGS,
+				     cntr_bist.val);
+	if (err)
 		return err;
+
+	/* Configure the CGU PLL using the parameters from the function
+	 * capabilities.
+	 */
+	return ice_cfg_cgu_pll_e82x(hw, ts_info->time_ref,
+				   (enum ice_clk_src)ts_info->clk_src);
+}
+
+/**
+ * ice_ptp_tmr_cmd_to_src_reg - Convert to source timer command value
+ * @hw: pointer to HW struct
+ * @cmd: Timer command
+ *
+ * Return: the source timer command register value for the given PTP timer
+ * command.
+ */
+static u32 ice_ptp_tmr_cmd_to_src_reg(struct ice_hw *hw,
+				      enum ice_ptp_tmr_cmd cmd)
+{
+	u32 cmd_val, tmr_idx;
+
+	switch (cmd) {
+	case ICE_PTP_INIT_TIME:
+		cmd_val = GLTSYN_CMD_INIT_TIME;
+		break;
+	case ICE_PTP_INIT_INCVAL:
+		cmd_val = GLTSYN_CMD_INIT_INCVAL;
+		break;
+	case ICE_PTP_ADJ_TIME:
+		cmd_val = GLTSYN_CMD_ADJ_TIME;
+		break;
+	case ICE_PTP_ADJ_TIME_AT_TIME:
+		cmd_val = GLTSYN_CMD_ADJ_INIT_TIME;
+		break;
+	case ICE_PTP_NOP:
+	case ICE_PTP_READ_TIME:
+		cmd_val = GLTSYN_CMD_READ_TIME;
+		break;
+	default:
+		dev_warn(ice_hw_to_dev(hw),
+			 "Ignoring unrecognized timer command %u\n", cmd);
+		cmd_val = 0;
 	}
 
-	return 0;
+	tmr_idx = ice_get_ptp_src_clock_index(hw);
+
+	return tmr_idx << SEL_CPK_SRC | cmd_val;
 }
 
 /**
- * ice_write_40b_phy_reg_e82x - Write a 40b value to the PHY
- * @hw: pointer to the HW struct
- * @port: port to write to
- * @low_addr: offset of the low register
- * @val: 40b value to write
+ * ice_ptp_tmr_cmd_to_port_reg- Convert to port timer command value
+ * @hw: pointer to HW struct
+ * @cmd: Timer command
  *
- * Write the provided 40b value to the two associated registers by splitting
- * it up into two chunks, the lower 8 bits and the upper 32 bits.
+ * Note that some hardware families use a different command register value for
+ * the PHY ports, while other hardware families use the same register values
+ * as the source timer.
+ *
+ * Return: the PHY port timer command register value for the given PTP timer
+ * command.
  */
-static int
-ice_write_40b_phy_reg_e82x(struct ice_hw *hw, u8 port, u16 low_addr, u64 val)
+static u32 ice_ptp_tmr_cmd_to_port_reg(struct ice_hw *hw,
+				       enum ice_ptp_tmr_cmd cmd)
 {
-	u32 low, high;
-	u16 high_addr;
-	int err;
+	u32 cmd_val, tmr_idx;
 
-	/* Only operate on registers known to be split into a lower 8 bit
-	 * register and an upper 32 bit register.
+	/* Certain hardware families share the same register values for the
+	 * port register and source timer register.
 	 */
-	if (!ice_is_40b_phy_reg_e82x(low_addr, &high_addr)) {
-		ice_debug(hw, ICE_DBG_PTP, "Invalid 40b register addr 0x%08x\n",
-			  low_addr);
-		return -EINVAL;
+	switch (hw->ptp.phy_model) {
+	case ICE_PHY_E810:
+		return ice_ptp_tmr_cmd_to_src_reg(hw, cmd) & TS_CMD_MASK_E810;
+	default:
+		break;
 	}
 
-	low = (u32)(val & P_REG_40B_LOW_M);
-	high = (u32)(val >> P_REG_40B_HIGH_S);
-
-	err = ice_write_phy_reg_e82x(hw, port, low_addr, low);
-	if (err) {
-		ice_debug(hw, ICE_DBG_PTP, "Failed to write to low register 0x%08x\n, err %d",
-			  low_addr, err);
-		return err;
+	switch (cmd) {
+	case ICE_PTP_INIT_TIME:
+		cmd_val = PHY_CMD_INIT_TIME;
+		break;
+	case ICE_PTP_INIT_INCVAL:
+		cmd_val = PHY_CMD_INIT_INCVAL;
+		break;
+	case ICE_PTP_ADJ_TIME:
+		cmd_val = PHY_CMD_ADJ_TIME;
+		break;
+	case ICE_PTP_ADJ_TIME_AT_TIME:
+		cmd_val = PHY_CMD_ADJ_TIME_AT_TIME;
+		break;
+	case ICE_PTP_READ_TIME:
+		cmd_val = PHY_CMD_READ_TIME;
+		break;
+	case ICE_PTP_NOP:
+		cmd_val = 0;
+		break;
+	default:
+		dev_warn(ice_hw_to_dev(hw),
+			 "Ignoring unrecognized timer command %u\n", cmd);
+		cmd_val = 0;
 	}
 
-	err = ice_write_phy_reg_e82x(hw, port, high_addr, high);
-	if (err) {
-		ice_debug(hw, ICE_DBG_PTP, "Failed to write to high register 0x%08x\n, err %d",
-			  high_addr, err);
-		return err;
-	}
+	tmr_idx = ice_get_ptp_src_clock_index(hw);
 
-	return 0;
+	return tmr_idx << SEL_PHY_SRC | cmd_val;
 }
 
 /**
- * ice_write_64b_phy_reg_e82x - Write a 64bit value to PHY registers
- * @hw: pointer to the HW struct
- * @port: PHY port to read from
- * @low_addr: offset of the lower register to read from
- * @val: the contents of the 64bit value to write to PHY
+ * ice_ptp_src_cmd - Prepare source timer for a timer command
+ * @hw: pointer to HW structure
+ * @cmd: Timer command
  *
- * Write the 64bit value to the two associated 32bit PHY registers. The offset
- * is always specified as the lower register, and the high address is looked
- * up. This function only operates on registers known to be two parts of
- * a 64bit value.
+ * Prepare the source timer for an upcoming timer sync command.
  */
-static int
-ice_write_64b_phy_reg_e82x(struct ice_hw *hw, u8 port, u16 low_addr, u64 val)
+void ice_ptp_src_cmd(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd)
 {
-	u32 low, high;
-	u16 high_addr;
-	int err;
-
-	/* Only operate on registers known to be split into two 32bit
-	 * registers.
-	 */
-	if (!ice_is_64b_phy_reg_e82x(low_addr, &high_addr)) {
-		ice_debug(hw, ICE_DBG_PTP, "Invalid 64b register addr 0x%08x\n",
-			  low_addr);
-		return -EINVAL;
-	}
-
-	low = lower_32_bits(val);
-	high = upper_32_bits(val);
+	u32 cmd_val = ice_ptp_tmr_cmd_to_src_reg(hw, cmd);
 
-	err = ice_write_phy_reg_e82x(hw, port, low_addr, low);
-	if (err) {
-		ice_debug(hw, ICE_DBG_PTP, "Failed to write to low register 0x%08x\n, err %d",
-			  low_addr, err);
-		return err;
-	}
+	wr32(hw, GLTSYN_CMD, cmd_val);
+}
 
-	err = ice_write_phy_reg_e82x(hw, port, high_addr, high);
-	if (err) {
-		ice_debug(hw, ICE_DBG_PTP, "Failed to write to high register 0x%08x\n, err %d",
-			  high_addr, err);
-		return err;
-	}
+/**
+ * ice_ptp_exec_tmr_cmd - Execute all prepared timer commands
+ * @hw: pointer to HW struct
+ *
+ * Write the SYNC_EXEC_CMD bit to the GLTSYN_CMD_SYNC register, and flush the
+ * write immediately. This triggers the hardware to begin executing all of the
+ * source and PHY timer commands synchronously.
+ */
+static void ice_ptp_exec_tmr_cmd(struct ice_hw *hw)
+{
+	struct ice_pf *pf = container_of(hw, struct ice_pf, hw);
 
-	return 0;
+	guard(spinlock)(&pf->adapter->ptp_gltsyn_time_lock);
+	wr32(hw, GLTSYN_CMD_SYNC, SYNC_EXEC_CMD);
+	ice_flush(hw);
 }
 
+/* E822 family functions
+ *
+ * The following functions operate on the E822 family of devices.
+ */
+
 /**
- * ice_fill_quad_msg_e82x - Fill message data for quad register access
+ * ice_fill_phy_msg_e82x - Fill message data for a PHY register access
  * @hw: pointer to the HW struct
  * @msg: the PHY message buffer to fill in
- * @quad: the quad to access
+ * @port: the port to access
  * @offset: the register offset
- *
- * Fill a message buffer for accessing a register in a quad shared between
- * multiple PHYs.
- *
- * Return:
- * * %0       - OK
- * * %-EINVAL - invalid quad number
  */
-static int ice_fill_quad_msg_e82x(struct ice_hw *hw,
-				  struct ice_sbq_msg_input *msg, u8 quad,
+static void ice_fill_phy_msg_e82x(struct ice_hw *hw,
+				  struct ice_sbq_msg_input *msg, u8 port,
 				  u16 offset)
 {
-	u32 addr;
+	int phy_port, phy, quadtype;
 
-	if (quad >= ICE_GET_QUAD_NUM(hw->ptp.num_lports))
-		return -EINVAL;
+	phy_port = port % hw->ptp.ports_per_phy;
+	phy = port / hw->ptp.ports_per_phy;
+	quadtype = ICE_GET_QUAD_NUM(port) %
+		   ICE_GET_QUAD_NUM(hw->ptp.ports_per_phy);
 
-	msg->dest_dev = rmn_0;
+	if (quadtype == 0) {
+		msg->msg_addr_low = P_Q0_L(P_0_BASE + offset, phy_port);
+		msg->msg_addr_high = P_Q0_H(P_0_BASE + offset, phy_port);
+	} else {
+		msg->msg_addr_low = P_Q1_L(P_4_BASE + offset, phy_port);
+		msg->msg_addr_high = P_Q1_H(P_4_BASE + offset, phy_port);
+	}
 
-	if (!(quad % ICE_GET_QUAD_NUM(hw->ptp.ports_per_phy)))
-		addr = Q_0_BASE + offset;
+	if (phy == 0)
+		msg->dest_dev = rmn_0;
+	else if (phy == 1)
+		msg->dest_dev = rmn_1;
 	else
-		addr = Q_1_BASE + offset;
-
-	msg->msg_addr_low = lower_16_bits(addr);
-	msg->msg_addr_high = upper_16_bits(addr);
-
-	return 0;
+		msg->dest_dev = rmn_2;
 }
 
 /**
- * ice_read_quad_reg_e82x - Read a PHY quad register
- * @hw: pointer to the HW struct
- * @quad: quad to read from
- * @offset: quad register offset to read
- * @val: on return, the contents read from the quad
+ * ice_is_64b_phy_reg_e82x - Check if this is a 64bit PHY register
+ * @low_addr: the low address to check
+ * @high_addr: on return, contains the high address of the 64bit register
  *
- * Read a quad register over the device sideband queue. Quad registers are
- * shared between multiple PHYs.
+ * Checks if the provided low address is one of the known 64bit PHY values
+ * represented as two 32bit registers. If it is, return the appropriate high
+ * register offset to use.
  */
-int
-ice_read_quad_reg_e82x(struct ice_hw *hw, u8 quad, u16 offset, u32 *val)
+static bool ice_is_64b_phy_reg_e82x(u16 low_addr, u16 *high_addr)
 {
-	struct ice_sbq_msg_input msg = {0};
-	int err;
-
-	err = ice_fill_quad_msg_e82x(hw, &msg, quad, offset);
-	if (err)
-		return err;
-
-	msg.opcode = ice_sbq_msg_rd;
-
-	err = ice_sbq_rw_reg(hw, &msg);
-	if (err) {
-		ice_debug(hw, ICE_DBG_PTP, "Failed to send message to PHY, err %d\n",
-			  err);
-		return err;
+	switch (low_addr) {
+	case P_REG_PAR_PCS_TX_OFFSET_L:
+		*high_addr = P_REG_PAR_PCS_TX_OFFSET_U;
+		return true;
+	case P_REG_PAR_PCS_RX_OFFSET_L:
+		*high_addr = P_REG_PAR_PCS_RX_OFFSET_U;
+		return true;
+	case P_REG_PAR_TX_TIME_L:
+		*high_addr = P_REG_PAR_TX_TIME_U;
+		return true;
+	case P_REG_PAR_RX_TIME_L:
+		*high_addr = P_REG_PAR_RX_TIME_U;
+		return true;
+	case P_REG_TOTAL_TX_OFFSET_L:
+		*high_addr = P_REG_TOTAL_TX_OFFSET_U;
+		return true;
+	case P_REG_TOTAL_RX_OFFSET_L:
+		*high_addr = P_REG_TOTAL_RX_OFFSET_U;
+		return true;
+	case P_REG_UIX66_10G_40G_L:
+		*high_addr = P_REG_UIX66_10G_40G_U;
+		return true;
+	case P_REG_UIX66_25G_100G_L:
+		*high_addr = P_REG_UIX66_25G_100G_U;
+		return true;
+	case P_REG_TX_CAPTURE_L:
+		*high_addr = P_REG_TX_CAPTURE_U;
+		return true;
+	case P_REG_RX_CAPTURE_L:
+		*high_addr = P_REG_RX_CAPTURE_U;
+		return true;
+	case P_REG_TX_TIMER_INC_PRE_L:
+		*high_addr = P_REG_TX_TIMER_INC_PRE_U;
+		return true;
+	case P_REG_RX_TIMER_INC_PRE_L:
+		*high_addr = P_REG_RX_TIMER_INC_PRE_U;
+		return true;
+	default:
+		return false;
 	}
+}
 
-	*val = msg.data;
-
-	return 0;
+/**
+ * ice_is_40b_phy_reg_e82x - Check if this is a 40bit PHY register
+ * @low_addr: the low address to check
+ * @high_addr: on return, contains the high address of the 40bit value
+ *
+ * Checks if the provided low address is one of the known 40bit PHY values
+ * split into two registers with the lower 8 bits in the low register and the
+ * upper 32 bits in the high register. If it is, return the appropriate high
+ * register offset to use.
+ */
+static bool ice_is_40b_phy_reg_e82x(u16 low_addr, u16 *high_addr)
+{
+	switch (low_addr) {
+	case P_REG_TIMETUS_L:
+		*high_addr = P_REG_TIMETUS_U;
+		return true;
+	case P_REG_PAR_RX_TUS_L:
+		*high_addr = P_REG_PAR_RX_TUS_U;
+		return true;
+	case P_REG_PAR_TX_TUS_L:
+		*high_addr = P_REG_PAR_TX_TUS_U;
+		return true;
+	case P_REG_PCS_RX_TUS_L:
+		*high_addr = P_REG_PCS_RX_TUS_U;
+		return true;
+	case P_REG_PCS_TX_TUS_L:
+		*high_addr = P_REG_PCS_TX_TUS_U;
+		return true;
+	case P_REG_DESK_PAR_RX_TUS_L:
+		*high_addr = P_REG_DESK_PAR_RX_TUS_U;
+		return true;
+	case P_REG_DESK_PAR_TX_TUS_L:
+		*high_addr = P_REG_DESK_PAR_TX_TUS_U;
+		return true;
+	case P_REG_DESK_PCS_RX_TUS_L:
+		*high_addr = P_REG_DESK_PCS_RX_TUS_U;
+		return true;
+	case P_REG_DESK_PCS_TX_TUS_L:
+		*high_addr = P_REG_DESK_PCS_TX_TUS_U;
+		return true;
+	default:
+		return false;
+	}
 }
 
 /**
- * ice_write_quad_reg_e82x - Write a PHY quad register
+ * ice_read_phy_reg_e82x - Read a PHY register
  * @hw: pointer to the HW struct
- * @quad: quad to write to
- * @offset: quad register offset to write
- * @val: The value to write to the register
+ * @port: PHY port to read from
+ * @offset: PHY register offset to read
+ * @val: on return, the contents read from the PHY
  *
- * Write a quad register over the device sideband queue. Quad registers are
- * shared between multiple PHYs.
+ * Read a PHY register for the given port over the device sideband queue.
  */
-int
-ice_write_quad_reg_e82x(struct ice_hw *hw, u8 quad, u16 offset, u32 val)
+static int
+ice_read_phy_reg_e82x(struct ice_hw *hw, u8 port, u16 offset, u32 *val)
 {
 	struct ice_sbq_msg_input msg = {0};
 	int err;
 
-	err = ice_fill_quad_msg_e82x(hw, &msg, quad, offset);
-	if (err)
-		return err;
-
-	msg.opcode = ice_sbq_msg_wr;
-	msg.data = val;
+	ice_fill_phy_msg_e82x(hw, &msg, port, offset);
+	msg.opcode = ice_sbq_msg_rd;
 
 	err = ice_sbq_rw_reg(hw, &msg);
 	if (err) {
@@ -792,85 +804,81 @@ ice_write_quad_reg_e82x(struct ice_hw *hw, u8 quad, u16 offset, u32 val)
 		return err;
 	}
 
+	*val = msg.data;
+
 	return 0;
 }
 
 /**
- * ice_read_phy_tstamp_e82x - Read a PHY timestamp out of the quad block
+ * ice_read_64b_phy_reg_e82x - Read a 64bit value from PHY registers
  * @hw: pointer to the HW struct
- * @quad: the quad to read from
- * @idx: the timestamp index to read
- * @tstamp: on return, the 40bit timestamp value
+ * @port: PHY port to read from
+ * @low_addr: offset of the lower register to read from
+ * @val: on return, the contents of the 64bit value from the PHY registers
  *
- * Read a 40bit timestamp value out of the two associated registers in the
- * quad memory block that is shared between the internal PHYs of the E822
- * family of devices.
+ * Reads the two registers associated with a 64bit value and returns it in the
+ * val pointer. The offset always specifies the lower register offset to use.
+ * The high offset is looked up. This function only operates on registers
+ * known to be two parts of a 64bit value.
  */
 static int
-ice_read_phy_tstamp_e82x(struct ice_hw *hw, u8 quad, u8 idx, u64 *tstamp)
+ice_read_64b_phy_reg_e82x(struct ice_hw *hw, u8 port, u16 low_addr, u64 *val)
 {
-	u16 lo_addr, hi_addr;
-	u32 lo, hi;
+	u32 low, high;
+	u16 high_addr;
 	int err;
 
-	lo_addr = (u16)TS_L(Q_REG_TX_MEMORY_BANK_START, idx);
-	hi_addr = (u16)TS_H(Q_REG_TX_MEMORY_BANK_START, idx);
+	/* Only operate on registers known to be split into two 32bit
+	 * registers.
+	 */
+	if (!ice_is_64b_phy_reg_e82x(low_addr, &high_addr)) {
+		ice_debug(hw, ICE_DBG_PTP, "Invalid 64b register addr 0x%08x\n",
+			  low_addr);
+		return -EINVAL;
+	}
 
-	err = ice_read_quad_reg_e82x(hw, quad, lo_addr, &lo);
+	err = ice_read_phy_reg_e82x(hw, port, low_addr, &low);
 	if (err) {
-		ice_debug(hw, ICE_DBG_PTP, "Failed to read low PTP timestamp register, err %d\n",
-			  err);
+		ice_debug(hw, ICE_DBG_PTP, "Failed to read from low register 0x%08x\n, err %d",
+			  low_addr, err);
 		return err;
 	}
 
-	err = ice_read_quad_reg_e82x(hw, quad, hi_addr, &hi);
+	err = ice_read_phy_reg_e82x(hw, port, high_addr, &high);
 	if (err) {
-		ice_debug(hw, ICE_DBG_PTP, "Failed to read high PTP timestamp register, err %d\n",
-			  err);
+		ice_debug(hw, ICE_DBG_PTP, "Failed to read from high register 0x%08x\n, err %d",
+			  high_addr, err);
 		return err;
 	}
 
-	/* For E822 based internal PHYs, the timestamp is reported with the
-	 * lower 8 bits in the low register, and the upper 32 bits in the high
-	 * register.
-	 */
-	*tstamp = ((u64)hi) << TS_PHY_HIGH_S | ((u64)lo & TS_PHY_LOW_M);
+	*val = (u64)high << 32 | low;
 
 	return 0;
 }
 
 /**
- * ice_clear_phy_tstamp_e82x - Clear a timestamp from the quad block
+ * ice_write_phy_reg_e82x - Write a PHY register
  * @hw: pointer to the HW struct
- * @quad: the quad to read from
- * @idx: the timestamp index to reset
- *
- * Read the timestamp out of the quad to clear its timestamp status bit from
- * the PHY quad block that is shared between the internal PHYs of the E822
- * devices.
- *
- * Note that unlike E810, software cannot directly write to the quad memory
- * bank registers. E822 relies on the ice_get_phy_tx_tstamp_ready() function
- * to determine which timestamps are valid. Reading a timestamp auto-clears
- * the valid bit.
- *
- * To directly clear the contents of the timestamp block entirely, discarding
- * all timestamp data at once, software should instead use
- * ice_ptp_reset_ts_memory_quad_e82x().
+ * @port: PHY port to write to
+ * @offset: PHY register offset to write
+ * @val: The value to write to the register
  *
- * This function should only be called on an idx whose bit is set according to
- * ice_get_phy_tx_tstamp_ready().
+ * Write a PHY register for the given port over the device sideband queue.
  */
 static int
-ice_clear_phy_tstamp_e82x(struct ice_hw *hw, u8 quad, u8 idx)
+ice_write_phy_reg_e82x(struct ice_hw *hw, u8 port, u16 offset, u32 val)
 {
-	u64 unused_tstamp;
+	struct ice_sbq_msg_input msg = {0};
 	int err;
 
-	err = ice_read_phy_tstamp_e82x(hw, quad, idx, &unused_tstamp);
+	ice_fill_phy_msg_e82x(hw, &msg, port, offset);
+	msg.opcode = ice_sbq_msg_wr;
+	msg.data = val;
+
+	err = ice_sbq_rw_reg(hw, &msg);
 	if (err) {
-		ice_debug(hw, ICE_DBG_PTP, "Failed to read the timestamp register for quad %u, idx %u, err %d\n",
-			  quad, idx, err);
+		ice_debug(hw, ICE_DBG_PTP, "Failed to send message to PHY, err %d\n",
+			  err);
 		return err;
 	}
 
@@ -878,312 +886,307 @@ ice_clear_phy_tstamp_e82x(struct ice_hw *hw, u8 quad, u8 idx)
 }
 
 /**
- * ice_ptp_reset_ts_memory_quad_e82x - Clear all timestamps from the quad block
- * @hw: pointer to the HW struct
- * @quad: the quad to read from
- *
- * Clear all timestamps from the PHY quad block that is shared between the
- * internal PHYs on the E822 devices.
- */
-void ice_ptp_reset_ts_memory_quad_e82x(struct ice_hw *hw, u8 quad)
-{
-	ice_write_quad_reg_e82x(hw, quad, Q_REG_TS_CTRL, Q_REG_TS_CTRL_M);
-	ice_write_quad_reg_e82x(hw, quad, Q_REG_TS_CTRL, ~(u32)Q_REG_TS_CTRL_M);
-}
-
-/**
- * ice_ptp_reset_ts_memory_e82x - Clear all timestamps from all quad blocks
- * @hw: pointer to the HW struct
- */
-static void ice_ptp_reset_ts_memory_e82x(struct ice_hw *hw)
-{
-	unsigned int quad;
-
-	for (quad = 0; quad < ICE_GET_QUAD_NUM(hw->ptp.num_lports); quad++)
-		ice_ptp_reset_ts_memory_quad_e82x(hw, quad);
-}
-
-/**
- * ice_read_cgu_reg_e82x - Read a CGU register
+ * ice_write_40b_phy_reg_e82x - Write a 40b value to the PHY
  * @hw: pointer to the HW struct
- * @addr: Register address to read
- * @val: storage for register value read
+ * @port: port to write to
+ * @low_addr: offset of the low register
+ * @val: 40b value to write
  *
- * Read the contents of a register of the Clock Generation Unit. Only
- * applicable to E822 devices.
+ * Write the provided 40b value to the two associated registers by splitting
+ * it up into two chunks, the lower 8 bits and the upper 32 bits.
  */
 static int
-ice_read_cgu_reg_e82x(struct ice_hw *hw, u32 addr, u32 *val)
+ice_write_40b_phy_reg_e82x(struct ice_hw *hw, u8 port, u16 low_addr, u64 val)
 {
-	struct ice_sbq_msg_input cgu_msg;
+	u32 low, high;
+	u16 high_addr;
 	int err;
 
-	cgu_msg.opcode = ice_sbq_msg_rd;
-	cgu_msg.dest_dev = cgu;
-	cgu_msg.msg_addr_low = addr;
-	cgu_msg.msg_addr_high = 0x0;
+	/* Only operate on registers known to be split into a lower 8 bit
+	 * register and an upper 32 bit register.
+	 */
+	if (!ice_is_40b_phy_reg_e82x(low_addr, &high_addr)) {
+		ice_debug(hw, ICE_DBG_PTP, "Invalid 40b register addr 0x%08x\n",
+			  low_addr);
+		return -EINVAL;
+	}
+	low = FIELD_GET(P_REG_40B_LOW_M, val);
+	high = (u32)(val >> P_REG_40B_HIGH_S);
 
-	err = ice_sbq_rw_reg(hw, &cgu_msg);
+	err = ice_write_phy_reg_e82x(hw, port, low_addr, low);
 	if (err) {
-		ice_debug(hw, ICE_DBG_PTP, "Failed to read CGU register 0x%04x, err %d\n",
-			  addr, err);
+		ice_debug(hw, ICE_DBG_PTP, "Failed to write to low register 0x%08x\n, err %d",
+			  low_addr, err);
 		return err;
 	}
 
-	*val = cgu_msg.data;
+	err = ice_write_phy_reg_e82x(hw, port, high_addr, high);
+	if (err) {
+		ice_debug(hw, ICE_DBG_PTP, "Failed to write to high register 0x%08x\n, err %d",
+			  high_addr, err);
+		return err;
+	}
 
-	return err;
+	return 0;
 }
 
 /**
- * ice_write_cgu_reg_e82x - Write a CGU register
+ * ice_write_64b_phy_reg_e82x - Write a 64bit value to PHY registers
  * @hw: pointer to the HW struct
- * @addr: Register address to write
- * @val: value to write into the register
+ * @port: PHY port to read from
+ * @low_addr: offset of the lower register to read from
+ * @val: the contents of the 64bit value to write to PHY
  *
- * Write the specified value to a register of the Clock Generation Unit. Only
- * applicable to E822 devices.
+ * Write the 64bit value to the two associated 32bit PHY registers. The offset
+ * is always specified as the lower register, and the high address is looked
+ * up. This function only operates on registers known to be two parts of
+ * a 64bit value.
  */
 static int
-ice_write_cgu_reg_e82x(struct ice_hw *hw, u32 addr, u32 val)
+ice_write_64b_phy_reg_e82x(struct ice_hw *hw, u8 port, u16 low_addr, u64 val)
 {
-	struct ice_sbq_msg_input cgu_msg;
+	u32 low, high;
+	u16 high_addr;
 	int err;
 
-	cgu_msg.opcode = ice_sbq_msg_wr;
-	cgu_msg.dest_dev = cgu;
-	cgu_msg.msg_addr_low = addr;
-	cgu_msg.msg_addr_high = 0x0;
-	cgu_msg.data = val;
+	/* Only operate on registers known to be split into two 32bit
+	 * registers.
+	 */
+	if (!ice_is_64b_phy_reg_e82x(low_addr, &high_addr)) {
+		ice_debug(hw, ICE_DBG_PTP, "Invalid 64b register addr 0x%08x\n",
+			  low_addr);
+		return -EINVAL;
+	}
+
+	low = lower_32_bits(val);
+	high = upper_32_bits(val);
 
-	err = ice_sbq_rw_reg(hw, &cgu_msg);
+	err = ice_write_phy_reg_e82x(hw, port, low_addr, low);
 	if (err) {
-		ice_debug(hw, ICE_DBG_PTP, "Failed to write CGU register 0x%04x, err %d\n",
-			  addr, err);
+		ice_debug(hw, ICE_DBG_PTP, "Failed to write to low register 0x%08x\n, err %d",
+			  low_addr, err);
 		return err;
 	}
 
-	return err;
-}
-
-/**
- * ice_clk_freq_str - Convert time_ref_freq to string
- * @clk_freq: Clock frequency
- *
- * Convert the specified TIME_REF clock frequency to a string.
- */
-static const char *ice_clk_freq_str(u8 clk_freq)
-{
-	switch ((enum ice_time_ref_freq)clk_freq) {
-	case ICE_TIME_REF_FREQ_25_000:
-		return "25 MHz";
-	case ICE_TIME_REF_FREQ_122_880:
-		return "122.88 MHz";
-	case ICE_TIME_REF_FREQ_125_000:
-		return "125 MHz";
-	case ICE_TIME_REF_FREQ_153_600:
-		return "153.6 MHz";
-	case ICE_TIME_REF_FREQ_156_250:
-		return "156.25 MHz";
-	case ICE_TIME_REF_FREQ_245_760:
-		return "245.76 MHz";
-	default:
-		return "Unknown";
+	err = ice_write_phy_reg_e82x(hw, port, high_addr, high);
+	if (err) {
+		ice_debug(hw, ICE_DBG_PTP, "Failed to write to high register 0x%08x\n, err %d",
+			  high_addr, err);
+		return err;
 	}
+
+	return 0;
 }
 
 /**
- * ice_clk_src_str - Convert time_ref_src to string
- * @clk_src: Clock source
+ * ice_fill_quad_msg_e82x - Fill message data for quad register access
+ * @hw: pointer to the HW struct
+ * @msg: the PHY message buffer to fill in
+ * @quad: the quad to access
+ * @offset: the register offset
+ *
+ * Fill a message buffer for accessing a register in a quad shared between
+ * multiple PHYs.
  *
- * Convert the specified clock source to its string name.
+ * Return:
+ * * %0       - OK
+ * * %-EINVAL - invalid quad number
  */
-static const char *ice_clk_src_str(u8 clk_src)
+static int ice_fill_quad_msg_e82x(struct ice_hw *hw,
+				  struct ice_sbq_msg_input *msg, u8 quad,
+				  u16 offset)
 {
-	switch ((enum ice_clk_src)clk_src) {
-	case ICE_CLK_SRC_TCX0:
-		return "TCX0";
-	case ICE_CLK_SRC_TIME_REF:
-		return "TIME_REF";
-	default:
-		return "Unknown";
-	}
+	u32 addr;
+
+	if (quad >= ICE_GET_QUAD_NUM(hw->ptp.num_lports))
+		return -EINVAL;
+
+	msg->dest_dev = rmn_0;
+
+	if (!(quad % ICE_GET_QUAD_NUM(hw->ptp.ports_per_phy)))
+		addr = Q_0_BASE + offset;
+	else
+		addr = Q_1_BASE + offset;
+
+	msg->msg_addr_low = lower_16_bits(addr);
+	msg->msg_addr_high = upper_16_bits(addr);
+
+	return 0;
 }
 
 /**
- * ice_cfg_cgu_pll_e82x - Configure the Clock Generation Unit
+ * ice_read_quad_reg_e82x - Read a PHY quad register
  * @hw: pointer to the HW struct
- * @clk_freq: Clock frequency to program
- * @clk_src: Clock source to select (TIME_REF, or TCX0)
+ * @quad: quad to read from
+ * @offset: quad register offset to read
+ * @val: on return, the contents read from the quad
  *
- * Configure the Clock Generation Unit with the desired clock frequency and
- * time reference, enabling the PLL which drives the PTP hardware clock.
+ * Read a quad register over the device sideband queue. Quad registers are
+ * shared between multiple PHYs.
  */
-static int
-ice_cfg_cgu_pll_e82x(struct ice_hw *hw, enum ice_time_ref_freq clk_freq,
-		     enum ice_clk_src clk_src)
+int
+ice_read_quad_reg_e82x(struct ice_hw *hw, u8 quad, u16 offset, u32 *val)
 {
-	union tspll_ro_bwm_lf bwm_lf;
-	union nac_cgu_dword19 dw19;
-	union nac_cgu_dword22 dw22;
-	union nac_cgu_dword24 dw24;
-	union nac_cgu_dword9 dw9;
+	struct ice_sbq_msg_input msg = {0};
 	int err;
 
-	if (clk_freq >= NUM_ICE_TIME_REF_FREQ) {
-		dev_warn(ice_hw_to_dev(hw), "Invalid TIME_REF frequency %u\n",
-			 clk_freq);
-		return -EINVAL;
-	}
-
-	if (clk_src >= NUM_ICE_CLK_SRC) {
-		dev_warn(ice_hw_to_dev(hw), "Invalid clock source %u\n",
-			 clk_src);
-		return -EINVAL;
-	}
-
-	if (clk_src == ICE_CLK_SRC_TCX0 &&
-	    clk_freq != ICE_TIME_REF_FREQ_25_000) {
-		dev_warn(ice_hw_to_dev(hw),
-			 "TCX0 only supports 25 MHz frequency\n");
-		return -EINVAL;
-	}
-
-	err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD9, &dw9.val);
+	err = ice_fill_quad_msg_e82x(hw, &msg, quad, offset);
 	if (err)
 		return err;
 
-	err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD24, &dw24.val);
-	if (err)
-		return err;
+	msg.opcode = ice_sbq_msg_rd;
 
-	err = ice_read_cgu_reg_e82x(hw, TSPLL_RO_BWM_LF, &bwm_lf.val);
-	if (err)
+	err = ice_sbq_rw_reg(hw, &msg);
+	if (err) {
+		ice_debug(hw, ICE_DBG_PTP, "Failed to send message to PHY, err %d\n",
+			  err);
 		return err;
-
-	/* Log the current clock configuration */
-	ice_debug(hw, ICE_DBG_PTP, "Current CGU configuration -- %s, clk_src %s, clk_freq %s, PLL %s\n",
-		  dw24.field.ts_pll_enable ? "enabled" : "disabled",
-		  ice_clk_src_str(dw24.field.time_ref_sel),
-		  ice_clk_freq_str(dw9.field.time_ref_freq_sel),
-		  bwm_lf.field.plllock_true_lock_cri ? "locked" : "unlocked");
-
-	/* Disable the PLL before changing the clock source or frequency */
-	if (dw24.field.ts_pll_enable) {
-		dw24.field.ts_pll_enable = 0;
-
-		err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD24, dw24.val);
-		if (err)
-			return err;
 	}
 
-	/* Set the frequency */
-	dw9.field.time_ref_freq_sel = clk_freq;
-	err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD9, dw9.val);
-	if (err)
-		return err;
-
-	/* Configure the TS PLL feedback divisor */
-	err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD19, &dw19.val);
-	if (err)
-		return err;
+	*val = msg.data;
 
-	dw19.field.tspll_fbdiv_intgr = e822_cgu_params[clk_freq].feedback_div;
-	dw19.field.tspll_ndivratio = 1;
+	return 0;
+}
 
-	err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD19, dw19.val);
-	if (err)
-		return err;
+/**
+ * ice_write_quad_reg_e82x - Write a PHY quad register
+ * @hw: pointer to the HW struct
+ * @quad: quad to write to
+ * @offset: quad register offset to write
+ * @val: The value to write to the register
+ *
+ * Write a quad register over the device sideband queue. Quad registers are
+ * shared between multiple PHYs.
+ */
+int
+ice_write_quad_reg_e82x(struct ice_hw *hw, u8 quad, u16 offset, u32 val)
+{
+	struct ice_sbq_msg_input msg = {0};
+	int err;
 
-	/* Configure the TS PLL post divisor */
-	err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD22, &dw22.val);
+	err = ice_fill_quad_msg_e82x(hw, &msg, quad, offset);
 	if (err)
 		return err;
 
-	dw22.field.time1588clk_div = e822_cgu_params[clk_freq].post_pll_div;
-	dw22.field.time1588clk_sel_div2 = 0;
-
-	err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD22, dw22.val);
-	if (err)
-		return err;
+	msg.opcode = ice_sbq_msg_wr;
+	msg.data = val;
 
-	/* Configure the TS PLL pre divisor and clock source */
-	err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD24, &dw24.val);
-	if (err)
+	err = ice_sbq_rw_reg(hw, &msg);
+	if (err) {
+		ice_debug(hw, ICE_DBG_PTP, "Failed to send message to PHY, err %d\n",
+			  err);
 		return err;
+	}
 
-	dw24.field.ref1588_ck_div = e822_cgu_params[clk_freq].refclk_pre_div;
-	dw24.field.tspll_fbdiv_frac = e822_cgu_params[clk_freq].frac_n_div;
-	dw24.field.time_ref_sel = clk_src;
+	return 0;
+}
 
-	err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD24, dw24.val);
-	if (err)
-		return err;
+/**
+ * ice_read_phy_tstamp_e82x - Read a PHY timestamp out of the quad block
+ * @hw: pointer to the HW struct
+ * @quad: the quad to read from
+ * @idx: the timestamp index to read
+ * @tstamp: on return, the 40bit timestamp value
+ *
+ * Read a 40bit timestamp value out of the two associated registers in the
+ * quad memory block that is shared between the internal PHYs of the E822
+ * family of devices.
+ */
+static int
+ice_read_phy_tstamp_e82x(struct ice_hw *hw, u8 quad, u8 idx, u64 *tstamp)
+{
+	u16 lo_addr, hi_addr;
+	u32 lo, hi;
+	int err;
 
-	/* Finally, enable the PLL */
-	dw24.field.ts_pll_enable = 1;
+	lo_addr = (u16)TS_L(Q_REG_TX_MEMORY_BANK_START, idx);
+	hi_addr = (u16)TS_H(Q_REG_TX_MEMORY_BANK_START, idx);
 
-	err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD24, dw24.val);
-	if (err)
+	err = ice_read_quad_reg_e82x(hw, quad, lo_addr, &lo);
+	if (err) {
+		ice_debug(hw, ICE_DBG_PTP, "Failed to read low PTP timestamp register, err %d\n",
+			  err);
 		return err;
+	}
 
-	/* Wait to verify if the PLL locks */
-	usleep_range(1000, 5000);
-
-	err = ice_read_cgu_reg_e82x(hw, TSPLL_RO_BWM_LF, &bwm_lf.val);
-	if (err)
+	err = ice_read_quad_reg_e82x(hw, quad, hi_addr, &hi);
+	if (err) {
+		ice_debug(hw, ICE_DBG_PTP, "Failed to read high PTP timestamp register, err %d\n",
+			  err);
 		return err;
-
-	if (!bwm_lf.field.plllock_true_lock_cri) {
-		dev_warn(ice_hw_to_dev(hw), "CGU PLL failed to lock\n");
-		return -EBUSY;
 	}
 
-	/* Log the current clock configuration */
-	ice_debug(hw, ICE_DBG_PTP, "New CGU configuration -- %s, clk_src %s, clk_freq %s, PLL %s\n",
-		  dw24.field.ts_pll_enable ? "enabled" : "disabled",
-		  ice_clk_src_str(dw24.field.time_ref_sel),
-		  ice_clk_freq_str(dw9.field.time_ref_freq_sel),
-		  bwm_lf.field.plllock_true_lock_cri ? "locked" : "unlocked");
+	/* For E822 based internal PHYs, the timestamp is reported with the
+	 * lower 8 bits in the low register, and the upper 32 bits in the high
+	 * register.
+	 */
+	*tstamp = FIELD_PREP(TS_PHY_HIGH_M, hi) | FIELD_PREP(TS_PHY_LOW_M, lo);
 
 	return 0;
 }
 
 /**
- * ice_init_cgu_e82x - Initialize CGU with settings from firmware
- * @hw: pointer to the HW structure
+ * ice_clear_phy_tstamp_e82x - Clear a timestamp from the quad block
+ * @hw: pointer to the HW struct
+ * @quad: the quad to read from
+ * @idx: the timestamp index to reset
  *
- * Initialize the Clock Generation Unit of the E822 device.
+ * Read the timestamp out of the quad to clear its timestamp status bit from
+ * the PHY quad block that is shared between the internal PHYs of the E822
+ * devices.
+ *
+ * Note that unlike E810, software cannot directly write to the quad memory
+ * bank registers. E822 relies on the ice_get_phy_tx_tstamp_ready() function
+ * to determine which timestamps are valid. Reading a timestamp auto-clears
+ * the valid bit.
+ *
+ * To directly clear the contents of the timestamp block entirely, discarding
+ * all timestamp data at once, software should instead use
+ * ice_ptp_reset_ts_memory_quad_e82x().
+ *
+ * This function should only be called on an idx whose bit is set according to
+ * ice_get_phy_tx_tstamp_ready().
  */
-static int ice_init_cgu_e82x(struct ice_hw *hw)
+static int
+ice_clear_phy_tstamp_e82x(struct ice_hw *hw, u8 quad, u8 idx)
 {
-	struct ice_ts_func_info *ts_info = &hw->func_caps.ts_func_info;
-	union tspll_cntr_bist_settings cntr_bist;
+	u64 unused_tstamp;
 	int err;
 
-	err = ice_read_cgu_reg_e82x(hw, TSPLL_CNTR_BIST_SETTINGS,
-				    &cntr_bist.val);
-	if (err)
+	err = ice_read_phy_tstamp_e82x(hw, quad, idx, &unused_tstamp);
+	if (err) {
+		ice_debug(hw, ICE_DBG_PTP, "Failed to read the timestamp register for quad %u, idx %u, err %d\n",
+			  quad, idx, err);
 		return err;
+	}
 
-	/* Disable sticky lock detection so lock err reported is accurate */
-	cntr_bist.field.i_plllock_sel_0 = 0;
-	cntr_bist.field.i_plllock_sel_1 = 0;
+	return 0;
+}
 
-	err = ice_write_cgu_reg_e82x(hw, TSPLL_CNTR_BIST_SETTINGS,
-				     cntr_bist.val);
-	if (err)
-		return err;
+/**
+ * ice_ptp_reset_ts_memory_quad_e82x - Clear all timestamps from the quad block
+ * @hw: pointer to the HW struct
+ * @quad: the quad to read from
+ *
+ * Clear all timestamps from the PHY quad block that is shared between the
+ * internal PHYs on the E822 devices.
+ */
+void ice_ptp_reset_ts_memory_quad_e82x(struct ice_hw *hw, u8 quad)
+{
+	ice_write_quad_reg_e82x(hw, quad, Q_REG_TS_CTRL, Q_REG_TS_CTRL_M);
+	ice_write_quad_reg_e82x(hw, quad, Q_REG_TS_CTRL, ~(u32)Q_REG_TS_CTRL_M);
+}
 
-	/* Configure the CGU PLL using the parameters from the function
-	 * capabilities.
-	 */
-	err = ice_cfg_cgu_pll_e82x(hw, ts_info->time_ref,
-				   (enum ice_clk_src)ts_info->clk_src);
-	if (err)
-		return err;
+/**
+ * ice_ptp_reset_ts_memory_e82x - Clear all timestamps from all quad blocks
+ * @hw: pointer to the HW struct
+ */
+static void ice_ptp_reset_ts_memory_e82x(struct ice_hw *hw)
+{
+	unsigned int quad;
 
-	return 0;
+	for (quad = 0; quad < ICE_GET_QUAD_NUM(hw->ptp.num_lports); quad++)
+		ice_ptp_reset_ts_memory_quad_e82x(hw, quad);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
index 5223e17d28063..2d8ba9c2251d3 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
@@ -377,7 +377,7 @@ int ice_cgu_get_output_pin_state_caps(struct ice_hw *hw, u8 pin_id,
 #define P_REG_TIMETUS_L			0x410
 #define P_REG_TIMETUS_U			0x414
 
-#define P_REG_40B_LOW_M			0xFF
+#define P_REG_40B_LOW_M			GENMASK(7, 0)
 #define P_REG_40B_HIGH_S		8
 
 /* PHY window length registers */
-- 
GitLab


From 1f374d57c39386520586539641cafc999d0f3ef5 Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Tue, 28 May 2024 16:03:56 -0700
Subject: [PATCH 679/950] ice: Introduce ice_get_base_incval() helper

Add a new helper for getting base clock increment value for specific HW.

Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Arkadiusz Kubalewski <arkadiusz.kubalewski@intel.com>
Signed-off-by: Karol Kolacinski <karol.kolacinski@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20240528-next-2024-05-28-ptp-refactors-v1-6-c082739bb6f6@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/ice/ice_ptp.c    |  9 +--------
 drivers/net/ethernet/intel/ice/ice_ptp_hw.h | 18 ++++++++++++++++++
 2 files changed, 19 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c
index 4ed2213247f72..923011c9609a1 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.c
@@ -7,8 +7,6 @@
 
 #define E810_OUT_PROP_DELAY_NS 1
 
-#define UNKNOWN_INCVAL_E82X 0x100000000ULL
-
 static const struct ptp_pin_desc ice_pin_desc_e810t[] = {
 	/* name    idx   func         chan */
 	{ "GNSS",  GNSS, PTP_PF_EXTTS, 0, { 0, } },
@@ -1210,12 +1208,7 @@ static u64 ice_base_incval(struct ice_pf *pf)
 	struct ice_hw *hw = &pf->hw;
 	u64 incval;
 
-	if (ice_is_e810(hw))
-		incval = ICE_PTP_NOMINAL_INCVAL_E810;
-	else if (ice_e82x_time_ref(hw) < NUM_ICE_TIME_REF_FREQ)
-		incval = ice_e82x_nominal_incval(ice_e82x_time_ref(hw));
-	else
-		incval = UNKNOWN_INCVAL_E82X;
+	incval = ice_get_base_incval(hw);
 
 	dev_dbg(ice_pf_to_dev(pf), "PTP: using base increment value of 0x%016llx\n",
 		incval);
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
index 2d8ba9c2251d3..3fe12a1694fc0 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
@@ -285,6 +285,24 @@ int ice_get_cgu_rclk_pin_info(struct ice_hw *hw, u8 *base_idx, u8 *pin_num);
 int ice_cgu_get_output_pin_state_caps(struct ice_hw *hw, u8 pin_id,
 				      unsigned long *caps);
 
+/**
+ * ice_get_base_incval - Get base clock increment value
+ * @hw: pointer to the HW struct
+ *
+ * Return: base clock increment value for supported PHYs, 0 otherwise
+ */
+static inline u64 ice_get_base_incval(struct ice_hw *hw)
+{
+	switch (hw->ptp.phy_model) {
+	case ICE_PHY_E810:
+		return ICE_PTP_NOMINAL_INCVAL_E810;
+	case ICE_PHY_E82X:
+		return ice_e82x_nominal_incval(ice_e82x_time_ref(hw));
+	default:
+		return 0;
+	}
+}
+
 #define PFTSYN_SEM_BYTES	4
 
 #define ICE_PTP_CLOCK_INDEX_0	0x00
-- 
GitLab


From 7cab44f1c35f5fb01930e592aee9cc460f17903d Mon Sep 17 00:00:00 2001
From: Sergey Temerkhanov <sergey.temerkhanov@intel.com>
Date: Tue, 28 May 2024 16:03:57 -0700
Subject: [PATCH 680/950] ice: Introduce ETH56G PHY model for E825C products

E825C products feature a new PHY model - ETH56G.

Introduces all necessary PHY definitions, functions etc. for ETH56G PHY,
analogous to E82X and E810 ones with addition of a few HW-specific
functionalities for ETH56G like one-step timestamping.

It ensures correct PTP initialization and operation for E825C products.

Co-developed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Co-developed-by: Michal Michalik <michal.michalik@intel.com>
Signed-off-by: Michal Michalik <michal.michalik@intel.com>
Signed-off-by: Sergey Temerkhanov <sergey.temerkhanov@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Arkadiusz Kubalewski <arkadiusz.kubalewski@intel.com>
Co-developed-by: Karol Kolacinski <karol.kolacinski@intel.com>
Signed-off-by: Karol Kolacinski <karol.kolacinski@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20240528-next-2024-05-28-ptp-refactors-v1-7-c082739bb6f6@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/ice/ice_common.c   |   10 +-
 drivers/net/ethernet/intel/ice/ice_common.h   |    1 +
 drivers/net/ethernet/intel/ice/ice_ptp.c      |  101 +-
 drivers/net/ethernet/intel/ice/ice_ptp.h      |    1 +
 .../net/ethernet/intel/ice/ice_ptp_consts.h   |  315 +++
 drivers/net/ethernet/intel/ice/ice_ptp_hw.c   | 2069 ++++++++++++++++-
 drivers/net/ethernet/intel/ice/ice_ptp_hw.h   |  240 +-
 drivers/net/ethernet/intel/ice/ice_sbq_cmd.h  |   10 +-
 drivers/net/ethernet/intel/ice/ice_type.h     |   20 +-
 9 files changed, 2613 insertions(+), 154 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index 61eb6af37f8e2..c37042d9bdd9b 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -3067,11 +3067,13 @@ bool ice_is_100m_speed_supported(struct ice_hw *hw)
  * Note: In the structure of [phy_type_low, phy_type_high], there should
  * be one bit set, as this function will convert one PHY type to its
  * speed.
- * If no bit gets set, ICE_AQ_LINK_SPEED_UNKNOWN will be returned
- * If more than one bit gets set, ICE_AQ_LINK_SPEED_UNKNOWN will be returned
+ *
+ * Return:
+ * * PHY speed for recognized PHY type
+ * * If no bit gets set, ICE_AQ_LINK_SPEED_UNKNOWN will be returned
+ * * If more than one bit gets set, ICE_AQ_LINK_SPEED_UNKNOWN will be returned
  */
-static u16
-ice_get_link_speed_based_on_phy_type(u64 phy_type_low, u64 phy_type_high)
+u16 ice_get_link_speed_based_on_phy_type(u64 phy_type_low, u64 phy_type_high)
 {
 	u16 speed_phy_type_high = ICE_AQ_LINK_SPEED_UNKNOWN;
 	u16 speed_phy_type_low = ICE_AQ_LINK_SPEED_UNKNOWN;
diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h
index 70f57340eb0df..86cc1df469dd9 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.h
+++ b/drivers/net/ethernet/intel/ice/ice_common.h
@@ -262,6 +262,7 @@ int
 ice_aq_get_gpio(struct ice_hw *hw, u16 gpio_ctrl_handle, u8 pin_idx,
 		bool *value, struct ice_sq_cd *cd);
 bool ice_is_100m_speed_supported(struct ice_hw *hw);
+u16 ice_get_link_speed_based_on_phy_type(u64 phy_type_low, u64 phy_type_high);
 int
 ice_aq_set_lldp_mib(struct ice_hw *hw, u8 mib_type, void *buf, u16 buf_size,
 		    struct ice_sq_cd *cd);
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c
index 923011c9609a1..3af0f4a2c3be8 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.c
@@ -1011,6 +1011,28 @@ ice_ptp_release_tx_tracker(struct ice_pf *pf, struct ice_ptp_tx *tx)
 	tx->len = 0;
 }
 
+/**
+ * ice_ptp_init_tx_eth56g - Initialize tracking for Tx timestamps
+ * @pf: Board private structure
+ * @tx: the Tx tracking structure to initialize
+ * @port: the port this structure tracks
+ *
+ * Initialize the Tx timestamp tracker for this port. ETH56G PHYs
+ * have independent memory blocks for all ports.
+ *
+ * Return: 0 for success, -ENOMEM when failed to allocate Tx tracker
+ */
+static int ice_ptp_init_tx_eth56g(struct ice_pf *pf, struct ice_ptp_tx *tx,
+				  u8 port)
+{
+	tx->block = port;
+	tx->offset = 0;
+	tx->len = INDEX_PER_PORT_ETH56G;
+	tx->has_ready_bitmap = 1;
+
+	return ice_ptp_alloc_tx_tracker(tx);
+}
+
 /**
  * ice_ptp_init_tx_e82x - Initialize tracking for Tx timestamps
  * @pf: Board private structure
@@ -1341,10 +1363,19 @@ ice_ptp_port_phy_stop(struct ice_ptp_port *ptp_port)
 
 	mutex_lock(&ptp_port->ps_lock);
 
-	kthread_cancel_delayed_work_sync(&ptp_port->ov_work);
+	switch (hw->ptp.phy_model) {
+	case ICE_PHY_ETH56G:
+		err = ice_stop_phy_timer_eth56g(hw, port, true);
+		break;
+	case ICE_PHY_E82X:
+		kthread_cancel_delayed_work_sync(&ptp_port->ov_work);
 
-	err = ice_stop_phy_timer_e82x(hw, port, true);
-	if (err)
+		err = ice_stop_phy_timer_e82x(hw, port, true);
+		break;
+	default:
+		err = -ENODEV;
+	}
+	if (err && err != -EBUSY)
 		dev_err(ice_pf_to_dev(pf), "PTP failed to set PHY port %d down, err %d\n",
 			port, err);
 
@@ -1378,27 +1409,39 @@ ice_ptp_port_phy_restart(struct ice_ptp_port *ptp_port)
 
 	mutex_lock(&ptp_port->ps_lock);
 
-	kthread_cancel_delayed_work_sync(&ptp_port->ov_work);
+	switch (hw->ptp.phy_model) {
+	case ICE_PHY_ETH56G:
+		err = ice_start_phy_timer_eth56g(hw, port);
+		break;
+	case ICE_PHY_E82X:
+		/* Start the PHY timer in Vernier mode */
+		kthread_cancel_delayed_work_sync(&ptp_port->ov_work);
 
-	/* temporarily disable Tx timestamps while calibrating PHY offset */
-	spin_lock_irqsave(&ptp_port->tx.lock, flags);
-	ptp_port->tx.calibrating = true;
-	spin_unlock_irqrestore(&ptp_port->tx.lock, flags);
-	ptp_port->tx_fifo_busy_cnt = 0;
+		/* temporarily disable Tx timestamps while calibrating
+		 * PHY offset
+		 */
+		spin_lock_irqsave(&ptp_port->tx.lock, flags);
+		ptp_port->tx.calibrating = true;
+		spin_unlock_irqrestore(&ptp_port->tx.lock, flags);
+		ptp_port->tx_fifo_busy_cnt = 0;
 
-	/* Start the PHY timer in Vernier mode */
-	err = ice_start_phy_timer_e82x(hw, port);
-	if (err)
-		goto out_unlock;
+		/* Start the PHY timer in Vernier mode */
+		err = ice_start_phy_timer_e82x(hw, port);
+		if (err)
+			break;
 
-	/* Enable Tx timestamps right away */
-	spin_lock_irqsave(&ptp_port->tx.lock, flags);
-	ptp_port->tx.calibrating = false;
-	spin_unlock_irqrestore(&ptp_port->tx.lock, flags);
+		/* Enable Tx timestamps right away */
+		spin_lock_irqsave(&ptp_port->tx.lock, flags);
+		ptp_port->tx.calibrating = false;
+		spin_unlock_irqrestore(&ptp_port->tx.lock, flags);
 
-	kthread_queue_delayed_work(pf->ptp.kworker, &ptp_port->ov_work, 0);
+		kthread_queue_delayed_work(pf->ptp.kworker, &ptp_port->ov_work,
+					   0);
+		break;
+	default:
+		err = -ENODEV;
+	}
 
-out_unlock:
 	if (err)
 		dev_err(ice_pf_to_dev(pf), "PTP failed to set PHY port %d up, err %d\n",
 			port, err);
@@ -1436,6 +1479,7 @@ void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup)
 	case ICE_PHY_E810:
 		/* Do not reconfigure E810 PHY */
 		return;
+	case ICE_PHY_ETH56G:
 	case ICE_PHY_E82X:
 		ice_ptp_port_phy_restart(ptp_port);
 		return;
@@ -1465,6 +1509,22 @@ static int ice_ptp_cfg_phy_interrupt(struct ice_pf *pf, bool ena, u32 threshold)
 	ice_ptp_reset_ts_memory(hw);
 
 	switch (hw->ptp.phy_model) {
+	case ICE_PHY_ETH56G: {
+		int port;
+
+		for (port = 0; port < hw->ptp.num_lports; port++) {
+			int err;
+
+			err = ice_phy_cfg_intr_eth56g(hw, port, ena, threshold);
+			if (err) {
+				dev_err(dev, "Failed to configure PHY interrupt for port %d, err %d\n",
+					port, err);
+				return err;
+			}
+		}
+
+		return 0;
+	}
 	case ICE_PHY_E82X: {
 		int quad;
 
@@ -3075,6 +3135,9 @@ static int ice_ptp_init_port(struct ice_pf *pf, struct ice_ptp_port *ptp_port)
 	mutex_init(&ptp_port->ps_lock);
 
 	switch (hw->ptp.phy_model) {
+	case ICE_PHY_ETH56G:
+		return ice_ptp_init_tx_eth56g(pf, &ptp_port->tx,
+					      ptp_port->port_num);
 	case ICE_PHY_E810:
 		return ice_ptp_init_tx_e810(pf, &ptp_port->tx);
 	case ICE_PHY_E82X:
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.h b/drivers/net/ethernet/intel/ice/ice_ptp.h
index 3af20025043a6..e0c23aaedc125 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.h
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.h
@@ -153,6 +153,7 @@ struct ice_ptp_tx {
 #define INDEX_PER_QUAD			64
 #define INDEX_PER_PORT_E82X		16
 #define INDEX_PER_PORT_E810		64
+#define INDEX_PER_PORT_ETH56G		64
 
 /**
  * struct ice_ptp_port - data used to initialize an external port for PTP
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_consts.h b/drivers/net/ethernet/intel/ice/ice_ptp_consts.h
index 2c4dab0c48ab5..ef180936f60c7 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_consts.h
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_consts.h
@@ -9,6 +9,321 @@
  */
 /* Constants defined for the PTP 1588 clock hardware. */
 
+const struct ice_phy_reg_info_eth56g eth56g_phy_res[NUM_ETH56G_PHY_RES] = {
+	/* ETH56G_PHY_REG_PTP */
+	{
+		/* base_addr */
+		{
+			0x092000,
+			0x126000,
+			0x1BA000,
+			0x24E000,
+			0x2E2000,
+		},
+		/* step */
+		0x98,
+	},
+	/* ETH56G_PHY_MEM_PTP */
+	{
+		/* base_addr */
+		{
+			0x093000,
+			0x127000,
+			0x1BB000,
+			0x24F000,
+			0x2E3000,
+		},
+		/* step */
+		0x200,
+	},
+	/* ETH56G_PHY_REG_XPCS */
+	{
+		/* base_addr */
+		{
+			0x000000,
+			0x009400,
+			0x128000,
+			0x1BC000,
+			0x250000,
+		},
+		/* step */
+		0x21000,
+	},
+	/* ETH56G_PHY_REG_MAC */
+	{
+		/* base_addr */
+		{
+			0x085000,
+			0x119000,
+			0x1AD000,
+			0x241000,
+			0x2D5000,
+		},
+		/* step */
+		0x1000,
+	},
+	/* ETH56G_PHY_REG_GPCS */
+	{
+		/* base_addr */
+		{
+			0x084000,
+			0x118000,
+			0x1AC000,
+			0x240000,
+			0x2D4000,
+		},
+		/* step */
+		0x400,
+	},
+};
+
+const
+struct ice_eth56g_mac_reg_cfg eth56g_mac_cfg[NUM_ICE_ETH56G_LNK_SPD] = {
+	[ICE_ETH56G_LNK_SPD_1G] = {
+		.tx_mode = { .def = 6, },
+		.rx_mode = { .def = 6, },
+		.blks_per_clk = 1,
+		.blktime = 0x4000, /* 32 */
+		.tx_offset = {
+			.serdes = 0x6666, /* 51.2 */
+			.no_fec = 0xd066, /* 104.2 */
+			.sfd = 0x3000, /* 24 */
+			.onestep = 0x30000 /* 384 */
+		},
+		.rx_offset = {
+			.serdes = 0xffffc59a, /* -29.2 */
+			.no_fec = 0xffff0a80, /* -122.75 */
+			.sfd = 0x2c00, /* 22 */
+			.bs_ds = 0x19a /* 0.8 */
+			/* Dynamic bitslip 0 equals to 10 */
+		}
+	},
+	[ICE_ETH56G_LNK_SPD_2_5G] = {
+		.tx_mode = { .def = 6, },
+		.rx_mode = { .def = 6, },
+		.blks_per_clk = 1,
+		.blktime = 0x199a, /* 12.8 */
+		.tx_offset = {
+			.serdes = 0x28f6, /* 20.48 */
+			.no_fec = 0x53b8, /* 41.86 */
+			.sfd = 0x1333, /* 9.6 */
+			.onestep = 0x13333 /* 153.6 */
+		},
+		.rx_offset = {
+			.serdes = 0xffffe8a4, /* -11.68 */
+			.no_fec = 0xffff9a76, /* -50.77 */
+			.sfd = 0xf33, /* 7.6 */
+			.bs_ds = 0xa4 /* 0.32 */
+		}
+	},
+	[ICE_ETH56G_LNK_SPD_10G] = {
+		.tx_mode = { .def = 1, },
+		.rx_mode = { .def = 1, },
+		.blks_per_clk = 1,
+		.blktime = 0x666, /* 3.2 */
+		.tx_offset = {
+			.serdes = 0x234c, /* 17.6484848 */
+			.no_fec = 0x8e80, /* 71.25 */
+			.fc = 0xb4a4, /* 90.32 */
+			.sfd = 0x4a4, /* 2.32 */
+			.onestep = 0x4ccd /* 38.4 */
+		},
+		.rx_offset = {
+			.serdes = 0xffffeb27, /* -10.42424 */
+			.no_fec = 0xffffcccd, /* -25.6 */
+			.fc = 0xfffe0014, /* -255.96 */
+			.sfd = 0x4a4, /* 2.32 */
+			.bs_ds = 0x32 /* 0.0969697 */
+		}
+	},
+	[ICE_ETH56G_LNK_SPD_25G] = {
+		.tx_mode = {
+			.def = 1,
+			.rs = 4
+		},
+		.tx_mk_dly = 4,
+		.tx_cw_dly = {
+			.def = 1,
+			.onestep = 6
+		},
+		.rx_mode = {
+			.def = 1,
+			.rs = 4
+		},
+		.rx_mk_dly = {
+			.def = 1,
+			.rs = 1
+		},
+		.rx_cw_dly = {
+			.def = 1,
+			.rs = 1
+		},
+		.blks_per_clk = 1,
+		.blktime = 0x28f, /* 1.28 */
+		.mktime = 0x147b, /* 10.24, only if RS-FEC enabled */
+		.tx_offset = {
+			.serdes = 0xe1e, /* 7.0593939 */
+			.no_fec = 0x3857, /* 28.17 */
+			.fc = 0x48c3, /* 36.38 */
+			.rs = 0x8100, /* 64.5 */
+			.sfd = 0x1dc, /* 0.93 */
+			.onestep = 0x1eb8 /* 15.36 */
+		},
+		.rx_offset = {
+			.serdes = 0xfffff7a9, /* -4.1697 */
+			.no_fec = 0xffffe71a, /* -12.45 */
+			.fc = 0xfffe894d, /* -187.35 */
+			.rs = 0xfffff8cd, /* -3.6 */
+			.sfd = 0x1dc, /* 0.93 */
+			.bs_ds = 0x14 /* 0.0387879, RS-FEC 0 */
+		}
+	},
+	[ICE_ETH56G_LNK_SPD_40G] = {
+		.tx_mode = { .def = 3 },
+		.tx_mk_dly = 4,
+		.tx_cw_dly = {
+			.def = 1,
+			.onestep = 6
+		},
+		.rx_mode = { .def = 4 },
+		.rx_mk_dly = { .def = 1 },
+		.rx_cw_dly = { .def = 1 },
+		.blktime = 0x333, /* 1.6 */
+		.mktime = 0xccd, /* 6.4 */
+		.tx_offset = {
+			.serdes = 0x234c, /* 17.6484848 */
+			.no_fec = 0x5a8a, /* 45.27 */
+			.fc = 0x81b8, /* 64.86 */
+			.sfd = 0x4a4, /* 2.32 */
+			.onestep = 0x1333 /* 9.6 */
+		},
+		.rx_offset = {
+			.serdes = 0xffffeb27, /* -10.42424 */
+			.no_fec = 0xfffff594, /* -5.21 */
+			.fc = 0xfffe3080, /* -231.75 */
+			.sfd = 0x4a4, /* 2.32 */
+			.bs_ds = 0xccd /* 6.4 */
+		}
+	},
+	[ICE_ETH56G_LNK_SPD_50G] = {
+		.tx_mode = { .def = 5 },
+		.tx_mk_dly = 4,
+		.tx_cw_dly = {
+			.def = 1,
+			.onestep = 6
+		},
+		.rx_mode = { .def = 5 },
+		.rx_mk_dly = { .def = 1 },
+		.rx_cw_dly = { .def = 1 },
+		.blktime = 0x28f, /* 1.28 */
+		.mktime = 0xa3d, /* 5.12 */
+		.tx_offset = {
+			.serdes = 0x13ba, /* 9.86353 */
+			.rs = 0x5400, /* 42 */
+			.sfd = 0xe6, /* 0.45 */
+			.onestep = 0xf5c /* 7.68 */
+		},
+		.rx_offset = {
+			.serdes = 0xfffff7e8, /* -4.04706 */
+			.rs = 0xfffff994, /* -3.21 */
+			.sfd = 0xe6 /* 0.45 */
+		}
+	},
+	[ICE_ETH56G_LNK_SPD_50G2] = {
+		.tx_mode = {
+			.def = 3,
+			.rs = 2
+		},
+		.tx_mk_dly = 4,
+		.tx_cw_dly = {
+			.def = 1,
+			.onestep = 6
+		},
+		.rx_mode = {
+			.def = 4,
+			.rs = 1
+		},
+		.rx_mk_dly = { .def = 1 },
+		.rx_cw_dly = { .def = 1 },
+		.blktime = 0x28f, /* 1.28 */
+		.mktime = 0xa3d, /* 5.12 */
+		.tx_offset = {
+			.serdes = 0xe1e, /* 7.0593939 */
+			.no_fec = 0x3d33, /* 30.6 */
+			.rs = 0x5057, /* 40.17 */
+			.sfd = 0x1dc, /* 0.93 */
+			.onestep = 0xf5c /* 7.68 */
+		},
+		.rx_offset = {
+			.serdes = 0xfffff7a9, /* -4.1697 */
+			.no_fec = 0xfffff8cd, /* -3.6 */
+			.rs = 0xfffff21a, /* -6.95 */
+			.sfd = 0x1dc, /* 0.93 */
+			.bs_ds = 0xa3d /* 5.12, RS-FEC 0x633 (3.1) */
+		}
+	},
+	[ICE_ETH56G_LNK_SPD_100G] = {
+		.tx_mode = {
+			.def = 3,
+			.rs = 2
+		},
+		.tx_mk_dly = 10,
+		.tx_cw_dly = {
+			.def = 3,
+			.onestep = 6
+		},
+		.rx_mode = {
+			.def = 4,
+			.rs = 1
+		},
+		.rx_mk_dly = { .def = 5 },
+		.rx_cw_dly = { .def = 5 },
+		.blks_per_clk = 1,
+		.blktime = 0x148, /* 0.64 */
+		.mktime = 0x199a, /* 12.8 */
+		.tx_offset = {
+			.serdes = 0xe1e, /* 7.0593939 */
+			.no_fec = 0x67ec, /* 51.96 */
+			.rs = 0x44fb, /* 34.49 */
+			.sfd = 0x1dc, /* 0.93 */
+			.onestep = 0xf5c /* 7.68 */
+		},
+		.rx_offset = {
+			.serdes = 0xfffff7a9, /* -4.1697 */
+			.no_fec = 0xfffff5a9, /* -5.17 */
+			.rs = 0xfffff6e6, /* -4.55 */
+			.sfd = 0x1dc, /* 0.93 */
+			.bs_ds = 0x199a /* 12.8, RS-FEC 0x31b (1.552) */
+		}
+	},
+	[ICE_ETH56G_LNK_SPD_100G2] = {
+		.tx_mode = { .def = 5 },
+		.tx_mk_dly = 10,
+		.tx_cw_dly = {
+			.def = 3,
+			.onestep = 6
+		},
+		.rx_mode = { .def = 5 },
+		.rx_mk_dly = { .def = 5 },
+		.rx_cw_dly = { .def = 5 },
+		.blks_per_clk = 1,
+		.blktime = 0x148, /* 0.64 */
+		.mktime = 0x199a, /* 12.8 */
+		.tx_offset = {
+			.serdes = 0x13ba, /* 9.86353 */
+			.rs = 0x460a, /* 35.02 */
+			.sfd = 0xe6, /* 0.45 */
+			.onestep = 0xf5c /* 7.68 */
+		},
+		.rx_offset = {
+			.serdes = 0xfffff7e8, /* -4.04706 */
+			.rs = 0xfffff548, /* -5.36 */
+			.sfd = 0xe6, /* 0.45 */
+			.bs_ds = 0x303 /* 1.506 */
+		}
+	}
+};
+
 /* struct ice_time_ref_info_e82x
  *
  * E822 hardware can use different sources as the reference for the PTP
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
index 7224bce7aa28b..1b333b1c2738a 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
@@ -2,6 +2,7 @@
 /* Copyright (C) 2021, Intel Corporation. */
 
 #include <linux/delay.h>
+#include <linux/iopoll.h>
 #include "ice_common.h"
 #include "ice_ptp_hw.h"
 #include "ice_ptp_consts.h"
@@ -642,6 +643,1810 @@ static void ice_ptp_exec_tmr_cmd(struct ice_hw *hw)
 	ice_flush(hw);
 }
 
+/* 56G PHY device functions
+ *
+ * The following functions operate on devices with the ETH 56G PHY.
+ */
+
+/**
+ * ice_write_phy_eth56g - Write a PHY port register
+ * @hw: pointer to the HW struct
+ * @phy_idx: PHY index
+ * @addr: PHY register address
+ * @val: Value to write
+ *
+ * Return: 0 on success, other error codes when failed to write to PHY
+ */
+static int ice_write_phy_eth56g(struct ice_hw *hw, u8 phy_idx, u32 addr,
+				u32 val)
+{
+	struct ice_sbq_msg_input phy_msg;
+	int err;
+
+	phy_msg.opcode = ice_sbq_msg_wr;
+
+	phy_msg.msg_addr_low = lower_16_bits(addr);
+	phy_msg.msg_addr_high = upper_16_bits(addr);
+
+	phy_msg.data = val;
+	phy_msg.dest_dev = hw->ptp.phy.eth56g.phy_addr[phy_idx];
+
+	err = ice_sbq_rw_reg(hw, &phy_msg);
+
+	if (err)
+		ice_debug(hw, ICE_DBG_PTP, "PTP failed to send msg to phy %d\n",
+			  err);
+
+	return err;
+}
+
+/**
+ * ice_read_phy_eth56g - Read a PHY port register
+ * @hw: pointer to the HW struct
+ * @phy_idx: PHY index
+ * @addr: PHY register address
+ * @val: Value to write
+ *
+ * Return: 0 on success, other error codes when failed to read from PHY
+ */
+static int ice_read_phy_eth56g(struct ice_hw *hw, u8 phy_idx, u32 addr,
+			       u32 *val)
+{
+	struct ice_sbq_msg_input phy_msg;
+	int err;
+
+	phy_msg.opcode = ice_sbq_msg_rd;
+
+	phy_msg.msg_addr_low = lower_16_bits(addr);
+	phy_msg.msg_addr_high = upper_16_bits(addr);
+
+	phy_msg.data = 0;
+	phy_msg.dest_dev = hw->ptp.phy.eth56g.phy_addr[phy_idx];
+
+	err = ice_sbq_rw_reg(hw, &phy_msg);
+	if (err) {
+		ice_debug(hw, ICE_DBG_PTP, "PTP failed to send msg to phy %d\n",
+			  err);
+		return err;
+	}
+
+	*val = phy_msg.data;
+
+	return 0;
+}
+
+/**
+ * ice_phy_res_address_eth56g - Calculate a PHY port register address
+ * @port: Port number to be written
+ * @res_type: resource type (register/memory)
+ * @offset: Offset from PHY port register base
+ * @addr: The result address
+ *
+ * Return:
+ * * %0      - success
+ * * %EINVAL - invalid port number or resource type
+ */
+static int ice_phy_res_address_eth56g(u8 port, enum eth56g_res_type res_type,
+				      u32 offset, u32 *addr)
+{
+	u8 lane = port % ICE_PORTS_PER_QUAD;
+	u8 phy = ICE_GET_QUAD_NUM(port);
+
+	if (res_type >= NUM_ETH56G_PHY_RES)
+		return -EINVAL;
+
+	*addr = eth56g_phy_res[res_type].base[phy] +
+		lane * eth56g_phy_res[res_type].step + offset;
+	return 0;
+}
+
+/**
+ * ice_write_port_eth56g - Write a PHY port register
+ * @hw: pointer to the HW struct
+ * @offset: PHY register offset
+ * @port: Port number
+ * @val: Value to write
+ * @res_type: resource type (register/memory)
+ *
+ * Return:
+ * * %0      - success
+ * * %EINVAL - invalid port number or resource type
+ * * %other  - failed to write to PHY
+ */
+static int ice_write_port_eth56g(struct ice_hw *hw, u8 port, u32 offset,
+				 u32 val, enum eth56g_res_type res_type)
+{
+	u8 phy_port = port % hw->ptp.ports_per_phy;
+	u8 phy_idx = port / hw->ptp.ports_per_phy;
+	u32 addr;
+	int err;
+
+	if (port >= hw->ptp.num_lports)
+		return -EINVAL;
+
+	err = ice_phy_res_address_eth56g(phy_port, res_type, offset, &addr);
+	if (err)
+		return err;
+
+	return ice_write_phy_eth56g(hw, phy_idx, addr, val);
+}
+
+/**
+ * ice_read_port_eth56g - Read a PHY port register
+ * @hw: pointer to the HW struct
+ * @offset: PHY register offset
+ * @port: Port number
+ * @val: Value to write
+ * @res_type: resource type (register/memory)
+ *
+ * Return:
+ * * %0      - success
+ * * %EINVAL - invalid port number or resource type
+ * * %other  - failed to read from PHY
+ */
+static int ice_read_port_eth56g(struct ice_hw *hw, u8 port, u32 offset,
+				u32 *val, enum eth56g_res_type res_type)
+{
+	u8 phy_port = port % hw->ptp.ports_per_phy;
+	u8 phy_idx = port / hw->ptp.ports_per_phy;
+	u32 addr;
+	int err;
+
+	if (port >= hw->ptp.num_lports)
+		return -EINVAL;
+
+	err = ice_phy_res_address_eth56g(phy_port, res_type, offset, &addr);
+	if (err)
+		return err;
+
+	return ice_read_phy_eth56g(hw, phy_idx, addr, val);
+}
+
+/**
+ * ice_write_ptp_reg_eth56g - Write a PHY port register
+ * @hw: pointer to the HW struct
+ * @port: Port number to be written
+ * @offset: Offset from PHY port register base
+ * @val: Value to write
+ *
+ * Return:
+ * * %0      - success
+ * * %EINVAL - invalid port number or resource type
+ * * %other  - failed to write to PHY
+ */
+static int ice_write_ptp_reg_eth56g(struct ice_hw *hw, u8 port, u16 offset,
+				    u32 val)
+{
+	return ice_write_port_eth56g(hw, port, offset, val, ETH56G_PHY_REG_PTP);
+}
+
+/**
+ * ice_write_mac_reg_eth56g - Write a MAC PHY port register
+ * parameter
+ * @hw: pointer to the HW struct
+ * @port: Port number to be written
+ * @offset: Offset from PHY port register base
+ * @val: Value to write
+ *
+ * Return:
+ * * %0      - success
+ * * %EINVAL - invalid port number or resource type
+ * * %other  - failed to write to PHY
+ */
+static int ice_write_mac_reg_eth56g(struct ice_hw *hw, u8 port, u32 offset,
+				    u32 val)
+{
+	return ice_write_port_eth56g(hw, port, offset, val, ETH56G_PHY_REG_MAC);
+}
+
+/**
+ * ice_write_xpcs_reg_eth56g - Write a PHY port register
+ * @hw: pointer to the HW struct
+ * @port: Port number to be written
+ * @offset: Offset from PHY port register base
+ * @val: Value to write
+ *
+ * Return:
+ * * %0      - success
+ * * %EINVAL - invalid port number or resource type
+ * * %other  - failed to write to PHY
+ */
+static int ice_write_xpcs_reg_eth56g(struct ice_hw *hw, u8 port, u32 offset,
+				     u32 val)
+{
+	return ice_write_port_eth56g(hw, port, offset, val,
+				     ETH56G_PHY_REG_XPCS);
+}
+
+/**
+ * ice_read_ptp_reg_eth56g - Read a PHY port register
+ * @hw: pointer to the HW struct
+ * @port: Port number to be read
+ * @offset: Offset from PHY port register base
+ * @val: Pointer to the value to read (out param)
+ *
+ * Return:
+ * * %0      - success
+ * * %EINVAL - invalid port number or resource type
+ * * %other  - failed to read from PHY
+ */
+static int ice_read_ptp_reg_eth56g(struct ice_hw *hw, u8 port, u16 offset,
+				   u32 *val)
+{
+	return ice_read_port_eth56g(hw, port, offset, val, ETH56G_PHY_REG_PTP);
+}
+
+/**
+ * ice_read_mac_reg_eth56g - Read a PHY port register
+ * @hw: pointer to the HW struct
+ * @port: Port number to be read
+ * @offset: Offset from PHY port register base
+ * @val: Pointer to the value to read (out param)
+ *
+ * Return:
+ * * %0      - success
+ * * %EINVAL - invalid port number or resource type
+ * * %other  - failed to read from PHY
+ */
+static int ice_read_mac_reg_eth56g(struct ice_hw *hw, u8 port, u16 offset,
+				   u32 *val)
+{
+	return ice_read_port_eth56g(hw, port, offset, val, ETH56G_PHY_REG_MAC);
+}
+
+/**
+ * ice_read_gpcs_reg_eth56g - Read a PHY port register
+ * @hw: pointer to the HW struct
+ * @port: Port number to be read
+ * @offset: Offset from PHY port register base
+ * @val: Pointer to the value to read (out param)
+ *
+ * Return:
+ * * %0      - success
+ * * %EINVAL - invalid port number or resource type
+ * * %other  - failed to read from PHY
+ */
+static int ice_read_gpcs_reg_eth56g(struct ice_hw *hw, u8 port, u16 offset,
+				    u32 *val)
+{
+	return ice_read_port_eth56g(hw, port, offset, val, ETH56G_PHY_REG_GPCS);
+}
+
+/**
+ * ice_read_port_mem_eth56g - Read a PHY port memory location
+ * @hw: pointer to the HW struct
+ * @port: Port number to be read
+ * @offset: Offset from PHY port register base
+ * @val: Pointer to the value to read (out param)
+ *
+ * Return:
+ * * %0      - success
+ * * %EINVAL - invalid port number or resource type
+ * * %other  - failed to read from PHY
+ */
+static int ice_read_port_mem_eth56g(struct ice_hw *hw, u8 port, u16 offset,
+				    u32 *val)
+{
+	return ice_read_port_eth56g(hw, port, offset, val, ETH56G_PHY_MEM_PTP);
+}
+
+/**
+ * ice_write_port_mem_eth56g - Write a PHY port memory location
+ * @hw: pointer to the HW struct
+ * @port: Port number to be read
+ * @offset: Offset from PHY port register base
+ * @val: Pointer to the value to read (out param)
+ *
+ * Return:
+ * * %0      - success
+ * * %EINVAL - invalid port number or resource type
+ * * %other  - failed to write to PHY
+ */
+static int ice_write_port_mem_eth56g(struct ice_hw *hw, u8 port, u16 offset,
+				     u32 val)
+{
+	return ice_write_port_eth56g(hw, port, offset, val, ETH56G_PHY_MEM_PTP);
+}
+
+/**
+ * ice_is_64b_phy_reg_eth56g - Check if this is a 64bit PHY register
+ * @low_addr: the low address to check
+ * @high_addr: on return, contains the high address of the 64bit register
+ *
+ * Write the appropriate high register offset to use.
+ *
+ * Return: true if the provided low address is one of the known 64bit PHY values
+ * represented as two 32bit registers, false otherwise.
+ */
+static bool ice_is_64b_phy_reg_eth56g(u16 low_addr, u16 *high_addr)
+{
+	switch (low_addr) {
+	case PHY_REG_TX_TIMER_INC_PRE_L:
+		*high_addr = PHY_REG_TX_TIMER_INC_PRE_U;
+		return true;
+	case PHY_REG_RX_TIMER_INC_PRE_L:
+		*high_addr = PHY_REG_RX_TIMER_INC_PRE_U;
+		return true;
+	case PHY_REG_TX_CAPTURE_L:
+		*high_addr = PHY_REG_TX_CAPTURE_U;
+		return true;
+	case PHY_REG_RX_CAPTURE_L:
+		*high_addr = PHY_REG_RX_CAPTURE_U;
+		return true;
+	case PHY_REG_TOTAL_TX_OFFSET_L:
+		*high_addr = PHY_REG_TOTAL_TX_OFFSET_U;
+		return true;
+	case PHY_REG_TOTAL_RX_OFFSET_L:
+		*high_addr = PHY_REG_TOTAL_RX_OFFSET_U;
+		return true;
+	case PHY_REG_TX_MEMORY_STATUS_L:
+		*high_addr = PHY_REG_TX_MEMORY_STATUS_U;
+		return true;
+	default:
+		return false;
+	}
+}
+
+/**
+ * ice_is_40b_phy_reg_eth56g - Check if this is a 40bit PHY register
+ * @low_addr: the low address to check
+ * @high_addr: on return, contains the high address of the 40bit value
+ *
+ * Write the appropriate high register offset to use.
+ *
+ * Return: true if the provided low address is one of the known 40bit PHY
+ * values split into two registers with the lower 8 bits in the low register and
+ * the upper 32 bits in the high register, false otherwise.
+ */
+static bool ice_is_40b_phy_reg_eth56g(u16 low_addr, u16 *high_addr)
+{
+	switch (low_addr) {
+	case PHY_REG_TIMETUS_L:
+		*high_addr = PHY_REG_TIMETUS_U;
+		return true;
+	case PHY_PCS_REF_TUS_L:
+		*high_addr = PHY_PCS_REF_TUS_U;
+		return true;
+	case PHY_PCS_REF_INC_L:
+		*high_addr = PHY_PCS_REF_INC_U;
+		return true;
+	default:
+		return false;
+	}
+}
+
+/**
+ * ice_read_64b_phy_reg_eth56g - Read a 64bit value from PHY registers
+ * @hw: pointer to the HW struct
+ * @port: PHY port to read from
+ * @low_addr: offset of the lower register to read from
+ * @val: on return, the contents of the 64bit value from the PHY registers
+ * @res_type: resource type
+ *
+ * Check if the caller has specified a known 40 bit register offset and read
+ * the two registers associated with a 40bit value and return it in the val
+ * pointer.
+ *
+ * Return:
+ * * %0      - success
+ * * %EINVAL - not a 64 bit register
+ * * %other  - failed to read from PHY
+ */
+static int ice_read_64b_phy_reg_eth56g(struct ice_hw *hw, u8 port, u16 low_addr,
+				       u64 *val, enum eth56g_res_type res_type)
+{
+	u16 high_addr;
+	u32 lo, hi;
+	int err;
+
+	if (!ice_is_64b_phy_reg_eth56g(low_addr, &high_addr))
+		return -EINVAL;
+
+	err = ice_read_port_eth56g(hw, port, low_addr, &lo, res_type);
+	if (err) {
+		ice_debug(hw, ICE_DBG_PTP, "Failed to read from low register %#08x\n, err %d",
+			  low_addr, err);
+		return err;
+	}
+
+	err = ice_read_port_eth56g(hw, port, high_addr, &hi, res_type);
+	if (err) {
+		ice_debug(hw, ICE_DBG_PTP, "Failed to read from high register %#08x\n, err %d",
+			  high_addr, err);
+		return err;
+	}
+
+	*val = ((u64)hi << 32) | lo;
+
+	return 0;
+}
+
+/**
+ * ice_read_64b_ptp_reg_eth56g - Read a 64bit value from PHY registers
+ * @hw: pointer to the HW struct
+ * @port: PHY port to read from
+ * @low_addr: offset of the lower register to read from
+ * @val: on return, the contents of the 64bit value from the PHY registers
+ *
+ * Check if the caller has specified a known 40 bit register offset and read
+ * the two registers associated with a 40bit value and return it in the val
+ * pointer.
+ *
+ * Return:
+ * * %0      - success
+ * * %EINVAL - not a 64 bit register
+ * * %other  - failed to read from PHY
+ */
+static int ice_read_64b_ptp_reg_eth56g(struct ice_hw *hw, u8 port, u16 low_addr,
+				       u64 *val)
+{
+	return ice_read_64b_phy_reg_eth56g(hw, port, low_addr, val,
+					   ETH56G_PHY_REG_PTP);
+}
+
+/**
+ * ice_write_40b_phy_reg_eth56g - Write a 40b value to the PHY
+ * @hw: pointer to the HW struct
+ * @port: port to write to
+ * @low_addr: offset of the low register
+ * @val: 40b value to write
+ * @res_type: resource type
+ *
+ * Check if the caller has specified a known 40 bit register offset and write
+ * provided 40b value to the two associated registers by splitting it up into
+ * two chunks, the lower 8 bits and the upper 32 bits.
+ *
+ * Return:
+ * * %0      - success
+ * * %EINVAL - not a 40 bit register
+ * * %other  - failed to write to PHY
+ */
+static int ice_write_40b_phy_reg_eth56g(struct ice_hw *hw, u8 port,
+					u16 low_addr, u64 val,
+					enum eth56g_res_type res_type)
+{
+	u16 high_addr;
+	u32 lo, hi;
+	int err;
+
+	if (!ice_is_40b_phy_reg_eth56g(low_addr, &high_addr))
+		return -EINVAL;
+
+	lo = FIELD_GET(P_REG_40B_LOW_M, val);
+	hi = (u32)(val >> P_REG_40B_HIGH_S);
+
+	err = ice_write_port_eth56g(hw, port, low_addr, lo, res_type);
+	if (err) {
+		ice_debug(hw, ICE_DBG_PTP, "Failed to write to low register 0x%08x\n, err %d",
+			  low_addr, err);
+		return err;
+	}
+
+	err = ice_write_port_eth56g(hw, port, high_addr, hi, res_type);
+	if (err) {
+		ice_debug(hw, ICE_DBG_PTP, "Failed to write to high register 0x%08x\n, err %d",
+			  high_addr, err);
+		return err;
+	}
+
+	return 0;
+}
+
+/**
+ * ice_write_40b_ptp_reg_eth56g - Write a 40b value to the PHY
+ * @hw: pointer to the HW struct
+ * @port: port to write to
+ * @low_addr: offset of the low register
+ * @val: 40b value to write
+ *
+ * Check if the caller has specified a known 40 bit register offset and write
+ * provided 40b value to the two associated registers by splitting it up into
+ * two chunks, the lower 8 bits and the upper 32 bits.
+ *
+ * Return:
+ * * %0      - success
+ * * %EINVAL - not a 40 bit register
+ * * %other  - failed to write to PHY
+ */
+static int ice_write_40b_ptp_reg_eth56g(struct ice_hw *hw, u8 port,
+					u16 low_addr, u64 val)
+{
+	return ice_write_40b_phy_reg_eth56g(hw, port, low_addr, val,
+					    ETH56G_PHY_REG_PTP);
+}
+
+/**
+ * ice_write_64b_phy_reg_eth56g - Write a 64bit value to PHY registers
+ * @hw: pointer to the HW struct
+ * @port: PHY port to read from
+ * @low_addr: offset of the lower register to read from
+ * @val: the contents of the 64bit value to write to PHY
+ * @res_type: resource type
+ *
+ * Check if the caller has specified a known 64 bit register offset and write
+ * the 64bit value to the two associated 32bit PHY registers.
+ *
+ * Return:
+ * * %0      - success
+ * * %EINVAL - not a 64 bit register
+ * * %other  - failed to write to PHY
+ */
+static int ice_write_64b_phy_reg_eth56g(struct ice_hw *hw, u8 port,
+					u16 low_addr, u64 val,
+					enum eth56g_res_type res_type)
+{
+	u16 high_addr;
+	u32 lo, hi;
+	int err;
+
+	if (!ice_is_64b_phy_reg_eth56g(low_addr, &high_addr))
+		return -EINVAL;
+
+	lo = lower_32_bits(val);
+	hi = upper_32_bits(val);
+
+	err = ice_write_port_eth56g(hw, port, low_addr, lo, res_type);
+	if (err) {
+		ice_debug(hw, ICE_DBG_PTP, "Failed to write to low register 0x%08x\n, err %d",
+			  low_addr, err);
+		return err;
+	}
+
+	err = ice_write_port_eth56g(hw, port, high_addr, hi, res_type);
+	if (err) {
+		ice_debug(hw, ICE_DBG_PTP, "Failed to write to high register 0x%08x\n, err %d",
+			  high_addr, err);
+		return err;
+	}
+
+	return 0;
+}
+
+/**
+ * ice_write_64b_ptp_reg_eth56g - Write a 64bit value to PHY registers
+ * @hw: pointer to the HW struct
+ * @port: PHY port to read from
+ * @low_addr: offset of the lower register to read from
+ * @val: the contents of the 64bit value to write to PHY
+ *
+ * Check if the caller has specified a known 64 bit register offset and write
+ * the 64bit value to the two associated 32bit PHY registers.
+ *
+ * Return:
+ * * %0      - success
+ * * %EINVAL - not a 64 bit register
+ * * %other  - failed to write to PHY
+ */
+static int ice_write_64b_ptp_reg_eth56g(struct ice_hw *hw, u8 port,
+					u16 low_addr, u64 val)
+{
+	return ice_write_64b_phy_reg_eth56g(hw, port, low_addr, val,
+					    ETH56G_PHY_REG_PTP);
+}
+
+/**
+ * ice_read_ptp_tstamp_eth56g - Read a PHY timestamp out of the port memory
+ * @hw: pointer to the HW struct
+ * @port: the port to read from
+ * @idx: the timestamp index to read
+ * @tstamp: on return, the 40bit timestamp value
+ *
+ * Read a 40bit timestamp value out of the two associated entries in the
+ * port memory block of the internal PHYs of the 56G devices.
+ *
+ * Return:
+ * * %0     - success
+ * * %other - failed to read from PHY
+ */
+static int ice_read_ptp_tstamp_eth56g(struct ice_hw *hw, u8 port, u8 idx,
+				      u64 *tstamp)
+{
+	u16 lo_addr, hi_addr;
+	u32 lo, hi;
+	int err;
+
+	lo_addr = (u16)PHY_TSTAMP_L(idx);
+	hi_addr = (u16)PHY_TSTAMP_U(idx);
+
+	err = ice_read_port_mem_eth56g(hw, port, lo_addr, &lo);
+	if (err) {
+		ice_debug(hw, ICE_DBG_PTP, "Failed to read low PTP timestamp register, err %d\n",
+			  err);
+		return err;
+	}
+
+	err = ice_read_port_mem_eth56g(hw, port, hi_addr, &hi);
+	if (err) {
+		ice_debug(hw, ICE_DBG_PTP, "Failed to read high PTP timestamp register, err %d\n",
+			  err);
+		return err;
+	}
+
+	/* For 56G based internal PHYs, the timestamp is reported with the
+	 * lower 8 bits in the low register, and the upper 32 bits in the high
+	 * register.
+	 */
+	*tstamp = ((u64)hi) << TS_PHY_HIGH_S | ((u64)lo & TS_PHY_LOW_M);
+
+	return 0;
+}
+
+/**
+ * ice_clear_ptp_tstamp_eth56g - Clear a timestamp from the quad block
+ * @hw: pointer to the HW struct
+ * @port: the quad to read from
+ * @idx: the timestamp index to reset
+ *
+ * Read and then forcibly clear the timestamp index to ensure the valid bit is
+ * cleared and the timestamp status bit is reset in the PHY port memory of
+ * internal PHYs of the 56G devices.
+ *
+ * To directly clear the contents of the timestamp block entirely, discarding
+ * all timestamp data at once, software should instead use
+ * ice_ptp_reset_ts_memory_quad_eth56g().
+ *
+ * This function should only be called on an idx whose bit is set according to
+ * ice_get_phy_tx_tstamp_ready().
+ *
+ * Return:
+ * * %0     - success
+ * * %other - failed to write to PHY
+ */
+static int ice_clear_ptp_tstamp_eth56g(struct ice_hw *hw, u8 port, u8 idx)
+{
+	u64 unused_tstamp;
+	u16 lo_addr;
+	int err;
+
+	/* Read the timestamp register to ensure the timestamp status bit is
+	 * cleared.
+	 */
+	err = ice_read_ptp_tstamp_eth56g(hw, port, idx, &unused_tstamp);
+	if (err) {
+		ice_debug(hw, ICE_DBG_PTP, "Failed to read the PHY timestamp register for port %u, idx %u, err %d\n",
+			  port, idx, err);
+	}
+
+	lo_addr = (u16)PHY_TSTAMP_L(idx);
+
+	err = ice_write_port_mem_eth56g(hw, port, lo_addr, 0);
+	if (err) {
+		ice_debug(hw, ICE_DBG_PTP, "Failed to clear low PTP timestamp register for port %u, idx %u, err %d\n",
+			  port, idx, err);
+		return err;
+	}
+
+	return 0;
+}
+
+/**
+ * ice_ptp_reset_ts_memory_eth56g - Clear all timestamps from the port block
+ * @hw: pointer to the HW struct
+ */
+static void ice_ptp_reset_ts_memory_eth56g(struct ice_hw *hw)
+{
+	unsigned int port;
+
+	for (port = 0; port < hw->ptp.num_lports; port++) {
+		ice_write_ptp_reg_eth56g(hw, port, PHY_REG_TX_MEMORY_STATUS_L,
+					 0);
+		ice_write_ptp_reg_eth56g(hw, port, PHY_REG_TX_MEMORY_STATUS_U,
+					 0);
+	}
+}
+
+/**
+ * ice_ptp_prep_port_time_eth56g - Prepare one PHY port with initial time
+ * @hw: pointer to the HW struct
+ * @port: port number
+ * @time: time to initialize the PHY port clocks to
+ *
+ * Write a new initial time value into registers of a specific PHY port.
+ *
+ * Return:
+ * * %0     - success
+ * * %other - failed to write to PHY
+ */
+static int ice_ptp_prep_port_time_eth56g(struct ice_hw *hw, u8 port,
+					 u64 time)
+{
+	int err;
+
+	/* Tx case */
+	err = ice_write_64b_ptp_reg_eth56g(hw, port, PHY_REG_TX_TIMER_INC_PRE_L,
+					   time);
+	if (err)
+		return err;
+
+	/* Rx case */
+	return ice_write_64b_ptp_reg_eth56g(hw, port,
+					    PHY_REG_RX_TIMER_INC_PRE_L, time);
+}
+
+/**
+ * ice_ptp_prep_phy_time_eth56g - Prepare PHY port with initial time
+ * @hw: pointer to the HW struct
+ * @time: Time to initialize the PHY port clocks to
+ *
+ * Program the PHY port registers with a new initial time value. The port
+ * clock will be initialized once the driver issues an ICE_PTP_INIT_TIME sync
+ * command. The time value is the upper 32 bits of the PHY timer, usually in
+ * units of nominal nanoseconds.
+ *
+ * Return:
+ * * %0     - success
+ * * %other - failed to write to PHY
+ */
+static int ice_ptp_prep_phy_time_eth56g(struct ice_hw *hw, u32 time)
+{
+	u64 phy_time;
+	u8 port;
+
+	/* The time represents the upper 32 bits of the PHY timer, so we need
+	 * to shift to account for this when programming.
+	 */
+	phy_time = (u64)time << 32;
+
+	for (port = 0; port < hw->ptp.num_lports; port++) {
+		int err;
+
+		err = ice_ptp_prep_port_time_eth56g(hw, port, phy_time);
+		if (err) {
+			ice_debug(hw, ICE_DBG_PTP, "Failed to write init time for port %u, err %d\n",
+				  port, err);
+			return err;
+		}
+	}
+
+	return 0;
+}
+
+/**
+ * ice_ptp_prep_port_adj_eth56g - Prepare a single port for time adjust
+ * @hw: pointer to HW struct
+ * @port: Port number to be programmed
+ * @time: time in cycles to adjust the port clocks
+ *
+ * Program the port for an atomic adjustment by writing the Tx and Rx timer
+ * registers. The atomic adjustment won't be completed until the driver issues
+ * an ICE_PTP_ADJ_TIME command.
+ *
+ * Note that time is not in units of nanoseconds. It is in clock time
+ * including the lower sub-nanosecond portion of the port timer.
+ *
+ * Negative adjustments are supported using 2s complement arithmetic.
+ *
+ * Return:
+ * * %0     - success
+ * * %other - failed to write to PHY
+ */
+static int ice_ptp_prep_port_adj_eth56g(struct ice_hw *hw, u8 port, s64 time)
+{
+	u32 l_time, u_time;
+	int err;
+
+	l_time = lower_32_bits(time);
+	u_time = upper_32_bits(time);
+
+	/* Tx case */
+	err = ice_write_ptp_reg_eth56g(hw, port, PHY_REG_TX_TIMER_INC_PRE_L,
+				       l_time);
+	if (err)
+		goto exit_err;
+
+	err = ice_write_ptp_reg_eth56g(hw, port, PHY_REG_TX_TIMER_INC_PRE_U,
+				       u_time);
+	if (err)
+		goto exit_err;
+
+	/* Rx case */
+	err = ice_write_ptp_reg_eth56g(hw, port, PHY_REG_RX_TIMER_INC_PRE_L,
+				       l_time);
+	if (err)
+		goto exit_err;
+
+	err = ice_write_ptp_reg_eth56g(hw, port, PHY_REG_RX_TIMER_INC_PRE_U,
+				       u_time);
+	if (err)
+		goto exit_err;
+
+	return 0;
+
+exit_err:
+	ice_debug(hw, ICE_DBG_PTP, "Failed to write time adjust for port %u, err %d\n",
+		  port, err);
+	return err;
+}
+
+/**
+ * ice_ptp_prep_phy_adj_eth56g - Prep PHY ports for a time adjustment
+ * @hw: pointer to HW struct
+ * @adj: adjustment in nanoseconds
+ *
+ * Prepare the PHY ports for an atomic time adjustment by programming the PHY
+ * Tx and Rx port registers. The actual adjustment is completed by issuing an
+ * ICE_PTP_ADJ_TIME or ICE_PTP_ADJ_TIME_AT_TIME sync command.
+ *
+ * Return:
+ * * %0     - success
+ * * %other - failed to write to PHY
+ */
+static int ice_ptp_prep_phy_adj_eth56g(struct ice_hw *hw, s32 adj)
+{
+	s64 cycles;
+	u8 port;
+
+	/* The port clock supports adjustment of the sub-nanosecond portion of
+	 * the clock (lowest 32 bits). We shift the provided adjustment in
+	 * nanoseconds by 32 to calculate the appropriate adjustment to program
+	 * into the PHY ports.
+	 */
+	cycles = (s64)adj << 32;
+
+	for (port = 0; port < hw->ptp.num_lports; port++) {
+		int err;
+
+		err = ice_ptp_prep_port_adj_eth56g(hw, port, cycles);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+/**
+ * ice_ptp_prep_phy_incval_eth56g - Prepare PHY ports for time adjustment
+ * @hw: pointer to HW struct
+ * @incval: new increment value to prepare
+ *
+ * Prepare each of the PHY ports for a new increment value by programming the
+ * port's TIMETUS registers. The new increment value will be updated after
+ * issuing an ICE_PTP_INIT_INCVAL command.
+ *
+ * Return:
+ * * %0     - success
+ * * %other - failed to write to PHY
+ */
+static int ice_ptp_prep_phy_incval_eth56g(struct ice_hw *hw, u64 incval)
+{
+	u8 port;
+
+	for (port = 0; port < hw->ptp.num_lports; port++) {
+		int err;
+
+		err = ice_write_40b_ptp_reg_eth56g(hw, port, PHY_REG_TIMETUS_L,
+						   incval);
+		if (err) {
+			ice_debug(hw, ICE_DBG_PTP, "Failed to write incval for port %u, err %d\n",
+				  port, err);
+			return err;
+		}
+	}
+
+	return 0;
+}
+
+/**
+ * ice_ptp_read_port_capture_eth56g - Read a port's local time capture
+ * @hw: pointer to HW struct
+ * @port: Port number to read
+ * @tx_ts: on return, the Tx port time capture
+ * @rx_ts: on return, the Rx port time capture
+ *
+ * Read the port's Tx and Rx local time capture values.
+ *
+ * Return:
+ * * %0     - success
+ * * %other - failed to read from PHY
+ */
+static int ice_ptp_read_port_capture_eth56g(struct ice_hw *hw, u8 port,
+					    u64 *tx_ts, u64 *rx_ts)
+{
+	int err;
+
+	/* Tx case */
+	err = ice_read_64b_ptp_reg_eth56g(hw, port, PHY_REG_TX_CAPTURE_L,
+					  tx_ts);
+	if (err) {
+		ice_debug(hw, ICE_DBG_PTP, "Failed to read REG_TX_CAPTURE, err %d\n",
+			  err);
+		return err;
+	}
+
+	ice_debug(hw, ICE_DBG_PTP, "tx_init = %#016llx\n", *tx_ts);
+
+	/* Rx case */
+	err = ice_read_64b_ptp_reg_eth56g(hw, port, PHY_REG_RX_CAPTURE_L,
+					  rx_ts);
+	if (err) {
+		ice_debug(hw, ICE_DBG_PTP, "Failed to read RX_CAPTURE, err %d\n",
+			  err);
+		return err;
+	}
+
+	ice_debug(hw, ICE_DBG_PTP, "rx_init = %#016llx\n", *rx_ts);
+
+	return 0;
+}
+
+/**
+ * ice_ptp_write_port_cmd_eth56g - Prepare a single PHY port for a timer command
+ * @hw: pointer to HW struct
+ * @port: Port to which cmd has to be sent
+ * @cmd: Command to be sent to the port
+ *
+ * Prepare the requested port for an upcoming timer sync command.
+ *
+ * Return:
+ * * %0     - success
+ * * %other - failed to write to PHY
+ */
+static int ice_ptp_write_port_cmd_eth56g(struct ice_hw *hw, u8 port,
+					 enum ice_ptp_tmr_cmd cmd)
+{
+	u32 val = ice_ptp_tmr_cmd_to_port_reg(hw, cmd);
+	int err;
+
+	/* Tx case */
+	err = ice_write_ptp_reg_eth56g(hw, port, PHY_REG_TX_TMR_CMD, val);
+	if (err) {
+		ice_debug(hw, ICE_DBG_PTP, "Failed to write back TX_TMR_CMD, err %d\n",
+			  err);
+		return err;
+	}
+
+	/* Rx case */
+	err = ice_write_ptp_reg_eth56g(hw, port, PHY_REG_RX_TMR_CMD, val);
+	if (err) {
+		ice_debug(hw, ICE_DBG_PTP, "Failed to write back RX_TMR_CMD, err %d\n",
+			  err);
+		return err;
+	}
+
+	return 0;
+}
+
+/**
+ * ice_phy_get_speed_eth56g - Get link speed based on PHY link type
+ * @li: pointer to link information struct
+ *
+ * Return: simplified ETH56G PHY speed
+ */
+static enum ice_eth56g_link_spd
+ice_phy_get_speed_eth56g(struct ice_link_status *li)
+{
+	u16 speed = ice_get_link_speed_based_on_phy_type(li->phy_type_low,
+							 li->phy_type_high);
+
+	switch (speed) {
+	case ICE_AQ_LINK_SPEED_1000MB:
+		return ICE_ETH56G_LNK_SPD_1G;
+	case ICE_AQ_LINK_SPEED_2500MB:
+		return ICE_ETH56G_LNK_SPD_2_5G;
+	case ICE_AQ_LINK_SPEED_10GB:
+		return ICE_ETH56G_LNK_SPD_10G;
+	case ICE_AQ_LINK_SPEED_25GB:
+		return ICE_ETH56G_LNK_SPD_25G;
+	case ICE_AQ_LINK_SPEED_40GB:
+		return ICE_ETH56G_LNK_SPD_40G;
+	case ICE_AQ_LINK_SPEED_50GB:
+		switch (li->phy_type_low) {
+		case ICE_PHY_TYPE_LOW_50GBASE_SR:
+		case ICE_PHY_TYPE_LOW_50GBASE_FR:
+		case ICE_PHY_TYPE_LOW_50GBASE_LR:
+		case ICE_PHY_TYPE_LOW_50GBASE_KR_PAM4:
+		case ICE_PHY_TYPE_LOW_50G_AUI1_AOC_ACC:
+		case ICE_PHY_TYPE_LOW_50G_AUI1:
+			return ICE_ETH56G_LNK_SPD_50G;
+		default:
+			return ICE_ETH56G_LNK_SPD_50G2;
+		}
+	case ICE_AQ_LINK_SPEED_100GB:
+		if (li->phy_type_high ||
+		    li->phy_type_low == ICE_PHY_TYPE_LOW_100GBASE_SR2)
+			return ICE_ETH56G_LNK_SPD_100G2;
+		else
+			return ICE_ETH56G_LNK_SPD_100G;
+	default:
+		return ICE_ETH56G_LNK_SPD_1G;
+	}
+}
+
+/**
+ * ice_phy_cfg_parpcs_eth56g - Configure TUs per PAR/PCS clock cycle
+ * @hw: pointer to the HW struct
+ * @port: port to configure
+ *
+ * Configure the number of TUs for the PAR and PCS clocks used as part of the
+ * timestamp calibration process.
+ *
+ * Return:
+ * * %0     - success
+ * * %other - PHY read/write failed
+ */
+static int ice_phy_cfg_parpcs_eth56g(struct ice_hw *hw, u8 port)
+{
+	u8 port_blk = port & ~(ICE_PORTS_PER_QUAD - 1);
+	u32 val;
+	int err;
+
+	err = ice_write_xpcs_reg_eth56g(hw, port, PHY_VENDOR_TXLANE_THRESH,
+					ICE_ETH56G_NOMINAL_THRESH4);
+	if (err) {
+		ice_debug(hw, ICE_DBG_PTP, "Failed to read VENDOR_TXLANE_THRESH, status: %d",
+			  err);
+		return err;
+	}
+
+	switch (ice_phy_get_speed_eth56g(&hw->port_info->phy.link_info)) {
+	case ICE_ETH56G_LNK_SPD_1G:
+	case ICE_ETH56G_LNK_SPD_2_5G:
+		err = ice_read_ptp_reg_eth56g(hw, port_blk,
+					      PHY_GPCS_CONFIG_REG0, &val);
+		if (err) {
+			ice_debug(hw, ICE_DBG_PTP, "Failed to read PHY_GPCS_CONFIG_REG0, status: %d",
+				  err);
+			return err;
+		}
+
+		val &= ~PHY_GPCS_CONFIG_REG0_TX_THR_M;
+		val |= FIELD_PREP(PHY_GPCS_CONFIG_REG0_TX_THR_M,
+				  ICE_ETH56G_NOMINAL_TX_THRESH);
+
+		err = ice_write_ptp_reg_eth56g(hw, port_blk,
+					       PHY_GPCS_CONFIG_REG0, val);
+		if (err) {
+			ice_debug(hw, ICE_DBG_PTP, "Failed to write PHY_GPCS_CONFIG_REG0, status: %d",
+				  err);
+			return err;
+		}
+		break;
+	default:
+		break;
+	}
+
+	err = ice_write_40b_ptp_reg_eth56g(hw, port, PHY_PCS_REF_TUS_L,
+					   ICE_ETH56G_NOMINAL_PCS_REF_TUS);
+	if (err) {
+		ice_debug(hw, ICE_DBG_PTP, "Failed to write PHY_PCS_REF_TUS, status: %d",
+			  err);
+		return err;
+	}
+
+	err = ice_write_40b_ptp_reg_eth56g(hw, port, PHY_PCS_REF_INC_L,
+					   ICE_ETH56G_NOMINAL_PCS_REF_INC);
+	if (err) {
+		ice_debug(hw, ICE_DBG_PTP, "Failed to write PHY_PCS_REF_INC, status: %d",
+			  err);
+		return err;
+	}
+
+	return 0;
+}
+
+/**
+ * ice_phy_cfg_ptp_1step_eth56g - Configure 1-step PTP settings
+ * @hw: Pointer to the HW struct
+ * @port: Port to configure
+ *
+ * Return:
+ * * %0     - success
+ * * %other - PHY read/write failed
+ */
+int ice_phy_cfg_ptp_1step_eth56g(struct ice_hw *hw, u8 port)
+{
+	u8 port_blk = port & ~(ICE_PORTS_PER_QUAD - 1);
+	u8 blk_port = port & (ICE_PORTS_PER_QUAD - 1);
+	bool enable, sfd_ena;
+	u32 val, peer_delay;
+	int err;
+
+	enable = hw->ptp.phy.eth56g.onestep_ena;
+	peer_delay = hw->ptp.phy.eth56g.peer_delay;
+	sfd_ena = hw->ptp.phy.eth56g.sfd_ena;
+
+	/* PHY_PTP_1STEP_CONFIG */
+	err = ice_read_ptp_reg_eth56g(hw, port_blk, PHY_PTP_1STEP_CONFIG, &val);
+	if (err)
+		return err;
+
+	if (enable)
+		val |= blk_port;
+	else
+		val &= ~blk_port;
+
+	val &= ~(PHY_PTP_1STEP_T1S_UP64_M | PHY_PTP_1STEP_T1S_DELTA_M);
+
+	err = ice_write_ptp_reg_eth56g(hw, port_blk, PHY_PTP_1STEP_CONFIG, val);
+	if (err)
+		return err;
+
+	/* PHY_PTP_1STEP_PEER_DELAY */
+	val = FIELD_PREP(PHY_PTP_1STEP_PD_DELAY_M, peer_delay);
+	if (peer_delay)
+		val |= PHY_PTP_1STEP_PD_ADD_PD_M;
+	val |= PHY_PTP_1STEP_PD_DLY_V_M;
+	err = ice_write_ptp_reg_eth56g(hw, port_blk,
+				       PHY_PTP_1STEP_PEER_DELAY(blk_port), val);
+	if (err)
+		return err;
+
+	val &= ~PHY_PTP_1STEP_PD_DLY_V_M;
+	err = ice_write_ptp_reg_eth56g(hw, port_blk,
+				       PHY_PTP_1STEP_PEER_DELAY(blk_port), val);
+	if (err)
+		return err;
+
+	/* PHY_MAC_XIF_MODE */
+	err = ice_read_mac_reg_eth56g(hw, port, PHY_MAC_XIF_MODE, &val);
+	if (err)
+		return err;
+
+	val &= ~(PHY_MAC_XIF_1STEP_ENA_M | PHY_MAC_XIF_TS_BIN_MODE_M |
+		 PHY_MAC_XIF_TS_SFD_ENA_M | PHY_MAC_XIF_GMII_TS_SEL_M);
+
+	switch (ice_phy_get_speed_eth56g(&hw->port_info->phy.link_info)) {
+	case ICE_ETH56G_LNK_SPD_1G:
+	case ICE_ETH56G_LNK_SPD_2_5G:
+		val |= PHY_MAC_XIF_GMII_TS_SEL_M;
+		break;
+	default:
+		break;
+	}
+
+	val |= FIELD_PREP(PHY_MAC_XIF_1STEP_ENA_M, enable) |
+	       FIELD_PREP(PHY_MAC_XIF_TS_BIN_MODE_M, enable) |
+	       FIELD_PREP(PHY_MAC_XIF_TS_SFD_ENA_M, sfd_ena);
+
+	return ice_write_mac_reg_eth56g(hw, port, PHY_MAC_XIF_MODE, val);
+}
+
+/**
+ * mul_u32_u32_fx_q9 - Multiply two u32 fixed point Q9 values
+ * @a: multiplier value
+ * @b: multiplicand value
+ *
+ * Return: result of multiplication
+ */
+static u32 mul_u32_u32_fx_q9(u32 a, u32 b)
+{
+	return (u32)(((u64)a * b) >> ICE_ETH56G_MAC_CFG_FRAC_W);
+}
+
+/**
+ * add_u32_u32_fx - Add two u32 fixed point values and discard overflow
+ * @a: first value
+ * @b: second value
+ *
+ * Return: result of addition
+ */
+static u32 add_u32_u32_fx(u32 a, u32 b)
+{
+	return lower_32_bits(((u64)a + b));
+}
+
+/**
+ * ice_ptp_calc_bitslip_eth56g - Calculate bitslip value
+ * @hw: pointer to the HW struct
+ * @port: port to configure
+ * @bs: bitslip multiplier
+ * @fc: FC-FEC enabled
+ * @rs: RS-FEC enabled
+ * @spd: link speed
+ *
+ * Return: calculated bitslip value
+ */
+static u32 ice_ptp_calc_bitslip_eth56g(struct ice_hw *hw, u8 port, u32 bs,
+				       bool fc, bool rs,
+				       enum ice_eth56g_link_spd spd)
+{
+	u8 port_offset = port & (ICE_PORTS_PER_QUAD - 1);
+	u8 port_blk = port & ~(ICE_PORTS_PER_QUAD - 1);
+	u32 bitslip;
+	int err;
+
+	if (!bs || rs)
+		return 0;
+
+	if (spd == ICE_ETH56G_LNK_SPD_1G || spd == ICE_ETH56G_LNK_SPD_2_5G)
+		err = ice_read_gpcs_reg_eth56g(hw, port, PHY_GPCS_BITSLIP,
+					       &bitslip);
+	else
+		err = ice_read_ptp_reg_eth56g(hw, port_blk,
+					      PHY_REG_SD_BIT_SLIP(port_offset),
+					      &bitslip);
+	if (err)
+		return 0;
+
+	if (spd == ICE_ETH56G_LNK_SPD_1G && !bitslip) {
+		/* Bitslip register value of 0 corresponds to 10 so substitute
+		 * it for calculations
+		 */
+		bitslip = 10;
+	} else if (spd == ICE_ETH56G_LNK_SPD_10G ||
+		   spd == ICE_ETH56G_LNK_SPD_25G) {
+		if (fc)
+			bitslip = bitslip * 2 + 32;
+		else
+			bitslip = (u32)((s32)bitslip * -1 + 20);
+	}
+
+	bitslip <<= ICE_ETH56G_MAC_CFG_FRAC_W;
+	return mul_u32_u32_fx_q9(bitslip, bs);
+}
+
+/**
+ * ice_ptp_calc_deskew_eth56g - Calculate deskew value
+ * @hw: pointer to the HW struct
+ * @port: port to configure
+ * @ds: deskew multiplier
+ * @rs: RS-FEC enabled
+ * @spd: link speed
+ *
+ * Return: calculated deskew value
+ */
+static u32 ice_ptp_calc_deskew_eth56g(struct ice_hw *hw, u8 port, u32 ds,
+				      bool rs, enum ice_eth56g_link_spd spd)
+{
+	u32 deskew_i, deskew_f;
+	int err;
+
+	if (!ds)
+		return 0;
+
+	read_poll_timeout(ice_read_ptp_reg_eth56g, err,
+			  FIELD_GET(PHY_REG_DESKEW_0_VALID, deskew_i), 500,
+			  50 * USEC_PER_MSEC, false, hw, port, PHY_REG_DESKEW_0,
+			  &deskew_i);
+	if (err)
+		return err;
+
+	deskew_f = FIELD_GET(PHY_REG_DESKEW_0_RLEVEL_FRAC, deskew_i);
+	deskew_i = FIELD_GET(PHY_REG_DESKEW_0_RLEVEL, deskew_i);
+
+	if (rs && spd == ICE_ETH56G_LNK_SPD_50G2)
+		ds = 0x633; /* 3.1 */
+	else if (rs && spd == ICE_ETH56G_LNK_SPD_100G)
+		ds = 0x31b; /* 1.552 */
+
+	deskew_i = FIELD_PREP(ICE_ETH56G_MAC_CFG_RX_OFFSET_INT, deskew_i);
+	/* Shift 3 fractional bits to the end of the integer part */
+	deskew_f <<= ICE_ETH56G_MAC_CFG_FRAC_W - PHY_REG_DESKEW_0_RLEVEL_FRAC_W;
+	return mul_u32_u32_fx_q9(deskew_i | deskew_f, ds);
+}
+
+/**
+ * ice_phy_set_offsets_eth56g - Set Tx/Rx offset values
+ * @hw: pointer to the HW struct
+ * @port: port to configure
+ * @spd: link speed
+ * @cfg: structure to store output values
+ * @fc: FC-FEC enabled
+ * @rs: RS-FEC enabled
+ *
+ * Return:
+ * * %0     - success
+ * * %other - failed to write to PHY
+ */
+static int ice_phy_set_offsets_eth56g(struct ice_hw *hw, u8 port,
+				      enum ice_eth56g_link_spd spd,
+				      const struct ice_eth56g_mac_reg_cfg *cfg,
+				      bool fc, bool rs)
+{
+	u32 rx_offset, tx_offset, bs_ds;
+	bool onestep, sfd;
+
+	onestep = hw->ptp.phy.eth56g.onestep_ena;
+	sfd = hw->ptp.phy.eth56g.sfd_ena;
+	bs_ds = cfg->rx_offset.bs_ds;
+
+	if (fc)
+		rx_offset = cfg->rx_offset.fc;
+	else if (rs)
+		rx_offset = cfg->rx_offset.rs;
+	else
+		rx_offset = cfg->rx_offset.no_fec;
+
+	rx_offset = add_u32_u32_fx(rx_offset, cfg->rx_offset.serdes);
+	if (sfd)
+		rx_offset = add_u32_u32_fx(rx_offset, cfg->rx_offset.sfd);
+
+	if (spd < ICE_ETH56G_LNK_SPD_40G)
+		bs_ds = ice_ptp_calc_bitslip_eth56g(hw, port, bs_ds, fc, rs,
+						    spd);
+	else
+		bs_ds = ice_ptp_calc_deskew_eth56g(hw, port, bs_ds, rs, spd);
+	rx_offset = add_u32_u32_fx(rx_offset, bs_ds);
+	rx_offset &= ICE_ETH56G_MAC_CFG_RX_OFFSET_INT |
+		     ICE_ETH56G_MAC_CFG_RX_OFFSET_FRAC;
+
+	if (fc)
+		tx_offset = cfg->tx_offset.fc;
+	else if (rs)
+		tx_offset = cfg->tx_offset.rs;
+	else
+		tx_offset = cfg->tx_offset.no_fec;
+	tx_offset += cfg->tx_offset.serdes + cfg->tx_offset.sfd * sfd +
+		     cfg->tx_offset.onestep * onestep;
+
+	ice_write_mac_reg_eth56g(hw, port, PHY_MAC_RX_OFFSET, rx_offset);
+	return ice_write_mac_reg_eth56g(hw, port, PHY_MAC_TX_OFFSET, tx_offset);
+}
+
+/**
+ * ice_phy_cfg_mac_eth56g - Configure MAC for PTP
+ * @hw: Pointer to the HW struct
+ * @port: Port to configure
+ *
+ * Return:
+ * * %0     - success
+ * * %other - failed to write to PHY
+ */
+static int ice_phy_cfg_mac_eth56g(struct ice_hw *hw, u8 port)
+{
+	const struct ice_eth56g_mac_reg_cfg *cfg;
+	enum ice_eth56g_link_spd spd;
+	struct ice_link_status *li;
+	bool fc = false;
+	bool rs = false;
+	bool onestep;
+	u32 val;
+	int err;
+
+	onestep = hw->ptp.phy.eth56g.onestep_ena;
+	li = &hw->port_info->phy.link_info;
+	spd = ice_phy_get_speed_eth56g(li);
+	if (!!(li->an_info & ICE_AQ_FEC_EN)) {
+		if (spd == ICE_ETH56G_LNK_SPD_10G) {
+			fc = true;
+		} else {
+			fc = !!(li->fec_info & ICE_AQ_LINK_25G_KR_FEC_EN);
+			rs = !!(li->fec_info & ~ICE_AQ_LINK_25G_KR_FEC_EN);
+		}
+	}
+	cfg = &eth56g_mac_cfg[spd];
+
+	err = ice_write_mac_reg_eth56g(hw, port, PHY_MAC_RX_MODULO, 0);
+	if (err)
+		return err;
+
+	err = ice_write_mac_reg_eth56g(hw, port, PHY_MAC_TX_MODULO, 0);
+	if (err)
+		return err;
+
+	val = FIELD_PREP(PHY_MAC_TSU_CFG_TX_MODE_M,
+			 cfg->tx_mode.def + rs * cfg->tx_mode.rs) |
+	      FIELD_PREP(PHY_MAC_TSU_CFG_TX_MII_MK_DLY_M, cfg->tx_mk_dly) |
+	      FIELD_PREP(PHY_MAC_TSU_CFG_TX_MII_CW_DLY_M,
+			 cfg->tx_cw_dly.def +
+			 onestep * cfg->tx_cw_dly.onestep) |
+	      FIELD_PREP(PHY_MAC_TSU_CFG_RX_MODE_M,
+			 cfg->rx_mode.def + rs * cfg->rx_mode.rs) |
+	      FIELD_PREP(PHY_MAC_TSU_CFG_RX_MII_MK_DLY_M,
+			 cfg->rx_mk_dly.def + rs * cfg->rx_mk_dly.rs) |
+	      FIELD_PREP(PHY_MAC_TSU_CFG_RX_MII_CW_DLY_M,
+			 cfg->rx_cw_dly.def + rs * cfg->rx_cw_dly.rs) |
+	      FIELD_PREP(PHY_MAC_TSU_CFG_BLKS_PER_CLK_M, cfg->blks_per_clk);
+	err = ice_write_mac_reg_eth56g(hw, port, PHY_MAC_TSU_CONFIG, val);
+	if (err)
+		return err;
+
+	err = ice_write_mac_reg_eth56g(hw, port, PHY_MAC_BLOCKTIME,
+				       cfg->blktime);
+	if (err)
+		return err;
+
+	err = ice_phy_set_offsets_eth56g(hw, port, spd, cfg, fc, rs);
+	if (err)
+		return err;
+
+	if (spd == ICE_ETH56G_LNK_SPD_25G && !rs)
+		val = 0;
+	else
+		val = cfg->mktime;
+
+	return ice_write_mac_reg_eth56g(hw, port, PHY_MAC_MARKERTIME, val);
+}
+
+/**
+ * ice_phy_cfg_intr_eth56g - Configure TX timestamp interrupt
+ * @hw: pointer to the HW struct
+ * @port: the timestamp port
+ * @ena: enable or disable interrupt
+ * @threshold: interrupt threshold
+ *
+ * Configure TX timestamp interrupt for the specified port
+ *
+ * Return:
+ * * %0     - success
+ * * %other - PHY read/write failed
+ */
+int ice_phy_cfg_intr_eth56g(struct ice_hw *hw, u8 port, bool ena, u8 threshold)
+{
+	int err;
+	u32 val;
+
+	err = ice_read_ptp_reg_eth56g(hw, port, PHY_REG_TS_INT_CONFIG, &val);
+	if (err)
+		return err;
+
+	if (ena) {
+		val |= PHY_TS_INT_CONFIG_ENA_M;
+		val &= ~PHY_TS_INT_CONFIG_THRESHOLD_M;
+		val |= FIELD_PREP(PHY_TS_INT_CONFIG_THRESHOLD_M, threshold);
+	} else {
+		val &= ~PHY_TS_INT_CONFIG_ENA_M;
+	}
+
+	return ice_write_ptp_reg_eth56g(hw, port, PHY_REG_TS_INT_CONFIG, val);
+}
+
+/**
+ * ice_read_phy_and_phc_time_eth56g - Simultaneously capture PHC and PHY time
+ * @hw: pointer to the HW struct
+ * @port: the PHY port to read
+ * @phy_time: on return, the 64bit PHY timer value
+ * @phc_time: on return, the lower 64bits of PHC time
+ *
+ * Issue a ICE_PTP_READ_TIME timer command to simultaneously capture the PHY
+ * and PHC timer values.
+ *
+ * Return:
+ * * %0     - success
+ * * %other - PHY read/write failed
+ */
+static int ice_read_phy_and_phc_time_eth56g(struct ice_hw *hw, u8 port,
+					    u64 *phy_time, u64 *phc_time)
+{
+	u64 tx_time, rx_time;
+	u32 zo, lo;
+	u8 tmr_idx;
+	int err;
+
+	tmr_idx = ice_get_ptp_src_clock_index(hw);
+
+	/* Prepare the PHC timer for a ICE_PTP_READ_TIME capture command */
+	ice_ptp_src_cmd(hw, ICE_PTP_READ_TIME);
+
+	/* Prepare the PHY timer for a ICE_PTP_READ_TIME capture command */
+	err = ice_ptp_one_port_cmd(hw, port, ICE_PTP_READ_TIME);
+	if (err)
+		return err;
+
+	/* Issue the sync to start the ICE_PTP_READ_TIME capture */
+	ice_ptp_exec_tmr_cmd(hw);
+
+	/* Read the captured PHC time from the shadow time registers */
+	zo = rd32(hw, GLTSYN_SHTIME_0(tmr_idx));
+	lo = rd32(hw, GLTSYN_SHTIME_L(tmr_idx));
+	*phc_time = (u64)lo << 32 | zo;
+
+	/* Read the captured PHY time from the PHY shadow registers */
+	err = ice_ptp_read_port_capture_eth56g(hw, port, &tx_time, &rx_time);
+	if (err)
+		return err;
+
+	/* If the PHY Tx and Rx timers don't match, log a warning message.
+	 * Note that this should not happen in normal circumstances since the
+	 * driver always programs them together.
+	 */
+	if (tx_time != rx_time)
+		dev_warn(ice_hw_to_dev(hw), "PHY port %u Tx and Rx timers do not match, tx_time 0x%016llX, rx_time 0x%016llX\n",
+			 port, tx_time, rx_time);
+
+	*phy_time = tx_time;
+
+	return 0;
+}
+
+/**
+ * ice_sync_phy_timer_eth56g - Synchronize the PHY timer with PHC timer
+ * @hw: pointer to the HW struct
+ * @port: the PHY port to synchronize
+ *
+ * Perform an adjustment to ensure that the PHY and PHC timers are in sync.
+ * This is done by issuing a ICE_PTP_READ_TIME command which triggers a
+ * simultaneous read of the PHY timer and PHC timer. Then we use the
+ * difference to calculate an appropriate 2s complement addition to add
+ * to the PHY timer in order to ensure it reads the same value as the
+ * primary PHC timer.
+ *
+ * Return:
+ * * %0     - success
+ * * %-EBUSY- failed to acquire PTP semaphore
+ * * %other - PHY read/write failed
+ */
+static int ice_sync_phy_timer_eth56g(struct ice_hw *hw, u8 port)
+{
+	u64 phc_time, phy_time, difference;
+	int err;
+
+	if (!ice_ptp_lock(hw)) {
+		ice_debug(hw, ICE_DBG_PTP, "Failed to acquire PTP semaphore\n");
+		return -EBUSY;
+	}
+
+	err = ice_read_phy_and_phc_time_eth56g(hw, port, &phy_time, &phc_time);
+	if (err)
+		goto err_unlock;
+
+	/* Calculate the amount required to add to the port time in order for
+	 * it to match the PHC time.
+	 *
+	 * Note that the port adjustment is done using 2s complement
+	 * arithmetic. This is convenient since it means that we can simply
+	 * calculate the difference between the PHC time and the port time,
+	 * and it will be interpreted correctly.
+	 */
+
+	ice_ptp_src_cmd(hw, ICE_PTP_NOP);
+	difference = phc_time - phy_time;
+
+	err = ice_ptp_prep_port_adj_eth56g(hw, port, (s64)difference);
+	if (err)
+		goto err_unlock;
+
+	err = ice_ptp_one_port_cmd(hw, port, ICE_PTP_ADJ_TIME);
+	if (err)
+		goto err_unlock;
+
+	/* Issue the sync to activate the time adjustment */
+	ice_ptp_exec_tmr_cmd(hw);
+
+	/* Re-capture the timer values to flush the command registers and
+	 * verify that the time was properly adjusted.
+	 */
+	err = ice_read_phy_and_phc_time_eth56g(hw, port, &phy_time, &phc_time);
+	if (err)
+		goto err_unlock;
+
+	dev_info(ice_hw_to_dev(hw),
+		 "Port %u PHY time synced to PHC: 0x%016llX, 0x%016llX\n",
+		 port, phy_time, phc_time);
+
+err_unlock:
+	ice_ptp_unlock(hw);
+	return err;
+}
+
+/**
+ * ice_stop_phy_timer_eth56g - Stop the PHY clock timer
+ * @hw: pointer to the HW struct
+ * @port: the PHY port to stop
+ * @soft_reset: if true, hold the SOFT_RESET bit of PHY_REG_PS
+ *
+ * Stop the clock of a PHY port. This must be done as part of the flow to
+ * re-calibrate Tx and Rx timestamping offsets whenever the clock time is
+ * initialized or when link speed changes.
+ *
+ * Return:
+ * * %0     - success
+ * * %other - failed to write to PHY
+ */
+int ice_stop_phy_timer_eth56g(struct ice_hw *hw, u8 port, bool soft_reset)
+{
+	int err;
+
+	err = ice_write_ptp_reg_eth56g(hw, port, PHY_REG_TX_OFFSET_READY, 0);
+	if (err)
+		return err;
+
+	err = ice_write_ptp_reg_eth56g(hw, port, PHY_REG_RX_OFFSET_READY, 0);
+	if (err)
+		return err;
+
+	ice_debug(hw, ICE_DBG_PTP, "Disabled clock on PHY port %u\n", port);
+
+	return 0;
+}
+
+/**
+ * ice_start_phy_timer_eth56g - Start the PHY clock timer
+ * @hw: pointer to the HW struct
+ * @port: the PHY port to start
+ *
+ * Start the clock of a PHY port. This must be done as part of the flow to
+ * re-calibrate Tx and Rx timestamping offsets whenever the clock time is
+ * initialized or when link speed changes.
+ *
+ * Return:
+ * * %0     - success
+ * * %other - PHY read/write failed
+ */
+int ice_start_phy_timer_eth56g(struct ice_hw *hw, u8 port)
+{
+	u32 lo, hi;
+	u64 incval;
+	u8 tmr_idx;
+	int err;
+
+	tmr_idx = ice_get_ptp_src_clock_index(hw);
+
+	err = ice_stop_phy_timer_eth56g(hw, port, false);
+	if (err)
+		return err;
+
+	ice_ptp_src_cmd(hw, ICE_PTP_NOP);
+
+	err = ice_phy_cfg_parpcs_eth56g(hw, port);
+	if (err)
+		return err;
+
+	err = ice_phy_cfg_ptp_1step_eth56g(hw, port);
+	if (err)
+		return err;
+
+	err = ice_phy_cfg_mac_eth56g(hw, port);
+	if (err)
+		return err;
+
+	lo = rd32(hw, GLTSYN_INCVAL_L(tmr_idx));
+	hi = rd32(hw, GLTSYN_INCVAL_H(tmr_idx));
+	incval = (u64)hi << 32 | lo;
+
+	err = ice_write_40b_ptp_reg_eth56g(hw, port, PHY_REG_TIMETUS_L, incval);
+	if (err)
+		return err;
+
+	err = ice_ptp_one_port_cmd(hw, port, ICE_PTP_INIT_INCVAL);
+	if (err)
+		return err;
+
+	ice_ptp_exec_tmr_cmd(hw);
+
+	err = ice_sync_phy_timer_eth56g(hw, port);
+	if (err)
+		return err;
+
+	err = ice_write_ptp_reg_eth56g(hw, port, PHY_REG_TX_OFFSET_READY, 1);
+	if (err)
+		return err;
+
+	err = ice_write_ptp_reg_eth56g(hw, port, PHY_REG_RX_OFFSET_READY, 1);
+	if (err)
+		return err;
+
+	ice_debug(hw, ICE_DBG_PTP, "Enabled clock on PHY port %u\n", port);
+
+	return 0;
+}
+
+/**
+ * ice_sb_access_ena_eth56g - Enable SB devices (PHY and others) access
+ * @hw: pointer to HW struct
+ * @enable: Enable or disable access
+ *
+ * Enable sideband devices (PHY and others) access.
+ */
+static void ice_sb_access_ena_eth56g(struct ice_hw *hw, bool enable)
+{
+	u32 val = rd32(hw, PF_SB_REM_DEV_CTL);
+
+	if (enable)
+		val |= BIT(eth56g_phy_0) | BIT(cgu) | BIT(eth56g_phy_1);
+	else
+		val &= ~(BIT(eth56g_phy_0) | BIT(cgu) | BIT(eth56g_phy_1));
+
+	wr32(hw, PF_SB_REM_DEV_CTL, val);
+}
+
+/**
+ * ice_ptp_init_phc_eth56g - Perform E82X specific PHC initialization
+ * @hw: pointer to HW struct
+ *
+ * Perform PHC initialization steps specific to E82X devices.
+ *
+ * Return:
+ * * %0     - success
+ * * %other - failed to initialize CGU
+ */
+static int ice_ptp_init_phc_eth56g(struct ice_hw *hw)
+{
+	ice_sb_access_ena_eth56g(hw, true);
+	/* Initialize the Clock Generation Unit */
+	return ice_init_cgu_e82x(hw);
+}
+
+/**
+ * ice_ptp_read_tx_hwtstamp_status_eth56g - Get TX timestamp status
+ * @hw: pointer to the HW struct
+ * @ts_status: the timestamp mask pointer
+ *
+ * Read the PHY Tx timestamp status mask indicating which ports have Tx
+ * timestamps available.
+ *
+ * Return:
+ * * %0     - success
+ * * %other - failed to read from PHY
+ */
+int ice_ptp_read_tx_hwtstamp_status_eth56g(struct ice_hw *hw, u32 *ts_status)
+{
+	const struct ice_eth56g_params *params = &hw->ptp.phy.eth56g;
+	u8 phy, mask;
+	u32 status;
+
+	mask = (1 << hw->ptp.ports_per_phy) - 1;
+	*ts_status = 0;
+
+	for (phy = 0; phy < params->num_phys; phy++) {
+		int err;
+
+		err = ice_read_phy_eth56g(hw, phy, PHY_PTP_INT_STATUS, &status);
+		if (err)
+			return err;
+
+		*ts_status |= (status & mask) << (phy * hw->ptp.ports_per_phy);
+	}
+
+	ice_debug(hw, ICE_DBG_PTP, "PHY interrupt err: %x\n", *ts_status);
+
+	return 0;
+}
+
+/**
+ * ice_get_phy_tx_tstamp_ready_eth56g - Read the Tx memory status register
+ * @hw: pointer to the HW struct
+ * @port: the PHY port to read from
+ * @tstamp_ready: contents of the Tx memory status register
+ *
+ * Read the PHY_REG_TX_MEMORY_STATUS register indicating which timestamps in
+ * the PHY are ready. A set bit means the corresponding timestamp is valid and
+ * ready to be captured from the PHY timestamp block.
+ *
+ * Return:
+ * * %0     - success
+ * * %other - failed to read from PHY
+ */
+static int ice_get_phy_tx_tstamp_ready_eth56g(struct ice_hw *hw, u8 port,
+					      u64 *tstamp_ready)
+{
+	int err;
+
+	err = ice_read_64b_ptp_reg_eth56g(hw, port, PHY_REG_TX_MEMORY_STATUS_L,
+					  tstamp_ready);
+	if (err) {
+		ice_debug(hw, ICE_DBG_PTP, "Failed to read TX_MEMORY_STATUS for port %u, err %d\n",
+			  port, err);
+		return err;
+	}
+
+	return 0;
+}
+
+/**
+ * ice_ptp_init_phy_e825c - initialize PHY parameters
+ * @hw: pointer to the HW struct
+ */
+static void ice_ptp_init_phy_e825c(struct ice_hw *hw)
+{
+	struct ice_ptp_hw *ptp = &hw->ptp;
+	struct ice_eth56g_params *params;
+	u8 phy;
+
+	ptp->phy_model = ICE_PHY_ETH56G;
+	params = &ptp->phy.eth56g;
+	params->onestep_ena = false;
+	params->peer_delay = 0;
+	params->sfd_ena = false;
+	params->phy_addr[0] = eth56g_phy_0;
+	params->phy_addr[1] = eth56g_phy_1;
+	params->num_phys = 2;
+	ptp->ports_per_phy = 4;
+	ptp->num_lports = params->num_phys * ptp->ports_per_phy;
+
+	ice_sb_access_ena_eth56g(hw, true);
+	for (phy = 0; phy < params->num_phys; phy++) {
+		u32 phy_rev;
+		int err;
+
+		err = ice_read_phy_eth56g(hw, phy, PHY_REG_REVISION, &phy_rev);
+		if (err || phy_rev != PHY_REVISION_ETH56G) {
+			ptp->phy_model = ICE_PHY_UNSUP;
+			return;
+		}
+	}
+}
+
 /* E822 family functions
  *
  * The following functions operate on the E822 family of devices.
@@ -1223,15 +3028,14 @@ static int ice_ptp_set_vernier_wl(struct ice_hw *hw)
 static int ice_ptp_init_phc_e82x(struct ice_hw *hw)
 {
 	int err;
-	u32 regval;
+	u32 val;
 
 	/* Enable reading switch and PHY registers over the sideband queue */
 #define PF_SB_REM_DEV_CTL_SWITCH_READ BIT(1)
 #define PF_SB_REM_DEV_CTL_PHY0 BIT(2)
-	regval = rd32(hw, PF_SB_REM_DEV_CTL);
-	regval |= (PF_SB_REM_DEV_CTL_SWITCH_READ |
-		   PF_SB_REM_DEV_CTL_PHY0);
-	wr32(hw, PF_SB_REM_DEV_CTL, regval);
+	val = rd32(hw, PF_SB_REM_DEV_CTL);
+	val |= (PF_SB_REM_DEV_CTL_SWITCH_READ | PF_SB_REM_DEV_CTL_PHY0);
+	wr32(hw, PF_SB_REM_DEV_CTL, val);
 
 	/* Initialize the Clock Generation Unit */
 	err = ice_init_cgu_e82x(hw);
@@ -1458,51 +3262,20 @@ ice_ptp_read_port_capture(struct ice_hw *hw, u8 port, u64 *tx_ts, u64 *rx_ts)
  *
  * Prepare the requested port for an upcoming timer sync command.
  *
- * Do not use this function directly. If you want to configure exactly one
- * port, use ice_ptp_one_port_cmd() instead.
+ * Note there is no equivalent of this operation on E810, as that device
+ * always handles all external PHYs internally.
+ *
+ * Return:
+ * * %0     - success
+ * * %other - failed to write to PHY
  */
 static int ice_ptp_write_port_cmd_e82x(struct ice_hw *hw, u8 port,
 				       enum ice_ptp_tmr_cmd cmd)
 {
-	u32 cmd_val, val;
-	u8 tmr_idx;
+	u32 val = ice_ptp_tmr_cmd_to_port_reg(hw, cmd);
 	int err;
 
-	tmr_idx = ice_get_ptp_src_clock_index(hw);
-	cmd_val = tmr_idx << SEL_PHY_SRC;
-	switch (cmd) {
-	case ICE_PTP_INIT_TIME:
-		cmd_val |= PHY_CMD_INIT_TIME;
-		break;
-	case ICE_PTP_INIT_INCVAL:
-		cmd_val |= PHY_CMD_INIT_INCVAL;
-		break;
-	case ICE_PTP_ADJ_TIME:
-		cmd_val |= PHY_CMD_ADJ_TIME;
-		break;
-	case ICE_PTP_READ_TIME:
-		cmd_val |= PHY_CMD_READ_TIME;
-		break;
-	case ICE_PTP_ADJ_TIME_AT_TIME:
-		cmd_val |= PHY_CMD_ADJ_TIME_AT_TIME;
-		break;
-	case ICE_PTP_NOP:
-		break;
-	}
-
 	/* Tx case */
-	/* Read, modify, write */
-	err = ice_read_phy_reg_e82x(hw, port, P_REG_TX_TMR_CMD, &val);
-	if (err) {
-		ice_debug(hw, ICE_DBG_PTP, "Failed to read TX_TMR_CMD, err %d\n",
-			  err);
-		return err;
-	}
-
-	/* Modify necessary bits only and perform write */
-	val &= ~TS_CMD_MASK;
-	val |= cmd_val;
-
 	err = ice_write_phy_reg_e82x(hw, port, P_REG_TX_TMR_CMD, val);
 	if (err) {
 		ice_debug(hw, ICE_DBG_PTP, "Failed to write back TX_TMR_CMD, err %d\n",
@@ -1511,19 +3284,8 @@ static int ice_ptp_write_port_cmd_e82x(struct ice_hw *hw, u8 port,
 	}
 
 	/* Rx case */
-	/* Read, modify, write */
-	err = ice_read_phy_reg_e82x(hw, port, P_REG_RX_TMR_CMD, &val);
-	if (err) {
-		ice_debug(hw, ICE_DBG_PTP, "Failed to read RX_TMR_CMD, err %d\n",
-			  err);
-		return err;
-	}
-
-	/* Modify necessary bits only and perform write */
-	val &= ~TS_CMD_MASK;
-	val |= cmd_val;
-
-	err = ice_write_phy_reg_e82x(hw, port, P_REG_RX_TMR_CMD, val);
+	err = ice_write_phy_reg_e82x(hw, port, P_REG_RX_TMR_CMD,
+				     val | TS_CMD_RX_TYPE);
 	if (err) {
 		ice_debug(hw, ICE_DBG_PTP, "Failed to write back RX_TMR_CMD, err %d\n",
 			  err);
@@ -1533,63 +3295,6 @@ static int ice_ptp_write_port_cmd_e82x(struct ice_hw *hw, u8 port,
 	return 0;
 }
 
-/**
- * ice_ptp_one_port_cmd - Prepare one port for a timer command
- * @hw: pointer to the HW struct
- * @configured_port: the port to configure with configured_cmd
- * @configured_cmd: timer command to prepare on the configured_port
- *
- * Prepare the configured_port for the configured_cmd, and prepare all other
- * ports for ICE_PTP_NOP. This causes the configured_port to execute the
- * desired command while all other ports perform no operation.
- */
-static int
-ice_ptp_one_port_cmd(struct ice_hw *hw, u8 configured_port,
-		     enum ice_ptp_tmr_cmd configured_cmd)
-{
-	u8 port;
-
-	for (port = 0; port < hw->ptp.num_lports; port++) {
-		enum ice_ptp_tmr_cmd cmd;
-		int err;
-
-		if (port == configured_port)
-			cmd = configured_cmd;
-		else
-			cmd = ICE_PTP_NOP;
-
-		err = ice_ptp_write_port_cmd_e82x(hw, port, cmd);
-		if (err)
-			return err;
-	}
-
-	return 0;
-}
-
-/**
- * ice_ptp_port_cmd_e82x - Prepare all ports for a timer command
- * @hw: pointer to the HW struct
- * @cmd: timer command to prepare
- *
- * Prepare all ports connected to this device for an upcoming timer sync
- * command.
- */
-static int
-ice_ptp_port_cmd_e82x(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd)
-{
-	u8 port;
-
-	for (port = 0; port < hw->ptp.num_lports; port++) {
-		int err;
-
-		err = ice_ptp_write_port_cmd_e82x(hw, port, cmd);
-		if (err)
-			return err;
-	}
-
-	return 0;
-}
-
 /* E822 Vernier calibration functions
  *
  * The following functions are used as part of the vernier calibration of
@@ -3437,10 +5142,114 @@ void ice_ptp_init_hw(struct ice_hw *hw)
 		ice_ptp_init_phy_e82x(ptp);
 	else if (ice_is_e810(hw))
 		ice_ptp_init_phy_e810(ptp);
+	else if (ice_is_e825c(hw))
+		ice_ptp_init_phy_e825c(hw);
 	else
 		ptp->phy_model = ICE_PHY_UNSUP;
 }
 
+/**
+ * ice_ptp_write_port_cmd - Prepare a single PHY port for a timer command
+ * @hw: pointer to HW struct
+ * @port: Port to which cmd has to be sent
+ * @cmd: Command to be sent to the port
+ *
+ * Prepare one port for the upcoming timer sync command. Do not use this for
+ * programming only a single port, instead use ice_ptp_one_port_cmd() to
+ * ensure non-modified ports get properly initialized to ICE_PTP_NOP.
+ *
+ * Return:
+ * * %0     - success
+ *  %-EBUSY - PHY type not supported
+ * * %other - failed to write port command
+ */
+static int ice_ptp_write_port_cmd(struct ice_hw *hw, u8 port,
+				  enum ice_ptp_tmr_cmd cmd)
+{
+	switch (hw->ptp.phy_model) {
+	case ICE_PHY_ETH56G:
+		return ice_ptp_write_port_cmd_eth56g(hw, port, cmd);
+	case ICE_PHY_E82X:
+		return ice_ptp_write_port_cmd_e82x(hw, port, cmd);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+/**
+ * ice_ptp_one_port_cmd - Program one PHY port for a timer command
+ * @hw: pointer to HW struct
+ * @configured_port: the port that should execute the command
+ * @configured_cmd: the command to be executed on the configured port
+ *
+ * Prepare one port for executing a timer command, while preparing all other
+ * ports to ICE_PTP_NOP. This allows executing a command on a single port
+ * while ensuring all other ports do not execute stale commands.
+ *
+ * Return:
+ * * %0     - success
+ * * %other - failed to write port command
+ */
+int ice_ptp_one_port_cmd(struct ice_hw *hw, u8 configured_port,
+			 enum ice_ptp_tmr_cmd configured_cmd)
+{
+	u32 port;
+
+	for (port = 0; port < hw->ptp.num_lports; port++) {
+		int err;
+
+		/* Program the configured port with the configured command,
+		 * program all other ports with ICE_PTP_NOP.
+		 */
+		if (port == configured_port)
+			err = ice_ptp_write_port_cmd(hw, port, configured_cmd);
+		else
+			err = ice_ptp_write_port_cmd(hw, port, ICE_PTP_NOP);
+
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+/**
+ * ice_ptp_port_cmd - Prepare PHY ports for a timer sync command
+ * @hw: pointer to HW struct
+ * @cmd: the timer command to setup
+ *
+ * Prepare all PHY ports on this device for the requested timer command. For
+ * some families this can be done in one shot, but for other families each
+ * port must be configured individually.
+ *
+ * Return:
+ * * %0     - success
+ * * %other - failed to write port command
+ */
+static int ice_ptp_port_cmd(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd)
+{
+	u32 port;
+
+	/* PHY models which can program all ports simultaneously */
+	switch (hw->ptp.phy_model) {
+	case ICE_PHY_E810:
+		return ice_ptp_port_cmd_e810(hw, cmd);
+	default:
+		break;
+	}
+
+	/* PHY models which require programming each port separately */
+	for (port = 0; port < hw->ptp.num_lports; port++) {
+		int err;
+
+		err = ice_ptp_write_port_cmd(hw, port, cmd);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
 /**
  * ice_ptp_tmr_cmd - Prepare and trigger a timer sync command
  * @hw: pointer to HW struct
@@ -3459,17 +5268,7 @@ static int ice_ptp_tmr_cmd(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd)
 	ice_ptp_src_cmd(hw, cmd);
 
 	/* Next, prepare the ports */
-	switch (hw->ptp.phy_model) {
-	case ICE_PHY_E810:
-		err = ice_ptp_port_cmd_e810(hw, cmd);
-		break;
-	case ICE_PHY_E82X:
-		err = ice_ptp_port_cmd_e82x(hw, cmd);
-		break;
-	default:
-		err = -EOPNOTSUPP;
-	}
-
+	err = ice_ptp_port_cmd(hw, cmd);
 	if (err) {
 		ice_debug(hw, ICE_DBG_PTP, "Failed to prepare PHY ports for timer command %u, err %d\n",
 			  cmd, err);
@@ -3512,6 +5311,10 @@ int ice_ptp_init_time(struct ice_hw *hw, u64 time)
 	/* PHY timers */
 	/* Fill Rx and Tx ports and send msg to PHY */
 	switch (hw->ptp.phy_model) {
+	case ICE_PHY_ETH56G:
+		err = ice_ptp_prep_phy_time_eth56g(hw,
+						   (u32)(time & 0xFFFFFFFF));
+		break;
 	case ICE_PHY_E810:
 		err = ice_ptp_prep_phy_time_e810(hw, time & 0xFFFFFFFF);
 		break;
@@ -3554,6 +5357,9 @@ int ice_ptp_write_incval(struct ice_hw *hw, u64 incval)
 	wr32(hw, GLTSYN_SHADJ_H(tmr_idx), upper_32_bits(incval));
 
 	switch (hw->ptp.phy_model) {
+	case ICE_PHY_ETH56G:
+		err = ice_ptp_prep_phy_incval_eth56g(hw, incval);
+		break;
 	case ICE_PHY_E810:
 		err = ice_ptp_prep_phy_incval_e810(hw, incval);
 		break;
@@ -3620,6 +5426,9 @@ int ice_ptp_adj_clock(struct ice_hw *hw, s32 adj)
 	wr32(hw, GLTSYN_SHADJ_H(tmr_idx), adj);
 
 	switch (hw->ptp.phy_model) {
+	case ICE_PHY_ETH56G:
+		err = ice_ptp_prep_phy_adj_eth56g(hw, adj);
+		break;
 	case ICE_PHY_E810:
 		err = ice_ptp_prep_phy_adj_e810(hw, adj);
 		break;
@@ -3650,6 +5459,8 @@ int ice_ptp_adj_clock(struct ice_hw *hw, s32 adj)
 int ice_read_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx, u64 *tstamp)
 {
 	switch (hw->ptp.phy_model) {
+	case ICE_PHY_ETH56G:
+		return ice_read_ptp_tstamp_eth56g(hw, block, idx, tstamp);
 	case ICE_PHY_E810:
 		return ice_read_phy_tstamp_e810(hw, block, idx, tstamp);
 	case ICE_PHY_E82X:
@@ -3678,6 +5489,8 @@ int ice_read_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx, u64 *tstamp)
 int ice_clear_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx)
 {
 	switch (hw->ptp.phy_model) {
+	case ICE_PHY_ETH56G:
+		return ice_clear_ptp_tstamp_eth56g(hw, block, idx);
 	case ICE_PHY_E810:
 		return ice_clear_phy_tstamp_e810(hw, block, idx);
 	case ICE_PHY_E82X:
@@ -3739,6 +5552,9 @@ static int ice_get_pf_c827_idx(struct ice_hw *hw, u8 *idx)
 void ice_ptp_reset_ts_memory(struct ice_hw *hw)
 {
 	switch (hw->ptp.phy_model) {
+	case ICE_PHY_ETH56G:
+		ice_ptp_reset_ts_memory_eth56g(hw);
+		break;
 	case ICE_PHY_E82X:
 		ice_ptp_reset_ts_memory_e82x(hw);
 		break;
@@ -3765,6 +5581,8 @@ int ice_ptp_init_phc(struct ice_hw *hw)
 	(void)rd32(hw, GLTSYN_STAT(src_idx));
 
 	switch (hw->ptp.phy_model) {
+	case ICE_PHY_ETH56G:
+		return ice_ptp_init_phc_eth56g(hw);
 	case ICE_PHY_E810:
 		return ice_ptp_init_phc_e810(hw);
 	case ICE_PHY_E82X:
@@ -3788,6 +5606,9 @@ int ice_ptp_init_phc(struct ice_hw *hw)
 int ice_get_phy_tx_tstamp_ready(struct ice_hw *hw, u8 block, u64 *tstamp_ready)
 {
 	switch (hw->ptp.phy_model) {
+	case ICE_PHY_ETH56G:
+		return ice_get_phy_tx_tstamp_ready_eth56g(hw, block,
+							  tstamp_ready);
 	case ICE_PHY_E810:
 		return ice_get_phy_tx_tstamp_ready_e810(hw, block,
 							tstamp_ready);
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
index 3fe12a1694fc0..184573509e629 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
@@ -41,6 +41,41 @@ enum ice_ptp_fec_mode {
 	ICE_PTP_FEC_MODE_RS_FEC
 };
 
+enum eth56g_res_type {
+	ETH56G_PHY_REG_PTP,
+	ETH56G_PHY_MEM_PTP,
+	ETH56G_PHY_REG_XPCS,
+	ETH56G_PHY_REG_MAC,
+	ETH56G_PHY_REG_GPCS,
+	NUM_ETH56G_PHY_RES
+};
+
+enum ice_eth56g_link_spd {
+	ICE_ETH56G_LNK_SPD_1G,
+	ICE_ETH56G_LNK_SPD_2_5G,
+	ICE_ETH56G_LNK_SPD_10G,
+	ICE_ETH56G_LNK_SPD_25G,
+	ICE_ETH56G_LNK_SPD_40G,
+	ICE_ETH56G_LNK_SPD_50G,
+	ICE_ETH56G_LNK_SPD_50G2,
+	ICE_ETH56G_LNK_SPD_100G,
+	ICE_ETH56G_LNK_SPD_100G2,
+	NUM_ICE_ETH56G_LNK_SPD /* Must be last */
+};
+
+/**
+ * struct ice_phy_reg_info_eth56g - ETH56G PHY register parameters
+ * @base: base address for each PHY block
+ * @step: step between PHY lanes
+ *
+ * Characteristic information for the various PHY register parameters in the
+ * ETH56G devices
+ */
+struct ice_phy_reg_info_eth56g {
+	u32 base[NUM_ETH56G_PHY_RES];
+	u32 step;
+};
+
 /**
  * struct ice_time_ref_info_e82x
  * @pll_freq: Frequency of PLL that drives timer ticks in Hz
@@ -94,6 +129,73 @@ struct ice_vernier_info_e82x {
 	u32 rx_fixed_delay;
 };
 
+#define ICE_ETH56G_MAC_CFG_RX_OFFSET_INT	GENMASK(19, 9)
+#define ICE_ETH56G_MAC_CFG_RX_OFFSET_FRAC	GENMASK(8, 0)
+#define ICE_ETH56G_MAC_CFG_FRAC_W		9
+/**
+ * struct ice_eth56g_mac_reg_cfg - MAC config values for specific PTP registers
+ * @tx_mode: Tx timestamp compensation mode
+ * @tx_mk_dly: Tx timestamp marker start strobe delay
+ * @tx_cw_dly: Tx timestamp codeword start strobe delay
+ * @rx_mode: Rx timestamp compensation mode
+ * @rx_mk_dly: Rx timestamp marker start strobe delay
+ * @rx_cw_dly: Rx timestamp codeword start strobe delay
+ * @blks_per_clk: number of blocks transferred per clock cycle
+ * @blktime: block time, fixed point
+ * @mktime: marker time, fixed point
+ * @tx_offset: total Tx offset, fixed point
+ * @rx_offset: total Rx offset, contains value for bitslip/deskew, fixed point
+ *
+ * All fixed point registers except Rx offset are 23 bit unsigned ints with
+ * a 9 bit fractional.
+ * Rx offset is 11 bit unsigned int with a 9 bit fractional.
+ */
+struct ice_eth56g_mac_reg_cfg {
+	struct {
+		u8 def;
+		u8 rs;
+	} tx_mode;
+	u8 tx_mk_dly;
+	struct {
+		u8 def;
+		u8 onestep;
+	} tx_cw_dly;
+	struct {
+		u8 def;
+		u8 rs;
+	} rx_mode;
+	struct {
+		u8 def;
+		u8 rs;
+	} rx_mk_dly;
+	struct {
+		u8 def;
+		u8 rs;
+	} rx_cw_dly;
+	u8 blks_per_clk;
+	u16 blktime;
+	u16 mktime;
+	struct {
+		u32 serdes;
+		u32 no_fec;
+		u32 fc;
+		u32 rs;
+		u32 sfd;
+		u32 onestep;
+	} tx_offset;
+	struct {
+		u32 serdes;
+		u32 no_fec;
+		u32 fc;
+		u32 rs;
+		u32 sfd;
+		u32 bs_ds;
+	} rx_offset;
+};
+
+extern
+const struct ice_eth56g_mac_reg_cfg eth56g_mac_cfg[NUM_ICE_ETH56G_LNK_SPD];
+
 /**
  * struct ice_cgu_pll_params_e82x
  * @refclk_pre_div: Reference clock pre-divisor
@@ -188,6 +290,9 @@ ice_cgu_pll_params_e82x e822_cgu_params[NUM_ICE_TIME_REF_FREQ];
 #define E810C_QSFP_C827_0_HANDLE 2
 #define E810C_QSFP_C827_1_HANDLE 3
 
+/* Table of constants related to possible ETH56G PHY resources */
+extern const struct ice_phy_reg_info_eth56g eth56g_phy_res[NUM_ETH56G_PHY_RES];
+
 /* Table of constants related to possible TIME_REF sources */
 extern const struct ice_time_ref_info_e82x e822_time_ref[NUM_ICE_TIME_REF_FREQ];
 
@@ -197,7 +302,9 @@ extern const struct ice_vernier_info_e82x e822_vernier[NUM_ICE_PTP_LNK_SPD];
 /* Increment value to generate nanoseconds in the GLTSYN_TIME_L register for
  * the E810 devices. Based off of a PLL with an 812.5 MHz frequency.
  */
-#define ICE_PTP_NOMINAL_INCVAL_E810 0x13b13b13bULL
+#define ICE_E810_PLL_FREQ		812500000
+#define ICE_PTP_NOMINAL_INCVAL_E810	0x13b13b13bULL
+#define E810_OUT_PROP_DELAY_NS 1
 
 /* Device agnostic functions */
 u8 ice_get_ptp_src_clock_index(struct ice_hw *hw);
@@ -215,6 +322,8 @@ void ice_ptp_reset_ts_memory(struct ice_hw *hw);
 int ice_ptp_init_phc(struct ice_hw *hw);
 void ice_ptp_init_hw(struct ice_hw *hw);
 int ice_get_phy_tx_tstamp_ready(struct ice_hw *hw, u8 block, u64 *tstamp_ready);
+int ice_ptp_one_port_cmd(struct ice_hw *hw, u8 configured_port,
+			 enum ice_ptp_tmr_cmd configured_cmd);
 
 /* E822 family functions */
 int ice_read_quad_reg_e82x(struct ice_hw *hw, u8 quad, u16 offset, u32 *val);
@@ -285,6 +394,21 @@ int ice_get_cgu_rclk_pin_info(struct ice_hw *hw, u8 *base_idx, u8 *pin_num);
 int ice_cgu_get_output_pin_state_caps(struct ice_hw *hw, u8 pin_id,
 				      unsigned long *caps);
 
+/* ETH56G family functions */
+int ice_ptp_read_tx_hwtstamp_status_eth56g(struct ice_hw *hw, u32 *ts_status);
+int ice_stop_phy_timer_eth56g(struct ice_hw *hw, u8 port, bool soft_reset);
+int ice_start_phy_timer_eth56g(struct ice_hw *hw, u8 port);
+int ice_phy_cfg_tx_offset_eth56g(struct ice_hw *hw, u8 port);
+int ice_phy_cfg_rx_offset_eth56g(struct ice_hw *hw, u8 port);
+int ice_phy_cfg_intr_eth56g(struct ice_hw *hw, u8 port, bool ena, u8 threshold);
+int ice_phy_cfg_ptp_1step_eth56g(struct ice_hw *hw, u8 port);
+
+#define ICE_ETH56G_NOMINAL_INCVAL	0x140000000ULL
+#define ICE_ETH56G_NOMINAL_PCS_REF_TUS	0x100000000ULL
+#define ICE_ETH56G_NOMINAL_PCS_REF_INC	0x300000000ULL
+#define ICE_ETH56G_NOMINAL_THRESH4	0x7777
+#define ICE_ETH56G_NOMINAL_TX_THRESH	0x6
+
 /**
  * ice_get_base_incval - Get base clock increment value
  * @hw: pointer to the HW struct
@@ -294,6 +418,8 @@ int ice_cgu_get_output_pin_state_caps(struct ice_hw *hw, u8 pin_id,
 static inline u64 ice_get_base_incval(struct ice_hw *hw)
 {
 	switch (hw->ptp.phy_model) {
+	case ICE_PHY_ETH56G:
+		return ICE_ETH56G_NOMINAL_INCVAL;
 	case ICE_PHY_E810:
 		return ICE_PTP_NOMINAL_INCVAL_E810;
 	case ICE_PHY_E82X:
@@ -330,6 +456,7 @@ static inline u64 ice_get_base_incval(struct ice_hw *hw)
 #define TS_CMD_MASK_E810		0xFF
 #define TS_CMD_MASK			0xF
 #define SYNC_EXEC_CMD			0x3
+#define TS_CMD_RX_TYPE			ICE_M(0x18, 0x4)
 
 /* Macros to derive port low and high addresses on both quads */
 #define P_Q0_L(a, p) ((((a) + (0x2000 * (p)))) & 0xFFFF)
@@ -564,4 +691,115 @@ static inline u64 ice_get_base_incval(struct ice_hw *hw)
 /* E810T PCA9575 IO controller pin control */
 #define ICE_E810T_P0_GNSS_PRSNT_N	BIT(4)
 
+/* ETH56G PHY register addresses */
+/* Timestamp PHY incval registers */
+#define PHY_REG_TIMETUS_L		0x8
+#define PHY_REG_TIMETUS_U		0xC
+
+/* Timestamp PCS registers */
+#define PHY_PCS_REF_TUS_L		0x18
+#define PHY_PCS_REF_TUS_U		0x1C
+
+/* Timestamp PCS ref incval registers */
+#define PHY_PCS_REF_INC_L		0x20
+#define PHY_PCS_REF_INC_U		0x24
+
+/* Timestamp init registers */
+#define PHY_REG_RX_TIMER_INC_PRE_L	0x64
+#define PHY_REG_RX_TIMER_INC_PRE_U	0x68
+#define PHY_REG_TX_TIMER_INC_PRE_L	0x44
+#define PHY_REG_TX_TIMER_INC_PRE_U	0x48
+
+/* Timestamp match and adjust target registers */
+#define PHY_REG_RX_TIMER_CNT_ADJ_L	0x6C
+#define PHY_REG_RX_TIMER_CNT_ADJ_U	0x70
+#define PHY_REG_TX_TIMER_CNT_ADJ_L	0x4C
+#define PHY_REG_TX_TIMER_CNT_ADJ_U	0x50
+
+/* Timestamp command registers */
+#define PHY_REG_TX_TMR_CMD		0x40
+#define PHY_REG_RX_TMR_CMD		0x60
+
+/* Phy offset ready registers */
+#define PHY_REG_TX_OFFSET_READY		0x54
+#define PHY_REG_RX_OFFSET_READY		0x74
+
+/* Phy total offset registers */
+#define PHY_REG_TOTAL_TX_OFFSET_L	0x38
+#define PHY_REG_TOTAL_TX_OFFSET_U	0x3C
+#define PHY_REG_TOTAL_RX_OFFSET_L	0x58
+#define PHY_REG_TOTAL_RX_OFFSET_U	0x5C
+
+/* Timestamp capture registers */
+#define PHY_REG_TX_CAPTURE_L		0x78
+#define PHY_REG_TX_CAPTURE_U		0x7C
+#define PHY_REG_RX_CAPTURE_L		0x8C
+#define PHY_REG_RX_CAPTURE_U		0x90
+
+/* Memory status registers */
+#define PHY_REG_TX_MEMORY_STATUS_L	0x80
+#define PHY_REG_TX_MEMORY_STATUS_U	0x84
+
+/* Interrupt config register */
+#define PHY_REG_TS_INT_CONFIG		0x88
+
+/* XIF mode config register */
+#define PHY_MAC_XIF_MODE		0x24
+#define PHY_MAC_XIF_1STEP_ENA_M		ICE_M(0x1, 5)
+#define PHY_MAC_XIF_TS_BIN_MODE_M	ICE_M(0x1, 11)
+#define PHY_MAC_XIF_TS_SFD_ENA_M	ICE_M(0x1, 20)
+#define PHY_MAC_XIF_GMII_TS_SEL_M	ICE_M(0x1, 21)
+
+/* GPCS config register */
+#define PHY_GPCS_CONFIG_REG0		0x268
+#define PHY_GPCS_CONFIG_REG0_TX_THR_M	ICE_M(0xF, 24)
+#define PHY_GPCS_BITSLIP		0x5C
+
+#define PHY_TS_INT_CONFIG_THRESHOLD_M	ICE_M(0x3F, 0)
+#define PHY_TS_INT_CONFIG_ENA_M		BIT(6)
+
+/* 1-step PTP config */
+#define PHY_PTP_1STEP_CONFIG		0x270
+#define PHY_PTP_1STEP_T1S_UP64_M	ICE_M(0xF, 4)
+#define PHY_PTP_1STEP_T1S_DELTA_M	ICE_M(0xF, 8)
+#define PHY_PTP_1STEP_PEER_DELAY(_port)	(0x274 + 4 * (_port))
+#define PHY_PTP_1STEP_PD_ADD_PD_M	ICE_M(0x1, 0)
+#define PHY_PTP_1STEP_PD_DELAY_M	ICE_M(0x3fffffff, 1)
+#define PHY_PTP_1STEP_PD_DLY_V_M	ICE_M(0x1, 31)
+
+/* Macros to derive offsets for TimeStampLow and TimeStampHigh */
+#define PHY_TSTAMP_L(x) (((x) * 8) + 0)
+#define PHY_TSTAMP_U(x) (((x) * 8) + 4)
+
+#define PHY_REG_REVISION		0x85000
+
+#define PHY_REG_DESKEW_0		0x94
+#define PHY_REG_DESKEW_0_RLEVEL		GENMASK(6, 0)
+#define PHY_REG_DESKEW_0_RLEVEL_FRAC	GENMASK(9, 7)
+#define PHY_REG_DESKEW_0_RLEVEL_FRAC_W	3
+#define PHY_REG_DESKEW_0_VALID		GENMASK(10, 10)
+
+#define PHY_REG_GPCS_BITSLIP		0x5C
+#define PHY_REG_SD_BIT_SLIP(_port_offset)	(0x29C + 4 * (_port_offset))
+#define PHY_REVISION_ETH56G		0x10200
+#define PHY_VENDOR_TXLANE_THRESH	0x2000C
+
+#define PHY_MAC_TSU_CONFIG		0x40
+#define PHY_MAC_TSU_CFG_RX_MODE_M	ICE_M(0x7, 0)
+#define PHY_MAC_TSU_CFG_RX_MII_CW_DLY_M	ICE_M(0x7, 4)
+#define PHY_MAC_TSU_CFG_RX_MII_MK_DLY_M	ICE_M(0x7, 8)
+#define PHY_MAC_TSU_CFG_TX_MODE_M	ICE_M(0x7, 12)
+#define PHY_MAC_TSU_CFG_TX_MII_CW_DLY_M	ICE_M(0x1F, 16)
+#define PHY_MAC_TSU_CFG_TX_MII_MK_DLY_M	ICE_M(0x1F, 21)
+#define PHY_MAC_TSU_CFG_BLKS_PER_CLK_M	ICE_M(0x1, 28)
+#define PHY_MAC_RX_MODULO		0x44
+#define PHY_MAC_RX_OFFSET		0x48
+#define PHY_MAC_RX_OFFSET_M		ICE_M(0xFFFFFF, 0)
+#define PHY_MAC_TX_MODULO		0x4C
+#define PHY_MAC_BLOCKTIME		0x50
+#define PHY_MAC_MARKERTIME		0x54
+#define PHY_MAC_TX_OFFSET		0x58
+
+#define PHY_PTP_INT_STATUS		0x7FD140
+
 #endif /* _ICE_PTP_HW_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_sbq_cmd.h b/drivers/net/ethernet/intel/ice/ice_sbq_cmd.h
index ead75fe2bcdad..3b0054faf70c7 100644
--- a/drivers/net/ethernet/intel/ice/ice_sbq_cmd.h
+++ b/drivers/net/ethernet/intel/ice/ice_sbq_cmd.h
@@ -47,10 +47,12 @@ struct ice_sbq_evt_desc {
 };
 
 enum ice_sbq_msg_dev {
-	rmn_0	= 0x02,
-	rmn_1	= 0x03,
-	rmn_2	= 0x04,
-	cgu	= 0x06
+	eth56g_phy_0	= 0x02,
+	rmn_0		= 0x02,
+	rmn_1		= 0x03,
+	rmn_2		= 0x04,
+	cgu		= 0x06,
+	eth56g_phy_1	= 0x0D,
 };
 
 enum ice_sbq_msg_opcode {
diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h
index 2d2af80a65a9d..f039fc665455c 100644
--- a/drivers/net/ethernet/intel/ice/ice_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_type.h
@@ -322,7 +322,9 @@ enum ice_time_ref_freq {
 	ICE_TIME_REF_FREQ_156_250	= 4,
 	ICE_TIME_REF_FREQ_245_760	= 5,
 
-	NUM_ICE_TIME_REF_FREQ
+	NUM_ICE_TIME_REF_FREQ,
+
+	ICE_TIME_REF_FREQ_INVALID	= -1,
 };
 
 /* Clock source specification */
@@ -821,15 +823,29 @@ struct ice_mbx_data {
 #define ICE_PORTS_PER_QUAD	4
 #define ICE_GET_QUAD_NUM(port) ((port) / ICE_PORTS_PER_QUAD)
 
+struct ice_eth56g_params {
+	u8 num_phys;
+	u8 phy_addr[2];
+	bool onestep_ena;
+	bool sfd_ena;
+	u32 peer_delay;
+};
+
+union ice_phy_params {
+	struct ice_eth56g_params eth56g;
+};
+
 /* PHY model */
 enum ice_phy_model {
 	ICE_PHY_UNSUP = -1,
-	ICE_PHY_E810  = 1,
+	ICE_PHY_E810 = 1,
 	ICE_PHY_E82X,
+	ICE_PHY_ETH56G,
 };
 
 struct ice_ptp_hw {
 	enum ice_phy_model phy_model;
+	union ice_phy_params phy;
 	u8 num_lports;
 	u8 ports_per_phy;
 };
-- 
GitLab


From b390ecc2e375f8973c512a5041a69555069f502a Mon Sep 17 00:00:00 2001
From: Karol Kolacinski <karol.kolacinski@intel.com>
Date: Tue, 28 May 2024 16:03:58 -0700
Subject: [PATCH 681/950] ice: Change CGU regs struct to anonymous

Simplify the code by using anonymous struct in CGU registers instead of
naming each structure 'field'.

Suggested-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Arkadiusz Kubalewski <arkadiusz.kubalewski@intel.com>
Signed-off-by: Karol Kolacinski <karol.kolacinski@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20240528-next-2024-05-28-ptp-refactors-v1-8-c082739bb6f6@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/ice/ice_cgu_regs.h | 12 ++---
 drivers/net/ethernet/intel/ice/ice_ptp_hw.c   | 44 +++++++++----------
 2 files changed, 28 insertions(+), 28 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_cgu_regs.h b/drivers/net/ethernet/intel/ice/ice_cgu_regs.h
index 57abd52386d0d..36aeb10eefb73 100644
--- a/drivers/net/ethernet/intel/ice/ice_cgu_regs.h
+++ b/drivers/net/ethernet/intel/ice/ice_cgu_regs.h
@@ -23,7 +23,7 @@ union nac_cgu_dword9 {
 		u32 clk_synce0_amp : 2;
 		u32 one_pps_out_amp : 2;
 		u32 misc24 : 12;
-	} field;
+	};
 	u32 val;
 };
 
@@ -39,7 +39,7 @@ union nac_cgu_dword19 {
 		u32 japll_ndivratio : 4;
 		u32 japll_iref_ndivratio : 3;
 		u32 misc27 : 1;
-	} field;
+	};
 	u32 val;
 };
 
@@ -63,7 +63,7 @@ union nac_cgu_dword22 {
 		u32 fdpllclk_sel_div2 : 1;
 		u32 time1588clk_sel_div2 : 1;
 		u32 misc3 : 1;
-	} field;
+	};
 	u32 val;
 };
 
@@ -77,7 +77,7 @@ union nac_cgu_dword24 {
 		u32 ext_synce_sel : 1;
 		u32 ref1588_ck_div : 4;
 		u32 time_ref_sel : 1;
-	} field;
+	};
 	u32 val;
 };
 
@@ -92,7 +92,7 @@ union tspll_cntr_bist_settings {
 		u32 i_plllock_cnt_6_0 : 7;
 		u32 i_plllock_cnt_10_7 : 4;
 		u32 reserved200 : 4;
-	} field;
+	};
 	u32 val;
 };
 
@@ -109,7 +109,7 @@ union tspll_ro_bwm_lf {
 		u32 afcdone_cri : 1;
 		u32 feedfwrdgain_cal_cri_7_0 : 8;
 		u32 m2fbdivmod_cri_7_0 : 8;
-	} field;
+	};
 	u32 val;
 };
 
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
index 1b333b1c2738a..691ea20811e72 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
@@ -393,14 +393,14 @@ static int ice_cfg_cgu_pll_e82x(struct ice_hw *hw,
 
 	/* Log the current clock configuration */
 	ice_debug(hw, ICE_DBG_PTP, "Current CGU configuration -- %s, clk_src %s, clk_freq %s, PLL %s\n",
-		  dw24.field.ts_pll_enable ? "enabled" : "disabled",
-		  ice_clk_src_str(dw24.field.time_ref_sel),
-		  ice_clk_freq_str(dw9.field.time_ref_freq_sel),
-		  bwm_lf.field.plllock_true_lock_cri ? "locked" : "unlocked");
+		  dw24.ts_pll_enable ? "enabled" : "disabled",
+		  ice_clk_src_str(dw24.time_ref_sel),
+		  ice_clk_freq_str(dw9.time_ref_freq_sel),
+		  bwm_lf.plllock_true_lock_cri ? "locked" : "unlocked");
 
 	/* Disable the PLL before changing the clock source or frequency */
-	if (dw24.field.ts_pll_enable) {
-		dw24.field.ts_pll_enable = 0;
+	if (dw24.ts_pll_enable) {
+		dw24.ts_pll_enable = 0;
 
 		err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD24, dw24.val);
 		if (err)
@@ -408,7 +408,7 @@ static int ice_cfg_cgu_pll_e82x(struct ice_hw *hw,
 	}
 
 	/* Set the frequency */
-	dw9.field.time_ref_freq_sel = clk_freq;
+	dw9.time_ref_freq_sel = clk_freq;
 	err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD9, dw9.val);
 	if (err)
 		return err;
@@ -418,8 +418,8 @@ static int ice_cfg_cgu_pll_e82x(struct ice_hw *hw,
 	if (err)
 		return err;
 
-	dw19.field.tspll_fbdiv_intgr = e822_cgu_params[clk_freq].feedback_div;
-	dw19.field.tspll_ndivratio = 1;
+	dw19.tspll_fbdiv_intgr = e822_cgu_params[clk_freq].feedback_div;
+	dw19.tspll_ndivratio = 1;
 
 	err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD19, dw19.val);
 	if (err)
@@ -430,8 +430,8 @@ static int ice_cfg_cgu_pll_e82x(struct ice_hw *hw,
 	if (err)
 		return err;
 
-	dw22.field.time1588clk_div = e822_cgu_params[clk_freq].post_pll_div;
-	dw22.field.time1588clk_sel_div2 = 0;
+	dw22.time1588clk_div = e822_cgu_params[clk_freq].post_pll_div;
+	dw22.time1588clk_sel_div2 = 0;
 
 	err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD22, dw22.val);
 	if (err)
@@ -442,16 +442,16 @@ static int ice_cfg_cgu_pll_e82x(struct ice_hw *hw,
 	if (err)
 		return err;
 
-	dw24.field.ref1588_ck_div = e822_cgu_params[clk_freq].refclk_pre_div;
-	dw24.field.tspll_fbdiv_frac = e822_cgu_params[clk_freq].frac_n_div;
-	dw24.field.time_ref_sel = clk_src;
+	dw24.ref1588_ck_div = e822_cgu_params[clk_freq].refclk_pre_div;
+	dw24.tspll_fbdiv_frac = e822_cgu_params[clk_freq].frac_n_div;
+	dw24.time_ref_sel = clk_src;
 
 	err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD24, dw24.val);
 	if (err)
 		return err;
 
 	/* Finally, enable the PLL */
-	dw24.field.ts_pll_enable = 1;
+	dw24.ts_pll_enable = 1;
 
 	err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD24, dw24.val);
 	if (err)
@@ -464,17 +464,17 @@ static int ice_cfg_cgu_pll_e82x(struct ice_hw *hw,
 	if (err)
 		return err;
 
-	if (!bwm_lf.field.plllock_true_lock_cri) {
+	if (!bwm_lf.plllock_true_lock_cri) {
 		dev_warn(ice_hw_to_dev(hw), "CGU PLL failed to lock\n");
 		return -EBUSY;
 	}
 
 	/* Log the current clock configuration */
 	ice_debug(hw, ICE_DBG_PTP, "New CGU configuration -- %s, clk_src %s, clk_freq %s, PLL %s\n",
-		  dw24.field.ts_pll_enable ? "enabled" : "disabled",
-		  ice_clk_src_str(dw24.field.time_ref_sel),
-		  ice_clk_freq_str(dw9.field.time_ref_freq_sel),
-		  bwm_lf.field.plllock_true_lock_cri ? "locked" : "unlocked");
+		  dw24.ts_pll_enable ? "enabled" : "disabled",
+		  ice_clk_src_str(dw24.time_ref_sel),
+		  ice_clk_freq_str(dw9.time_ref_freq_sel),
+		  bwm_lf.plllock_true_lock_cri ? "locked" : "unlocked");
 
 	return 0;
 }
@@ -499,8 +499,8 @@ static int ice_init_cgu_e82x(struct ice_hw *hw)
 		return err;
 
 	/* Disable sticky lock detection so lock err reported is accurate */
-	cntr_bist.field.i_plllock_sel_0 = 0;
-	cntr_bist.field.i_plllock_sel_1 = 0;
+	cntr_bist.i_plllock_sel_0 = 0;
+	cntr_bist.i_plllock_sel_1 = 0;
 
 	err = ice_write_cgu_reg_e82x(hw, TSPLL_CNTR_BIST_SETTINGS,
 				     cntr_bist.val);
-- 
GitLab


From 713dcad2a8c74de23d593a73bec4c22365ebc83f Mon Sep 17 00:00:00 2001
From: Michal Michalik <michal.michalik@intel.com>
Date: Tue, 28 May 2024 16:03:59 -0700
Subject: [PATCH 682/950] ice: Add support for E825-C TS PLL handling

The CGU layout of E825-C is a little different than E822/E823. Add
support the new hardware adding relevant functions.

Signed-off-by: Michal Michalik <michal.michalik@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Arkadiusz Kubalewski <arkadiusz.kubalewski@intel.com>
Signed-off-by: Karol Kolacinski <karol.kolacinski@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20240528-next-2024-05-28-ptp-refactors-v1-9-c082739bb6f6@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/ice/ice_cgu_regs.h |  65 +++++
 drivers/net/ethernet/intel/ice/ice_common.c   |   9 +-
 .../net/ethernet/intel/ice/ice_ptp_consts.h   |  87 ++++++
 drivers/net/ethernet/intel/ice/ice_ptp_hw.c   | 261 +++++++++++++++++-
 drivers/net/ethernet/intel/ice/ice_ptp_hw.h   |  24 +-
 drivers/net/ethernet/intel/ice/ice_type.h     |   2 +-
 6 files changed, 429 insertions(+), 19 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_cgu_regs.h b/drivers/net/ethernet/intel/ice/ice_cgu_regs.h
index 36aeb10eefb73..10d9d74f35455 100644
--- a/drivers/net/ethernet/intel/ice/ice_cgu_regs.h
+++ b/drivers/net/ethernet/intel/ice/ice_cgu_regs.h
@@ -27,6 +27,17 @@ union nac_cgu_dword9 {
 	u32 val;
 };
 
+#define NAC_CGU_DWORD16_E825C 0x40
+union nac_cgu_dword16_e825c {
+	struct {
+		u32 synce_remndr : 6;
+		u32 synce_phlmt_en : 1;
+		u32 misc13 : 17;
+		u32 tspll_ck_refclkfreq : 8;
+	};
+	u32 val;
+};
+
 #define NAC_CGU_DWORD19 0x4c
 union nac_cgu_dword19 {
 	struct {
@@ -67,6 +78,22 @@ union nac_cgu_dword22 {
 	u32 val;
 };
 
+#define NAC_CGU_DWORD23_E825C 0x5C
+union nac_cgu_dword23_e825c {
+	struct {
+		u32 cgupll_fbdiv_intgr : 10;
+		u32 ux56pll_fbdiv_intgr : 10;
+		u32 misc20 : 4;
+		u32 ts_pll_enable : 1;
+		u32 time_sync_tspll_align_sel : 1;
+		u32 ext_synce_sel : 1;
+		u32 ref1588_ck_div : 4;
+		u32 time_ref_sel : 1;
+
+	};
+	u32 val;
+};
+
 #define NAC_CGU_DWORD24 0x60
 union nac_cgu_dword24 {
 	struct {
@@ -113,4 +140,42 @@ union tspll_ro_bwm_lf {
 	u32 val;
 };
 
+#define TSPLL_RO_LOCK_E825C 0x3f0
+union tspll_ro_lock_e825c {
+	struct {
+		u32 bw_freqov_high_cri_7_0 : 8;
+		u32 bw_freqov_high_cri_9_8 : 2;
+		u32 reserved455 : 1;
+		u32 plllock_gain_tran_cri : 1;
+		u32 plllock_true_lock_cri : 1;
+		u32 pllunlock_flag_cri : 1;
+		u32 afcerr_cri : 1;
+		u32 afcdone_cri : 1;
+		u32 feedfwrdgain_cal_cri_7_0 : 8;
+		u32 reserved462 : 8;
+	};
+	u32 val;
+};
+
+#define TSPLL_BW_TDC_E825C 0x31c
+union tspll_bw_tdc_e825c {
+	struct {
+		u32 i_tdc_offset_lock_1_0 : 2;
+		u32 i_bbthresh1_2_0 : 3;
+		u32 i_bbthresh2_2_0 : 3;
+		u32 i_tdcsel_1_0 : 2;
+		u32 i_tdcovccorr_en_h : 1;
+		u32 i_divretimeren : 1;
+		u32 i_bw_ampmeas_window : 1;
+		u32 i_bw_lowerbound_2_0 : 3;
+		u32 i_bw_upperbound_2_0 : 3;
+		u32 i_bw_mode_1_0 : 2;
+		u32 i_ft_mode_sel_2_0 : 3;
+		u32 i_bwphase_4_0 : 5;
+		u32 i_plllock_sel_1_0 : 2;
+		u32 i_afc_divratio : 1;
+	};
+	u32 val;
+};
+
 #endif /* _ICE_CGU_REGS_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index c37042d9bdd9b..4dbd3fca55273 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -2314,8 +2314,13 @@ ice_parse_1588_func_caps(struct ice_hw *hw, struct ice_hw_func_caps *func_p,
 	info->tmr_index_owned = ((number & ICE_TS_TMR_IDX_OWND_M) != 0);
 	info->tmr_index_assoc = ((number & ICE_TS_TMR_IDX_ASSOC_M) != 0);
 
-	info->clk_freq = FIELD_GET(ICE_TS_CLK_FREQ_M, number);
-	info->clk_src = ((number & ICE_TS_CLK_SRC_M) != 0);
+	if (!ice_is_e825c(hw)) {
+		info->clk_freq = FIELD_GET(ICE_TS_CLK_FREQ_M, number);
+		info->clk_src = ((number & ICE_TS_CLK_SRC_M) != 0);
+	} else {
+		info->clk_freq = ICE_TIME_REF_FREQ_156_250;
+		info->clk_src = ICE_CLK_SRC_TCXO;
+	}
 
 	if (info->clk_freq < NUM_ICE_TIME_REF_FREQ) {
 		info->time_ref = (enum ice_time_ref_freq)info->clk_freq;
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_consts.h b/drivers/net/ethernet/intel/ice/ice_ptp_consts.h
index ef180936f60c7..e6980b94a6c1d 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_consts.h
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_consts.h
@@ -470,6 +470,93 @@ const struct ice_cgu_pll_params_e82x e822_cgu_params[NUM_ICE_TIME_REF_FREQ] = {
 	},
 };
 
+const
+struct ice_cgu_pll_params_e825c e825c_cgu_params[NUM_ICE_TIME_REF_FREQ] = {
+	/* ICE_TIME_REF_FREQ_25_000 -> 25 MHz */
+	{
+		/* tspll_ck_refclkfreq */
+		0x19,
+		/* tspll_ndivratio */
+		1,
+		/* tspll_fbdiv_intgr */
+		320,
+		/* tspll_fbdiv_frac */
+		0,
+		/* ref1588_ck_div */
+		0,
+	},
+
+	/* ICE_TIME_REF_FREQ_122_880 -> 122.88 MHz */
+	{
+		/* tspll_ck_refclkfreq */
+		0x29,
+		/* tspll_ndivratio */
+		3,
+		/* tspll_fbdiv_intgr */
+		195,
+		/* tspll_fbdiv_frac */
+		1342177280UL,
+		/* ref1588_ck_div */
+		0,
+	},
+
+	/* ICE_TIME_REF_FREQ_125_000 -> 125 MHz */
+	{
+		/* tspll_ck_refclkfreq */
+		0x3E,
+		/* tspll_ndivratio */
+		2,
+		/* tspll_fbdiv_intgr */
+		128,
+		/* tspll_fbdiv_frac */
+		0,
+		/* ref1588_ck_div */
+		0,
+	},
+
+	/* ICE_TIME_REF_FREQ_153_600 -> 153.6 MHz */
+	{
+		/* tspll_ck_refclkfreq */
+		0x33,
+		/* tspll_ndivratio */
+		3,
+		/* tspll_fbdiv_intgr */
+		156,
+		/* tspll_fbdiv_frac */
+		1073741824UL,
+		/* ref1588_ck_div */
+		0,
+	},
+
+	/* ICE_TIME_REF_FREQ_156_250 -> 156.25 MHz */
+	{
+		/* tspll_ck_refclkfreq */
+		0x1F,
+		/* tspll_ndivratio */
+		5,
+		/* tspll_fbdiv_intgr */
+		256,
+		/* tspll_fbdiv_frac */
+		0,
+		/* ref1588_ck_div */
+		0,
+	},
+
+	/* ICE_TIME_REF_FREQ_245_760 -> 245.76 MHz */
+	{
+		/* tspll_ck_refclkfreq */
+		0x52,
+		/* tspll_ndivratio */
+		3,
+		/* tspll_fbdiv_intgr */
+		97,
+		/* tspll_fbdiv_frac */
+		2818572288UL,
+		/* ref1588_ck_div */
+		0,
+	},
+};
+
 /* struct ice_vernier_info_e82x
  *
  * E822 hardware calibrates the delay of the timestamp indication from the
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
index 691ea20811e72..2c41921f76e80 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
@@ -325,8 +325,8 @@ static const char *ice_clk_freq_str(enum ice_time_ref_freq clk_freq)
 static const char *ice_clk_src_str(enum ice_clk_src clk_src)
 {
 	switch (clk_src) {
-	case ICE_CLK_SRC_TCX0:
-		return "TCX0";
+	case ICE_CLK_SRC_TCXO:
+		return "TCXO";
 	case ICE_CLK_SRC_TIME_REF:
 		return "TIME_REF";
 	default:
@@ -338,7 +338,7 @@ static const char *ice_clk_src_str(enum ice_clk_src clk_src)
  * ice_cfg_cgu_pll_e82x - Configure the Clock Generation Unit
  * @hw: pointer to the HW struct
  * @clk_freq: Clock frequency to program
- * @clk_src: Clock source to select (TIME_REF, or TCX0)
+ * @clk_src: Clock source to select (TIME_REF, or TCXO)
  *
  * Configure the Clock Generation Unit with the desired clock frequency and
  * time reference, enabling the PLL which drives the PTP hardware clock.
@@ -372,10 +372,10 @@ static int ice_cfg_cgu_pll_e82x(struct ice_hw *hw,
 		return -EINVAL;
 	}
 
-	if (clk_src == ICE_CLK_SRC_TCX0 &&
+	if (clk_src == ICE_CLK_SRC_TCXO &&
 	    clk_freq != ICE_TIME_REF_FREQ_25_000) {
 		dev_warn(ice_hw_to_dev(hw),
-			 "TCX0 only supports 25 MHz frequency\n");
+			 "TCXO only supports 25 MHz frequency\n");
 		return -EINVAL;
 	}
 
@@ -480,16 +480,198 @@ static int ice_cfg_cgu_pll_e82x(struct ice_hw *hw,
 }
 
 /**
- * ice_init_cgu_e82x - Initialize CGU with settings from firmware
- * @hw: pointer to the HW structure
+ * ice_cfg_cgu_pll_e825c - Configure the Clock Generation Unit for E825-C
+ * @hw: pointer to the HW struct
+ * @clk_freq: Clock frequency to program
+ * @clk_src: Clock source to select (TIME_REF, or TCXO)
  *
- * Initialize the Clock Generation Unit of the E822 device.
+ * Configure the Clock Generation Unit with the desired clock frequency and
+ * time reference, enabling the PLL which drives the PTP hardware clock.
  *
- * Return: 0 on success, other error codes when failed to read/write/cfg CGU
+ * Return:
+ * * %0       - success
+ * * %-EINVAL - input parameters are incorrect
+ * * %-EBUSY  - failed to lock TS PLL
+ * * %other   - CGU read/write failure
  */
-static int ice_init_cgu_e82x(struct ice_hw *hw)
+static int ice_cfg_cgu_pll_e825c(struct ice_hw *hw,
+				 enum ice_time_ref_freq clk_freq,
+				 enum ice_clk_src clk_src)
+{
+	union tspll_ro_lock_e825c ro_lock;
+	union nac_cgu_dword16_e825c dw16;
+	union nac_cgu_dword23_e825c dw23;
+	union nac_cgu_dword19 dw19;
+	union nac_cgu_dword22 dw22;
+	union nac_cgu_dword24 dw24;
+	union nac_cgu_dword9 dw9;
+	int err;
+
+	if (clk_freq >= NUM_ICE_TIME_REF_FREQ) {
+		dev_warn(ice_hw_to_dev(hw), "Invalid TIME_REF frequency %u\n",
+			 clk_freq);
+		return -EINVAL;
+	}
+
+	if (clk_src >= NUM_ICE_CLK_SRC) {
+		dev_warn(ice_hw_to_dev(hw), "Invalid clock source %u\n",
+			 clk_src);
+		return -EINVAL;
+	}
+
+	if (clk_src == ICE_CLK_SRC_TCXO &&
+	    clk_freq != ICE_TIME_REF_FREQ_156_250) {
+		dev_warn(ice_hw_to_dev(hw),
+			 "TCXO only supports 156.25 MHz frequency\n");
+		return -EINVAL;
+	}
+
+	err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD9, &dw9.val);
+	if (err)
+		return err;
+
+	err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD24, &dw24.val);
+	if (err)
+		return err;
+
+	err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD16_E825C, &dw16.val);
+	if (err)
+		return err;
+
+	err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD23_E825C, &dw23.val);
+	if (err)
+		return err;
+
+	err = ice_read_cgu_reg_e82x(hw, TSPLL_RO_LOCK_E825C, &ro_lock.val);
+	if (err)
+		return err;
+
+	/* Log the current clock configuration */
+	ice_debug(hw, ICE_DBG_PTP, "Current CGU configuration -- %s, clk_src %s, clk_freq %s, PLL %s\n",
+		  dw24.ts_pll_enable ? "enabled" : "disabled",
+		  ice_clk_src_str(dw23.time_ref_sel),
+		  ice_clk_freq_str(dw9.time_ref_freq_sel),
+		  ro_lock.plllock_true_lock_cri ? "locked" : "unlocked");
+
+	/* Disable the PLL before changing the clock source or frequency */
+	if (dw23.ts_pll_enable) {
+		dw23.ts_pll_enable = 0;
+
+		err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD23_E825C,
+					     dw23.val);
+		if (err)
+			return err;
+	}
+
+	/* Set the frequency */
+	dw9.time_ref_freq_sel = clk_freq;
+
+	/* Enable the correct receiver */
+	if (clk_src == ICE_CLK_SRC_TCXO) {
+		dw9.time_ref_en = 0;
+		dw9.clk_eref0_en = 1;
+	} else {
+		dw9.time_ref_en = 1;
+		dw9.clk_eref0_en = 0;
+	}
+	err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD9, dw9.val);
+	if (err)
+		return err;
+
+	/* Choose the referenced frequency */
+	dw16.tspll_ck_refclkfreq =
+	e825c_cgu_params[clk_freq].tspll_ck_refclkfreq;
+	err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD16_E825C, dw16.val);
+	if (err)
+		return err;
+
+	/* Configure the TS PLL feedback divisor */
+	err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD19, &dw19.val);
+	if (err)
+		return err;
+
+	dw19.tspll_fbdiv_intgr =
+		e825c_cgu_params[clk_freq].tspll_fbdiv_intgr;
+	dw19.tspll_ndivratio =
+		e825c_cgu_params[clk_freq].tspll_ndivratio;
+
+	err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD19, dw19.val);
+	if (err)
+		return err;
+
+	/* Configure the TS PLL post divisor */
+	err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD22, &dw22.val);
+	if (err)
+		return err;
+
+	/* These two are constant for E825C */
+	dw22.time1588clk_div = 5;
+	dw22.time1588clk_sel_div2 = 0;
+
+	err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD22, dw22.val);
+	if (err)
+		return err;
+
+	/* Configure the TS PLL pre divisor and clock source */
+	err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD23_E825C, &dw23.val);
+	if (err)
+		return err;
+
+	dw23.ref1588_ck_div =
+		e825c_cgu_params[clk_freq].ref1588_ck_div;
+	dw23.time_ref_sel = clk_src;
+
+	err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD23_E825C, dw23.val);
+	if (err)
+		return err;
+
+	dw24.tspll_fbdiv_frac =
+		e825c_cgu_params[clk_freq].tspll_fbdiv_frac;
+
+	err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD24, dw24.val);
+	if (err)
+		return err;
+
+	/* Finally, enable the PLL */
+	dw23.ts_pll_enable = 1;
+
+	err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD23_E825C, dw23.val);
+	if (err)
+		return err;
+
+	/* Wait to verify if the PLL locks */
+	usleep_range(1000, 5000);
+
+	err = ice_read_cgu_reg_e82x(hw, TSPLL_RO_LOCK_E825C, &ro_lock.val);
+	if (err)
+		return err;
+
+	if (!ro_lock.plllock_true_lock_cri) {
+		dev_warn(ice_hw_to_dev(hw), "CGU PLL failed to lock\n");
+		return -EBUSY;
+	}
+
+	/* Log the current clock configuration */
+	ice_debug(hw, ICE_DBG_PTP, "New CGU configuration -- %s, clk_src %s, clk_freq %s, PLL %s\n",
+		  dw24.ts_pll_enable ? "enabled" : "disabled",
+		  ice_clk_src_str(dw23.time_ref_sel),
+		  ice_clk_freq_str(dw9.time_ref_freq_sel),
+		  ro_lock.plllock_true_lock_cri ? "locked" : "unlocked");
+
+	return 0;
+}
+
+/**
+ * ice_cfg_cgu_pll_dis_sticky_bits_e82x - disable TS PLL sticky bits
+ * @hw: pointer to the HW struct
+ *
+ * Configure the Clock Generation Unit TS PLL sticky bits so they don't latch on
+ * losing TS PLL lock, but always show current state.
+ *
+ * Return: 0 on success, other error codes when failed to read/write CGU
+ */
+static int ice_cfg_cgu_pll_dis_sticky_bits_e82x(struct ice_hw *hw)
 {
-	struct ice_ts_func_info *ts_info = &hw->func_caps.ts_func_info;
 	union tspll_cntr_bist_settings cntr_bist;
 	int err;
 
@@ -502,16 +684,65 @@ static int ice_init_cgu_e82x(struct ice_hw *hw)
 	cntr_bist.i_plllock_sel_0 = 0;
 	cntr_bist.i_plllock_sel_1 = 0;
 
-	err = ice_write_cgu_reg_e82x(hw, TSPLL_CNTR_BIST_SETTINGS,
-				     cntr_bist.val);
+	return ice_write_cgu_reg_e82x(hw, TSPLL_CNTR_BIST_SETTINGS,
+				      cntr_bist.val);
+}
+
+/**
+ * ice_cfg_cgu_pll_dis_sticky_bits_e825c - disable TS PLL sticky bits for E825-C
+ * @hw: pointer to the HW struct
+ *
+ * Configure the Clock Generation Unit TS PLL sticky bits so they don't latch on
+ * losing TS PLL lock, but always show current state.
+ *
+ * Return: 0 on success, other error codes when failed to read/write CGU
+ */
+static int ice_cfg_cgu_pll_dis_sticky_bits_e825c(struct ice_hw *hw)
+{
+	union tspll_bw_tdc_e825c bw_tdc;
+	int err;
+
+	err = ice_read_cgu_reg_e82x(hw, TSPLL_BW_TDC_E825C, &bw_tdc.val);
+	if (err)
+		return err;
+
+	bw_tdc.i_plllock_sel_1_0 = 0;
+
+	return ice_write_cgu_reg_e82x(hw, TSPLL_BW_TDC_E825C, bw_tdc.val);
+}
+
+/**
+ * ice_init_cgu_e82x - Initialize CGU with settings from firmware
+ * @hw: pointer to the HW structure
+ *
+ * Initialize the Clock Generation Unit of the E822 device.
+ *
+ * Return: 0 on success, other error codes when failed to read/write/cfg CGU
+ */
+static int ice_init_cgu_e82x(struct ice_hw *hw)
+{
+	struct ice_ts_func_info *ts_info = &hw->func_caps.ts_func_info;
+	int err;
+
+	/* Disable sticky lock detection so lock err reported is accurate */
+	if (ice_is_e825c(hw))
+		err = ice_cfg_cgu_pll_dis_sticky_bits_e825c(hw);
+	else
+		err = ice_cfg_cgu_pll_dis_sticky_bits_e82x(hw);
 	if (err)
 		return err;
 
 	/* Configure the CGU PLL using the parameters from the function
 	 * capabilities.
 	 */
-	return ice_cfg_cgu_pll_e82x(hw, ts_info->time_ref,
-				   (enum ice_clk_src)ts_info->clk_src);
+	if (ice_is_e825c(hw))
+		err = ice_cfg_cgu_pll_e825c(hw, ts_info->time_ref,
+					    (enum ice_clk_src)ts_info->clk_src);
+	else
+		err = ice_cfg_cgu_pll_e82x(hw, ts_info->time_ref,
+					   (enum ice_clk_src)ts_info->clk_src);
+
+	return err;
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
index 184573509e629..0852a34ade918 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
@@ -197,7 +197,7 @@ extern
 const struct ice_eth56g_mac_reg_cfg eth56g_mac_cfg[NUM_ICE_ETH56G_LNK_SPD];
 
 /**
- * struct ice_cgu_pll_params_e82x
+ * struct ice_cgu_pll_params_e82x - E82X CGU parameters
  * @refclk_pre_div: Reference clock pre-divisor
  * @feedback_div: Feedback divisor
  * @frac_n_div: Fractional divisor
@@ -287,6 +287,28 @@ struct ice_cgu_pin_desc {
 extern const struct
 ice_cgu_pll_params_e82x e822_cgu_params[NUM_ICE_TIME_REF_FREQ];
 
+/**
+ * struct ice_cgu_pll_params_e825c - E825C CGU parameters
+ * @tspll_ck_refclkfreq: tspll_ck_refclkfreq selection
+ * @tspll_ndivratio: ndiv ratio that goes directly to the pll
+ * @tspll_fbdiv_intgr: TS PLL integer feedback divide
+ * @tspll_fbdiv_frac:  TS PLL fractional feedback divide
+ * @ref1588_ck_div: clock divider for tspll ref
+ *
+ * Clock Generation Unit parameters used to program the PLL based on the
+ * selected TIME_REF/TCXO frequency.
+ */
+struct ice_cgu_pll_params_e825c {
+	u32 tspll_ck_refclkfreq;
+	u32 tspll_ndivratio;
+	u32 tspll_fbdiv_intgr;
+	u32 tspll_fbdiv_frac;
+	u32 ref1588_ck_div;
+};
+
+extern const struct
+ice_cgu_pll_params_e825c e825c_cgu_params[NUM_ICE_TIME_REF_FREQ];
+
 #define E810C_QSFP_C827_0_HANDLE 2
 #define E810C_QSFP_C827_1_HANDLE 3
 
diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h
index f039fc665455c..39d8fc08d651d 100644
--- a/drivers/net/ethernet/intel/ice/ice_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_type.h
@@ -329,7 +329,7 @@ enum ice_time_ref_freq {
 
 /* Clock source specification */
 enum ice_clk_src {
-	ICE_CLK_SRC_TCX0	= 0, /* Temperature compensated oscillator  */
+	ICE_CLK_SRC_TCXO	= 0, /* Temperature compensated oscillator */
 	ICE_CLK_SRC_TIME_REF	= 1, /* Use TIME_REF reference clock */
 
 	NUM_ICE_CLK_SRC
-- 
GitLab


From 5f847eede63889cbada9a23ea7c8f68659e3e918 Mon Sep 17 00:00:00 2001
From: Grzegorz Nitka <grzegorz.nitka@intel.com>
Date: Tue, 28 May 2024 16:04:00 -0700
Subject: [PATCH 683/950] ice: Add NAC Topology device capability parser

Add new device capability ICE_AQC_CAPS_NAC_TOPOLOGY which allows to
determine the mode of operation (1 or 2 NAC).
Define a new structure to store data from new capability and
corresponding parser code.

Co-developed-by: Prathisna Padmasanan <prathisna.padmasanan@intel.com>
Signed-off-by: Prathisna Padmasanan <prathisna.padmasanan@intel.com>
Signed-off-by: Grzegorz Nitka <grzegorz.nitka@intel.com>
Reviewed-by: Pawel Kaminski <pawel.kaminski@intel.com>
Reviewed-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Arkadiusz Kubalewski <arkadiusz.kubalewski@intel.com>
Signed-off-by: Karol Kolacinski <karol.kolacinski@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20240528-next-2024-05-28-ptp-refactors-v1-10-c082739bb6f6@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/intel/ice/ice_adminq_cmd.h   |  1 +
 drivers/net/ethernet/intel/ice/ice_common.c   | 31 +++++++++++++++++++
 drivers/net/ethernet/intel/ice/ice_type.h     | 10 ++++++
 3 files changed, 42 insertions(+)

diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
index e76c388b99055..621a2ca7093eb 100644
--- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
@@ -122,6 +122,7 @@ struct ice_aqc_list_caps_elem {
 #define ICE_AQC_CAPS_POST_UPDATE_RESET_RESTRICT		0x0077
 #define ICE_AQC_CAPS_NVM_MGMT				0x0080
 #define ICE_AQC_CAPS_TX_SCHED_TOPO_COMP_MODE		0x0085
+#define ICE_AQC_CAPS_NAC_TOPOLOGY			0x0087
 #define ICE_AQC_CAPS_FW_LAG_SUPPORT			0x0092
 #define ICE_AQC_BIT_ROCEV2_LAG				0x01
 #define ICE_AQC_BIT_SRIOV_LAG				0x02
diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index 4dbd3fca55273..9ae61cd8923e3 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -2593,6 +2593,34 @@ ice_parse_sensor_reading_cap(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p,
 		  dev_p->supported_sensors);
 }
 
+/**
+ * ice_parse_nac_topo_dev_caps - Parse ICE_AQC_CAPS_NAC_TOPOLOGY cap
+ * @hw: pointer to the HW struct
+ * @dev_p: pointer to device capabilities structure
+ * @cap: capability element to parse
+ *
+ * Parse ICE_AQC_CAPS_NAC_TOPOLOGY for device capabilities.
+ */
+static void ice_parse_nac_topo_dev_caps(struct ice_hw *hw,
+					struct ice_hw_dev_caps *dev_p,
+					struct ice_aqc_list_caps_elem *cap)
+{
+	dev_p->nac_topo.mode = le32_to_cpu(cap->number);
+	dev_p->nac_topo.id = le32_to_cpu(cap->phys_id) & ICE_NAC_TOPO_ID_M;
+
+	dev_info(ice_hw_to_dev(hw),
+		 "PF is configured in %s mode with IP instance ID %d\n",
+		 (dev_p->nac_topo.mode & ICE_NAC_TOPO_PRIMARY_M) ?
+		 "primary" : "secondary", dev_p->nac_topo.id);
+
+	ice_debug(hw, ICE_DBG_INIT, "dev caps: nac topology is_primary = %d\n",
+		  !!(dev_p->nac_topo.mode & ICE_NAC_TOPO_PRIMARY_M));
+	ice_debug(hw, ICE_DBG_INIT, "dev caps: nac topology is_dual = %d\n",
+		  !!(dev_p->nac_topo.mode & ICE_NAC_TOPO_DUAL_M));
+	ice_debug(hw, ICE_DBG_INIT, "dev caps: nac topology id = %d\n",
+		  dev_p->nac_topo.id);
+}
+
 /**
  * ice_parse_dev_caps - Parse device capabilities
  * @hw: pointer to the HW struct
@@ -2644,6 +2672,9 @@ ice_parse_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p,
 		case ICE_AQC_CAPS_SENSOR_READING:
 			ice_parse_sensor_reading_cap(hw, dev_p, &cap_resp[i]);
 			break;
+		case ICE_AQC_CAPS_NAC_TOPOLOGY:
+			ice_parse_nac_topo_dev_caps(hw, dev_p, &cap_resp[i]);
+			break;
 		default:
 			/* Don't list common capabilities as unknown */
 			if (!found)
diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h
index 39d8fc08d651d..841860784e3ce 100644
--- a/drivers/net/ethernet/intel/ice/ice_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_type.h
@@ -374,6 +374,15 @@ struct ice_ts_dev_info {
 	u8 ts_ll_int_read;
 };
 
+#define ICE_NAC_TOPO_PRIMARY_M	BIT(0)
+#define ICE_NAC_TOPO_DUAL_M	BIT(1)
+#define ICE_NAC_TOPO_ID_M	GENMASK(0xF, 0)
+
+struct ice_nac_topology {
+	u32 mode;
+	u8 id;
+};
+
 /* Function specific capabilities */
 struct ice_hw_func_caps {
 	struct ice_hw_common_caps common_cap;
@@ -395,6 +404,7 @@ struct ice_hw_dev_caps {
 	u32 num_flow_director_fltr;	/* Number of FD filters available */
 	struct ice_ts_dev_info ts_dev_info;
 	u32 num_funcs;
+	struct ice_nac_topology nac_topo;
 	/* bitmap of supported sensors
 	 * bit 0 - internal temperature sensor
 	 * bit 31:1 - Reserved
-- 
GitLab


From 4409ea1726cb9ce2769808873f8fbe33378c201b Mon Sep 17 00:00:00 2001
From: Grzegorz Nitka <grzegorz.nitka@intel.com>
Date: Tue, 28 May 2024 16:04:01 -0700
Subject: [PATCH 684/950] ice: Adjust PTP init for 2x50G E825C devices

>From FW/HW perspective, 2 port topology in E825C devices requires
merging of 2 port mapping internally and breakout mapping externally.
As a consequence, it requires different port numbering from PTP code
perspective.
For that topology, pf_id can not be used to index PTP ports. Even if
the 2nd port is identified as port with pf_id = 1, all PHY operations
need to be performed as it was port 2. Thus, special mapping is needed
for the 2nd port.
This change adds detection of 2x50G topology and applies 'custom'
mapping on the 2nd port.

Signed-off-by: Grzegorz Nitka <grzegorz.nitka@intel.com>
Reviewed-by: Arkadiusz Kubalewski <arkadiusz.kubalewski@intel.com>
Signed-off-by: Karol Kolacinski <karol.kolacinski@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20240528-next-2024-05-28-ptp-refactors-v1-11-c082739bb6f6@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/intel/ice/ice_hw_autogen.h   |  4 ++++
 drivers/net/ethernet/intel/ice/ice_ptp.c      |  5 +++++
 drivers/net/ethernet/intel/ice/ice_ptp_hw.c   | 22 +++++++++++++++++++
 drivers/net/ethernet/intel/ice/ice_type.h     |  9 ++++++++
 4 files changed, 40 insertions(+)

diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
index cfac1d432c155..91cbae1eec89a 100644
--- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
+++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
@@ -157,6 +157,8 @@
 #define GLGEN_RTRIG_CORER_M			BIT(0)
 #define GLGEN_RTRIG_GLOBR_M			BIT(1)
 #define GLGEN_STAT				0x000B612C
+#define GLGEN_SWITCH_MODE_CONFIG		0x000B81E0
+#define GLGEN_SWITCH_MODE_CONFIG_25X4_QUAD_M	BIT(2)
 #define GLGEN_VFLRSTAT(_i)			(0x00093A04 + ((_i) * 4))
 #define PFGEN_CTRL				0x00091000
 #define PFGEN_CTRL_PFSWR_M			BIT(0)
@@ -177,6 +179,8 @@
 #define GLINT_CTL_ITR_GRAN_50_M			ICE_M(0xF, 24)
 #define GLINT_CTL_ITR_GRAN_25_S			28
 #define GLINT_CTL_ITR_GRAN_25_M			ICE_M(0xF, 28)
+#define GLGEN_MAC_LINK_TOPO			0x000B81DC
+#define GLGEN_MAC_LINK_TOPO_LINK_TOPO_M		GENMASK(1, 0)
 #define GLINT_DYN_CTL(_INT)			(0x00160000 + ((_INT) * 4))
 #define GLINT_DYN_CTL_INTENA_M			BIT(0)
 #define GLINT_DYN_CTL_CLEARPBA_M		BIT(1)
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c
index 3af0f4a2c3be8..adbb9cffe20c2 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.c
@@ -1469,6 +1469,8 @@ void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup)
 		return;
 
 	ptp_port = &pf->ptp.port;
+	if (ice_is_e825c(hw) && hw->ptp.is_2x50g_muxed_topo)
+		port *= 2;
 	if (WARN_ON_ONCE(ptp_port->port_num != port))
 		return;
 
@@ -3282,6 +3284,9 @@ void ice_ptp_init(struct ice_pf *pf)
 	}
 
 	ptp->port.port_num = hw->pf_id;
+	if (ice_is_e825c(hw) && hw->ptp.is_2x50g_muxed_topo)
+		ptp->port.port_num = hw->pf_id * 2;
+
 	err = ice_ptp_init_port(pf, &ptp->port);
 	if (err)
 		goto err;
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
index 2c41921f76e80..1e9a4ccd0ea27 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
@@ -2644,6 +2644,26 @@ static int ice_get_phy_tx_tstamp_ready_eth56g(struct ice_hw *hw, u8 port,
 	return 0;
 }
 
+/**
+ * ice_is_muxed_topo - detect breakout 2x50G topology for E825C
+ * @hw: pointer to the HW struct
+ *
+ * Return: true if it's 2x50 breakout topology, false otherwise
+ */
+static bool ice_is_muxed_topo(struct ice_hw *hw)
+{
+	u8 link_topo;
+	bool mux;
+	u32 val;
+
+	val = rd32(hw, GLGEN_SWITCH_MODE_CONFIG);
+	mux = FIELD_GET(GLGEN_SWITCH_MODE_CONFIG_25X4_QUAD_M, val);
+	val = rd32(hw, GLGEN_MAC_LINK_TOPO);
+	link_topo = FIELD_GET(GLGEN_MAC_LINK_TOPO_LINK_TOPO_M, val);
+
+	return (mux && link_topo == ICE_LINK_TOPO_UP_TO_2_LINKS);
+}
+
 /**
  * ice_ptp_init_phy_e825c - initialize PHY parameters
  * @hw: pointer to the HW struct
@@ -2676,6 +2696,8 @@ static void ice_ptp_init_phy_e825c(struct ice_hw *hw)
 			return;
 		}
 	}
+
+	ptp->is_2x50g_muxed_topo = ice_is_muxed_topo(hw);
 }
 
 /* E822 family functions
diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h
index 841860784e3ce..5f0da6850b03b 100644
--- a/drivers/net/ethernet/intel/ice/ice_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_type.h
@@ -853,11 +853,20 @@ enum ice_phy_model {
 	ICE_PHY_ETH56G,
 };
 
+/* Global Link Topology */
+enum ice_global_link_topo {
+	ICE_LINK_TOPO_UP_TO_2_LINKS,
+	ICE_LINK_TOPO_UP_TO_4_LINKS,
+	ICE_LINK_TOPO_UP_TO_8_LINKS,
+	ICE_LINK_TOPO_RESERVED,
+};
+
 struct ice_ptp_hw {
 	enum ice_phy_model phy_model;
 	union ice_phy_params phy;
 	u8 num_lports;
 	u8 ports_per_phy;
+	bool is_2x50g_muxed_topo;
 };
 
 /* Port hardware description */
-- 
GitLab


From 8105378c0c02309221b63d15cfe8fe92e7fe1434 Mon Sep 17 00:00:00 2001
From: Jason Xing <kernelxing@tencent.com>
Date: Thu, 30 May 2024 11:27:17 +0800
Subject: [PATCH 685/950] net: rps: fix error when CONFIG_RFS_ACCEL is off

John Sperbeck reported that if we turn off CONFIG_RFS_ACCEL, the 'head'
is not defined, which will trigger compile error. So I move the 'head'
out of the CONFIG_RFS_ACCEL scope.

Fixes: 84b6823cd96b ("net: rps: protect last_qtail with rps_input_queue_tail_save() helper")
Reported-by: John Sperbeck <jsperbeck@google.com>
Closes: https://lore.kernel.org/all/20240529203421.2432481-1-jsperbeck@google.com/
Signed-off-by: Jason Xing <kernelxing@tencent.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20240530032717.57787-1-kerneljasonxing@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/dev.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index e1bb6d7856d92..4d4de9008f6f3 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4516,12 +4516,13 @@ set_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 	    struct rps_dev_flow *rflow, u16 next_cpu)
 {
 	if (next_cpu < nr_cpu_ids) {
+		u32 head;
 #ifdef CONFIG_RFS_ACCEL
 		struct netdev_rx_queue *rxqueue;
 		struct rps_dev_flow_table *flow_table;
 		struct rps_dev_flow *old_rflow;
-		u32 flow_id, head;
 		u16 rxq_index;
+		u32 flow_id;
 		int rc;
 
 		/* Should we steer this flow to a different hardware queue? */
-- 
GitLab


From 165f87691a898aea113923224c269bae14749ebc Mon Sep 17 00:00:00 2001
From: Vadim Fedorenko <vadfed@meta.com>
Date: Thu, 30 May 2024 13:47:51 -0700
Subject: [PATCH 686/950] bnxt_en: add timestamping statistics support

The ethtool_ts_stats structure was introduced earlier this year. Now
it's time to support this group of counters in more drivers.
This patch adds support to bnxt driver.

Signed-off-by: Vadim Fedorenko <vadfed@meta.com>
Reviewed-by: Michael Chan <michael.chan@broadcom.com>
Link: https://lore.kernel.org/r/20240530204751.99636-1-vadfed@meta.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c      | 18 +++++++++++++-----
 .../net/ethernet/broadcom/bnxt/bnxt_ethtool.c  | 14 ++++++++++++++
 drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c  |  8 ++++++++
 drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h  |  8 ++++++++
 4 files changed, 43 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index c437ca1c0fd39..6d9faa78e391c 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -512,8 +512,11 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) {
 		struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
 
-		if (ptp && ptp->tx_tstamp_en && !skb_is_gso(skb) &&
-		    atomic_dec_if_positive(&ptp->tx_avail) >= 0) {
+		if (ptp && ptp->tx_tstamp_en && !skb_is_gso(skb)) {
+			if (!atomic_dec_if_positive(&ptp->tx_avail)) {
+				atomic64_inc(&ptp->stats.ts_err);
+				goto tx_no_ts;
+			}
 			if (!bnxt_ptp_parse(skb, &ptp->tx_seqid,
 					    &ptp->tx_hdr_off)) {
 				if (vlan_tag_flags)
@@ -526,6 +529,7 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		}
 	}
 
+tx_no_ts:
 	if (unlikely(skb->no_fcs))
 		lflags |= cpu_to_le32(TX_BD_FLAGS_NO_CRC);
 
@@ -732,8 +736,10 @@ tx_done:
 	return NETDEV_TX_OK;
 
 tx_dma_error:
-	if (BNXT_TX_PTP_IS_SET(lflags))
+	if (BNXT_TX_PTP_IS_SET(lflags)) {
+		atomic64_inc(&bp->ptp_cfg->stats.ts_err);
 		atomic_inc(&bp->ptp_cfg->tx_avail);
+	}
 
 	last_frag = i;
 
@@ -812,10 +818,12 @@ static void __bnxt_tx_int(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
 		if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS)) {
 			if (BNXT_CHIP_P5(bp)) {
 				/* PTP worker takes ownership of the skb */
-				if (!bnxt_get_tx_ts_p5(bp, skb))
+				if (!bnxt_get_tx_ts_p5(bp, skb)) {
 					skb = NULL;
-				else
+				} else {
+					atomic64_inc(&bp->ptp_cfg->stats.ts_err);
 					atomic_inc(&bp->ptp_cfg->tx_avail);
+				}
 			}
 		}
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 8763f8a01457f..bf157f6cc0427 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -5233,6 +5233,19 @@ static void bnxt_get_rmon_stats(struct net_device *dev,
 	*ranges = bnxt_rmon_ranges;
 }
 
+static void bnxt_get_ptp_stats(struct net_device *dev,
+			       struct ethtool_ts_stats *ts_stats)
+{
+	struct bnxt *bp = netdev_priv(dev);
+	struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
+
+	if (ptp) {
+		ts_stats->pkts = ptp->stats.ts_pkts;
+		ts_stats->lost = ptp->stats.ts_lost;
+		ts_stats->err = atomic64_read(&ptp->stats.ts_err);
+	}
+}
+
 static void bnxt_get_link_ext_stats(struct net_device *dev,
 				    struct ethtool_link_ext_stats *stats)
 {
@@ -5316,4 +5329,5 @@ const struct ethtool_ops bnxt_ethtool_ops = {
 	.get_eth_mac_stats	= bnxt_get_eth_mac_stats,
 	.get_eth_ctrl_stats	= bnxt_get_eth_ctrl_stats,
 	.get_rmon_stats		= bnxt_get_rmon_stats,
+	.get_ts_stats		= bnxt_get_ptp_stats,
 };
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
index e661ab154d6b2..a14d46b9bfdf0 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
@@ -696,11 +696,13 @@ static void bnxt_stamp_tx_skb(struct bnxt *bp, struct sk_buff *skb)
 		spin_unlock_bh(&ptp->ptp_lock);
 		timestamp.hwtstamp = ns_to_ktime(ns);
 		skb_tstamp_tx(ptp->tx_skb, &timestamp);
+		ptp->stats.ts_pkts++;
 	} else {
 		if (!time_after_eq(jiffies, ptp->abs_txts_tmo)) {
 			ptp->txts_pending = true;
 			return;
 		}
+		ptp->stats.ts_lost++;
 		netdev_warn_once(bp->dev,
 				 "TS query for TX timer failed rc = %x\n", rc);
 	}
@@ -979,6 +981,11 @@ int bnxt_ptp_init(struct bnxt *bp, bool phc_cfg)
 		rc = err;
 		goto out;
 	}
+
+	ptp->stats.ts_pkts = 0;
+	ptp->stats.ts_lost = 0;
+	atomic64_set(&ptp->stats.ts_err, 0);
+
 	if (BNXT_CHIP_P5(bp)) {
 		spin_lock_bh(&ptp->ptp_lock);
 		bnxt_refclk_read(bp, NULL, &ptp->current_time);
@@ -1013,5 +1020,6 @@ void bnxt_ptp_clear(struct bnxt *bp)
 		dev_kfree_skb_any(ptp->tx_skb);
 		ptp->tx_skb = NULL;
 	}
+
 	bnxt_unmap_ptp_regs(bp);
 }
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h
index 2c3415c8fc034..8c30b428a428d 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h
@@ -79,6 +79,12 @@ struct bnxt_pps {
 	struct pps_pin pins[BNXT_MAX_TSIO_PINS];
 };
 
+struct bnxt_ptp_stats {
+	u64		ts_pkts;
+	u64		ts_lost;
+	atomic64_t	ts_err;
+};
+
 struct bnxt_ptp_cfg {
 	struct ptp_clock_info	ptp_info;
 	struct ptp_clock	*ptp_clock;
@@ -125,6 +131,8 @@ struct bnxt_ptp_cfg {
 	u32			refclk_mapped_regs[2];
 	u32			txts_tmo;
 	unsigned long		abs_txts_tmo;
+
+	struct bnxt_ptp_stats	stats;
 };
 
 #if BITS_PER_LONG == 32
-- 
GitLab


From 19249c0724f2048ab68179eac69004947b07d431 Mon Sep 17 00:00:00 2001
From: Matteo Croce <teknoraver@meta.com>
Date: Fri, 31 May 2024 01:27:21 +0200
Subject: [PATCH 687/950] net: make net.core.{r,w}mem_{default,max} namespaced

The following sysctl are global and can't be read from a netns:

net.core.rmem_default
net.core.rmem_max
net.core.wmem_default
net.core.wmem_max

Make the following sysctl parameters available readonly from within a
network namespace, allowing a container to read them.

Signed-off-by: Matteo Croce <teknoraver@meta.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Shakeel Butt <shakeel.butt@linux.dev>
Link: https://lore.kernel.org/r/20240530232722.45255-2-technoboy85@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/sysctl_net_core.c | 75 +++++++++++++++++++++-----------------
 1 file changed, 42 insertions(+), 33 deletions(-)

diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index c9fb9ad874857..2079000691e28 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -382,38 +382,6 @@ proc_dolongvec_minmax_bpf_restricted(struct ctl_table *table, int write,
 #endif
 
 static struct ctl_table net_core_table[] = {
-	{
-		.procname	= "wmem_max",
-		.data		= &sysctl_wmem_max,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &min_sndbuf,
-	},
-	{
-		.procname	= "rmem_max",
-		.data		= &sysctl_rmem_max,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &min_rcvbuf,
-	},
-	{
-		.procname	= "wmem_default",
-		.data		= &sysctl_wmem_default,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &min_sndbuf,
-	},
-	{
-		.procname	= "rmem_default",
-		.data		= &sysctl_rmem_default,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &min_rcvbuf,
-	},
 	{
 		.procname	= "mem_pcpu_rsv",
 		.data		= &net_hotdata.sysctl_mem_pcpu_rsv,
@@ -697,6 +665,41 @@ static struct ctl_table netns_core_table[] = {
 		.extra2		= SYSCTL_ONE,
 		.proc_handler	= proc_dou8vec_minmax,
 	},
+	/* sysctl_core_net_init() will set the values after this
+	 * to readonly in network namespaces
+	 */
+	{
+		.procname	= "wmem_max",
+		.data		= &sysctl_wmem_max,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &min_sndbuf,
+	},
+	{
+		.procname	= "rmem_max",
+		.data		= &sysctl_rmem_max,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &min_rcvbuf,
+	},
+	{
+		.procname	= "wmem_default",
+		.data		= &sysctl_wmem_default,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &min_sndbuf,
+	},
+	{
+		.procname	= "rmem_default",
+		.data		= &sysctl_rmem_default,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &min_rcvbuf,
+	},
 };
 
 static int __init fb_tunnels_only_for_init_net_sysctl_setup(char *str)
@@ -724,8 +727,14 @@ static __net_init int sysctl_core_net_init(struct net *net)
 		if (tbl == NULL)
 			goto err_dup;
 
-		for (i = 0; i < table_size; ++i)
+		for (i = 0; i < table_size; ++i) {
+			if (tbl[i].data == &sysctl_wmem_max)
+				break;
+
 			tbl[i].data += (char *)net - (char *)&init_net;
+		}
+		for (; i < table_size; ++i)
+			tbl[i].mode &= ~0222;
 	}
 
 	net->core.sysctl_hdr = register_net_sysctl_sz(net, "net/core", tbl, table_size);
-- 
GitLab


From 5b5233fb81bfecbfb7502178a9cf6790dde04a2c Mon Sep 17 00:00:00 2001
From: Matteo Croce <teknoraver@meta.com>
Date: Fri, 31 May 2024 01:27:22 +0200
Subject: [PATCH 688/950] selftests: net: tests net.core.{r,w}mem_{default,max}
 sysctls in a netns

Add a selftest which checks that the sysctl is present in a netns,
that the value is read from the init one, and that it's readonly.

Signed-off-by: Matteo Croce <teknoraver@meta.com>
Link: https://lore.kernel.org/r/20240530232722.45255-3-technoboy85@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/Makefile        |  1 +
 tools/testing/selftests/net/netns-sysctl.sh | 40 +++++++++++++++++++++
 2 files changed, 41 insertions(+)
 create mode 100755 tools/testing/selftests/net/netns-sysctl.sh

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index bd01e4a0be2c2..6da63d1831c11 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -53,6 +53,7 @@ TEST_PROGS += bind_bhash.sh
 TEST_PROGS += ip_local_port_range.sh
 TEST_PROGS += rps_default_mask.sh
 TEST_PROGS += big_tcp.sh
+TEST_PROGS += netns-sysctl.sh
 TEST_PROGS_EXTENDED := toeplitz_client.sh toeplitz.sh
 TEST_GEN_FILES =  socket nettest
 TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any
diff --git a/tools/testing/selftests/net/netns-sysctl.sh b/tools/testing/selftests/net/netns-sysctl.sh
new file mode 100755
index 0000000000000..45c34a3b9aae3
--- /dev/null
+++ b/tools/testing/selftests/net/netns-sysctl.sh
@@ -0,0 +1,40 @@
+#!/bin/bash -e
+# SPDX-License-Identifier: GPL-2.0
+#
+# This test checks that the network buffer sysctls are present
+# in a network namespaces, and that they are readonly.
+
+source lib.sh
+
+cleanup() {
+    cleanup_ns $test_ns
+}
+
+trap cleanup EXIT
+
+fail() {
+	echo "ERROR: $*" >&2
+	exit 1
+}
+
+setup_ns test_ns
+
+for sc in {r,w}mem_{default,max}; do
+	# check that this is writable in a netns
+	[ -w "/proc/sys/net/core/$sc" ] ||
+		fail "$sc isn't writable in the init netns!"
+
+	# change the value in the host netns
+	sysctl -qw "net.core.$sc=300000" ||
+		fail "Can't write $sc in init netns!"
+
+	# check that the value is read from the init netns
+	[ "$(ip netns exec $test_ns sysctl -n "net.core.$sc")" -eq 300000 ] ||
+		fail "Value for $sc mismatch!"
+
+	# check that this isn't writable in a netns
+	ip netns exec $test_ns [ -w "/proc/sys/net/core/$sc" ] &&
+		fail "$sc is writable in a netns!"
+done
+
+echo 'Test passed OK'
-- 
GitLab


From a967d3cee86e8e8eb15c9e12f818c59b36416001 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Wed, 29 May 2024 16:00:00 +0200
Subject: [PATCH 689/950] net: ethernet: cortina: Rename adjust link callback

The callback passed to of_phy_get_and_connect() in the
Cortina Gemini driver is called "gmac_speed_set" which is
archaic, rename it to "gmac_adjust_link" following the
pattern of most other drivers.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20240529-gemini-phylib-fixes-v4-1-16487ca4c2fe@linaro.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cortina/gemini.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c
index 7ebd61a3a49b0..8de68a2576114 100644
--- a/drivers/net/ethernet/cortina/gemini.c
+++ b/drivers/net/ethernet/cortina/gemini.c
@@ -288,7 +288,7 @@ static void gmac_set_flow_control(struct net_device *netdev, bool tx, bool rx)
 	spin_unlock_irqrestore(&port->config_lock, flags);
 }
 
-static void gmac_speed_set(struct net_device *netdev)
+static void gmac_adjust_link(struct net_device *netdev)
 {
 	struct gemini_ethernet_port *port = netdev_priv(netdev);
 	struct phy_device *phydev = netdev->phydev;
@@ -367,7 +367,7 @@ static int gmac_setup_phy(struct net_device *netdev)
 
 	phy = of_phy_get_and_connect(netdev,
 				     dev->of_node,
-				     gmac_speed_set);
+				     gmac_adjust_link);
 	if (!phy)
 		return -ENODEV;
 	netdev->phydev = phy;
-- 
GitLab


From 15c22101db71369c022e25001a339f91cd3f8ddc Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Wed, 29 May 2024 16:00:01 +0200
Subject: [PATCH 690/950] net: ethernet: cortina: Use negotiated TX/RX pause

Instead of directly poking into registers of the PHY, use
the existing function to query phylib about this directly.

Suggested-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20240529-gemini-phylib-fixes-v4-2-16487ca4c2fe@linaro.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cortina/gemini.c | 15 +++++----------
 1 file changed, 5 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c
index 8de68a2576114..a37d21ceb1318 100644
--- a/drivers/net/ethernet/cortina/gemini.c
+++ b/drivers/net/ethernet/cortina/gemini.c
@@ -293,8 +293,8 @@ static void gmac_adjust_link(struct net_device *netdev)
 	struct gemini_ethernet_port *port = netdev_priv(netdev);
 	struct phy_device *phydev = netdev->phydev;
 	union gmac_status status, old_status;
-	int pause_tx = 0;
-	int pause_rx = 0;
+	bool pause_tx = false;
+	bool pause_rx = false;
 
 	status.bits32 = readl(port->gmac_base + GMAC_STATUS);
 	old_status.bits32 = status.bits32;
@@ -329,14 +329,9 @@ static void gmac_adjust_link(struct net_device *netdev)
 	}
 
 	if (phydev->duplex == DUPLEX_FULL) {
-		u16 lcladv = phy_read(phydev, MII_ADVERTISE);
-		u16 rmtadv = phy_read(phydev, MII_LPA);
-		u8 cap = mii_resolve_flowctrl_fdx(lcladv, rmtadv);
-
-		if (cap & FLOW_CTRL_RX)
-			pause_rx = 1;
-		if (cap & FLOW_CTRL_TX)
-			pause_tx = 1;
+		phy_get_pause(phydev, &pause_tx, &pause_rx);
+		netdev_dbg(netdev, "set negotiated pause params pause TX = %s, pause RX = %s\n",
+			   pause_tx ? "ON" : "OFF", pause_rx ? "ON" : "OFF");
 	}
 
 	gmac_set_flow_control(netdev, pause_tx, pause_rx);
-- 
GitLab


From dbdb0918da671bde4e9c4c3e974a5e15358dfa5c Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Wed, 29 May 2024 16:00:02 +0200
Subject: [PATCH 691/950] net: ethernet: cortina: Implement .set_pauseparam()

The Cortina Gemini ethernet can very well set up TX or RX
pausing, so add this functionality to the driver in a
.set_pauseparam() callback. Essentially just call down to
phylib and let phylib deal with this, .adjust_link()
will respect the setting from phylib.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://lore.kernel.org/r/20240529-gemini-phylib-fixes-v4-3-16487ca4c2fe@linaro.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cortina/gemini.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c
index a37d21ceb1318..73e1c71c5092e 100644
--- a/drivers/net/ethernet/cortina/gemini.c
+++ b/drivers/net/ethernet/cortina/gemini.c
@@ -2126,6 +2126,19 @@ static void gmac_get_pauseparam(struct net_device *netdev,
 	pparam->autoneg = true;
 }
 
+static int gmac_set_pauseparam(struct net_device *netdev,
+			       struct ethtool_pauseparam *pparam)
+{
+	struct phy_device *phydev = netdev->phydev;
+
+	if (!pparam->autoneg)
+		return -EOPNOTSUPP;
+
+	phy_set_asym_pause(phydev, pparam->rx_pause, pparam->tx_pause);
+
+	return 0;
+}
+
 static void gmac_get_ringparam(struct net_device *netdev,
 			       struct ethtool_ringparam *rp,
 			       struct kernel_ethtool_ringparam *kernel_rp,
@@ -2246,6 +2259,7 @@ static const struct ethtool_ops gmac_351x_ethtool_ops = {
 	.set_link_ksettings = gmac_set_ksettings,
 	.nway_reset	= gmac_nway_reset,
 	.get_pauseparam	= gmac_get_pauseparam,
+	.set_pauseparam = gmac_set_pauseparam,
 	.get_ringparam	= gmac_get_ringparam,
 	.set_ringparam	= gmac_set_ringparam,
 	.get_coalesce	= gmac_get_coalesce,
-- 
GitLab


From e85e271dec0270982afed84f70dc37703fcc1d52 Mon Sep 17 00:00:00 2001
From: DelphineCCChiu <delphine_cc_chiu@wiwynn.com>
Date: Wed, 29 May 2024 14:58:55 +0800
Subject: [PATCH 692/950] net/ncsi: Fix the multi thread manner of NCSI driver

Currently NCSI driver will send several NCSI commands back to back without
waiting the response of previous NCSI command or timeout in some state
when NIC have multi channel. This operation against the single thread
manner defined by NCSI SPEC(section 6.3.2.3 in DSP0222_1.1.1)

According to NCSI SPEC(section 6.2.13.1 in DSP0222_1.1.1), we should probe
one channel at a time by sending NCSI commands (Clear initial state, Get
version ID, Get capabilities...), than repeat this steps until the max
number of channels which we got from NCSI command (Get capabilities) has
been probed.

Fixes: e6f44ed6d04d ("net/ncsi: Package and channel management")
Signed-off-by: DelphineCCChiu <delphine_cc_chiu@wiwynn.com>
Link: https://lore.kernel.org/r/20240529065856.825241-1-delphine_cc_chiu@wiwynn.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ncsi/internal.h    |  2 ++
 net/ncsi/ncsi-manage.c | 73 +++++++++++++++++++++---------------------
 net/ncsi/ncsi-rsp.c    |  4 ++-
 3 files changed, 41 insertions(+), 38 deletions(-)

diff --git a/net/ncsi/internal.h b/net/ncsi/internal.h
index 374412ed780b6..ef0f8f73826f5 100644
--- a/net/ncsi/internal.h
+++ b/net/ncsi/internal.h
@@ -325,6 +325,7 @@ struct ncsi_dev_priv {
 	spinlock_t          lock;            /* Protect the NCSI device    */
 	unsigned int        package_probe_id;/* Current ID during probe    */
 	unsigned int        package_num;     /* Number of packages         */
+	unsigned int        channel_probe_id;/* Current cahnnel ID during probe */
 	struct list_head    packages;        /* List of packages           */
 	struct ncsi_channel *hot_channel;    /* Channel was ever active    */
 	struct ncsi_request requests[256];   /* Request table              */
@@ -343,6 +344,7 @@ struct ncsi_dev_priv {
 	bool                multi_package;   /* Enable multiple packages   */
 	bool                mlx_multi_host;  /* Enable multi host Mellanox */
 	u32                 package_whitelist; /* Packages to configure    */
+	unsigned char       channel_count;     /* Num of channels to probe   */
 };
 
 struct ncsi_cmd_arg {
diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c
index 745c788f1d1df..5ecf611c88200 100644
--- a/net/ncsi/ncsi-manage.c
+++ b/net/ncsi/ncsi-manage.c
@@ -510,17 +510,19 @@ static void ncsi_suspend_channel(struct ncsi_dev_priv *ndp)
 
 		break;
 	case ncsi_dev_state_suspend_gls:
-		ndp->pending_req_num = np->channel_num;
+		ndp->pending_req_num = 1;
 
 		nca.type = NCSI_PKT_CMD_GLS;
 		nca.package = np->id;
+		nca.channel = ndp->channel_probe_id;
+		ret = ncsi_xmit_cmd(&nca);
+		if (ret)
+			goto error;
+		ndp->channel_probe_id++;
 
-		nd->state = ncsi_dev_state_suspend_dcnt;
-		NCSI_FOR_EACH_CHANNEL(np, nc) {
-			nca.channel = nc->id;
-			ret = ncsi_xmit_cmd(&nca);
-			if (ret)
-				goto error;
+		if (ndp->channel_probe_id == ndp->channel_count) {
+			ndp->channel_probe_id = 0;
+			nd->state = ncsi_dev_state_suspend_dcnt;
 		}
 
 		break;
@@ -1345,7 +1347,6 @@ static void ncsi_probe_channel(struct ncsi_dev_priv *ndp)
 {
 	struct ncsi_dev *nd = &ndp->ndev;
 	struct ncsi_package *np;
-	struct ncsi_channel *nc;
 	struct ncsi_cmd_arg nca;
 	unsigned char index;
 	int ret;
@@ -1423,23 +1424,6 @@ static void ncsi_probe_channel(struct ncsi_dev_priv *ndp)
 
 		nd->state = ncsi_dev_state_probe_cis;
 		break;
-	case ncsi_dev_state_probe_cis:
-		ndp->pending_req_num = NCSI_RESERVED_CHANNEL;
-
-		/* Clear initial state */
-		nca.type = NCSI_PKT_CMD_CIS;
-		nca.package = ndp->active_package->id;
-		for (index = 0; index < NCSI_RESERVED_CHANNEL; index++) {
-			nca.channel = index;
-			ret = ncsi_xmit_cmd(&nca);
-			if (ret)
-				goto error;
-		}
-
-		nd->state = ncsi_dev_state_probe_gvi;
-		if (IS_ENABLED(CONFIG_NCSI_OEM_CMD_KEEP_PHY))
-			nd->state = ncsi_dev_state_probe_keep_phy;
-		break;
 	case ncsi_dev_state_probe_keep_phy:
 		ndp->pending_req_num = 1;
 
@@ -1452,14 +1436,17 @@ static void ncsi_probe_channel(struct ncsi_dev_priv *ndp)
 
 		nd->state = ncsi_dev_state_probe_gvi;
 		break;
+	case ncsi_dev_state_probe_cis:
 	case ncsi_dev_state_probe_gvi:
 	case ncsi_dev_state_probe_gc:
 	case ncsi_dev_state_probe_gls:
 		np = ndp->active_package;
-		ndp->pending_req_num = np->channel_num;
+		ndp->pending_req_num = 1;
 
-		/* Retrieve version, capability or link status */
-		if (nd->state == ncsi_dev_state_probe_gvi)
+		/* Clear initial state Retrieve version, capability or link status */
+		if (nd->state == ncsi_dev_state_probe_cis)
+			nca.type = NCSI_PKT_CMD_CIS;
+		else if (nd->state == ncsi_dev_state_probe_gvi)
 			nca.type = NCSI_PKT_CMD_GVI;
 		else if (nd->state == ncsi_dev_state_probe_gc)
 			nca.type = NCSI_PKT_CMD_GC;
@@ -1467,19 +1454,29 @@ static void ncsi_probe_channel(struct ncsi_dev_priv *ndp)
 			nca.type = NCSI_PKT_CMD_GLS;
 
 		nca.package = np->id;
-		NCSI_FOR_EACH_CHANNEL(np, nc) {
-			nca.channel = nc->id;
-			ret = ncsi_xmit_cmd(&nca);
-			if (ret)
-				goto error;
-		}
+		nca.channel = ndp->channel_probe_id;
 
-		if (nd->state == ncsi_dev_state_probe_gvi)
+		ret = ncsi_xmit_cmd(&nca);
+		if (ret)
+			goto error;
+
+		if (nd->state == ncsi_dev_state_probe_cis) {
+			nd->state = ncsi_dev_state_probe_gvi;
+			if (IS_ENABLED(CONFIG_NCSI_OEM_CMD_KEEP_PHY) && ndp->channel_probe_id == 0)
+				nd->state = ncsi_dev_state_probe_keep_phy;
+		} else if (nd->state == ncsi_dev_state_probe_gvi) {
 			nd->state = ncsi_dev_state_probe_gc;
-		else if (nd->state == ncsi_dev_state_probe_gc)
+		} else if (nd->state == ncsi_dev_state_probe_gc) {
 			nd->state = ncsi_dev_state_probe_gls;
-		else
+		} else {
+			nd->state = ncsi_dev_state_probe_cis;
+			ndp->channel_probe_id++;
+		}
+
+		if (ndp->channel_probe_id == ndp->channel_count) {
+			ndp->channel_probe_id = 0;
 			nd->state = ncsi_dev_state_probe_dp;
+		}
 		break;
 	case ncsi_dev_state_probe_dp:
 		ndp->pending_req_num = 1;
@@ -1780,6 +1777,7 @@ struct ncsi_dev *ncsi_register_dev(struct net_device *dev,
 		ndp->requests[i].ndp = ndp;
 		timer_setup(&ndp->requests[i].timer, ncsi_request_timeout, 0);
 	}
+	ndp->channel_count = NCSI_RESERVED_CHANNEL;
 
 	spin_lock_irqsave(&ncsi_dev_lock, flags);
 	list_add_tail_rcu(&ndp->node, &ncsi_dev_list);
@@ -1813,6 +1811,7 @@ int ncsi_start_dev(struct ncsi_dev *nd)
 
 	if (!(ndp->flags & NCSI_DEV_PROBED)) {
 		ndp->package_probe_id = 0;
+		ndp->channel_probe_id = 0;
 		nd->state = ncsi_dev_state_probe;
 		schedule_work(&ndp->work);
 		return 0;
diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c
index bee290d0f48b6..e28be33bdf2c4 100644
--- a/net/ncsi/ncsi-rsp.c
+++ b/net/ncsi/ncsi-rsp.c
@@ -795,12 +795,13 @@ static int ncsi_rsp_handler_gc(struct ncsi_request *nr)
 	struct ncsi_rsp_gc_pkt *rsp;
 	struct ncsi_dev_priv *ndp = nr->ndp;
 	struct ncsi_channel *nc;
+	struct ncsi_package *np;
 	size_t size;
 
 	/* Find the channel */
 	rsp = (struct ncsi_rsp_gc_pkt *)skb_network_header(nr->rsp);
 	ncsi_find_package_and_channel(ndp, rsp->rsp.common.channel,
-				      NULL, &nc);
+				      &np, &nc);
 	if (!nc)
 		return -ENODEV;
 
@@ -835,6 +836,7 @@ static int ncsi_rsp_handler_gc(struct ncsi_request *nr)
 	 */
 	nc->vlan_filter.bitmap = U64_MAX;
 	nc->vlan_filter.n_vids = rsp->vlan_cnt;
+	np->ndp->channel_count = rsp->channel_cnt;
 
 	return 0;
 }
-- 
GitLab


From 5160b129f65fc6e1a4aa282d44f824e12aa800ee Mon Sep 17 00:00:00 2001
From: Rengarajan S <rengarajan.s@microchip.com>
Date: Wed, 29 May 2024 19:32:55 +0530
Subject: [PATCH 693/950] lan78xx: Enable 125 MHz CLK configuration for LAN7801
 if NO EEPROM is detected

The 125MHz and 25MHz clock configurations are enabled in the initialization
regardless of EEPROM (125MHz is needed for RGMII 1000Mbps operation). After
a lite reset (lan78xx_reset), these contents go back to defaults(all 0, so
no 125MHz or 25MHz clock).

Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Rengarajan S <rengarajan.s@microchip.com>
Link: https://lore.kernel.org/r/20240529140256.1849764-2-rengarajan.s@microchip.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/lan78xx.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 7a5cc49ebec66..2472216564e71 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -2941,6 +2941,8 @@ static int lan78xx_reset(struct lan78xx_net *dev)
 		return ret;
 
 	buf |= HW_CFG_MEF_;
+	buf |= HW_CFG_CLK125_EN_;
+	buf |= HW_CFG_REFCLK25_EN_;
 
 	ret = lan78xx_write_reg(dev, HW_CFG, buf);
 	if (ret < 0)
-- 
GitLab


From 799f532de13601f91ecb9cc6169d45d6e6933b0f Mon Sep 17 00:00:00 2001
From: Rengarajan S <rengarajan.s@microchip.com>
Date: Wed, 29 May 2024 19:32:56 +0530
Subject: [PATCH 694/950] lan78xx: Enable Auto Speed and Auto Duplex
 configuration for LAN7801 if NO EEPROM is detected

Enabled ASD/ADD configuration for LAN7801 in the absence of EEPROM.
After the lite reset these contents go back to defaults where ASD/
ADD is disabled. The check is already available for LAN7800.

Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Rengarajan S <rengarajan.s@microchip.com>
Link: https://lore.kernel.org/r/20240529140256.1849764-3-rengarajan.s@microchip.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/lan78xx.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 2472216564e71..8adf77e3557e7 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -3031,8 +3031,11 @@ static int lan78xx_reset(struct lan78xx_net *dev)
 		return ret;
 
 	/* LAN7801 only has RGMII mode */
-	if (dev->chipid == ID_REV_CHIP_ID_7801_)
+	if (dev->chipid == ID_REV_CHIP_ID_7801_) {
 		buf &= ~MAC_CR_GMII_EN_;
+		/* Enable Auto Duplex and Auto speed */
+		buf |= MAC_CR_AUTO_DUPLEX_ | MAC_CR_AUTO_SPEED_;
+	}
 
 	if (dev->chipid == ID_REV_CHIP_ID_7800_ ||
 	    dev->chipid == ID_REV_CHIP_ID_7850_) {
-- 
GitLab


From 33700a0c9b562700c28d31360a5f04508f459a45 Mon Sep 17 00:00:00 2001
From: Dmitry Safonov <0x7f454c46@gmail.com>
Date: Wed, 29 May 2024 18:29:32 +0100
Subject: [PATCH 695/950] net/tcp: Don't consider TCP_CLOSE in
 TCP_AO_ESTABLISHED

TCP_CLOSE may or may not have current/rnext keys and should not be
considered "established". The fast-path for TCP_CLOSE is
SKB_DROP_REASON_TCP_CLOSE. This is what tcp_rcv_state_process() does
anyways. Add an early drop path to not spend any time verifying
segment signatures for sockets in TCP_CLOSE state.

Cc: stable@vger.kernel.org # v6.7
Fixes: 0a3a809089eb ("net/tcp: Verify inbound TCP-AO signed segments")
Signed-off-by: Dmitry Safonov <0x7f454c46@gmail.com>
Link: https://lore.kernel.org/r/20240529-tcp_ao-sk_state-v1-1-d69b5d323c52@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/tcp_ao.h |  7 ++++---
 net/ipv4/tcp_ao.c    | 13 +++++++++----
 2 files changed, 13 insertions(+), 7 deletions(-)

diff --git a/include/net/tcp_ao.h b/include/net/tcp_ao.h
index 471e177362b4c..5d8e9ed2c0056 100644
--- a/include/net/tcp_ao.h
+++ b/include/net/tcp_ao.h
@@ -86,7 +86,8 @@ static inline int tcp_ao_sizeof_key(const struct tcp_ao_key *key)
 struct tcp_ao_info {
 	/* List of tcp_ao_key's */
 	struct hlist_head	head;
-	/* current_key and rnext_key aren't maintained on listen sockets.
+	/* current_key and rnext_key are maintained on sockets
+	 * in TCP_AO_ESTABLISHED states.
 	 * Their purpose is to cache keys on established connections,
 	 * saving needless lookups. Never dereference any of them from
 	 * listen sockets.
@@ -201,9 +202,9 @@ struct tcp6_ao_context {
 };
 
 struct tcp_sigpool;
+/* Established states are fast-path and there always is current_key/rnext_key */
 #define TCP_AO_ESTABLISHED (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_FIN_WAIT2 | \
-			    TCPF_CLOSE | TCPF_CLOSE_WAIT | \
-			    TCPF_LAST_ACK | TCPF_CLOSING)
+			    TCPF_CLOSE_WAIT | TCPF_LAST_ACK | TCPF_CLOSING)
 
 int tcp_ao_transmit_skb(struct sock *sk, struct sk_buff *skb,
 			struct tcp_ao_key *key, struct tcphdr *th,
diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c
index 781b67a525719..37c42b63ff993 100644
--- a/net/ipv4/tcp_ao.c
+++ b/net/ipv4/tcp_ao.c
@@ -933,6 +933,7 @@ tcp_inbound_ao_hash(struct sock *sk, const struct sk_buff *skb,
 	struct tcp_ao_key *key;
 	__be32 sisn, disn;
 	u8 *traffic_key;
+	int state;
 	u32 sne = 0;
 
 	info = rcu_dereference(tcp_sk(sk)->ao_info);
@@ -948,8 +949,9 @@ tcp_inbound_ao_hash(struct sock *sk, const struct sk_buff *skb,
 		disn = 0;
 	}
 
+	state = READ_ONCE(sk->sk_state);
 	/* Fast-path */
-	if (likely((1 << sk->sk_state) & TCP_AO_ESTABLISHED)) {
+	if (likely((1 << state) & TCP_AO_ESTABLISHED)) {
 		enum skb_drop_reason err;
 		struct tcp_ao_key *current_key;
 
@@ -988,6 +990,9 @@ tcp_inbound_ao_hash(struct sock *sk, const struct sk_buff *skb,
 		return SKB_NOT_DROPPED_YET;
 	}
 
+	if (unlikely(state == TCP_CLOSE))
+		return SKB_DROP_REASON_TCP_CLOSE;
+
 	/* Lookup key based on peer address and keyid.
 	 * current_key and rnext_key must not be used on tcp listen
 	 * sockets as otherwise:
@@ -1001,7 +1006,7 @@ tcp_inbound_ao_hash(struct sock *sk, const struct sk_buff *skb,
 	if (th->syn && !th->ack)
 		goto verify_hash;
 
-	if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_NEW_SYN_RECV)) {
+	if ((1 << state) & (TCPF_LISTEN | TCPF_NEW_SYN_RECV)) {
 		/* Make the initial syn the likely case here */
 		if (unlikely(req)) {
 			sne = tcp_ao_compute_sne(0, tcp_rsk(req)->rcv_isn,
@@ -1018,14 +1023,14 @@ tcp_inbound_ao_hash(struct sock *sk, const struct sk_buff *skb,
 			/* no way to figure out initial sisn/disn - drop */
 			return SKB_DROP_REASON_TCP_FLAGS;
 		}
-	} else if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
+	} else if ((1 << state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
 		disn = info->lisn;
 		if (th->syn || th->rst)
 			sisn = th->seq;
 		else
 			sisn = info->risn;
 	} else {
-		WARN_ONCE(1, "TCP-AO: Unexpected sk_state %d", sk->sk_state);
+		WARN_ONCE(1, "TCP-AO: Unexpected sk_state %d", state);
 		return SKB_DROP_REASON_TCP_AOFAILURE;
 	}
 verify_hash:
-- 
GitLab


From b5c089880723b2c18531c40e445235bd646a51d1 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Wed, 29 May 2024 07:46:48 -0700
Subject: [PATCH 696/950] af_unix: Remove dead code in
 unix_stream_read_generic().

When splice() support was added in commit 2b514574f7e8 ("net:
af_unix: implement splice for stream af_unix sockets"), we had
to release unix_sk(sk)->readlock (current iolock) before calling
splice_to_pipe().

Due to the unlock, commit 73ed5d25dce0 ("af-unix: fix use-after-free
with concurrent readers while splicing") added a safeguard in
unix_stream_read_generic(); we had to bump the skb refcount before
calling ->recv_actor() and then check if the skb was consumed by a
concurrent reader.

However, the pipe side locking was refactored, and since commit
25869262ef7a ("skb_splice_bits(): get rid of callback"), we can
call splice_to_pipe() without releasing unix_sk(sk)->iolock.

Now, the skb is always alive after the ->recv_actor() callback,
so let's remove the unnecessary drop_skb logic.

This is mostly the revert of commit 73ed5d25dce0 ("af-unix: fix
use-after-free with concurrent readers while splicing").

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://lore.kernel.org/r/20240529144648.68591-1-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/unix/af_unix.c | 21 ++-------------------
 1 file changed, 2 insertions(+), 19 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 25b49efc0926b..861793b489f6b 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -654,8 +654,8 @@ static void unix_release_sock(struct sock *sk, int embrion)
 	while ((skb = skb_dequeue(&sk->sk_receive_queue)) != NULL) {
 		if (state == TCP_LISTEN)
 			unix_release_sock(skb->sk, 1);
+
 		/* passed fds are erased in the kfree_skb hook	      */
-		UNIXCB(skb).consumed = skb->len;
 		kfree_skb(skb);
 	}
 
@@ -2704,9 +2704,8 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state,
 	skip = max(sk_peek_offset(sk, flags), 0);
 
 	do {
-		int chunk;
-		bool drop_skb;
 		struct sk_buff *skb, *last;
+		int chunk;
 
 redo:
 		unix_state_lock(sk);
@@ -2802,11 +2801,7 @@ unlock:
 		}
 
 		chunk = min_t(unsigned int, unix_skb_len(skb) - skip, size);
-		skb_get(skb);
 		chunk = state->recv_actor(skb, skip, chunk, state);
-		drop_skb = !unix_skb_len(skb);
-		/* skb is only safe to use if !drop_skb */
-		consume_skb(skb);
 		if (chunk < 0) {
 			if (copied == 0)
 				copied = -EFAULT;
@@ -2815,18 +2810,6 @@ unlock:
 		copied += chunk;
 		size -= chunk;
 
-		if (drop_skb) {
-			/* the skb was touched by a concurrent reader;
-			 * we should not expect anything from this skb
-			 * anymore and assume it invalid - we can be
-			 * sure it was dropped from the socket queue
-			 *
-			 * let's report a short read
-			 */
-			err = 0;
-			break;
-		}
-
 		/* Mark read part of skb as used */
 		if (!(flags & MSG_PEEK)) {
 			UNIXCB(skb).consumed += chunk;
-- 
GitLab


From c3f38fa61af77b49866b006939479069cd451173 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 2 Jun 2024 15:44:56 -0700
Subject: [PATCH 697/950] Linux 6.10-rc2

---
 Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index f975b63963280..7f921ae547f11 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 6
 PATCHLEVEL = 10
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc2
 NAME = Baby Opossum Posse
 
 # *DOCUMENTATION*
-- 
GitLab


From 9373ed280651af79e0adfc29797c26ab47bb9f34 Mon Sep 17 00:00:00 2001
From: Jiapeng Chong <jiapeng.chong@linux.alibaba.com>
Date: Wed, 29 May 2024 10:02:44 +0800
Subject: [PATCH 698/950] wifi: rtw89: chan: Use swap() in
 rtw89_swap_sub_entity()

Use existing swap() function instead of keeping duplicate source code.

./drivers/net/wireless/realtek/rtw89/chan.c:2336:32-33: WARNING opportunity for swap().

Reported-by: Abaci Robot <abaci@linux.alibaba.com>
Closes: https://bugzilla.openanolis.cn/show_bug.cgi?id=9174
Signed-off-by: Jiapeng Chong <jiapeng.chong@linux.alibaba.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://msgid.link/20240529020244.129027-1-jiapeng.chong@linux.alibaba.com
---
 drivers/net/wireless/realtek/rtw89/chan.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/chan.c b/drivers/net/wireless/realtek/rtw89/chan.c
index 051a3cad6101b..3b1997223cc52 100644
--- a/drivers/net/wireless/realtek/rtw89/chan.c
+++ b/drivers/net/wireless/realtek/rtw89/chan.c
@@ -2322,7 +2322,6 @@ static void rtw89_swap_sub_entity(struct rtw89_dev *rtwdev,
 				  enum rtw89_sub_entity_idx idx2)
 {
 	struct rtw89_hal *hal = &rtwdev->hal;
-	struct rtw89_sub_entity tmp;
 	struct rtw89_vif *rtwvif;
 	u8 cur;
 
@@ -2332,9 +2331,7 @@ static void rtw89_swap_sub_entity(struct rtw89_dev *rtwdev,
 	hal->sub[idx1].cfg->idx = idx2;
 	hal->sub[idx2].cfg->idx = idx1;
 
-	tmp = hal->sub[idx1];
-	hal->sub[idx1] = hal->sub[idx2];
-	hal->sub[idx2] = tmp;
+	swap(hal->sub[idx1], hal->sub[idx2]);
 
 	rtw89_for_each_rtwvif(rtwdev, rtwvif) {
 		if (!rtwvif->chanctx_assigned)
-- 
GitLab


From 6c3ca6654a74dd396bc477839ba8d9792eced441 Mon Sep 17 00:00:00 2001
From: Tiezhu Yang <yangtiezhu@loongson.cn>
Date: Mon, 3 Jun 2024 15:45:53 +0800
Subject: [PATCH 699/950] LoongArch: Remove CONFIG_ACPI_TABLE_UPGRADE in
 platform_init()

Both acpi_table_upgrade() and acpi_boot_table_init() are defined as
empty functions under !CONFIG_ACPI_TABLE_UPGRADE and !CONFIG_ACPI in
include/linux/acpi.h, there are no implicit declaration errors with
various configs.

  #ifdef CONFIG_ACPI_TABLE_UPGRADE
  void acpi_table_upgrade(void);
  #else
  static inline void acpi_table_upgrade(void) { }
  #endif

  #ifdef	CONFIG_ACPI
  ...
  void acpi_boot_table_init (void);
  ...
  #else	/* !CONFIG_ACPI */
  ...
  static inline void acpi_boot_table_init(void)
  {
  }
  ...
  #endif	/* !CONFIG_ACPI */

As Huacai suggested, CONFIG_ACPI_TABLE_UPGRADE is ugly and not necessary
here, just remove it. At the same time, just keep CONFIG_ACPI to prevent
potential build errors in future, and give a signal to indicate the code
is ACPI-specific. For the same reason, we also put acpi_table_upgrade()
under CONFIG_ACPI.

Signed-off-by: Tiezhu Yang <yangtiezhu@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kernel/setup.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c
index 60e0fe97f61a3..89ad756aeeed2 100644
--- a/arch/loongarch/kernel/setup.c
+++ b/arch/loongarch/kernel/setup.c
@@ -351,10 +351,8 @@ void __init platform_init(void)
 	arch_reserve_vmcore();
 	arch_reserve_crashkernel();
 
-#ifdef CONFIG_ACPI_TABLE_UPGRADE
-	acpi_table_upgrade();
-#endif
 #ifdef CONFIG_ACPI
+	acpi_table_upgrade();
 	acpi_gbl_use_default_register_widths = false;
 	acpi_boot_table_init();
 #endif
-- 
GitLab


From b56f67a6c748bb009f313f91651c8020d2338d63 Mon Sep 17 00:00:00 2001
From: Jiaxun Yang <jiaxun.yang@flygoat.com>
Date: Mon, 3 Jun 2024 15:45:53 +0800
Subject: [PATCH 700/950] LoongArch: Fix built-in DTB detection

fdt_check_header(__dtb_start) will always success because kernel
provides a dummy dtb, and by coincidence __dtb_start clashed with
entry of this dummy dtb. The consequence is fdt passed from firmware
will never be taken.

Fix by trying to utilise __dtb_start only when CONFIG_BUILTIN_DTB is
enabled.

Cc: stable@vger.kernel.org
Fixes: 7b937cc243e5 ("of: Create of_root if no dtb provided by firmware")
Signed-off-by: Jiaxun Yang <jiaxun.yang@flygoat.com>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kernel/setup.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c
index 89ad756aeeed2..3d048f1be1438 100644
--- a/arch/loongarch/kernel/setup.c
+++ b/arch/loongarch/kernel/setup.c
@@ -282,7 +282,7 @@ static void __init fdt_setup(void)
 		return;
 
 	/* Prefer to use built-in dtb, checking its legality first. */
-	if (!fdt_check_header(__dtb_start))
+	if (IS_ENABLED(CONFIG_BUILTIN_DTB) && !fdt_check_header(__dtb_start))
 		fdt_pointer = __dtb_start;
 	else
 		fdt_pointer = efi_fdt_pointer(); /* Fallback to firmware dtb */
-- 
GitLab


From 3de9c42d02a79a5e09bbee7a4421ddc00cfd5c6d Mon Sep 17 00:00:00 2001
From: Jiaxun Yang <jiaxun.yang@flygoat.com>
Date: Mon, 3 Jun 2024 15:45:53 +0800
Subject: [PATCH 701/950] LoongArch: Add all CPUs enabled by fdt to NUMA node 0

NUMA enabled kernel on FDT based machine fails to boot because CPUs
are all in NUMA_NO_NODE and mm subsystem won't accept that.

Fix by adding them to default NUMA node at FDT parsing phase and move
numa_add_cpu(0) to a later point.

Cc: stable@vger.kernel.org
Fixes: 88d4d957edc7 ("LoongArch: Add FDT booting support from efi system table")
Signed-off-by: Jiaxun Yang <jiaxun.yang@flygoat.com>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/include/asm/numa.h | 1 +
 arch/loongarch/kernel/smp.c       | 5 ++++-
 2 files changed, 5 insertions(+), 1 deletion(-)

diff --git a/arch/loongarch/include/asm/numa.h b/arch/loongarch/include/asm/numa.h
index 27f319b498625..b5f9de9f102e4 100644
--- a/arch/loongarch/include/asm/numa.h
+++ b/arch/loongarch/include/asm/numa.h
@@ -56,6 +56,7 @@ extern int early_cpu_to_node(int cpu);
 static inline void early_numa_add_cpu(int cpuid, s16 node)	{ }
 static inline void numa_add_cpu(unsigned int cpu)		{ }
 static inline void numa_remove_cpu(unsigned int cpu)		{ }
+static inline void set_cpuid_to_node(int cpuid, s16 node)	{ }
 
 static inline int early_cpu_to_node(int cpu)
 {
diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c
index 0dfe2388ef413..1436d2465939b 100644
--- a/arch/loongarch/kernel/smp.c
+++ b/arch/loongarch/kernel/smp.c
@@ -273,7 +273,6 @@ static void __init fdt_smp_setup(void)
 
 		if (cpuid == loongson_sysconf.boot_cpu_id) {
 			cpu = 0;
-			numa_add_cpu(cpu);
 		} else {
 			cpu = cpumask_next_zero(-1, cpu_present_mask);
 		}
@@ -283,6 +282,9 @@ static void __init fdt_smp_setup(void)
 		set_cpu_present(cpu, true);
 		__cpu_number_map[cpuid] = cpu;
 		__cpu_logical_map[cpu] = cpuid;
+
+		early_numa_add_cpu(cpu, 0);
+		set_cpuid_to_node(cpuid, 0);
 	}
 
 	loongson_sysconf.nr_cpus = num_processors;
@@ -468,6 +470,7 @@ void smp_prepare_boot_cpu(void)
 	set_cpu_possible(0, true);
 	set_cpu_online(0, true);
 	set_my_cpu_offset(per_cpu_offset(0));
+	numa_add_cpu(0);
 
 	rr_node = first_node(node_online_map);
 	for_each_possible_cpu(cpu) {
-- 
GitLab


From beb2800074c15362cf9f6c7301120910046d6556 Mon Sep 17 00:00:00 2001
From: Jiaxun Yang <jiaxun.yang@flygoat.com>
Date: Mon, 3 Jun 2024 15:45:53 +0800
Subject: [PATCH 702/950] LoongArch: Fix entry point in kernel image header

Currently kernel entry in head.S is in DMW address range, firmware is
instructed to jump to this address after loading the kernel image.

However kernel should not make any assumption on firmware's DMW
setting, thus the entry point should be a physical address falls into
direct translation region.

Fix by converting entry address to physical and amend entry calculation
logic in libstub accordingly.

BTW, use ABSOLUTE() to calculate variables to make Clang/LLVM happy.

Cc: stable@vger.kernel.org
Signed-off-by: Jiaxun Yang <jiaxun.yang@flygoat.com>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kernel/head.S             |  2 +-
 arch/loongarch/kernel/vmlinux.lds.S      | 10 ++++++----
 drivers/firmware/efi/libstub/loongarch.c |  2 +-
 3 files changed, 8 insertions(+), 6 deletions(-)

diff --git a/arch/loongarch/kernel/head.S b/arch/loongarch/kernel/head.S
index c4f7de2e28054..4677ea8fa8e98 100644
--- a/arch/loongarch/kernel/head.S
+++ b/arch/loongarch/kernel/head.S
@@ -22,7 +22,7 @@
 _head:
 	.word	MZ_MAGIC		/* "MZ", MS-DOS header */
 	.org	0x8
-	.dword	kernel_entry		/* Kernel entry point */
+	.dword	_kernel_entry		/* Kernel entry point (physical address) */
 	.dword	_kernel_asize		/* Kernel image effective size */
 	.quad	PHYS_LINK_KADDR		/* Kernel image load offset from start of RAM */
 	.org	0x38			/* 0x20 ~ 0x37 reserved */
diff --git a/arch/loongarch/kernel/vmlinux.lds.S b/arch/loongarch/kernel/vmlinux.lds.S
index e8e97dbf9ca40..3c7595342730e 100644
--- a/arch/loongarch/kernel/vmlinux.lds.S
+++ b/arch/loongarch/kernel/vmlinux.lds.S
@@ -6,6 +6,7 @@
 
 #define PAGE_SIZE _PAGE_SIZE
 #define RO_EXCEPTION_TABLE_ALIGN	4
+#define PHYSADDR_MASK			0xffffffffffff /* 48-bit */
 
 /*
  * Put .bss..swapper_pg_dir as the first thing in .bss. This will
@@ -142,10 +143,11 @@ SECTIONS
 
 #ifdef CONFIG_EFI_STUB
 	/* header symbols */
-	_kernel_asize = _end - _text;
-	_kernel_fsize = _edata - _text;
-	_kernel_vsize = _end - __initdata_begin;
-	_kernel_rsize = _edata - __initdata_begin;
+	_kernel_entry = ABSOLUTE(kernel_entry & PHYSADDR_MASK);
+	_kernel_asize = ABSOLUTE(_end - _text);
+	_kernel_fsize = ABSOLUTE(_edata - _text);
+	_kernel_vsize = ABSOLUTE(_end - __initdata_begin);
+	_kernel_rsize = ABSOLUTE(_edata - __initdata_begin);
 #endif
 
 	.gptab.sdata : {
diff --git a/drivers/firmware/efi/libstub/loongarch.c b/drivers/firmware/efi/libstub/loongarch.c
index 684c9354637c6..d0ef93551c44f 100644
--- a/drivers/firmware/efi/libstub/loongarch.c
+++ b/drivers/firmware/efi/libstub/loongarch.c
@@ -41,7 +41,7 @@ static efi_status_t exit_boot_func(struct efi_boot_memmap *map, void *priv)
 unsigned long __weak kernel_entry_address(unsigned long kernel_addr,
 		efi_loaded_image_t *image)
 {
-	return *(unsigned long *)(kernel_addr + 8) - VMLINUX_LOAD_ADDRESS + kernel_addr;
+	return *(unsigned long *)(kernel_addr + 8) - PHYSADDR(VMLINUX_LOAD_ADDRESS) + kernel_addr;
 }
 
 efi_status_t efi_boot_kernel(void *handle, efi_loaded_image_t *image,
-- 
GitLab


From 1098efd299ffe9c8af818425338c7f6c4f930a98 Mon Sep 17 00:00:00 2001
From: Jiaxun Yang <jiaxun.yang@flygoat.com>
Date: Mon, 3 Jun 2024 15:45:53 +0800
Subject: [PATCH 703/950] LoongArch: Override higher address bits in
 JUMP_VIRT_ADDR

In JUMP_VIRT_ADDR we are performing an or calculation on address value
directly from pcaddi.

This will only work if we are currently running from direct 1:1 mapping
addresses or firmware's DMW is configured exactly same as kernel. Still,
we should not rely on such assumption.

Fix by overriding higher bits in address comes from pcaddi, so we can
get rid of or operator.

Cc: stable@vger.kernel.org
Signed-off-by: Jiaxun Yang <jiaxun.yang@flygoat.com>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/include/asm/stackframe.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/loongarch/include/asm/stackframe.h b/arch/loongarch/include/asm/stackframe.h
index 45b507a7b06fc..d9eafd3ee3d1e 100644
--- a/arch/loongarch/include/asm/stackframe.h
+++ b/arch/loongarch/include/asm/stackframe.h
@@ -42,7 +42,7 @@
 	.macro JUMP_VIRT_ADDR temp1 temp2
 	li.d	\temp1, CACHE_BASE
 	pcaddi	\temp2, 0
-	or	\temp1, \temp1, \temp2
+	bstrins.d  \temp1, \temp2, (DMW_PABITS - 1), 0
 	jirl	zero, \temp1, 0xc
 	.endm
 
-- 
GitLab


From eb36e520f4f1b690fd776f15cbac452f82ff7bfa Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhuacai@loongson.cn>
Date: Mon, 3 Jun 2024 15:45:53 +0800
Subject: [PATCH 704/950] LoongArch: Fix GMAC's phy-mode definitions in dts

The GMAC of Loongson chips cannot insert the correct 1.5-2ns delay. So
we need the PHY to insert internal delays for both transmit and receive
data lines from/to the PHY device. Fix this by changing the "phy-mode"
from "rgmii" to "rgmii-id" in dts.

Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/boot/dts/loongson-2k0500-ref.dts | 4 ++--
 arch/loongarch/boot/dts/loongson-2k1000-ref.dts | 4 ++--
 arch/loongarch/boot/dts/loongson-2k2000-ref.dts | 2 +-
 3 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/arch/loongarch/boot/dts/loongson-2k0500-ref.dts b/arch/loongarch/boot/dts/loongson-2k0500-ref.dts
index 8aefb0c126722..a34734a6c3ce8 100644
--- a/arch/loongarch/boot/dts/loongson-2k0500-ref.dts
+++ b/arch/loongarch/boot/dts/loongson-2k0500-ref.dts
@@ -44,14 +44,14 @@
 &gmac0 {
 	status = "okay";
 
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	bus_id = <0x0>;
 };
 
 &gmac1 {
 	status = "okay";
 
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	bus_id = <0x1>;
 };
 
diff --git a/arch/loongarch/boot/dts/loongson-2k1000-ref.dts b/arch/loongarch/boot/dts/loongson-2k1000-ref.dts
index 8463fe035386e..23cf26cc3e5f1 100644
--- a/arch/loongarch/boot/dts/loongson-2k1000-ref.dts
+++ b/arch/loongarch/boot/dts/loongson-2k1000-ref.dts
@@ -43,7 +43,7 @@
 &gmac0 {
 	status = "okay";
 
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	phy-handle = <&phy0>;
 	mdio {
 		compatible = "snps,dwmac-mdio";
@@ -58,7 +58,7 @@
 &gmac1 {
 	status = "okay";
 
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	phy-handle = <&phy1>;
 	mdio {
 		compatible = "snps,dwmac-mdio";
diff --git a/arch/loongarch/boot/dts/loongson-2k2000-ref.dts b/arch/loongarch/boot/dts/loongson-2k2000-ref.dts
index 74b99bd234cc3..ea9e6985d0e9f 100644
--- a/arch/loongarch/boot/dts/loongson-2k2000-ref.dts
+++ b/arch/loongarch/boot/dts/loongson-2k2000-ref.dts
@@ -92,7 +92,7 @@
 &gmac2 {
 	status = "okay";
 
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	phy-handle = <&phy2>;
 	mdio {
 		compatible = "snps,dwmac-mdio";
-- 
GitLab


From 6149db4997f582e958da675092f21c666e3b67b7 Mon Sep 17 00:00:00 2001
From: Tristram Ha <tristram.ha@microchip.com>
Date: Tue, 28 May 2024 19:20:23 -0700
Subject: [PATCH 705/950] net: phy: micrel: fix KSZ9477 PHY issues after
 suspend/resume

When the PHY is powered up after powered down most of the registers are
reset, so the PHY setup code needs to be done again.  In addition the
interrupt register will need to be setup again so that link status
indication works again.

Fixes: 26dd2974c5b5 ("net: phy: micrel: Move KSZ9477 errata fixes to PHY driver")
Signed-off-by: Tristram Ha <tristram.ha@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/micrel.c | 62 ++++++++++++++++++++++++++++++++++++----
 1 file changed, 56 insertions(+), 6 deletions(-)

diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index 2b8f8b7f1517c..8c20cf9375306 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -1939,7 +1939,7 @@ static const struct ksz9477_errata_write ksz9477_errata_writes[] = {
 	{0x1c, 0x20, 0xeeee},
 };
 
-static int ksz9477_config_init(struct phy_device *phydev)
+static int ksz9477_phy_errata(struct phy_device *phydev)
 {
 	int err;
 	int i;
@@ -1967,16 +1967,30 @@ static int ksz9477_config_init(struct phy_device *phydev)
 			return err;
 	}
 
+	err = genphy_restart_aneg(phydev);
+	if (err)
+		return err;
+
+	return err;
+}
+
+static int ksz9477_config_init(struct phy_device *phydev)
+{
+	int err;
+
+	/* Only KSZ9897 family of switches needs this fix. */
+	if ((phydev->phy_id & 0xf) == 1) {
+		err = ksz9477_phy_errata(phydev);
+		if (err)
+			return err;
+	}
+
 	/* According to KSZ9477 Errata DS80000754C (Module 4) all EEE modes
 	 * in this switch shall be regarded as broken.
 	 */
 	if (phydev->dev_flags & MICREL_NO_EEE)
 		phydev->eee_broken_modes = -1;
 
-	err = genphy_restart_aneg(phydev);
-	if (err)
-		return err;
-
 	return kszphy_config_init(phydev);
 }
 
@@ -2085,6 +2099,42 @@ static int kszphy_resume(struct phy_device *phydev)
 	return 0;
 }
 
+static int ksz9477_resume(struct phy_device *phydev)
+{
+	int ret;
+
+	/* No need to initialize registers if not powered down. */
+	ret = phy_read(phydev, MII_BMCR);
+	if (ret < 0)
+		return ret;
+	if (!(ret & BMCR_PDOWN))
+		return 0;
+
+	genphy_resume(phydev);
+
+	/* After switching from power-down to normal mode, an internal global
+	 * reset is automatically generated. Wait a minimum of 1 ms before
+	 * read/write access to the PHY registers.
+	 */
+	usleep_range(1000, 2000);
+
+	/* Only KSZ9897 family of switches needs this fix. */
+	if ((phydev->phy_id & 0xf) == 1) {
+		ret = ksz9477_phy_errata(phydev);
+		if (ret)
+			return ret;
+	}
+
+	/* Enable PHY Interrupts */
+	if (phy_interrupt_is_valid(phydev)) {
+		phydev->interrupts = PHY_INTERRUPT_ENABLED;
+		if (phydev->drv->config_intr)
+			phydev->drv->config_intr(phydev);
+	}
+
+	return 0;
+}
+
 static int kszphy_probe(struct phy_device *phydev)
 {
 	const struct kszphy_type *type = phydev->drv->driver_data;
@@ -5493,7 +5543,7 @@ static struct phy_driver ksphy_driver[] = {
 	.config_intr	= kszphy_config_intr,
 	.handle_interrupt = kszphy_handle_interrupt,
 	.suspend	= genphy_suspend,
-	.resume		= genphy_resume,
+	.resume		= ksz9477_resume,
 	.get_features	= ksz9477_get_features,
 } };
 
-- 
GitLab


From 3ac14b9dfbd345e891d48d89f6c2fa519848f0f4 Mon Sep 17 00:00:00 2001
From: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Date: Mon, 3 Jun 2024 11:00:18 +0800
Subject: [PATCH 706/950] net/smc: set rmb's SG_MAX_SINGLE_ALLOC limitation
 only when CONFIG_ARCH_NO_SG_CHAIN is defined

SG_MAX_SINGLE_ALLOC is used to limit maximum number of entries that
will be allocated in one piece of scatterlist. When the entries of
scatterlist exceeds SG_MAX_SINGLE_ALLOC, sg chain will be used. From
commit 7c703e54cc71 ("arch: switch the default on ARCH_HAS_SG_CHAIN"),
we can know that the macro CONFIG_ARCH_NO_SG_CHAIN is used to identify
whether sg chain is supported. So, SMC-R's rmb buffer should be limited
by SG_MAX_SINGLE_ALLOC only when the macro CONFIG_ARCH_NO_SG_CHAIN is
defined.

Fixes: a3fe3d01bd0d ("net/smc: introduce sg-logic for RMBs")
Signed-off-by: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Co-developed-by: Wen Gu <guwen@linux.alibaba.com>
Signed-off-by: Wen Gu <guwen@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/smc_core.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index fafdb97adfad9..acca3b1a068f0 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -2015,7 +2015,6 @@ out:
  */
 static u8 smc_compress_bufsize(int size, bool is_smcd, bool is_rmb)
 {
-	const unsigned int max_scat = SG_MAX_SINGLE_ALLOC * PAGE_SIZE;
 	u8 compressed;
 
 	if (size <= SMC_BUF_MIN_SIZE)
@@ -2025,9 +2024,11 @@ static u8 smc_compress_bufsize(int size, bool is_smcd, bool is_rmb)
 	compressed = min_t(u8, ilog2(size) + 1,
 			   is_smcd ? SMCD_DMBE_SIZES : SMCR_RMBE_SIZES);
 
+#ifdef CONFIG_ARCH_NO_SG_CHAIN
 	if (!is_smcd && is_rmb)
 		/* RMBs are backed by & limited to max size of scatterlists */
-		compressed = min_t(u8, compressed, ilog2(max_scat >> 14));
+		compressed = min_t(u8, compressed, ilog2((SG_MAX_SINGLE_ALLOC * PAGE_SIZE) >> 14));
+#endif
 
 	return compressed;
 }
-- 
GitLab


From 2f4b101c542e102c680d136fc6dca081e3fbda4a Mon Sep 17 00:00:00 2001
From: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Date: Mon, 3 Jun 2024 11:00:19 +0800
Subject: [PATCH 707/950] net/smc: change SMCR_RMBE_SIZES from 5 to 15

SMCR_RMBE_SIZES is the upper boundary of SMC-R's snd_buf and rcv_buf.
The maximum bytes of snd_buf and rcv_buf can be calculated by 2^SMCR_
RMBE_SIZES * 16KB. SMCR_RMBE_SIZES = 5 means the upper boundary is 512KB.
TCP's snd_buf and rcv_buf max size is configured by net.ipv4.tcp_w/rmem[2]
whose default value is 4MB or 6MB, is much larger than SMC-R's upper
boundary.

In some scenarios, such as Recommendation System, the communication
pattern is mainly large size send/recv, where the size of snd_buf and
rcv_buf greatly affects performance. Due to the upper boundary
disadvantage, SMC-R performs poor than TCP in those scenarios. So it
is time to enlarge the upper boundary size of SMC-R's snd_buf and rcv_buf,
so that the SMC-R's snd_buf and rcv_buf can be configured to larger size
for performance gain in such scenarios.

The SMC-R rcv_buf's size will be transferred to peer by the field
rmbe_size in clc accept and confirm message. The length of the field
rmbe_size is four bits, which means the maximum value of SMCR_RMBE_SIZES
is 15. In case of frequently adjusting the value of SMCR_RMBE_SIZES
in different scenarios, set the value of SMCR_RMBE_SIZES to the maximum
value 15, which means the upper boundary of SMC-R's snd_buf and rcv_buf
is 512MB. As the real memory usage is determined by the value of
net.smc.w/rmem, not by the upper boundary, set the value of SMCR_RMBE_SIZES
to the maximum value has no side affects.

Signed-off-by: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Co-developed-by: Wen Gu <guwen@linux.alibaba.com>
Signed-off-by: Wen Gu <guwen@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/smc_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index acca3b1a068f0..3b95828d99760 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -2006,7 +2006,7 @@ out:
 }
 
 #define SMCD_DMBE_SIZES		6 /* 0 -> 16KB, 1 -> 32KB, .. 6 -> 1MB */
-#define SMCR_RMBE_SIZES		5 /* 0 -> 16KB, 1 -> 32KB, .. 5 -> 512KB */
+#define SMCR_RMBE_SIZES		15 /* 0 -> 16KB, 1 -> 32KB, .. 15 -> 512MB */
 
 /* convert the RMB size into the compressed notation (minimum 16K, see
  * SMCD/R_DMBE_SIZES.
-- 
GitLab


From 454cfffe8dc112f1ed3966923f5dccdafa3bebf2 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Thu, 30 May 2024 19:33:26 +0300
Subject: [PATCH 708/950] net: dsa: ocelot: use devres in ocelot_ext_probe()

Russell King suggested that felix_vsc9959, seville_vsc9953 and
ocelot_ext have a large portion of duplicated init and teardown code,
which could be made common [1]. The teardown code could even be
simplified away if we made use of devres, something which is used here
and there in the felix driver, just not very consistently.

[1] https://lore.kernel.org/all/Zh1GvcOTXqb7CpQt@shell.armlinux.org.uk/

Prepare the ground in the ocelot_ext driver, by allocating the data
structures using devres and deleting the kfree() calls. This also
deletes the "Failed to allocate ..." message, since memory allocation
errors are extremely loud anyway, and it's hard to miss them.

Suggested-by: "Russell King (Oracle)" <linux@armlinux.org.uk>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Colin Foster <colin.foster@in-advantage.com>
Tested-by: Colin Foster <colin.foster@in-advantage.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/ocelot/ocelot_ext.c | 24 +++++-------------------
 1 file changed, 5 insertions(+), 19 deletions(-)

diff --git a/drivers/net/dsa/ocelot/ocelot_ext.c b/drivers/net/dsa/ocelot/ocelot_ext.c
index a8927dc7aca4f..c893f3ee238b5 100644
--- a/drivers/net/dsa/ocelot/ocelot_ext.c
+++ b/drivers/net/dsa/ocelot/ocelot_ext.c
@@ -71,7 +71,7 @@ static int ocelot_ext_probe(struct platform_device *pdev)
 	struct felix *felix;
 	int err;
 
-	felix = kzalloc(sizeof(*felix), GFP_KERNEL);
+	felix = devm_kzalloc(dev, sizeof(*felix), GFP_KERNEL);
 	if (!felix)
 		return -ENOMEM;
 
@@ -84,12 +84,9 @@ static int ocelot_ext_probe(struct platform_device *pdev)
 
 	felix->info = &vsc7512_info;
 
-	ds = kzalloc(sizeof(*ds), GFP_KERNEL);
-	if (!ds) {
-		err = -ENOMEM;
-		dev_err_probe(dev, err, "Failed to allocate DSA switch\n");
-		goto err_free_felix;
-	}
+	ds = devm_kzalloc(dev, sizeof(*ds), GFP_KERNEL);
+	if (!ds)
+		return -ENOMEM;
 
 	ds->dev = dev;
 	ds->num_ports = felix->info->num_ports;
@@ -102,17 +99,9 @@ static int ocelot_ext_probe(struct platform_device *pdev)
 	felix->tag_proto = DSA_TAG_PROTO_OCELOT;
 
 	err = dsa_register_switch(ds);
-	if (err) {
+	if (err)
 		dev_err_probe(dev, err, "Failed to register DSA switch\n");
-		goto err_free_ds;
-	}
-
-	return 0;
 
-err_free_ds:
-	kfree(ds);
-err_free_felix:
-	kfree(felix);
 	return err;
 }
 
@@ -124,9 +113,6 @@ static void ocelot_ext_remove(struct platform_device *pdev)
 		return;
 
 	dsa_unregister_switch(felix->ds);
-
-	kfree(felix->ds);
-	kfree(felix);
 }
 
 static void ocelot_ext_shutdown(struct platform_device *pdev)
-- 
GitLab


From 90ee9a5b49cea302b666217068e52e0bb325304d Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Thu, 30 May 2024 19:33:27 +0300
Subject: [PATCH 709/950] net: dsa: ocelot: use devres in seville_probe()

Russell King suggested that felix_vsc9959, seville_vsc9953 and
ocelot_ext have a large portion of duplicated init and teardown code,
which could be made common [1]. The teardown code could even be
simplified away if we made use of devres, something which is used here
and there in the felix driver, just not very consistently.

[1] https://lore.kernel.org/all/Zh1GvcOTXqb7CpQt@shell.armlinux.org.uk/

Prepare the ground in the seville_vsc9953 driver, by allocating the data
structures using devres and deleting the kfree() calls. This also
deletes the "Failed to allocate ..." message, since memory allocation
errors are extremely loud anyway, and it's hard to miss them.

Suggested-by: "Russell King (Oracle)" <linux@armlinux.org.uk>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/ocelot/seville_vsc9953.c | 44 +++++++-----------------
 1 file changed, 13 insertions(+), 31 deletions(-)

diff --git a/drivers/net/dsa/ocelot/seville_vsc9953.c b/drivers/net/dsa/ocelot/seville_vsc9953.c
index 5ac8897e232b5..e63247d3dfdb7 100644
--- a/drivers/net/dsa/ocelot/seville_vsc9953.c
+++ b/drivers/net/dsa/ocelot/seville_vsc9953.c
@@ -971,42 +971,36 @@ static const struct felix_info seville_info_vsc9953 = {
 
 static int seville_probe(struct platform_device *pdev)
 {
+	struct device *dev = &pdev->dev;
 	struct dsa_switch *ds;
 	struct ocelot *ocelot;
 	struct resource *res;
 	struct felix *felix;
 	int err;
 
-	felix = kzalloc(sizeof(struct felix), GFP_KERNEL);
-	if (!felix) {
-		err = -ENOMEM;
-		dev_err(&pdev->dev, "Failed to allocate driver memory\n");
-		goto err_alloc_felix;
-	}
+	felix = devm_kzalloc(dev, sizeof(struct felix), GFP_KERNEL);
+	if (!felix)
+		return -ENOMEM;
 
 	platform_set_drvdata(pdev, felix);
 
 	ocelot = &felix->ocelot;
-	ocelot->dev = &pdev->dev;
+	ocelot->dev = dev;
 	ocelot->num_flooding_pgids = 1;
 	felix->info = &seville_info_vsc9953;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!res) {
-		err = -EINVAL;
-		dev_err(&pdev->dev, "Invalid resource\n");
-		goto err_alloc_felix;
+		dev_err(dev, "Invalid resource\n");
+		return -EINVAL;
 	}
 	felix->switch_base = res->start;
 
-	ds = kzalloc(sizeof(struct dsa_switch), GFP_KERNEL);
-	if (!ds) {
-		err = -ENOMEM;
-		dev_err(&pdev->dev, "Failed to allocate DSA switch\n");
-		goto err_alloc_ds;
-	}
+	ds = devm_kzalloc(dev, sizeof(struct dsa_switch), GFP_KERNEL);
+	if (!ds)
+		return -ENOMEM;
 
-	ds->dev = &pdev->dev;
+	ds->dev = dev;
 	ds->num_ports = felix->info->num_ports;
 	ds->ops = &felix_switch_ops;
 	ds->phylink_mac_ops = &felix_phylink_mac_ops;
@@ -1015,18 +1009,9 @@ static int seville_probe(struct platform_device *pdev)
 	felix->tag_proto = DSA_TAG_PROTO_SEVILLE;
 
 	err = dsa_register_switch(ds);
-	if (err) {
-		dev_err(&pdev->dev, "Failed to register DSA switch: %d\n", err);
-		goto err_register_ds;
-	}
+	if (err)
+		dev_err(dev, "Failed to register DSA switch: %d\n", err);
 
-	return 0;
-
-err_register_ds:
-	kfree(ds);
-err_alloc_ds:
-err_alloc_felix:
-	kfree(felix);
 	return err;
 }
 
@@ -1038,9 +1023,6 @@ static void seville_remove(struct platform_device *pdev)
 		return;
 
 	dsa_unregister_switch(felix->ds);
-
-	kfree(felix->ds);
-	kfree(felix);
 }
 
 static void seville_shutdown(struct platform_device *pdev)
-- 
GitLab


From cc711c523da7280c3bb01ec726596154f5af9798 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Thu, 30 May 2024 19:33:28 +0300
Subject: [PATCH 710/950] net: dsa: ocelot: delete open coded status =
 "disabled" parsing

Since commit 6fffbc7ae137 ("PCI: Honor firmware's device disabled
status"), PCI device drivers with OF bindings no longer need this check.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/ocelot/felix_vsc9959.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c
index d4799a908abcf..eabb55da0982f 100644
--- a/drivers/net/dsa/ocelot/felix_vsc9959.c
+++ b/drivers/net/dsa/ocelot/felix_vsc9959.c
@@ -2668,11 +2668,6 @@ static int felix_pci_probe(struct pci_dev *pdev,
 	struct felix *felix;
 	int err;
 
-	if (pdev->dev.of_node && !of_device_is_available(pdev->dev.of_node)) {
-		dev_info(&pdev->dev, "device is disabled, skipping\n");
-		return -ENODEV;
-	}
-
 	err = pci_enable_device(pdev);
 	if (err) {
 		dev_err(&pdev->dev, "device enable failed\n");
-- 
GitLab


From 4510bbd38cbef7e6fc1a786f3e0213ba07fe0a00 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Thu, 30 May 2024 19:33:29 +0300
Subject: [PATCH 711/950] net: dsa: ocelot: consistently use devres in
 felix_pci_probe()

Russell King suggested that felix_vsc9959, seville_vsc9953 and
ocelot_ext have a large portion of duplicated init and teardown code,
which could be made common [1]. The teardown code could even be
simplified away if we made use of devres, something which is used here
and there in the felix driver, just not very consistently.

[1] https://lore.kernel.org/all/Zh1GvcOTXqb7CpQt@shell.armlinux.org.uk/

Prepare the ground in the felix_vsc9959 driver, by allocating the data
structures using devres and deleting the kfree() calls. This also
deletes the "Failed to allocate ..." message, since memory allocation
errors are extremely loud anyway, and it's hard to miss them.

Suggested-by: "Russell King (Oracle)" <linux@armlinux.org.uk>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/ocelot/felix_vsc9959.c | 40 ++++++++++----------------
 1 file changed, 15 insertions(+), 25 deletions(-)

diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c
index eabb55da0982f..34155a0ffd7e8 100644
--- a/drivers/net/dsa/ocelot/felix_vsc9959.c
+++ b/drivers/net/dsa/ocelot/felix_vsc9959.c
@@ -2663,6 +2663,7 @@ static irqreturn_t felix_irq_handler(int irq, void *data)
 static int felix_pci_probe(struct pci_dev *pdev,
 			   const struct pci_device_id *id)
 {
+	struct device *dev = &pdev->dev;
 	struct dsa_switch *ds;
 	struct ocelot *ocelot;
 	struct felix *felix;
@@ -2670,45 +2671,43 @@ static int felix_pci_probe(struct pci_dev *pdev,
 
 	err = pci_enable_device(pdev);
 	if (err) {
-		dev_err(&pdev->dev, "device enable failed\n");
-		goto err_pci_enable;
+		dev_err(dev, "device enable failed: %pe\n", ERR_PTR(err));
+		return err;
 	}
 
-	felix = kzalloc(sizeof(struct felix), GFP_KERNEL);
+	felix = devm_kzalloc(dev, sizeof(struct felix), GFP_KERNEL);
 	if (!felix) {
 		err = -ENOMEM;
-		dev_err(&pdev->dev, "Failed to allocate driver memory\n");
-		goto err_alloc_felix;
+		goto out_disable;
 	}
 
 	pci_set_drvdata(pdev, felix);
 	ocelot = &felix->ocelot;
-	ocelot->dev = &pdev->dev;
+	ocelot->dev = dev;
 	ocelot->num_flooding_pgids = OCELOT_NUM_TC;
 	felix->info = &felix_info_vsc9959;
 	felix->switch_base = pci_resource_start(pdev, VSC9959_SWITCH_PCI_BAR);
 
 	pci_set_master(pdev);
 
-	err = devm_request_threaded_irq(&pdev->dev, pdev->irq, NULL,
+	err = devm_request_threaded_irq(dev, pdev->irq, NULL,
 					&felix_irq_handler, IRQF_ONESHOT,
 					"felix-intb", ocelot);
 	if (err) {
-		dev_err(&pdev->dev, "Failed to request irq\n");
-		goto err_alloc_irq;
+		dev_err(dev, "Failed to request irq: %pe\n", ERR_PTR(err));
+		goto out_disable;
 	}
 
 	ocelot->ptp = 1;
 	ocelot->mm_supported = true;
 
-	ds = kzalloc(sizeof(struct dsa_switch), GFP_KERNEL);
+	ds = devm_kzalloc(dev, sizeof(struct dsa_switch), GFP_KERNEL);
 	if (!ds) {
 		err = -ENOMEM;
-		dev_err(&pdev->dev, "Failed to allocate DSA switch\n");
-		goto err_alloc_ds;
+		goto out_disable;
 	}
 
-	ds->dev = &pdev->dev;
+	ds->dev = dev;
 	ds->num_ports = felix->info->num_ports;
 	ds->num_tx_queues = felix->info->num_tx_queues;
 	ds->ops = &felix_switch_ops;
@@ -2719,20 +2718,14 @@ static int felix_pci_probe(struct pci_dev *pdev,
 
 	err = dsa_register_switch(ds);
 	if (err) {
-		dev_err_probe(&pdev->dev, err, "Failed to register DSA switch\n");
-		goto err_register_ds;
+		dev_err_probe(dev, err, "Failed to register DSA switch\n");
+		goto out_disable;
 	}
 
 	return 0;
 
-err_register_ds:
-	kfree(ds);
-err_alloc_ds:
-err_alloc_irq:
-	kfree(felix);
-err_alloc_felix:
+out_disable:
 	pci_disable_device(pdev);
-err_pci_enable:
 	return err;
 }
 
@@ -2745,9 +2738,6 @@ static void felix_pci_remove(struct pci_dev *pdev)
 
 	dsa_unregister_switch(felix->ds);
 
-	kfree(felix->ds);
-	kfree(felix);
-
 	pci_disable_device(pdev);
 }
 
-- 
GitLab


From 0367a1775933aab80a99ebc91a14efbcaaa45a00 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Thu, 30 May 2024 19:33:30 +0300
Subject: [PATCH 712/950] net: dsa: ocelot: move devm_request_threaded_irq() to
 felix_setup()

The current placement of devm_request_threaded_irq() is inconvenient.
It is between the allocation of the "felix" structure and
dsa_register_switch(), both of which we'd like to refactor into a
function that's common for all switches. But the IRQ is specific to
felix_vsc9959.

A closer inspection of the felix_irq_handler() code suggests that
it does things that depend on the data structures having been fully
initialized. For example, ocelot_get_txtstamp() takes
&port->tx_skbs.lock, which has only been initialized in
ocelot_init_port() which has not run yet.

It is not one of those IRQF_SHARED IRQs, so CONFIG_DEBUG_SHIRQ_FIXME
shouldn't apply here, and thus, it doesn't really matter, because in
practice, the IRQ will not be triggered so early. Nonetheless, it is a
good practice for the driver to be prepared for it to fire as soon as it
is requested.

Create a new felix->info method for running custom code for vsc9959 from
within felix_setup(), and move the request_irq() call there. The
ocelot_ext should have an IRQ as well, so this should be a step in the
right direction for that model (VSC7512) as well.

Some minor changes are made while moving the code. Casts from void *
aren't necessary, so drop them, and rename felix_irq_handler() to the
more specific vsc9959_irq_handler().

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/ocelot/felix.c         |  9 ++++++
 drivers/net/dsa/ocelot/felix.h         |  1 +
 drivers/net/dsa/ocelot/felix_vsc9959.c | 44 ++++++++++++++------------
 3 files changed, 33 insertions(+), 21 deletions(-)

diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c
index 3aa66bf9eafc3..09c0800b18ab4 100644
--- a/drivers/net/dsa/ocelot/felix.c
+++ b/drivers/net/dsa/ocelot/felix.c
@@ -1597,6 +1597,15 @@ static int felix_setup(struct dsa_switch *ds)
 		felix_port_qos_map_init(ocelot, dp->index);
 	}
 
+	if (felix->info->request_irq) {
+		err = felix->info->request_irq(ocelot);
+		if (err) {
+			dev_err(ocelot->dev, "Failed to request IRQ: %pe\n",
+				ERR_PTR(err));
+			goto out_deinit_ports;
+		}
+	}
+
 	err = ocelot_devlink_sb_register(ocelot);
 	if (err)
 		goto out_deinit_ports;
diff --git a/drivers/net/dsa/ocelot/felix.h b/drivers/net/dsa/ocelot/felix.h
index 4d3489aaa6597..e67a25f6f816c 100644
--- a/drivers/net/dsa/ocelot/felix.h
+++ b/drivers/net/dsa/ocelot/felix.h
@@ -64,6 +64,7 @@ struct felix_info {
 				      const struct phylink_link_state *state);
 	int	(*configure_serdes)(struct ocelot *ocelot, int port,
 				    struct device_node *portnp);
+	int	(*request_irq)(struct ocelot *ocelot);
 };
 
 /* Methods for initializing the hardware resources specific to a tagging
diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c
index 34155a0ffd7e8..20563abd617f1 100644
--- a/drivers/net/dsa/ocelot/felix_vsc9959.c
+++ b/drivers/net/dsa/ocelot/felix_vsc9959.c
@@ -2605,6 +2605,28 @@ set:
 	}
 }
 
+/* The INTB interrupt is shared between for PTP TX timestamp availability
+ * notification and MAC Merge status change on each port.
+ */
+static irqreturn_t vsc9959_irq_handler(int irq, void *data)
+{
+	struct ocelot *ocelot = data;
+
+	ocelot_get_txtstamp(ocelot);
+	ocelot_mm_irq(ocelot);
+
+	return IRQ_HANDLED;
+}
+
+static int vsc9959_request_irq(struct ocelot *ocelot)
+{
+	struct pci_dev *pdev = to_pci_dev(ocelot->dev);
+
+	return devm_request_threaded_irq(ocelot->dev, pdev->irq, NULL,
+					 &vsc9959_irq_handler, IRQF_ONESHOT,
+					 "felix-intb", ocelot);
+}
+
 static const struct ocelot_ops vsc9959_ops = {
 	.reset			= vsc9959_reset,
 	.wm_enc			= vsc9959_wm_enc,
@@ -2645,21 +2667,9 @@ static const struct felix_info felix_info_vsc9959 = {
 	.port_modes		= vsc9959_port_modes,
 	.port_setup_tc		= vsc9959_port_setup_tc,
 	.port_sched_speed_set	= vsc9959_sched_speed_set,
+	.request_irq		= vsc9959_request_irq,
 };
 
-/* The INTB interrupt is shared between for PTP TX timestamp availability
- * notification and MAC Merge status change on each port.
- */
-static irqreturn_t felix_irq_handler(int irq, void *data)
-{
-	struct ocelot *ocelot = (struct ocelot *)data;
-
-	ocelot_get_txtstamp(ocelot);
-	ocelot_mm_irq(ocelot);
-
-	return IRQ_HANDLED;
-}
-
 static int felix_pci_probe(struct pci_dev *pdev,
 			   const struct pci_device_id *id)
 {
@@ -2690,14 +2700,6 @@ static int felix_pci_probe(struct pci_dev *pdev,
 
 	pci_set_master(pdev);
 
-	err = devm_request_threaded_irq(dev, pdev->irq, NULL,
-					&felix_irq_handler, IRQF_ONESHOT,
-					"felix-intb", ocelot);
-	if (err) {
-		dev_err(dev, "Failed to request irq: %pe\n", ERR_PTR(err));
-		goto out_disable;
-	}
-
 	ocelot->ptp = 1;
 	ocelot->mm_supported = true;
 
-- 
GitLab


From 4ca54dd96eca57adea961c0e6cca28bf76168429 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Thu, 30 May 2024 19:33:31 +0300
Subject: [PATCH 713/950] net: dsa: ocelot: use ds->num_tx_queues =
 OCELOT_NUM_TC for all models

Russell King points out that seville_vsc9953 populates
felix->info->num_tx_queues = 8, but this doesn't make it all the way
into ds->num_tx_queues (which is how the user interface netdev queues
get allocated) [1].

[1]: https://lore.kernel.org/all/20240415160150.yejcazpjqvn7vhxu@skbuf/

When num_tx_queues=0 for seville, this is implicitly converted to 1 by
dsa_user_create(), and this is good enough for basic operation for a
switch port. The tc qdisc offload layer works with netdev TX queues,
so for QoS offload we need to pretend we have multiple TX queues. The
VSC9953, like ocelot_ext, doesn't export QoS offload, so it doesn't
really matter. But we can definitely set num_tx_queues=8 for all
switches.

The felix->info->num_tx_queues construct itself seems unnecessary.
It was introduced by commit de143c0e274b ("net: dsa: felix: Configure
Time-Aware Scheduler via taprio offload") at a time when vsc9959
(LS1028A) was the only switch supported by the driver.

8 traffic classes, and 1 queue per traffic class, is a common
architectural feature of all switches in the family. So they could
all just set OCELOT_NUM_TC and be fine.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Colin Foster <colin.foster@in-advantage.com>
Tested-by: Colin Foster <colin.foster@in-advantage.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/ocelot/felix.h           | 1 -
 drivers/net/dsa/ocelot/felix_vsc9959.c   | 4 ++--
 drivers/net/dsa/ocelot/ocelot_ext.c      | 3 +--
 drivers/net/dsa/ocelot/seville_vsc9953.c | 3 ++-
 4 files changed, 5 insertions(+), 6 deletions(-)

diff --git a/drivers/net/dsa/ocelot/felix.h b/drivers/net/dsa/ocelot/felix.h
index e67a25f6f816c..e0bfea10ff525 100644
--- a/drivers/net/dsa/ocelot/felix.h
+++ b/drivers/net/dsa/ocelot/felix.h
@@ -32,7 +32,6 @@ struct felix_info {
 	const u32			*port_modes;
 	int				num_mact_rows;
 	int				num_ports;
-	int				num_tx_queues;
 	struct vcap_props		*vcap;
 	u16				vcap_pol_base;
 	u16				vcap_pol_max;
diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c
index 20563abd617f1..ec8b124e8f618 100644
--- a/drivers/net/dsa/ocelot/felix_vsc9959.c
+++ b/drivers/net/dsa/ocelot/felix_vsc9959.c
@@ -2658,7 +2658,6 @@ static const struct felix_info felix_info_vsc9959 = {
 	.vcap_pol_max2		= 0,
 	.num_mact_rows		= 2048,
 	.num_ports		= VSC9959_NUM_PORTS,
-	.num_tx_queues		= OCELOT_NUM_TC,
 	.quirks			= FELIX_MAC_QUIRKS,
 	.quirk_no_xtr_irq	= true,
 	.ptp_caps		= &vsc9959_ptp_caps,
@@ -2711,7 +2710,8 @@ static int felix_pci_probe(struct pci_dev *pdev,
 
 	ds->dev = dev;
 	ds->num_ports = felix->info->num_ports;
-	ds->num_tx_queues = felix->info->num_tx_queues;
+	ds->num_tx_queues = OCELOT_NUM_TC;
+
 	ds->ops = &felix_switch_ops;
 	ds->phylink_mac_ops = &felix_phylink_mac_ops;
 	ds->priv = ocelot;
diff --git a/drivers/net/dsa/ocelot/ocelot_ext.c b/drivers/net/dsa/ocelot/ocelot_ext.c
index c893f3ee238b5..9cd24f77dc49b 100644
--- a/drivers/net/dsa/ocelot/ocelot_ext.c
+++ b/drivers/net/dsa/ocelot/ocelot_ext.c
@@ -57,7 +57,6 @@ static const struct felix_info vsc7512_info = {
 	.vcap				= vsc7514_vcap_props,
 	.num_mact_rows			= 1024,
 	.num_ports			= VSC7514_NUM_PORTS,
-	.num_tx_queues			= OCELOT_NUM_TC,
 	.port_modes			= vsc7512_port_modes,
 	.phylink_mac_config		= ocelot_phylink_mac_config,
 	.configure_serdes		= ocelot_port_configure_serdes,
@@ -90,7 +89,7 @@ static int ocelot_ext_probe(struct platform_device *pdev)
 
 	ds->dev = dev;
 	ds->num_ports = felix->info->num_ports;
-	ds->num_tx_queues = felix->info->num_tx_queues;
+	ds->num_tx_queues = OCELOT_NUM_TC;
 
 	ds->ops = &felix_switch_ops;
 	ds->phylink_mac_ops = &felix_phylink_mac_ops;
diff --git a/drivers/net/dsa/ocelot/seville_vsc9953.c b/drivers/net/dsa/ocelot/seville_vsc9953.c
index e63247d3dfdb7..83bd0e1ee692b 100644
--- a/drivers/net/dsa/ocelot/seville_vsc9953.c
+++ b/drivers/net/dsa/ocelot/seville_vsc9953.c
@@ -963,7 +963,6 @@ static const struct felix_info seville_info_vsc9953 = {
 	.quirks			= FELIX_MAC_QUIRKS,
 	.num_mact_rows		= 2048,
 	.num_ports		= VSC9953_NUM_PORTS,
-	.num_tx_queues		= OCELOT_NUM_TC,
 	.mdio_bus_alloc		= vsc9953_mdio_bus_alloc,
 	.mdio_bus_free		= vsc9953_mdio_bus_free,
 	.port_modes		= vsc9953_port_modes,
@@ -1002,6 +1001,8 @@ static int seville_probe(struct platform_device *pdev)
 
 	ds->dev = dev;
 	ds->num_ports = felix->info->num_ports;
+	ds->num_tx_queues = OCELOT_NUM_TC;
+
 	ds->ops = &felix_switch_ops;
 	ds->phylink_mac_ops = &felix_phylink_mac_ops;
 	ds->priv = ocelot;
-- 
GitLab


From efdbee7d07916d994bc0ff0235d00d46fa991b61 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Thu, 30 May 2024 19:33:32 +0300
Subject: [PATCH 714/950] net: dsa: ocelot: common probing code

Russell King suggested that felix_vsc9959, seville_vsc9953 and
ocelot_ext have a large portion of duplicated init code, which could be
made common [1].

[1]: https://lore.kernel.org/all/Zh1GvcOTXqb7CpQt@shell.armlinux.org.uk/

Here, we take the following common steps:
- "felix" and "ds" structure allocation
- "felix", "ocelot" and "ds" basic structure initialization
- dsa_register_switch() call

and we make a common function out of them.

For every driver except felix_vsc9959, this is also the entire probing
procedure. For felix_vsc9959, we also need to do some PCI-specific
stuff, which can easily be reordered to be done before, and unwound on
failure.

We also have to convert the bus-specific platform_set_drvdata() and
pci_set_drvdata() calls into dev_set_drvdata(). But this should have no
impact on the behavior.

Suggested-by: "Russell King (Oracle)" <linux@armlinux.org.uk>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Tested-by: Colin Foster <colin.foster@in-advantage.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/ocelot/felix.c           | 47 ++++++++++++++++++++++++
 drivers/net/dsa/ocelot/felix.h           |  5 +++
 drivers/net/dsa/ocelot/felix_vsc9959.c   | 44 +++-------------------
 drivers/net/dsa/ocelot/ocelot_ext.c      | 40 +-------------------
 drivers/net/dsa/ocelot/seville_vsc9953.c | 38 ++-----------------
 5 files changed, 63 insertions(+), 111 deletions(-)

diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c
index 09c0800b18ab4..accf737f7b69b 100644
--- a/drivers/net/dsa/ocelot/felix.c
+++ b/drivers/net/dsa/ocelot/felix.c
@@ -2195,6 +2195,53 @@ const struct dsa_switch_ops felix_switch_ops = {
 };
 EXPORT_SYMBOL_GPL(felix_switch_ops);
 
+int felix_register_switch(struct device *dev, resource_size_t switch_base,
+			  int num_flooding_pgids, bool ptp,
+			  bool mm_supported,
+			  enum dsa_tag_protocol init_tag_proto,
+			  const struct felix_info *info)
+{
+	struct dsa_switch *ds;
+	struct ocelot *ocelot;
+	struct felix *felix;
+	int err;
+
+	felix = devm_kzalloc(dev, sizeof(*felix), GFP_KERNEL);
+	if (!felix)
+		return -ENOMEM;
+
+	ds = devm_kzalloc(dev, sizeof(*ds), GFP_KERNEL);
+	if (!ds)
+		return -ENOMEM;
+
+	dev_set_drvdata(dev, felix);
+
+	ocelot = &felix->ocelot;
+	ocelot->dev = dev;
+	ocelot->num_flooding_pgids = num_flooding_pgids;
+	ocelot->ptp = ptp;
+	ocelot->mm_supported = mm_supported;
+
+	felix->info = info;
+	felix->switch_base = switch_base;
+	felix->ds = ds;
+	felix->tag_proto = init_tag_proto;
+
+	ds->dev = dev;
+	ds->num_ports = info->num_ports;
+	ds->num_tx_queues = OCELOT_NUM_TC;
+	ds->ops = &felix_switch_ops;
+	ds->phylink_mac_ops = &felix_phylink_mac_ops;
+	ds->priv = ocelot;
+
+	err = dsa_register_switch(ds);
+	if (err)
+		dev_err_probe(dev, err, "Failed to register DSA switch\n");
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(felix_register_switch);
+
 struct net_device *felix_port_to_netdev(struct ocelot *ocelot, int port)
 {
 	struct felix *felix = ocelot_to_felix(ocelot);
diff --git a/drivers/net/dsa/ocelot/felix.h b/drivers/net/dsa/ocelot/felix.h
index e0bfea10ff525..85b4f8616003c 100644
--- a/drivers/net/dsa/ocelot/felix.h
+++ b/drivers/net/dsa/ocelot/felix.h
@@ -100,6 +100,11 @@ struct felix {
 	unsigned long			host_flood_mc_mask;
 };
 
+int felix_register_switch(struct device *dev, resource_size_t switch_base,
+			  int num_flooding_pgids, bool ptp,
+			  bool mm_supported,
+			  enum dsa_tag_protocol init_tag_proto,
+			  const struct felix_info *info);
 struct net_device *felix_port_to_netdev(struct ocelot *ocelot, int port);
 int felix_netdev_to_port(struct net_device *dev);
 
diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c
index ec8b124e8f618..ba37a566da39a 100644
--- a/drivers/net/dsa/ocelot/felix_vsc9959.c
+++ b/drivers/net/dsa/ocelot/felix_vsc9959.c
@@ -2673,9 +2673,7 @@ static int felix_pci_probe(struct pci_dev *pdev,
 			   const struct pci_device_id *id)
 {
 	struct device *dev = &pdev->dev;
-	struct dsa_switch *ds;
-	struct ocelot *ocelot;
-	struct felix *felix;
+	resource_size_t switch_base;
 	int err;
 
 	err = pci_enable_device(pdev);
@@ -2684,45 +2682,15 @@ static int felix_pci_probe(struct pci_dev *pdev,
 		return err;
 	}
 
-	felix = devm_kzalloc(dev, sizeof(struct felix), GFP_KERNEL);
-	if (!felix) {
-		err = -ENOMEM;
-		goto out_disable;
-	}
-
-	pci_set_drvdata(pdev, felix);
-	ocelot = &felix->ocelot;
-	ocelot->dev = dev;
-	ocelot->num_flooding_pgids = OCELOT_NUM_TC;
-	felix->info = &felix_info_vsc9959;
-	felix->switch_base = pci_resource_start(pdev, VSC9959_SWITCH_PCI_BAR);
-
 	pci_set_master(pdev);
 
-	ocelot->ptp = 1;
-	ocelot->mm_supported = true;
+	switch_base = pci_resource_start(pdev, VSC9959_SWITCH_PCI_BAR);
 
-	ds = devm_kzalloc(dev, sizeof(struct dsa_switch), GFP_KERNEL);
-	if (!ds) {
-		err = -ENOMEM;
+	err = felix_register_switch(dev, switch_base, OCELOT_NUM_TC,
+				    true, true, DSA_TAG_PROTO_OCELOT,
+				    &felix_info_vsc9959);
+	if (err)
 		goto out_disable;
-	}
-
-	ds->dev = dev;
-	ds->num_ports = felix->info->num_ports;
-	ds->num_tx_queues = OCELOT_NUM_TC;
-
-	ds->ops = &felix_switch_ops;
-	ds->phylink_mac_ops = &felix_phylink_mac_ops;
-	ds->priv = ocelot;
-	felix->ds = ds;
-	felix->tag_proto = DSA_TAG_PROTO_OCELOT;
-
-	err = dsa_register_switch(ds);
-	if (err) {
-		dev_err_probe(dev, err, "Failed to register DSA switch\n");
-		goto out_disable;
-	}
 
 	return 0;
 
diff --git a/drivers/net/dsa/ocelot/ocelot_ext.c b/drivers/net/dsa/ocelot/ocelot_ext.c
index 9cd24f77dc49b..5632a7248cd41 100644
--- a/drivers/net/dsa/ocelot/ocelot_ext.c
+++ b/drivers/net/dsa/ocelot/ocelot_ext.c
@@ -64,44 +64,8 @@ static const struct felix_info vsc7512_info = {
 
 static int ocelot_ext_probe(struct platform_device *pdev)
 {
-	struct device *dev = &pdev->dev;
-	struct dsa_switch *ds;
-	struct ocelot *ocelot;
-	struct felix *felix;
-	int err;
-
-	felix = devm_kzalloc(dev, sizeof(*felix), GFP_KERNEL);
-	if (!felix)
-		return -ENOMEM;
-
-	dev_set_drvdata(dev, felix);
-
-	ocelot = &felix->ocelot;
-	ocelot->dev = dev;
-
-	ocelot->num_flooding_pgids = 1;
-
-	felix->info = &vsc7512_info;
-
-	ds = devm_kzalloc(dev, sizeof(*ds), GFP_KERNEL);
-	if (!ds)
-		return -ENOMEM;
-
-	ds->dev = dev;
-	ds->num_ports = felix->info->num_ports;
-	ds->num_tx_queues = OCELOT_NUM_TC;
-
-	ds->ops = &felix_switch_ops;
-	ds->phylink_mac_ops = &felix_phylink_mac_ops;
-	ds->priv = ocelot;
-	felix->ds = ds;
-	felix->tag_proto = DSA_TAG_PROTO_OCELOT;
-
-	err = dsa_register_switch(ds);
-	if (err)
-		dev_err_probe(dev, err, "Failed to register DSA switch\n");
-
-	return err;
+	return felix_register_switch(&pdev->dev, 0, 1, false, false,
+				     DSA_TAG_PROTO_OCELOT, &vsc7512_info);
 }
 
 static void ocelot_ext_remove(struct platform_device *pdev)
diff --git a/drivers/net/dsa/ocelot/seville_vsc9953.c b/drivers/net/dsa/ocelot/seville_vsc9953.c
index 83bd0e1ee692b..70782649c3957 100644
--- a/drivers/net/dsa/ocelot/seville_vsc9953.c
+++ b/drivers/net/dsa/ocelot/seville_vsc9953.c
@@ -971,49 +971,17 @@ static const struct felix_info seville_info_vsc9953 = {
 static int seville_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
-	struct dsa_switch *ds;
-	struct ocelot *ocelot;
 	struct resource *res;
-	struct felix *felix;
-	int err;
-
-	felix = devm_kzalloc(dev, sizeof(struct felix), GFP_KERNEL);
-	if (!felix)
-		return -ENOMEM;
-
-	platform_set_drvdata(pdev, felix);
-
-	ocelot = &felix->ocelot;
-	ocelot->dev = dev;
-	ocelot->num_flooding_pgids = 1;
-	felix->info = &seville_info_vsc9953;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!res) {
 		dev_err(dev, "Invalid resource\n");
 		return -EINVAL;
 	}
-	felix->switch_base = res->start;
-
-	ds = devm_kzalloc(dev, sizeof(struct dsa_switch), GFP_KERNEL);
-	if (!ds)
-		return -ENOMEM;
-
-	ds->dev = dev;
-	ds->num_ports = felix->info->num_ports;
-	ds->num_tx_queues = OCELOT_NUM_TC;
-
-	ds->ops = &felix_switch_ops;
-	ds->phylink_mac_ops = &felix_phylink_mac_ops;
-	ds->priv = ocelot;
-	felix->ds = ds;
-	felix->tag_proto = DSA_TAG_PROTO_SEVILLE;
-
-	err = dsa_register_switch(ds);
-	if (err)
-		dev_err(dev, "Failed to register DSA switch: %d\n", err);
 
-	return err;
+	return felix_register_switch(dev, res->start, 1, false, false,
+				     DSA_TAG_PROTO_SEVILLE,
+				     &seville_info_vsc9953);
 }
 
 static void seville_remove(struct platform_device *pdev)
-- 
GitLab


From a4303941c6f399816eac0a56c627008a41c9336d Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Thu, 30 May 2024 19:33:33 +0300
Subject: [PATCH 715/950] net: dsa: ocelot: unexport felix_phylink_mac_ops and
 felix_switch_ops

Now that the common felix_register_switch() from the umbrella driver
is the only entity that accesses these data structures, we can remove
them from the list of the exported symbols.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Sai Krishna <saikrishnag@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/ocelot/felix.c | 6 ++----
 drivers/net/dsa/ocelot/felix.h | 3 ---
 2 files changed, 2 insertions(+), 7 deletions(-)

diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c
index accf737f7b69b..d12c4e85baa77 100644
--- a/drivers/net/dsa/ocelot/felix.c
+++ b/drivers/net/dsa/ocelot/felix.c
@@ -2106,15 +2106,14 @@ static void felix_get_mm_stats(struct dsa_switch *ds, int port,
 	ocelot_port_get_mm_stats(ocelot, port, stats);
 }
 
-const struct phylink_mac_ops felix_phylink_mac_ops = {
+static const struct phylink_mac_ops felix_phylink_mac_ops = {
 	.mac_select_pcs		= felix_phylink_mac_select_pcs,
 	.mac_config		= felix_phylink_mac_config,
 	.mac_link_down		= felix_phylink_mac_link_down,
 	.mac_link_up		= felix_phylink_mac_link_up,
 };
-EXPORT_SYMBOL_GPL(felix_phylink_mac_ops);
 
-const struct dsa_switch_ops felix_switch_ops = {
+static const struct dsa_switch_ops felix_switch_ops = {
 	.get_tag_protocol		= felix_get_tag_protocol,
 	.change_tag_protocol		= felix_change_tag_protocol,
 	.connect_tag_protocol		= felix_connect_tag_protocol,
@@ -2193,7 +2192,6 @@ const struct dsa_switch_ops felix_switch_ops = {
 	.port_set_host_flood		= felix_port_set_host_flood,
 	.port_change_conduit		= felix_port_change_conduit,
 };
-EXPORT_SYMBOL_GPL(felix_switch_ops);
 
 int felix_register_switch(struct device *dev, resource_size_t switch_base,
 			  int num_flooding_pgids, bool ptp,
diff --git a/drivers/net/dsa/ocelot/felix.h b/drivers/net/dsa/ocelot/felix.h
index 85b4f8616003c..211991f494e35 100644
--- a/drivers/net/dsa/ocelot/felix.h
+++ b/drivers/net/dsa/ocelot/felix.h
@@ -82,9 +82,6 @@ struct felix_tag_proto_ops {
 			      struct netlink_ext_ack *extack);
 };
 
-extern const struct phylink_mac_ops felix_phylink_mac_ops;
-extern const struct dsa_switch_ops felix_switch_ops;
-
 /* DSA glue / front-end for struct ocelot */
 struct felix {
 	struct dsa_switch		*ds;
-- 
GitLab


From 809055628bce824b7fe18331abb65e44d02b0ecf Mon Sep 17 00:00:00 2001
From: Baochen Qiang <quic_bqiang@quicinc.com>
Date: Thu, 30 May 2024 18:56:52 +0300
Subject: [PATCH 716/950] wifi: ath12k: add panic handler

Currently for ath12k PCI devices, firmware could be running in one of
several execution environments, e.g., PBL, SBL and mission mode etc. Among
which PBL is the only stage where PCIe link negotiation could happen. So
normally firmware runs in PBL in order to be enumerated during system reboot.

However it might not work in kernel crash scenario: ath12k target is not
found after warm reboot from kernel crash. This is because when kernel crashes,
ath12k host does nothing to firmware. And during warm reboot, WLAN power
is sustained. So firmware is likely to keep running in mission mode throughout
the bootup process. As a result PCIe link is not established and thus target
not enumerated.

So add a handler in panic notification list for ath12k. When kernel crashes,
this handler gets called and tries to reset target to PBL state. Then PCIe
link negotiation could happen and target gets enumerated.

This change applies to all PCI devices including WCN7850 and QCN9274.

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0-03427-QCAHMTSWPL_V1.0_V2.0_SILICONZ-1.15378.4

Signed-off-by: Baochen Qiang <quic_bqiang@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240529021533.10861-1-quic_bqiang@quicinc.com
---
 drivers/net/wireless/ath/ath12k/core.c | 29 ++++++++++++++++++++++++++
 drivers/net/wireless/ath/ath12k/core.h |  3 +++
 drivers/net/wireless/ath/ath12k/hif.h  |  9 ++++++++
 drivers/net/wireless/ath/ath12k/pci.c  |  8 +++++++
 4 files changed, 49 insertions(+)

diff --git a/drivers/net/wireless/ath/ath12k/core.c b/drivers/net/wireless/ath/ath12k/core.c
index e7f628e935e4a..4c3eab4686c24 100644
--- a/drivers/net/wireless/ath/ath12k/core.c
+++ b/drivers/net/wireless/ath/ath12k/core.c
@@ -1188,6 +1188,29 @@ int ath12k_core_pre_init(struct ath12k_base *ab)
 	return 0;
 }
 
+static int ath12k_core_panic_handler(struct notifier_block *nb,
+				     unsigned long action, void *data)
+{
+	struct ath12k_base *ab = container_of(nb, struct ath12k_base,
+					      panic_nb);
+
+	return ath12k_hif_panic_handler(ab);
+}
+
+static int ath12k_core_panic_notifier_register(struct ath12k_base *ab)
+{
+	ab->panic_nb.notifier_call = ath12k_core_panic_handler;
+
+	return atomic_notifier_chain_register(&panic_notifier_list,
+					      &ab->panic_nb);
+}
+
+static void ath12k_core_panic_notifier_unregister(struct ath12k_base *ab)
+{
+	atomic_notifier_chain_unregister(&panic_notifier_list,
+					 &ab->panic_nb);
+}
+
 int ath12k_core_init(struct ath12k_base *ab)
 {
 	int ret;
@@ -1198,11 +1221,17 @@ int ath12k_core_init(struct ath12k_base *ab)
 		return ret;
 	}
 
+	ret = ath12k_core_panic_notifier_register(ab);
+	if (ret)
+		ath12k_warn(ab, "failed to register panic handler: %d\n", ret);
+
 	return 0;
 }
 
 void ath12k_core_deinit(struct ath12k_base *ab)
 {
+	ath12k_core_panic_notifier_unregister(ab);
+
 	mutex_lock(&ab->core_lock);
 
 	ath12k_core_pdev_destroy(ab);
diff --git a/drivers/net/wireless/ath/ath12k/core.h b/drivers/net/wireless/ath/ath12k/core.h
index 7d20b09c52e66..44ca30b67fa2e 100644
--- a/drivers/net/wireless/ath/ath12k/core.h
+++ b/drivers/net/wireless/ath/ath12k/core.h
@@ -14,6 +14,7 @@
 #include <linux/dmi.h>
 #include <linux/ctype.h>
 #include <linux/firmware.h>
+#include <linux/panic_notifier.h>
 #include "qmi.h"
 #include "htc.h"
 #include "wmi.h"
@@ -924,6 +925,8 @@ struct ath12k_base {
 
 #endif /* CONFIG_ACPI */
 
+	struct notifier_block panic_nb;
+
 	/* must be last */
 	u8 drv_priv[] __aligned(sizeof(void *));
 };
diff --git a/drivers/net/wireless/ath/ath12k/hif.h b/drivers/net/wireless/ath/ath12k/hif.h
index 7f0926fe751d2..0e53ec269fa4f 100644
--- a/drivers/net/wireless/ath/ath12k/hif.h
+++ b/drivers/net/wireless/ath/ath12k/hif.h
@@ -30,6 +30,7 @@ struct ath12k_hif_ops {
 	void (*ce_irq_enable)(struct ath12k_base *ab);
 	void (*ce_irq_disable)(struct ath12k_base *ab);
 	void (*get_ce_msi_idx)(struct ath12k_base *ab, u32 ce_id, u32 *msi_idx);
+	int (*panic_handler)(struct ath12k_base *ab);
 };
 
 static inline int ath12k_hif_map_service_to_pipe(struct ath12k_base *ab, u16 service_id,
@@ -147,4 +148,12 @@ static inline void ath12k_hif_power_down(struct ath12k_base *ab, bool is_suspend
 	ab->hif.ops->power_down(ab, is_suspend);
 }
 
+static inline int ath12k_hif_panic_handler(struct ath12k_base *ab)
+{
+	if (!ab->hif.ops->panic_handler)
+		return NOTIFY_DONE;
+
+	return ab->hif.ops->panic_handler(ab);
+}
+
 #endif /* ATH12K_HIF_H */
diff --git a/drivers/net/wireless/ath/ath12k/pci.c b/drivers/net/wireless/ath/ath12k/pci.c
index 11b95d0370518..876c029f58f62 100644
--- a/drivers/net/wireless/ath/ath12k/pci.c
+++ b/drivers/net/wireless/ath/ath12k/pci.c
@@ -1302,6 +1302,13 @@ void ath12k_pci_power_down(struct ath12k_base *ab, bool is_suspend)
 	ath12k_pci_sw_reset(ab_pci->ab, false);
 }
 
+static int ath12k_pci_panic_handler(struct ath12k_base *ab)
+{
+	ath12k_pci_sw_reset(ab, false);
+
+	return NOTIFY_OK;
+}
+
 static const struct ath12k_hif_ops ath12k_pci_hif_ops = {
 	.start = ath12k_pci_start,
 	.stop = ath12k_pci_stop,
@@ -1319,6 +1326,7 @@ static const struct ath12k_hif_ops ath12k_pci_hif_ops = {
 	.ce_irq_enable = ath12k_pci_hif_ce_irq_enable,
 	.ce_irq_disable = ath12k_pci_hif_ce_irq_disable,
 	.get_ce_msi_idx = ath12k_pci_get_ce_msi_idx,
+	.panic_handler = ath12k_pci_panic_handler,
 };
 
 static
-- 
GitLab


From 22767241e64427bbcffea2e2d51531ab467bc4ef Mon Sep 17 00:00:00 2001
From: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Date: Thu, 30 May 2024 18:56:52 +0300
Subject: [PATCH 717/950] wifi: ath12k: add hw_link_id in ath12k_pdev

Currently, hw_link_id is sent in WMI service ready event but it
is not parsed anywhere.

But, in future, for multi-link operation, this parameter would be
needed by many WMI commands such as WMI beacon template
(WMI_BCN_TMPL_CMDID), WMI vdev start for Multi-link virtual AP
interfaces (WMI_VDEV_START_REQUEST_CMDID), WMI peer assoc command
(WMI_PEER_ASSOC_CMDID) for Multi-link peer and so on.

Hence, add changes to parse and store the hw_link_id received in
WMI service ready event in ath12k_pdev structure.

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

Signed-off-by: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Signed-off-by: Harshitha Prem <quic_hprem@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240529054955.4105240-1-quic_hprem@quicinc.com
---
 drivers/net/wireless/ath/ath12k/core.h | 1 +
 drivers/net/wireless/ath/ath12k/mac.c  | 2 +-
 drivers/net/wireless/ath/ath12k/wmi.c  | 1 +
 3 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath12k/core.h b/drivers/net/wireless/ath/ath12k/core.h
index 44ca30b67fa2e..d03326a68a9f5 100644
--- a/drivers/net/wireless/ath/ath12k/core.h
+++ b/drivers/net/wireless/ath/ath12k/core.h
@@ -690,6 +690,7 @@ struct mlo_timestamp {
 struct ath12k_pdev {
 	struct ath12k *ar;
 	u32 pdev_id;
+	u32 hw_link_id;
 	struct ath12k_pdev_cap cap;
 	u8 mac_addr[ETH_ALEN];
 	struct mlo_timestamp timestamp;
diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index 784964ae03ec5..509c02bffdae8 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -9229,7 +9229,7 @@ static struct ath12k_hw *ath12k_mac_hw_allocate(struct ath12k_base *ab,
 		ar = ath12k_ah_to_ar(ah, i);
 		ar->ah = ah;
 		ar->ab = ab;
-		ar->hw_link_id = i;
+		ar->hw_link_id = pdev->hw_link_id;
 		ar->pdev = pdev;
 		ar->pdev_idx = pdev_idx;
 		pdev->ar = ar;
diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index 99106b088311c..d6e1d1398cdbd 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -500,6 +500,7 @@ ath12k_pull_mac_phy_cap_svc_ready_ext(struct ath12k_wmi_pdev *wmi_handle,
 	mac_caps = wmi_mac_phy_caps + phy_idx;
 
 	pdev->pdev_id = ath12k_wmi_mac_phy_get_pdev_id(mac_caps);
+	pdev->hw_link_id = ath12k_wmi_mac_phy_get_hw_link_id(mac_caps);
 	pdev_cap->supported_bands |= le32_to_cpu(mac_caps->supported_bands);
 	pdev_cap->ampdu_density = le32_to_cpu(mac_caps->ampdu_density);
 
-- 
GitLab


From c6144a21169fe7d0d70f1a0dae6f6301e5918d30 Mon Sep 17 00:00:00 2001
From: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Date: Mon, 3 Jun 2024 22:43:11 +0900
Subject: [PATCH 718/950] tomoyo: update project links

TOMOYO project has moved to SourceForge.net .

Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
---
 Documentation/admin-guide/LSM/tomoyo.rst | 35 ++++++++----------------
 MAINTAINERS                              |  2 +-
 security/tomoyo/Kconfig                  |  2 +-
 security/tomoyo/common.c                 |  2 +-
 4 files changed, 14 insertions(+), 27 deletions(-)

diff --git a/Documentation/admin-guide/LSM/tomoyo.rst b/Documentation/admin-guide/LSM/tomoyo.rst
index 4bc9c2b4da6f3..bdb2c2e2a1b26 100644
--- a/Documentation/admin-guide/LSM/tomoyo.rst
+++ b/Documentation/admin-guide/LSM/tomoyo.rst
@@ -9,8 +9,8 @@ TOMOYO is a name-based MAC extension (LSM module) for the Linux kernel.
 
 LiveCD-based tutorials are available at
 
-http://tomoyo.sourceforge.jp/1.8/ubuntu12.04-live.html
-http://tomoyo.sourceforge.jp/1.8/centos6-live.html
+https://tomoyo.sourceforge.net/1.8/ubuntu12.04-live.html
+https://tomoyo.sourceforge.net/1.8/centos6-live.html
 
 Though these tutorials use non-LSM version of TOMOYO, they are useful for you
 to know what TOMOYO is.
@@ -21,45 +21,32 @@ How to enable TOMOYO?
 Build the kernel with ``CONFIG_SECURITY_TOMOYO=y`` and pass ``security=tomoyo`` on
 kernel's command line.
 
-Please see http://tomoyo.osdn.jp/2.5/ for details.
+Please see https://tomoyo.sourceforge.net/2.6/ for details.
 
 Where is documentation?
 =======================
 
 User <-> Kernel interface documentation is available at
-https://tomoyo.osdn.jp/2.5/policy-specification/index.html .
+https://tomoyo.sourceforge.net/2.6/policy-specification/index.html .
 
 Materials we prepared for seminars and symposiums are available at
-https://osdn.jp/projects/tomoyo/docs/?category_id=532&language_id=1 .
+https://sourceforge.net/projects/tomoyo/files/docs/ .
 Below lists are chosen from three aspects.
 
 What is TOMOYO?
   TOMOYO Linux Overview
-    https://osdn.jp/projects/tomoyo/docs/lca2009-takeda.pdf
+    https://sourceforge.net/projects/tomoyo/files/docs/lca2009-takeda.pdf
   TOMOYO Linux: pragmatic and manageable security for Linux
-    https://osdn.jp/projects/tomoyo/docs/freedomhectaipei-tomoyo.pdf
+    https://sourceforge.net/projects/tomoyo/files/docs/freedomhectaipei-tomoyo.pdf
   TOMOYO Linux: A Practical Method to Understand and Protect Your Own Linux Box
-    https://osdn.jp/projects/tomoyo/docs/PacSec2007-en-no-demo.pdf
+    https://sourceforge.net/projects/tomoyo/files/docs/PacSec2007-en-no-demo.pdf
 
 What can TOMOYO do?
   Deep inside TOMOYO Linux
-    https://osdn.jp/projects/tomoyo/docs/lca2009-kumaneko.pdf
+    https://sourceforge.net/projects/tomoyo/files/docs/lca2009-kumaneko.pdf
   The role of "pathname based access control" in security.
-    https://osdn.jp/projects/tomoyo/docs/lfj2008-bof.pdf
+    https://sourceforge.net/projects/tomoyo/files/docs/lfj2008-bof.pdf
 
 History of TOMOYO?
   Realities of Mainlining
-    https://osdn.jp/projects/tomoyo/docs/lfj2008.pdf
-
-What is future plan?
-====================
-
-We believe that inode based security and name based security are complementary
-and both should be used together. But unfortunately, so far, we cannot enable
-multiple LSM modules at the same time. We feel sorry that you have to give up
-SELinux/SMACK/AppArmor etc. when you want to use TOMOYO.
-
-We hope that LSM becomes stackable in future. Meanwhile, you can use non-LSM
-version of TOMOYO, available at http://tomoyo.osdn.jp/1.8/ .
-LSM version of TOMOYO is a subset of non-LSM version of TOMOYO. We are planning
-to port non-LSM version's functionalities to LSM versions.
+    https://sourceforge.net/projects/tomoyo/files/docs/lfj2008.pdf
diff --git a/MAINTAINERS b/MAINTAINERS
index 8754ac2c259dc..4154db83a172b 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -22679,7 +22679,7 @@ L:	tomoyo-users-en@lists.osdn.me (subscribers-only, for users in English)
 L:	tomoyo-dev@lists.osdn.me (subscribers-only, for developers in Japanese)
 L:	tomoyo-users@lists.osdn.me (subscribers-only, for users in Japanese)
 S:	Maintained
-W:	https://tomoyo.osdn.jp/
+W:	https://tomoyo.sourceforge.net/
 F:	security/tomoyo/
 
 TOPSTAR LAPTOP EXTRAS DRIVER
diff --git a/security/tomoyo/Kconfig b/security/tomoyo/Kconfig
index fad75be5f381d..1e0dd1a6d0b0e 100644
--- a/security/tomoyo/Kconfig
+++ b/security/tomoyo/Kconfig
@@ -10,7 +10,7 @@ config SECURITY_TOMOYO
 	help
 	  This selects TOMOYO Linux, pathname-based access control.
 	  Required userspace tools and further information may be
-	  found at <https://tomoyo.osdn.jp/>.
+	  found at <https://tomoyo.sourceforge.net/>.
 	  If you are unsure how to answer this question, answer N.
 
 config SECURITY_TOMOYO_MAX_ACCEPT_ENTRY
diff --git a/security/tomoyo/common.c b/security/tomoyo/common.c
index ea3140d510ecb..5c7b059a332aa 100644
--- a/security/tomoyo/common.c
+++ b/security/tomoyo/common.c
@@ -2787,7 +2787,7 @@ void tomoyo_check_profile(void)
 		else
 			continue;
 		pr_err("Userland tools for TOMOYO 2.6 must be installed and policy must be initialized.\n");
-		pr_err("Please see https://tomoyo.osdn.jp/2.6/ for more information.\n");
+		pr_err("Please see https://tomoyo.sourceforge.net/2.6/ for more information.\n");
 		panic("STOP!");
 	}
 	tomoyo_read_unlock(idx);
-- 
GitLab


From 96a27ee76f0e95b56f94b6902da7a5ebef372612 Mon Sep 17 00:00:00 2001
From: Xiao Wang <xiao.w.wang@intel.com>
Date: Fri, 24 May 2024 15:55:43 +0800
Subject: [PATCH 719/950] riscv, bpf: Introduce shift add helper with Zba
 optimization
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Zba extension is very useful for generating addresses that index into array
of basic data types. This patch introduces sh2add and sh3add helpers for
RV32 and RV64 respectively, to accelerate addressing for array of unsigned
long data.

Signed-off-by: Xiao Wang <xiao.w.wang@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Björn Töpel <bjorn@kernel.org>
Link: https://lore.kernel.org/bpf/20240524075543.4050464-3-xiao.w.wang@intel.com
---
 arch/riscv/net/bpf_jit.h        | 33 +++++++++++++++++++++++++++++++++
 arch/riscv/net/bpf_jit_comp32.c |  3 +--
 arch/riscv/net/bpf_jit_comp64.c |  9 +++------
 3 files changed, 37 insertions(+), 8 deletions(-)

diff --git a/arch/riscv/net/bpf_jit.h b/arch/riscv/net/bpf_jit.h
index 97041b58237a8..1d1c78d4cff1e 100644
--- a/arch/riscv/net/bpf_jit.h
+++ b/arch/riscv/net/bpf_jit.h
@@ -742,6 +742,17 @@ static inline u16 rvc_swsp(u32 imm8, u8 rs2)
 	return rv_css_insn(0x6, imm, rs2, 0x2);
 }
 
+/* RVZBA instructions. */
+static inline u32 rvzba_sh2add(u8 rd, u8 rs1, u8 rs2)
+{
+	return rv_r_insn(0x10, rs2, rs1, 0x4, rd, 0x33);
+}
+
+static inline u32 rvzba_sh3add(u8 rd, u8 rs1, u8 rs2)
+{
+	return rv_r_insn(0x10, rs2, rs1, 0x6, rd, 0x33);
+}
+
 /* RVZBB instructions. */
 static inline u32 rvzbb_sextb(u8 rd, u8 rs1)
 {
@@ -1095,6 +1106,28 @@ static inline void emit_sw(u8 rs1, s32 off, u8 rs2, struct rv_jit_context *ctx)
 		emit(rv_sw(rs1, off, rs2), ctx);
 }
 
+static inline void emit_sh2add(u8 rd, u8 rs1, u8 rs2, struct rv_jit_context *ctx)
+{
+	if (rvzba_enabled()) {
+		emit(rvzba_sh2add(rd, rs1, rs2), ctx);
+		return;
+	}
+
+	emit_slli(rd, rs1, 2, ctx);
+	emit_add(rd, rd, rs2, ctx);
+}
+
+static inline void emit_sh3add(u8 rd, u8 rs1, u8 rs2, struct rv_jit_context *ctx)
+{
+	if (rvzba_enabled()) {
+		emit(rvzba_sh3add(rd, rs1, rs2), ctx);
+		return;
+	}
+
+	emit_slli(rd, rs1, 3, ctx);
+	emit_add(rd, rd, rs2, ctx);
+}
+
 /* RV64-only helper functions. */
 #if __riscv_xlen == 64
 
diff --git a/arch/riscv/net/bpf_jit_comp32.c b/arch/riscv/net/bpf_jit_comp32.c
index f5ba73bb153d7..592dd86fbf811 100644
--- a/arch/riscv/net/bpf_jit_comp32.c
+++ b/arch/riscv/net/bpf_jit_comp32.c
@@ -811,8 +811,7 @@ static int emit_bpf_tail_call(int insn, struct rv_jit_context *ctx)
 	 * if (!prog)
 	 *   goto out;
 	 */
-	emit(rv_slli(RV_REG_T0, lo(idx_reg), 2), ctx);
-	emit(rv_add(RV_REG_T0, RV_REG_T0, lo(arr_reg)), ctx);
+	emit_sh2add(RV_REG_T0, lo(idx_reg), lo(arr_reg), ctx);
 	off = offsetof(struct bpf_array, ptrs);
 	if (is_12b_check(off, insn))
 		return -1;
diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index 2bc4c14ea59a5..d5cebb0b0afee 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -380,8 +380,7 @@ static int emit_bpf_tail_call(int insn, struct rv_jit_context *ctx)
 	 * if (!prog)
 	 *     goto out;
 	 */
-	emit_slli(RV_REG_T2, RV_REG_A2, 3, ctx);
-	emit_add(RV_REG_T2, RV_REG_T2, RV_REG_A1, ctx);
+	emit_sh3add(RV_REG_T2, RV_REG_A2, RV_REG_A1, ctx);
 	off = offsetof(struct bpf_array, ptrs);
 	if (is_12b_check(off, insn))
 		return -1;
@@ -1099,12 +1098,10 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 			/* Load current CPU number in T1 */
 			emit_ld(RV_REG_T1, offsetof(struct thread_info, cpu),
 				RV_REG_TP, ctx);
-			/* << 3 because offsets are 8 bytes */
-			emit_slli(RV_REG_T1, RV_REG_T1, 3, ctx);
 			/* Load address of __per_cpu_offset array in T2 */
 			emit_addr(RV_REG_T2, (u64)&__per_cpu_offset, extra_pass, ctx);
-			/* Add offset of current CPU to  __per_cpu_offset */
-			emit_add(RV_REG_T1, RV_REG_T2, RV_REG_T1, ctx);
+			/* Get address of __per_cpu_offset[cpu] in T1 */
+			emit_sh3add(RV_REG_T1, RV_REG_T1, RV_REG_T2, ctx);
 			/* Load __per_cpu_offset[cpu] in T1 */
 			emit_ld(RV_REG_T1, 0, RV_REG_T1, ctx);
 			/* Add the offset to Rd */
-- 
GitLab


From dfa7c9ffa607235119e029b70ced72f29059f8f3 Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Mon, 3 Jun 2024 00:41:10 +0100
Subject: [PATCH 720/950] selftests/bpf: Remove unused struct 'scale_test_def'

'scale_test_def' is unused since commit 3762a39ce85f ("selftests/bpf: Split out
bpf_verif_scale selftests into multiple tests"). Remove it.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20240602234112.225107-2-linux@treblig.org
---
 tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
index 4c6ada5b270b2..73f669014b692 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
@@ -45,12 +45,6 @@ err_out:
 	return err;
 }
 
-struct scale_test_def {
-	const char *file;
-	enum bpf_prog_type attach_type;
-	bool fails;
-};
-
 static void scale_test(const char *file,
 		       enum bpf_prog_type attach_type,
 		       bool should_fail)
-- 
GitLab


From 3f67639d8e582c89c79549c619b22a00dd330e4e Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Mon, 3 Jun 2024 00:41:11 +0100
Subject: [PATCH 721/950] selftests/bpf: Remove unused 'key_t' structs

'key_t' is unused in a couple of files since the original commit 60dd49ea6539
("selftests/bpf: Add test for bpf array map iterators"). Remove it.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20240602234112.225107-3-linux@treblig.org
---
 tools/testing/selftests/bpf/progs/bpf_iter_bpf_array_map.c  | 6 ------
 .../selftests/bpf/progs/bpf_iter_bpf_percpu_array_map.c     | 6 ------
 2 files changed, 12 deletions(-)

diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_array_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_array_map.c
index c5969ca6f26b5..564835ba7d516 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_array_map.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_array_map.c
@@ -6,12 +6,6 @@
 
 char _license[] SEC("license") = "GPL";
 
-struct key_t {
-	int a;
-	int b;
-	int c;
-};
-
 struct {
 	__uint(type, BPF_MAP_TYPE_ARRAY);
 	__uint(max_entries, 3);
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_array_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_array_map.c
index 85fa710fad908..9f0e0705b2bf6 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_array_map.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_array_map.c
@@ -6,12 +6,6 @@
 
 char _license[] SEC("license") = "GPL";
 
-struct key_t {
-	int a;
-	int b;
-	int c;
-};
-
 struct {
 	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
 	__uint(max_entries, 3);
-- 
GitLab


From a450d36b05fa225b071ce9fbf522544caea06594 Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Mon, 3 Jun 2024 00:41:12 +0100
Subject: [PATCH 722/950] selftests/bpf: Remove unused struct 'libcap'

'libcap' is unused since commit b1c2768a82b9 ("bpf: selftests: Remove libcap
usage from test_verifier"). Remove it.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20240602234112.225107-4-linux@treblig.org
---
 tools/testing/selftests/bpf/test_verifier.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index df04bda1c9277..610392dfc4fbc 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -1237,11 +1237,6 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type,
 	fixup_prog_kfuncs(prog, fd_array, test->fixup_kfunc_btf_id);
 }
 
-struct libcap {
-	struct __user_cap_header_struct hdr;
-	struct __user_cap_data_struct data[2];
-};
-
 static int set_admin(bool admin)
 {
 	int err;
-- 
GitLab


From ce5249b91e34d81255c00950d415ebd4c3cae8d4 Mon Sep 17 00:00:00 2001
From: Swan Beaujard <beaujardswan@gmail.com>
Date: Mon, 3 Jun 2024 00:58:12 +0200
Subject: [PATCH 723/950] bpftool: Fix typo in MAX_NUM_METRICS macro name

Correct typo in bpftool profiler and change all instances of 'MATRICS' to
'METRICS' in the profiler.bpf.c file.

Signed-off-by: Swan Beaujard <beaujardswan@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Quentin Monnet <qmo@kernel.org>
Link: https://lore.kernel.org/bpf/20240602225812.81171-1-beaujardswan@gmail.com
---
 tools/bpf/bpftool/skeleton/profiler.bpf.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/tools/bpf/bpftool/skeleton/profiler.bpf.c b/tools/bpf/bpftool/skeleton/profiler.bpf.c
index 2f80edc682f11..f48c783cb9f7f 100644
--- a/tools/bpf/bpftool/skeleton/profiler.bpf.c
+++ b/tools/bpf/bpftool/skeleton/profiler.bpf.c
@@ -40,17 +40,17 @@ struct {
 
 const volatile __u32 num_cpu = 1;
 const volatile __u32 num_metric = 1;
-#define MAX_NUM_MATRICS 4
+#define MAX_NUM_METRICS 4
 
 SEC("fentry/XXX")
 int BPF_PROG(fentry_XXX)
 {
-	struct bpf_perf_event_value___local *ptrs[MAX_NUM_MATRICS];
+	struct bpf_perf_event_value___local *ptrs[MAX_NUM_METRICS];
 	u32 key = bpf_get_smp_processor_id();
 	u32 i;
 
 	/* look up before reading, to reduce error */
-	for (i = 0; i < num_metric && i < MAX_NUM_MATRICS; i++) {
+	for (i = 0; i < num_metric && i < MAX_NUM_METRICS; i++) {
 		u32 flag = i;
 
 		ptrs[i] = bpf_map_lookup_elem(&fentry_readings, &flag);
@@ -58,7 +58,7 @@ int BPF_PROG(fentry_XXX)
 			return 0;
 	}
 
-	for (i = 0; i < num_metric && i < MAX_NUM_MATRICS; i++) {
+	for (i = 0; i < num_metric && i < MAX_NUM_METRICS; i++) {
 		struct bpf_perf_event_value___local reading;
 		int err;
 
@@ -99,14 +99,14 @@ fexit_update_maps(u32 id, struct bpf_perf_event_value___local *after)
 SEC("fexit/XXX")
 int BPF_PROG(fexit_XXX)
 {
-	struct bpf_perf_event_value___local readings[MAX_NUM_MATRICS];
+	struct bpf_perf_event_value___local readings[MAX_NUM_METRICS];
 	u32 cpu = bpf_get_smp_processor_id();
 	u32 i, zero = 0;
 	int err;
 	u64 *count;
 
 	/* read all events before updating the maps, to reduce error */
-	for (i = 0; i < num_metric && i < MAX_NUM_MATRICS; i++) {
+	for (i = 0; i < num_metric && i < MAX_NUM_METRICS; i++) {
 		err = bpf_perf_event_read_value(&events, cpu + i * num_cpu,
 						(void *)(readings + i),
 						sizeof(*readings));
@@ -116,7 +116,7 @@ int BPF_PROG(fexit_XXX)
 	count = bpf_map_lookup_elem(&counts, &zero);
 	if (count) {
 		*count += 1;
-		for (i = 0; i < num_metric && i < MAX_NUM_MATRICS; i++)
+		for (i = 0; i < num_metric && i < MAX_NUM_METRICS; i++)
 			fexit_update_maps(i, &readings[i]);
 	}
 	return 0;
-- 
GitLab


From ec1249d3278183d419276b9a7fe73591cd3dd505 Mon Sep 17 00:00:00 2001
From: Jeff Johnson <quic_jjohnson@quicinc.com>
Date: Fri, 31 May 2024 09:28:43 -0700
Subject: [PATCH 724/950] test_bpf: Add missing MODULE_DESCRIPTION()

make allmodconfig && make W=1 C=1 reports:
WARNING: modpost: missing MODULE_DESCRIPTION() in lib/test_bpf.o

Add the missing invocation of the MODULE_DESCRIPTION() macro.

Signed-off-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20240531-md-lib-test_bpf-v1-1-868e4bd2f9ed@quicinc.com
---
 lib/test_bpf.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/lib/test_bpf.c b/lib/test_bpf.c
index 207ff87194db7..ce5716c3999a4 100644
--- a/lib/test_bpf.c
+++ b/lib/test_bpf.c
@@ -15706,4 +15706,5 @@ static void __exit test_bpf_exit(void)
 module_init(test_bpf_init);
 module_exit(test_bpf_exit);
 
+MODULE_DESCRIPTION("Testsuite for BPF interpreter and BPF JIT compiler");
 MODULE_LICENSE("GPL");
-- 
GitLab


From 2317dc2c22cc353b699c7d1db47b2fe91f54055c Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@toblux.com>
Date: Wed, 29 May 2024 12:19:01 +0200
Subject: [PATCH 725/950] bpf, devmap: Remove unnecessary if check in for loop
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The iterator variable dst cannot be NULL and the if check can be removed.
Remove it and fix the following Coccinelle/coccicheck warning reported
by itnull.cocci:

	ERROR: iterator variable bound on line 762 cannot be NULL

Signed-off-by: Thorsten Blum <thorsten.blum@toblux.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/bpf/20240529101900.103913-2-thorsten.blum@toblux.com
---
 kernel/bpf/devmap.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index 4e2cdbb5629f2..7f3b34452243c 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -760,9 +760,6 @@ int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb,
 		for (i = 0; i < dtab->n_buckets; i++) {
 			head = dev_map_index_hash(dtab, i);
 			hlist_for_each_entry_safe(dst, next, head, index_hlist) {
-				if (!dst)
-					continue;
-
 				if (is_ifindex_excluded(excluded_devices, num_excluded,
 							dst->dev->ifindex))
 					continue;
-- 
GitLab


From 1e24c31351787e24b7eebe84866bd55fd62a0aef Mon Sep 17 00:00:00 2001
From: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Date: Fri, 31 May 2024 16:00:04 -0700
Subject: [PATCH 726/950] cpufreq: intel_pstate: Fix unchecked HWP MSR access

Fix unchecked MSR access error for processors with no HWP support. On
such processors, maximum frequency can be changed by the system firmware
using ACPI event ACPI_PROCESSOR_NOTIFY_HIGEST_PERF_CHANGED. This results
in accessing HWP MSR 0x771.

Call Trace:
	<TASK>
	generic_exec_single+0x58/0x120
	smp_call_function_single+0xbf/0x110
	rdmsrl_on_cpu+0x46/0x60
	intel_pstate_get_hwp_cap+0x1b/0x70
	intel_pstate_update_limits+0x2a/0x60
	acpi_processor_notify+0xb7/0x140
	acpi_ev_notify_dispatch+0x3b/0x60

HWP MSR 0x771 can be only read on a CPU which supports HWP and enabled.
Hence intel_pstate_get_hwp_cap() can only be called when hwp_active is
true.

Reported-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Closes: https://lore.kernel.org/linux-pm/20240529155740.Hq2Hw7be@linutronix.de/
Fixes: e8217b4bece3 ("cpufreq: intel_pstate: Update the maximum CPU frequency consistently")
Tested-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/intel_pstate.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 4b986c044741e..65d3f79104bd5 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -1153,7 +1153,8 @@ static void intel_pstate_update_policies(void)
 static void __intel_pstate_update_max_freq(struct cpudata *cpudata,
 					   struct cpufreq_policy *policy)
 {
-	intel_pstate_get_hwp_cap(cpudata);
+	if (hwp_active)
+		intel_pstate_get_hwp_cap(cpudata);
 
 	policy->cpuinfo.max_freq = READ_ONCE(global.no_turbo) ?
 			cpudata->pstate.max_freq : cpudata->pstate.turbo_freq;
-- 
GitLab


From 2884dc7d08d98a89d8d65121524bb7533183a63a Mon Sep 17 00:00:00 2001
From: Cong Wang <cong.wang@bytedance.com>
Date: Sun, 2 Jun 2024 11:27:03 -0700
Subject: [PATCH 727/950] bpf: Fix a potential use-after-free in
 bpf_link_free()

After commit 1a80dbcb2dba, bpf_link can be freed by
link->ops->dealloc_deferred, but the code still tests and uses
link->ops->dealloc afterward, which leads to a use-after-free as
reported by syzbot. Actually, one of them should be sufficient, so
just call one of them instead of both. Also add a WARN_ON() in case
of any problematic implementation.

Fixes: 1a80dbcb2dba ("bpf: support deferring bpf_link dealloc to after RCU grace period")
Reported-by: syzbot+1989ee16d94720836244@syzkaller.appspotmail.com
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/bpf/20240602182703.207276-1-xiyou.wangcong@gmail.com
---
 kernel/bpf/syscall.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 2222c3ff88e7f..f45ed6adc092a 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2998,6 +2998,7 @@ static int bpf_obj_get(const union bpf_attr *attr)
 void bpf_link_init(struct bpf_link *link, enum bpf_link_type type,
 		   const struct bpf_link_ops *ops, struct bpf_prog *prog)
 {
+	WARN_ON(ops->dealloc && ops->dealloc_deferred);
 	atomic64_set(&link->refcnt, 1);
 	link->type = type;
 	link->id = 0;
@@ -3056,16 +3057,17 @@ static void bpf_link_defer_dealloc_mult_rcu_gp(struct rcu_head *rcu)
 /* bpf_link_free is guaranteed to be called from process context */
 static void bpf_link_free(struct bpf_link *link)
 {
+	const struct bpf_link_ops *ops = link->ops;
 	bool sleepable = false;
 
 	bpf_link_free_id(link->id);
 	if (link->prog) {
 		sleepable = link->prog->sleepable;
 		/* detach BPF program, clean up used resources */
-		link->ops->release(link);
+		ops->release(link);
 		bpf_prog_put(link->prog);
 	}
-	if (link->ops->dealloc_deferred) {
+	if (ops->dealloc_deferred) {
 		/* schedule BPF link deallocation; if underlying BPF program
 		 * is sleepable, we need to first wait for RCU tasks trace
 		 * sync, then go through "classic" RCU grace period
@@ -3074,9 +3076,8 @@ static void bpf_link_free(struct bpf_link *link)
 			call_rcu_tasks_trace(&link->rcu, bpf_link_defer_dealloc_mult_rcu_gp);
 		else
 			call_rcu(&link->rcu, bpf_link_defer_dealloc_rcu_gp);
-	}
-	if (link->ops->dealloc)
-		link->ops->dealloc(link);
+	} else if (ops->dealloc)
+		ops->dealloc(link);
 }
 
 static void bpf_link_put_deferred(struct work_struct *work)
-- 
GitLab


From 27bd5fdc24c0d5d1306f968ef24105c4577242b0 Mon Sep 17 00:00:00 2001
From: Nikunj A Dadhania <nikunj@amd.com>
Date: Fri, 31 May 2024 04:46:42 +0000
Subject: [PATCH 728/950] KVM: SEV-ES: Prevent MSR access post VMSA encryption

KVM currently allows userspace to read/write MSRs even after the VMSA is
encrypted. This can cause unintentional issues if MSR access has side-
effects. For ex, while migrating a guest, userspace could attempt to
migrate MSR_IA32_DEBUGCTLMSR and end up unintentionally disabling LBRV on
the target. Fix this by preventing access to those MSRs which are context
switched via the VMSA, once the VMSA is encrypted.

Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Nikunj A Dadhania <nikunj@amd.com>
Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com>
Message-ID: <20240531044644.768-2-ravi.bangoria@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/svm/svm.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 1d3c8be39479b..f265361f4518b 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -2822,10 +2822,24 @@ static int svm_get_msr_feature(struct kvm_msr_entry *msr)
 	return 0;
 }
 
+static bool
+sev_es_prevent_msr_access(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
+{
+	return sev_es_guest(vcpu->kvm) &&
+	       vcpu->arch.guest_state_protected &&
+	       svm_msrpm_offset(msr_info->index) != MSR_INVALID &&
+	       !msr_write_intercepted(vcpu, msr_info->index);
+}
+
 static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
+	if (sev_es_prevent_msr_access(vcpu, msr_info)) {
+		msr_info->data = 0;
+		return -EINVAL;
+	}
+
 	switch (msr_info->index) {
 	case MSR_AMD64_TSC_RATIO:
 		if (!msr_info->host_initiated &&
@@ -2976,6 +2990,10 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 
 	u32 ecx = msr->index;
 	u64 data = msr->data;
+
+	if (sev_es_prevent_msr_access(vcpu, msr))
+		return -EINVAL;
+
 	switch (ecx) {
 	case MSR_AMD64_TSC_RATIO:
 
-- 
GitLab


From d922056215617eedfbdbc29fe49953423686fe5e Mon Sep 17 00:00:00 2001
From: Ravi Bangoria <ravi.bangoria@amd.com>
Date: Fri, 31 May 2024 04:46:43 +0000
Subject: [PATCH 729/950] KVM: SEV-ES: Disallow SEV-ES guests when
 X86_FEATURE_LBRV is absent

As documented in APM[1], LBR Virtualization must be enabled for SEV-ES
guests. So, prevent SEV-ES guests when LBRV support is missing.

[1]: AMD64 Architecture Programmer's Manual Pub. 40332, Rev. 4.07 - June
     2023, Vol 2, 15.35.2 Enabling SEV-ES.
     https://bugzilla.kernel.org/attachment.cgi?id=304653

Fixes: 376c6d285017 ("KVM: SVM: Provide support for SEV-ES vCPU creation/loading")
Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com>
Message-ID: <20240531044644.768-3-ravi.bangoria@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/svm/sev.c |  6 ++++++
 arch/x86/kvm/svm/svm.c | 16 +++++++---------
 arch/x86/kvm/svm/svm.h |  1 +
 3 files changed, 14 insertions(+), 9 deletions(-)

diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 0623cfaa7bb0e..8b52bbba02c0f 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -2406,6 +2406,12 @@ void __init sev_hardware_setup(void)
 	if (!boot_cpu_has(X86_FEATURE_SEV_ES))
 		goto out;
 
+	if (!lbrv) {
+		WARN_ONCE(!boot_cpu_has(X86_FEATURE_LBRV),
+			  "LBRV must be present for SEV-ES support");
+		goto out;
+	}
+
 	/* Has the system been allocated ASIDs for SEV-ES? */
 	if (min_sev_asid == 1)
 		goto out;
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index f265361f4518b..223a551bf44e4 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -215,7 +215,7 @@ int vgif = true;
 module_param(vgif, int, 0444);
 
 /* enable/disable LBR virtualization */
-static int lbrv = true;
+int lbrv = true;
 module_param(lbrv, int, 0444);
 
 static int tsc_scaling = true;
@@ -5294,6 +5294,12 @@ static __init int svm_hardware_setup(void)
 
 	nrips = nrips && boot_cpu_has(X86_FEATURE_NRIPS);
 
+	if (lbrv) {
+		if (!boot_cpu_has(X86_FEATURE_LBRV))
+			lbrv = false;
+		else
+			pr_info("LBR virtualization supported\n");
+	}
 	/*
 	 * Note, SEV setup consumes npt_enabled and enable_mmio_caching (which
 	 * may be modified by svm_adjust_mmio_mask()), as well as nrips.
@@ -5347,14 +5353,6 @@ static __init int svm_hardware_setup(void)
 		svm_x86_ops.set_vnmi_pending = NULL;
 	}
 
-
-	if (lbrv) {
-		if (!boot_cpu_has(X86_FEATURE_LBRV))
-			lbrv = false;
-		else
-			pr_info("LBR virtualization supported\n");
-	}
-
 	if (!enable_pmu)
 		pr_info("PMU virtualization is disabled\n");
 
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index be57213cd2959..59bbb8122b750 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -39,6 +39,7 @@ extern int vgif;
 extern bool intercept_smi;
 extern bool x2avic_enabled;
 extern bool vnmi;
+extern int lbrv;
 
 /*
  * Clean bits in VMCB.
-- 
GitLab


From b7e4be0a224fe5c6be30c1c8bdda8d2317ad6ba4 Mon Sep 17 00:00:00 2001
From: Ravi Bangoria <ravi.bangoria@amd.com>
Date: Fri, 31 May 2024 04:46:44 +0000
Subject: [PATCH 730/950] KVM: SEV-ES: Delegate LBR virtualization to the
 processor

As documented in APM[1], LBR Virtualization must be enabled for SEV-ES
guests. Although KVM currently enforces LBRV for SEV-ES guests, there
are multiple issues with it:

o MSR_IA32_DEBUGCTLMSR is still intercepted. Since MSR_IA32_DEBUGCTLMSR
  interception is used to dynamically toggle LBRV for performance reasons,
  this can be fatal for SEV-ES guests. For ex SEV-ES guest on Zen3:

  [guest ~]# wrmsr 0x1d9 0x4
  KVM: entry failed, hardware error 0xffffffff
  EAX=00000004 EBX=00000000 ECX=000001d9 EDX=00000000

  Fix this by never intercepting MSR_IA32_DEBUGCTLMSR for SEV-ES guests.
  No additional save/restore logic is required since MSR_IA32_DEBUGCTLMSR
  is of swap type A.

o KVM will disable LBRV if userspace sets MSR_IA32_DEBUGCTLMSR before the
  VMSA is encrypted. Fix this by moving LBRV enablement code post VMSA
  encryption.

[1]: AMD64 Architecture Programmer's Manual Pub. 40332, Rev. 4.07 - June
     2023, Vol 2, 15.35.2 Enabling SEV-ES.
     https://bugzilla.kernel.org/attachment.cgi?id=304653

Fixes: 376c6d285017 ("KVM: SVM: Provide support for SEV-ES vCPU creation/loading")
Co-developed-by: Nikunj A Dadhania <nikunj@amd.com>
Signed-off-by: Nikunj A Dadhania <nikunj@amd.com>
Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com>
Message-ID: <20240531044644.768-4-ravi.bangoria@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/svm/sev.c | 13 ++++++++-----
 arch/x86/kvm/svm/svm.c |  8 +++++++-
 arch/x86/kvm/svm/svm.h |  3 ++-
 3 files changed, 17 insertions(+), 7 deletions(-)

diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 8b52bbba02c0f..95095a233a459 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -779,6 +779,14 @@ static int __sev_launch_update_vmsa(struct kvm *kvm, struct kvm_vcpu *vcpu,
 	 */
 	fpstate_set_confidential(&vcpu->arch.guest_fpu);
 	vcpu->arch.guest_state_protected = true;
+
+	/*
+	 * SEV-ES guest mandates LBR Virtualization to be _always_ ON. Enable it
+	 * only after setting guest_state_protected because KVM_SET_MSRS allows
+	 * dynamic toggling of LBRV (for performance reason) on write access to
+	 * MSR_IA32_DEBUGCTLMSR when guest_state_protected is not set.
+	 */
+	svm_enable_lbrv(vcpu);
 	return 0;
 }
 
@@ -3222,7 +3230,6 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm)
 	struct kvm_vcpu *vcpu = &svm->vcpu;
 
 	svm->vmcb->control.nested_ctl |= SVM_NESTED_CTL_SEV_ES_ENABLE;
-	svm->vmcb->control.virt_ext |= LBR_CTL_ENABLE_MASK;
 
 	/*
 	 * An SEV-ES guest requires a VMSA area that is a separate from the
@@ -3274,10 +3281,6 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm)
 	/* Clear intercepts on selected MSRs */
 	set_msr_interception(vcpu, svm->msrpm, MSR_EFER, 1, 1);
 	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_CR_PAT, 1, 1);
-	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHFROMIP, 1, 1);
-	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 1, 1);
-	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 1, 1);
-	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 1, 1);
 }
 
 void sev_init_vmcb(struct vcpu_svm *svm)
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 223a551bf44e4..296c524988f95 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -99,6 +99,7 @@ static const struct svm_direct_access_msrs {
 	{ .index = MSR_IA32_SPEC_CTRL,			.always = false },
 	{ .index = MSR_IA32_PRED_CMD,			.always = false },
 	{ .index = MSR_IA32_FLUSH_CMD,			.always = false },
+	{ .index = MSR_IA32_DEBUGCTLMSR,		.always = false },
 	{ .index = MSR_IA32_LASTBRANCHFROMIP,		.always = false },
 	{ .index = MSR_IA32_LASTBRANCHTOIP,		.always = false },
 	{ .index = MSR_IA32_LASTINTFROMIP,		.always = false },
@@ -990,7 +991,7 @@ void svm_copy_lbrs(struct vmcb *to_vmcb, struct vmcb *from_vmcb)
 	vmcb_mark_dirty(to_vmcb, VMCB_LBR);
 }
 
-static void svm_enable_lbrv(struct kvm_vcpu *vcpu)
+void svm_enable_lbrv(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
@@ -1000,6 +1001,9 @@ static void svm_enable_lbrv(struct kvm_vcpu *vcpu)
 	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 1, 1);
 	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 1, 1);
 
+	if (sev_es_guest(vcpu->kvm))
+		set_msr_interception(vcpu, svm->msrpm, MSR_IA32_DEBUGCTLMSR, 1, 1);
+
 	/* Move the LBR msrs to the vmcb02 so that the guest can see them. */
 	if (is_guest_mode(vcpu))
 		svm_copy_lbrs(svm->vmcb, svm->vmcb01.ptr);
@@ -1009,6 +1013,8 @@ static void svm_disable_lbrv(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
+	KVM_BUG_ON(sev_es_guest(vcpu->kvm), vcpu->kvm);
+
 	svm->vmcb->control.virt_ext &= ~LBR_CTL_ENABLE_MASK;
 	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHFROMIP, 0, 0);
 	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 0, 0);
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 59bbb8122b750..0f1472690b593 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -30,7 +30,7 @@
 #define	IOPM_SIZE PAGE_SIZE * 3
 #define	MSRPM_SIZE PAGE_SIZE * 2
 
-#define MAX_DIRECT_ACCESS_MSRS	47
+#define MAX_DIRECT_ACCESS_MSRS	48
 #define MSRPM_OFFSETS	32
 extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly;
 extern bool npt_enabled;
@@ -553,6 +553,7 @@ u32 *svm_vcpu_alloc_msrpm(void);
 void svm_vcpu_init_msrpm(struct kvm_vcpu *vcpu, u32 *msrpm);
 void svm_vcpu_free_msrpm(u32 *msrpm);
 void svm_copy_lbrs(struct vmcb *to_vmcb, struct vmcb *from_vmcb);
+void svm_enable_lbrv(struct kvm_vcpu *vcpu);
 void svm_update_lbrv(struct kvm_vcpu *vcpu);
 
 int svm_set_efer(struct kvm_vcpu *vcpu, u64 efer);
-- 
GitLab


From 89a58812c47f1823191e9d0b08b53df2dd304ae2 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 21 May 2024 18:03:04 -0700
Subject: [PATCH 731/950] KVM: x86: Drop support for hand tuning APIC timer
 advancement from userspace

Remove support for specifying a static local APIC timer advancement value,
and instead present a read-only boolean parameter to let userspace enable
or disable KVM's dynamic APIC timer advancement.  Realistically, it's all
but impossible for userspace to specify an advancement that is more
precise than what KVM's adaptive tuning can provide.  E.g. a static value
needs to be tuned for the exact hardware and kernel, and if KVM is using
hrtimers, likely requires additional tuning for the exact configuration of
the entire system.

Dropping support for a userspace provided value also fixes several flaws
in the interface.  E.g. KVM interprets a negative value other than -1 as a
large advancement, toggling between a negative and positive value yields
unpredictable behavior as vCPUs will switch from dynamic to static
advancement, changing the advancement in the middle of VM creation can
result in different values for vCPUs within a VM, etc.  Those flaws are
mostly fixable, but there's almost no justification for taking on yet more
complexity (it's minimal complexity, but still non-zero).

The only arguments against using KVM's adaptive tuning is if a setup needs
a higher maximum, or if the adjustments are too reactive, but those are
arguments for letting userspace control the absolute max advancement and
the granularity of each adjustment, e.g. similar to how KVM provides knobs
for halt polling.

Link: https://lore.kernel.org/all/20240520115334.852510-1-zhoushuling@huawei.com
Cc: Shuling Zhou <zhoushuling@huawei.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-ID: <20240522010304.1650603-1-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/lapic.c | 39 +++++++++++++++++++++------------------
 arch/x86/kvm/lapic.h |  2 +-
 arch/x86/kvm/x86.c   | 11 +----------
 3 files changed, 23 insertions(+), 29 deletions(-)

diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index ebf41023be382..acd7d48100a1d 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -59,7 +59,17 @@
 #define MAX_APIC_VECTOR			256
 #define APIC_VECTORS_PER_REG		32
 
-static bool lapic_timer_advance_dynamic __read_mostly;
+/*
+ * Enable local APIC timer advancement (tscdeadline mode only) with adaptive
+ * tuning.  When enabled, KVM programs the host timer event to fire early, i.e.
+ * before the deadline expires, to account for the delay between taking the
+ * VM-Exit (to inject the guest event) and the subsequent VM-Enter to resume
+ * the guest, i.e. so that the interrupt arrives in the guest with minimal
+ * latency relative to the deadline programmed by the guest.
+ */
+static bool lapic_timer_advance __read_mostly = true;
+module_param(lapic_timer_advance, bool, 0444);
+
 #define LAPIC_TIMER_ADVANCE_ADJUST_MIN	100	/* clock cycles */
 #define LAPIC_TIMER_ADVANCE_ADJUST_MAX	10000	/* clock cycles */
 #define LAPIC_TIMER_ADVANCE_NS_INIT	1000
@@ -1854,16 +1864,14 @@ static void __kvm_wait_lapic_expire(struct kvm_vcpu *vcpu)
 	guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc());
 	trace_kvm_wait_lapic_expire(vcpu->vcpu_id, guest_tsc - tsc_deadline);
 
-	if (lapic_timer_advance_dynamic) {
-		adjust_lapic_timer_advance(vcpu, guest_tsc - tsc_deadline);
-		/*
-		 * If the timer fired early, reread the TSC to account for the
-		 * overhead of the above adjustment to avoid waiting longer
-		 * than is necessary.
-		 */
-		if (guest_tsc < tsc_deadline)
-			guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc());
-	}
+	adjust_lapic_timer_advance(vcpu, guest_tsc - tsc_deadline);
+
+	/*
+	 * If the timer fired early, reread the TSC to account for the overhead
+	 * of the above adjustment to avoid waiting longer than is necessary.
+	 */
+	if (guest_tsc < tsc_deadline)
+		guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc());
 
 	if (guest_tsc < tsc_deadline)
 		__wait_lapic_expire(vcpu, tsc_deadline - guest_tsc);
@@ -2812,7 +2820,7 @@ static enum hrtimer_restart apic_timer_fn(struct hrtimer *data)
 		return HRTIMER_NORESTART;
 }
 
-int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns)
+int kvm_create_lapic(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic;
 
@@ -2845,13 +2853,8 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns)
 	hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC,
 		     HRTIMER_MODE_ABS_HARD);
 	apic->lapic_timer.timer.function = apic_timer_fn;
-	if (timer_advance_ns == -1) {
+	if (lapic_timer_advance)
 		apic->lapic_timer.timer_advance_ns = LAPIC_TIMER_ADVANCE_NS_INIT;
-		lapic_timer_advance_dynamic = true;
-	} else {
-		apic->lapic_timer.timer_advance_ns = timer_advance_ns;
-		lapic_timer_advance_dynamic = false;
-	}
 
 	/*
 	 * Stuff the APIC ENABLE bit in lieu of temporarily incrementing
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index 0a0ea4b5dd8ce..a69e706b9080a 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -85,7 +85,7 @@ struct kvm_lapic {
 
 struct dest_map;
 
-int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns);
+int kvm_create_lapic(struct kvm_vcpu *vcpu);
 void kvm_free_lapic(struct kvm_vcpu *vcpu);
 
 int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 082ac6d95a3a0..8c9e4281d978d 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -164,15 +164,6 @@ module_param(kvmclock_periodic_sync, bool, 0444);
 static u32 __read_mostly tsc_tolerance_ppm = 250;
 module_param(tsc_tolerance_ppm, uint, 0644);
 
-/*
- * lapic timer advance (tscdeadline mode only) in nanoseconds.  '-1' enables
- * adaptive tuning starting from default advancement of 1000ns.  '0' disables
- * advancement entirely.  Any other value is used as-is and disables adaptive
- * tuning, i.e. allows privileged userspace to set an exact advancement time.
- */
-static int __read_mostly lapic_timer_advance_ns = -1;
-module_param(lapic_timer_advance_ns, int, 0644);
-
 static bool __read_mostly vector_hashing = true;
 module_param(vector_hashing, bool, 0444);
 
@@ -12169,7 +12160,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 	if (r < 0)
 		return r;
 
-	r = kvm_create_lapic(vcpu, lapic_timer_advance_ns);
+	r = kvm_create_lapic(vcpu);
 	if (r < 0)
 		goto fail_mmu_destroy;
 
-- 
GitLab


From d95ba15b97847f4ae520db83bd98b61d50fb3068 Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Thu, 23 May 2024 14:49:57 +0800
Subject: [PATCH 732/950] selftests/bpf: Fix tx_prog_fd values in test_sockmap

The values of tx_prog_fd in run_options() should not be 0, so set it as -1
in else branch, and test it using "if (tx_prog_fd > 0)" condition, not
"if (tx_prog_fd)" or "if (tx_prog_fd >= 0)".

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: Jakub Sitnicki <jakub@cloudflare.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/08b20ffc544324d40939efeae93800772a91a58e.1716446893.git.tanggeliang@kylinos.cn
---
 tools/testing/selftests/bpf/test_sockmap.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index ddc6a9cef36f9..892a690c4e7b4 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -1027,9 +1027,9 @@ run:
 	else if (txmsg_drop)
 		tx_prog_fd = prog_fd[8];
 	else
-		tx_prog_fd = 0;
+		tx_prog_fd = -1;
 
-	if (tx_prog_fd) {
+	if (tx_prog_fd > 0) {
 		int redir_fd, i = 0;
 
 		err = bpf_prog_attach(tx_prog_fd,
@@ -1285,7 +1285,7 @@ out:
 	bpf_prog_detach2(prog_fd[0], map_fd[8], BPF_SK_SKB_STREAM_PARSER);
 	bpf_prog_detach2(prog_fd[2], map_fd[8], BPF_SK_SKB_STREAM_VERDICT);
 
-	if (tx_prog_fd >= 0)
+	if (tx_prog_fd > 0)
 		bpf_prog_detach2(tx_prog_fd, map_fd[1], BPF_SK_MSG_VERDICT);
 
 	for (i = 0; i < 8; i++) {
-- 
GitLab


From a9f0ea175948c21640ae1cc145e679db7fc45fa6 Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Thu, 23 May 2024 14:49:58 +0800
Subject: [PATCH 733/950] selftests/bpf: Drop duplicate definition of i in
 test_sockmap

There's already a definition of i in run_options() at the beginning, no
need to define a new one in "if (tx_prog_fd > 0)" block.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: Jakub Sitnicki <jakub@cloudflare.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/8d690682330a59361562bca75d6903253d16f312.1716446893.git.tanggeliang@kylinos.cn
---
 tools/testing/selftests/bpf/test_sockmap.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index 892a690c4e7b4..6d724fea59fbf 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -1030,7 +1030,7 @@ run:
 		tx_prog_fd = -1;
 
 	if (tx_prog_fd > 0) {
-		int redir_fd, i = 0;
+		int redir_fd;
 
 		err = bpf_prog_attach(tx_prog_fd,
 				      map_fd[1], BPF_SK_MSG_VERDICT, 0);
@@ -1041,6 +1041,7 @@ run:
 			goto out;
 		}
 
+		i = 0;
 		err = bpf_map_update_elem(map_fd[1], &i, &c1, BPF_ANY);
 		if (err) {
 			fprintf(stderr,
-- 
GitLab


From 3f32a115f61d31049e3e91d469bca849f712a979 Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Thu, 23 May 2024 14:49:59 +0800
Subject: [PATCH 734/950] selftests/bpf: Use bpf_link attachments in
 test_sockmap

Switch attachments to bpf_link using bpf_program__attach_sockmap() instead
of bpf_prog_attach().

This patch adds a new array progs[] to replace prog_fd[] array, set in
populate_progs() for each program in bpf object.

And another new array links[] to save the attached bpf_link. It is
initalized as NULL in populate_progs, set as the return valuses of
bpf_program__attach_sockmap(), and detached by bpf_link__detach().

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: Jakub Sitnicki <jakub@cloudflare.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/32cf8376a810e2e9c719f8e4cfb97132ed2d1f9c.1716446893.git.tanggeliang@kylinos.cn
---
 tools/testing/selftests/bpf/test_sockmap.c | 59 ++++++++++++----------
 1 file changed, 31 insertions(+), 28 deletions(-)

diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index 6d724fea59fbf..81e7a57c727c4 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -64,6 +64,8 @@ int failed;
 int map_fd[9];
 struct bpf_map *maps[9];
 int prog_fd[9];
+struct bpf_program *progs[9];
+struct bpf_link *links[9];
 
 int txmsg_pass;
 int txmsg_redir;
@@ -960,43 +962,39 @@ static int run_options(struct sockmap_options *options, int cg_fd,  int test)
 
 	/* Attach programs to sockmap */
 	if (!txmsg_omit_skb_parser) {
-		err = bpf_prog_attach(prog_fd[0], map_fd[0],
-				      BPF_SK_SKB_STREAM_PARSER, 0);
-		if (err) {
+		links[0] = bpf_program__attach_sockmap(progs[0], map_fd[0]);
+		if (!links[0]) {
 			fprintf(stderr,
-				"ERROR: bpf_prog_attach (sockmap %i->%i): %d (%s)\n",
-				prog_fd[0], map_fd[0], err, strerror(errno));
-			return err;
+				"ERROR: bpf_program__attach_sockmap (sockmap %i->%i): (%s)\n",
+				bpf_program__fd(progs[0]), map_fd[0], strerror(errno));
+			return -1;
 		}
 	}
 
-	err = bpf_prog_attach(prog_fd[1], map_fd[0],
-				BPF_SK_SKB_STREAM_VERDICT, 0);
-	if (err) {
-		fprintf(stderr, "ERROR: bpf_prog_attach (sockmap): %d (%s)\n",
-			err, strerror(errno));
-		return err;
+	links[1] = bpf_program__attach_sockmap(progs[1], map_fd[0]);
+	if (!links[1]) {
+		fprintf(stderr, "ERROR: bpf_program__attach_sockmap (sockmap): (%s)\n",
+			strerror(errno));
+		return -1;
 	}
 
 	/* Attach programs to TLS sockmap */
 	if (txmsg_ktls_skb) {
 		if (!txmsg_omit_skb_parser) {
-			err = bpf_prog_attach(prog_fd[0], map_fd[8],
-					      BPF_SK_SKB_STREAM_PARSER, 0);
-			if (err) {
+			links[2] = bpf_program__attach_sockmap(progs[0], map_fd[8]);
+			if (!links[2]) {
 				fprintf(stderr,
-					"ERROR: bpf_prog_attach (TLS sockmap %i->%i): %d (%s)\n",
-					prog_fd[0], map_fd[8], err, strerror(errno));
-				return err;
+					"ERROR: bpf_program__attach_sockmap (TLS sockmap %i->%i): (%s)\n",
+					bpf_program__fd(progs[0]), map_fd[8], strerror(errno));
+				return -1;
 			}
 		}
 
-		err = bpf_prog_attach(prog_fd[2], map_fd[8],
-				      BPF_SK_SKB_STREAM_VERDICT, 0);
-		if (err) {
-			fprintf(stderr, "ERROR: bpf_prog_attach (TLS sockmap): %d (%s)\n",
-				err, strerror(errno));
-			return err;
+		links[3] = bpf_program__attach_sockmap(progs[2], map_fd[8]);
+		if (!links[3]) {
+			fprintf(stderr, "ERROR: bpf_program__attach_sockmap (TLS sockmap): (%s)\n",
+				strerror(errno));
+			return -1;
 		}
 	}
 
@@ -1281,10 +1279,11 @@ run:
 out:
 	/* Detatch and zero all the maps */
 	bpf_prog_detach2(prog_fd[3], cg_fd, BPF_CGROUP_SOCK_OPS);
-	bpf_prog_detach2(prog_fd[0], map_fd[0], BPF_SK_SKB_STREAM_PARSER);
-	bpf_prog_detach2(prog_fd[1], map_fd[0], BPF_SK_SKB_STREAM_VERDICT);
-	bpf_prog_detach2(prog_fd[0], map_fd[8], BPF_SK_SKB_STREAM_PARSER);
-	bpf_prog_detach2(prog_fd[2], map_fd[8], BPF_SK_SKB_STREAM_VERDICT);
+
+	for (i = 0; i < ARRAY_SIZE(links); i++) {
+		if (links[i])
+			bpf_link__detach(links[i]);
+	}
 
 	if (tx_prog_fd > 0)
 		bpf_prog_detach2(tx_prog_fd, map_fd[1], BPF_SK_MSG_VERDICT);
@@ -1805,6 +1804,7 @@ static int populate_progs(char *bpf_file)
 	i = bpf_object__load(obj);
 	i = 0;
 	bpf_object__for_each_program(prog, obj) {
+		progs[i] = prog;
 		prog_fd[i] = bpf_program__fd(prog);
 		i++;
 	}
@@ -1819,6 +1819,9 @@ static int populate_progs(char *bpf_file)
 		}
 	}
 
+	for (i = 0; i < ARRAY_SIZE(links); i++)
+		links[i] = NULL;
+
 	return 0;
 }
 
-- 
GitLab


From 24bb90a42633ea47256d4f13289dd3181236e028 Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Thu, 23 May 2024 14:50:00 +0800
Subject: [PATCH 735/950] selftests/bpf: Replace tx_prog_fd with tx_prog in
 test_sockmap

bpf_program__attach_sockmap() needs to take a parameter of type bpf_program
instead of an fd, so tx_prog_fd becomes useless. This patch uses a pointer
tx_prog to point to an item in progs[] array.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: Jakub Sitnicki <jakub@cloudflare.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/23b37f932c547dd1ebfe154bbc0b0e957be21ee6.1716446893.git.tanggeliang@kylinos.cn
---
 tools/testing/selftests/bpf/test_sockmap.c | 30 ++++++++++------------
 1 file changed, 14 insertions(+), 16 deletions(-)

diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index 81e7a57c727c4..c185c4242abb5 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -954,7 +954,8 @@ enum {
 
 static int run_options(struct sockmap_options *options, int cg_fd,  int test)
 {
-	int i, key, next_key, err, tx_prog_fd = -1, zero = 0;
+	int i, key, next_key, err, zero = 0;
+	struct bpf_program *tx_prog;
 
 	/* If base test skip BPF setup */
 	if (test == BASE || test == BASE_SENDPAGE)
@@ -1015,27 +1016,27 @@ run:
 
 	/* Attach txmsg program to sockmap */
 	if (txmsg_pass)
-		tx_prog_fd = prog_fd[4];
+		tx_prog = progs[4];
 	else if (txmsg_redir)
-		tx_prog_fd = prog_fd[5];
+		tx_prog = progs[5];
 	else if (txmsg_apply)
-		tx_prog_fd = prog_fd[6];
+		tx_prog = progs[6];
 	else if (txmsg_cork)
-		tx_prog_fd = prog_fd[7];
+		tx_prog = progs[7];
 	else if (txmsg_drop)
-		tx_prog_fd = prog_fd[8];
+		tx_prog = progs[8];
 	else
-		tx_prog_fd = -1;
+		tx_prog = NULL;
 
-	if (tx_prog_fd > 0) {
+	if (tx_prog) {
 		int redir_fd;
 
-		err = bpf_prog_attach(tx_prog_fd,
-				      map_fd[1], BPF_SK_MSG_VERDICT, 0);
-		if (err) {
+		links[4] = bpf_program__attach_sockmap(tx_prog, map_fd[1]);
+		if (!links[4]) {
 			fprintf(stderr,
-				"ERROR: bpf_prog_attach (txmsg): %d (%s)\n",
-				err, strerror(errno));
+				"ERROR: bpf_program__attach_sockmap (txmsg): (%s)\n",
+				strerror(errno));
+			err = -1;
 			goto out;
 		}
 
@@ -1285,9 +1286,6 @@ out:
 			bpf_link__detach(links[i]);
 	}
 
-	if (tx_prog_fd > 0)
-		bpf_prog_detach2(tx_prog_fd, map_fd[1], BPF_SK_MSG_VERDICT);
-
 	for (i = 0; i < 8; i++) {
 		key = next_key = 0;
 		bpf_map_update_elem(map_fd[i], &key, &zero, BPF_ANY);
-- 
GitLab


From 467a0c79b5514d7301ae679770380679a8e32668 Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Thu, 23 May 2024 14:50:01 +0800
Subject: [PATCH 736/950] selftests/bpf: Drop prog_fd array in test_sockmap

The program fds can be got by using bpf_program__fd(progs[]), then
prog_fd becomes useless. This patch drops it.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: Jakub Sitnicki <jakub@cloudflare.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/9a6335e4d8dbab23c0d8906074457ceddd61e74b.1716446893.git.tanggeliang@kylinos.cn
---
 tools/testing/selftests/bpf/test_sockmap.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index c185c4242abb5..64b38a1a1b603 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -63,7 +63,6 @@ int passed;
 int failed;
 int map_fd[9];
 struct bpf_map *maps[9];
-int prog_fd[9];
 struct bpf_program *progs[9];
 struct bpf_link *links[9];
 
@@ -1000,7 +999,7 @@ static int run_options(struct sockmap_options *options, int cg_fd,  int test)
 	}
 
 	/* Attach to cgroups */
-	err = bpf_prog_attach(prog_fd[3], cg_fd, BPF_CGROUP_SOCK_OPS, 0);
+	err = bpf_prog_attach(bpf_program__fd(progs[3]), cg_fd, BPF_CGROUP_SOCK_OPS, 0);
 	if (err) {
 		fprintf(stderr, "ERROR: bpf_prog_attach (groups): %d (%s)\n",
 			err, strerror(errno));
@@ -1279,7 +1278,7 @@ run:
 		fprintf(stderr, "unknown test\n");
 out:
 	/* Detatch and zero all the maps */
-	bpf_prog_detach2(prog_fd[3], cg_fd, BPF_CGROUP_SOCK_OPS);
+	bpf_prog_detach2(bpf_program__fd(progs[3]), cg_fd, BPF_CGROUP_SOCK_OPS);
 
 	for (i = 0; i < ARRAY_SIZE(links); i++) {
 		if (links[i])
@@ -1803,7 +1802,6 @@ static int populate_progs(char *bpf_file)
 	i = 0;
 	bpf_object__for_each_program(prog, obj) {
 		progs[i] = prog;
-		prog_fd[i] = bpf_program__fd(prog);
 		i++;
 	}
 
-- 
GitLab


From dcb681b659f2a0a546752730c9daa92dc6120d52 Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Thu, 23 May 2024 14:50:02 +0800
Subject: [PATCH 737/950] selftests/bpf: Fix size of map_fd in test_sockmap

The array size of map_fd[] is 9, not 8. This patch changes it as a more
general form: ARRAY_SIZE(map_fd).

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: Jakub Sitnicki <jakub@cloudflare.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/0972529ee01ebf8a8fd2b310bdec90831c94be77.1716446893.git.tanggeliang@kylinos.cn
---
 tools/testing/selftests/bpf/test_sockmap.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index 64b38a1a1b603..e29f8203bd4f1 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -1285,7 +1285,7 @@ out:
 			bpf_link__detach(links[i]);
 	}
 
-	for (i = 0; i < 8; i++) {
+	for (i = 0; i < ARRAY_SIZE(map_fd); i++) {
 		key = next_key = 0;
 		bpf_map_update_elem(map_fd[i], &key, &zero, BPF_ANY);
 		while (bpf_map_get_next_key(map_fd[i], &key, &next_key) == 0) {
-- 
GitLab


From de1b5ea789dc28066cc8dc634b6825bd6148f38b Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Thu, 23 May 2024 14:50:03 +0800
Subject: [PATCH 738/950] selftests/bpf: Check length of recv in test_sockmap

The value of recv in msg_loop may be negative, like EWOULDBLOCK, so it's
necessary to check if it is positive before accumulating it to bytes_recvd.

Fixes: 16962b2404ac ("bpf: sockmap, add selftests")
Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: Jakub Sitnicki <jakub@cloudflare.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/5172563f7c7b2a2e953cef02e89fc34664a7b190.1716446893.git.tanggeliang@kylinos.cn
---
 tools/testing/selftests/bpf/test_sockmap.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index e29f8203bd4f1..9cba4ec844a53 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -681,7 +681,8 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 				}
 			}
 
-			s->bytes_recvd += recv;
+			if (recv > 0)
+				s->bytes_recvd += recv;
 
 			if (opt->check_recved_len && s->bytes_recvd > total_bytes) {
 				errno = EMSGSIZE;
-- 
GitLab


From 49784c7979321c49a8055f5c588d24c34a8c55fc Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Thu, 23 May 2024 14:50:04 +0800
Subject: [PATCH 739/950] selftests/bpf: Drop duplicate bpf_map_lookup_elem in
 test_sockmap

bpf_map_lookup_elem is invoked in bpf_prog3() already, no need to invoke
it again. This patch drops it.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: Jakub Sitnicki <jakub@cloudflare.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/ea8458462b876ee445173e3effb535fd126137ed.1716446893.git.tanggeliang@kylinos.cn
---
 tools/testing/selftests/bpf/progs/test_sockmap_kern.h | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_kern.h b/tools/testing/selftests/bpf/progs/test_sockmap_kern.h
index 3dff0813730b4..f48f85f1bd702 100644
--- a/tools/testing/selftests/bpf/progs/test_sockmap_kern.h
+++ b/tools/testing/selftests/bpf/progs/test_sockmap_kern.h
@@ -177,9 +177,6 @@ int bpf_prog3(struct __sk_buff *skb)
 		return bpf_sk_redirect_hash(skb, &tls_sock_map, &ret, flags);
 #endif
 	}
-	f = bpf_map_lookup_elem(&sock_skb_opts, &one);
-	if (f && *f)
-		ret = SK_DROP;
 	err = bpf_skb_adjust_room(skb, 4, 0, 0);
 	if (err)
 		return SK_DROP;
-- 
GitLab


From 4933b066fefbee4f1d2d708de53c4ab7f09026ad Mon Sep 17 00:00:00 2001
From: Douglas Anderson <dianders@chromium.org>
Date: Thu, 30 May 2024 16:43:08 -0700
Subject: [PATCH 740/950] r8152: If inaccessible at resume time, issue a reset

If we happened to get a USB transfer error during the transition to
suspend then the usb_queue_reset_device() that r8152_control_msg()
calls will get dropped on the floor. This is because
usb_lock_device_for_reset() (which usb_queue_reset_device() uses)
silently fails if it's called when a device is suspended or if too
much time passes.

Let's resolve this by resetting the device ourselves in r8152's
resume() function.

NOTE: due to timing, it's _possible_ that we could end up with two USB
resets: the one queued previously and the one called from the resume()
patch. This didn't happen in test cases I ran, though it's conceivably
possible. We can't easily know if this happened since
usb_queue_reset_device() can just silently drop the reset request. In
any case, it's not expected that this is a problem since the two
resets can't run at the same time (because of the device lock) and it
should be OK to reset the device twice. If somehow the double-reset
causes problems we could prevent resets from being queued up while
suspend is running.

Signed-off-by: Douglas Anderson <dianders@chromium.org>
Acked-by: Hayes Wang <hayeswang@realtek.com>
Link: https://lore.kernel.org/r/66590f22.170a0220.8b5ad.1750@mx.google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/r8152.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 19df1cd9f0724..6a3f4b2114eef 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -8554,6 +8554,19 @@ static int rtl8152_system_resume(struct r8152 *tp)
 		usb_submit_urb(tp->intr_urb, GFP_NOIO);
 	}
 
+	/* If the device is RTL8152_INACCESSIBLE here then we should do a
+	 * reset. This is important because the usb_lock_device_for_reset()
+	 * that happens as a result of usb_queue_reset_device() will silently
+	 * fail if the device was suspended or if too much time passed.
+	 *
+	 * NOTE: The device is locked here so we can directly do the reset.
+	 * We don't need usb_lock_device_for_reset() because that's just a
+	 * wrapper over device_lock() and device_resume() (which calls us)
+	 * does that for us.
+	 */
+	if (test_bit(RTL8152_INACCESSIBLE, &tp->flags))
+		usb_reset_device(tp->udev);
+
 	return 0;
 }
 
-- 
GitLab


From 8c1d92a740c002f36a919a55689d0ef83b61fd1c Mon Sep 17 00:00:00 2001
From: Douglas Anderson <dianders@chromium.org>
Date: Thu, 30 May 2024 16:43:09 -0700
Subject: [PATCH 741/950] r8152: Wake up the system if the we need a reset

If we get to the end of the r8152's suspend() routine and we find that
the USB device is INACCESSIBLE then it means that some of our
preparation for suspend didn't take place. We need a USB reset to get
ourselves back in a consistent state so we can try again and that
can't happen during system suspend. Call pm_wakeup_event() to wake the
system up in this case.

Signed-off-by: Douglas Anderson <dianders@chromium.org>
Acked-by: Hayes Wang <hayeswang@realtek.com>
Link: https://lore.kernel.org/r/66590f25.170a0220.8b5ad.1752@mx.google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/r8152.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 6a3f4b2114eef..09fe70bc45d48 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -8647,6 +8647,13 @@ static int rtl8152_system_suspend(struct r8152 *tp)
 		tasklet_enable(&tp->tx_tl);
 	}
 
+	/* If we're inaccessible here then some of the work that we did to
+	 * get the adapter ready for suspend didn't work. Queue up a wakeup
+	 * event so we can try again.
+	 */
+	if (test_bit(RTL8152_INACCESSIBLE, &tp->flags))
+		pm_wakeup_event(&tp->udev->dev, 0);
+
 	return 0;
 }
 
-- 
GitLab


From ffbe335b8d471f79b259e950cb20999700670456 Mon Sep 17 00:00:00 2001
From: Matthias Stocker <mstocker@barracuda.com>
Date: Fri, 31 May 2024 12:37:11 +0200
Subject: [PATCH 742/950] vmxnet3: disable rx data ring on dma allocation
 failure

When vmxnet3_rq_create() fails to allocate memory for rq->data_ring.base,
the subsequent call to vmxnet3_rq_destroy_all_rxdataring does not reset
rq->data_ring.desc_size for the data ring that failed, which presumably
causes the hypervisor to reference it on packet reception.

To fix this bug, rq->data_ring.desc_size needs to be set to 0 to tell
the hypervisor to disable this feature.

[   95.436876] kernel BUG at net/core/skbuff.c:207!
[   95.439074] invalid opcode: 0000 [#1] PREEMPT SMP NOPTI
[   95.440411] CPU: 7 PID: 0 Comm: swapper/7 Not tainted 6.9.3-dirty #1
[   95.441558] Hardware name: VMware, Inc. VMware Virtual
Platform/440BX Desktop Reference Platform, BIOS 6.00 12/12/2018
[   95.443481] RIP: 0010:skb_panic+0x4d/0x4f
[   95.444404] Code: 4f 70 50 8b 87 c0 00 00 00 50 8b 87 bc 00 00 00 50
ff b7 d0 00 00 00 4c 8b 8f c8 00 00 00 48 c7 c7 68 e8 be 9f e8 63 58 f9
ff <0f> 0b 48 8b 14 24 48 c7 c1 d0 73 65 9f e8 a1 ff ff ff 48 8b 14 24
[   95.447684] RSP: 0018:ffffa13340274dd0 EFLAGS: 00010246
[   95.448762] RAX: 0000000000000089 RBX: ffff8fbbc72b02d0 RCX: 000000000000083f
[   95.450148] RDX: 0000000000000000 RSI: 00000000000000f6 RDI: 000000000000083f
[   95.451520] RBP: 000000000000002d R08: 0000000000000000 R09: ffffa13340274c60
[   95.452886] R10: ffffffffa04ed468 R11: 0000000000000002 R12: 0000000000000000
[   95.454293] R13: ffff8fbbdab3c2d0 R14: ffff8fbbdbd829e0 R15: ffff8fbbdbd809e0
[   95.455682] FS:  0000000000000000(0000) GS:ffff8fbeefd80000(0000) knlGS:0000000000000000
[   95.457178] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   95.458340] CR2: 00007fd0d1f650c8 CR3: 0000000115f28000 CR4: 00000000000406f0
[   95.459791] Call Trace:
[   95.460515]  <IRQ>
[   95.461180]  ? __die_body.cold+0x19/0x27
[   95.462150]  ? die+0x2e/0x50
[   95.462976]  ? do_trap+0xca/0x110
[   95.463973]  ? do_error_trap+0x6a/0x90
[   95.464966]  ? skb_panic+0x4d/0x4f
[   95.465901]  ? exc_invalid_op+0x50/0x70
[   95.466849]  ? skb_panic+0x4d/0x4f
[   95.467718]  ? asm_exc_invalid_op+0x1a/0x20
[   95.468758]  ? skb_panic+0x4d/0x4f
[   95.469655]  skb_put.cold+0x10/0x10
[   95.470573]  vmxnet3_rq_rx_complete+0x862/0x11e0 [vmxnet3]
[   95.471853]  vmxnet3_poll_rx_only+0x36/0xb0 [vmxnet3]
[   95.473185]  __napi_poll+0x2b/0x160
[   95.474145]  net_rx_action+0x2c6/0x3b0
[   95.475115]  handle_softirqs+0xe7/0x2a0
[   95.476122]  __irq_exit_rcu+0x97/0xb0
[   95.477109]  common_interrupt+0x85/0xa0
[   95.478102]  </IRQ>
[   95.478846]  <TASK>
[   95.479603]  asm_common_interrupt+0x26/0x40
[   95.480657] RIP: 0010:pv_native_safe_halt+0xf/0x20
[   95.481801] Code: 22 d7 e9 54 87 01 00 0f 1f 40 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 f3 0f 1e fa eb 07 0f 00 2d 93 ba 3b 00 fb f4 <e9> 2c 87 01 00 66 66 2e 0f 1f 84 00 00 00 00 00 90 90 90 90 90 90
[   95.485563] RSP: 0018:ffffa133400ffe58 EFLAGS: 00000246
[   95.486882] RAX: 0000000000004000 RBX: ffff8fbbc1d14064 RCX: 0000000000000000
[   95.488477] RDX: ffff8fbeefd80000 RSI: ffff8fbbc1d14000 RDI: 0000000000000001
[   95.490067] RBP: ffff8fbbc1d14064 R08: ffffffffa0652260 R09: 00000000000010d3
[   95.491683] R10: 0000000000000018 R11: ffff8fbeefdb4764 R12: ffffffffa0652260
[   95.493389] R13: ffffffffa06522e0 R14: 0000000000000001 R15: 0000000000000000
[   95.495035]  acpi_safe_halt+0x14/0x20
[   95.496127]  acpi_idle_do_entry+0x2f/0x50
[   95.497221]  acpi_idle_enter+0x7f/0xd0
[   95.498272]  cpuidle_enter_state+0x81/0x420
[   95.499375]  cpuidle_enter+0x2d/0x40
[   95.500400]  do_idle+0x1e5/0x240
[   95.501385]  cpu_startup_entry+0x29/0x30
[   95.502422]  start_secondary+0x11c/0x140
[   95.503454]  common_startup_64+0x13e/0x141
[   95.504466]  </TASK>
[   95.505197] Modules linked in: nft_fib_inet nft_fib_ipv4
nft_fib_ipv6 nft_fib nft_reject_inet nf_reject_ipv4 nf_reject_ipv6
nft_reject nft_ct nft_chain_nat nf_nat nf_conntrack nf_defrag_ipv6
nf_defrag_ipv4 rfkill ip_set nf_tables vsock_loopback
vmw_vsock_virtio_transport_common qrtr vmw_vsock_vmci_transport vsock
sunrpc binfmt_misc pktcdvd vmw_balloon pcspkr vmw_vmci i2c_piix4 joydev
loop dm_multipath nfnetlink zram crct10dif_pclmul crc32_pclmul vmwgfx
crc32c_intel polyval_clmulni polyval_generic ghash_clmulni_intel
sha512_ssse3 sha256_ssse3 vmxnet3 sha1_ssse3 drm_ttm_helper vmw_pvscsi
ttm ata_generic pata_acpi serio_raw scsi_dh_rdac scsi_dh_emc
scsi_dh_alua ip6_tables ip_tables fuse
[   95.516536] ---[ end trace 0000000000000000 ]---

Fixes: 6f4833383e85 ("net: vmxnet3: Fix NULL pointer dereference in vmxnet3_rq_rx_complete()")
Signed-off-by: Matthias Stocker <mstocker@barracuda.com>
Reviewed-by: Subbaraya Sundeep <sbhatta@marvell.com>
Reviewed-by: Ronak Doshi <ronak.doshi@broadcom.com>
Link: https://lore.kernel.org/r/20240531103711.101961-1-mstocker@barracuda.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/vmxnet3/vmxnet3_drv.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index 89ca6e75fcc6b..63822d454c00c 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -2034,8 +2034,8 @@ vmxnet3_rq_destroy_all_rxdataring(struct vmxnet3_adapter *adapter)
 					  rq->data_ring.base,
 					  rq->data_ring.basePA);
 			rq->data_ring.base = NULL;
-			rq->data_ring.desc_size = 0;
 		}
+		rq->data_ring.desc_size = 0;
 	}
 }
 
-- 
GitLab


From 2fe40483ec257de2a0d819ef88e3e76c7e261319 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 31 May 2024 13:26:32 +0000
Subject: [PATCH 743/950] ipv6: ioam: block BH from ioam6_output()

As explained in commit 1378817486d6 ("tipc: block BH
before using dst_cache"), net/core/dst_cache.c
helpers need to be called with BH disabled.

Disabling preemption in ioam6_output() is not good enough,
because ioam6_output() is called from process context,
lwtunnel_output() only uses rcu_read_lock().

We might be interrupted by a softirq, re-enter ioam6_output()
and corrupt dst_cache data structures.

Fix the race by using local_bh_disable() instead of
preempt_disable().

Fixes: 8cb3bf8bff3c ("ipv6: ioam: Add support for the ip6ip6 encapsulation")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Justin Iurman <justin.iurman@uliege.be>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Link: https://lore.kernel.org/r/20240531132636.2637995-2-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/ioam6_iptunnel.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/ioam6_iptunnel.c b/net/ipv6/ioam6_iptunnel.c
index 7563f8c6aa87c..bf7120ecea1eb 100644
--- a/net/ipv6/ioam6_iptunnel.c
+++ b/net/ipv6/ioam6_iptunnel.c
@@ -351,9 +351,9 @@ do_encap:
 		goto drop;
 
 	if (!ipv6_addr_equal(&orig_daddr, &ipv6_hdr(skb)->daddr)) {
-		preempt_disable();
+		local_bh_disable();
 		dst = dst_cache_get(&ilwt->cache);
-		preempt_enable();
+		local_bh_enable();
 
 		if (unlikely(!dst)) {
 			struct ipv6hdr *hdr = ipv6_hdr(skb);
@@ -373,9 +373,9 @@ do_encap:
 				goto drop;
 			}
 
-			preempt_disable();
+			local_bh_disable();
 			dst_cache_set_ip6(&ilwt->cache, dst, &fl6.saddr);
-			preempt_enable();
+			local_bh_enable();
 		}
 
 		skb_dst_drop(skb);
-- 
GitLab


From db0090c6eb12c31246438b7fe2a8f1b833e7a653 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 31 May 2024 13:26:33 +0000
Subject: [PATCH 744/950] net: ipv6: rpl_iptunnel: block BH in rpl_output() and
 rpl_input()

As explained in commit 1378817486d6 ("tipc: block BH
before using dst_cache"), net/core/dst_cache.c
helpers need to be called with BH disabled.

Disabling preemption in rpl_output() is not good enough,
because rpl_output() is called from process context,
lwtunnel_output() only uses rcu_read_lock().

We might be interrupted by a softirq, re-enter rpl_output()
and corrupt dst_cache data structures.

Fix the race by using local_bh_disable() instead of
preempt_disable().

Apply a similar change in rpl_input().

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Alexander Aring <aahringo@redhat.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Link: https://lore.kernel.org/r/20240531132636.2637995-3-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/rpl_iptunnel.c | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

diff --git a/net/ipv6/rpl_iptunnel.c b/net/ipv6/rpl_iptunnel.c
index a013b92cbb860..2c83b7586422d 100644
--- a/net/ipv6/rpl_iptunnel.c
+++ b/net/ipv6/rpl_iptunnel.c
@@ -212,9 +212,9 @@ static int rpl_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 	if (unlikely(err))
 		goto drop;
 
-	preempt_disable();
+	local_bh_disable();
 	dst = dst_cache_get(&rlwt->cache);
-	preempt_enable();
+	local_bh_enable();
 
 	if (unlikely(!dst)) {
 		struct ipv6hdr *hdr = ipv6_hdr(skb);
@@ -234,9 +234,9 @@ static int rpl_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 			goto drop;
 		}
 
-		preempt_disable();
+		local_bh_disable();
 		dst_cache_set_ip6(&rlwt->cache, dst, &fl6.saddr);
-		preempt_enable();
+		local_bh_enable();
 	}
 
 	skb_dst_drop(skb);
@@ -268,23 +268,21 @@ static int rpl_input(struct sk_buff *skb)
 		return err;
 	}
 
-	preempt_disable();
+	local_bh_disable();
 	dst = dst_cache_get(&rlwt->cache);
-	preempt_enable();
 
 	if (!dst) {
 		ip6_route_input(skb);
 		dst = skb_dst(skb);
 		if (!dst->error) {
-			preempt_disable();
 			dst_cache_set_ip6(&rlwt->cache, dst,
 					  &ipv6_hdr(skb)->saddr);
-			preempt_enable();
 		}
 	} else {
 		skb_dst_drop(skb);
 		skb_dst_set(skb, dst);
 	}
+	local_bh_enable();
 
 	err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev));
 	if (unlikely(err))
-- 
GitLab


From c0b98ac1cc104f48763cdb27b1e9ac25fd81fc90 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 31 May 2024 13:26:34 +0000
Subject: [PATCH 745/950] ipv6: sr: block BH in seg6_output_core() and
 seg6_input_core()

As explained in commit 1378817486d6 ("tipc: block BH
before using dst_cache"), net/core/dst_cache.c
helpers need to be called with BH disabled.

Disabling preemption in seg6_output_core() is not good enough,
because seg6_output_core() is called from process context,
lwtunnel_output() only uses rcu_read_lock().

We might be interrupted by a softirq, re-enter seg6_output_core()
and corrupt dst_cache data structures.

Fix the race by using local_bh_disable() instead of
preempt_disable().

Apply a similar change in seg6_input_core().

Fixes: fa79581ea66c ("ipv6: sr: fix several BUGs when preemption is enabled")
Fixes: 6c8702c60b88 ("ipv6: sr: add support for SRH encapsulation and injection with lwtunnels")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: David Lebrun <dlebrun@google.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Link: https://lore.kernel.org/r/20240531132636.2637995-4-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/seg6_iptunnel.c | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index a75df2ec8db0d..098632adc9b5a 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -464,23 +464,21 @@ static int seg6_input_core(struct net *net, struct sock *sk,
 
 	slwt = seg6_lwt_lwtunnel(orig_dst->lwtstate);
 
-	preempt_disable();
+	local_bh_disable();
 	dst = dst_cache_get(&slwt->cache);
-	preempt_enable();
 
 	if (!dst) {
 		ip6_route_input(skb);
 		dst = skb_dst(skb);
 		if (!dst->error) {
-			preempt_disable();
 			dst_cache_set_ip6(&slwt->cache, dst,
 					  &ipv6_hdr(skb)->saddr);
-			preempt_enable();
 		}
 	} else {
 		skb_dst_drop(skb);
 		skb_dst_set(skb, dst);
 	}
+	local_bh_enable();
 
 	err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev));
 	if (unlikely(err))
@@ -536,9 +534,9 @@ static int seg6_output_core(struct net *net, struct sock *sk,
 
 	slwt = seg6_lwt_lwtunnel(orig_dst->lwtstate);
 
-	preempt_disable();
+	local_bh_disable();
 	dst = dst_cache_get(&slwt->cache);
-	preempt_enable();
+	local_bh_enable();
 
 	if (unlikely(!dst)) {
 		struct ipv6hdr *hdr = ipv6_hdr(skb);
@@ -558,9 +556,9 @@ static int seg6_output_core(struct net *net, struct sock *sk,
 			goto drop;
 		}
 
-		preempt_disable();
+		local_bh_disable();
 		dst_cache_set_ip6(&slwt->cache, dst, &fl6.saddr);
-		preempt_enable();
+		local_bh_enable();
 	}
 
 	skb_dst_drop(skb);
-- 
GitLab


From cf28ff8e4c02e1ffa850755288ac954b6ff0db8c Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 31 May 2024 13:26:35 +0000
Subject: [PATCH 746/950] ila: block BH in ila_output()

As explained in commit 1378817486d6 ("tipc: block BH
before using dst_cache"), net/core/dst_cache.c
helpers need to be called with BH disabled.

ila_output() is called from lwtunnel_output()
possibly from process context, and under rcu_read_lock().

We might be interrupted by a softirq, re-enter ila_output()
and corrupt dst_cache data structures.

Fix the race by using local_bh_disable().

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Link: https://lore.kernel.org/r/20240531132636.2637995-5-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/ila/ila_lwt.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/ila/ila_lwt.c b/net/ipv6/ila/ila_lwt.c
index 0601bad798221..ff7e734e335b0 100644
--- a/net/ipv6/ila/ila_lwt.c
+++ b/net/ipv6/ila/ila_lwt.c
@@ -58,7 +58,9 @@ static int ila_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 		return orig_dst->lwtstate->orig_output(net, sk, skb);
 	}
 
+	local_bh_disable();
 	dst = dst_cache_get(&ilwt->dst_cache);
+	local_bh_enable();
 	if (unlikely(!dst)) {
 		struct ipv6hdr *ip6h = ipv6_hdr(skb);
 		struct flowi6 fl6;
@@ -86,8 +88,11 @@ static int ila_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 			goto drop;
 		}
 
-		if (ilwt->connected)
+		if (ilwt->connected) {
+			local_bh_disable();
 			dst_cache_set_ip6(&ilwt->dst_cache, dst, &fl6.saddr);
+			local_bh_enable();
+		}
 	}
 
 	skb_dst_set(skb, dst);
-- 
GitLab


From 2fe6fb36c781b50482b1c3323fb526bc07d1af59 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 31 May 2024 13:26:36 +0000
Subject: [PATCH 747/950] net: dst_cache: add two DEBUG_NET warnings

After fixing four different bugs involving dst_cache
users, it might be worth adding a check about BH being
blocked by dst_cache callers.

DEBUG_NET_WARN_ON_ONCE(!in_softirq());

It is not fatal, if we missed valid case where no
BH deadlock is to be feared, we might change this.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Link: https://lore.kernel.org/r/20240531132636.2637995-6-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/dst_cache.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/core/dst_cache.c b/net/core/dst_cache.c
index 6a0482e676d37..70c634b9e7b02 100644
--- a/net/core/dst_cache.c
+++ b/net/core/dst_cache.c
@@ -27,6 +27,7 @@ struct dst_cache_pcpu {
 static void dst_cache_per_cpu_dst_set(struct dst_cache_pcpu *dst_cache,
 				      struct dst_entry *dst, u32 cookie)
 {
+	DEBUG_NET_WARN_ON_ONCE(!in_softirq());
 	dst_release(dst_cache->dst);
 	if (dst)
 		dst_hold(dst);
@@ -40,6 +41,7 @@ static struct dst_entry *dst_cache_per_cpu_get(struct dst_cache *dst_cache,
 {
 	struct dst_entry *dst;
 
+	DEBUG_NET_WARN_ON_ONCE(!in_softirq());
 	dst = idst->dst;
 	if (!dst)
 		goto fail;
-- 
GitLab


From c6cab01d7e20a028ffcee1e0a0b782332a16b5e6 Mon Sep 17 00:00:00 2001
From: Jeff Johnson <quic_jjohnson@quicinc.com>
Date: Fri, 31 May 2024 18:35:43 -0700
Subject: [PATCH 748/950] lib/test_rhashtable: add missing MODULE_DESCRIPTION()
 macro

make allmodconfig && make W=1 C=1 reports:
WARNING: modpost: missing MODULE_DESCRIPTION() in lib/test_rhashtable.o

Add the missing invocation of the MODULE_DESCRIPTION() macro.

Signed-off-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Link: https://lore.kernel.org/r/20240531-md-lib-test_rhashtable-v1-1-cd6d4138f1b6@quicinc.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 lib/test_rhashtable.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/lib/test_rhashtable.c b/lib/test_rhashtable.c
index 42b585208249c..c63db03ebb9dc 100644
--- a/lib/test_rhashtable.c
+++ b/lib/test_rhashtable.c
@@ -811,4 +811,5 @@ static void __exit test_rht_exit(void)
 module_init(test_rht_init);
 module_exit(test_rht_exit);
 
+MODULE_DESCRIPTION("Resizable, Scalable, Concurrent Hash Table test module");
 MODULE_LICENSE("GPL v2");
-- 
GitLab


From c95a3be45ad22ee8925d6d1ab531d5ba98216311 Mon Sep 17 00:00:00 2001
From: Kui-Feng Lee <thinker.li@gmail.com>
Date: Thu, 23 May 2024 10:41:54 -0700
Subject: [PATCH 749/950] bpf: Remove unnecessary checks on the offset of
 btf_field.

reg_find_field_offset() always return a btf_field with a matching offset
value. Checking the offset of the returned btf_field is unnecessary.

Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Kui-Feng Lee <thinker.li@gmail.com>
Link: https://lore.kernel.org/r/20240523174202.461236-2-thinker.li@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/verifier.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 77da1f438becc..57c0c255bf4c6 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -11640,7 +11640,7 @@ __process_kf_arg_ptr_to_graph_node(struct bpf_verifier_env *env,
 
 	node_off = reg->off + reg->var_off.value;
 	field = reg_find_field_offset(reg, node_off, node_field_type);
-	if (!field || field->offset != node_off) {
+	if (!field) {
 		verbose(env, "%s not found at offset=%u\n", node_type_name, node_off);
 		return -EINVAL;
 	}
-- 
GitLab


From 482f7133791e894b94a57ab3251e03d4c98ea42b Mon Sep 17 00:00:00 2001
From: Kui-Feng Lee <thinker.li@gmail.com>
Date: Thu, 23 May 2024 10:41:55 -0700
Subject: [PATCH 750/950] bpf: Remove unnecessary call to
 btf_field_type_size().

field->size has been initialized by bpf_parse_fields() with the value
returned by btf_field_type_size(). Use it instead of calling
btf_field_type_size() again.

Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Kui-Feng Lee <thinker.li@gmail.com>
Link: https://lore.kernel.org/r/20240523174202.461236-3-thinker.li@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/btf.c      | 2 +-
 kernel/bpf/verifier.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 821063660d9f9..226138bd139af 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -6693,7 +6693,7 @@ int btf_struct_access(struct bpf_verifier_log *log,
 		for (i = 0; i < rec->cnt; i++) {
 			struct btf_field *field = &rec->fields[i];
 			u32 offset = field->offset;
-			if (off < offset + btf_field_type_size(field->type) && offset < off + size) {
+			if (off < offset + field->size && offset < off + size) {
 				bpf_log(log,
 					"direct access to %s is disallowed\n",
 					btf_field_type_name(field->type));
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 57c0c255bf4c6..81a3d2ced78d5 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5448,7 +5448,7 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno,
 		 * this program. To check that [x1, x2) overlaps with [y1, y2),
 		 * it is sufficient to check x1 < y2 && y1 < x2.
 		 */
-		if (reg->smin_value + off < p + btf_field_type_size(field->type) &&
+		if (reg->smin_value + off < p + field->size &&
 		    p < reg->umax_value + off + size) {
 			switch (field->type) {
 			case BPF_KPTR_UNREF:
-- 
GitLab


From a7db0d4f872a869feb7c0201c0fa736c309192d5 Mon Sep 17 00:00:00 2001
From: Kui-Feng Lee <thinker.li@gmail.com>
Date: Thu, 23 May 2024 10:41:56 -0700
Subject: [PATCH 751/950] bpf: refactor btf_find_struct_field() and
 btf_find_datasec_var().

Move common code of the two functions to btf_find_field_one().

Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Kui-Feng Lee <thinker.li@gmail.com>
Link: https://lore.kernel.org/r/20240523174202.461236-4-thinker.li@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/btf.c | 180 +++++++++++++++++++++--------------------------
 1 file changed, 79 insertions(+), 101 deletions(-)

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 226138bd139af..2ce61c3a7e283 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -3494,72 +3494,95 @@ end:
 
 #undef field_mask_test_name
 
+static int btf_find_field_one(const struct btf *btf,
+			      const struct btf_type *var,
+			      const struct btf_type *var_type,
+			      int var_idx,
+			      u32 off, u32 expected_size,
+			      u32 field_mask, u32 *seen_mask,
+			      struct btf_field_info *info, int info_cnt)
+{
+	int ret, align, sz, field_type;
+	struct btf_field_info tmp;
+
+	field_type = btf_get_field_type(__btf_name_by_offset(btf, var_type->name_off),
+					field_mask, seen_mask, &align, &sz);
+	if (field_type == 0)
+		return 0;
+	if (field_type < 0)
+		return field_type;
+
+	if (expected_size && expected_size != sz)
+		return 0;
+	if (off % align)
+		return 0;
+
+	switch (field_type) {
+	case BPF_SPIN_LOCK:
+	case BPF_TIMER:
+	case BPF_WORKQUEUE:
+	case BPF_LIST_NODE:
+	case BPF_RB_NODE:
+	case BPF_REFCOUNT:
+		ret = btf_find_struct(btf, var_type, off, sz, field_type,
+				      info_cnt ? &info[0] : &tmp);
+		if (ret < 0)
+			return ret;
+		break;
+	case BPF_KPTR_UNREF:
+	case BPF_KPTR_REF:
+	case BPF_KPTR_PERCPU:
+		ret = btf_find_kptr(btf, var_type, off, sz,
+				    info_cnt ? &info[0] : &tmp);
+		if (ret < 0)
+			return ret;
+		break;
+	case BPF_LIST_HEAD:
+	case BPF_RB_ROOT:
+		ret = btf_find_graph_root(btf, var, var_type,
+					  var_idx, off, sz,
+					  info_cnt ? &info[0] : &tmp,
+					  field_type);
+		if (ret < 0)
+			return ret;
+		break;
+	default:
+		return -EFAULT;
+	}
+
+	if (ret == BTF_FIELD_IGNORE)
+		return 0;
+	if (!info_cnt)
+		return -E2BIG;
+
+	return 1;
+}
+
 static int btf_find_struct_field(const struct btf *btf,
 				 const struct btf_type *t, u32 field_mask,
 				 struct btf_field_info *info, int info_cnt)
 {
-	int ret, idx = 0, align, sz, field_type;
+	int ret, idx = 0;
 	const struct btf_member *member;
-	struct btf_field_info tmp;
 	u32 i, off, seen_mask = 0;
 
 	for_each_member(i, t, member) {
 		const struct btf_type *member_type = btf_type_by_id(btf,
 								    member->type);
 
-		field_type = btf_get_field_type(__btf_name_by_offset(btf, member_type->name_off),
-						field_mask, &seen_mask, &align, &sz);
-		if (field_type == 0)
-			continue;
-		if (field_type < 0)
-			return field_type;
-
 		off = __btf_member_bit_offset(t, member);
 		if (off % 8)
 			/* valid C code cannot generate such BTF */
 			return -EINVAL;
 		off /= 8;
-		if (off % align)
-			continue;
-
-		switch (field_type) {
-		case BPF_SPIN_LOCK:
-		case BPF_TIMER:
-		case BPF_WORKQUEUE:
-		case BPF_LIST_NODE:
-		case BPF_RB_NODE:
-		case BPF_REFCOUNT:
-			ret = btf_find_struct(btf, member_type, off, sz, field_type,
-					      idx < info_cnt ? &info[idx] : &tmp);
-			if (ret < 0)
-				return ret;
-			break;
-		case BPF_KPTR_UNREF:
-		case BPF_KPTR_REF:
-		case BPF_KPTR_PERCPU:
-			ret = btf_find_kptr(btf, member_type, off, sz,
-					    idx < info_cnt ? &info[idx] : &tmp);
-			if (ret < 0)
-				return ret;
-			break;
-		case BPF_LIST_HEAD:
-		case BPF_RB_ROOT:
-			ret = btf_find_graph_root(btf, t, member_type,
-						  i, off, sz,
-						  idx < info_cnt ? &info[idx] : &tmp,
-						  field_type);
-			if (ret < 0)
-				return ret;
-			break;
-		default:
-			return -EFAULT;
-		}
 
-		if (ret == BTF_FIELD_IGNORE)
-			continue;
-		if (idx >= info_cnt)
-			return -E2BIG;
-		++idx;
+		ret = btf_find_field_one(btf, t, member_type, i,
+					 off, 0,
+					 field_mask, &seen_mask,
+					 &info[idx], info_cnt - idx);
+		if (ret < 0)
+			return ret;
+		idx += ret;
 	}
 	return idx;
 }
@@ -3568,66 +3591,21 @@ static int btf_find_datasec_var(const struct btf *btf, const struct btf_type *t,
 				u32 field_mask, struct btf_field_info *info,
 				int info_cnt)
 {
-	int ret, idx = 0, align, sz, field_type;
+	int ret, idx = 0;
 	const struct btf_var_secinfo *vsi;
-	struct btf_field_info tmp;
 	u32 i, off, seen_mask = 0;
 
 	for_each_vsi(i, t, vsi) {
 		const struct btf_type *var = btf_type_by_id(btf, vsi->type);
 		const struct btf_type *var_type = btf_type_by_id(btf, var->type);
 
-		field_type = btf_get_field_type(__btf_name_by_offset(btf, var_type->name_off),
-						field_mask, &seen_mask, &align, &sz);
-		if (field_type == 0)
-			continue;
-		if (field_type < 0)
-			return field_type;
-
 		off = vsi->offset;
-		if (vsi->size != sz)
-			continue;
-		if (off % align)
-			continue;
-
-		switch (field_type) {
-		case BPF_SPIN_LOCK:
-		case BPF_TIMER:
-		case BPF_WORKQUEUE:
-		case BPF_LIST_NODE:
-		case BPF_RB_NODE:
-		case BPF_REFCOUNT:
-			ret = btf_find_struct(btf, var_type, off, sz, field_type,
-					      idx < info_cnt ? &info[idx] : &tmp);
-			if (ret < 0)
-				return ret;
-			break;
-		case BPF_KPTR_UNREF:
-		case BPF_KPTR_REF:
-		case BPF_KPTR_PERCPU:
-			ret = btf_find_kptr(btf, var_type, off, sz,
-					    idx < info_cnt ? &info[idx] : &tmp);
-			if (ret < 0)
-				return ret;
-			break;
-		case BPF_LIST_HEAD:
-		case BPF_RB_ROOT:
-			ret = btf_find_graph_root(btf, var, var_type,
-						  -1, off, sz,
-						  idx < info_cnt ? &info[idx] : &tmp,
-						  field_type);
-			if (ret < 0)
-				return ret;
-			break;
-		default:
-			return -EFAULT;
-		}
-
-		if (ret == BTF_FIELD_IGNORE)
-			continue;
-		if (idx >= info_cnt)
-			return -E2BIG;
-		++idx;
+		ret = btf_find_field_one(btf, var, var_type, -1, off, vsi->size,
+					 field_mask, &seen_mask,
+					 &info[idx], info_cnt - idx);
+		if (ret < 0)
+			return ret;
+		idx += ret;
 	}
 	return idx;
 }
-- 
GitLab


From 994796c0256c4001633488fd24c3d54691949f8d Mon Sep 17 00:00:00 2001
From: Kui-Feng Lee <thinker.li@gmail.com>
Date: Thu, 23 May 2024 10:41:57 -0700
Subject: [PATCH 752/950] bpf: create repeated fields for arrays.

The verifier uses field information for certain special types, such as
kptr, rbtree root, and list head. These types are treated
differently. However, we did not previously support these types in
arrays. This update examines arrays and duplicates field information the
same number of times as the length of the array if the element type is one
of the special types.

Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Kui-Feng Lee <thinker.li@gmail.com>
Link: https://lore.kernel.org/r/20240523174202.461236-5-thinker.li@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/btf.c | 62 ++++++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 58 insertions(+), 4 deletions(-)

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 2ce61c3a7e283..4fefa27d5aeaf 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -3494,6 +3494,41 @@ end:
 
 #undef field_mask_test_name
 
+/* Repeat a field for a specified number of times.
+ *
+ * Copy and repeat the first field for repeat_cnt
+ * times. The field is repeated by adding the offset of each field
+ * with
+ *   (i + 1) * elem_size
+ * where i is the repeat index and elem_size is the size of an element.
+ */
+static int btf_repeat_field(struct btf_field_info *info,
+			    u32 repeat_cnt, u32 elem_size)
+{
+	u32 i;
+	u32 cur;
+
+	/* Ensure not repeating fields that should not be repeated. */
+	switch (info[0].type) {
+	case BPF_KPTR_UNREF:
+	case BPF_KPTR_REF:
+	case BPF_KPTR_PERCPU:
+	case BPF_LIST_HEAD:
+	case BPF_RB_ROOT:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	cur = 1;
+	for (i = 0; i < repeat_cnt; i++) {
+		memcpy(&info[cur], &info[0], sizeof(info[0]));
+		info[cur++].off += (i + 1) * elem_size;
+	}
+
+	return 0;
+}
+
 static int btf_find_field_one(const struct btf *btf,
 			      const struct btf_type *var,
 			      const struct btf_type *var_type,
@@ -3504,6 +3539,21 @@ static int btf_find_field_one(const struct btf *btf,
 {
 	int ret, align, sz, field_type;
 	struct btf_field_info tmp;
+	const struct btf_array *array;
+	u32 i, nelems = 1;
+
+	/* Walk into array types to find the element type and the number of
+	 * elements in the (flattened) array.
+	 */
+	for (i = 0; i < MAX_RESOLVE_DEPTH && btf_type_is_array(var_type); i++) {
+		array = btf_array(var_type);
+		nelems *= array->nelems;
+		var_type = btf_type_by_id(btf, array->type);
+	}
+	if (i == MAX_RESOLVE_DEPTH)
+		return -E2BIG;
+	if (nelems == 0)
+		return 0;
 
 	field_type = btf_get_field_type(__btf_name_by_offset(btf, var_type->name_off),
 					field_mask, seen_mask, &align, &sz);
@@ -3512,7 +3562,7 @@ static int btf_find_field_one(const struct btf *btf,
 	if (field_type < 0)
 		return field_type;
 
-	if (expected_size && expected_size != sz)
+	if (expected_size && expected_size != sz * nelems)
 		return 0;
 	if (off % align)
 		return 0;
@@ -3552,10 +3602,14 @@ static int btf_find_field_one(const struct btf *btf,
 
 	if (ret == BTF_FIELD_IGNORE)
 		return 0;
-	if (!info_cnt)
+	if (nelems > info_cnt)
 		return -E2BIG;
-
-	return 1;
+	if (nelems > 1) {
+		ret = btf_repeat_field(info, nelems - 1, sz);
+		if (ret < 0)
+			return ret;
+	}
+	return nelems;
 }
 
 static int btf_find_struct_field(const struct btf *btf,
-- 
GitLab


From 64e8ee814819f21beeeda00d4119221443d77992 Mon Sep 17 00:00:00 2001
From: Kui-Feng Lee <thinker.li@gmail.com>
Date: Thu, 23 May 2024 10:41:58 -0700
Subject: [PATCH 753/950] bpf: look into the types of the fields of a struct
 type recursively.

The verifier has field information for specific special types, such as
kptr, rbtree root, and list head. These types are handled
differently. However, we did not previously examine the types of fields of
a struct type variable. Field information records were not generated for
the kptrs, rbtree roots, and linked_list heads that are not located at the
outermost struct type of a variable.

For example,

  struct A {
    struct task_struct __kptr * task;
  };

  struct B {
    struct A mem_a;
  }

  struct B var_b;

It did not examine "struct A" so as not to generate field information for
the kptr in "struct A" for "var_b".

This patch enables BPF programs to define fields of these special types in
a struct type other than the direct type of a variable or in a struct type
that is the type of a field in the value type of a map.

Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Kui-Feng Lee <thinker.li@gmail.com>
Link: https://lore.kernel.org/r/20240523174202.461236-6-thinker.li@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/btf.c | 100 ++++++++++++++++++++++++++++++++++++-----------
 1 file changed, 77 insertions(+), 23 deletions(-)

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 4fefa27d5aeaf..5e2b231a9af4c 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -3442,10 +3442,12 @@ btf_find_graph_root(const struct btf *btf, const struct btf_type *pt,
 		goto end;						\
 	}
 
-static int btf_get_field_type(const char *name, u32 field_mask, u32 *seen_mask,
+static int btf_get_field_type(const struct btf *btf, const struct btf_type *var_type,
+			      u32 field_mask, u32 *seen_mask,
 			      int *align, int *sz)
 {
 	int type = 0;
+	const char *name = __btf_name_by_offset(btf, var_type->name_off);
 
 	if (field_mask & BPF_SPIN_LOCK) {
 		if (!strcmp(name, "bpf_spin_lock")) {
@@ -3481,7 +3483,7 @@ static int btf_get_field_type(const char *name, u32 field_mask, u32 *seen_mask,
 	field_mask_test_name(BPF_REFCOUNT,  "bpf_refcount");
 
 	/* Only return BPF_KPTR when all other types with matchable names fail */
-	if (field_mask & BPF_KPTR) {
+	if (field_mask & BPF_KPTR && !__btf_type_is_struct(var_type)) {
 		type = BPF_KPTR_REF;
 		goto end;
 	}
@@ -3494,41 +3496,83 @@ end:
 
 #undef field_mask_test_name
 
-/* Repeat a field for a specified number of times.
+/* Repeat a number of fields for a specified number of times.
  *
- * Copy and repeat the first field for repeat_cnt
- * times. The field is repeated by adding the offset of each field
- * with
+ * Copy the fields starting from the first field and repeat them for
+ * repeat_cnt times. The fields are repeated by adding the offset of each
+ * field with
  *   (i + 1) * elem_size
  * where i is the repeat index and elem_size is the size of an element.
  */
-static int btf_repeat_field(struct btf_field_info *info,
-			    u32 repeat_cnt, u32 elem_size)
+static int btf_repeat_fields(struct btf_field_info *info,
+			     u32 field_cnt, u32 repeat_cnt, u32 elem_size)
 {
-	u32 i;
+	u32 i, j;
 	u32 cur;
 
 	/* Ensure not repeating fields that should not be repeated. */
-	switch (info[0].type) {
-	case BPF_KPTR_UNREF:
-	case BPF_KPTR_REF:
-	case BPF_KPTR_PERCPU:
-	case BPF_LIST_HEAD:
-	case BPF_RB_ROOT:
-		break;
-	default:
-		return -EINVAL;
+	for (i = 0; i < field_cnt; i++) {
+		switch (info[i].type) {
+		case BPF_KPTR_UNREF:
+		case BPF_KPTR_REF:
+		case BPF_KPTR_PERCPU:
+		case BPF_LIST_HEAD:
+		case BPF_RB_ROOT:
+			break;
+		default:
+			return -EINVAL;
+		}
 	}
 
-	cur = 1;
+	cur = field_cnt;
 	for (i = 0; i < repeat_cnt; i++) {
-		memcpy(&info[cur], &info[0], sizeof(info[0]));
-		info[cur++].off += (i + 1) * elem_size;
+		memcpy(&info[cur], &info[0], field_cnt * sizeof(info[0]));
+		for (j = 0; j < field_cnt; j++)
+			info[cur++].off += (i + 1) * elem_size;
 	}
 
 	return 0;
 }
 
+static int btf_find_struct_field(const struct btf *btf,
+				 const struct btf_type *t, u32 field_mask,
+				 struct btf_field_info *info, int info_cnt);
+
+/* Find special fields in the struct type of a field.
+ *
+ * This function is used to find fields of special types that is not a
+ * global variable or a direct field of a struct type. It also handles the
+ * repetition if it is the element type of an array.
+ */
+static int btf_find_nested_struct(const struct btf *btf, const struct btf_type *t,
+				  u32 off, u32 nelems,
+				  u32 field_mask, struct btf_field_info *info,
+				  int info_cnt)
+{
+	int ret, err, i;
+
+	ret = btf_find_struct_field(btf, t, field_mask, info, info_cnt);
+
+	if (ret <= 0)
+		return ret;
+
+	/* Shift the offsets of the nested struct fields to the offsets
+	 * related to the container.
+	 */
+	for (i = 0; i < ret; i++)
+		info[i].off += off;
+
+	if (nelems > 1) {
+		err = btf_repeat_fields(info, ret, nelems - 1, t->size);
+		if (err == 0)
+			ret *= nelems;
+		else
+			ret = err;
+	}
+
+	return ret;
+}
+
 static int btf_find_field_one(const struct btf *btf,
 			      const struct btf_type *var,
 			      const struct btf_type *var_type,
@@ -3555,8 +3599,18 @@ static int btf_find_field_one(const struct btf *btf,
 	if (nelems == 0)
 		return 0;
 
-	field_type = btf_get_field_type(__btf_name_by_offset(btf, var_type->name_off),
+	field_type = btf_get_field_type(btf, var_type,
 					field_mask, seen_mask, &align, &sz);
+	/* Look into variables of struct types */
+	if (!field_type && __btf_type_is_struct(var_type)) {
+		sz = var_type->size;
+		if (expected_size && expected_size != sz * nelems)
+			return 0;
+		ret = btf_find_nested_struct(btf, var_type, off, nelems, field_mask,
+					     &info[0], info_cnt);
+		return ret;
+	}
+
 	if (field_type == 0)
 		return 0;
 	if (field_type < 0)
@@ -3605,7 +3659,7 @@ static int btf_find_field_one(const struct btf *btf,
 	if (nelems > info_cnt)
 		return -E2BIG;
 	if (nelems > 1) {
-		ret = btf_repeat_field(info, nelems - 1, sz);
+		ret = btf_repeat_fields(info, 1, nelems - 1, sz);
 		if (ret < 0)
 			return ret;
 	}
-- 
GitLab


From f19caf57d80f4432acea61d858d45ce194444389 Mon Sep 17 00:00:00 2001
From: Kui-Feng Lee <thinker.li@gmail.com>
Date: Thu, 23 May 2024 10:41:59 -0700
Subject: [PATCH 754/950] bpf: limit the number of levels of a nested struct
 type.

Limit the number of levels looking into struct types to avoid running out
of stack space.

Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Kui-Feng Lee <thinker.li@gmail.com>
Link: https://lore.kernel.org/r/20240523174202.461236-7-thinker.li@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/btf.c | 30 +++++++++++++++++++-----------
 1 file changed, 19 insertions(+), 11 deletions(-)

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 5e2b231a9af4c..7928d920056f7 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -3536,7 +3536,8 @@ static int btf_repeat_fields(struct btf_field_info *info,
 
 static int btf_find_struct_field(const struct btf *btf,
 				 const struct btf_type *t, u32 field_mask,
-				 struct btf_field_info *info, int info_cnt);
+				 struct btf_field_info *info, int info_cnt,
+				 u32 level);
 
 /* Find special fields in the struct type of a field.
  *
@@ -3547,11 +3548,15 @@ static int btf_find_struct_field(const struct btf *btf,
 static int btf_find_nested_struct(const struct btf *btf, const struct btf_type *t,
 				  u32 off, u32 nelems,
 				  u32 field_mask, struct btf_field_info *info,
-				  int info_cnt)
+				  int info_cnt, u32 level)
 {
 	int ret, err, i;
 
-	ret = btf_find_struct_field(btf, t, field_mask, info, info_cnt);
+	level++;
+	if (level >= MAX_RESOLVE_DEPTH)
+		return -E2BIG;
+
+	ret = btf_find_struct_field(btf, t, field_mask, info, info_cnt, level);
 
 	if (ret <= 0)
 		return ret;
@@ -3579,7 +3584,8 @@ static int btf_find_field_one(const struct btf *btf,
 			      int var_idx,
 			      u32 off, u32 expected_size,
 			      u32 field_mask, u32 *seen_mask,
-			      struct btf_field_info *info, int info_cnt)
+			      struct btf_field_info *info, int info_cnt,
+			      u32 level)
 {
 	int ret, align, sz, field_type;
 	struct btf_field_info tmp;
@@ -3607,7 +3613,7 @@ static int btf_find_field_one(const struct btf *btf,
 		if (expected_size && expected_size != sz * nelems)
 			return 0;
 		ret = btf_find_nested_struct(btf, var_type, off, nelems, field_mask,
-					     &info[0], info_cnt);
+					     &info[0], info_cnt, level);
 		return ret;
 	}
 
@@ -3668,7 +3674,8 @@ static int btf_find_field_one(const struct btf *btf,
 
 static int btf_find_struct_field(const struct btf *btf,
 				 const struct btf_type *t, u32 field_mask,
-				 struct btf_field_info *info, int info_cnt)
+				 struct btf_field_info *info, int info_cnt,
+				 u32 level)
 {
 	int ret, idx = 0;
 	const struct btf_member *member;
@@ -3687,7 +3694,7 @@ static int btf_find_struct_field(const struct btf *btf,
 		ret = btf_find_field_one(btf, t, member_type, i,
 					 off, 0,
 					 field_mask, &seen_mask,
-					 &info[idx], info_cnt - idx);
+					 &info[idx], info_cnt - idx, level);
 		if (ret < 0)
 			return ret;
 		idx += ret;
@@ -3697,7 +3704,7 @@ static int btf_find_struct_field(const struct btf *btf,
 
 static int btf_find_datasec_var(const struct btf *btf, const struct btf_type *t,
 				u32 field_mask, struct btf_field_info *info,
-				int info_cnt)
+				int info_cnt, u32 level)
 {
 	int ret, idx = 0;
 	const struct btf_var_secinfo *vsi;
@@ -3710,7 +3717,8 @@ static int btf_find_datasec_var(const struct btf *btf, const struct btf_type *t,
 		off = vsi->offset;
 		ret = btf_find_field_one(btf, var, var_type, -1, off, vsi->size,
 					 field_mask, &seen_mask,
-					 &info[idx], info_cnt - idx);
+					 &info[idx], info_cnt - idx,
+					 level);
 		if (ret < 0)
 			return ret;
 		idx += ret;
@@ -3723,9 +3731,9 @@ static int btf_find_field(const struct btf *btf, const struct btf_type *t,
 			  int info_cnt)
 {
 	if (__btf_type_is_struct(t))
-		return btf_find_struct_field(btf, t, field_mask, info, info_cnt);
+		return btf_find_struct_field(btf, t, field_mask, info, info_cnt, 0);
 	else if (btf_type_is_datasec(t))
-		return btf_find_datasec_var(btf, t, field_mask, info, info_cnt);
+		return btf_find_datasec_var(btf, t, field_mask, info, info_cnt, 0);
 	return -EINVAL;
 }
 
-- 
GitLab


From c4c6c3b785a0b1426add15d078da61f899abeaac Mon Sep 17 00:00:00 2001
From: Kui-Feng Lee <thinker.li@gmail.com>
Date: Thu, 23 May 2024 10:42:00 -0700
Subject: [PATCH 755/950] selftests/bpf: Test kptr arrays and kptrs in nested
 struct fields.

Make sure that BPF programs can declare global kptr arrays and kptr fields
in struct types that is the type of a global variable or the type of a
nested descendant field in a global variable.

An array with only one element is special case, that it treats the element
like a non-array kptr field. Nested arrays are also tested to ensure they
are handled properly.

Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Kui-Feng Lee <thinker.li@gmail.com>
Link: https://lore.kernel.org/r/20240523174202.461236-8-thinker.li@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../selftests/bpf/prog_tests/cpumask.c        |   5 +
 .../selftests/bpf/progs/cpumask_success.c     | 171 ++++++++++++++++++
 2 files changed, 176 insertions(+)

diff --git a/tools/testing/selftests/bpf/prog_tests/cpumask.c b/tools/testing/selftests/bpf/prog_tests/cpumask.c
index ecf89df781098..2570bd4b0cb22 100644
--- a/tools/testing/selftests/bpf/prog_tests/cpumask.c
+++ b/tools/testing/selftests/bpf/prog_tests/cpumask.c
@@ -18,6 +18,11 @@ static const char * const cpumask_success_testcases[] = {
 	"test_insert_leave",
 	"test_insert_remove_release",
 	"test_global_mask_rcu",
+	"test_global_mask_array_one_rcu",
+	"test_global_mask_array_rcu",
+	"test_global_mask_array_l2_rcu",
+	"test_global_mask_nested_rcu",
+	"test_global_mask_nested_deep_rcu",
 	"test_cpumask_weight",
 };
 
diff --git a/tools/testing/selftests/bpf/progs/cpumask_success.c b/tools/testing/selftests/bpf/progs/cpumask_success.c
index 7a1e64c6c065c..fd8106831c32c 100644
--- a/tools/testing/selftests/bpf/progs/cpumask_success.c
+++ b/tools/testing/selftests/bpf/progs/cpumask_success.c
@@ -12,6 +12,31 @@ char _license[] SEC("license") = "GPL";
 
 int pid, nr_cpus;
 
+struct kptr_nested {
+	struct bpf_cpumask __kptr * mask;
+};
+
+struct kptr_nested_pair {
+	struct bpf_cpumask __kptr * mask_1;
+	struct bpf_cpumask __kptr * mask_2;
+};
+
+struct kptr_nested_mid {
+	int dummy;
+	struct kptr_nested m;
+};
+
+struct kptr_nested_deep {
+	struct kptr_nested_mid ptrs[2];
+	struct kptr_nested_pair ptr_pairs[3];
+};
+
+private(MASK) static struct bpf_cpumask __kptr * global_mask_array[2];
+private(MASK) static struct bpf_cpumask __kptr * global_mask_array_l2[2][1];
+private(MASK) static struct bpf_cpumask __kptr * global_mask_array_one[1];
+private(MASK) static struct kptr_nested global_mask_nested[2];
+private(MASK_DEEP) static struct kptr_nested_deep global_mask_nested_deep;
+
 static bool is_test_task(void)
 {
 	int cur_pid = bpf_get_current_pid_tgid() >> 32;
@@ -460,6 +485,152 @@ int BPF_PROG(test_global_mask_rcu, struct task_struct *task, u64 clone_flags)
 	return 0;
 }
 
+SEC("tp_btf/task_newtask")
+int BPF_PROG(test_global_mask_array_one_rcu, struct task_struct *task, u64 clone_flags)
+{
+	struct bpf_cpumask *local, *prev;
+
+	if (!is_test_task())
+		return 0;
+
+	/* Kptr arrays with one element are special cased, being treated
+	 * just like a single pointer.
+	 */
+
+	local = create_cpumask();
+	if (!local)
+		return 0;
+
+	prev = bpf_kptr_xchg(&global_mask_array_one[0], local);
+	if (prev) {
+		bpf_cpumask_release(prev);
+		err = 3;
+		return 0;
+	}
+
+	bpf_rcu_read_lock();
+	local = global_mask_array_one[0];
+	if (!local) {
+		err = 4;
+		bpf_rcu_read_unlock();
+		return 0;
+	}
+
+	bpf_rcu_read_unlock();
+
+	return 0;
+}
+
+static int _global_mask_array_rcu(struct bpf_cpumask **mask0,
+				  struct bpf_cpumask **mask1)
+{
+	struct bpf_cpumask *local;
+
+	if (!is_test_task())
+		return 0;
+
+	/* Check if two kptrs in the array work and independently */
+
+	local = create_cpumask();
+	if (!local)
+		return 0;
+
+	bpf_rcu_read_lock();
+
+	local = bpf_kptr_xchg(mask0, local);
+	if (local) {
+		err = 1;
+		goto err_exit;
+	}
+
+	/* [<mask 0>, NULL] */
+	if (!*mask0 || *mask1) {
+		err = 2;
+		goto err_exit;
+	}
+
+	local = create_cpumask();
+	if (!local) {
+		err = 9;
+		goto err_exit;
+	}
+
+	local = bpf_kptr_xchg(mask1, local);
+	if (local) {
+		err = 10;
+		goto err_exit;
+	}
+
+	/* [<mask 0>, <mask 1>] */
+	if (!*mask0 || !*mask1 || *mask0 == *mask1) {
+		err = 11;
+		goto err_exit;
+	}
+
+err_exit:
+	if (local)
+		bpf_cpumask_release(local);
+	bpf_rcu_read_unlock();
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+int BPF_PROG(test_global_mask_array_rcu, struct task_struct *task, u64 clone_flags)
+{
+	return _global_mask_array_rcu(&global_mask_array[0], &global_mask_array[1]);
+}
+
+SEC("tp_btf/task_newtask")
+int BPF_PROG(test_global_mask_array_l2_rcu, struct task_struct *task, u64 clone_flags)
+{
+	return _global_mask_array_rcu(&global_mask_array_l2[0][0], &global_mask_array_l2[1][0]);
+}
+
+SEC("tp_btf/task_newtask")
+int BPF_PROG(test_global_mask_nested_rcu, struct task_struct *task, u64 clone_flags)
+{
+	return _global_mask_array_rcu(&global_mask_nested[0].mask, &global_mask_nested[1].mask);
+}
+
+/* Ensure that the field->offset has been correctly advanced from one
+ * nested struct or array sub-tree to another. In the case of
+ * kptr_nested_deep, it comprises two sub-trees: ktpr_1 and kptr_2.  By
+ * calling bpf_kptr_xchg() on every single kptr in both nested sub-trees,
+ * the verifier should reject the program if the field->offset of any kptr
+ * is incorrect.
+ *
+ * For instance, if we have 10 kptrs in a nested struct and a program that
+ * accesses each kptr individually with bpf_kptr_xchg(), the compiler
+ * should emit instructions to access 10 different offsets if it works
+ * correctly. If the field->offset values of any pair of them are
+ * incorrectly the same, the number of unique offsets in btf_record for
+ * this nested struct should be less than 10. The verifier should fail to
+ * discover some of the offsets emitted by the compiler.
+ *
+ * Even if the field->offset values of kptrs are not duplicated, the
+ * verifier should fail to find a btf_field for the instruction accessing a
+ * kptr if the corresponding field->offset is pointing to a random
+ * incorrect offset.
+ */
+SEC("tp_btf/task_newtask")
+int BPF_PROG(test_global_mask_nested_deep_rcu, struct task_struct *task, u64 clone_flags)
+{
+	int r, i;
+
+	r = _global_mask_array_rcu(&global_mask_nested_deep.ptrs[0].m.mask,
+				   &global_mask_nested_deep.ptrs[1].m.mask);
+	if (r)
+		return r;
+
+	for (i = 0; i < 3; i++) {
+		r = _global_mask_array_rcu(&global_mask_nested_deep.ptr_pairs[i].mask_1,
+					   &global_mask_nested_deep.ptr_pairs[i].mask_2);
+		if (r)
+			return r;
+	}
+	return 0;
+}
+
 SEC("tp_btf/task_newtask")
 int BPF_PROG(test_cpumask_weight, struct task_struct *task, u64 clone_flags)
 {
-- 
GitLab


From d55c765a9b2d54b53ef86a62d6209e2e5eb62585 Mon Sep 17 00:00:00 2001
From: Kui-Feng Lee <thinker.li@gmail.com>
Date: Thu, 23 May 2024 10:42:01 -0700
Subject: [PATCH 756/950] selftests/bpf: Test global bpf_rb_root arrays and
 fields in nested struct types.

Make sure global arrays of bpf_rb_root and fields of bpf_rb_root in nested
struct types work correctly.

Signed-off-by: Kui-Feng Lee <thinker.li@gmail.com>
Link: https://lore.kernel.org/r/20240523174202.461236-9-thinker.li@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../testing/selftests/bpf/prog_tests/rbtree.c | 47 +++++++++++
 tools/testing/selftests/bpf/progs/rbtree.c    | 77 +++++++++++++++++++
 2 files changed, 124 insertions(+)

diff --git a/tools/testing/selftests/bpf/prog_tests/rbtree.c b/tools/testing/selftests/bpf/prog_tests/rbtree.c
index e9300c96607d3..9818f06c97c5a 100644
--- a/tools/testing/selftests/bpf/prog_tests/rbtree.c
+++ b/tools/testing/selftests/bpf/prog_tests/rbtree.c
@@ -31,6 +31,28 @@ static void test_rbtree_add_nodes(void)
 	rbtree__destroy(skel);
 }
 
+static void test_rbtree_add_nodes_nested(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts,
+		    .data_in = &pkt_v4,
+		    .data_size_in = sizeof(pkt_v4),
+		    .repeat = 1,
+	);
+	struct rbtree *skel;
+	int ret;
+
+	skel = rbtree__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "rbtree__open_and_load"))
+		return;
+
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.rbtree_add_nodes_nested), &opts);
+	ASSERT_OK(ret, "rbtree_add_nodes_nested run");
+	ASSERT_OK(opts.retval, "rbtree_add_nodes_nested retval");
+	ASSERT_EQ(skel->data->less_callback_ran, 1, "rbtree_add_nodes_nested less_callback_ran");
+
+	rbtree__destroy(skel);
+}
+
 static void test_rbtree_add_and_remove(void)
 {
 	LIBBPF_OPTS(bpf_test_run_opts, opts,
@@ -53,6 +75,27 @@ static void test_rbtree_add_and_remove(void)
 	rbtree__destroy(skel);
 }
 
+static void test_rbtree_add_and_remove_array(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts,
+		    .data_in = &pkt_v4,
+		    .data_size_in = sizeof(pkt_v4),
+		    .repeat = 1,
+	);
+	struct rbtree *skel;
+	int ret;
+
+	skel = rbtree__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "rbtree__open_and_load"))
+		return;
+
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.rbtree_add_and_remove_array), &opts);
+	ASSERT_OK(ret, "rbtree_add_and_remove_array");
+	ASSERT_OK(opts.retval, "rbtree_add_and_remove_array retval");
+
+	rbtree__destroy(skel);
+}
+
 static void test_rbtree_first_and_remove(void)
 {
 	LIBBPF_OPTS(bpf_test_run_opts, opts,
@@ -104,8 +147,12 @@ void test_rbtree_success(void)
 {
 	if (test__start_subtest("rbtree_add_nodes"))
 		test_rbtree_add_nodes();
+	if (test__start_subtest("rbtree_add_nodes_nested"))
+		test_rbtree_add_nodes_nested();
 	if (test__start_subtest("rbtree_add_and_remove"))
 		test_rbtree_add_and_remove();
+	if (test__start_subtest("rbtree_add_and_remove_array"))
+		test_rbtree_add_and_remove_array();
 	if (test__start_subtest("rbtree_first_and_remove"))
 		test_rbtree_first_and_remove();
 	if (test__start_subtest("rbtree_api_release_aliasing"))
diff --git a/tools/testing/selftests/bpf/progs/rbtree.c b/tools/testing/selftests/bpf/progs/rbtree.c
index b09f4fffe57cf..a3620c15c1367 100644
--- a/tools/testing/selftests/bpf/progs/rbtree.c
+++ b/tools/testing/selftests/bpf/progs/rbtree.c
@@ -13,6 +13,15 @@ struct node_data {
 	struct bpf_rb_node node;
 };
 
+struct root_nested_inner {
+	struct bpf_spin_lock glock;
+	struct bpf_rb_root root __contains(node_data, node);
+};
+
+struct root_nested {
+	struct root_nested_inner inner;
+};
+
 long less_callback_ran = -1;
 long removed_key = -1;
 long first_data[2] = {-1, -1};
@@ -20,6 +29,9 @@ long first_data[2] = {-1, -1};
 #define private(name) SEC(".data." #name) __hidden __attribute__((aligned(8)))
 private(A) struct bpf_spin_lock glock;
 private(A) struct bpf_rb_root groot __contains(node_data, node);
+private(A) struct bpf_rb_root groot_array[2] __contains(node_data, node);
+private(A) struct bpf_rb_root groot_array_one[1] __contains(node_data, node);
+private(B) struct root_nested groot_nested;
 
 static bool less(struct bpf_rb_node *a, const struct bpf_rb_node *b)
 {
@@ -71,6 +83,12 @@ long rbtree_add_nodes(void *ctx)
 	return __add_three(&groot, &glock);
 }
 
+SEC("tc")
+long rbtree_add_nodes_nested(void *ctx)
+{
+	return __add_three(&groot_nested.inner.root, &groot_nested.inner.glock);
+}
+
 SEC("tc")
 long rbtree_add_and_remove(void *ctx)
 {
@@ -109,6 +127,65 @@ err_out:
 	return 1;
 }
 
+SEC("tc")
+long rbtree_add_and_remove_array(void *ctx)
+{
+	struct bpf_rb_node *res1 = NULL, *res2 = NULL, *res3 = NULL;
+	struct node_data *nodes[3][2] = {{NULL, NULL}, {NULL, NULL}, {NULL, NULL}};
+	struct node_data *n;
+	long k1 = -1, k2 = -1, k3 = -1;
+	int i, j;
+
+	for (i = 0; i < 3; i++) {
+		for (j = 0; j < 2; j++) {
+			nodes[i][j] = bpf_obj_new(typeof(*nodes[i][j]));
+			if (!nodes[i][j])
+				goto err_out;
+			nodes[i][j]->key = i * 2 + j;
+		}
+	}
+
+	bpf_spin_lock(&glock);
+	for (i = 0; i < 2; i++)
+		for (j = 0; j < 2; j++)
+			bpf_rbtree_add(&groot_array[i], &nodes[i][j]->node, less);
+	for (j = 0; j < 2; j++)
+		bpf_rbtree_add(&groot_array_one[0], &nodes[2][j]->node, less);
+	res1 = bpf_rbtree_remove(&groot_array[0], &nodes[0][0]->node);
+	res2 = bpf_rbtree_remove(&groot_array[1], &nodes[1][0]->node);
+	res3 = bpf_rbtree_remove(&groot_array_one[0], &nodes[2][0]->node);
+	bpf_spin_unlock(&glock);
+
+	if (res1) {
+		n = container_of(res1, struct node_data, node);
+		k1 = n->key;
+		bpf_obj_drop(n);
+	}
+	if (res2) {
+		n = container_of(res2, struct node_data, node);
+		k2 = n->key;
+		bpf_obj_drop(n);
+	}
+	if (res3) {
+		n = container_of(res3, struct node_data, node);
+		k3 = n->key;
+		bpf_obj_drop(n);
+	}
+	if (k1 != 0 || k2 != 2 || k3 != 4)
+		return 2;
+
+	return 0;
+
+err_out:
+	for (i = 0; i < 3; i++) {
+		for (j = 0; j < 2; j++) {
+			if (nodes[i][j])
+				bpf_obj_drop(nodes[i][j]);
+		}
+	}
+	return 1;
+}
+
 SEC("tc")
 long rbtree_first_and_remove(void *ctx)
 {
-- 
GitLab


From 43d50ffb1f7e32865cdd343224659614d8b558b9 Mon Sep 17 00:00:00 2001
From: Kui-Feng Lee <thinker.li@gmail.com>
Date: Thu, 23 May 2024 10:42:02 -0700
Subject: [PATCH 757/950] selftests/bpf: Test global bpf_list_head arrays.

Make sure global arrays of bpf_list_heads and fields of bpf_list_heads in
nested struct types work correctly.

Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Kui-Feng Lee <thinker.li@gmail.com>
Link: https://lore.kernel.org/r/20240523174202.461236-10-thinker.li@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../selftests/bpf/prog_tests/linked_list.c    | 12 ++++++
 .../testing/selftests/bpf/progs/linked_list.c | 42 +++++++++++++++++++
 2 files changed, 54 insertions(+)

diff --git a/tools/testing/selftests/bpf/prog_tests/linked_list.c b/tools/testing/selftests/bpf/prog_tests/linked_list.c
index 2fb89de63bd22..77d07e0a4a55c 100644
--- a/tools/testing/selftests/bpf/prog_tests/linked_list.c
+++ b/tools/testing/selftests/bpf/prog_tests/linked_list.c
@@ -183,6 +183,18 @@ static void test_linked_list_success(int mode, bool leave_in_map)
 	if (!leave_in_map)
 		clear_fields(skel->maps.bss_A);
 
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.global_list_push_pop_nested), &opts);
+	ASSERT_OK(ret, "global_list_push_pop_nested");
+	ASSERT_OK(opts.retval, "global_list_push_pop_nested retval");
+	if (!leave_in_map)
+		clear_fields(skel->maps.bss_A);
+
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.global_list_array_push_pop), &opts);
+	ASSERT_OK(ret, "global_list_array_push_pop");
+	ASSERT_OK(opts.retval, "global_list_array_push_pop retval");
+	if (!leave_in_map)
+		clear_fields(skel->maps.bss_A);
+
 	if (mode == PUSH_POP)
 		goto end;
 
diff --git a/tools/testing/selftests/bpf/progs/linked_list.c b/tools/testing/selftests/bpf/progs/linked_list.c
index 26205ca806796..f69bf3e30321a 100644
--- a/tools/testing/selftests/bpf/progs/linked_list.c
+++ b/tools/testing/selftests/bpf/progs/linked_list.c
@@ -11,6 +11,22 @@
 
 #include "linked_list.h"
 
+struct head_nested_inner {
+	struct bpf_spin_lock lock;
+	struct bpf_list_head head __contains(foo, node2);
+};
+
+struct head_nested {
+	int dummy;
+	struct head_nested_inner inner;
+};
+
+private(C) struct bpf_spin_lock glock_c;
+private(C) struct bpf_list_head ghead_array[2] __contains(foo, node2);
+private(C) struct bpf_list_head ghead_array_one[1] __contains(foo, node2);
+
+private(D) struct head_nested ghead_nested;
+
 static __always_inline
 int list_push_pop(struct bpf_spin_lock *lock, struct bpf_list_head *head, bool leave_in_map)
 {
@@ -309,6 +325,32 @@ int global_list_push_pop(void *ctx)
 	return test_list_push_pop(&glock, &ghead);
 }
 
+SEC("tc")
+int global_list_push_pop_nested(void *ctx)
+{
+	return test_list_push_pop(&ghead_nested.inner.lock, &ghead_nested.inner.head);
+}
+
+SEC("tc")
+int global_list_array_push_pop(void *ctx)
+{
+	int r;
+
+	r = test_list_push_pop(&glock_c, &ghead_array[0]);
+	if (r)
+		return r;
+
+	r = test_list_push_pop(&glock_c, &ghead_array[1]);
+	if (r)
+		return r;
+
+	/* Arrays with only one element is a special case, being treated
+	 * just like a bpf_list_head variable by the verifier, not an
+	 * array.
+	 */
+	return test_list_push_pop(&glock_c, &ghead_array_one[0]);
+}
+
 SEC("tc")
 int map_list_push_pop_multiple(void *ctx)
 {
-- 
GitLab


From 4fdb6b6063f07d959a1c52a2ee580afc4da34e2d Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 29 May 2024 09:25:27 -0700
Subject: [PATCH 758/950] net: count drops due to missing qdisc as
 dev->tx_drops

Catching and debugging missing qdiscs is pretty tricky. When qdisc
is deleted we replace it with a noop qdisc, which silently drops
all the packets. Since the noop qdisc has a single static instance
we can't count drops at the qdisc level. Count them as dev->tx_drops.

  ip netns add red
  ip link add type veth peer netns red
  ip            link set dev veth0 up
  ip -netns red link set dev veth0 up
  ip            a a dev veth0 10.0.0.1/24
  ip -netns red a a dev veth0 10.0.0.2/24
  ping -c 2 10.0.0.2
  #  2 packets transmitted, 2 received, 0% packet loss, time 1031ms
  ip -s link show dev veth0
  #  TX:  bytes packets errors dropped carrier collsns
  #        1314      17      0       0       0       0

  tc qdisc replace dev veth0 root handle 1234: mq
  tc qdisc replace dev veth0 parent 1234:1 pfifo
  tc qdisc del dev veth0 parent 1234:1
  ping -c 2 10.0.0.2
  #  2 packets transmitted, 0 received, 100% packet loss, time 1034ms
  ip -s link show dev veth0
  #  TX:  bytes packets errors dropped carrier collsns
  #        1314      17      0       3       0       0

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20240529162527.3688979-1-kuba@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/sched/sch_generic.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 2a637a17061b9..1417f1991452f 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -633,6 +633,7 @@ EXPORT_SYMBOL_GPL(netif_carrier_event);
 static int noop_enqueue(struct sk_buff *skb, struct Qdisc *qdisc,
 			struct sk_buff **to_free)
 {
+	dev_core_stats_tx_dropped_inc(skb->dev);
 	__qdisc_drop(skb, to_free);
 	return NET_XMIT_CN;
 }
-- 
GitLab


From 668b6a2ef832a878494cc1b12a881c8ec0494b25 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Thu, 30 May 2024 19:08:34 +0200
Subject: [PATCH 759/950] flow_dissector: add support for tunnel control flags

Dissect [no]csum, [no]dontfrag, [no]oam, [no]crit flags from skb metadata.
This is a prerequisite for matching these control flags using TC flower.

Suggested-by: Ilya Maximets <i.maximets@ovn.org>
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/net/flow_dissector.h |  9 +++++++++
 include/net/ip_tunnels.h     | 12 ++++++++++++
 net/core/flow_dissector.c    | 16 +++++++++++++++-
 3 files changed, 36 insertions(+), 1 deletion(-)

diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h
index 9ab376d1a6771..99626475c3f4a 100644
--- a/include/net/flow_dissector.h
+++ b/include/net/flow_dissector.h
@@ -329,6 +329,14 @@ struct flow_dissector_key_cfm {
 #define FLOW_DIS_CFM_MDL_MASK GENMASK(7, 5)
 #define FLOW_DIS_CFM_MDL_MAX 7
 
+/**
+ * struct flow_dissector_key_enc_flags: tunnel metadata control flags
+ * @flags: tunnel control flags
+ */
+struct flow_dissector_key_enc_flags {
+	u32 flags;
+};
+
 enum flow_dissector_key_id {
 	FLOW_DISSECTOR_KEY_CONTROL, /* struct flow_dissector_key_control */
 	FLOW_DISSECTOR_KEY_BASIC, /* struct flow_dissector_key_basic */
@@ -363,6 +371,7 @@ enum flow_dissector_key_id {
 	FLOW_DISSECTOR_KEY_L2TPV3, /* struct flow_dissector_key_l2tpv3 */
 	FLOW_DISSECTOR_KEY_CFM, /* struct flow_dissector_key_cfm */
 	FLOW_DISSECTOR_KEY_IPSEC, /* struct flow_dissector_key_ipsec */
+	FLOW_DISSECTOR_KEY_ENC_FLAGS, /* struct flow_dissector_key_enc_flags */
 
 	FLOW_DISSECTOR_KEY_MAX,
 };
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index 9a6a08ec77139..5a530d4fb02c6 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -247,6 +247,18 @@ static inline bool ip_tunnel_is_options_present(const unsigned long *flags)
 	return ip_tunnel_flags_intersect(flags, present);
 }
 
+static inline void ip_tunnel_set_encflags_present(unsigned long *flags)
+{
+	IP_TUNNEL_DECLARE_FLAGS(present) = { };
+
+	__set_bit(IP_TUNNEL_CSUM_BIT, present);
+	__set_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, present);
+	__set_bit(IP_TUNNEL_OAM_BIT, present);
+	__set_bit(IP_TUNNEL_CRIT_OPT_BIT, present);
+
+	ip_tunnel_flags_or(flags, flags, present);
+}
+
 static inline bool ip_tunnel_flags_is_be16_compat(const unsigned long *flags)
 {
 	IP_TUNNEL_DECLARE_FLAGS(supp) = { };
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index f82e9a7d3b379..59fe46077b3ca 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -382,7 +382,9 @@ skb_flow_dissect_tunnel_info(const struct sk_buff *skb,
 	    !dissector_uses_key(flow_dissector,
 				FLOW_DISSECTOR_KEY_ENC_IP) &&
 	    !dissector_uses_key(flow_dissector,
-				FLOW_DISSECTOR_KEY_ENC_OPTS))
+				FLOW_DISSECTOR_KEY_ENC_OPTS) &&
+	    !dissector_uses_key(flow_dissector,
+				FLOW_DISSECTOR_KEY_ENC_FLAGS))
 		return;
 
 	info = skb_tunnel_info(skb);
@@ -475,6 +477,18 @@ skb_flow_dissect_tunnel_info(const struct sk_buff *skb,
 				    IP_TUNNEL_GENEVE_OPT_BIT);
 		enc_opt->dst_opt_type = val < __IP_TUNNEL_FLAG_NUM ? val : 0;
 	}
+
+	if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_FLAGS)) {
+		struct flow_dissector_key_enc_flags *enc_flags;
+		IP_TUNNEL_DECLARE_FLAGS(flags) = {};
+
+		enc_flags = skb_flow_dissector_target(flow_dissector,
+						      FLOW_DISSECTOR_KEY_ENC_FLAGS,
+						      target_container);
+		ip_tunnel_set_encflags_present(flags);
+		ip_tunnel_flags_and(flags, flags, info->key.tun_flags);
+		enc_flags->flags = bitmap_read(flags, IP_TUNNEL_CSUM_BIT, 32);
+	}
 }
 EXPORT_SYMBOL(skb_flow_dissect_tunnel_info);
 
-- 
GitLab


From 1d17568e74dedbcb54d36af0662a15128297d681 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Thu, 30 May 2024 19:08:35 +0200
Subject: [PATCH 760/950] net/sched: cls_flower: add support for matching
 tunnel control flags

extend cls_flower to match TUNNEL_FLAGS_PRESENT bits in tunnel metadata.

Suggested-by: Ilya Maximets <i.maximets@ovn.org>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/uapi/linux/pkt_cls.h |  3 ++
 net/sched/cls_flower.c       | 56 +++++++++++++++++++++++++++++++++++-
 2 files changed, 58 insertions(+), 1 deletion(-)

diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h
index 229fc925ec3a2..b6d38f5fd7c05 100644
--- a/include/uapi/linux/pkt_cls.h
+++ b/include/uapi/linux/pkt_cls.h
@@ -554,6 +554,9 @@ enum {
 	TCA_FLOWER_KEY_SPI,		/* be32 */
 	TCA_FLOWER_KEY_SPI_MASK,	/* be32 */
 
+	TCA_FLOWER_KEY_ENC_FLAGS,	/* u32 */
+	TCA_FLOWER_KEY_ENC_FLAGS_MASK,	/* u32 */
+
 	__TCA_FLOWER_MAX,
 };
 
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index fd9a6f20b60b4..eef570c577ac7 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -41,6 +41,12 @@
 #define TCA_FLOWER_KEY_CT_FLAGS_MASK \
 		(TCA_FLOWER_KEY_CT_FLAGS_MAX - 1)
 
+#define TUNNEL_FLAGS_PRESENT (\
+	_BITUL(IP_TUNNEL_CSUM_BIT) |		\
+	_BITUL(IP_TUNNEL_DONT_FRAGMENT_BIT) |	\
+	_BITUL(IP_TUNNEL_OAM_BIT) |		\
+	_BITUL(IP_TUNNEL_CRIT_OPT_BIT))
+
 struct fl_flow_key {
 	struct flow_dissector_key_meta meta;
 	struct flow_dissector_key_control control;
@@ -75,6 +81,7 @@ struct fl_flow_key {
 	struct flow_dissector_key_l2tpv3 l2tpv3;
 	struct flow_dissector_key_ipsec ipsec;
 	struct flow_dissector_key_cfm cfm;
+	struct flow_dissector_key_enc_flags enc_flags;
 } __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */
 
 struct fl_flow_mask_range {
@@ -732,6 +739,10 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = {
 	[TCA_FLOWER_KEY_SPI_MASK]	= { .type = NLA_U32 },
 	[TCA_FLOWER_L2_MISS]		= NLA_POLICY_MAX(NLA_U8, 1),
 	[TCA_FLOWER_KEY_CFM]		= { .type = NLA_NESTED },
+	[TCA_FLOWER_KEY_ENC_FLAGS]	= NLA_POLICY_MASK(NLA_U32,
+							  TUNNEL_FLAGS_PRESENT),
+	[TCA_FLOWER_KEY_ENC_FLAGS_MASK]	= NLA_POLICY_MASK(NLA_U32,
+							  TUNNEL_FLAGS_PRESENT),
 };
 
 static const struct nla_policy
@@ -1825,6 +1836,21 @@ static int fl_set_key_cfm(struct nlattr **tb,
 	return 0;
 }
 
+static int fl_set_key_enc_flags(struct nlattr **tb, u32 *flags_key,
+				u32 *flags_mask, struct netlink_ext_ack *extack)
+{
+	/* mask is mandatory for flags */
+	if (NL_REQ_ATTR_CHECK(extack, NULL, tb, TCA_FLOWER_KEY_ENC_FLAGS_MASK)) {
+		NL_SET_ERR_MSG(extack, "missing enc_flags mask");
+		return -EINVAL;
+	}
+
+	*flags_key = nla_get_u32(tb[TCA_FLOWER_KEY_ENC_FLAGS]);
+	*flags_mask = nla_get_u32(tb[TCA_FLOWER_KEY_ENC_FLAGS_MASK]);
+
+	return 0;
+}
+
 static int fl_set_key(struct net *net, struct nlattr **tb,
 		      struct fl_flow_key *key, struct fl_flow_key *mask,
 		      struct netlink_ext_ack *extack)
@@ -2059,9 +2085,16 @@ static int fl_set_key(struct net *net, struct nlattr **tb,
 	if (ret)
 		return ret;
 
-	if (tb[TCA_FLOWER_KEY_FLAGS])
+	if (tb[TCA_FLOWER_KEY_FLAGS]) {
 		ret = fl_set_key_flags(tb, &key->control.flags,
 				       &mask->control.flags, extack);
+		if (ret)
+			return ret;
+	}
+
+	if (tb[TCA_FLOWER_KEY_ENC_FLAGS])
+		ret = fl_set_key_enc_flags(tb, &key->enc_flags.flags,
+					   &mask->enc_flags.flags, extack);
 
 	return ret;
 }
@@ -2175,6 +2208,8 @@ static void fl_init_dissector(struct flow_dissector *dissector,
 			     FLOW_DISSECTOR_KEY_IPSEC, ipsec);
 	FL_KEY_SET_IF_MASKED(mask, keys, cnt,
 			     FLOW_DISSECTOR_KEY_CFM, cfm);
+	FL_KEY_SET_IF_MASKED(mask, keys, cnt,
+			     FLOW_DISSECTOR_KEY_ENC_FLAGS, enc_flags);
 
 	skb_flow_dissector_init(dissector, keys, cnt);
 }
@@ -3291,6 +3326,22 @@ err_cfm_opts:
 	return err;
 }
 
+static int fl_dump_key_enc_flags(struct sk_buff *skb,
+				 struct flow_dissector_key_enc_flags *key,
+				 struct flow_dissector_key_enc_flags *mask)
+{
+	if (!memchr_inv(mask, 0, sizeof(*mask)))
+		return 0;
+
+	if (nla_put_u32(skb, TCA_FLOWER_KEY_ENC_FLAGS, key->flags))
+		return -EMSGSIZE;
+
+	if (nla_put_u32(skb, TCA_FLOWER_KEY_ENC_FLAGS_MASK, mask->flags))
+		return -EMSGSIZE;
+
+	return 0;
+}
+
 static int fl_dump_key_options(struct sk_buff *skb, int enc_opt_type,
 			       struct flow_dissector_key_enc_opts *enc_opts)
 {
@@ -3592,6 +3643,9 @@ static int fl_dump_key(struct sk_buff *skb, struct net *net,
 	if (fl_dump_key_cfm(skb, &key->cfm, &mask->cfm))
 		goto nla_put_failure;
 
+	if (fl_dump_key_enc_flags(skb, &key->enc_flags, &mask->enc_flags))
+		goto nla_put_failure;
+
 	return 0;
 
 nla_put_failure:
-- 
GitLab


From a535d59432370343058755100ee75ab03c0e3f91 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 30 May 2024 16:26:07 -0700
Subject: [PATCH 761/950] net: tls: fix marking packets as decrypted

For TLS offload we mark packets with skb->decrypted to make sure
they don't escape the host without getting encrypted first.
The crypto state lives in the socket, so it may get detached
by a call to skb_orphan(). As a safety check - the egress path
drops all packets with skb->decrypted and no "crypto-safe" socket.

The skb marking was added to sendpage only (and not sendmsg),
because tls_device injected data into the TCP stack using sendpage.
This special case was missed when sendpage got folded into sendmsg.

Fixes: c5c37af6ecad ("tcp: Convert do_tcp_sendpages() to use MSG_SPLICE_PAGES")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20240530232607.82686-1-kuba@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/ipv4/tcp.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 681b54e1f3a64..4d8cc2ebb64c7 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1165,6 +1165,9 @@ new_segment:
 
 			process_backlog++;
 
+#ifdef CONFIG_SKB_DECRYPTED
+			skb->decrypted = !!(flags & MSG_SENDPAGE_DECRYPTED);
+#endif
 			tcp_skb_entail(sk, skb);
 			copy = size_goal;
 
-- 
GitLab


From 071115301838c6c265065dd5d6bf43a9a987a550 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 30 May 2024 16:36:14 -0700
Subject: [PATCH 762/950] tcp: wrap mptcp and decrypted checks into
 tcp_skb_can_collapse_rx()

tcp_skb_can_collapse() checks for conditions which don't make
sense on input. Because of this we ended up sprinkling a few
pairs of mptcp_skb_can_collapse() and skb_cmp_decrypted() calls
on the input path. Group them in a new helper. This should make
it less likely that someone will check mptcp and not decrypted
or vice versa when adding new code.

This implicitly adds a decrypted check early in tcp_collapse().
AFAIU this will very slightly increase our ability to collapse
packets under memory pressure, not a real bug.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/net/tcp.h    |  7 +++++++
 net/ipv4/tcp_input.c | 11 +++--------
 net/ipv4/tcp_ipv4.c  |  3 +--
 3 files changed, 11 insertions(+), 10 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 32815a40dea16..32741856da015 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1071,6 +1071,13 @@ static inline bool tcp_skb_can_collapse(const struct sk_buff *to,
 		      skb_pure_zcopy_same(to, from));
 }
 
+static inline bool tcp_skb_can_collapse_rx(const struct sk_buff *to,
+					   const struct sk_buff *from)
+{
+	return likely(mptcp_skb_can_collapse(to, from) &&
+		      !skb_cmp_decrypted(to, from));
+}
+
 /* Events passed to congestion control interface */
 enum tcp_ca_event {
 	CA_EVENT_TX_START,	/* first transmit when no packets in flight */
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 5aadf64e554d8..212b6fd0caf76 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4813,10 +4813,7 @@ static bool tcp_try_coalesce(struct sock *sk,
 	if (TCP_SKB_CB(from)->seq != TCP_SKB_CB(to)->end_seq)
 		return false;
 
-	if (!mptcp_skb_can_collapse(to, from))
-		return false;
-
-	if (skb_cmp_decrypted(from, to))
+	if (!tcp_skb_can_collapse_rx(to, from))
 		return false;
 
 	if (!skb_try_coalesce(to, from, fragstolen, &delta))
@@ -5372,7 +5369,7 @@ restart:
 			break;
 		}
 
-		if (n && n != tail && mptcp_skb_can_collapse(skb, n) &&
+		if (n && n != tail && tcp_skb_can_collapse_rx(skb, n) &&
 		    TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(n)->seq) {
 			end_of_skbs = false;
 			break;
@@ -5423,11 +5420,9 @@ restart:
 				skb = tcp_collapse_one(sk, skb, list, root);
 				if (!skb ||
 				    skb == tail ||
-				    !mptcp_skb_can_collapse(nskb, skb) ||
+				    !tcp_skb_can_collapse_rx(nskb, skb) ||
 				    (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)))
 					goto end;
-				if (skb_cmp_decrypted(skb, nskb))
-					goto end;
 			}
 		}
 	}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 59d5b064f2334..04044605cadf1 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2044,8 +2044,7 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb,
 	      TCP_SKB_CB(skb)->tcp_flags) & TCPHDR_ACK) ||
 	    ((TCP_SKB_CB(tail)->tcp_flags ^
 	      TCP_SKB_CB(skb)->tcp_flags) & (TCPHDR_ECE | TCPHDR_CWR)) ||
-	    !mptcp_skb_can_collapse(tail, skb) ||
-	    skb_cmp_decrypted(tail, skb) ||
+	    !tcp_skb_can_collapse_rx(tail, skb) ||
 	    thtail->doff != th->doff ||
 	    memcmp(thtail + 1, th + 1, hdrlen - sizeof(*th)))
 		goto no_coalesce;
-- 
GitLab


From 1be68a87ab333af37b02ad928a724a722a5a8203 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 30 May 2024 16:36:15 -0700
Subject: [PATCH 763/950] tcp: add a helper for setting EOR on tail skb

TLS (and hopefully soon PSP will) use EOR to prevent skbs
with different decrypted state from getting merged, without
adding new tests to the skb handling. In both cases once
the connection switches to an "encrypted" state, all subsequent
skbs will be encrypted, so a single "EOR fence" is sufficient
to prevent mixing.

Add a helper for setting the EOR bit, to make this arrangement
more explicit.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/net/tcp.h    |  9 +++++++++
 net/tls/tls_device.c | 11 ++---------
 2 files changed, 11 insertions(+), 9 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 32741856da015..08c3b99501cf6 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1066,6 +1066,7 @@ static inline bool tcp_skb_can_collapse_to(const struct sk_buff *skb)
 static inline bool tcp_skb_can_collapse(const struct sk_buff *to,
 					const struct sk_buff *from)
 {
+	/* skb_cmp_decrypted() not needed, use tcp_write_collapse_fence() */
 	return likely(tcp_skb_can_collapse_to(to) &&
 		      mptcp_skb_can_collapse(to, from) &&
 		      skb_pure_zcopy_same(to, from));
@@ -2102,6 +2103,14 @@ static inline void tcp_rtx_queue_unlink_and_free(struct sk_buff *skb, struct soc
 	tcp_wmem_free_skb(sk, skb);
 }
 
+static inline void tcp_write_collapse_fence(struct sock *sk)
+{
+	struct sk_buff *skb = tcp_write_queue_tail(sk);
+
+	if (skb)
+		TCP_SKB_CB(skb)->eor = 1;
+}
+
 static inline void tcp_push_pending_frames(struct sock *sk)
 {
 	if (tcp_send_head(sk)) {
diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index ab6e694f7bc25..dc063c2c7950e 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -231,14 +231,10 @@ static void tls_device_resync_tx(struct sock *sk, struct tls_context *tls_ctx,
 				 u32 seq)
 {
 	struct net_device *netdev;
-	struct sk_buff *skb;
 	int err = 0;
 	u8 *rcd_sn;
 
-	skb = tcp_write_queue_tail(sk);
-	if (skb)
-		TCP_SKB_CB(skb)->eor = 1;
-
+	tcp_write_collapse_fence(sk);
 	rcd_sn = tls_ctx->tx.rec_seq;
 
 	trace_tls_device_tx_resync_send(sk, seq, rcd_sn);
@@ -1067,7 +1063,6 @@ int tls_set_device_offload(struct sock *sk)
 	struct tls_prot_info *prot;
 	struct net_device *netdev;
 	struct tls_context *ctx;
-	struct sk_buff *skb;
 	char *iv, *rec_seq;
 	int rc;
 
@@ -1138,9 +1133,7 @@ int tls_set_device_offload(struct sock *sk)
 	 * SKBs where only part of the payload needs to be encrypted.
 	 * So mark the last skb in the write queue as end of record.
 	 */
-	skb = tcp_write_queue_tail(sk);
-	if (skb)
-		TCP_SKB_CB(skb)->eor = 1;
+	tcp_write_collapse_fence(sk);
 
 	/* Avoid offloading if the device is down
 	 * We don't want to offload new flows after
-- 
GitLab


From 99b8add01f98a8ecf498de1467e8bf13dbf02daa Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 30 May 2024 16:36:16 -0700
Subject: [PATCH 764/950] net: skb: add compatibility warnings to skb_shift()

According to current semantics we should never try to shift data
between skbs which differ on decrypted or pp_recycle status.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/core/skbuff.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 466999a7515e6..c8ac79851cd67 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4139,6 +4139,9 @@ int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen)
 	if (skb_zcopy(tgt) || skb_zcopy(skb))
 		return 0;
 
+	DEBUG_NET_WARN_ON_ONCE(tgt->pp_recycle != skb->pp_recycle);
+	DEBUG_NET_WARN_ON_ONCE(skb_cmp_decrypted(tgt, skb));
+
 	todo = shiftlen;
 	from = 0;
 	to = skb_shinfo(tgt)->nr_frags;
-- 
GitLab


From 87bb39ed40bdf1596b8820e800226e24eb642677 Mon Sep 17 00:00:00 2001
From: Fuad Tabba <tabba@google.com>
Date: Mon, 3 Jun 2024 13:28:43 +0100
Subject: [PATCH 765/950] KVM: arm64: Reintroduce __sve_save_state

Now that the hypervisor is handling the host sve state in
protected mode, it needs to be able to save it.

This reverts commit e66425fc9ba3 ("KVM: arm64: Remove unused
__sve_save_state").

Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Fuad Tabba <tabba@google.com>
Link: https://lore.kernel.org/r/20240603122852.3923848-2-tabba@google.com
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_hyp.h | 1 +
 arch/arm64/kvm/hyp/fpsimd.S      | 6 ++++++
 2 files changed, 7 insertions(+)

diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
index 3e80464f89531..2ab23589339a0 100644
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -111,6 +111,7 @@ void __debug_restore_host_buffers_nvhe(struct kvm_vcpu *vcpu);
 
 void __fpsimd_save_state(struct user_fpsimd_state *fp_regs);
 void __fpsimd_restore_state(struct user_fpsimd_state *fp_regs);
+void __sve_save_state(void *sve_pffr, u32 *fpsr);
 void __sve_restore_state(void *sve_pffr, u32 *fpsr);
 
 u64 __guest_enter(struct kvm_vcpu *vcpu);
diff --git a/arch/arm64/kvm/hyp/fpsimd.S b/arch/arm64/kvm/hyp/fpsimd.S
index 61e6f3ba7b7d1..e950875e31cee 100644
--- a/arch/arm64/kvm/hyp/fpsimd.S
+++ b/arch/arm64/kvm/hyp/fpsimd.S
@@ -25,3 +25,9 @@ SYM_FUNC_START(__sve_restore_state)
 	sve_load 0, x1, x2, 3
 	ret
 SYM_FUNC_END(__sve_restore_state)
+
+SYM_FUNC_START(__sve_save_state)
+	mov	x2, #1
+	sve_save 0, x1, x2, 3
+	ret
+SYM_FUNC_END(__sve_save_state)
-- 
GitLab


From 45f4ea9bcfe909b3461059990b1e232e55dde809 Mon Sep 17 00:00:00 2001
From: Fuad Tabba <tabba@google.com>
Date: Mon, 3 Jun 2024 13:28:44 +0100
Subject: [PATCH 766/950] KVM: arm64: Fix prototype for
 __sve_save_state/__sve_restore_state

Since the prototypes for __sve_save_state/__sve_restore_state at
hyp were added, the underlying macro has acquired a third
parameter for saving/restoring ffr.

Fix the prototypes to account for the third parameter, and
restore the ffr for the guest since it is saved.

Suggested-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Fuad Tabba <tabba@google.com>
Reviewed-by: Mark Brown <broonie@kernel.org>
Link: https://lore.kernel.org/r/20240603122852.3923848-3-tabba@google.com
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_hyp.h        | 4 ++--
 arch/arm64/kvm/hyp/include/hyp/switch.h | 3 ++-
 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
index 2ab23589339a0..686cce7e4e96c 100644
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -111,8 +111,8 @@ void __debug_restore_host_buffers_nvhe(struct kvm_vcpu *vcpu);
 
 void __fpsimd_save_state(struct user_fpsimd_state *fp_regs);
 void __fpsimd_restore_state(struct user_fpsimd_state *fp_regs);
-void __sve_save_state(void *sve_pffr, u32 *fpsr);
-void __sve_restore_state(void *sve_pffr, u32 *fpsr);
+void __sve_save_state(void *sve_pffr, u32 *fpsr, int save_ffr);
+void __sve_restore_state(void *sve_pffr, u32 *fpsr, int restore_ffr);
 
 u64 __guest_enter(struct kvm_vcpu *vcpu);
 
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index a92566f36022e..d58933ae8fd5c 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -316,7 +316,8 @@ static inline void __hyp_sve_restore_guest(struct kvm_vcpu *vcpu)
 {
 	sve_cond_update_zcr_vq(vcpu_sve_max_vq(vcpu) - 1, SYS_ZCR_EL2);
 	__sve_restore_state(vcpu_sve_pffr(vcpu),
-			    &vcpu->arch.ctxt.fp_regs.fpsr);
+			    &vcpu->arch.ctxt.fp_regs.fpsr,
+			    true);
 	write_sysreg_el1(__vcpu_sys_reg(vcpu, ZCR_EL1), SYS_ZCR);
 }
 
-- 
GitLab


From 6d8fb3cbf7e06431a607c30c1bc4cd53a62c220a Mon Sep 17 00:00:00 2001
From: Fuad Tabba <tabba@google.com>
Date: Mon, 3 Jun 2024 13:28:45 +0100
Subject: [PATCH 767/950] KVM: arm64: Abstract set/clear of CPTR_EL2 bits
 behind helper

The same traps controlled by CPTR_EL2 or CPACR_EL1 need to be
toggled in different parts of the code, but the exact bits and
their polarity differ between these two formats and the mode
(vhe/nvhe/hvhe).

To reduce the amount of duplicated code and the chance of getting
the wrong bit/polarity or missing a field, abstract the set/clear
of CPTR_EL2 bits behind a helper.

Since (h)VHE is the way of the future, use the CPACR_EL1 format,
which is a subset of the VHE CPTR_EL2, as a reference.

No functional change intended.

Suggested-by: Oliver Upton <oliver.upton@linux.dev>
Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Fuad Tabba <tabba@google.com>
Link: https://lore.kernel.org/r/20240603122852.3923848-4-tabba@google.com
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_arm.h        |  6 +++
 arch/arm64/include/asm/kvm_emulate.h    | 62 +++++++++++++++++++++++++
 arch/arm64/kvm/hyp/include/hyp/switch.h | 18 ++-----
 arch/arm64/kvm/hyp/nvhe/hyp-main.c      |  6 +--
 4 files changed, 73 insertions(+), 19 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index e01bb5ca13b7c..b2adc2c6c82a5 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -305,6 +305,12 @@
 				 GENMASK(19, 14) |	\
 				 BIT(11))
 
+#define CPTR_VHE_EL2_RES0	(GENMASK(63, 32) |	\
+				 GENMASK(27, 26) |	\
+				 GENMASK(23, 22) |	\
+				 GENMASK(19, 18) |	\
+				 GENMASK(15, 0))
+
 /* Hyp Debug Configuration Register bits */
 #define MDCR_EL2_E2TB_MASK	(UL(0x3))
 #define MDCR_EL2_E2TB_SHIFT	(UL(24))
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 501e3e019c930..2d7a0bdf9d03f 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -557,6 +557,68 @@ static __always_inline void kvm_incr_pc(struct kvm_vcpu *vcpu)
 		vcpu_set_flag((v), e);					\
 	} while (0)
 
+#define __build_check_all_or_none(r, bits)				\
+	BUILD_BUG_ON(((r) & (bits)) && ((r) & (bits)) != (bits))
+
+#define __cpacr_to_cptr_clr(clr, set)					\
+	({								\
+		u64 cptr = 0;						\
+									\
+		if ((set) & CPACR_ELx_FPEN)				\
+			cptr |= CPTR_EL2_TFP;				\
+		if ((set) & CPACR_ELx_ZEN)				\
+			cptr |= CPTR_EL2_TZ;				\
+		if ((set) & CPACR_ELx_SMEN)				\
+			cptr |= CPTR_EL2_TSM;				\
+		if ((clr) & CPACR_ELx_TTA)				\
+			cptr |= CPTR_EL2_TTA;				\
+		if ((clr) & CPTR_EL2_TAM)				\
+			cptr |= CPTR_EL2_TAM;				\
+		if ((clr) & CPTR_EL2_TCPAC)				\
+			cptr |= CPTR_EL2_TCPAC;				\
+									\
+		cptr;							\
+	})
+
+#define __cpacr_to_cptr_set(clr, set)					\
+	({								\
+		u64 cptr = 0;						\
+									\
+		if ((clr) & CPACR_ELx_FPEN)				\
+			cptr |= CPTR_EL2_TFP;				\
+		if ((clr) & CPACR_ELx_ZEN)				\
+			cptr |= CPTR_EL2_TZ;				\
+		if ((clr) & CPACR_ELx_SMEN)				\
+			cptr |= CPTR_EL2_TSM;				\
+		if ((set) & CPACR_ELx_TTA)				\
+			cptr |= CPTR_EL2_TTA;				\
+		if ((set) & CPTR_EL2_TAM)				\
+			cptr |= CPTR_EL2_TAM;				\
+		if ((set) & CPTR_EL2_TCPAC)				\
+			cptr |= CPTR_EL2_TCPAC;				\
+									\
+		cptr;							\
+	})
+
+#define cpacr_clear_set(clr, set)					\
+	do {								\
+		BUILD_BUG_ON((set) & CPTR_VHE_EL2_RES0);		\
+		BUILD_BUG_ON((clr) & CPACR_ELx_E0POE);			\
+		__build_check_all_or_none((clr), CPACR_ELx_FPEN);	\
+		__build_check_all_or_none((set), CPACR_ELx_FPEN);	\
+		__build_check_all_or_none((clr), CPACR_ELx_ZEN);	\
+		__build_check_all_or_none((set), CPACR_ELx_ZEN);	\
+		__build_check_all_or_none((clr), CPACR_ELx_SMEN);	\
+		__build_check_all_or_none((set), CPACR_ELx_SMEN);	\
+									\
+		if (has_vhe() || has_hvhe())				\
+			sysreg_clear_set(cpacr_el1, clr, set);		\
+		else							\
+			sysreg_clear_set(cptr_el2,			\
+					 __cpacr_to_cptr_clr(clr, set),	\
+					 __cpacr_to_cptr_set(clr, set));\
+	} while (0)
+
 static __always_inline void kvm_write_cptr_el2(u64 val)
 {
 	if (has_vhe() || has_hvhe())
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index d58933ae8fd5c..055d2ca7264e0 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -331,7 +331,6 @@ static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code)
 {
 	bool sve_guest;
 	u8 esr_ec;
-	u64 reg;
 
 	if (!system_supports_fpsimd())
 		return false;
@@ -354,19 +353,10 @@ static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code)
 	/* Valid trap.  Switch the context: */
 
 	/* First disable enough traps to allow us to update the registers */
-	if (has_vhe() || has_hvhe()) {
-		reg = CPACR_EL1_FPEN_EL0EN | CPACR_EL1_FPEN_EL1EN;
-		if (sve_guest)
-			reg |= CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN;
-
-		sysreg_clear_set(cpacr_el1, 0, reg);
-	} else {
-		reg = CPTR_EL2_TFP;
-		if (sve_guest)
-			reg |= CPTR_EL2_TZ;
-
-		sysreg_clear_set(cptr_el2, reg, 0);
-	}
+	if (sve_guest)
+		cpacr_clear_set(0, CPACR_ELx_FPEN | CPACR_ELx_ZEN);
+	else
+		cpacr_clear_set(0, CPACR_ELx_FPEN);
 	isb();
 
 	/* Write out the host state if it's in the registers */
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
index d5c48dc98f679..f71394d0e32a7 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
@@ -405,11 +405,7 @@ void handle_trap(struct kvm_cpu_context *host_ctxt)
 		handle_host_smc(host_ctxt);
 		break;
 	case ESR_ELx_EC_SVE:
-		if (has_hvhe())
-			sysreg_clear_set(cpacr_el1, 0, (CPACR_EL1_ZEN_EL1EN |
-							CPACR_EL1_ZEN_EL0EN));
-		else
-			sysreg_clear_set(cptr_el2, CPTR_EL2_TZ, 0);
+		cpacr_clear_set(0, CPACR_ELx_ZEN);
 		isb();
 		sve_cond_update_zcr_vq(ZCR_ELx_LEN_MASK, SYS_ZCR_EL2);
 		break;
-- 
GitLab


From e511e08a9f496948b13aac50610f2d17335f56c3 Mon Sep 17 00:00:00 2001
From: Fuad Tabba <tabba@google.com>
Date: Mon, 3 Jun 2024 13:28:46 +0100
Subject: [PATCH 768/950] KVM: arm64: Specialize handling of host fpsimd state
 on trap

In subsequent patches, n/vhe will diverge on saving the host
fpsimd/sve state when taking a guest fpsimd/sve trap. Add a
specialized helper to handle it.

No functional change intended.

Reviewed-by: Mark Brown <broonie@kernel.org>
Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Fuad Tabba <tabba@google.com>
Link: https://lore.kernel.org/r/20240603122852.3923848-5-tabba@google.com
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/hyp/include/hyp/switch.h | 4 +++-
 arch/arm64/kvm/hyp/nvhe/switch.c        | 5 +++++
 arch/arm64/kvm/hyp/vhe/switch.c         | 5 +++++
 3 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index 055d2ca7264e0..9b904c858df08 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -321,6 +321,8 @@ static inline void __hyp_sve_restore_guest(struct kvm_vcpu *vcpu)
 	write_sysreg_el1(__vcpu_sys_reg(vcpu, ZCR_EL1), SYS_ZCR);
 }
 
+static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu);
+
 /*
  * We trap the first access to the FP/SIMD to save the host context and
  * restore the guest context lazily.
@@ -361,7 +363,7 @@ static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code)
 
 	/* Write out the host state if it's in the registers */
 	if (host_owns_fp_regs())
-		__fpsimd_save_state(*host_data_ptr(fpsimd_state));
+		kvm_hyp_save_fpsimd_host(vcpu);
 
 	/* Restore the guest state */
 	if (sve_guest)
diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c
index 6758cd9055706..019f863922fa4 100644
--- a/arch/arm64/kvm/hyp/nvhe/switch.c
+++ b/arch/arm64/kvm/hyp/nvhe/switch.c
@@ -182,6 +182,11 @@ static bool kvm_handle_pvm_sys64(struct kvm_vcpu *vcpu, u64 *exit_code)
 		kvm_handle_pvm_sysreg(vcpu, exit_code));
 }
 
+static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu)
+{
+	__fpsimd_save_state(*host_data_ptr(fpsimd_state));
+}
+
 static const exit_handler_fn hyp_exit_handlers[] = {
 	[0 ... ESR_ELx_EC_MAX]		= NULL,
 	[ESR_ELx_EC_CP15_32]		= kvm_hyp_handle_cp15_32,
diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index d7af5f46f22a3..20073579e9f5b 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -262,6 +262,11 @@ static bool kvm_hyp_handle_eret(struct kvm_vcpu *vcpu, u64 *exit_code)
 	return true;
 }
 
+static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu)
+{
+	__fpsimd_save_state(*host_data_ptr(fpsimd_state));
+}
+
 static const exit_handler_fn hyp_exit_handlers[] = {
 	[0 ... ESR_ELx_EC_MAX]		= NULL,
 	[ESR_ELx_EC_CP15_32]		= kvm_hyp_handle_cp15_32,
-- 
GitLab


From 66d5b53e20a6e00b7ce3b652a3e2db967f7b33d0 Mon Sep 17 00:00:00 2001
From: Fuad Tabba <tabba@google.com>
Date: Mon, 3 Jun 2024 13:28:47 +0100
Subject: [PATCH 769/950] KVM: arm64: Allocate memory mapped at hyp for host
 sve state in pKVM

Protected mode needs to maintain (save/restore) the host's sve
state, rather than relying on the host kernel to do that. This is
to avoid leaking information to the host about guests and the
type of operations they are performing.

As a first step towards that, allocate memory mapped at hyp, per
cpu, for the host sve state. The following patch will use this
memory to save/restore the host state.

Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Fuad Tabba <tabba@google.com>
Link: https://lore.kernel.org/r/20240603122852.3923848-6-tabba@google.com
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_host.h | 17 ++++++++
 arch/arm64/include/asm/kvm_hyp.h  |  1 +
 arch/arm64/include/asm/kvm_pkvm.h |  9 ++++
 arch/arm64/kvm/arm.c              | 68 +++++++++++++++++++++++++++++++
 arch/arm64/kvm/hyp/nvhe/pkvm.c    |  2 +
 arch/arm64/kvm/hyp/nvhe/setup.c   | 24 +++++++++++
 arch/arm64/kvm/reset.c            |  3 ++
 7 files changed, 124 insertions(+)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 8170c04fde914..90df7ccec5f4f 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -76,6 +76,7 @@ static inline enum kvm_mode kvm_get_mode(void) { return KVM_MODE_NONE; };
 DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use);
 
 extern unsigned int __ro_after_init kvm_sve_max_vl;
+extern unsigned int __ro_after_init kvm_host_sve_max_vl;
 int __init kvm_arm_init_sve(void);
 
 u32 __attribute_const__ kvm_target_cpu(void);
@@ -521,6 +522,20 @@ struct kvm_cpu_context {
 	u64 *vncr_array;
 };
 
+struct cpu_sve_state {
+	__u64 zcr_el1;
+
+	/*
+	 * Ordering is important since __sve_save_state/__sve_restore_state
+	 * relies on it.
+	 */
+	__u32 fpsr;
+	__u32 fpcr;
+
+	/* Must be SVE_VQ_BYTES (128 bit) aligned. */
+	__u8 sve_regs[];
+};
+
 /*
  * This structure is instantiated on a per-CPU basis, and contains
  * data that is:
@@ -534,7 +549,9 @@ struct kvm_cpu_context {
  */
 struct kvm_host_data {
 	struct kvm_cpu_context host_ctxt;
+
 	struct user_fpsimd_state *fpsimd_state;	/* hyp VA */
+	struct cpu_sve_state *sve_state;	/* hyp VA */
 
 	/* Ownership of the FP regs */
 	enum {
diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
index 686cce7e4e96c..b05bceca33850 100644
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -143,5 +143,6 @@ extern u64 kvm_nvhe_sym(id_aa64smfr0_el1_sys_val);
 
 extern unsigned long kvm_nvhe_sym(__icache_flags);
 extern unsigned int kvm_nvhe_sym(kvm_arm_vmid_bits);
+extern unsigned int kvm_nvhe_sym(kvm_host_sve_max_vl);
 
 #endif /* __ARM64_KVM_HYP_H__ */
diff --git a/arch/arm64/include/asm/kvm_pkvm.h b/arch/arm64/include/asm/kvm_pkvm.h
index ad9cfb5c1ff4e..cd56acd9a842c 100644
--- a/arch/arm64/include/asm/kvm_pkvm.h
+++ b/arch/arm64/include/asm/kvm_pkvm.h
@@ -128,4 +128,13 @@ static inline unsigned long hyp_ffa_proxy_pages(void)
 	return (2 * KVM_FFA_MBOX_NR_PAGES) + DIV_ROUND_UP(desc_max, PAGE_SIZE);
 }
 
+static inline size_t pkvm_host_sve_state_size(void)
+{
+	if (!system_supports_sve())
+		return 0;
+
+	return size_add(sizeof(struct cpu_sve_state),
+			SVE_SIG_REGS_SIZE(sve_vq_from_vl(kvm_host_sve_max_vl)));
+}
+
 #endif	/* __ARM64_KVM_PKVM_H__ */
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 9996a989b52e8..1acf7415e831b 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -1931,6 +1931,11 @@ static unsigned long nvhe_percpu_order(void)
 	return size ? get_order(size) : 0;
 }
 
+static size_t pkvm_host_sve_state_order(void)
+{
+	return get_order(pkvm_host_sve_state_size());
+}
+
 /* A lookup table holding the hypervisor VA for each vector slot */
 static void *hyp_spectre_vector_selector[BP_HARDEN_EL2_SLOTS];
 
@@ -2310,12 +2315,20 @@ static void __init teardown_subsystems(void)
 
 static void __init teardown_hyp_mode(void)
 {
+	bool free_sve = system_supports_sve() && is_protected_kvm_enabled();
 	int cpu;
 
 	free_hyp_pgds();
 	for_each_possible_cpu(cpu) {
 		free_page(per_cpu(kvm_arm_hyp_stack_page, cpu));
 		free_pages(kvm_nvhe_sym(kvm_arm_hyp_percpu_base)[cpu], nvhe_percpu_order());
+
+		if (free_sve) {
+			struct cpu_sve_state *sve_state;
+
+			sve_state = per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->sve_state;
+			free_pages((unsigned long) sve_state, pkvm_host_sve_state_order());
+		}
 	}
 }
 
@@ -2398,6 +2411,50 @@ static int __init kvm_hyp_init_protection(u32 hyp_va_bits)
 	return 0;
 }
 
+static int init_pkvm_host_sve_state(void)
+{
+	int cpu;
+
+	if (!system_supports_sve())
+		return 0;
+
+	/* Allocate pages for host sve state in protected mode. */
+	for_each_possible_cpu(cpu) {
+		struct page *page = alloc_pages(GFP_KERNEL, pkvm_host_sve_state_order());
+
+		if (!page)
+			return -ENOMEM;
+
+		per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->sve_state = page_address(page);
+	}
+
+	/*
+	 * Don't map the pages in hyp since these are only used in protected
+	 * mode, which will (re)create its own mapping when initialized.
+	 */
+
+	return 0;
+}
+
+/*
+ * Finalizes the initialization of hyp mode, once everything else is initialized
+ * and the initialziation process cannot fail.
+ */
+static void finalize_init_hyp_mode(void)
+{
+	int cpu;
+
+	if (!is_protected_kvm_enabled() || !system_supports_sve())
+		return;
+
+	for_each_possible_cpu(cpu) {
+		struct cpu_sve_state *sve_state;
+
+		sve_state = per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->sve_state;
+		per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->sve_state = kern_hyp_va(sve_state);
+	}
+}
+
 static void pkvm_hyp_init_ptrauth(void)
 {
 	struct kvm_cpu_context *hyp_ctxt;
@@ -2566,6 +2623,10 @@ static int __init init_hyp_mode(void)
 			goto out_err;
 		}
 
+		err = init_pkvm_host_sve_state();
+		if (err)
+			goto out_err;
+
 		err = kvm_hyp_init_protection(hyp_va_bits);
 		if (err) {
 			kvm_err("Failed to init hyp memory protection\n");
@@ -2730,6 +2791,13 @@ static __init int kvm_arm_init(void)
 	if (err)
 		goto out_subs;
 
+	/*
+	 * This should be called after initialization is done and failure isn't
+	 * possible anymore.
+	 */
+	if (!in_hyp_mode)
+		finalize_init_hyp_mode();
+
 	kvm_arm_initialised = true;
 
 	return 0;
diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c
index 16aa4875ddb8c..25e9a94f6d764 100644
--- a/arch/arm64/kvm/hyp/nvhe/pkvm.c
+++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c
@@ -18,6 +18,8 @@ unsigned long __icache_flags;
 /* Used by kvm_get_vttbr(). */
 unsigned int kvm_arm_vmid_bits;
 
+unsigned int kvm_host_sve_max_vl;
+
 /*
  * Set trap register values based on features in ID_AA64PFR0.
  */
diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c
index 859f22f754d37..3fae424795982 100644
--- a/arch/arm64/kvm/hyp/nvhe/setup.c
+++ b/arch/arm64/kvm/hyp/nvhe/setup.c
@@ -67,6 +67,28 @@ static int divide_memory_pool(void *virt, unsigned long size)
 	return 0;
 }
 
+static int pkvm_create_host_sve_mappings(void)
+{
+	void *start, *end;
+	int ret, i;
+
+	if (!system_supports_sve())
+		return 0;
+
+	for (i = 0; i < hyp_nr_cpus; i++) {
+		struct kvm_host_data *host_data = per_cpu_ptr(&kvm_host_data, i);
+		struct cpu_sve_state *sve_state = host_data->sve_state;
+
+		start = kern_hyp_va(sve_state);
+		end = start + PAGE_ALIGN(pkvm_host_sve_state_size());
+		ret = pkvm_create_mappings(start, end, PAGE_HYP);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
 static int recreate_hyp_mappings(phys_addr_t phys, unsigned long size,
 				 unsigned long *per_cpu_base,
 				 u32 hyp_va_bits)
@@ -125,6 +147,8 @@ static int recreate_hyp_mappings(phys_addr_t phys, unsigned long size,
 			return ret;
 	}
 
+	pkvm_create_host_sve_mappings();
+
 	/*
 	 * Map the host sections RO in the hypervisor, but transfer the
 	 * ownership from the host to the hypervisor itself to make sure they
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index 1b7b58cb121f9..3fc8ca164dbe4 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -32,6 +32,7 @@
 
 /* Maximum phys_shift supported for any VM on this host */
 static u32 __ro_after_init kvm_ipa_limit;
+unsigned int __ro_after_init kvm_host_sve_max_vl;
 
 /*
  * ARMv8 Reset Values
@@ -51,6 +52,8 @@ int __init kvm_arm_init_sve(void)
 {
 	if (system_supports_sve()) {
 		kvm_sve_max_vl = sve_max_virtualisable_vl();
+		kvm_host_sve_max_vl = sve_max_vl();
+		kvm_nvhe_sym(kvm_host_sve_max_vl) = kvm_host_sve_max_vl;
 
 		/*
 		 * The get_sve_reg()/set_sve_reg() ioctl interface will need
-- 
GitLab


From b5b9955617bc0b41546f2fa7c3dbcc048b43dc82 Mon Sep 17 00:00:00 2001
From: Fuad Tabba <tabba@google.com>
Date: Mon, 3 Jun 2024 13:28:48 +0100
Subject: [PATCH 770/950] KVM: arm64: Eagerly restore host fpsimd/sve state in
 pKVM

When running in protected mode we don't want to leak protected
guest state to the host, including whether a guest has used
fpsimd/sve. Therefore, eagerly restore the host state on guest
exit when running in protected mode, which happens only if the
guest has used fpsimd/sve.

Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Fuad Tabba <tabba@google.com>
Link: https://lore.kernel.org/r/20240603122852.3923848-7-tabba@google.com
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/hyp/include/hyp/switch.h | 13 ++++-
 arch/arm64/kvm/hyp/nvhe/hyp-main.c      | 67 +++++++++++++++++++++++--
 arch/arm64/kvm/hyp/nvhe/pkvm.c          |  2 +
 arch/arm64/kvm/hyp/nvhe/switch.c        | 16 +++++-
 4 files changed, 93 insertions(+), 5 deletions(-)

diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index 9b904c858df08..0c4de44534b7a 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -321,6 +321,17 @@ static inline void __hyp_sve_restore_guest(struct kvm_vcpu *vcpu)
 	write_sysreg_el1(__vcpu_sys_reg(vcpu, ZCR_EL1), SYS_ZCR);
 }
 
+static inline void __hyp_sve_save_host(void)
+{
+	struct cpu_sve_state *sve_state = *host_data_ptr(sve_state);
+
+	sve_state->zcr_el1 = read_sysreg_el1(SYS_ZCR);
+	write_sysreg_s(ZCR_ELx_LEN_MASK, SYS_ZCR_EL2);
+	__sve_save_state(sve_state->sve_regs + sve_ffr_offset(kvm_host_sve_max_vl),
+			 &sve_state->fpsr,
+			 true);
+}
+
 static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu);
 
 /*
@@ -355,7 +366,7 @@ static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code)
 	/* Valid trap.  Switch the context: */
 
 	/* First disable enough traps to allow us to update the registers */
-	if (sve_guest)
+	if (sve_guest || (is_protected_kvm_enabled() && system_supports_sve()))
 		cpacr_clear_set(0, CPACR_ELx_FPEN | CPACR_ELx_ZEN);
 	else
 		cpacr_clear_set(0, CPACR_ELx_FPEN);
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
index f71394d0e32a7..bd93b8a9e1726 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
@@ -23,20 +23,80 @@ DEFINE_PER_CPU(struct kvm_nvhe_init_params, kvm_init_params);
 
 void __kvm_hyp_host_forward_smc(struct kvm_cpu_context *host_ctxt);
 
+static void __hyp_sve_save_guest(struct kvm_vcpu *vcpu)
+{
+	__vcpu_sys_reg(vcpu, ZCR_EL1) = read_sysreg_el1(SYS_ZCR);
+	/*
+	 * On saving/restoring guest sve state, always use the maximum VL for
+	 * the guest. The layout of the data when saving the sve state depends
+	 * on the VL, so use a consistent (i.e., the maximum) guest VL.
+	 */
+	sve_cond_update_zcr_vq(vcpu_sve_max_vq(vcpu) - 1, SYS_ZCR_EL2);
+	__sve_save_state(vcpu_sve_pffr(vcpu), &vcpu->arch.ctxt.fp_regs.fpsr, true);
+	write_sysreg_s(ZCR_ELx_LEN_MASK, SYS_ZCR_EL2);
+}
+
+static void __hyp_sve_restore_host(void)
+{
+	struct cpu_sve_state *sve_state = *host_data_ptr(sve_state);
+
+	/*
+	 * On saving/restoring host sve state, always use the maximum VL for
+	 * the host. The layout of the data when saving the sve state depends
+	 * on the VL, so use a consistent (i.e., the maximum) host VL.
+	 *
+	 * Setting ZCR_EL2 to ZCR_ELx_LEN_MASK sets the effective length
+	 * supported by the system (or limited at EL3).
+	 */
+	write_sysreg_s(ZCR_ELx_LEN_MASK, SYS_ZCR_EL2);
+	__sve_restore_state(sve_state->sve_regs + sve_ffr_offset(kvm_host_sve_max_vl),
+			    &sve_state->fpsr,
+			    true);
+	write_sysreg_el1(sve_state->zcr_el1, SYS_ZCR);
+}
+
+static void fpsimd_sve_flush(void)
+{
+	*host_data_ptr(fp_owner) = FP_STATE_HOST_OWNED;
+}
+
+static void fpsimd_sve_sync(struct kvm_vcpu *vcpu)
+{
+	if (!guest_owns_fp_regs())
+		return;
+
+	cpacr_clear_set(0, CPACR_ELx_FPEN | CPACR_ELx_ZEN);
+	isb();
+
+	if (vcpu_has_sve(vcpu))
+		__hyp_sve_save_guest(vcpu);
+	else
+		__fpsimd_save_state(&vcpu->arch.ctxt.fp_regs);
+
+	if (system_supports_sve())
+		__hyp_sve_restore_host();
+	else
+		__fpsimd_restore_state(*host_data_ptr(fpsimd_state));
+
+	*host_data_ptr(fp_owner) = FP_STATE_HOST_OWNED;
+}
+
 static void flush_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu)
 {
 	struct kvm_vcpu *host_vcpu = hyp_vcpu->host_vcpu;
 
+	fpsimd_sve_flush();
+
 	hyp_vcpu->vcpu.arch.ctxt	= host_vcpu->arch.ctxt;
 
 	hyp_vcpu->vcpu.arch.sve_state	= kern_hyp_va(host_vcpu->arch.sve_state);
-	hyp_vcpu->vcpu.arch.sve_max_vl	= host_vcpu->arch.sve_max_vl;
+	/* Limit guest vector length to the maximum supported by the host.  */
+	hyp_vcpu->vcpu.arch.sve_max_vl	= min(host_vcpu->arch.sve_max_vl, kvm_host_sve_max_vl);
 
 	hyp_vcpu->vcpu.arch.hw_mmu	= host_vcpu->arch.hw_mmu;
 
 	hyp_vcpu->vcpu.arch.hcr_el2	= host_vcpu->arch.hcr_el2;
 	hyp_vcpu->vcpu.arch.mdcr_el2	= host_vcpu->arch.mdcr_el2;
-	hyp_vcpu->vcpu.arch.cptr_el2	= host_vcpu->arch.cptr_el2;
 
 	hyp_vcpu->vcpu.arch.iflags	= host_vcpu->arch.iflags;
 
@@ -54,10 +114,11 @@ static void sync_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu)
 	struct vgic_v3_cpu_if *host_cpu_if = &host_vcpu->arch.vgic_cpu.vgic_v3;
 	unsigned int i;
 
+	fpsimd_sve_sync(&hyp_vcpu->vcpu);
+
 	host_vcpu->arch.ctxt		= hyp_vcpu->vcpu.arch.ctxt;
 
 	host_vcpu->arch.hcr_el2		= hyp_vcpu->vcpu.arch.hcr_el2;
-	host_vcpu->arch.cptr_el2	= hyp_vcpu->vcpu.arch.cptr_el2;
 
 	host_vcpu->arch.fault		= hyp_vcpu->vcpu.arch.fault;
 
diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c
index 25e9a94f6d764..feb27b4ce4592 100644
--- a/arch/arm64/kvm/hyp/nvhe/pkvm.c
+++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c
@@ -588,6 +588,8 @@ unlock:
 	if (ret)
 		unmap_donated_memory(hyp_vcpu, sizeof(*hyp_vcpu));
 
+	hyp_vcpu->vcpu.arch.cptr_el2 = kvm_get_reset_cptr_el2(&hyp_vcpu->vcpu);
+
 	return ret;
 }
 
diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c
index 019f863922fa4..bef74de7065b3 100644
--- a/arch/arm64/kvm/hyp/nvhe/switch.c
+++ b/arch/arm64/kvm/hyp/nvhe/switch.c
@@ -184,7 +184,21 @@ static bool kvm_handle_pvm_sys64(struct kvm_vcpu *vcpu, u64 *exit_code)
 
 static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu)
 {
-	__fpsimd_save_state(*host_data_ptr(fpsimd_state));
+	/*
+	 * Non-protected kvm relies on the host restoring its sve state.
+	 * Protected kvm restores the host's sve state as not to reveal that
+	 * fpsimd was used by a guest nor leak upper sve bits.
+	 */
+	if (unlikely(is_protected_kvm_enabled() && system_supports_sve())) {
+		__hyp_sve_save_host();
+
+		/* Re-enable SVE traps if not supported for the guest vcpu. */
+		if (!vcpu_has_sve(vcpu))
+			cpacr_clear_set(CPACR_ELx_ZEN, 0);
+
+	} else {
+		__fpsimd_save_state(*host_data_ptr(fpsimd_state));
+	}
 }
 
 static const exit_handler_fn hyp_exit_handlers[] = {
-- 
GitLab


From 1696fc2174dbab12228ea9ec4c213d6aeea348f8 Mon Sep 17 00:00:00 2001
From: Fuad Tabba <tabba@google.com>
Date: Mon, 3 Jun 2024 13:28:49 +0100
Subject: [PATCH 771/950] KVM: arm64: Consolidate initializing the host data's
 fpsimd_state/sve in pKVM

Now that we have introduced finalize_init_hyp_mode(), lets
consolidate the initializing of the host_data fpsimd_state and
sve state.

Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Fuad Tabba <tabba@google.com>
Reviewed-by: Mark Brown <broonie@kernel.org>
Link: https://lore.kernel.org/r/20240603122852.3923848-8-tabba@google.com
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_host.h      | 10 ++++++++--
 arch/arm64/kvm/arm.c                   | 20 ++++++++++++++------
 arch/arm64/kvm/hyp/include/nvhe/pkvm.h |  1 -
 arch/arm64/kvm/hyp/nvhe/pkvm.c         | 11 -----------
 arch/arm64/kvm/hyp/nvhe/setup.c        |  1 -
 5 files changed, 22 insertions(+), 21 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 90df7ccec5f4f..36b8e97bf49ec 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -550,8 +550,14 @@ struct cpu_sve_state {
 struct kvm_host_data {
 	struct kvm_cpu_context host_ctxt;
 
-	struct user_fpsimd_state *fpsimd_state;	/* hyp VA */
-	struct cpu_sve_state *sve_state;	/* hyp VA */
+	/*
+	 * All pointers in this union are hyp VA.
+	 * sve_state is only used in pKVM and if system_supports_sve().
+	 */
+	union {
+		struct user_fpsimd_state *fpsimd_state;
+		struct cpu_sve_state *sve_state;
+	};
 
 	/* Ownership of the FP regs */
 	enum {
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 1acf7415e831b..59716789fe0f3 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -2444,14 +2444,22 @@ static void finalize_init_hyp_mode(void)
 {
 	int cpu;
 
-	if (!is_protected_kvm_enabled() || !system_supports_sve())
-		return;
+	if (system_supports_sve() && is_protected_kvm_enabled()) {
+		for_each_possible_cpu(cpu) {
+			struct cpu_sve_state *sve_state;
 
-	for_each_possible_cpu(cpu) {
-		struct cpu_sve_state *sve_state;
+			sve_state = per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->sve_state;
+			per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->sve_state =
+				kern_hyp_va(sve_state);
+		}
+	} else {
+		for_each_possible_cpu(cpu) {
+			struct user_fpsimd_state *fpsimd_state;
 
-		sve_state = per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->sve_state;
-		per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->sve_state = kern_hyp_va(sve_state);
+			fpsimd_state = &per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->host_ctxt.fp_regs;
+			per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->fpsimd_state =
+				kern_hyp_va(fpsimd_state);
+		}
 	}
 }
 
diff --git a/arch/arm64/kvm/hyp/include/nvhe/pkvm.h b/arch/arm64/kvm/hyp/include/nvhe/pkvm.h
index 22f374e9f5329..24a9a8330d190 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/pkvm.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/pkvm.h
@@ -59,7 +59,6 @@ static inline bool pkvm_hyp_vcpu_is_protected(struct pkvm_hyp_vcpu *hyp_vcpu)
 }
 
 void pkvm_hyp_vm_table_init(void *tbl);
-void pkvm_host_fpsimd_state_init(void);
 
 int __pkvm_init_vm(struct kvm *host_kvm, unsigned long vm_hva,
 		   unsigned long pgd_hva);
diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c
index feb27b4ce4592..ea67fcbf83761 100644
--- a/arch/arm64/kvm/hyp/nvhe/pkvm.c
+++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c
@@ -249,17 +249,6 @@ void pkvm_hyp_vm_table_init(void *tbl)
 	vm_table = tbl;
 }
 
-void pkvm_host_fpsimd_state_init(void)
-{
-	unsigned long i;
-
-	for (i = 0; i < hyp_nr_cpus; i++) {
-		struct kvm_host_data *host_data = per_cpu_ptr(&kvm_host_data, i);
-
-		host_data->fpsimd_state = &host_data->host_ctxt.fp_regs;
-	}
-}
-
 /*
  * Return the hyp vm structure corresponding to the handle.
  */
diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c
index 3fae424795982..f4350ba07b0b0 100644
--- a/arch/arm64/kvm/hyp/nvhe/setup.c
+++ b/arch/arm64/kvm/hyp/nvhe/setup.c
@@ -324,7 +324,6 @@ void __noreturn __pkvm_init_finalise(void)
 		goto out;
 
 	pkvm_hyp_vm_table_init(vm_table_base);
-	pkvm_host_fpsimd_state_init();
 out:
 	/*
 	 * We tail-called to here from handle___pkvm_init() and will not return,
-- 
GitLab


From a69283ae1db8dd416870d931caa9e2d3d2c1cd8b Mon Sep 17 00:00:00 2001
From: Fuad Tabba <tabba@google.com>
Date: Mon, 3 Jun 2024 13:28:50 +0100
Subject: [PATCH 772/950] KVM: arm64: Refactor CPACR trap bit setting/clearing
 to use ELx format

When setting/clearing CPACR bits for EL0 and EL1, use the ELx
format of the bits, which covers both. This makes the code
clearer, and reduces the chances of accidentally missing a bit.

No functional change intended.

Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Fuad Tabba <tabba@google.com>
Link: https://lore.kernel.org/r/20240603122852.3923848-9-tabba@google.com
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/el2_setup.h   | 6 +++---
 arch/arm64/include/asm/kvm_emulate.h | 9 ++++-----
 arch/arm64/kvm/fpsimd.c              | 4 +---
 arch/arm64/kvm/hyp/nvhe/pkvm.c       | 2 +-
 arch/arm64/kvm/hyp/nvhe/switch.c     | 5 ++---
 arch/arm64/kvm/hyp/vhe/switch.c      | 7 +++----
 6 files changed, 14 insertions(+), 19 deletions(-)

diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h
index e4546b29dd0cb..fd87c4b8f9840 100644
--- a/arch/arm64/include/asm/el2_setup.h
+++ b/arch/arm64/include/asm/el2_setup.h
@@ -146,7 +146,7 @@
 /* Coprocessor traps */
 .macro __init_el2_cptr
 	__check_hvhe .LnVHE_\@, x1
-	mov	x0, #(CPACR_EL1_FPEN_EL1EN | CPACR_EL1_FPEN_EL0EN)
+	mov	x0, #CPACR_ELx_FPEN
 	msr	cpacr_el1, x0
 	b	.Lskip_set_cptr_\@
 .LnVHE_\@:
@@ -277,7 +277,7 @@
 
 	// (h)VHE case
 	mrs	x0, cpacr_el1			// Disable SVE traps
-	orr	x0, x0, #(CPACR_EL1_ZEN_EL1EN | CPACR_EL1_ZEN_EL0EN)
+	orr	x0, x0, #CPACR_ELx_ZEN
 	msr	cpacr_el1, x0
 	b	.Lskip_set_cptr_\@
 
@@ -298,7 +298,7 @@
 
 	// (h)VHE case
 	mrs	x0, cpacr_el1			// Disable SME traps
-	orr	x0, x0, #(CPACR_EL1_SMEN_EL0EN | CPACR_EL1_SMEN_EL1EN)
+	orr	x0, x0, #CPACR_ELx_SMEN
 	msr	cpacr_el1, x0
 	b	.Lskip_set_cptr_sme_\@
 
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 2d7a0bdf9d03f..21650e7924d45 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -632,17 +632,16 @@ static __always_inline u64 kvm_get_reset_cptr_el2(struct kvm_vcpu *vcpu)
 	u64 val;
 
 	if (has_vhe()) {
-		val = (CPACR_EL1_FPEN_EL0EN | CPACR_EL1_FPEN_EL1EN |
-		       CPACR_EL1_ZEN_EL1EN);
+		val = (CPACR_ELx_FPEN | CPACR_EL1_ZEN_EL1EN);
 		if (cpus_have_final_cap(ARM64_SME))
 			val |= CPACR_EL1_SMEN_EL1EN;
 	} else if (has_hvhe()) {
-		val = (CPACR_EL1_FPEN_EL0EN | CPACR_EL1_FPEN_EL1EN);
+		val = CPACR_ELx_FPEN;
 
 		if (!vcpu_has_sve(vcpu) || !guest_owns_fp_regs())
-			val |= CPACR_EL1_ZEN_EL1EN | CPACR_EL1_ZEN_EL0EN;
+			val |= CPACR_ELx_ZEN;
 		if (cpus_have_final_cap(ARM64_SME))
-			val |= CPACR_EL1_SMEN_EL1EN | CPACR_EL1_SMEN_EL0EN;
+			val |= CPACR_ELx_SMEN;
 	} else {
 		val = CPTR_NVHE_EL2_RES1;
 
diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c
index 1807d3a79a8af..eb21f29d91fc5 100644
--- a/arch/arm64/kvm/fpsimd.c
+++ b/arch/arm64/kvm/fpsimd.c
@@ -161,9 +161,7 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu)
 	if (has_vhe() && system_supports_sme()) {
 		/* Also restore EL0 state seen on entry */
 		if (vcpu_get_flag(vcpu, HOST_SME_ENABLED))
-			sysreg_clear_set(CPACR_EL1, 0,
-					 CPACR_EL1_SMEN_EL0EN |
-					 CPACR_EL1_SMEN_EL1EN);
+			sysreg_clear_set(CPACR_EL1, 0, CPACR_ELx_SMEN);
 		else
 			sysreg_clear_set(CPACR_EL1,
 					 CPACR_EL1_SMEN_EL0EN,
diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c
index ea67fcbf83761..95cf185742517 100644
--- a/arch/arm64/kvm/hyp/nvhe/pkvm.c
+++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c
@@ -65,7 +65,7 @@ static void pvm_init_traps_aa64pfr0(struct kvm_vcpu *vcpu)
 	/* Trap SVE */
 	if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_SVE), feature_ids)) {
 		if (has_hvhe())
-			cptr_clear |= CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN;
+			cptr_clear |= CPACR_ELx_ZEN;
 		else
 			cptr_set |= CPTR_EL2_TZ;
 	}
diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c
index bef74de7065b3..6af179c6356d6 100644
--- a/arch/arm64/kvm/hyp/nvhe/switch.c
+++ b/arch/arm64/kvm/hyp/nvhe/switch.c
@@ -48,15 +48,14 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
 	val |= has_hvhe() ? CPACR_EL1_TTA : CPTR_EL2_TTA;
 	if (cpus_have_final_cap(ARM64_SME)) {
 		if (has_hvhe())
-			val &= ~(CPACR_EL1_SMEN_EL1EN | CPACR_EL1_SMEN_EL0EN);
+			val &= ~CPACR_ELx_SMEN;
 		else
 			val |= CPTR_EL2_TSM;
 	}
 
 	if (!guest_owns_fp_regs()) {
 		if (has_hvhe())
-			val &= ~(CPACR_EL1_FPEN_EL0EN | CPACR_EL1_FPEN_EL1EN |
-				 CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN);
+			val &= ~(CPACR_ELx_FPEN | CPACR_ELx_ZEN);
 		else
 			val |= CPTR_EL2_TFP | CPTR_EL2_TZ;
 
diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index 20073579e9f5b..8fbb6a2e0559d 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -93,8 +93,7 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
 
 	val = read_sysreg(cpacr_el1);
 	val |= CPACR_ELx_TTA;
-	val &= ~(CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN |
-		 CPACR_EL1_SMEN_EL0EN | CPACR_EL1_SMEN_EL1EN);
+	val &= ~(CPACR_ELx_ZEN | CPACR_ELx_SMEN);
 
 	/*
 	 * With VHE (HCR.E2H == 1), accesses to CPACR_EL1 are routed to
@@ -109,9 +108,9 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
 
 	if (guest_owns_fp_regs()) {
 		if (vcpu_has_sve(vcpu))
-			val |= CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN;
+			val |= CPACR_ELx_ZEN;
 	} else {
-		val &= ~(CPACR_EL1_FPEN_EL0EN | CPACR_EL1_FPEN_EL1EN);
+		val &= ~CPACR_ELx_FPEN;
 		__activate_traps_fpsimd32(vcpu);
 	}
 
-- 
GitLab


From afb91f5f8ad7af172d993a34fde1947892408f53 Mon Sep 17 00:00:00 2001
From: Fuad Tabba <tabba@google.com>
Date: Mon, 3 Jun 2024 13:28:51 +0100
Subject: [PATCH 773/950] KVM: arm64: Ensure that SME controls are disabled in
 protected mode

KVM (and pKVM) do not support SME guests. Therefore KVM ensures
that the host's SME state is flushed and that SME controls for
enabling access to ZA storage and for streaming are disabled.

pKVM needs to protect against a buggy/malicious host. Ensure that
it wouldn't run a guest when protected mode is enabled should any
of the SME controls be enabled.

Signed-off-by: Fuad Tabba <tabba@google.com>
Link: https://lore.kernel.org/r/20240603122852.3923848-10-tabba@google.com
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/fpsimd.c            |  7 +++++++
 arch/arm64/kvm/hyp/nvhe/hyp-main.c | 11 +++++++++++
 2 files changed, 18 insertions(+)

diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c
index eb21f29d91fc5..521b32868d0d2 100644
--- a/arch/arm64/kvm/fpsimd.c
+++ b/arch/arm64/kvm/fpsimd.c
@@ -90,6 +90,13 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu)
 			fpsimd_save_and_flush_cpu_state();
 		}
 	}
+
+	/*
+	 * If normal guests gain SME support, maintain this behavior for pKVM
+	 * guests, which don't support SME.
+	 */
+	WARN_ON(is_protected_kvm_enabled() && system_supports_sme() &&
+		read_sysreg_s(SYS_SVCR));
 }
 
 /*
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
index bd93b8a9e1726..f43d845f3c4ec 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
@@ -140,6 +140,17 @@ static void handle___kvm_vcpu_run(struct kvm_cpu_context *host_ctxt)
 		struct pkvm_hyp_vcpu *hyp_vcpu;
 		struct kvm *host_kvm;
 
+		/*
+		 * KVM (and pKVM) doesn't support SME guests for now, and
+		 * ensures that SME features aren't enabled in pstate when
+		 * loading a vcpu. Therefore, if SME features enabled the host
+		 * is misbehaving.
+		 */
+		if (unlikely(system_supports_sme() && read_sysreg_s(SYS_SVCR))) {
+			ret = -EINVAL;
+			goto out;
+		}
+
 		host_kvm = kern_hyp_va(host_vcpu->kvm);
 		hyp_vcpu = pkvm_load_hyp_vcpu(host_kvm->arch.pkvm.handle,
 					      host_vcpu->vcpu_idx);
-- 
GitLab


From 8c3fdff2171c834df5fa5ff353b94ada2e5376ca Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Fri, 31 May 2024 04:15:49 -0700
Subject: [PATCH 774/950] openvswitch: Move stats allocation to core

With commit 34d21de99cea9 ("net: Move {l,t,d}stats allocation to core and
convert veth & vrf"), stats allocation could be done on net core instead
of this driver.

With this new approach, the driver doesn't have to bother with error
handling (allocation failure checking, making sure free happens in the
right spot, etc). This is core responsibility now.

Move openvswitch driver to leverage the core allocation.

Signed-off-by: Breno Leitao <leitao@debian.org>
Link: https://lore.kernel.org/r/20240531111552.3209198-1-leitao@debian.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/openvswitch/vport-internal_dev.c | 9 +--------
 1 file changed, 1 insertion(+), 8 deletions(-)

diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c
index 74c88a6baa43a..7daba6ac69124 100644
--- a/net/openvswitch/vport-internal_dev.c
+++ b/net/openvswitch/vport-internal_dev.c
@@ -140,11 +140,7 @@ static struct vport *internal_dev_create(const struct vport_parms *parms)
 		err = -ENOMEM;
 		goto error_free_vport;
 	}
-	vport->dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
-	if (!vport->dev->tstats) {
-		err = -ENOMEM;
-		goto error_free_netdev;
-	}
+	dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS;
 
 	dev_net_set(vport->dev, ovs_dp_get_net(vport->dp));
 	dev->ifindex = parms->desired_ifindex;
@@ -169,8 +165,6 @@ static struct vport *internal_dev_create(const struct vport_parms *parms)
 
 error_unlock:
 	rtnl_unlock();
-	free_percpu(dev->tstats);
-error_free_netdev:
 	free_netdev(dev);
 error_free_vport:
 	ovs_vport_free(vport);
@@ -186,7 +180,6 @@ static void internal_dev_destroy(struct vport *vport)
 
 	/* unregister_netdevice() waits for an RCU grace period. */
 	unregister_netdevice(vport->dev);
-	free_percpu(vport->dev->tstats);
 	rtnl_unlock();
 }
 
-- 
GitLab


From 2b438c5774cc491a4aa8bb1ec4f49c1a0760a173 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Fri, 31 May 2024 04:15:50 -0700
Subject: [PATCH 775/950] openvswitch: Remove generic .ndo_get_stats64

Commit 3e2f544dd8a33 ("net: get stats64 if device if driver is
configured") moved the callback to dev_get_tstats64() to net core, so,
unless the driver is doing some custom stats collection, it does not
need to set .ndo_get_stats64.

Since this driver is now relying in NETDEV_PCPU_STAT_TSTATS, then, it
doesn't need to set the dev_get_tstats64() generic .ndo_get_stats64
function pointer.

Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Subbaraya Sundeep <sbhatta@marvell.com>
Link: https://lore.kernel.org/r/20240531111552.3209198-2-leitao@debian.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/openvswitch/vport-internal_dev.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c
index 7daba6ac69124..4b33133cbdfff 100644
--- a/net/openvswitch/vport-internal_dev.c
+++ b/net/openvswitch/vport-internal_dev.c
@@ -85,7 +85,6 @@ static const struct net_device_ops internal_dev_netdev_ops = {
 	.ndo_stop = internal_dev_stop,
 	.ndo_start_xmit = internal_dev_xmit,
 	.ndo_set_mac_address = eth_mac_addr,
-	.ndo_get_stats64 = dev_get_tstats64,
 };
 
 static struct rtnl_link_ops internal_dev_link_ops __read_mostly = {
-- 
GitLab


From a6ba5125f10bd7307e775e585ad21a8f7eda1b59 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 4 Jun 2024 10:54:57 -0700
Subject: [PATCH 776/950] Revert "ethernet: octeontx2: avoid linking objects
 into multiple modules"

This reverts commit 727c94c9539aa8865cdbf6a783da6a6585f1fec2.

Stephen reports that this commit causes a circular module dependency
for him. Revert, and we'll try to address the problem, again.

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Link: https://lore.kernel.org/all/20240531152223.25591c8e@canb.auug.org.au
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/marvell/octeontx2/nic/Makefile    | 14 ++++++--------
 .../ethernet/marvell/octeontx2/nic/otx2_dcbnl.c    | 11 -----------
 .../ethernet/marvell/octeontx2/nic/otx2_devlink.c  |  6 ------
 3 files changed, 6 insertions(+), 25 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/Makefile b/drivers/net/ethernet/marvell/octeontx2/nic/Makefile
index e4c5dc46dd42d..5664f768cb0cd 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/Makefile
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/Makefile
@@ -3,18 +3,16 @@
 # Makefile for Marvell's RVU Ethernet device drivers
 #
 
-obj-$(CONFIG_OCTEONTX2_PF) += rvu_nicpf.o otx2_ptp.o otx2_devlink.o
-obj-$(CONFIG_OCTEONTX2_VF) += rvu_nicvf.o otx2_ptp.o otx2_devlink.o
+obj-$(CONFIG_OCTEONTX2_PF) += rvu_nicpf.o otx2_ptp.o
+obj-$(CONFIG_OCTEONTX2_VF) += rvu_nicvf.o otx2_ptp.o
 
 rvu_nicpf-y := otx2_pf.o otx2_common.o otx2_txrx.o otx2_ethtool.o \
                otx2_flows.o otx2_tc.o cn10k.o otx2_dmac_flt.o \
-               qos_sq.o qos.o
-rvu_nicvf-y := otx2_vf.o
+               otx2_devlink.o qos_sq.o qos.o
+rvu_nicvf-y := otx2_vf.o otx2_devlink.o
 
-ifdef CONFIG_DCB
-obj-$(CONFIG_OCTEONTX2_PF) += otx2_dcbnl.o
-obj-$(CONFIG_OCTEONTX2_VF) += otx2_dcbnl.o
-endif
+rvu_nicpf-$(CONFIG_DCB) += otx2_dcbnl.o
+rvu_nicvf-$(CONFIG_DCB) += otx2_dcbnl.o
 rvu_nicpf-$(CONFIG_MACSEC) += cn10k_macsec.o
 
 ccflags-y += -I$(srctree)/drivers/net/ethernet/marvell/octeontx2/af
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c
index 0d7e611d9a05a..28fb643d2917f 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c
@@ -54,7 +54,6 @@ int otx2_pfc_txschq_config(struct otx2_nic *pfvf)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(otx2_pfc_txschq_config);
 
 static int otx2_pfc_txschq_alloc_one(struct otx2_nic *pfvf, u8 prio)
 {
@@ -123,7 +122,6 @@ int otx2_pfc_txschq_alloc(struct otx2_nic *pfvf)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(otx2_pfc_txschq_alloc);
 
 static int otx2_pfc_txschq_stop_one(struct otx2_nic *pfvf, u8 prio)
 {
@@ -262,7 +260,6 @@ update_sq_smq_map:
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(otx2_pfc_txschq_update);
 
 int otx2_pfc_txschq_stop(struct otx2_nic *pfvf)
 {
@@ -285,7 +282,6 @@ int otx2_pfc_txschq_stop(struct otx2_nic *pfvf)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(otx2_pfc_txschq_stop);
 
 int otx2_config_priority_flow_ctrl(struct otx2_nic *pfvf)
 {
@@ -325,7 +321,6 @@ unlock:
 	mutex_unlock(&pfvf->mbox.lock);
 	return err;
 }
-EXPORT_SYMBOL_GPL(otx2_config_priority_flow_ctrl);
 
 void otx2_update_bpid_in_rqctx(struct otx2_nic *pfvf, int vlan_prio, int qidx,
 			       bool pfc_enable)
@@ -390,7 +385,6 @@ out:
 			 "Updating BPIDs in CQ and Aura contexts of RQ%d failed with err %d\n",
 			 qidx, err);
 }
-EXPORT_SYMBOL_GPL(otx2_update_bpid_in_rqctx);
 
 static int otx2_dcbnl_ieee_getpfc(struct net_device *dev, struct ieee_pfc *pfc)
 {
@@ -478,8 +472,3 @@ int otx2_dcbnl_set_ops(struct net_device *dev)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(otx2_dcbnl_set_ops);
-
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("Marvell RVU dcbnl");
-MODULE_AUTHOR("Sunil Goutham <sgoutham@marvell.com>");
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c
index 440f574d11958..99ddf31269d96 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c
@@ -113,7 +113,6 @@ err_dl:
 	devlink_free(dl);
 	return err;
 }
-EXPORT_SYMBOL_GPL(otx2_register_dl);
 
 void otx2_unregister_dl(struct otx2_nic *pfvf)
 {
@@ -125,8 +124,3 @@ void otx2_unregister_dl(struct otx2_nic *pfvf)
 				  ARRAY_SIZE(otx2_dl_params));
 	devlink_free(dl);
 }
-EXPORT_SYMBOL_GPL(otx2_unregister_dl);
-
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("Marvell RVU PF/VF Netdev Devlink");
-MODULE_AUTHOR("Sunil Goutham <sgoutham@marvell.com>");
-- 
GitLab


From 61ce0ea7591fef2eb6e89ce40ffcc24fda4dbbc5 Mon Sep 17 00:00:00 2001
From: Song Liu <song@kernel.org>
Date: Tue, 4 Jun 2024 00:07:00 -0700
Subject: [PATCH 777/950] selftests/bpf: Fix bpf_cookie and find_vma in nested
 VM

bpf_cookie and find_vma are flaky in nested VMs, which is used by some CI
systems. It turns out these failures are caused by unreliable perf event
in nested VM. Fix these by:

  1. Use PERF_COUNT_SW_CPU_CLOCK in find_vma;
  2. Increase sample_freq in bpf_cookie.

Signed-off-by: Song Liu <song@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20240604070700.3032142-1-song@kernel.org
---
 tools/testing/selftests/bpf/prog_tests/bpf_cookie.c | 2 +-
 tools/testing/selftests/bpf/prog_tests/find_vma.c   | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c
index 4407ea428e77c..070c52c312e5f 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c
@@ -451,7 +451,7 @@ static void pe_subtest(struct test_bpf_cookie *skel)
 	attr.type = PERF_TYPE_SOFTWARE;
 	attr.config = PERF_COUNT_SW_CPU_CLOCK;
 	attr.freq = 1;
-	attr.sample_freq = 1000;
+	attr.sample_freq = 10000;
 	pfd = syscall(__NR_perf_event_open, &attr, -1, 0, -1, PERF_FLAG_FD_CLOEXEC);
 	if (!ASSERT_GE(pfd, 0, "perf_fd"))
 		goto cleanup;
diff --git a/tools/testing/selftests/bpf/prog_tests/find_vma.c b/tools/testing/selftests/bpf/prog_tests/find_vma.c
index 5165b38f0e59f..f7619e0ade10e 100644
--- a/tools/testing/selftests/bpf/prog_tests/find_vma.c
+++ b/tools/testing/selftests/bpf/prog_tests/find_vma.c
@@ -29,8 +29,8 @@ static int open_pe(void)
 
 	/* create perf event */
 	attr.size = sizeof(attr);
-	attr.type = PERF_TYPE_HARDWARE;
-	attr.config = PERF_COUNT_HW_CPU_CYCLES;
+	attr.type = PERF_TYPE_SOFTWARE;
+	attr.config = PERF_COUNT_SW_CPU_CLOCK;
 	attr.freq = 1;
 	attr.sample_freq = 1000;
 	pfd = syscall(__NR_perf_event_open, &attr, 0, -1, -1, PERF_FLAG_FD_CLOEXEC);
-- 
GitLab


From 898ac74c5b5f8b551a377d6a60ca4e30023ac9d2 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Tue, 4 Jun 2024 11:00:34 -0700
Subject: [PATCH 778/950] selftests/bpf: Ignore .llvm.<hash> suffix in
 kallsyms_find()

I hit the following failure when running selftests with
internal backported upstream kernel:
  test_ksyms:PASS:kallsyms_fopen 0 nsec
  test_ksyms:FAIL:ksym_find symbol 'bpf_link_fops' not found
  #123     ksyms:FAIL

In /proc/kallsyms, we have
  $ cat /proc/kallsyms | grep bpf_link_fops
  ffffffff829f0cb0 d bpf_link_fops.llvm.12608678492448798416
The CONFIG_LTO_CLANG_THIN is enabled in the kernel which is responsible
for bpf_link_fops.llvm.12608678492448798416 symbol name.

In prog_tests/ksyms.c we have
  kallsyms_find("bpf_link_fops", &link_fops_addr)
and kallsyms_find() compares "bpf_link_fops" with symbols
in /proc/kallsyms in order to find the entry. With
bpf_link_fops.llvm.<hash> in /proc/kallsyms, the kallsyms_find()
failed.

To fix the issue, in kallsyms_find(), if a symbol has suffix
.llvm.<hash>, that suffix will be ignored for comparison.
This fixed the test failure.

Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20240604180034.1356016-1-yonghong.song@linux.dev
---
 tools/testing/selftests/bpf/trace_helpers.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c
index 70e29f316fe7c..465d196c71651 100644
--- a/tools/testing/selftests/bpf/trace_helpers.c
+++ b/tools/testing/selftests/bpf/trace_helpers.c
@@ -211,7 +211,7 @@ long ksym_get_addr(const char *name)
  */
 int kallsyms_find(const char *sym, unsigned long long *addr)
 {
-	char type, name[500];
+	char type, name[500], *match;
 	unsigned long long value;
 	int err = 0;
 	FILE *f;
@@ -221,6 +221,17 @@ int kallsyms_find(const char *sym, unsigned long long *addr)
 		return -EINVAL;
 
 	while (fscanf(f, "%llx %c %499s%*[^\n]\n", &value, &type, name) > 0) {
+		/* If CONFIG_LTO_CLANG_THIN is enabled, static variable/function
+		 * symbols could be promoted to global due to cross-file inlining.
+		 * For such cases, clang compiler will add .llvm.<hash> suffix
+		 * to those symbols to avoid potential naming conflict.
+		 * Let us ignore .llvm.<hash> suffix during symbol comparison.
+		 */
+		if (type == 'd') {
+			match = strstr(name, ".llvm.");
+			if (match)
+				*match = '\0';
+		}
 		if (strcmp(name, sym) == 0) {
 			*addr = value;
 			goto out;
-- 
GitLab


From 0ea00e249ca992adee54dc71a526ee70ef109e40 Mon Sep 17 00:00:00 2001
From: Jan Beulich <jbeulich@suse.com>
Date: Wed, 29 May 2024 15:23:25 +0300
Subject: [PATCH 779/950] tpm_tis: Do *not* flush uninitialized work

tpm_tis_core_init() may fail before tpm_tis_probe_irq_single() is
called, in which case tpm_tis_remove() unconditionally calling
flush_work() is triggering a warning for .func still being NULL.

Cc: stable@vger.kernel.org # v6.5+
Fixes: 481c2d14627d ("tpm,tpm_tis: Disable interrupts after 1000 unhandled IRQs")
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Jarkko Sakkinen <jarkko@kernel.org>
Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org>
---
 drivers/char/tpm/tpm_tis_core.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c
index 176cd8dbf1db2..fdef214b9f6bf 100644
--- a/drivers/char/tpm/tpm_tis_core.c
+++ b/drivers/char/tpm/tpm_tis_core.c
@@ -1020,7 +1020,8 @@ void tpm_tis_remove(struct tpm_chip *chip)
 		interrupt = 0;
 
 	tpm_tis_write32(priv, reg, ~TPM_GLOBAL_INT_ENABLE & interrupt);
-	flush_work(&priv->free_irq_work);
+	if (priv->free_irq_work.func)
+		flush_work(&priv->free_irq_work);
 
 	tpm_tis_clkrun_enable(chip, false);
 
-- 
GitLab


From f071d02ecad4cfbf3ab41807c90bd1fef1cbfd3f Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Wed, 5 Jun 2024 01:28:42 +0300
Subject: [PATCH 780/950] tpm: Switch to new Intel CPU model defines

New CPU #defines encode vendor and family as well as model.

Link: https://lore.kernel.org/all/20240520224620.9480-4-tony.luck@intel.com/
Signed-off-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Jarkko Sakkinen <jarkko@kernel.org>
Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org>
---
 drivers/char/tpm/tpm.h          | 2 +-
 drivers/char/tpm/tpm_tis_core.h | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/char/tpm/tpm.h b/drivers/char/tpm/tpm.h
index 6b8b9956ba694..7bb87fa5f7a12 100644
--- a/drivers/char/tpm/tpm.h
+++ b/drivers/char/tpm/tpm.h
@@ -28,7 +28,7 @@
 #include <linux/tpm_eventlog.h>
 
 #ifdef CONFIG_X86
-#include <asm/intel-family.h>
+#include <asm/cpu_device_id.h>
 #endif
 
 #define TPM_MINOR		224	/* officially assigned */
diff --git a/drivers/char/tpm/tpm_tis_core.h b/drivers/char/tpm/tpm_tis_core.h
index 13e99cf65efe4..690ad8e9b7319 100644
--- a/drivers/char/tpm/tpm_tis_core.h
+++ b/drivers/char/tpm/tpm_tis_core.h
@@ -210,7 +210,7 @@ static inline int tpm_tis_verify_crc(struct tpm_tis_data *data, size_t len,
 static inline bool is_bsw(void)
 {
 #ifdef CONFIG_X86
-	return ((boot_cpu_data.x86_model == INTEL_FAM6_ATOM_AIRMONT) ? 1 : 0);
+	return (boot_cpu_data.x86_vfm == INTEL_ATOM_AIRMONT) ? 1 : 0;
 #else
 	return false;
 #endif
-- 
GitLab


From d0d1df8ba18abc57f28fb3bc053b2bf319367f2c Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Tue, 4 Jun 2024 17:00:24 +0200
Subject: [PATCH 781/950] bpf: Set run context for rawtp test_run callback

syzbot reported crash when rawtp program executed through the
test_run interface calls bpf_get_attach_cookie helper or any
other helper that touches task->bpf_ctx pointer.

Setting the run context (task->bpf_ctx pointer) for test_run
callback.

Fixes: 7adfc6c9b315 ("bpf: Add bpf_get_attach_cookie() BPF helper to access bpf_cookie value")
Reported-by: syzbot+3ab78ff125b7979e45f9@syzkaller.appspotmail.com
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Closes: https://syzkaller.appspot.com/bug?extid=3ab78ff125b7979e45f9
Link: https://lore.kernel.org/bpf/20240604150024.359247-1-jolsa@kernel.org
---
 net/bpf/test_run.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index f6aad4ed2ab2f..36ae54f57bf57 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -727,10 +727,16 @@ static void
 __bpf_prog_test_run_raw_tp(void *data)
 {
 	struct bpf_raw_tp_test_run_info *info = data;
+	struct bpf_trace_run_ctx run_ctx = {};
+	struct bpf_run_ctx *old_run_ctx;
+
+	old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx);
 
 	rcu_read_lock();
 	info->retval = bpf_prog_run(info->prog, info->ctx);
 	rcu_read_unlock();
+
+	bpf_reset_run_ctx(old_run_ctx);
 }
 
 int bpf_prog_test_run_raw_tp(struct bpf_prog *prog,
-- 
GitLab


From 7fcf26b315bbb728036da0862de6b335da83dff2 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Tue, 4 Jun 2024 14:29:25 +0200
Subject: [PATCH 782/950] Revert "xsk: Support redirect to any socket bound to
 the same umem"

This reverts commit 2863d665ea41282379f108e4da6c8a2366ba66db.

This patch introduced a potential kernel crash when multiple napi instances
redirect to the same AF_XDP socket. By removing the queue_index check, it is
possible for multiple napi instances to access the Rx ring at the same time,
which will result in a corrupted ring state which can lead to a crash when
flushing the rings in __xsk_flush(). This can happen when the linked list of
sockets to flush gets corrupted by concurrent accesses. A quick and small fix
is not possible, so let us revert this for now.

Reported-by: Yuval El-Hanany <YuvalE@radware.com>
Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/xdp-newbies/8100DBDC-0B7C-49DB-9995-6027F6E63147@radware.com
Link: https://lore.kernel.org/bpf/20240604122927.29080-2-magnus.karlsson@gmail.com
---
 net/xdp/xsk.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 727aa20be4bde..7d1c0986f9bb3 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -313,13 +313,10 @@ static bool xsk_is_bound(struct xdp_sock *xs)
 
 static int xsk_rcv_check(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)
 {
-	struct net_device *dev = xdp->rxq->dev;
-	u32 qid = xdp->rxq->queue_index;
-
 	if (!xsk_is_bound(xs))
 		return -ENXIO;
 
-	if (!dev->_rx[qid].pool || xs->umem != dev->_rx[qid].pool->umem)
+	if (xs->dev != xdp->rxq->dev || xs->queue_id != xdp->rxq->queue_index)
 		return -EINVAL;
 
 	if (len > xsk_pool_get_rx_frame_size(xs->pool) && !xs->sg) {
-- 
GitLab


From 03e38d315f3c5258270ad50f2ae784b6372e87c3 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Tue, 4 Jun 2024 14:29:26 +0200
Subject: [PATCH 783/950] Revert "xsk: Document ability to redirect to any
 socket bound to the same umem"

This reverts commit 968595a93669b6b4f6d1fcf80cf2d97956b6868f.

Reported-by: Yuval El-Hanany <YuvalE@radware.com>
Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/xdp-newbies/8100DBDC-0B7C-49DB-9995-6027F6E63147@radware.com
Link: https://lore.kernel.org/bpf/20240604122927.29080-3-magnus.karlsson@gmail.com
---
 Documentation/networking/af_xdp.rst | 33 ++++++++++++-----------------
 1 file changed, 14 insertions(+), 19 deletions(-)

diff --git a/Documentation/networking/af_xdp.rst b/Documentation/networking/af_xdp.rst
index 72da7057e4cf9..dceeb0d763aa2 100644
--- a/Documentation/networking/af_xdp.rst
+++ b/Documentation/networking/af_xdp.rst
@@ -329,24 +329,23 @@ XDP_SHARED_UMEM option and provide the initial socket's fd in the
 sxdp_shared_umem_fd field as you registered the UMEM on that
 socket. These two sockets will now share one and the same UMEM.
 
-In this case, it is possible to use the NIC's packet steering
-capabilities to steer the packets to the right queue. This is not
-possible in the previous example as there is only one queue shared
-among sockets, so the NIC cannot do this steering as it can only steer
-between queues.
-
-In libxdp (or libbpf prior to version 1.0), you need to use the
-xsk_socket__create_shared() API as it takes a reference to a FILL ring
-and a COMPLETION ring that will be created for you and bound to the
-shared UMEM. You can use this function for all the sockets you create,
-or you can use it for the second and following ones and use
-xsk_socket__create() for the first one. Both methods yield the same
-result.
+There is no need to supply an XDP program like the one in the previous
+case where sockets were bound to the same queue id and
+device. Instead, use the NIC's packet steering capabilities to steer
+the packets to the right queue. In the previous example, there is only
+one queue shared among sockets, so the NIC cannot do this steering. It
+can only steer between queues.
+
+In libbpf, you need to use the xsk_socket__create_shared() API as it
+takes a reference to a FILL ring and a COMPLETION ring that will be
+created for you and bound to the shared UMEM. You can use this
+function for all the sockets you create, or you can use it for the
+second and following ones and use xsk_socket__create() for the first
+one. Both methods yield the same result.
 
 Note that a UMEM can be shared between sockets on the same queue id
 and device, as well as between queues on the same device and between
-devices at the same time. It is also possible to redirect to any
-socket as long as it is bound to the same umem with XDP_SHARED_UMEM.
+devices at the same time.
 
 XDP_USE_NEED_WAKEUP bind flag
 -----------------------------
@@ -823,10 +822,6 @@ A: The short answer is no, that is not supported at the moment. The
    switch, or other distribution mechanism, in your NIC to direct
    traffic to the correct queue id and socket.
 
-   Note that if you are using the XDP_SHARED_UMEM option, it is
-   possible to switch traffic between any socket bound to the same
-   umem.
-
 Q: My packets are sometimes corrupted. What is wrong?
 
 A: Care has to be taken not to feed the same buffer in the UMEM into
-- 
GitLab


From 99280413a5b785f22d91e8a8a66dc38f4a214495 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Tue, 4 Jun 2024 17:45:20 +0200
Subject: [PATCH 784/950] efi: Add missing __nocfi annotations to runtime
 wrappers

The EFI runtime wrappers are a sandbox for calling into EFI runtime
services, which are invoked using indirect calls. When running with kCFI
enabled, the compiler will require the target of any indirect call to be
type annotated.

Given that the EFI runtime services prototypes and calling convention
are governed by the EFI spec, not the Linux kernel, adding such type
annotations for firmware routines is infeasible, and so the compiler
must be informed that prototype validation should be omitted.

Add the __nocfi annotation at the appropriate places in the EFI runtime
wrapper code to achieve this.

Note that this currently only affects 32-bit ARM, given that other
architectures that support both kCFI and EFI use an asm wrapper to call
EFI runtime services, and this hides the indirect call from the
compiler.

Fixes: 1a4fec49efe5 ("ARM: 9392/2: Support CLANG CFI")
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Tested-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 drivers/firmware/efi/runtime-wrappers.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/drivers/firmware/efi/runtime-wrappers.c b/drivers/firmware/efi/runtime-wrappers.c
index 5d56bc40a79d7..708b777857d34 100644
--- a/drivers/firmware/efi/runtime-wrappers.c
+++ b/drivers/firmware/efi/runtime-wrappers.c
@@ -213,7 +213,7 @@ extern struct semaphore __efi_uv_runtime_lock __alias(efi_runtime_lock);
  * Calls the appropriate efi_runtime_service() with the appropriate
  * arguments.
  */
-static void efi_call_rts(struct work_struct *work)
+static void __nocfi efi_call_rts(struct work_struct *work)
 {
 	const union efi_rts_args *args = efi_rts_work.args;
 	efi_status_t status = EFI_NOT_FOUND;
@@ -435,7 +435,7 @@ static efi_status_t virt_efi_set_variable(efi_char16_t *name,
 	return status;
 }
 
-static efi_status_t
+static efi_status_t __nocfi
 virt_efi_set_variable_nb(efi_char16_t *name, efi_guid_t *vendor, u32 attr,
 			 unsigned long data_size, void *data)
 {
@@ -469,7 +469,7 @@ static efi_status_t virt_efi_query_variable_info(u32 attr,
 	return status;
 }
 
-static efi_status_t
+static efi_status_t __nocfi
 virt_efi_query_variable_info_nb(u32 attr, u64 *storage_space,
 				u64 *remaining_space, u64 *max_variable_size)
 {
@@ -499,10 +499,9 @@ static efi_status_t virt_efi_get_next_high_mono_count(u32 *count)
 	return status;
 }
 
-static void virt_efi_reset_system(int reset_type,
-				  efi_status_t status,
-				  unsigned long data_size,
-				  efi_char16_t *data)
+static void __nocfi
+virt_efi_reset_system(int reset_type, efi_status_t status,
+		      unsigned long data_size, efi_char16_t *data)
 {
 	if (down_trylock(&efi_runtime_lock)) {
 		pr_warn("failed to invoke the reset_system() runtime service:\n"
-- 
GitLab


From 8b0f7410942cdc420c4557eda02bfcdf60ccec17 Mon Sep 17 00:00:00 2001
From: Subbaraya Sundeep <sbhatta@marvell.com>
Date: Wed, 29 May 2024 20:59:44 +0530
Subject: [PATCH 785/950] octeontx2-af: Always allocate PF entries from low
 prioriy zone

PF mcam entries has to be at low priority always so that VF
can install longest prefix match rules at higher priority.
This was taken care currently but when priority allocation
wrt reference entry is requested then entries are allocated
from mid-zone instead of low priority zone. Fix this and
always allocate entries from low priority zone for PFs.

Fixes: 7df5b4b260dd ("octeontx2-af: Allocate low priority entries for PF")
Signed-off-by: Subbaraya Sundeep <sbhatta@marvell.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/marvell/octeontx2/af/rvu_npc.c   | 33 ++++++++++++-------
 1 file changed, 22 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
index e8b73b9d75e31..97722ce8c4cb3 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
@@ -2519,7 +2519,17 @@ static int npc_mcam_alloc_entries(struct npc_mcam *mcam, u16 pcifunc,
 	 * - when available free entries are less.
 	 * Lower priority ones out of avaialble free entries are always
 	 * chosen when 'high vs low' question arises.
+	 *
+	 * For a VF base MCAM match rule is set by its PF. And all the
+	 * further MCAM rules installed by VF on its own are
+	 * concatenated with the base rule set by its PF. Hence PF entries
+	 * should be at lower priority compared to VF entries. Otherwise
+	 * base rule is hit always and rules installed by VF will be of
+	 * no use. Hence if the request is from PF then allocate low
+	 * priority entries.
 	 */
+	if (!(pcifunc & RVU_PFVF_FUNC_MASK))
+		goto lprio_alloc;
 
 	/* Get the search range for priority allocation request */
 	if (req->priority) {
@@ -2528,17 +2538,6 @@ static int npc_mcam_alloc_entries(struct npc_mcam *mcam, u16 pcifunc,
 		goto alloc;
 	}
 
-	/* For a VF base MCAM match rule is set by its PF. And all the
-	 * further MCAM rules installed by VF on its own are
-	 * concatenated with the base rule set by its PF. Hence PF entries
-	 * should be at lower priority compared to VF entries. Otherwise
-	 * base rule is hit always and rules installed by VF will be of
-	 * no use. Hence if the request is from PF and NOT a priority
-	 * allocation request then allocate low priority entries.
-	 */
-	if (!(pcifunc & RVU_PFVF_FUNC_MASK))
-		goto lprio_alloc;
-
 	/* Find out the search range for non-priority allocation request
 	 *
 	 * Get MCAM free entry count in middle zone.
@@ -2568,6 +2567,18 @@ lprio_alloc:
 		reverse = true;
 		start = 0;
 		end = mcam->bmap_entries;
+		/* Ensure PF requests are always at bottom and if PF requests
+		 * for higher/lower priority entry wrt reference entry then
+		 * honour that criteria and start search for entries from bottom
+		 * and not in mid zone.
+		 */
+		if (!(pcifunc & RVU_PFVF_FUNC_MASK) &&
+		    req->priority == NPC_MCAM_HIGHER_PRIO)
+			end = req->ref_entry;
+
+		if (!(pcifunc & RVU_PFVF_FUNC_MASK) &&
+		    req->priority == NPC_MCAM_LOWER_PRIO)
+			start = req->ref_entry;
 	}
 
 alloc:
-- 
GitLab


From fb0aa0781a5f457e3864da68af52c3b1f4f7fd8f Mon Sep 17 00:00:00 2001
From: Wen Gu <guwen@linux.alibaba.com>
Date: Fri, 31 May 2024 16:54:17 +0800
Subject: [PATCH 786/950] net/smc: avoid overwriting when adjusting sock
 bufsizes

When copying smc settings to clcsock, avoid setting clcsock's sk_sndbuf
to sysctl_tcp_wmem[1], since this may overwrite the value set by
tcp_sndbuf_expand() in TCP connection establishment.

And the other setting sk_{snd|rcv}buf to sysctl value in
smc_adjust_sock_bufsizes() can also be omitted since the initialization
of smc sock and clcsock has set sk_{snd|rcv}buf to smc.sysctl_{w|r}mem
or ipv4_sysctl_tcp_{w|r}mem[1].

Fixes: 30c3c4a4497c ("net/smc: Use correct buffer sizes when switching between TCP and SMC")
Link: https://lore.kernel.org/r/5eaf3858-e7fd-4db8-83e8-3d7a3e0e9ae2@linux.alibaba.com
Signed-off-by: Wen Gu <guwen@linux.alibaba.com>
Reviewed-by: Wenjia Zhang <wenjia@linux.ibm.com>
Reviewed-by: Gerd Bayer <gbayer@linux.ibm.com>, too.
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/af_smc.c | 22 ++--------------------
 1 file changed, 2 insertions(+), 20 deletions(-)

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index e50a286fd0fb7..c5f98c6b25613 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -459,29 +459,11 @@ out:
 static void smc_adjust_sock_bufsizes(struct sock *nsk, struct sock *osk,
 				     unsigned long mask)
 {
-	struct net *nnet = sock_net(nsk);
-
 	nsk->sk_userlocks = osk->sk_userlocks;
-	if (osk->sk_userlocks & SOCK_SNDBUF_LOCK) {
+	if (osk->sk_userlocks & SOCK_SNDBUF_LOCK)
 		nsk->sk_sndbuf = osk->sk_sndbuf;
-	} else {
-		if (mask == SK_FLAGS_SMC_TO_CLC)
-			WRITE_ONCE(nsk->sk_sndbuf,
-				   READ_ONCE(nnet->ipv4.sysctl_tcp_wmem[1]));
-		else
-			WRITE_ONCE(nsk->sk_sndbuf,
-				   2 * READ_ONCE(nnet->smc.sysctl_wmem));
-	}
-	if (osk->sk_userlocks & SOCK_RCVBUF_LOCK) {
+	if (osk->sk_userlocks & SOCK_RCVBUF_LOCK)
 		nsk->sk_rcvbuf = osk->sk_rcvbuf;
-	} else {
-		if (mask == SK_FLAGS_SMC_TO_CLC)
-			WRITE_ONCE(nsk->sk_rcvbuf,
-				   READ_ONCE(nnet->ipv4.sysctl_tcp_rmem[1]));
-		else
-			WRITE_ONCE(nsk->sk_rcvbuf,
-				   2 * READ_ONCE(nnet->smc.sysctl_rmem));
-	}
 }
 
 static void smc_copy_sock_settings(struct sock *nsk, struct sock *osk,
-- 
GitLab


From 3374136f3137ecdb34be228c715db6d6e0b97476 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Thu, 30 May 2024 23:53:07 +0200
Subject: [PATCH 787/950] dt-bindings: dsa: Rewrite Vitesse VSC73xx in schema

This rewrites the Vitesse VSC73xx DSA switches DT binding in
schema.

It was a bit tricky since I needed to come up with some way
of applying the SPI properties only on SPI devices and not
platform devices, but I figured something out that works.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../bindings/net/dsa/vitesse,vsc73xx.txt      | 129 --------------
 .../bindings/net/dsa/vitesse,vsc73xx.yaml     | 162 ++++++++++++++++++
 2 files changed, 162 insertions(+), 129 deletions(-)
 delete mode 100644 Documentation/devicetree/bindings/net/dsa/vitesse,vsc73xx.txt
 create mode 100644 Documentation/devicetree/bindings/net/dsa/vitesse,vsc73xx.yaml

diff --git a/Documentation/devicetree/bindings/net/dsa/vitesse,vsc73xx.txt b/Documentation/devicetree/bindings/net/dsa/vitesse,vsc73xx.txt
deleted file mode 100644
index 258bef483673f..0000000000000
--- a/Documentation/devicetree/bindings/net/dsa/vitesse,vsc73xx.txt
+++ /dev/null
@@ -1,129 +0,0 @@
-Vitesse VSC73xx Switches
-========================
-
-This defines device tree bindings for the Vitesse VSC73xx switch chips.
-The Vitesse company has been acquired by Microsemi and Microsemi has
-been acquired Microchip but retains this vendor branding.
-
-The currently supported switch chips are:
-Vitesse VSC7385 SparX-G5 5+1-port Integrated Gigabit Ethernet Switch
-Vitesse VSC7388 SparX-G8 8-port Integrated Gigabit Ethernet Switch
-Vitesse VSC7395 SparX-G5e 5+1-port Integrated Gigabit Ethernet Switch
-Vitesse VSC7398 SparX-G8e 8-port Integrated Gigabit Ethernet Switch
-
-This switch could have two different management interface.
-
-If SPI interface is used, the device tree node is an SPI device so it must
-reside inside a SPI bus device tree node, see spi/spi-bus.txt
-
-When the chip is connected to a parallel memory bus and work in memory-mapped
-I/O mode, a platform device is used to represent the vsc73xx. In this case it
-must reside inside a platform bus device tree node.
-
-Required properties:
-
-- compatible: must be exactly one of:
-	"vitesse,vsc7385"
-	"vitesse,vsc7388"
-	"vitesse,vsc7395"
-	"vitesse,vsc7398"
-- gpio-controller: indicates that this switch is also a GPIO controller,
-  see gpio/gpio.txt
-- #gpio-cells: this must be set to <2> and indicates that we are a twocell
-  GPIO controller, see gpio/gpio.txt
-
-Optional properties:
-
-- reset-gpios: a handle to a GPIO line that can issue reset of the chip.
-  It should be tagged as active low.
-
-Required subnodes:
-
-See net/dsa/dsa.txt for a list of additional required and optional properties
-and subnodes of DSA switches.
-
-Examples:
-
-SPI:
-switch@0 {
-	compatible = "vitesse,vsc7395";
-	reg = <0>;
-	/* Specified for 2.5 MHz or below */
-	spi-max-frequency = <2500000>;
-	gpio-controller;
-	#gpio-cells = <2>;
-
-	ports {
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		port@0 {
-			reg = <0>;
-			label = "lan1";
-		};
-		port@1 {
-			reg = <1>;
-			label = "lan2";
-		};
-		port@2 {
-			reg = <2>;
-			label = "lan3";
-		};
-		port@3 {
-			reg = <3>;
-			label = "lan4";
-		};
-		vsc: port@6 {
-			reg = <6>;
-			ethernet = <&gmac1>;
-			phy-mode = "rgmii";
-			fixed-link {
-				speed = <1000>;
-				full-duplex;
-				pause;
-			};
-		};
-	};
-};
-
-Platform:
-switch@2,0 {
-	#address-cells = <1>;
-	#size-cells = <1>;
-	compatible = "vitesse,vsc7385";
-	reg = <0x2 0x0 0x20000>;
-	reset-gpios = <&gpio0 12 GPIO_ACTIVE_LOW>;
-
-	ports {
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		port@0 {
-			reg = <0>;
-			label = "lan1";
-		};
-		port@1 {
-			reg = <1>;
-			label = "lan2";
-		};
-		port@2 {
-			reg = <2>;
-			label = "lan3";
-		};
-		port@3 {
-			reg = <3>;
-			label = "lan4";
-		};
-		vsc: port@6 {
-			reg = <6>;
-			ethernet = <&enet0>;
-			phy-mode = "rgmii";
-			fixed-link {
-				speed = <1000>;
-				full-duplex;
-				pause;
-			};
-		};
-	};
-
-};
diff --git a/Documentation/devicetree/bindings/net/dsa/vitesse,vsc73xx.yaml b/Documentation/devicetree/bindings/net/dsa/vitesse,vsc73xx.yaml
new file mode 100644
index 0000000000000..b99d7a694b70e
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/dsa/vitesse,vsc73xx.yaml
@@ -0,0 +1,162 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/net/dsa/vitesse,vsc73xx.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Vitesse VSC73xx DSA Switches
+
+maintainers:
+  - Linus Walleij <linus.walleij@linaro.org>
+
+description:
+  The Vitesse DSA Switches were produced in the early-to-mid 2000s.
+
+  The Vitesse company has been acquired by Microsemi and Microsemi has
+  been acquired Microchip but the new owner retains this vendor branding.
+
+  The currently supported switch chips are
+  Vitesse VSC7385 SparX-G5 5+1-port Integrated Gigabit Ethernet Switch
+  Vitesse VSC7388 SparX-G8 8-port Integrated Gigabit Ethernet Switch
+  Vitesse VSC7395 SparX-G5e 5+1-port Integrated Gigabit Ethernet Switch
+  Vitesse VSC7398 SparX-G8e 8-port Integrated Gigabit Ethernet Switch
+
+  This switch can use one of two different management interfaces.
+
+  If SPI interface is used, the device tree node is an SPI device so it must
+  reside inside a SPI bus device tree node, see spi/spi-bus.txt
+
+  When the chip is connected to a parallel memory bus and work in memory-mapped
+  I/O mode, a platform device is used to represent the vsc73xx. In this case it
+  must reside inside a platform bus device tree node.
+
+properties:
+  compatible:
+    enum:
+      - vitesse,vsc7385
+      - vitesse,vsc7388
+      - vitesse,vsc7395
+      - vitesse,vsc7398
+
+  reg:
+    maxItems: 1
+
+  gpio-controller: true
+  "#gpio-cells":
+    const: 2
+
+  reset-gpios:
+    description: GPIO to be used to reset the whole device
+    maxItems: 1
+
+allOf:
+  - $ref: dsa.yaml#/$defs/ethernet-ports
+
+# This checks if reg is a chipselect so the device is on an SPI
+# bus, the if-clause will fail if reg is a tuple such as for a
+# platform device.
+if:
+  properties:
+    reg:
+      minimum: 0
+      maximum: 256
+then:
+  $ref: /schemas/spi/spi-peripheral-props.yaml#
+
+required:
+  - compatible
+  - reg
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/gpio/gpio.h>
+
+    spi {
+      #address-cells = <1>;
+      #size-cells = <0>;
+
+      ethernet-switch@0 {
+        compatible = "vitesse,vsc7395";
+        reg = <0>;
+        spi-max-frequency = <2500000>;
+        gpio-controller;
+        #gpio-cells = <2>;
+
+        ethernet-ports {
+          #address-cells = <1>;
+          #size-cells = <0>;
+
+          ethernet-port@0 {
+            reg = <0>;
+            label = "lan1";
+          };
+          ethernet-port@1 {
+            reg = <1>;
+            label = "lan2";
+          };
+          ethernet-port@2 {
+            reg = <2>;
+            label = "lan3";
+          };
+          ethernet-port@3 {
+            reg = <3>;
+            label = "lan4";
+          };
+          ethernet-port@6 {
+            reg = <6>;
+            ethernet = <&gmac1>;
+            phy-mode = "rgmii";
+            fixed-link {
+              speed = <1000>;
+              full-duplex;
+              pause;
+            };
+          };
+        };
+      };
+    };
+
+    bus {
+      #address-cells = <1>;
+      #size-cells = <1>;
+
+      ethernet-switch@10000000 {
+        compatible = "vitesse,vsc7385";
+        reg = <0x10000000 0x20000>;
+        reset-gpios = <&gpio0 12 GPIO_ACTIVE_LOW>;
+
+        ethernet-ports {
+          #address-cells = <1>;
+          #size-cells = <0>;
+
+          ethernet-port@0 {
+            reg = <0>;
+            label = "lan1";
+          };
+          ethernet-port@1 {
+            reg = <1>;
+            label = "lan2";
+          };
+          ethernet-port@2 {
+            reg = <2>;
+            label = "lan3";
+          };
+          ethernet-port@3 {
+            reg = <3>;
+            label = "lan4";
+          };
+          ethernet-port@6 {
+            reg = <6>;
+            ethernet = <&enet0>;
+            phy-mode = "rgmii";
+            fixed-link {
+              speed = <1000>;
+              full-duplex;
+              pause;
+            };
+          };
+        };
+      };
+    };
-- 
GitLab


From 0a8d3f2e3e8d8aea8af017e14227b91d5989b696 Mon Sep 17 00:00:00 2001
From: Tristram Ha <tristram.ha@microchip.com>
Date: Thu, 30 May 2024 18:38:01 -0700
Subject: [PATCH 788/950] net: phy: Micrel KSZ8061: fix errata solution not
 taking effect problem

KSZ8061 needs to write to a MMD register at driver initialization to fix
an errata.  This worked in 5.0 kernel but not in newer kernels.  The
issue is the main phylib code no longer resets PHY at the very beginning.
Calling phy resuming code later will reset the chip if it is already
powered down at the beginning.  This wipes out the MMD register write.
Solution is to implement a phy resume function for KSZ8061 to take care
of this problem.

Fixes: 232ba3a51cc2 ("net: phy: Micrel KSZ8061: link failure after cable connect")
Signed-off-by: Tristram Ha <tristram.ha@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/micrel.c | 42 +++++++++++++++++++++++++++++++++++++++-
 1 file changed, 41 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index 8c20cf9375306..5aada7cf3da72 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -866,6 +866,17 @@ static int ksz8061_config_init(struct phy_device *phydev)
 {
 	int ret;
 
+	/* Chip can be powered down by the bootstrap code. */
+	ret = phy_read(phydev, MII_BMCR);
+	if (ret < 0)
+		return ret;
+	if (ret & BMCR_PDOWN) {
+		ret = phy_write(phydev, MII_BMCR, ret & ~BMCR_PDOWN);
+		if (ret < 0)
+			return ret;
+		usleep_range(1000, 2000);
+	}
+
 	ret = phy_write_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_DEVID1, 0xB61A);
 	if (ret)
 		return ret;
@@ -2135,6 +2146,35 @@ static int ksz9477_resume(struct phy_device *phydev)
 	return 0;
 }
 
+static int ksz8061_resume(struct phy_device *phydev)
+{
+	int ret;
+
+	/* This function can be called twice when the Ethernet device is on. */
+	ret = phy_read(phydev, MII_BMCR);
+	if (ret < 0)
+		return ret;
+	if (!(ret & BMCR_PDOWN))
+		return 0;
+
+	genphy_resume(phydev);
+	usleep_range(1000, 2000);
+
+	/* Re-program the value after chip is reset. */
+	ret = phy_write_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_DEVID1, 0xB61A);
+	if (ret)
+		return ret;
+
+	/* Enable PHY Interrupts */
+	if (phy_interrupt_is_valid(phydev)) {
+		phydev->interrupts = PHY_INTERRUPT_ENABLED;
+		if (phydev->drv->config_intr)
+			phydev->drv->config_intr(phydev);
+	}
+
+	return 0;
+}
+
 static int kszphy_probe(struct phy_device *phydev)
 {
 	const struct kszphy_type *type = phydev->drv->driver_data;
@@ -5389,7 +5429,7 @@ static struct phy_driver ksphy_driver[] = {
 	.config_intr	= kszphy_config_intr,
 	.handle_interrupt = kszphy_handle_interrupt,
 	.suspend	= kszphy_suspend,
-	.resume		= kszphy_resume,
+	.resume		= ksz8061_resume,
 }, {
 	.phy_id		= PHY_ID_KSZ9021,
 	.phy_id_mask	= 0x000ffffe,
-- 
GitLab


From cdbdb3c62af5bc13e6e8a9310470c71c33340d26 Mon Sep 17 00:00:00 2001
From: Chen Hanxiao <chenhx.fnst@fujitsu.com>
Date: Fri, 31 May 2024 16:54:02 +0800
Subject: [PATCH 789/950] net: bridge: fix an inconsistent indentation

Smatch complains:
net/bridge/br_netlink_tunnel.c:
   318 br_process_vlan_tunnel_info() warn: inconsistent indenting

Fix it with a proper indenting

Signed-off-by: Chen Hanxiao <chenhx.fnst@fujitsu.com>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_netlink_tunnel.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/bridge/br_netlink_tunnel.c b/net/bridge/br_netlink_tunnel.c
index 17abf092f7cac..71a12da30004c 100644
--- a/net/bridge/br_netlink_tunnel.c
+++ b/net/bridge/br_netlink_tunnel.c
@@ -315,8 +315,8 @@ int br_process_vlan_tunnel_info(const struct net_bridge *br,
 
 			if (curr_change)
 				*changed = curr_change;
-			 __vlan_tunnel_handle_range(p, &v_start, &v_end, v,
-						    curr_change);
+			__vlan_tunnel_handle_range(p, &v_start, &v_end, v,
+						   curr_change);
 		}
 		if (v_start && v_end)
 			br_vlan_notify(br, p, v_start->vid, v_end->vid,
-- 
GitLab


From 61e2bbafb00e4b9a5de45e6448a7b6b818658576 Mon Sep 17 00:00:00 2001
From: Jason Xing <kernelxing@tencent.com>
Date: Fri, 31 May 2024 23:46:34 +0800
Subject: [PATCH 790/950] net: remove NULL-pointer net parameter in
 ip_metrics_convert

When I was doing some experiments, I found that when using the first
parameter, namely, struct net, in ip_metrics_convert() always triggers NULL
pointer crash. Then I digged into this part, realizing that we can remove
this one due to its uselessness.

Signed-off-by: Jason Xing <kernelxing@tencent.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip.h         |  3 +--
 include/net/tcp.h        |  2 +-
 net/ipv4/fib_semantics.c |  5 ++---
 net/ipv4/metrics.c       |  8 ++++----
 net/ipv4/tcp_cong.c      | 11 +++++------
 net/ipv6/route.c         |  2 +-
 6 files changed, 14 insertions(+), 17 deletions(-)

diff --git a/include/net/ip.h b/include/net/ip.h
index 6d735e00d3f3e..c5606cadb1a55 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -506,8 +506,7 @@ static inline unsigned int ip_skb_dst_mtu(struct sock *sk,
 	return mtu - lwtunnel_headroom(skb_dst(skb)->lwtstate, mtu);
 }
 
-struct dst_metrics *ip_fib_metrics_init(struct net *net, struct nlattr *fc_mx,
-					int fc_mx_len,
+struct dst_metrics *ip_fib_metrics_init(struct nlattr *fc_mx, int fc_mx_len,
 					struct netlink_ext_ack *extack);
 static inline void ip_fib_metrics_put(struct dst_metrics *fib_metrics)
 {
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 08c3b99501cf6..a70fc39090fe8 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1224,7 +1224,7 @@ extern struct tcp_congestion_ops tcp_reno;
 
 struct tcp_congestion_ops *tcp_ca_find(const char *name);
 struct tcp_congestion_ops *tcp_ca_find_key(u32 key);
-u32 tcp_ca_get_key_by_name(struct net *net, const char *name, bool *ecn_ca);
+u32 tcp_ca_get_key_by_name(const char *name, bool *ecn_ca);
 #ifdef CONFIG_INET
 char *tcp_ca_get_name_by_key(u32 key, char *buffer);
 #else
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index f669da98d11d8..7b6b042208bd2 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1030,7 +1030,7 @@ bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi)
 			bool ecn_ca = false;
 
 			nla_strscpy(tmp, nla, sizeof(tmp));
-			val = tcp_ca_get_key_by_name(fi->fib_net, tmp, &ecn_ca);
+			val = tcp_ca_get_key_by_name(tmp, &ecn_ca);
 		} else {
 			if (nla_len(nla) != sizeof(u32))
 				return false;
@@ -1459,8 +1459,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
 	fi = kzalloc(struct_size(fi, fib_nh, nhs), GFP_KERNEL);
 	if (!fi)
 		goto failure;
-	fi->fib_metrics = ip_fib_metrics_init(fi->fib_net, cfg->fc_mx,
-					      cfg->fc_mx_len, extack);
+	fi->fib_metrics = ip_fib_metrics_init(cfg->fc_mx, cfg->fc_mx_len, extack);
 	if (IS_ERR(fi->fib_metrics)) {
 		err = PTR_ERR(fi->fib_metrics);
 		kfree(fi);
diff --git a/net/ipv4/metrics.c b/net/ipv4/metrics.c
index 0e3ee1532848c..8ddac1f595ed8 100644
--- a/net/ipv4/metrics.c
+++ b/net/ipv4/metrics.c
@@ -7,7 +7,7 @@
 #include <net/net_namespace.h>
 #include <net/tcp.h>
 
-static int ip_metrics_convert(struct net *net, struct nlattr *fc_mx,
+static int ip_metrics_convert(struct nlattr *fc_mx,
 			      int fc_mx_len, u32 *metrics,
 			      struct netlink_ext_ack *extack)
 {
@@ -31,7 +31,7 @@ static int ip_metrics_convert(struct net *net, struct nlattr *fc_mx,
 			char tmp[TCP_CA_NAME_MAX];
 
 			nla_strscpy(tmp, nla, sizeof(tmp));
-			val = tcp_ca_get_key_by_name(net, tmp, &ecn_ca);
+			val = tcp_ca_get_key_by_name(tmp, &ecn_ca);
 			if (val == TCP_CA_UNSPEC) {
 				NL_SET_ERR_MSG(extack, "Unknown tcp congestion algorithm");
 				return -EINVAL;
@@ -63,7 +63,7 @@ static int ip_metrics_convert(struct net *net, struct nlattr *fc_mx,
 	return 0;
 }
 
-struct dst_metrics *ip_fib_metrics_init(struct net *net, struct nlattr *fc_mx,
+struct dst_metrics *ip_fib_metrics_init(struct nlattr *fc_mx,
 					int fc_mx_len,
 					struct netlink_ext_ack *extack)
 {
@@ -77,7 +77,7 @@ struct dst_metrics *ip_fib_metrics_init(struct net *net, struct nlattr *fc_mx,
 	if (unlikely(!fib_metrics))
 		return ERR_PTR(-ENOMEM);
 
-	err = ip_metrics_convert(net, fc_mx, fc_mx_len, fib_metrics->metrics,
+	err = ip_metrics_convert(fc_mx, fc_mx_len, fib_metrics->metrics,
 				 extack);
 	if (!err) {
 		refcount_set(&fib_metrics->refcnt, 1);
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index 28ffcfbeef14e..48617d99abb0d 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -46,8 +46,7 @@ void tcp_set_ca_state(struct sock *sk, const u8 ca_state)
 }
 
 /* Must be called with rcu lock held */
-static struct tcp_congestion_ops *tcp_ca_find_autoload(struct net *net,
-						       const char *name)
+static struct tcp_congestion_ops *tcp_ca_find_autoload(const char *name)
 {
 	struct tcp_congestion_ops *ca = tcp_ca_find(name);
 
@@ -178,7 +177,7 @@ int tcp_update_congestion_control(struct tcp_congestion_ops *ca, struct tcp_cong
 	return ret;
 }
 
-u32 tcp_ca_get_key_by_name(struct net *net, const char *name, bool *ecn_ca)
+u32 tcp_ca_get_key_by_name(const char *name, bool *ecn_ca)
 {
 	const struct tcp_congestion_ops *ca;
 	u32 key = TCP_CA_UNSPEC;
@@ -186,7 +185,7 @@ u32 tcp_ca_get_key_by_name(struct net *net, const char *name, bool *ecn_ca)
 	might_sleep();
 
 	rcu_read_lock();
-	ca = tcp_ca_find_autoload(net, name);
+	ca = tcp_ca_find_autoload(name);
 	if (ca) {
 		key = ca->key;
 		*ecn_ca = ca->flags & TCP_CONG_NEEDS_ECN;
@@ -283,7 +282,7 @@ int tcp_set_default_congestion_control(struct net *net, const char *name)
 	int ret;
 
 	rcu_read_lock();
-	ca = tcp_ca_find_autoload(net, name);
+	ca = tcp_ca_find_autoload(name);
 	if (!ca) {
 		ret = -ENOENT;
 	} else if (!bpf_try_module_get(ca, ca->owner)) {
@@ -421,7 +420,7 @@ int tcp_set_congestion_control(struct sock *sk, const char *name, bool load,
 	if (!load)
 		ca = tcp_ca_find(name);
 	else
-		ca = tcp_ca_find_autoload(sock_net(sk), name);
+		ca = tcp_ca_find_autoload(name);
 
 	/* No change asking for existing value */
 	if (ca == icsk->icsk_ca_ops) {
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index a504b88ec06b5..12f647d0fec0f 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3761,7 +3761,7 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 	if (!rt)
 		goto out;
 
-	rt->fib6_metrics = ip_fib_metrics_init(net, cfg->fc_mx, cfg->fc_mx_len,
+	rt->fib6_metrics = ip_fib_metrics_init(cfg->fc_mx, cfg->fc_mx_len,
 					       extack);
 	if (IS_ERR(rt->fib6_metrics)) {
 		err = PTR_ERR(rt->fib6_metrics);
-- 
GitLab


From 6f49c3fb563c0a95a838216eaf7d9b02ece44bf5 Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Sat, 1 Jun 2024 00:29:17 +0100
Subject: [PATCH 791/950] net: caif: remove unused structs

'cfpktq' has been unused since
commit 73d6ac633c6c ("caif: code cleanup").

'caif_packet_funcs' is declared but never defined.

Remove both of them.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/caif/caif_layer.h | 2 --
 net/caif/cfpkt_skbuff.c       | 7 -------
 2 files changed, 9 deletions(-)

diff --git a/include/net/caif/caif_layer.h b/include/net/caif/caif_layer.h
index 51f7bb42a9361..0f45d875905f8 100644
--- a/include/net/caif/caif_layer.h
+++ b/include/net/caif/caif_layer.h
@@ -11,9 +11,7 @@
 
 struct cflayer;
 struct cfpkt;
-struct cfpktq;
 struct caif_payload_info;
-struct caif_packet_funcs;
 
 #define CAIF_LAYER_NAME_SZ 16
 
diff --git a/net/caif/cfpkt_skbuff.c b/net/caif/cfpkt_skbuff.c
index 7796414d47e52..2ae8cfa3df884 100644
--- a/net/caif/cfpkt_skbuff.c
+++ b/net/caif/cfpkt_skbuff.c
@@ -21,13 +21,6 @@ do {					   \
 	pr_warn(errmsg);		   \
 } while (0)
 
-struct cfpktq {
-	struct sk_buff_head head;
-	atomic_t count;
-	/* Lock protects count updates */
-	spinlock_t lock;
-};
-
 /*
  * net/caif/ is generic and does not
  * understand SKB, so we do this typecast
-- 
GitLab


From a23b0034e93453cecf435637dfdb14560eeda6c8 Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Sat, 1 Jun 2024 00:30:06 +0100
Subject: [PATCH 792/950] net: ethtool: remove unused struct
 'cable_test_tdr_req_info'

'cable_test_tdr_req_info' is unused since the original
commit f2bc8ad31a7f ("net: ethtool: Allow PHY cable test TDR data to
configured").

Remove it.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ethtool/cabletest.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/net/ethtool/cabletest.c b/net/ethtool/cabletest.c
index 06a151165c31c..f6f136ec7ddfc 100644
--- a/net/ethtool/cabletest.c
+++ b/net/ethtool/cabletest.c
@@ -207,10 +207,6 @@ err:
 }
 EXPORT_SYMBOL_GPL(ethnl_cable_test_fault_length);
 
-struct cable_test_tdr_req_info {
-	struct ethnl_req_info		base;
-};
-
 static const struct nla_policy cable_test_tdr_act_cfg_policy[] = {
 	[ETHTOOL_A_CABLE_TEST_TDR_CFG_FIRST]	= { .type = NLA_U32 },
 	[ETHTOOL_A_CABLE_TEST_TDR_CFG_LAST]	= { .type = NLA_U32 },
-- 
GitLab


From c11d5dbbe73fa7b450aaa77bb18df86a9714b422 Mon Sep 17 00:00:00 2001
From: Christian Marangi <ansuelsmth@gmail.com>
Date: Sat, 1 Jun 2024 01:35:02 +0200
Subject: [PATCH 793/950] net: phy: aquantia: move priv and hw stat to header

In preparation for LEDs support, move priv and hw stat to header to
reference priv struct also in other .c outside aquantia.main

Signed-off-by: Christian Marangi <ansuelsmth@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/aquantia/aquantia.h      | 38 ++++++++++++++++++++++++
 drivers/net/phy/aquantia/aquantia_main.c | 37 -----------------------
 2 files changed, 38 insertions(+), 37 deletions(-)

diff --git a/drivers/net/phy/aquantia/aquantia.h b/drivers/net/phy/aquantia/aquantia.h
index 1c19ae74ad2b4..c79b33d956287 100644
--- a/drivers/net/phy/aquantia/aquantia.h
+++ b/drivers/net/phy/aquantia/aquantia.h
@@ -87,6 +87,18 @@
 #define VEND1_GLOBAL_RSVD_STAT9_MODE		GENMASK(7, 0)
 #define VEND1_GLOBAL_RSVD_STAT9_1000BT2		0x23
 
+/* MDIO_MMD_C22EXT */
+#define MDIO_C22EXT_STAT_SGMII_RX_GOOD_FRAMES		0xd292
+#define MDIO_C22EXT_STAT_SGMII_RX_BAD_FRAMES		0xd294
+#define MDIO_C22EXT_STAT_SGMII_RX_FALSE_CARRIER		0xd297
+#define MDIO_C22EXT_STAT_SGMII_TX_GOOD_FRAMES		0xd313
+#define MDIO_C22EXT_STAT_SGMII_TX_BAD_FRAMES		0xd315
+#define MDIO_C22EXT_STAT_SGMII_TX_FALSE_CARRIER		0xd317
+#define MDIO_C22EXT_STAT_SGMII_TX_COLLISIONS		0xd318
+#define MDIO_C22EXT_STAT_SGMII_TX_LINE_COLLISIONS	0xd319
+#define MDIO_C22EXT_STAT_SGMII_TX_FRAME_ALIGN_ERR	0xd31a
+#define MDIO_C22EXT_STAT_SGMII_TX_RUNT_FRAMES		0xd31b
+
 #define VEND1_GLOBAL_INT_STD_STATUS		0xfc00
 #define VEND1_GLOBAL_INT_VEND_STATUS		0xfc01
 
@@ -113,6 +125,32 @@
 #define VEND1_GLOBAL_INT_VEND_MASK_GLOBAL2	BIT(1)
 #define VEND1_GLOBAL_INT_VEND_MASK_GLOBAL3	BIT(0)
 
+struct aqr107_hw_stat {
+	const char *name;
+	int reg;
+	int size;
+};
+
+#define SGMII_STAT(n, r, s) { n, MDIO_C22EXT_STAT_SGMII_ ## r, s }
+static const struct aqr107_hw_stat aqr107_hw_stats[] = {
+	SGMII_STAT("sgmii_rx_good_frames",	    RX_GOOD_FRAMES,	26),
+	SGMII_STAT("sgmii_rx_bad_frames",	    RX_BAD_FRAMES,	26),
+	SGMII_STAT("sgmii_rx_false_carrier_events", RX_FALSE_CARRIER,	 8),
+	SGMII_STAT("sgmii_tx_good_frames",	    TX_GOOD_FRAMES,	26),
+	SGMII_STAT("sgmii_tx_bad_frames",	    TX_BAD_FRAMES,	26),
+	SGMII_STAT("sgmii_tx_false_carrier_events", TX_FALSE_CARRIER,	 8),
+	SGMII_STAT("sgmii_tx_collisions",	    TX_COLLISIONS,	 8),
+	SGMII_STAT("sgmii_tx_line_collisions",	    TX_LINE_COLLISIONS,	 8),
+	SGMII_STAT("sgmii_tx_frame_alignment_err",  TX_FRAME_ALIGN_ERR,	16),
+	SGMII_STAT("sgmii_tx_runt_frames",	    TX_RUNT_FRAMES,	22),
+};
+
+#define AQR107_SGMII_STAT_SZ ARRAY_SIZE(aqr107_hw_stats)
+
+struct aqr107_priv {
+	u64 sgmii_stats[AQR107_SGMII_STAT_SZ];
+};
+
 #if IS_REACHABLE(CONFIG_HWMON)
 int aqr_hwmon_probe(struct phy_device *phydev);
 #else
diff --git a/drivers/net/phy/aquantia/aquantia_main.c b/drivers/net/phy/aquantia/aquantia_main.c
index d34cdec47636b..252123d12efbd 100644
--- a/drivers/net/phy/aquantia/aquantia_main.c
+++ b/drivers/net/phy/aquantia/aquantia_main.c
@@ -84,49 +84,12 @@
 #define MDIO_AN_RX_VEND_STAT3			0xe832
 #define MDIO_AN_RX_VEND_STAT3_AFR		BIT(0)
 
-/* MDIO_MMD_C22EXT */
-#define MDIO_C22EXT_STAT_SGMII_RX_GOOD_FRAMES		0xd292
-#define MDIO_C22EXT_STAT_SGMII_RX_BAD_FRAMES		0xd294
-#define MDIO_C22EXT_STAT_SGMII_RX_FALSE_CARRIER		0xd297
-#define MDIO_C22EXT_STAT_SGMII_TX_GOOD_FRAMES		0xd313
-#define MDIO_C22EXT_STAT_SGMII_TX_BAD_FRAMES		0xd315
-#define MDIO_C22EXT_STAT_SGMII_TX_FALSE_CARRIER		0xd317
-#define MDIO_C22EXT_STAT_SGMII_TX_COLLISIONS		0xd318
-#define MDIO_C22EXT_STAT_SGMII_TX_LINE_COLLISIONS	0xd319
-#define MDIO_C22EXT_STAT_SGMII_TX_FRAME_ALIGN_ERR	0xd31a
-#define MDIO_C22EXT_STAT_SGMII_TX_RUNT_FRAMES		0xd31b
-
 /* Sleep and timeout for checking if the Processor-Intensive
  * MDIO operation is finished
  */
 #define AQR107_OP_IN_PROG_SLEEP		1000
 #define AQR107_OP_IN_PROG_TIMEOUT	100000
 
-struct aqr107_hw_stat {
-	const char *name;
-	int reg;
-	int size;
-};
-
-#define SGMII_STAT(n, r, s) { n, MDIO_C22EXT_STAT_SGMII_ ## r, s }
-static const struct aqr107_hw_stat aqr107_hw_stats[] = {
-	SGMII_STAT("sgmii_rx_good_frames",	    RX_GOOD_FRAMES,	26),
-	SGMII_STAT("sgmii_rx_bad_frames",	    RX_BAD_FRAMES,	26),
-	SGMII_STAT("sgmii_rx_false_carrier_events", RX_FALSE_CARRIER,	 8),
-	SGMII_STAT("sgmii_tx_good_frames",	    TX_GOOD_FRAMES,	26),
-	SGMII_STAT("sgmii_tx_bad_frames",	    TX_BAD_FRAMES,	26),
-	SGMII_STAT("sgmii_tx_false_carrier_events", TX_FALSE_CARRIER,	 8),
-	SGMII_STAT("sgmii_tx_collisions",	    TX_COLLISIONS,	 8),
-	SGMII_STAT("sgmii_tx_line_collisions",	    TX_LINE_COLLISIONS,	 8),
-	SGMII_STAT("sgmii_tx_frame_alignment_err",  TX_FRAME_ALIGN_ERR,	16),
-	SGMII_STAT("sgmii_tx_runt_frames",	    TX_RUNT_FRAMES,	22),
-};
-#define AQR107_SGMII_STAT_SZ ARRAY_SIZE(aqr107_hw_stats)
-
-struct aqr107_priv {
-	u64 sgmii_stats[AQR107_SGMII_STAT_SZ];
-};
-
 static int aqr107_get_sset_count(struct phy_device *phydev)
 {
 	return AQR107_SGMII_STAT_SZ;
-- 
GitLab


From 61578f67937881abf54c8bd258eb913312dbe4c1 Mon Sep 17 00:00:00 2001
From: Daniel Golle <daniel@makrotopia.org>
Date: Sat, 1 Jun 2024 01:35:03 +0200
Subject: [PATCH 794/950] net: phy: aquantia: add support for PHY LEDs

Aquantia Ethernet PHYs got 3 LED output pins which are typically used
to indicate link status and activity.
Add a minimal LED controller driver supporting the most common uses
with the 'netdev' trigger as well as software-driven forced control of
the LEDs.

Signed-off-by: Daniel Golle <daniel@makrotopia.org>
[ rework indentation, fix checkpatch error and improve some functions ]
Signed-off-by: Christian Marangi <ansuelsmth@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/aquantia/Makefile        |   2 +-
 drivers/net/phy/aquantia/aquantia.h      |  40 ++++++
 drivers/net/phy/aquantia/aquantia_leds.c | 150 +++++++++++++++++++++++
 drivers/net/phy/aquantia/aquantia_main.c |  63 +++++++++-
 4 files changed, 252 insertions(+), 3 deletions(-)
 create mode 100644 drivers/net/phy/aquantia/aquantia_leds.c

diff --git a/drivers/net/phy/aquantia/Makefile b/drivers/net/phy/aquantia/Makefile
index aa77fb63c8ecf..c6c4d494ee2af 100644
--- a/drivers/net/phy/aquantia/Makefile
+++ b/drivers/net/phy/aquantia/Makefile
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
-aquantia-objs			+= aquantia_main.o aquantia_firmware.o
+aquantia-objs			+= aquantia_main.o aquantia_firmware.o aquantia_leds.o
 ifdef CONFIG_HWMON
 aquantia-objs			+= aquantia_hwmon.o
 endif
diff --git a/drivers/net/phy/aquantia/aquantia.h b/drivers/net/phy/aquantia/aquantia.h
index c79b33d956287..c0e1fd9d71520 100644
--- a/drivers/net/phy/aquantia/aquantia.h
+++ b/drivers/net/phy/aquantia/aquantia.h
@@ -63,6 +63,28 @@
 #define VEND1_GLOBAL_CONTROL2_UP_RUN_STALL_OVD	BIT(6)
 #define VEND1_GLOBAL_CONTROL2_UP_RUN_STALL	BIT(0)
 
+#define VEND1_GLOBAL_LED_PROV			0xc430
+#define AQR_LED_PROV(x)				(VEND1_GLOBAL_LED_PROV + (x))
+#define VEND1_GLOBAL_LED_PROV_LINK2500		BIT(14)
+#define VEND1_GLOBAL_LED_PROV_LINK5000		BIT(15)
+#define VEND1_GLOBAL_LED_PROV_FORCE_ON		BIT(8)
+#define VEND1_GLOBAL_LED_PROV_LINK10000		BIT(7)
+#define VEND1_GLOBAL_LED_PROV_LINK1000		BIT(6)
+#define VEND1_GLOBAL_LED_PROV_LINK100		BIT(5)
+#define VEND1_GLOBAL_LED_PROV_RX_ACT		BIT(3)
+#define VEND1_GLOBAL_LED_PROV_TX_ACT		BIT(2)
+#define VEND1_GLOBAL_LED_PROV_ACT_STRETCH	GENMASK(0, 1)
+
+#define VEND1_GLOBAL_LED_PROV_LINK_MASK		(VEND1_GLOBAL_LED_PROV_LINK100 | \
+						 VEND1_GLOBAL_LED_PROV_LINK1000 | \
+						 VEND1_GLOBAL_LED_PROV_LINK10000 | \
+						 VEND1_GLOBAL_LED_PROV_LINK5000 | \
+						 VEND1_GLOBAL_LED_PROV_LINK2500)
+
+#define VEND1_GLOBAL_LED_DRIVE			0xc438
+#define VEND1_GLOBAL_LED_DRIVE_VDD		BIT(1)
+#define AQR_LED_DRIVE(x)			(VEND1_GLOBAL_LED_DRIVE + (x))
+
 #define VEND1_THERMAL_PROV_HIGH_TEMP_FAIL	0xc421
 #define VEND1_THERMAL_PROV_LOW_TEMP_FAIL	0xc422
 #define VEND1_THERMAL_PROV_HIGH_TEMP_WARN	0xc423
@@ -125,6 +147,8 @@
 #define VEND1_GLOBAL_INT_VEND_MASK_GLOBAL2	BIT(1)
 #define VEND1_GLOBAL_INT_VEND_MASK_GLOBAL3	BIT(0)
 
+#define AQR_MAX_LEDS				3
+
 struct aqr107_hw_stat {
 	const char *name;
 	int reg;
@@ -149,6 +173,7 @@ static const struct aqr107_hw_stat aqr107_hw_stats[] = {
 
 struct aqr107_priv {
 	u64 sgmii_stats[AQR107_SGMII_STAT_SZ];
+	unsigned long leds_active_low;
 };
 
 #if IS_REACHABLE(CONFIG_HWMON)
@@ -158,3 +183,18 @@ static inline int aqr_hwmon_probe(struct phy_device *phydev) { return 0; }
 #endif
 
 int aqr_firmware_load(struct phy_device *phydev);
+
+int aqr_phy_led_blink_set(struct phy_device *phydev, u8 index,
+			  unsigned long *delay_on,
+			  unsigned long *delay_off);
+int aqr_phy_led_brightness_set(struct phy_device *phydev,
+			       u8 index, enum led_brightness value);
+int aqr_phy_led_hw_is_supported(struct phy_device *phydev, u8 index,
+				unsigned long rules);
+int aqr_phy_led_hw_control_get(struct phy_device *phydev, u8 index,
+			       unsigned long *rules);
+int aqr_phy_led_hw_control_set(struct phy_device *phydev, u8 index,
+			       unsigned long rules);
+int aqr_phy_led_active_low_set(struct phy_device *phydev, int index, bool enable);
+int aqr_phy_led_polarity_set(struct phy_device *phydev, int index,
+			     unsigned long modes);
diff --git a/drivers/net/phy/aquantia/aquantia_leds.c b/drivers/net/phy/aquantia/aquantia_leds.c
new file mode 100644
index 0000000000000..0516ac02c3f81
--- /dev/null
+++ b/drivers/net/phy/aquantia/aquantia_leds.c
@@ -0,0 +1,150 @@
+// SPDX-License-Identifier: GPL-2.0
+/* LED driver for Aquantia PHY
+ *
+ * Author: Daniel Golle <daniel@makrotopia.org>
+ */
+
+#include <linux/phy.h>
+
+#include "aquantia.h"
+
+int aqr_phy_led_brightness_set(struct phy_device *phydev,
+			       u8 index, enum led_brightness value)
+{
+	if (index >= AQR_MAX_LEDS)
+		return -EINVAL;
+
+	return phy_modify_mmd(phydev, MDIO_MMD_VEND1, AQR_LED_PROV(index),
+			      VEND1_GLOBAL_LED_PROV_LINK_MASK |
+			      VEND1_GLOBAL_LED_PROV_FORCE_ON |
+			      VEND1_GLOBAL_LED_PROV_RX_ACT |
+			      VEND1_GLOBAL_LED_PROV_TX_ACT,
+			      value ? VEND1_GLOBAL_LED_PROV_FORCE_ON : 0);
+}
+
+static const unsigned long supported_triggers = (BIT(TRIGGER_NETDEV_LINK) |
+						 BIT(TRIGGER_NETDEV_LINK_100) |
+						 BIT(TRIGGER_NETDEV_LINK_1000) |
+						 BIT(TRIGGER_NETDEV_LINK_2500) |
+						 BIT(TRIGGER_NETDEV_LINK_5000) |
+						 BIT(TRIGGER_NETDEV_LINK_10000)  |
+						 BIT(TRIGGER_NETDEV_RX) |
+						 BIT(TRIGGER_NETDEV_TX));
+
+int aqr_phy_led_hw_is_supported(struct phy_device *phydev, u8 index,
+				unsigned long rules)
+{
+	if (index >= AQR_MAX_LEDS)
+		return -EINVAL;
+
+	/* All combinations of the supported triggers are allowed */
+	if (rules & ~supported_triggers)
+		return -EOPNOTSUPP;
+
+	return 0;
+}
+
+int aqr_phy_led_hw_control_get(struct phy_device *phydev, u8 index,
+			       unsigned long *rules)
+{
+	int val;
+
+	if (index >= AQR_MAX_LEDS)
+		return -EINVAL;
+
+	val = phy_read_mmd(phydev, MDIO_MMD_VEND1, AQR_LED_PROV(index));
+	if (val < 0)
+		return val;
+
+	*rules = 0;
+	if (val & VEND1_GLOBAL_LED_PROV_LINK100)
+		*rules |= BIT(TRIGGER_NETDEV_LINK_100);
+
+	if (val & VEND1_GLOBAL_LED_PROV_LINK1000)
+		*rules |= BIT(TRIGGER_NETDEV_LINK_1000);
+
+	if (val & VEND1_GLOBAL_LED_PROV_LINK2500)
+		*rules |= BIT(TRIGGER_NETDEV_LINK_2500);
+
+	if (val & VEND1_GLOBAL_LED_PROV_LINK5000)
+		*rules |= BIT(TRIGGER_NETDEV_LINK_5000);
+
+	if (val & VEND1_GLOBAL_LED_PROV_LINK10000)
+		*rules |= BIT(TRIGGER_NETDEV_LINK_10000);
+
+	if (val & VEND1_GLOBAL_LED_PROV_RX_ACT)
+		*rules |= BIT(TRIGGER_NETDEV_RX);
+
+	if (val & VEND1_GLOBAL_LED_PROV_TX_ACT)
+		*rules |= BIT(TRIGGER_NETDEV_TX);
+
+	return 0;
+}
+
+int aqr_phy_led_hw_control_set(struct phy_device *phydev, u8 index,
+			       unsigned long rules)
+{
+	u16 val = 0;
+
+	if (index >= AQR_MAX_LEDS)
+		return -EINVAL;
+
+	if (rules & (BIT(TRIGGER_NETDEV_LINK_100) | BIT(TRIGGER_NETDEV_LINK)))
+		val |= VEND1_GLOBAL_LED_PROV_LINK100;
+
+	if (rules & (BIT(TRIGGER_NETDEV_LINK_1000) | BIT(TRIGGER_NETDEV_LINK)))
+		val |= VEND1_GLOBAL_LED_PROV_LINK1000;
+
+	if (rules & (BIT(TRIGGER_NETDEV_LINK_2500) | BIT(TRIGGER_NETDEV_LINK)))
+		val |= VEND1_GLOBAL_LED_PROV_LINK2500;
+
+	if (rules & (BIT(TRIGGER_NETDEV_LINK_5000) | BIT(TRIGGER_NETDEV_LINK)))
+		val |= VEND1_GLOBAL_LED_PROV_LINK5000;
+
+	if (rules & (BIT(TRIGGER_NETDEV_LINK_10000) | BIT(TRIGGER_NETDEV_LINK)))
+		val |= VEND1_GLOBAL_LED_PROV_LINK10000;
+
+	if (rules & BIT(TRIGGER_NETDEV_RX))
+		val |= VEND1_GLOBAL_LED_PROV_RX_ACT;
+
+	if (rules & BIT(TRIGGER_NETDEV_TX))
+		val |= VEND1_GLOBAL_LED_PROV_TX_ACT;
+
+	return phy_modify_mmd(phydev, MDIO_MMD_VEND1, AQR_LED_PROV(index),
+			      VEND1_GLOBAL_LED_PROV_LINK_MASK |
+			      VEND1_GLOBAL_LED_PROV_FORCE_ON |
+			      VEND1_GLOBAL_LED_PROV_RX_ACT |
+			      VEND1_GLOBAL_LED_PROV_TX_ACT, val);
+}
+
+int aqr_phy_led_active_low_set(struct phy_device *phydev, int index, bool enable)
+{
+	return phy_modify_mmd(phydev, MDIO_MMD_VEND1, AQR_LED_DRIVE(index),
+			      VEND1_GLOBAL_LED_DRIVE_VDD, enable);
+}
+
+int aqr_phy_led_polarity_set(struct phy_device *phydev, int index, unsigned long modes)
+{
+	struct aqr107_priv *priv = phydev->priv;
+	bool active_low = false;
+	u32 mode;
+
+	if (index >= AQR_MAX_LEDS)
+		return -EINVAL;
+
+	for_each_set_bit(mode, &modes, __PHY_LED_MODES_NUM) {
+		switch (mode) {
+		case PHY_LED_ACTIVE_LOW:
+			active_low = true;
+			break;
+		default:
+			return -EINVAL;
+		}
+	}
+
+	/* Save LED driver vdd state to restore on SW reset */
+	if (active_low)
+		priv->leds_active_low |= BIT(index);
+
+	return aqr_phy_led_active_low_set(phydev, index, active_low);
+}
diff --git a/drivers/net/phy/aquantia/aquantia_main.c b/drivers/net/phy/aquantia/aquantia_main.c
index 252123d12efbd..6c14355744b7e 100644
--- a/drivers/net/phy/aquantia/aquantia_main.c
+++ b/drivers/net/phy/aquantia/aquantia_main.c
@@ -475,7 +475,9 @@ static void aqr107_chip_info(struct phy_device *phydev)
 
 static int aqr107_config_init(struct phy_device *phydev)
 {
-	int ret;
+	struct aqr107_priv *priv = phydev->priv;
+	u32 led_active_low;
+	int ret, index = 0;
 
 	/* Check that the PHY interface type is compatible */
 	if (phydev->interface != PHY_INTERFACE_MODE_SGMII &&
@@ -496,7 +498,19 @@ static int aqr107_config_init(struct phy_device *phydev)
 	if (!ret)
 		aqr107_chip_info(phydev);
 
-	return aqr107_set_downshift(phydev, MDIO_AN_VEND_PROV_DOWNSHIFT_DFLT);
+	ret = aqr107_set_downshift(phydev, MDIO_AN_VEND_PROV_DOWNSHIFT_DFLT);
+	if (ret)
+		return ret;
+
+	/* Restore LED polarity state after reset */
+	for_each_set_bit(led_active_low, &priv->leds_active_low, AQR_MAX_LEDS) {
+		ret = aqr_phy_led_active_low_set(phydev, index, led_active_low);
+		if (ret)
+			return ret;
+		index++;
+	}
+
+	return 0;
 }
 
 static int aqcs109_config_init(struct phy_device *phydev)
@@ -786,6 +800,11 @@ static struct phy_driver aqr_driver[] = {
 	.get_strings	= aqr107_get_strings,
 	.get_stats	= aqr107_get_stats,
 	.link_change_notify = aqr107_link_change_notify,
+	.led_brightness_set = aqr_phy_led_brightness_set,
+	.led_hw_is_supported = aqr_phy_led_hw_is_supported,
+	.led_hw_control_set = aqr_phy_led_hw_control_set,
+	.led_hw_control_get = aqr_phy_led_hw_control_get,
+	.led_polarity_set = aqr_phy_led_polarity_set,
 },
 {
 	PHY_ID_MATCH_MODEL(PHY_ID_AQCS109),
@@ -805,6 +824,11 @@ static struct phy_driver aqr_driver[] = {
 	.get_strings	= aqr107_get_strings,
 	.get_stats	= aqr107_get_stats,
 	.link_change_notify = aqr107_link_change_notify,
+	.led_brightness_set = aqr_phy_led_brightness_set,
+	.led_hw_is_supported = aqr_phy_led_hw_is_supported,
+	.led_hw_control_set = aqr_phy_led_hw_control_set,
+	.led_hw_control_get = aqr_phy_led_hw_control_get,
+	.led_polarity_set = aqr_phy_led_polarity_set,
 },
 {
 	PHY_ID_MATCH_MODEL(PHY_ID_AQR111),
@@ -824,6 +848,11 @@ static struct phy_driver aqr_driver[] = {
 	.get_strings	= aqr107_get_strings,
 	.get_stats	= aqr107_get_stats,
 	.link_change_notify = aqr107_link_change_notify,
+	.led_brightness_set = aqr_phy_led_brightness_set,
+	.led_hw_is_supported = aqr_phy_led_hw_is_supported,
+	.led_hw_control_set = aqr_phy_led_hw_control_set,
+	.led_hw_control_get = aqr_phy_led_hw_control_get,
+	.led_polarity_set = aqr_phy_led_polarity_set,
 },
 {
 	PHY_ID_MATCH_MODEL(PHY_ID_AQR111B0),
@@ -843,6 +872,11 @@ static struct phy_driver aqr_driver[] = {
 	.get_strings	= aqr107_get_strings,
 	.get_stats	= aqr107_get_stats,
 	.link_change_notify = aqr107_link_change_notify,
+	.led_brightness_set = aqr_phy_led_brightness_set,
+	.led_hw_is_supported = aqr_phy_led_hw_is_supported,
+	.led_hw_control_set = aqr_phy_led_hw_control_set,
+	.led_hw_control_get = aqr_phy_led_hw_control_get,
+	.led_polarity_set = aqr_phy_led_polarity_set,
 },
 {
 	PHY_ID_MATCH_MODEL(PHY_ID_AQR405),
@@ -869,6 +903,11 @@ static struct phy_driver aqr_driver[] = {
 	.get_strings	= aqr107_get_strings,
 	.get_stats	= aqr107_get_stats,
 	.link_change_notify = aqr107_link_change_notify,
+	.led_brightness_set = aqr_phy_led_brightness_set,
+	.led_hw_is_supported = aqr_phy_led_hw_is_supported,
+	.led_hw_control_set = aqr_phy_led_hw_control_set,
+	.led_hw_control_get = aqr_phy_led_hw_control_get,
+	.led_polarity_set = aqr_phy_led_polarity_set,
 },
 {
 	PHY_ID_MATCH_MODEL(PHY_ID_AQR412),
@@ -906,6 +945,11 @@ static struct phy_driver aqr_driver[] = {
 	.get_strings    = aqr107_get_strings,
 	.get_stats      = aqr107_get_stats,
 	.link_change_notify = aqr107_link_change_notify,
+	.led_brightness_set = aqr_phy_led_brightness_set,
+	.led_hw_is_supported = aqr_phy_led_hw_is_supported,
+	.led_hw_control_set = aqr_phy_led_hw_control_set,
+	.led_hw_control_get = aqr_phy_led_hw_control_get,
+	.led_polarity_set = aqr_phy_led_polarity_set,
 },
 {
 	PHY_ID_MATCH_MODEL(PHY_ID_AQR113C),
@@ -925,6 +969,11 @@ static struct phy_driver aqr_driver[] = {
 	.get_strings    = aqr107_get_strings,
 	.get_stats      = aqr107_get_stats,
 	.link_change_notify = aqr107_link_change_notify,
+	.led_brightness_set = aqr_phy_led_brightness_set,
+	.led_hw_is_supported = aqr_phy_led_hw_is_supported,
+	.led_hw_control_set = aqr_phy_led_hw_control_set,
+	.led_hw_control_get = aqr_phy_led_hw_control_get,
+	.led_polarity_set = aqr_phy_led_polarity_set,
 },
 {
 	PHY_ID_MATCH_MODEL(PHY_ID_AQR114C),
@@ -944,6 +993,11 @@ static struct phy_driver aqr_driver[] = {
 	.get_strings    = aqr107_get_strings,
 	.get_stats      = aqr107_get_stats,
 	.link_change_notify = aqr107_link_change_notify,
+	.led_brightness_set = aqr_phy_led_brightness_set,
+	.led_hw_is_supported = aqr_phy_led_hw_is_supported,
+	.led_hw_control_set = aqr_phy_led_hw_control_set,
+	.led_hw_control_get = aqr_phy_led_hw_control_get,
+	.led_polarity_set = aqr_phy_led_polarity_set,
 },
 {
 	PHY_ID_MATCH_MODEL(PHY_ID_AQR813),
@@ -963,6 +1017,11 @@ static struct phy_driver aqr_driver[] = {
 	.get_strings	= aqr107_get_strings,
 	.get_stats	= aqr107_get_stats,
 	.link_change_notify = aqr107_link_change_notify,
+	.led_brightness_set = aqr_phy_led_brightness_set,
+	.led_hw_is_supported = aqr_phy_led_hw_is_supported,
+	.led_hw_control_set = aqr_phy_led_hw_control_set,
+	.led_hw_control_get = aqr_phy_led_hw_control_get,
+	.led_polarity_set = aqr_phy_led_polarity_set,
 },
 };
 
-- 
GitLab


From 82dc29b9737edf2d13561ebcf6212c0b88c41129 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sun, 2 Jun 2024 16:18:52 +0200
Subject: [PATCH 795/950] devlink: Constify the 'table_ops' parameter of
 devl_dpipe_table_register()

"struct devlink_dpipe_table_ops" only contains some function pointers.

Update "struct devlink_dpipe_table" and the 'table_ops' parameter of
devl_dpipe_table_register() so that structures in drivers can be
constified.

Constifying these structures will move some data to a read-only section, so
increase overall security.

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/devlink.h | 4 ++--
 net/devlink/dpipe.c   | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/include/net/devlink.h b/include/net/devlink.h
index 35eb0f8843861..db5eff6cb60fa 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -352,7 +352,7 @@ struct devlink_dpipe_table {
 	bool resource_valid;
 	u64 resource_id;
 	u64 resource_units;
-	struct devlink_dpipe_table_ops *table_ops;
+	const struct devlink_dpipe_table_ops *table_ops;
 	struct rcu_head rcu;
 };
 
@@ -1751,7 +1751,7 @@ void devl_sb_unregister(struct devlink *devlink, unsigned int sb_index);
 void devlink_sb_unregister(struct devlink *devlink, unsigned int sb_index);
 int devl_dpipe_table_register(struct devlink *devlink,
 			      const char *table_name,
-			      struct devlink_dpipe_table_ops *table_ops,
+			      const struct devlink_dpipe_table_ops *table_ops,
 			      void *priv, bool counter_control_extern);
 void devl_dpipe_table_unregister(struct devlink *devlink,
 				 const char *table_name);
diff --git a/net/devlink/dpipe.c b/net/devlink/dpipe.c
index a72a9292efc5c..55009b377447f 100644
--- a/net/devlink/dpipe.c
+++ b/net/devlink/dpipe.c
@@ -839,7 +839,7 @@ EXPORT_SYMBOL_GPL(devlink_dpipe_table_counter_enabled);
  */
 int devl_dpipe_table_register(struct devlink *devlink,
 			      const char *table_name,
-			      struct devlink_dpipe_table_ops *table_ops,
+			      const struct devlink_dpipe_table_ops *table_ops,
 			      void *priv, bool counter_control_extern)
 {
 	struct devlink_dpipe_table *table;
-- 
GitLab


From b072aa7899189127e26b2daf8c38933c994f97d3 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sun, 2 Jun 2024 16:18:53 +0200
Subject: [PATCH 796/950] mlxsw: spectrum_router: Constify struct
 devlink_dpipe_table_ops

'struct devlink_dpipe_table_ops' are not modified in this driver.

Constifying these structures moves some data to a read-only section, so
increase overall security.

On a x86_64, with allmodconfig:
Before:
======
   text	   data	    bss	    dec	    hex	filename
  15557	    712	      0	  16269	   3f8d	drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.o

After:
=====
   text	   data	    bss	    dec	    hex	filename
  15789	    488	      0	  16277	   3f95	drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.o

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c
index ca80af06465f3..fa6eddd27ecf5 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c
@@ -283,7 +283,7 @@ static u64 mlxsw_sp_dpipe_table_erif_size_get(void *priv)
 	return MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS);
 }
 
-static struct devlink_dpipe_table_ops mlxsw_sp_erif_ops = {
+static const struct devlink_dpipe_table_ops mlxsw_sp_erif_ops = {
 	.matches_dump = mlxsw_sp_dpipe_table_erif_matches_dump,
 	.actions_dump = mlxsw_sp_dpipe_table_erif_actions_dump,
 	.entries_dump = mlxsw_sp_dpipe_table_erif_entries_dump,
@@ -734,7 +734,7 @@ static u64 mlxsw_sp_dpipe_table_host4_size_get(void *priv)
 	return mlxsw_sp_dpipe_table_host_size_get(mlxsw_sp, AF_INET);
 }
 
-static struct devlink_dpipe_table_ops mlxsw_sp_host4_ops = {
+static const struct devlink_dpipe_table_ops mlxsw_sp_host4_ops = {
 	.matches_dump = mlxsw_sp_dpipe_table_host4_matches_dump,
 	.actions_dump = mlxsw_sp_dpipe_table_host_actions_dump,
 	.entries_dump = mlxsw_sp_dpipe_table_host4_entries_dump,
@@ -811,7 +811,7 @@ static u64 mlxsw_sp_dpipe_table_host6_size_get(void *priv)
 	return mlxsw_sp_dpipe_table_host_size_get(mlxsw_sp, AF_INET6);
 }
 
-static struct devlink_dpipe_table_ops mlxsw_sp_host6_ops = {
+static const struct devlink_dpipe_table_ops mlxsw_sp_host6_ops = {
 	.matches_dump = mlxsw_sp_dpipe_table_host6_matches_dump,
 	.actions_dump = mlxsw_sp_dpipe_table_host_actions_dump,
 	.entries_dump = mlxsw_sp_dpipe_table_host6_entries_dump,
@@ -1230,7 +1230,7 @@ mlxsw_sp_dpipe_table_adj_size_get(void *priv)
 	return size;
 }
 
-static struct devlink_dpipe_table_ops mlxsw_sp_dpipe_table_adj_ops = {
+static const struct devlink_dpipe_table_ops mlxsw_sp_dpipe_table_adj_ops = {
 	.matches_dump = mlxsw_sp_dpipe_table_adj_matches_dump,
 	.actions_dump = mlxsw_sp_dpipe_table_adj_actions_dump,
 	.entries_dump = mlxsw_sp_dpipe_table_adj_entries_dump,
-- 
GitLab


From 491aee894a08bc9b8bb52e7363b9d4bc6403f363 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Mon, 3 Jun 2024 04:57:55 +0000
Subject: [PATCH 797/950] ionic: fix kernel panic in XDP_TX action

In the XDP_TX path, ionic driver sends a packet to the TX path with rx
page and corresponding dma address.
After tx is done, ionic_tx_clean() frees that page.
But RX ring buffer isn't reset to NULL.
So, it uses a freed page, which causes kernel panic.

BUG: unable to handle page fault for address: ffff8881576c110c
PGD 773801067 P4D 773801067 PUD 87f086067 PMD 87efca067 PTE 800ffffea893e060
Oops: Oops: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC KASAN NOPTI
CPU: 1 PID: 25 Comm: ksoftirqd/1 Not tainted 6.9.0+ #11
Hardware name: ASUS System Product Name/PRIME Z690-P D4, BIOS 0603 11/01/2021
RIP: 0010:bpf_prog_f0b8caeac1068a55_balancer_ingress+0x3b/0x44f
Code: 00 53 41 55 41 56 41 57 b8 01 00 00 00 48 8b 5f 08 4c 8b 77 00 4c 89 f7 48 83 c7 0e 48 39 d8
RSP: 0018:ffff888104e6fa28 EFLAGS: 00010283
RAX: 0000000000000002 RBX: ffff8881576c1140 RCX: 0000000000000002
RDX: ffffffffc0051f64 RSI: ffffc90002d33048 RDI: ffff8881576c110e
RBP: ffff888104e6fa88 R08: 0000000000000000 R09: ffffed1027a04a23
R10: 0000000000000000 R11: 0000000000000000 R12: ffff8881b03a21a8
R13: ffff8881589f800f R14: ffff8881576c1100 R15: 00000001576c1100
FS: 0000000000000000(0000) GS:ffff88881ae00000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: ffff8881576c110c CR3: 0000000767a90000 CR4: 00000000007506f0
PKRU: 55555554
Call Trace:
<TASK>
? __die+0x20/0x70
? page_fault_oops+0x254/0x790
? __pfx_page_fault_oops+0x10/0x10
? __pfx_is_prefetch.constprop.0+0x10/0x10
? search_bpf_extables+0x165/0x260
? fixup_exception+0x4a/0x970
? exc_page_fault+0xcb/0xe0
? asm_exc_page_fault+0x22/0x30
? 0xffffffffc0051f64
? bpf_prog_f0b8caeac1068a55_balancer_ingress+0x3b/0x44f
? do_raw_spin_unlock+0x54/0x220
ionic_rx_service+0x11ab/0x3010 [ionic 9180c3001ab627d82bbc5f3ebe8a0decaf6bb864]
? ionic_tx_clean+0x29b/0xc60 [ionic 9180c3001ab627d82bbc5f3ebe8a0decaf6bb864]
? __pfx_ionic_tx_clean+0x10/0x10 [ionic 9180c3001ab627d82bbc5f3ebe8a0decaf6bb864]
? __pfx_ionic_rx_service+0x10/0x10 [ionic 9180c3001ab627d82bbc5f3ebe8a0decaf6bb864]
? ionic_tx_cq_service+0x25d/0xa00 [ionic 9180c3001ab627d82bbc5f3ebe8a0decaf6bb864]
? __pfx_ionic_rx_service+0x10/0x10 [ionic 9180c3001ab627d82bbc5f3ebe8a0decaf6bb864]
ionic_cq_service+0x69/0x150 [ionic 9180c3001ab627d82bbc5f3ebe8a0decaf6bb864]
ionic_txrx_napi+0x11a/0x540 [ionic 9180c3001ab627d82bbc5f3ebe8a0decaf6bb864]
__napi_poll.constprop.0+0xa0/0x440
net_rx_action+0x7e7/0xc30
? __pfx_net_rx_action+0x10/0x10

Fixes: 8eeed8373e1c ("ionic: Add XDP_TX support")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Reviewed-by: Shannon Nelson <shannon.nelson@amd.com>
Reviewed-by: Brett Creeley <brett.creeley@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/pensando/ionic/ionic_txrx.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
index 5dba6d2d633cb..2427610f4306d 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
@@ -586,6 +586,7 @@ static bool ionic_run_xdp(struct ionic_rx_stats *stats,
 			netdev_dbg(netdev, "tx ionic_xdp_post_frame err %d\n", err);
 			goto out_xdp_abort;
 		}
+		buf_info->page = NULL;
 		stats->xdp_tx++;
 
 		/* the Tx completion will free the buffers */
-- 
GitLab


From affc18fdc694190ca7575b9a86632a73b9fe043d Mon Sep 17 00:00:00 2001
From: Hangyu Hua <hbh25y@gmail.com>
Date: Mon, 3 Jun 2024 15:13:03 +0800
Subject: [PATCH 798/950] net: sched: sch_multiq: fix possible OOB write in
 multiq_tune()

q->bands will be assigned to qopt->bands to execute subsequent code logic
after kmalloc. So the old q->bands should not be used in kmalloc.
Otherwise, an out-of-bounds write will occur.

Fixes: c2999f7fb05b ("net: sched: multiq: don't call qdisc_put() while holding tree lock")
Signed-off-by: Hangyu Hua <hbh25y@gmail.com>
Acked-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_multiq.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c
index 79e93a19d5fab..06e03f5cd7ce1 100644
--- a/net/sched/sch_multiq.c
+++ b/net/sched/sch_multiq.c
@@ -185,7 +185,7 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt,
 
 	qopt->bands = qdisc_dev(sch)->real_num_tx_queues;
 
-	removed = kmalloc(sizeof(*removed) * (q->max_bands - q->bands),
+	removed = kmalloc(sizeof(*removed) * (q->max_bands - qopt->bands),
 			  GFP_KERNEL);
 	if (!removed)
 		return -ENOMEM;
-- 
GitLab


From 1cd4bc987abb2823836cbb8f887026011ccddc8a Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Mon, 3 Jun 2024 10:59:26 +0200
Subject: [PATCH 799/950] vxlan: Fix regression when dropping packets due to
 invalid src addresses

Commit f58f45c1e5b9 ("vxlan: drop packets from invalid src-address")
has recently been added to vxlan mainly in the context of source
address snooping/learning so that when it is enabled, an entry in the
FDB is not being created for an invalid address for the corresponding
tunnel endpoint.

Before commit f58f45c1e5b9 vxlan was similarly behaving as geneve in
that it passed through whichever macs were set in the L2 header. It
turns out that this change in behavior breaks setups, for example,
Cilium with netkit in L3 mode for Pods as well as tunnel mode has been
passing before the change in f58f45c1e5b9 for both vxlan and geneve.
After mentioned change it is only passing for geneve as in case of
vxlan packets are dropped due to vxlan_set_mac() returning false as
source and destination macs are zero which for E/W traffic via tunnel
is totally fine.

Fix it by only opting into the is_valid_ether_addr() check in
vxlan_set_mac() when in fact source address snooping/learning is
actually enabled in vxlan. This is done by moving the check into
vxlan_snoop(). With this change, the Cilium connectivity test suite
passes again for both tunnel flavors.

Fixes: f58f45c1e5b9 ("vxlan: drop packets from invalid src-address")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: David Bauer <mail@david-bauer.net>
Cc: Ido Schimmel <idosch@nvidia.com>
Cc: Nikolay Aleksandrov <razor@blackwall.org>
Cc: Martin KaFai Lau <martin.lau@kernel.org>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Reviewed-by: David Bauer <mail@david-bauer.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan/vxlan_core.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c
index f78dd0438843b..567cb3faab709 100644
--- a/drivers/net/vxlan/vxlan_core.c
+++ b/drivers/net/vxlan/vxlan_core.c
@@ -1446,6 +1446,10 @@ static bool vxlan_snoop(struct net_device *dev,
 	struct vxlan_fdb *f;
 	u32 ifindex = 0;
 
+	/* Ignore packets from invalid src-address */
+	if (!is_valid_ether_addr(src_mac))
+		return true;
+
 #if IS_ENABLED(CONFIG_IPV6)
 	if (src_ip->sa.sa_family == AF_INET6 &&
 	    (ipv6_addr_type(&src_ip->sin6.sin6_addr) & IPV6_ADDR_LINKLOCAL))
@@ -1616,10 +1620,6 @@ static bool vxlan_set_mac(struct vxlan_dev *vxlan,
 	if (ether_addr_equal(eth_hdr(skb)->h_source, vxlan->dev->dev_addr))
 		return false;
 
-	/* Ignore packets from invalid src-address */
-	if (!is_valid_ether_addr(eth_hdr(skb)->h_source))
-		return false;
-
 	/* Get address from the outer IP header */
 	if (vxlan_get_sk_family(vs) == AF_INET) {
 		saddr.sin.sin_addr.s_addr = ip_hdr(skb)->saddr;
-- 
GitLab


From 712115a24b1a5318c10fc757d48d8f33815a6bfa Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Mon, 3 Jun 2024 17:30:19 +0800
Subject: [PATCH 800/950] selftests: hsr: add missing config for CONFIG_BRIDGE

hsr_redbox.sh test need to create bridge for testing. Add the missing
config CONFIG_BRIDGE in config file.

Fixes: eafbf0574e05 ("test: hsr: Extend the hsr_redbox.sh to have more SAN devices connected")
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Tested-by: Simon Horman <horms@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/hsr/config | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/testing/selftests/net/hsr/config b/tools/testing/selftests/net/hsr/config
index 22061204fb691..241542441c517 100644
--- a/tools/testing/selftests/net/hsr/config
+++ b/tools/testing/selftests/net/hsr/config
@@ -2,3 +2,4 @@ CONFIG_IPV6=y
 CONFIG_NET_SCH_NETEM=m
 CONFIG_HSR=y
 CONFIG_VETH=y
+CONFIG_BRIDGE=y
-- 
GitLab


From db574f2f96d0c9a245a9e787e3d9ec288fb2b445 Mon Sep 17 00:00:00 2001
From: Tao Su <tao1.su@linux.intel.com>
Date: Tue, 28 May 2024 18:22:34 +0800
Subject: [PATCH 801/950] KVM: x86/mmu: Don't save mmu_invalidate_seq after
 checking private attr

Drop the second snapshot of mmu_invalidate_seq in kvm_faultin_pfn().
Before checking the mismatch of private vs. shared, mmu_invalidate_seq is
saved to fault->mmu_seq, which can be used to detect an invalidation
related to the gfn occurred, i.e. KVM will not install a mapping in page
table if fault->mmu_seq != mmu_invalidate_seq.

Currently there is a second snapshot of mmu_invalidate_seq, which may not
be same as the first snapshot in kvm_faultin_pfn(), i.e. the gfn attribute
may be changed between the two snapshots, but the gfn may be mapped in
page table without hindrance. Therefore, drop the second snapshot as it
has no obvious benefits.

Fixes: f6adeae81f35 ("KVM: x86/mmu: Handle no-slot faults at the beginning of kvm_faultin_pfn()")
Signed-off-by: Tao Su <tao1.su@linux.intel.com>
Message-ID: <20240528102234.2162763-1-tao1.su@linux.intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/mmu.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index b7b4426a7221d..8d74bdef68c1d 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -4411,9 +4411,6 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
 			return RET_PF_EMULATE;
 	}
 
-	fault->mmu_seq = vcpu->kvm->mmu_invalidate_seq;
-	smp_rmb();
-
 	/*
 	 * Check for a relevant mmu_notifier invalidation event before getting
 	 * the pfn from the primary MMU, and before acquiring mmu_lock.
-- 
GitLab


From b907194a5d5bcd3b01d28d095f6a4d9fcd9c5354 Mon Sep 17 00:00:00 2001
From: Anshumali Gaur <agaur@marvell.com>
Date: Mon, 3 Jun 2024 16:52:48 +0530
Subject: [PATCH 802/950] octeontx2-af: Add debugfs support to dump NIX TM
 topology

This patch adds support to dump NIX transmit queue topology.
There are multiple levels of scheduling/shaping supported by
NIX and a packet traverses through multiple levels before sending
the packet out. At each level, there are set of scheduling/shaping
rules applied to a packet flow.

Each packet traverses through multiple levels
SQ->SMQ->TL4->TL3->TL2->TL1 and these levels are mapped in a parent-child
relationship.

This patch dumps the debug information related to all TM Levels in
the following way.

Example:
$ echo <nixlf> > /sys/kernel/debug/octeontx2/nix/tm_tree
$ cat /sys/kernel/debug/octeontx2/nix/tm_tree

A more desriptive set of registers at each level can be dumped
in the following way.

Example:
$ echo <nixlf> > /sys/kernel/debug/octeontx2/nix/tm_topo
$ cat /sys/kernel/debug/octeontx2/nix/tm_topo

Signed-off-by: Anshumali Gaur <agaur@marvell.com>
Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/marvell/octeontx2/af/rvu.h   |   1 +
 .../marvell/octeontx2/af/rvu_debugfs.c        | 365 ++++++++++++++++++
 .../ethernet/marvell/octeontx2/af/rvu_reg.h   |   7 +
 3 files changed, 373 insertions(+)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index 35834687e40fe..3063a84a45ef6 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -76,6 +76,7 @@ struct rvu_debugfs {
 	struct dump_ctx nix_cq_ctx;
 	struct dump_ctx nix_rq_ctx;
 	struct dump_ctx nix_sq_ctx;
+	struct dump_ctx nix_tm_ctx;
 	struct cpt_ctx cpt_ctx[MAX_CPT_BLKS];
 	int npa_qsize_id;
 	int nix_qsize_id;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
index 881d704644fbe..4a4ef5bd9e0bd 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
@@ -1603,6 +1603,367 @@ static void print_nix_cn10k_sq_ctx(struct seq_file *m,
 		   (u64)sq_ctx->dropped_pkts);
 }
 
+static void print_tm_tree(struct seq_file *m,
+			  struct nix_aq_enq_rsp *rsp, u64 sq)
+{
+	struct nix_sq_ctx_s *sq_ctx = &rsp->sq;
+	struct nix_hw *nix_hw = m->private;
+	struct rvu *rvu = nix_hw->rvu;
+	u16 p1, p2, p3, p4, schq;
+	int blkaddr;
+	u64 cfg;
+
+	blkaddr = nix_hw->blkaddr;
+	schq = sq_ctx->smq;
+
+	cfg = rvu_read64(rvu, blkaddr, NIX_AF_MDQX_PARENT(schq));
+	p1 = FIELD_GET(NIX_AF_MDQ_PARENT_MASK, cfg);
+
+	cfg = rvu_read64(rvu, blkaddr, NIX_AF_TL4X_PARENT(p1));
+	p2 = FIELD_GET(NIX_AF_TL4_PARENT_MASK, cfg);
+
+	cfg = rvu_read64(rvu, blkaddr, NIX_AF_TL3X_PARENT(p2));
+	p3 = FIELD_GET(NIX_AF_TL3_PARENT_MASK, cfg);
+
+	cfg = rvu_read64(rvu, blkaddr, NIX_AF_TL2X_PARENT(p3));
+	p4 = FIELD_GET(NIX_AF_TL2_PARENT_MASK, cfg);
+	seq_printf(m,
+		   "SQ(%llu) -> SMQ(%u) -> TL4(%u) -> TL3(%u) -> TL2(%u) -> TL1(%u)\n",
+		   sq, schq, p1, p2, p3, p4);
+}
+
+/*dumps given tm_tree registers*/
+static int rvu_dbg_nix_tm_tree_display(struct seq_file *m, void *unused)
+{
+	int qidx, nixlf, rc, id, max_id = 0;
+	struct nix_hw *nix_hw = m->private;
+	struct rvu *rvu = nix_hw->rvu;
+	struct nix_aq_enq_req aq_req;
+	struct nix_aq_enq_rsp rsp;
+	struct rvu_pfvf *pfvf;
+	u16 pcifunc;
+
+	nixlf = rvu->rvu_dbg.nix_tm_ctx.lf;
+	id = rvu->rvu_dbg.nix_tm_ctx.id;
+
+	if (!rvu_dbg_is_valid_lf(rvu, nix_hw->blkaddr, nixlf, &pcifunc))
+		return -EINVAL;
+
+	pfvf = rvu_get_pfvf(rvu, pcifunc);
+	max_id = pfvf->sq_ctx->qsize;
+
+	memset(&aq_req, 0, sizeof(struct nix_aq_enq_req));
+	aq_req.hdr.pcifunc = pcifunc;
+	aq_req.ctype = NIX_AQ_CTYPE_SQ;
+	aq_req.op = NIX_AQ_INSTOP_READ;
+	seq_printf(m, "pcifunc is 0x%x\n", pcifunc);
+	for (qidx = id; qidx < max_id; qidx++) {
+		aq_req.qidx = qidx;
+
+		/* Skip SQ's if not initialized */
+		if (!test_bit(qidx, pfvf->sq_bmap))
+			continue;
+
+		rc = rvu_mbox_handler_nix_aq_enq(rvu, &aq_req, &rsp);
+
+		if (rc) {
+			seq_printf(m, "Failed to read SQ(%d) context\n",
+				   aq_req.qidx);
+			continue;
+		}
+		print_tm_tree(m, &rsp, aq_req.qidx);
+	}
+	return 0;
+}
+
+static ssize_t rvu_dbg_nix_tm_tree_write(struct file *filp,
+					 const char __user *buffer,
+					 size_t count, loff_t *ppos)
+{
+	struct seq_file *m = filp->private_data;
+	struct nix_hw *nix_hw = m->private;
+	struct rvu *rvu = nix_hw->rvu;
+	struct rvu_pfvf *pfvf;
+	u16 pcifunc;
+	u64 nixlf;
+	int ret;
+
+	ret = kstrtoull_from_user(buffer, count, 10, &nixlf);
+	if (ret)
+		return ret;
+
+	if (!rvu_dbg_is_valid_lf(rvu, nix_hw->blkaddr, nixlf, &pcifunc))
+		return -EINVAL;
+
+	pfvf = rvu_get_pfvf(rvu, pcifunc);
+	if (!pfvf->sq_ctx) {
+		dev_warn(rvu->dev, "SQ context is not initialized\n");
+		return -EINVAL;
+	}
+
+	rvu->rvu_dbg.nix_tm_ctx.lf = nixlf;
+	return count;
+}
+
+RVU_DEBUG_SEQ_FOPS(nix_tm_tree, nix_tm_tree_display, nix_tm_tree_write);
+
+static void print_tm_topo(struct seq_file *m, u64 schq, u32 lvl)
+{
+	struct nix_hw *nix_hw = m->private;
+	struct rvu *rvu = nix_hw->rvu;
+	int blkaddr, link, link_level;
+	struct rvu_hwinfo *hw;
+
+	hw = rvu->hw;
+	blkaddr = nix_hw->blkaddr;
+	if (lvl == NIX_TXSCH_LVL_MDQ) {
+		seq_printf(m, "NIX_AF_SMQ[%llu]_CFG =0x%llx\n", schq,
+			   rvu_read64(rvu, blkaddr, NIX_AF_SMQX_CFG(schq)));
+		seq_printf(m, "NIX_AF_SMQ[%llu]_STATUS =0x%llx\n", schq,
+			   rvu_read64(rvu, blkaddr, NIX_AF_SMQX_STATUS(schq)));
+		seq_printf(m, "NIX_AF_MDQ[%llu]_OUT_MD_COUNT =0x%llx\n", schq,
+			   rvu_read64(rvu, blkaddr,
+				      NIX_AF_MDQX_OUT_MD_COUNT(schq)));
+		seq_printf(m, "NIX_AF_MDQ[%llu]_SCHEDULE =0x%llx\n", schq,
+			   rvu_read64(rvu, blkaddr,
+				      NIX_AF_MDQX_SCHEDULE(schq)));
+		seq_printf(m, "NIX_AF_MDQ[%llu]_SHAPE =0x%llx\n", schq,
+			   rvu_read64(rvu, blkaddr, NIX_AF_MDQX_SHAPE(schq)));
+		seq_printf(m, "NIX_AF_MDQ[%llu]_CIR =0x%llx\n", schq,
+			   rvu_read64(rvu, blkaddr, NIX_AF_MDQX_CIR(schq)));
+		seq_printf(m, "NIX_AF_MDQ[%llu]_PIR =0x%llx\n", schq,
+			   rvu_read64(rvu, blkaddr, NIX_AF_MDQX_PIR(schq)));
+		seq_printf(m, "NIX_AF_MDQ[%llu]_SW_XOFF =0x%llx\n", schq,
+			   rvu_read64(rvu, blkaddr, NIX_AF_MDQX_SW_XOFF(schq)));
+		seq_printf(m, "NIX_AF_MDQ[%llu]_PARENT =0x%llx\n", schq,
+			   rvu_read64(rvu, blkaddr, NIX_AF_MDQX_PARENT(schq)));
+		seq_puts(m, "\n");
+	}
+
+	if (lvl == NIX_TXSCH_LVL_TL4) {
+		seq_printf(m, "NIX_AF_TL4[%llu]_SDP_LINK_CFG =0x%llx\n", schq,
+			   rvu_read64(rvu, blkaddr,
+				      NIX_AF_TL4X_SDP_LINK_CFG(schq)));
+		seq_printf(m, "NIX_AF_TL4[%llu]_SCHEDULE =0x%llx\n", schq,
+			   rvu_read64(rvu, blkaddr,
+				      NIX_AF_TL4X_SCHEDULE(schq)));
+		seq_printf(m, "NIX_AF_TL4[%llu]_SHAPE =0x%llx\n", schq,
+			   rvu_read64(rvu, blkaddr, NIX_AF_TL4X_SHAPE(schq)));
+		seq_printf(m, "NIX_AF_TL4[%llu]_CIR =0x%llx\n", schq,
+			   rvu_read64(rvu, blkaddr, NIX_AF_TL4X_CIR(schq)));
+		seq_printf(m, "NIX_AF_TL4[%llu]_PIR =0x%llx\n", schq,
+			   rvu_read64(rvu, blkaddr, NIX_AF_TL4X_PIR(schq)));
+		seq_printf(m, "NIX_AF_TL4[%llu]_SW_XOFF =0x%llx\n", schq,
+			   rvu_read64(rvu, blkaddr, NIX_AF_TL4X_SW_XOFF(schq)));
+		seq_printf(m, "NIX_AF_TL4[%llu]_TOPOLOGY =0x%llx\n", schq,
+			   rvu_read64(rvu, blkaddr,
+				      NIX_AF_TL4X_TOPOLOGY(schq)));
+		seq_printf(m, "NIX_AF_TL4[%llu]_PARENT =0x%llx\n", schq,
+			   rvu_read64(rvu, blkaddr, NIX_AF_TL4X_PARENT(schq)));
+		seq_printf(m, "NIX_AF_TL4[%llu]_MD_DEBUG0 =0x%llx\n", schq,
+			   rvu_read64(rvu, blkaddr,
+				      NIX_AF_TL4X_MD_DEBUG0(schq)));
+		seq_printf(m, "NIX_AF_TL4[%llu]_MD_DEBUG1 =0x%llx\n", schq,
+			   rvu_read64(rvu, blkaddr,
+				      NIX_AF_TL4X_MD_DEBUG1(schq)));
+		seq_puts(m, "\n");
+	}
+
+	if (lvl == NIX_TXSCH_LVL_TL3) {
+		seq_printf(m, "NIX_AF_TL3[%llu]_SCHEDULE =0x%llx\n", schq,
+			   rvu_read64(rvu, blkaddr,
+				      NIX_AF_TL3X_SCHEDULE(schq)));
+		seq_printf(m, "NIX_AF_TL3[%llu]_SHAPE =0x%llx\n", schq,
+			   rvu_read64(rvu, blkaddr, NIX_AF_TL3X_SHAPE(schq)));
+		seq_printf(m, "NIX_AF_TL3[%llu]_CIR =0x%llx\n", schq,
+			   rvu_read64(rvu, blkaddr, NIX_AF_TL3X_CIR(schq)));
+		seq_printf(m, "NIX_AF_TL3[%llu]_PIR =0x%llx\n", schq,
+			   rvu_read64(rvu, blkaddr, NIX_AF_TL3X_PIR(schq)));
+		seq_printf(m, "NIX_AF_TL3[%llu]_SW_XOFF =0x%llx\n", schq,
+			   rvu_read64(rvu, blkaddr, NIX_AF_TL3X_SW_XOFF(schq)));
+		seq_printf(m, "NIX_AF_TL3[%llu]_TOPOLOGY =0x%llx\n", schq,
+			   rvu_read64(rvu, blkaddr,
+				      NIX_AF_TL3X_TOPOLOGY(schq)));
+		seq_printf(m, "NIX_AF_TL3[%llu]_PARENT =0x%llx\n", schq,
+			   rvu_read64(rvu, blkaddr, NIX_AF_TL3X_PARENT(schq)));
+		seq_printf(m, "NIX_AF_TL3[%llu]_MD_DEBUG0 =0x%llx\n", schq,
+			   rvu_read64(rvu, blkaddr,
+				      NIX_AF_TL3X_MD_DEBUG0(schq)));
+		seq_printf(m, "NIX_AF_TL3[%llu]_MD_DEBUG1 =0x%llx\n", schq,
+			   rvu_read64(rvu, blkaddr,
+				      NIX_AF_TL3X_MD_DEBUG1(schq)));
+
+		link_level = rvu_read64(rvu, blkaddr, NIX_AF_PSE_CHANNEL_LEVEL)
+				& 0x01 ? NIX_TXSCH_LVL_TL3 : NIX_TXSCH_LVL_TL2;
+		if (lvl == link_level) {
+			seq_printf(m,
+				   "NIX_AF_TL3_TL2[%llu]_BP_STATUS =0x%llx\n",
+				   schq, rvu_read64(rvu, blkaddr,
+				   NIX_AF_TL3_TL2X_BP_STATUS(schq)));
+			for (link = 0; link < hw->cgx_links; link++)
+				seq_printf(m,
+					   "NIX_AF_TL3_TL2[%llu]_LINK[%d]_CFG =0x%llx\n",
+					   schq, link,
+					   rvu_read64(rvu, blkaddr,
+						      NIX_AF_TL3_TL2X_LINKX_CFG(schq, link)));
+		}
+		seq_puts(m, "\n");
+	}
+
+	if (lvl == NIX_TXSCH_LVL_TL2) {
+		seq_printf(m, "NIX_AF_TL2[%llu]_SHAPE =0x%llx\n", schq,
+			   rvu_read64(rvu, blkaddr, NIX_AF_TL2X_SHAPE(schq)));
+		seq_printf(m, "NIX_AF_TL2[%llu]_CIR =0x%llx\n", schq,
+			   rvu_read64(rvu, blkaddr, NIX_AF_TL2X_CIR(schq)));
+		seq_printf(m, "NIX_AF_TL2[%llu]_PIR =0x%llx\n", schq,
+			   rvu_read64(rvu, blkaddr, NIX_AF_TL2X_PIR(schq)));
+		seq_printf(m, "NIX_AF_TL2[%llu]_SW_XOFF =0x%llx\n", schq,
+			   rvu_read64(rvu, blkaddr, NIX_AF_TL2X_SW_XOFF(schq)));
+		seq_printf(m, "NIX_AF_TL2[%llu]_TOPOLOGY =0x%llx\n", schq,
+			   rvu_read64(rvu, blkaddr,
+				      NIX_AF_TL2X_TOPOLOGY(schq)));
+		seq_printf(m, "NIX_AF_TL2[%llu]_PARENT =0x%llx\n", schq,
+			   rvu_read64(rvu, blkaddr, NIX_AF_TL2X_PARENT(schq)));
+		seq_printf(m, "NIX_AF_TL2[%llu]_MD_DEBUG0 =0x%llx\n", schq,
+			   rvu_read64(rvu, blkaddr,
+				      NIX_AF_TL2X_MD_DEBUG0(schq)));
+		seq_printf(m, "NIX_AF_TL2[%llu]_MD_DEBUG1 =0x%llx\n", schq,
+			   rvu_read64(rvu, blkaddr,
+				      NIX_AF_TL2X_MD_DEBUG1(schq)));
+
+		link_level = rvu_read64(rvu, blkaddr, NIX_AF_PSE_CHANNEL_LEVEL)
+				& 0x01 ? NIX_TXSCH_LVL_TL3 : NIX_TXSCH_LVL_TL2;
+		if (lvl == link_level) {
+			seq_printf(m,
+				   "NIX_AF_TL3_TL2[%llu]_BP_STATUS =0x%llx\n",
+				   schq, rvu_read64(rvu, blkaddr,
+				   NIX_AF_TL3_TL2X_BP_STATUS(schq)));
+			for (link = 0; link < hw->cgx_links; link++)
+				seq_printf(m,
+					   "NIX_AF_TL3_TL2[%llu]_LINK[%d]_CFG =0x%llx\n",
+					   schq, link, rvu_read64(rvu, blkaddr,
+					   NIX_AF_TL3_TL2X_LINKX_CFG(schq, link)));
+		}
+		seq_puts(m, "\n");
+	}
+
+	if (lvl == NIX_TXSCH_LVL_TL1) {
+		seq_printf(m, "NIX_AF_TX_LINK[%llu]_NORM_CREDIT =0x%llx\n",
+			   schq,
+			   rvu_read64(rvu, blkaddr,
+				      NIX_AF_TX_LINKX_NORM_CREDIT(schq)));
+		seq_printf(m, "NIX_AF_TX_LINK[%llu]_HW_XOFF =0x%llx\n", schq,
+			   rvu_read64(rvu, blkaddr,
+				      NIX_AF_TX_LINKX_HW_XOFF(schq)));
+		seq_printf(m, "NIX_AF_TL1[%llu]_SCHEDULE =0x%llx\n", schq,
+			   rvu_read64(rvu, blkaddr,
+				      NIX_AF_TL1X_SCHEDULE(schq)));
+		seq_printf(m, "NIX_AF_TL1[%llu]_SHAPE =0x%llx\n", schq,
+			   rvu_read64(rvu, blkaddr, NIX_AF_TL1X_SHAPE(schq)));
+		seq_printf(m, "NIX_AF_TL1[%llu]_CIR =0x%llx\n", schq,
+			   rvu_read64(rvu, blkaddr, NIX_AF_TL1X_CIR(schq)));
+		seq_printf(m, "NIX_AF_TL1[%llu]_SW_XOFF =0x%llx\n", schq,
+			   rvu_read64(rvu, blkaddr, NIX_AF_TL1X_SW_XOFF(schq)));
+		seq_printf(m, "NIX_AF_TL1[%llu]_TOPOLOGY =0x%llx\n", schq,
+			   rvu_read64(rvu, blkaddr,
+				      NIX_AF_TL1X_TOPOLOGY(schq)));
+		seq_printf(m, "NIX_AF_TL1[%llu]_MD_DEBUG0 =0x%llx\n", schq,
+			   rvu_read64(rvu, blkaddr,
+				      NIX_AF_TL1X_MD_DEBUG0(schq)));
+		seq_printf(m, "NIX_AF_TL1[%llu]_MD_DEBUG1 =0x%llx\n", schq,
+			   rvu_read64(rvu, blkaddr,
+				      NIX_AF_TL1X_MD_DEBUG1(schq)));
+		seq_printf(m, "NIX_AF_TL1[%llu]_DROPPED_PACKETS =0x%llx\n",
+			   schq,
+			   rvu_read64(rvu, blkaddr,
+				      NIX_AF_TL1X_DROPPED_PACKETS(schq)));
+		seq_printf(m, "NIX_AF_TL1[%llu]_DROPPED_BYTES =0x%llx\n", schq,
+			   rvu_read64(rvu, blkaddr,
+				      NIX_AF_TL1X_DROPPED_BYTES(schq)));
+		seq_printf(m, "NIX_AF_TL1[%llu]_RED_PACKETS =0x%llx\n", schq,
+			   rvu_read64(rvu, blkaddr,
+				      NIX_AF_TL1X_RED_PACKETS(schq)));
+		seq_printf(m, "NIX_AF_TL1[%llu]_RED_BYTES =0x%llx\n", schq,
+			   rvu_read64(rvu, blkaddr,
+				      NIX_AF_TL1X_RED_BYTES(schq)));
+		seq_printf(m, "NIX_AF_TL1[%llu]_YELLOW_PACKETS =0x%llx\n", schq,
+			   rvu_read64(rvu, blkaddr,
+				      NIX_AF_TL1X_YELLOW_PACKETS(schq)));
+		seq_printf(m, "NIX_AF_TL1[%llu]_YELLOW_BYTES =0x%llx\n", schq,
+			   rvu_read64(rvu, blkaddr,
+				      NIX_AF_TL1X_YELLOW_BYTES(schq)));
+		seq_printf(m, "NIX_AF_TL1[%llu]_GREEN_PACKETS =0x%llx\n", schq,
+			   rvu_read64(rvu, blkaddr,
+				      NIX_AF_TL1X_GREEN_PACKETS(schq)));
+		seq_printf(m, "NIX_AF_TL1[%llu]_GREEN_BYTES =0x%llx\n", schq,
+			   rvu_read64(rvu, blkaddr,
+				      NIX_AF_TL1X_GREEN_BYTES(schq)));
+		seq_puts(m, "\n");
+	}
+}
+
+/*dumps given tm_topo registers*/
+static int rvu_dbg_nix_tm_topo_display(struct seq_file *m, void *unused)
+{
+	struct nix_hw *nix_hw = m->private;
+	struct rvu *rvu = nix_hw->rvu;
+	struct nix_aq_enq_req aq_req;
+	struct nix_txsch *txsch;
+	int nixlf, lvl, schq;
+	u16 pcifunc;
+
+	nixlf = rvu->rvu_dbg.nix_tm_ctx.lf;
+
+	if (!rvu_dbg_is_valid_lf(rvu, nix_hw->blkaddr, nixlf, &pcifunc))
+		return -EINVAL;
+
+	memset(&aq_req, 0, sizeof(struct nix_aq_enq_req));
+	aq_req.hdr.pcifunc = pcifunc;
+	aq_req.ctype = NIX_AQ_CTYPE_SQ;
+	aq_req.op = NIX_AQ_INSTOP_READ;
+	seq_printf(m, "pcifunc is 0x%x\n", pcifunc);
+
+	for (lvl = 0; lvl < NIX_TXSCH_LVL_CNT; lvl++) {
+		txsch = &nix_hw->txsch[lvl];
+		for (schq = 0; schq < txsch->schq.max; schq++) {
+			if (TXSCH_MAP_FUNC(txsch->pfvf_map[schq]) == pcifunc)
+				print_tm_topo(m, schq, lvl);
+		}
+	}
+	return 0;
+}
+
+static ssize_t rvu_dbg_nix_tm_topo_write(struct file *filp,
+					 const char __user *buffer,
+					 size_t count, loff_t *ppos)
+{
+	struct seq_file *m = filp->private_data;
+	struct nix_hw *nix_hw = m->private;
+	struct rvu *rvu = nix_hw->rvu;
+	struct rvu_pfvf *pfvf;
+	u16 pcifunc;
+	u64 nixlf;
+	int ret;
+
+	ret = kstrtoull_from_user(buffer, count, 10, &nixlf);
+	if (ret)
+		return ret;
+
+	if (!rvu_dbg_is_valid_lf(rvu, nix_hw->blkaddr, nixlf, &pcifunc))
+		return -EINVAL;
+
+	pfvf = rvu_get_pfvf(rvu, pcifunc);
+	if (!pfvf->sq_ctx) {
+		dev_warn(rvu->dev, "SQ context is not initialized\n");
+		return -EINVAL;
+	}
+
+	rvu->rvu_dbg.nix_tm_ctx.lf = nixlf;
+	return count;
+}
+
+RVU_DEBUG_SEQ_FOPS(nix_tm_topo, nix_tm_topo_display, nix_tm_topo_write);
+
 /* Dumps given nix_sq's context */
 static void print_nix_sq_ctx(struct seq_file *m, struct nix_aq_enq_rsp *rsp)
 {
@@ -2349,6 +2710,10 @@ static void rvu_dbg_nix_init(struct rvu *rvu, int blkaddr)
 		nix_hw = &rvu->hw->nix[1];
 	}
 
+	debugfs_create_file("tm_tree", 0600, rvu->rvu_dbg.nix, nix_hw,
+			    &rvu_dbg_nix_tm_tree_fops);
+	debugfs_create_file("tm_topo", 0600, rvu->rvu_dbg.nix, nix_hw,
+			    &rvu_dbg_nix_tm_topo_fops);
 	debugfs_create_file("sq_ctx", 0600, rvu->rvu_dbg.nix, nix_hw,
 			    &rvu_dbg_nix_sq_ctx_fops);
 	debugfs_create_file("rq_ctx", 0600, rvu->rvu_dbg.nix, nix_hw,
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h
index 086f05c0376f5..5ec92654e7ad7 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h
@@ -429,6 +429,8 @@
 #define NIX_AF_RX_ACTIVE_CYCLES_PCX(a)	(0x4800 | (a) << 16)
 #define NIX_AF_LINKX_CFG(a)		(0x4010 | (a) << 17)
 #define NIX_AF_MDQX_IN_MD_COUNT(a)	(0x14e0 | (a) << 16)
+#define NIX_AF_SMQX_STATUS(a)		(0x730 | (a) << 16)
+#define NIX_AF_MDQX_OUT_MD_COUNT(a)	(0xdb0 | (a) << 16)
 
 #define NIX_PRIV_AF_INT_CFG		(0x8000000)
 #define NIX_PRIV_LFX_CFG		(0x8000010)
@@ -442,6 +444,11 @@
 #define NIX_CONST_MAX_BPIDS		GENMASK_ULL(23, 12)
 #define NIX_CONST_SDP_CHANS		GENMASK_ULL(11, 0)
 
+#define NIX_AF_MDQ_PARENT_MASK         GENMASK_ULL(24, 16)
+#define NIX_AF_TL4_PARENT_MASK         GENMASK_ULL(23, 16)
+#define NIX_AF_TL3_PARENT_MASK         GENMASK_ULL(23, 16)
+#define NIX_AF_TL2_PARENT_MASK         GENMASK_ULL(20, 16)
+
 /* SSO */
 #define SSO_AF_CONST			(0x1000)
 #define SSO_AF_CONST1			(0x1008)
-- 
GitLab


From 69e0b33a7fce4d96649b9fa32e56b696921aa48e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 3 Jun 2024 15:51:06 +0000
Subject: [PATCH 803/950] tcp: annotate data-races around tw->tw_ts_recent and
 tw->tw_ts_recent_stamp

These fields can be read and written locklessly, add annotations
around these minor races.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_ipv4.c      | 12 +++++++-----
 net/ipv4/tcp_minisocks.c | 22 ++++++++++++++--------
 net/ipv6/tcp_ipv6.c      |  6 +++---
 3 files changed, 24 insertions(+), 16 deletions(-)

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 04044605cadf1..3ef4b274c24b8 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -114,6 +114,7 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
 	const struct inet_timewait_sock *tw = inet_twsk(sktw);
 	const struct tcp_timewait_sock *tcptw = tcp_twsk(sktw);
 	struct tcp_sock *tp = tcp_sk(sk);
+	int ts_recent_stamp;
 
 	if (reuse == 2) {
 		/* Still does not detect *everything* that goes through
@@ -152,9 +153,10 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
 	   If TW bucket has been already destroyed we fall back to VJ's scheme
 	   and use initial timestamp retrieved from peer table.
 	 */
-	if (tcptw->tw_ts_recent_stamp &&
+	ts_recent_stamp = READ_ONCE(tcptw->tw_ts_recent_stamp);
+	if (ts_recent_stamp &&
 	    (!twp || (reuse && time_after32(ktime_get_seconds(),
-					    tcptw->tw_ts_recent_stamp)))) {
+					    ts_recent_stamp)))) {
 		/* inet_twsk_hashdance() sets sk_refcnt after putting twsk
 		 * and releasing the bucket lock.
 		 */
@@ -178,8 +180,8 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
 			if (!seq)
 				seq = 1;
 			WRITE_ONCE(tp->write_seq, seq);
-			tp->rx_opt.ts_recent	   = tcptw->tw_ts_recent;
-			tp->rx_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp;
+			tp->rx_opt.ts_recent	   = READ_ONCE(tcptw->tw_ts_recent);
+			tp->rx_opt.ts_recent_stamp = ts_recent_stamp;
 		}
 
 		return 1;
@@ -1064,7 +1066,7 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb)
 			tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
 			tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
 			tcp_tw_tsval(tcptw),
-			tcptw->tw_ts_recent,
+			READ_ONCE(tcptw->tw_ts_recent),
 			tw->tw_bound_dev_if, &key,
 			tw->tw_transparent ? IP_REPLY_ARG_NOSRCCHECK : 0,
 			tw->tw_tos,
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 538c06f95918d..4c894e540730a 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -101,16 +101,18 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
 	struct tcp_options_received tmp_opt;
 	struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw);
 	bool paws_reject = false;
+	int ts_recent_stamp;
 
 	tmp_opt.saw_tstamp = 0;
-	if (th->doff > (sizeof(*th) >> 2) && tcptw->tw_ts_recent_stamp) {
+	ts_recent_stamp = READ_ONCE(tcptw->tw_ts_recent_stamp);
+	if (th->doff > (sizeof(*th) >> 2) && ts_recent_stamp) {
 		tcp_parse_options(twsk_net(tw), skb, &tmp_opt, 0, NULL);
 
 		if (tmp_opt.saw_tstamp) {
 			if (tmp_opt.rcv_tsecr)
 				tmp_opt.rcv_tsecr -= tcptw->tw_ts_offset;
-			tmp_opt.ts_recent	= tcptw->tw_ts_recent;
-			tmp_opt.ts_recent_stamp	= tcptw->tw_ts_recent_stamp;
+			tmp_opt.ts_recent	= READ_ONCE(tcptw->tw_ts_recent);
+			tmp_opt.ts_recent_stamp	= ts_recent_stamp;
 			paws_reject = tcp_paws_reject(&tmp_opt, th->rst);
 		}
 	}
@@ -152,8 +154,10 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
 		twsk_rcv_nxt_update(tcptw, TCP_SKB_CB(skb)->end_seq);
 
 		if (tmp_opt.saw_tstamp) {
-			tcptw->tw_ts_recent_stamp = ktime_get_seconds();
-			tcptw->tw_ts_recent	  = tmp_opt.rcv_tsval;
+			WRITE_ONCE(tcptw->tw_ts_recent_stamp,
+				  ktime_get_seconds());
+			WRITE_ONCE(tcptw->tw_ts_recent,
+				   tmp_opt.rcv_tsval);
 		}
 
 		inet_twsk_reschedule(tw, TCP_TIMEWAIT_LEN);
@@ -197,8 +201,10 @@ kill:
 		}
 
 		if (tmp_opt.saw_tstamp) {
-			tcptw->tw_ts_recent	  = tmp_opt.rcv_tsval;
-			tcptw->tw_ts_recent_stamp = ktime_get_seconds();
+			WRITE_ONCE(tcptw->tw_ts_recent,
+				   tmp_opt.rcv_tsval);
+			WRITE_ONCE(tcptw->tw_ts_recent_stamp,
+				   ktime_get_seconds());
 		}
 
 		inet_twsk_put(tw);
@@ -225,7 +231,7 @@ kill:
 	if (th->syn && !th->rst && !th->ack && !paws_reject &&
 	    (after(TCP_SKB_CB(skb)->seq, tcptw->tw_rcv_nxt) ||
 	     (tmp_opt.saw_tstamp &&
-	      (s32)(tcptw->tw_ts_recent - tmp_opt.rcv_tsval) < 0))) {
+	      (s32)(READ_ONCE(tcptw->tw_ts_recent) - tmp_opt.rcv_tsval) < 0))) {
 		u32 isn = tcptw->tw_snd_nxt + 65535 + 2;
 		if (isn == 0)
 			isn++;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 5fe4365de89dd..f4777c03cdd7a 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1196,9 +1196,9 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb)
 	tcp_v6_send_ack(sk, skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
 			tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
 			tcp_tw_tsval(tcptw),
-			tcptw->tw_ts_recent, tw->tw_bound_dev_if, &key,
-			tw->tw_tclass, cpu_to_be32(tw->tw_flowlabel), tw->tw_priority,
-			tw->tw_txhash);
+			READ_ONCE(tcptw->tw_ts_recent), tw->tw_bound_dev_if,
+			&key, tw->tw_tclass, cpu_to_be32(tw->tw_flowlabel),
+			tw->tw_priority, tw->tw_txhash);
 
 #ifdef CONFIG_TCP_AO
 out:
-- 
GitLab


From a46d0ea5c94205f40ecf912d1bb7806a8a64704f Mon Sep 17 00:00:00 2001
From: Jason Xing <kernelxing@tencent.com>
Date: Tue, 4 Jun 2024 01:02:16 +0800
Subject: [PATCH 804/950] tcp: count CLOSE-WAIT sockets for TCP_MIB_CURRESTAB

According to RFC 1213, we should also take CLOSE-WAIT sockets into
consideration:

  "tcpCurrEstab OBJECT-TYPE
   ...
   The number of TCP connections for which the current state
   is either ESTABLISHED or CLOSE- WAIT."

After this, CurrEstab counter will display the total number of
ESTABLISHED and CLOSE-WAIT sockets.

The logic of counting
When we increment the counter?
a) if we change the state to ESTABLISHED.
b) if we change the state from SYN-RECEIVED to CLOSE-WAIT.

When we decrement the counter?
a) if the socket leaves ESTABLISHED and will never go into CLOSE-WAIT,
say, on the client side, changing from ESTABLISHED to FIN-WAIT-1.
b) if the socket leaves CLOSE-WAIT, say, on the server side, changing
from CLOSE-WAIT to LAST-ACK.

Please note: there are two chances that old state of socket can be changed
to CLOSE-WAIT in tcp_fin(). One is SYN-RECV, the other is ESTABLISHED.
So we have to take care of the former case.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Jason Xing <kernelxing@tencent.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 4d8cc2ebb64c7..e6790ea748773 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2649,6 +2649,10 @@ void tcp_set_state(struct sock *sk, int state)
 		if (oldstate != TCP_ESTABLISHED)
 			TCP_INC_STATS(sock_net(sk), TCP_MIB_CURRESTAB);
 		break;
+	case TCP_CLOSE_WAIT:
+		if (oldstate == TCP_SYN_RECV)
+			TCP_INC_STATS(sock_net(sk), TCP_MIB_CURRESTAB);
+		break;
 
 	case TCP_CLOSE:
 		if (oldstate == TCP_CLOSE_WAIT || oldstate == TCP_ESTABLISHED)
@@ -2660,7 +2664,7 @@ void tcp_set_state(struct sock *sk, int state)
 			inet_put_port(sk);
 		fallthrough;
 	default:
-		if (oldstate == TCP_ESTABLISHED)
+		if (oldstate == TCP_ESTABLISHED || oldstate == TCP_CLOSE_WAIT)
 			TCP_DEC_STATS(sock_net(sk), TCP_MIB_CURRESTAB);
 	}
 
-- 
GitLab


From 9633e9377e6af0244f7381e86b9aac5276f5be97 Mon Sep 17 00:00:00 2001
From: Jason Xing <kernelxing@tencent.com>
Date: Tue, 4 Jun 2024 01:02:17 +0800
Subject: [PATCH 805/950] mptcp: count CLOSE-WAIT sockets for
 MPTCP_MIB_CURRESTAB

Like previous patch does in TCP, we need to adhere to RFC 1213:

  "tcpCurrEstab OBJECT-TYPE
   ...
   The number of TCP connections for which the current state
   is either ESTABLISHED or CLOSE- WAIT."

So let's consider CLOSE-WAIT sockets.

The logic of counting
When we increment the counter?
a) Only if we change the state to ESTABLISHED.

When we decrement the counter?
a) if the socket leaves ESTABLISHED and will never go into CLOSE-WAIT,
say, on the client side, changing from ESTABLISHED to FIN-WAIT-1.
b) if the socket leaves CLOSE-WAIT, say, on the server side, changing
from CLOSE-WAIT to LAST-ACK.

Fixes: d9cd27b8cd19 ("mptcp: add CurrEstab MIB counter support")
Signed-off-by: Jason Xing <kernelxing@tencent.com>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/protocol.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 7d44196ec5b63..96b113854bd3c 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2916,9 +2916,14 @@ void mptcp_set_state(struct sock *sk, int state)
 		if (oldstate != TCP_ESTABLISHED)
 			MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_CURRESTAB);
 		break;
-
+	case TCP_CLOSE_WAIT:
+		/* Unlike TCP, MPTCP sk would not have the TCP_SYN_RECV state:
+		 * MPTCP "accepted" sockets will be created later on. So no
+		 * transition from TCP_SYN_RECV to TCP_CLOSE_WAIT.
+		 */
+		break;
 	default:
-		if (oldstate == TCP_ESTABLISHED)
+		if (oldstate == TCP_ESTABLISHED || oldstate == TCP_CLOSE_WAIT)
 			MPTCP_DEC_STATS(sock_net(sk), MPTCP_MIB_CURRESTAB);
 	}
 
-- 
GitLab


From 5b4b62a169e10401cca34a6e7ac39161986f5605 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 3 Jun 2024 11:48:26 -0700
Subject: [PATCH 806/950] rtnetlink: make the "split" NLM_DONE handling generic

Jaroslav reports Dell's OMSA Systems Management Data Engine
expects NLM_DONE in a separate recvmsg(), both for rtnl_dump_ifinfo()
and inet_dump_ifaddr(). We already added a similar fix previously in
commit 460b0d33cf10 ("inet: bring NLM_DONE out to a separate recv() again")

Instead of modifying all the dump handlers, and making them look
different than modern for_each_netdev_dump()-based dump handlers -
put the workaround in rtnetlink code. This will also help us move
the custom rtnl-locking from af_netlink in the future (in net-next).

Note that this change is not touching rtnl_dump_all(). rtnl_dump_all()
is different kettle of fish and a potential problem. We now mix families
in a single recvmsg(), but NLM_DONE is not coalesced.

Tested:

  ./cli.py --dbg-small-recv 4096 --spec netlink/specs/rt_addr.yaml \
           --dump getaddr --json '{"ifa-family": 2}'

  ./cli.py --dbg-small-recv 4096 --spec netlink/specs/rt_route.yaml \
           --dump getroute --json '{"rtm-family": 2}'

  ./cli.py --dbg-small-recv 4096 --spec netlink/specs/rt_link.yaml \
           --dump getlink

Fixes: 3e41af90767d ("rtnetlink: use xarray iterator to implement rtnl_dump_ifinfo()")
Fixes: cdb2f80f1c10 ("inet: use xa_array iterator to implement inet_dump_ifaddr()")
Reported-by: Jaroslav Pulchart <jaroslav.pulchart@gooddata.com>
Link: https://lore.kernel.org/all/CAK8fFZ7MKoFSEzMBDAOjoUt+vTZRRQgLDNXEOfdCCXSoXXKE0g@mail.gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/rtnetlink.h |  1 +
 net/core/rtnetlink.c    | 44 +++++++++++++++++++++++++++++++++++++++--
 net/ipv4/devinet.c      |  2 +-
 net/ipv4/fib_frontend.c |  7 +------
 4 files changed, 45 insertions(+), 9 deletions(-)

diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h
index 3bfb80bad1739..b45d57b5968af 100644
--- a/include/net/rtnetlink.h
+++ b/include/net/rtnetlink.h
@@ -13,6 +13,7 @@ enum rtnl_link_flags {
 	RTNL_FLAG_DOIT_UNLOCKED		= BIT(0),
 	RTNL_FLAG_BULK_DEL_SUPPORTED	= BIT(1),
 	RTNL_FLAG_DUMP_UNLOCKED		= BIT(2),
+	RTNL_FLAG_DUMP_SPLIT_NLM_DONE	= BIT(3),	/* legacy behavior */
 };
 
 enum rtnl_kinds {
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index b86b0a87367dd..4668d67180407 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -6484,6 +6484,46 @@ static int rtnl_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 /* Process one rtnetlink message. */
 
+static int rtnl_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	rtnl_dumpit_func dumpit = cb->data;
+	int err;
+
+	/* Previous iteration have already finished, avoid calling->dumpit()
+	 * again, it may not expect to be called after it reached the end.
+	 */
+	if (!dumpit)
+		return 0;
+
+	err = dumpit(skb, cb);
+
+	/* Old dump handlers used to send NLM_DONE as in a separate recvmsg().
+	 * Some applications which parse netlink manually depend on this.
+	 */
+	if (cb->flags & RTNL_FLAG_DUMP_SPLIT_NLM_DONE) {
+		if (err < 0 && err != -EMSGSIZE)
+			return err;
+		if (!err)
+			cb->data = NULL;
+
+		return skb->len;
+	}
+	return err;
+}
+
+static int rtnetlink_dump_start(struct sock *ssk, struct sk_buff *skb,
+				const struct nlmsghdr *nlh,
+				struct netlink_dump_control *control)
+{
+	if (control->flags & RTNL_FLAG_DUMP_SPLIT_NLM_DONE) {
+		WARN_ON(control->data);
+		control->data = control->dump;
+		control->dump = rtnl_dumpit;
+	}
+
+	return netlink_dump_start(ssk, skb, nlh, control);
+}
+
 static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 			     struct netlink_ext_ack *extack)
 {
@@ -6548,7 +6588,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 				.module		= owner,
 				.flags		= flags,
 			};
-			err = netlink_dump_start(rtnl, skb, nlh, &c);
+			err = rtnetlink_dump_start(rtnl, skb, nlh, &c);
 			/* netlink_dump_start() will keep a reference on
 			 * module if dump is still in progress.
 			 */
@@ -6694,7 +6734,7 @@ void __init rtnetlink_init(void)
 	register_netdevice_notifier(&rtnetlink_dev_notifier);
 
 	rtnl_register(PF_UNSPEC, RTM_GETLINK, rtnl_getlink,
-		      rtnl_dump_ifinfo, 0);
+		      rtnl_dump_ifinfo, RTNL_FLAG_DUMP_SPLIT_NLM_DONE);
 	rtnl_register(PF_UNSPEC, RTM_SETLINK, rtnl_setlink, NULL, 0);
 	rtnl_register(PF_UNSPEC, RTM_NEWLINK, rtnl_newlink, NULL, 0);
 	rtnl_register(PF_UNSPEC, RTM_DELLINK, rtnl_dellink, NULL, 0);
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index f3892ee9dfb33..d09f557eaa779 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -2805,7 +2805,7 @@ void __init devinet_init(void)
 	rtnl_register(PF_INET, RTM_NEWADDR, inet_rtm_newaddr, NULL, 0);
 	rtnl_register(PF_INET, RTM_DELADDR, inet_rtm_deladdr, NULL, 0);
 	rtnl_register(PF_INET, RTM_GETADDR, NULL, inet_dump_ifaddr,
-		      RTNL_FLAG_DUMP_UNLOCKED);
+		      RTNL_FLAG_DUMP_UNLOCKED | RTNL_FLAG_DUMP_SPLIT_NLM_DONE);
 	rtnl_register(PF_INET, RTM_GETNETCONF, inet_netconf_get_devconf,
 		      inet_netconf_dump_devconf,
 		      RTNL_FLAG_DOIT_UNLOCKED | RTNL_FLAG_DUMP_UNLOCKED);
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index c484b1c0fc00a..7ad2cafb92763 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1050,11 +1050,6 @@ next:
 			e++;
 		}
 	}
-
-	/* Don't let NLM_DONE coalesce into a message, even if it could.
-	 * Some user space expects NLM_DONE in a separate recv().
-	 */
-	err = skb->len;
 out:
 
 	cb->args[1] = e;
@@ -1665,5 +1660,5 @@ void __init ip_fib_init(void)
 	rtnl_register(PF_INET, RTM_NEWROUTE, inet_rtm_newroute, NULL, 0);
 	rtnl_register(PF_INET, RTM_DELROUTE, inet_rtm_delroute, NULL, 0);
 	rtnl_register(PF_INET, RTM_GETROUTE, NULL, inet_dump_fib,
-		      RTNL_FLAG_DUMP_UNLOCKED);
+		      RTNL_FLAG_DUMP_UNLOCKED | RTNL_FLAG_DUMP_SPLIT_NLM_DONE);
 }
-- 
GitLab


From 512bd0f9f926a05c724a9fd72bc4e14213845e01 Mon Sep 17 00:00:00 2001
From: Kevin Yang <yyd@google.com>
Date: Mon, 3 Jun 2024 21:30:53 +0000
Subject: [PATCH 807/950] tcp: derive delack_max with tcp_rto_min helper

Rto_min now has multiple sources, ordered by preprecedence high to
low: ip route option rto_min, icsk->icsk_rto_min.

When derive delack_max from rto_min, we should not only use ip
route option, but should use tcp_rto_min helper to get the correct
rto_min.

Signed-off-by: Kevin Yang <yyd@google.com>
Reviewed-by: Neal Cardwell <ncardwell@google.com>
Reviewed-by: Yuchung Cheng <ycheng@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Tony Lu <tonylu@linux.alibaba.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 11 ++---------
 1 file changed, 2 insertions(+), 9 deletions(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index f97e098f18a52..090fb0c245996 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -4163,16 +4163,9 @@ EXPORT_SYMBOL(tcp_connect);
 
 u32 tcp_delack_max(const struct sock *sk)
 {
-	const struct dst_entry *dst = __sk_dst_get(sk);
-	u32 delack_max = inet_csk(sk)->icsk_delack_max;
-
-	if (dst && dst_metric_locked(dst, RTAX_RTO_MIN)) {
-		u32 rto_min = dst_metric_rtt(dst, RTAX_RTO_MIN);
-		u32 delack_from_rto_min = max_t(int, 1, rto_min - 1);
+	u32 delack_from_rto_min = max(tcp_rto_min(sk), 2) - 1;
 
-		delack_max = min_t(u32, delack_max, delack_from_rto_min);
-	}
-	return delack_max;
+	return min(inet_csk(sk)->icsk_delack_max, delack_from_rto_min);
 }
 
 /* Send out a delayed ack, the caller does the policy checking
-- 
GitLab


From f086edef71be7174a16c1ed67ac65a085cda28b1 Mon Sep 17 00:00:00 2001
From: Kevin Yang <yyd@google.com>
Date: Mon, 3 Jun 2024 21:30:54 +0000
Subject: [PATCH 808/950] tcp: add sysctl_tcp_rto_min_us

Adding a sysctl knob to allow user to specify a default
rto_min at socket init time, other than using the hard
coded 200ms default rto_min.

Note that the rto_min route option has the highest precedence
for configuring this setting, followed by the TCP_BPF_RTO_MIN
socket option, followed by the tcp_rto_min_us sysctl.

Signed-off-by: Kevin Yang <yyd@google.com>
Reviewed-by: Neal Cardwell <ncardwell@google.com>
Reviewed-by: Yuchung Cheng <ycheng@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Tony Lu <tonylu@linux.alibaba.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ip-sysctl.rst | 13 +++++++++++++
 include/net/netns/ipv4.h               |  1 +
 net/ipv4/sysctl_net_ipv4.c             |  8 ++++++++
 net/ipv4/tcp.c                         |  4 +++-
 net/ipv4/tcp_ipv4.c                    |  1 +
 5 files changed, 26 insertions(+), 1 deletion(-)

diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst
index bd50df6a5a42e..6e99eccdb837c 100644
--- a/Documentation/networking/ip-sysctl.rst
+++ b/Documentation/networking/ip-sysctl.rst
@@ -1196,6 +1196,19 @@ tcp_pingpong_thresh - INTEGER
 
 	Default: 1
 
+tcp_rto_min_us - INTEGER
+	Minimal TCP retransmission timeout (in microseconds). Note that the
+	rto_min route option has the highest precedence for configuring this
+	setting, followed by the TCP_BPF_RTO_MIN socket option, followed by
+	this tcp_rto_min_us sysctl.
+
+	The recommended practice is to use a value less or equal to 200000
+	microseconds.
+
+	Possible Values: 1 - INT_MAX
+
+	Default: 200000
+
 UDP variables
 =============
 
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index c356c458b3409..a91bb971f9015 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -170,6 +170,7 @@ struct netns_ipv4 {
 	u8 sysctl_tcp_sack;
 	u8 sysctl_tcp_window_scaling;
 	u8 sysctl_tcp_timestamps;
+	int sysctl_tcp_rto_min_us;
 	u8 sysctl_tcp_recovery;
 	u8 sysctl_tcp_thin_linear_timeouts;
 	u8 sysctl_tcp_slow_start_after_idle;
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index d7892f34a15be..bb64c0ef092db 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -1503,6 +1503,14 @@ static struct ctl_table ipv4_net_table[] = {
 		.proc_handler	= proc_dou8vec_minmax,
 		.extra1		= SYSCTL_ONE,
 	},
+	{
+		.procname	= "tcp_rto_min_us",
+		.data		= &init_net.ipv4.sysctl_tcp_rto_min_us,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ONE,
+	},
 };
 
 static __net_init int ipv4_sysctl_init_net(struct net *net)
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 5fa68e7f6ddbf..fa43aaacd92bc 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -420,6 +420,7 @@ void tcp_init_sock(struct sock *sk)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
+	int rto_min_us;
 
 	tp->out_of_order_queue = RB_ROOT;
 	sk->tcp_rtx_queue = RB_ROOT;
@@ -428,7 +429,8 @@ void tcp_init_sock(struct sock *sk)
 	INIT_LIST_HEAD(&tp->tsorted_sent_queue);
 
 	icsk->icsk_rto = TCP_TIMEOUT_INIT;
-	icsk->icsk_rto_min = TCP_RTO_MIN;
+	rto_min_us = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rto_min_us);
+	icsk->icsk_rto_min = usecs_to_jiffies(rto_min_us);
 	icsk->icsk_delack_max = TCP_DELACK_MAX;
 	tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
 	minmax_reset(&tp->rtt_min, tcp_jiffies32, ~0U);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 3ef4b274c24b8..3613e08ca7949 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -3502,6 +3502,7 @@ static int __net_init tcp_sk_init(struct net *net)
 	net->ipv4.sysctl_tcp_shrink_window = 0;
 
 	net->ipv4.sysctl_tcp_pingpong_thresh = 1;
+	net->ipv4.sysctl_tcp_rto_min_us = jiffies_to_usecs(TCP_RTO_MIN);
 
 	return 0;
 }
-- 
GitLab


From c57e558194430d10d5e5f4acd8a8655b68dade13 Mon Sep 17 00:00:00 2001
From: Frank Wunderlich <frank-w@public-files.de>
Date: Mon, 3 Jun 2024 21:25:05 +0200
Subject: [PATCH 809/950] net: ethernet: mtk_eth_soc: handle dma buffer size
 soc specific

The mainline MTK ethernet driver suffers long time from rarly but
annoying tx queue timeouts. We think that this is caused by fixed
dma sizes hardcoded for all SoCs.

We suspect this problem arises from a low level of free TX DMADs,
the TX Ring alomost full.

The transmit timeout is caused by the Tx queue not waking up. The
Tx queue stops when the free counter is less than ring->thres, and
it will wake up once the free counter is greater than ring->thres.
If the CPU is too late to wake up the Tx queues, it may cause a
transmit timeout.
Therefore, we increased the TX and RX DMADs to improve this error
situation.

Use the dma-size implementation from SDK in a per SoC manner. In
difference to SDK we have no RSS feature yet, so all RX/TX sizes
should be raised from 512 to 2048 byte except fqdma on mt7988 to
avoid the tx timeout issue.

Fixes: 656e705243fd ("net-next: mediatek: add support for MT7623 ethernet")
Suggested-by: Daniel Golle <daniel@makrotopia.org>
Signed-off-by: Frank Wunderlich <frank-w@public-files.de>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mediatek/mtk_eth_soc.c | 104 +++++++++++++-------
 drivers/net/ethernet/mediatek/mtk_eth_soc.h |   9 +-
 2 files changed, 77 insertions(+), 36 deletions(-)

diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index cae46290a7aee..c84ce54a84a00 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -1131,9 +1131,9 @@ static int mtk_init_fq_dma(struct mtk_eth *eth)
 {
 	const struct mtk_soc_data *soc = eth->soc;
 	dma_addr_t phy_ring_tail;
-	int cnt = MTK_QDMA_RING_SIZE;
+	int cnt = soc->tx.fq_dma_size;
 	dma_addr_t dma_addr;
-	int i;
+	int i, j, len;
 
 	if (MTK_HAS_CAPS(eth->soc->caps, MTK_SRAM))
 		eth->scratch_ring = eth->sram_base;
@@ -1142,40 +1142,46 @@ static int mtk_init_fq_dma(struct mtk_eth *eth)
 						       cnt * soc->tx.desc_size,
 						       &eth->phy_scratch_ring,
 						       GFP_KERNEL);
+
 	if (unlikely(!eth->scratch_ring))
 		return -ENOMEM;
 
-	eth->scratch_head = kcalloc(cnt, MTK_QDMA_PAGE_SIZE, GFP_KERNEL);
-	if (unlikely(!eth->scratch_head))
-		return -ENOMEM;
+	phy_ring_tail = eth->phy_scratch_ring + soc->tx.desc_size * (cnt - 1);
 
-	dma_addr = dma_map_single(eth->dma_dev,
-				  eth->scratch_head, cnt * MTK_QDMA_PAGE_SIZE,
-				  DMA_FROM_DEVICE);
-	if (unlikely(dma_mapping_error(eth->dma_dev, dma_addr)))
-		return -ENOMEM;
+	for (j = 0; j < DIV_ROUND_UP(soc->tx.fq_dma_size, MTK_FQ_DMA_LENGTH); j++) {
+		len = min_t(int, cnt - j * MTK_FQ_DMA_LENGTH, MTK_FQ_DMA_LENGTH);
+		eth->scratch_head[j] = kcalloc(len, MTK_QDMA_PAGE_SIZE, GFP_KERNEL);
 
-	phy_ring_tail = eth->phy_scratch_ring + soc->tx.desc_size * (cnt - 1);
+		if (unlikely(!eth->scratch_head[j]))
+			return -ENOMEM;
 
-	for (i = 0; i < cnt; i++) {
-		dma_addr_t addr = dma_addr + i * MTK_QDMA_PAGE_SIZE;
-		struct mtk_tx_dma_v2 *txd;
+		dma_addr = dma_map_single(eth->dma_dev,
+					  eth->scratch_head[j], len * MTK_QDMA_PAGE_SIZE,
+					  DMA_FROM_DEVICE);
 
-		txd = eth->scratch_ring + i * soc->tx.desc_size;
-		txd->txd1 = addr;
-		if (i < cnt - 1)
-			txd->txd2 = eth->phy_scratch_ring +
-				    (i + 1) * soc->tx.desc_size;
+		if (unlikely(dma_mapping_error(eth->dma_dev, dma_addr)))
+			return -ENOMEM;
 
-		txd->txd3 = TX_DMA_PLEN0(MTK_QDMA_PAGE_SIZE);
-		if (MTK_HAS_CAPS(soc->caps, MTK_36BIT_DMA))
-			txd->txd3 |= TX_DMA_PREP_ADDR64(addr);
-		txd->txd4 = 0;
-		if (mtk_is_netsys_v2_or_greater(eth)) {
-			txd->txd5 = 0;
-			txd->txd6 = 0;
-			txd->txd7 = 0;
-			txd->txd8 = 0;
+		for (i = 0; i < cnt; i++) {
+			struct mtk_tx_dma_v2 *txd;
+
+			txd = eth->scratch_ring + (j * MTK_FQ_DMA_LENGTH + i) * soc->tx.desc_size;
+			txd->txd1 = dma_addr + i * MTK_QDMA_PAGE_SIZE;
+			if (j * MTK_FQ_DMA_LENGTH + i < cnt)
+				txd->txd2 = eth->phy_scratch_ring +
+					    (j * MTK_FQ_DMA_LENGTH + i + 1) * soc->tx.desc_size;
+
+			txd->txd3 = TX_DMA_PLEN0(MTK_QDMA_PAGE_SIZE);
+			if (MTK_HAS_CAPS(soc->caps, MTK_36BIT_DMA))
+				txd->txd3 |= TX_DMA_PREP_ADDR64(dma_addr + i * MTK_QDMA_PAGE_SIZE);
+
+			txd->txd4 = 0;
+			if (mtk_is_netsys_v2_or_greater(eth)) {
+				txd->txd5 = 0;
+				txd->txd6 = 0;
+				txd->txd7 = 0;
+				txd->txd8 = 0;
+			}
 		}
 	}
 
@@ -2457,7 +2463,7 @@ static int mtk_tx_alloc(struct mtk_eth *eth)
 	if (MTK_HAS_CAPS(soc->caps, MTK_QDMA))
 		ring_size = MTK_QDMA_RING_SIZE;
 	else
-		ring_size = MTK_DMA_SIZE;
+		ring_size = soc->tx.dma_size;
 
 	ring->buf = kcalloc(ring_size, sizeof(*ring->buf),
 			       GFP_KERNEL);
@@ -2465,8 +2471,8 @@ static int mtk_tx_alloc(struct mtk_eth *eth)
 		goto no_tx_mem;
 
 	if (MTK_HAS_CAPS(soc->caps, MTK_SRAM)) {
-		ring->dma = eth->sram_base + ring_size * sz;
-		ring->phys = eth->phy_scratch_ring + ring_size * (dma_addr_t)sz;
+		ring->dma = eth->sram_base + soc->tx.fq_dma_size * sz;
+		ring->phys = eth->phy_scratch_ring + soc->tx.fq_dma_size * (dma_addr_t)sz;
 	} else {
 		ring->dma = dma_alloc_coherent(eth->dma_dev, ring_size * sz,
 					       &ring->phys, GFP_KERNEL);
@@ -2588,6 +2594,7 @@ static void mtk_tx_clean(struct mtk_eth *eth)
 static int mtk_rx_alloc(struct mtk_eth *eth, int ring_no, int rx_flag)
 {
 	const struct mtk_reg_map *reg_map = eth->soc->reg_map;
+	const struct mtk_soc_data *soc = eth->soc;
 	struct mtk_rx_ring *ring;
 	int rx_data_len, rx_dma_size, tx_ring_size;
 	int i;
@@ -2595,7 +2602,7 @@ static int mtk_rx_alloc(struct mtk_eth *eth, int ring_no, int rx_flag)
 	if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA))
 		tx_ring_size = MTK_QDMA_RING_SIZE;
 	else
-		tx_ring_size = MTK_DMA_SIZE;
+		tx_ring_size = soc->tx.dma_size;
 
 	if (rx_flag == MTK_RX_FLAGS_QDMA) {
 		if (ring_no)
@@ -2610,7 +2617,7 @@ static int mtk_rx_alloc(struct mtk_eth *eth, int ring_no, int rx_flag)
 		rx_dma_size = MTK_HW_LRO_DMA_SIZE;
 	} else {
 		rx_data_len = ETH_DATA_LEN;
-		rx_dma_size = MTK_DMA_SIZE;
+		rx_dma_size = soc->rx.dma_size;
 	}
 
 	ring->frag_size = mtk_max_frag_size(rx_data_len);
@@ -3139,7 +3146,10 @@ static void mtk_dma_free(struct mtk_eth *eth)
 			mtk_rx_clean(eth, &eth->rx_ring[i], false);
 	}
 
-	kfree(eth->scratch_head);
+	for (i = 0; i < DIV_ROUND_UP(soc->tx.fq_dma_size, MTK_FQ_DMA_LENGTH); i++) {
+		kfree(eth->scratch_head[i]);
+		eth->scratch_head[i] = NULL;
+	}
 }
 
 static bool mtk_hw_reset_check(struct mtk_eth *eth)
@@ -5052,11 +5062,14 @@ static const struct mtk_soc_data mt2701_data = {
 		.desc_size = sizeof(struct mtk_tx_dma),
 		.dma_max_len = MTK_TX_DMA_BUF_LEN,
 		.dma_len_offset = 16,
+		.dma_size = MTK_DMA_SIZE(2K),
+		.fq_dma_size = MTK_DMA_SIZE(2K),
 	},
 	.rx = {
 		.desc_size = sizeof(struct mtk_rx_dma),
 		.irq_done_mask = MTK_RX_DONE_INT,
 		.dma_l4_valid = RX_DMA_L4_VALID,
+		.dma_size = MTK_DMA_SIZE(2K),
 		.dma_max_len = MTK_TX_DMA_BUF_LEN,
 		.dma_len_offset = 16,
 	},
@@ -5076,11 +5089,14 @@ static const struct mtk_soc_data mt7621_data = {
 		.desc_size = sizeof(struct mtk_tx_dma),
 		.dma_max_len = MTK_TX_DMA_BUF_LEN,
 		.dma_len_offset = 16,
+		.dma_size = MTK_DMA_SIZE(2K),
+		.fq_dma_size = MTK_DMA_SIZE(2K),
 	},
 	.rx = {
 		.desc_size = sizeof(struct mtk_rx_dma),
 		.irq_done_mask = MTK_RX_DONE_INT,
 		.dma_l4_valid = RX_DMA_L4_VALID,
+		.dma_size = MTK_DMA_SIZE(2K),
 		.dma_max_len = MTK_TX_DMA_BUF_LEN,
 		.dma_len_offset = 16,
 	},
@@ -5102,11 +5118,14 @@ static const struct mtk_soc_data mt7622_data = {
 		.desc_size = sizeof(struct mtk_tx_dma),
 		.dma_max_len = MTK_TX_DMA_BUF_LEN,
 		.dma_len_offset = 16,
+		.dma_size = MTK_DMA_SIZE(2K),
+		.fq_dma_size = MTK_DMA_SIZE(2K),
 	},
 	.rx = {
 		.desc_size = sizeof(struct mtk_rx_dma),
 		.irq_done_mask = MTK_RX_DONE_INT,
 		.dma_l4_valid = RX_DMA_L4_VALID,
+		.dma_size = MTK_DMA_SIZE(2K),
 		.dma_max_len = MTK_TX_DMA_BUF_LEN,
 		.dma_len_offset = 16,
 	},
@@ -5127,11 +5146,14 @@ static const struct mtk_soc_data mt7623_data = {
 		.desc_size = sizeof(struct mtk_tx_dma),
 		.dma_max_len = MTK_TX_DMA_BUF_LEN,
 		.dma_len_offset = 16,
+		.dma_size = MTK_DMA_SIZE(2K),
+		.fq_dma_size = MTK_DMA_SIZE(2K),
 	},
 	.rx = {
 		.desc_size = sizeof(struct mtk_rx_dma),
 		.irq_done_mask = MTK_RX_DONE_INT,
 		.dma_l4_valid = RX_DMA_L4_VALID,
+		.dma_size = MTK_DMA_SIZE(2K),
 		.dma_max_len = MTK_TX_DMA_BUF_LEN,
 		.dma_len_offset = 16,
 	},
@@ -5150,11 +5172,14 @@ static const struct mtk_soc_data mt7629_data = {
 		.desc_size = sizeof(struct mtk_tx_dma),
 		.dma_max_len = MTK_TX_DMA_BUF_LEN,
 		.dma_len_offset = 16,
+		.dma_size = MTK_DMA_SIZE(2K),
+		.fq_dma_size = MTK_DMA_SIZE(2K),
 	},
 	.rx = {
 		.desc_size = sizeof(struct mtk_rx_dma),
 		.irq_done_mask = MTK_RX_DONE_INT,
 		.dma_l4_valid = RX_DMA_L4_VALID,
+		.dma_size = MTK_DMA_SIZE(2K),
 		.dma_max_len = MTK_TX_DMA_BUF_LEN,
 		.dma_len_offset = 16,
 	},
@@ -5176,6 +5201,8 @@ static const struct mtk_soc_data mt7981_data = {
 		.desc_size = sizeof(struct mtk_tx_dma_v2),
 		.dma_max_len = MTK_TX_DMA_BUF_LEN_V2,
 		.dma_len_offset = 8,
+		.dma_size = MTK_DMA_SIZE(2K),
+		.fq_dma_size = MTK_DMA_SIZE(2K),
 	},
 	.rx = {
 		.desc_size = sizeof(struct mtk_rx_dma),
@@ -5183,6 +5210,7 @@ static const struct mtk_soc_data mt7981_data = {
 		.dma_l4_valid = RX_DMA_L4_VALID_V2,
 		.dma_max_len = MTK_TX_DMA_BUF_LEN,
 		.dma_len_offset = 16,
+		.dma_size = MTK_DMA_SIZE(2K),
 	},
 };
 
@@ -5202,6 +5230,8 @@ static const struct mtk_soc_data mt7986_data = {
 		.desc_size = sizeof(struct mtk_tx_dma_v2),
 		.dma_max_len = MTK_TX_DMA_BUF_LEN_V2,
 		.dma_len_offset = 8,
+		.dma_size = MTK_DMA_SIZE(2K),
+		.fq_dma_size = MTK_DMA_SIZE(2K),
 	},
 	.rx = {
 		.desc_size = sizeof(struct mtk_rx_dma),
@@ -5209,6 +5239,7 @@ static const struct mtk_soc_data mt7986_data = {
 		.dma_l4_valid = RX_DMA_L4_VALID_V2,
 		.dma_max_len = MTK_TX_DMA_BUF_LEN,
 		.dma_len_offset = 16,
+		.dma_size = MTK_DMA_SIZE(2K),
 	},
 };
 
@@ -5228,6 +5259,8 @@ static const struct mtk_soc_data mt7988_data = {
 		.desc_size = sizeof(struct mtk_tx_dma_v2),
 		.dma_max_len = MTK_TX_DMA_BUF_LEN_V2,
 		.dma_len_offset = 8,
+		.dma_size = MTK_DMA_SIZE(2K),
+		.fq_dma_size = MTK_DMA_SIZE(4K),
 	},
 	.rx = {
 		.desc_size = sizeof(struct mtk_rx_dma_v2),
@@ -5235,6 +5268,7 @@ static const struct mtk_soc_data mt7988_data = {
 		.dma_l4_valid = RX_DMA_L4_VALID_V2,
 		.dma_max_len = MTK_TX_DMA_BUF_LEN_V2,
 		.dma_len_offset = 8,
+		.dma_size = MTK_DMA_SIZE(2K),
 	},
 };
 
@@ -5249,6 +5283,7 @@ static const struct mtk_soc_data rt5350_data = {
 		.desc_size = sizeof(struct mtk_tx_dma),
 		.dma_max_len = MTK_TX_DMA_BUF_LEN,
 		.dma_len_offset = 16,
+		.dma_size = MTK_DMA_SIZE(2K),
 	},
 	.rx = {
 		.desc_size = sizeof(struct mtk_rx_dma),
@@ -5256,6 +5291,7 @@ static const struct mtk_soc_data rt5350_data = {
 		.dma_l4_valid = RX_DMA_L4_VALID_PDMA,
 		.dma_max_len = MTK_TX_DMA_BUF_LEN,
 		.dma_len_offset = 16,
+		.dma_size = MTK_DMA_SIZE(2K),
 	},
 };
 
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
index 4eab30b440706..f5174f6cb1bbe 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
@@ -32,7 +32,9 @@
 #define MTK_TX_DMA_BUF_LEN	0x3fff
 #define MTK_TX_DMA_BUF_LEN_V2	0xffff
 #define MTK_QDMA_RING_SIZE	2048
-#define MTK_DMA_SIZE		512
+#define MTK_DMA_SIZE(x)		(SZ_##x)
+#define MTK_FQ_DMA_HEAD		32
+#define MTK_FQ_DMA_LENGTH	2048
 #define MTK_RX_ETH_HLEN		(ETH_HLEN + ETH_FCS_LEN)
 #define MTK_RX_HLEN		(NET_SKB_PAD + MTK_RX_ETH_HLEN + NET_IP_ALIGN)
 #define MTK_DMA_DUMMY_DESC	0xffffffff
@@ -1176,6 +1178,8 @@ struct mtk_soc_data {
 		u32	desc_size;
 		u32	dma_max_len;
 		u32	dma_len_offset;
+		u32	dma_size;
+		u32	fq_dma_size;
 	} tx;
 	struct {
 		u32	desc_size;
@@ -1183,6 +1187,7 @@ struct mtk_soc_data {
 		u32	dma_l4_valid;
 		u32	dma_max_len;
 		u32	dma_len_offset;
+		u32	dma_size;
 	} rx;
 };
 
@@ -1264,7 +1269,7 @@ struct mtk_eth {
 	struct napi_struct		rx_napi;
 	void				*scratch_ring;
 	dma_addr_t			phy_scratch_ring;
-	void				*scratch_head;
+	void				*scratch_head[MTK_FQ_DMA_HEAD];
 	struct clk			*clks[MTK_CLK_MAX];
 
 	struct mii_bus			*mii_bus;
-- 
GitLab


From 33afbfcc105a572159750f2ebee834a8a70fdd96 Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@nvidia.com>
Date: Tue, 4 Jun 2024 00:04:42 +0300
Subject: [PATCH 810/950] net/mlx5: Stop waiting for PCI if pci channel is
 offline

In case pci channel becomes offline the driver should not wait for PCI
reads during health dump and recovery flow. The driver has timeout for
each of these loops trying to read PCI, so it would fail anyway.
However, in case of recovery waiting till timeout may cause the pci
error_detected() callback fail to meet pci_dpc_recovered() wait timeout.

Fixes: b3bd076f7501 ("net/mlx5: Report devlink health on FW fatal issues")
Signed-off-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Shay Drori <shayd@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/fw.c          | 4 ++++
 drivers/net/ethernet/mellanox/mlx5/core/health.c      | 8 ++++++++
 drivers/net/ethernet/mellanox/mlx5/core/lib/pci_vsc.c | 4 ++++
 3 files changed, 16 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
index 2d95a9b7b44e1..b61b7d9661141 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
@@ -373,6 +373,10 @@ int mlx5_cmd_fast_teardown_hca(struct mlx5_core_dev *dev)
 	do {
 		if (mlx5_get_nic_state(dev) == MLX5_INITIAL_SEG_NIC_INTERFACE_DISABLED)
 			break;
+		if (pci_channel_offline(dev->pdev)) {
+			mlx5_core_err(dev, "PCI channel offline, stop waiting for NIC IFC\n");
+			return -EACCES;
+		}
 
 		cond_resched();
 	} while (!time_after(jiffies, end));
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index ad38e31822df1..a6329ca2d9bff 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -248,6 +248,10 @@ recover_from_sw_reset:
 	do {
 		if (mlx5_get_nic_state(dev) == MLX5_INITIAL_SEG_NIC_INTERFACE_DISABLED)
 			break;
+		if (pci_channel_offline(dev->pdev)) {
+			mlx5_core_err(dev, "PCI channel offline, stop waiting for NIC IFC\n");
+			goto unlock;
+		}
 
 		msleep(20);
 	} while (!time_after(jiffies, end));
@@ -317,6 +321,10 @@ int mlx5_health_wait_pci_up(struct mlx5_core_dev *dev)
 			mlx5_core_warn(dev, "device is being removed, stop waiting for PCI\n");
 			return -ENODEV;
 		}
+		if (pci_channel_offline(dev->pdev)) {
+			mlx5_core_err(dev, "PCI channel offline, stop waiting for PCI\n");
+			return -EACCES;
+		}
 		msleep(100);
 	}
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/pci_vsc.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/pci_vsc.c
index 6b774e0c27665..d0b595ba61101 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/pci_vsc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/pci_vsc.c
@@ -74,6 +74,10 @@ int mlx5_vsc_gw_lock(struct mlx5_core_dev *dev)
 			ret = -EBUSY;
 			goto pci_unlock;
 		}
+		if (pci_channel_offline(dev->pdev)) {
+			ret = -EACCES;
+			goto pci_unlock;
+		}
 
 		/* Check if semaphore is already locked */
 		ret = vsc_read(dev, VSC_SEMAPHORE_OFFSET, &lock_val);
-- 
GitLab


From c8b3f38d2dae0397944814d691a419c451f9906f Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@nvidia.com>
Date: Tue, 4 Jun 2024 00:04:43 +0300
Subject: [PATCH 811/950] net/mlx5: Always stop health timer during driver
 removal

Currently, if teardown_hca fails to execute during driver removal, mlx5
does not stop the health timer. Afterwards, mlx5 continue with driver
teardown. This may lead to a UAF bug, which results in page fault
Oops[1], since the health timer invokes after resources were freed.

Hence, stop the health monitor even if teardown_hca fails.

[1]
mlx5_core 0000:18:00.0: E-Switch: Unload vfs: mode(LEGACY), nvfs(0), necvfs(0), active vports(0)
mlx5_core 0000:18:00.0: E-Switch: Disable: mode(LEGACY), nvfs(0), necvfs(0), active vports(0)
mlx5_core 0000:18:00.0: E-Switch: Disable: mode(LEGACY), nvfs(0), necvfs(0), active vports(0)
mlx5_core 0000:18:00.0: E-Switch: cleanup
mlx5_core 0000:18:00.0: wait_func:1155:(pid 1967079): TEARDOWN_HCA(0x103) timeout. Will cause a leak of a command resource
mlx5_core 0000:18:00.0: mlx5_function_close:1288:(pid 1967079): tear_down_hca failed, skip cleanup
BUG: unable to handle page fault for address: ffffa26487064230
PGD 100c00067 P4D 100c00067 PUD 100e5a067 PMD 105ed7067 PTE 0
Oops: 0000 [#1] PREEMPT SMP PTI
CPU: 0 PID: 0 Comm: swapper/0 Tainted: G           OE     -------  ---  6.7.0-68.fc38.x86_64 #1
Hardware name: Intel Corporation S2600WFT/S2600WFT, BIOS SE5C620.86B.02.01.0013.121520200651 12/15/2020
RIP: 0010:ioread32be+0x34/0x60
RSP: 0018:ffffa26480003e58 EFLAGS: 00010292
RAX: ffffa26487064200 RBX: ffff9042d08161a0 RCX: ffff904c108222c0
RDX: 000000010bbf1b80 RSI: ffffffffc055ddb0 RDI: ffffa26487064230
RBP: ffff9042d08161a0 R08: 0000000000000022 R09: ffff904c108222e8
R10: 0000000000000004 R11: 0000000000000441 R12: ffffffffc055ddb0
R13: ffffa26487064200 R14: ffffa26480003f00 R15: ffff904c108222c0
FS:  0000000000000000(0000) GS:ffff904c10800000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: ffffa26487064230 CR3: 00000002c4420006 CR4: 00000000007706f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
PKRU: 55555554
Call Trace:
 <IRQ>
 ? __die+0x23/0x70
 ? page_fault_oops+0x171/0x4e0
 ? exc_page_fault+0x175/0x180
 ? asm_exc_page_fault+0x26/0x30
 ? __pfx_poll_health+0x10/0x10 [mlx5_core]
 ? __pfx_poll_health+0x10/0x10 [mlx5_core]
 ? ioread32be+0x34/0x60
 mlx5_health_check_fatal_sensors+0x20/0x100 [mlx5_core]
 ? __pfx_poll_health+0x10/0x10 [mlx5_core]
 poll_health+0x42/0x230 [mlx5_core]
 ? __next_timer_interrupt+0xbc/0x110
 ? __pfx_poll_health+0x10/0x10 [mlx5_core]
 call_timer_fn+0x21/0x130
 ? __pfx_poll_health+0x10/0x10 [mlx5_core]
 __run_timers+0x222/0x2c0
 run_timer_softirq+0x1d/0x40
 __do_softirq+0xc9/0x2c8
 __irq_exit_rcu+0xa6/0xc0
 sysvec_apic_timer_interrupt+0x72/0x90
 </IRQ>
 <TASK>
 asm_sysvec_apic_timer_interrupt+0x1a/0x20
RIP: 0010:cpuidle_enter_state+0xcc/0x440
 ? cpuidle_enter_state+0xbd/0x440
 cpuidle_enter+0x2d/0x40
 do_idle+0x20d/0x270
 cpu_startup_entry+0x2a/0x30
 rest_init+0xd0/0xd0
 arch_call_rest_init+0xe/0x30
 start_kernel+0x709/0xa90
 x86_64_start_reservations+0x18/0x30
 x86_64_start_kernel+0x96/0xa0
 secondary_startup_64_no_verify+0x18f/0x19b
---[ end trace 0000000000000000 ]---

Fixes: 9b98d395b85d ("net/mlx5: Start health poll at earlier stage of driver load")
Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 6574c145dc1e2..459a836a5d9c1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1298,6 +1298,9 @@ static int mlx5_function_teardown(struct mlx5_core_dev *dev, bool boot)
 
 	if (!err)
 		mlx5_function_disable(dev, boot);
+	else
+		mlx5_stop_health_poll(dev, boot);
+
 	return err;
 }
 
-- 
GitLab


From 9a64e1bfd8a10c015c41fe0d289e89862486c50d Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sun, 2 Jun 2024 22:52:24 -0400
Subject: [PATCH 812/950] bcachefs: Fix GFP_KERNEL allocation in break_cycle()

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/btree_locking.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/bcachefs/btree_locking.c b/fs/bcachefs/btree_locking.c
index c3e9b0cc7bbdc..d66fff22109ae 100644
--- a/fs/bcachefs/btree_locking.c
+++ b/fs/bcachefs/btree_locking.c
@@ -215,6 +215,7 @@ static noinline int break_cycle(struct lock_graph *g, struct printbuf *cycle)
 
 	if (unlikely(!best)) {
 		struct printbuf buf = PRINTBUF;
+		buf.atomic++;
 
 		prt_printf(&buf, bch2_fmt(g->g->trans->c, "cycle of nofail locks"));
 
-- 
GitLab


From fdccb24352e589bb59c9ba90f23c4e0994b90518 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sun, 2 Jun 2024 22:25:18 -0400
Subject: [PATCH 813/950] bcachefs: Rereplicate now moves data off of
 durability=0 devices

This fixes an issue where setting a device to durability=0 after it's
been used makes it impossible to remove.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/move.c | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/fs/bcachefs/move.c b/fs/bcachefs/move.c
index 8171f947fac8f..2706d82423450 100644
--- a/fs/bcachefs/move.c
+++ b/fs/bcachefs/move.c
@@ -920,7 +920,20 @@ static bool rereplicate_pred(struct bch_fs *c, void *arg,
 		? c->opts.metadata_replicas
 		: io_opts->data_replicas;
 
-	if (!nr_good || nr_good >= replicas)
+	rcu_read_lock();
+	struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k);
+	unsigned i = 0;
+	bkey_for_each_ptr(ptrs, ptr) {
+		struct bch_dev *ca = bch2_dev_rcu(c, ptr->dev);
+		if (!ptr->cached &&
+		    (!ca || !ca->mi.durability))
+			data_opts->kill_ptrs |= BIT(i);
+		i++;
+	}
+	rcu_read_unlock();
+
+	if (!data_opts->kill_ptrs &&
+	    (!nr_good || nr_good >= replicas))
 		return false;
 
 	data_opts->target		= 0;
-- 
GitLab


From 319fef29e96524966bb8593117ce0c5867846eea Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 3 Jun 2024 18:00:48 -0400
Subject: [PATCH 814/950] bcachefs: Fix trans->locked assert

in bch2_move_data_btree, we might start with the trans unlocked from a
previous loop iteration - we need a trans_begin() before iter_init().

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/move.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/bcachefs/move.c b/fs/bcachefs/move.c
index 2706d82423450..6e477fadaa2a5 100644
--- a/fs/bcachefs/move.c
+++ b/fs/bcachefs/move.c
@@ -547,6 +547,7 @@ static int bch2_move_data_btree(struct moving_context *ctxt,
 		ctxt->stats->pos	= BBPOS(btree_id, start);
 	}
 
+	bch2_trans_begin(trans);
 	bch2_trans_iter_init(trans, &iter, btree_id, start,
 			     BTREE_ITER_prefetch|
 			     BTREE_ITER_all_snapshots);
-- 
GitLab


From 68153bb2fffbe59804370e514482f95c4b2053ff Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Tue, 4 Jun 2024 17:16:25 -0700
Subject: [PATCH 815/950] libbpf: Add BTF field iterator

Implement iterator-based type ID and string offset BTF field iterator.
This is used extensively in BTF-handling code and BPF linker code for
various sanity checks, rewriting IDs/offsets, etc. Currently this is
implemented as visitor pattern calling custom callbacks, which makes the
logic (especially in simple cases) unnecessarily obscure and harder to
follow.

Having equivalent functionality using iterator pattern makes for simpler
to understand and maintain code. As we add more code for BTF processing
logic in libbpf, it's best to switch to iterator pattern before adding
more callback-based code.

The idea for iterator-based implementation is to record offsets of
necessary fields within fixed btf_type parts (which should be iterated
just once), and, for kinds that have multiple members (based on vlen
field), record where in each member necessary fields are located.

Generic iteration code then just keeps track of last offset that was
returned and handles N members correctly. Return type is just u32
pointer, where NULL is returned when all relevant fields were already
iterated.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: Alan Maguire <alan.maguire@oracle.com>
Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/bpf/20240605001629.4061937-2-andrii@kernel.org
---
 tools/lib/bpf/btf.c             | 162 ++++++++++++++++++++++++++++++++
 tools/lib/bpf/libbpf_internal.h |  24 +++++
 2 files changed, 186 insertions(+)

diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 2d0840ef599af..50ff8b6eaf366 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -5133,6 +5133,168 @@ int btf_type_visit_str_offs(struct btf_type *t, str_off_visit_fn visit, void *ct
 	return 0;
 }
 
+int btf_field_iter_init(struct btf_field_iter *it, struct btf_type *t, enum btf_field_iter_kind iter_kind)
+{
+	it->p = NULL;
+	it->m_idx = -1;
+	it->off_idx = 0;
+	it->vlen = 0;
+
+	switch (iter_kind) {
+	case BTF_FIELD_ITER_IDS:
+		switch (btf_kind(t)) {
+		case BTF_KIND_UNKN:
+		case BTF_KIND_INT:
+		case BTF_KIND_FLOAT:
+		case BTF_KIND_ENUM:
+		case BTF_KIND_ENUM64:
+			it->desc = (struct btf_field_desc) {};
+			break;
+		case BTF_KIND_FWD:
+		case BTF_KIND_CONST:
+		case BTF_KIND_VOLATILE:
+		case BTF_KIND_RESTRICT:
+		case BTF_KIND_PTR:
+		case BTF_KIND_TYPEDEF:
+		case BTF_KIND_FUNC:
+		case BTF_KIND_VAR:
+		case BTF_KIND_DECL_TAG:
+		case BTF_KIND_TYPE_TAG:
+			it->desc = (struct btf_field_desc) { 1, {offsetof(struct btf_type, type)} };
+			break;
+		case BTF_KIND_ARRAY:
+			it->desc = (struct btf_field_desc) {
+				2, {sizeof(struct btf_type) + offsetof(struct btf_array, type),
+				    sizeof(struct btf_type) + offsetof(struct btf_array, index_type)}
+			};
+			break;
+		case BTF_KIND_STRUCT:
+		case BTF_KIND_UNION:
+			it->desc = (struct btf_field_desc) {
+				0, {},
+				sizeof(struct btf_member),
+				1, {offsetof(struct btf_member, type)}
+			};
+			break;
+		case BTF_KIND_FUNC_PROTO:
+			it->desc = (struct btf_field_desc) {
+				1, {offsetof(struct btf_type, type)},
+				sizeof(struct btf_param),
+				1, {offsetof(struct btf_param, type)}
+			};
+			break;
+		case BTF_KIND_DATASEC:
+			it->desc = (struct btf_field_desc) {
+				0, {},
+				sizeof(struct btf_var_secinfo),
+				1, {offsetof(struct btf_var_secinfo, type)}
+			};
+			break;
+		default:
+			return -EINVAL;
+		}
+		break;
+	case BTF_FIELD_ITER_STRS:
+		switch (btf_kind(t)) {
+		case BTF_KIND_UNKN:
+			it->desc = (struct btf_field_desc) {};
+			break;
+		case BTF_KIND_INT:
+		case BTF_KIND_FLOAT:
+		case BTF_KIND_FWD:
+		case BTF_KIND_ARRAY:
+		case BTF_KIND_CONST:
+		case BTF_KIND_VOLATILE:
+		case BTF_KIND_RESTRICT:
+		case BTF_KIND_PTR:
+		case BTF_KIND_TYPEDEF:
+		case BTF_KIND_FUNC:
+		case BTF_KIND_VAR:
+		case BTF_KIND_DECL_TAG:
+		case BTF_KIND_TYPE_TAG:
+		case BTF_KIND_DATASEC:
+			it->desc = (struct btf_field_desc) {
+				1, {offsetof(struct btf_type, name_off)}
+			};
+			break;
+		case BTF_KIND_ENUM:
+			it->desc = (struct btf_field_desc) {
+				1, {offsetof(struct btf_type, name_off)},
+				sizeof(struct btf_enum),
+				1, {offsetof(struct btf_enum, name_off)}
+			};
+			break;
+		case BTF_KIND_ENUM64:
+			it->desc = (struct btf_field_desc) {
+				1, {offsetof(struct btf_type, name_off)},
+				sizeof(struct btf_enum64),
+				1, {offsetof(struct btf_enum64, name_off)}
+			};
+			break;
+		case BTF_KIND_STRUCT:
+		case BTF_KIND_UNION:
+			it->desc = (struct btf_field_desc) {
+				1, {offsetof(struct btf_type, name_off)},
+				sizeof(struct btf_member),
+				1, {offsetof(struct btf_member, name_off)}
+			};
+			break;
+		case BTF_KIND_FUNC_PROTO:
+			it->desc = (struct btf_field_desc) {
+				1, {offsetof(struct btf_type, name_off)},
+				sizeof(struct btf_param),
+				1, {offsetof(struct btf_param, name_off)}
+			};
+			break;
+		default:
+			return -EINVAL;
+		}
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (it->desc.m_sz)
+		it->vlen = btf_vlen(t);
+
+	it->p = t;
+	return 0;
+}
+
+__u32 *btf_field_iter_next(struct btf_field_iter *it)
+{
+	if (!it->p)
+		return NULL;
+
+	if (it->m_idx < 0) {
+		if (it->off_idx < it->desc.t_cnt)
+			return it->p + it->desc.t_offs[it->off_idx++];
+		/* move to per-member iteration */
+		it->m_idx = 0;
+		it->p += sizeof(struct btf_type);
+		it->off_idx = 0;
+	}
+
+	/* if type doesn't have members, stop */
+	if (it->desc.m_sz == 0) {
+		it->p = NULL;
+		return NULL;
+	}
+
+	if (it->off_idx >= it->desc.m_cnt) {
+		/* exhausted this member's fields, go to the next member */
+		it->m_idx++;
+		it->p += it->desc.m_sz;
+		it->off_idx = 0;
+	}
+
+	if (it->m_idx < it->vlen)
+		return it->p + it->desc.m_offs[it->off_idx++];
+
+	it->p = NULL;
+	return NULL;
+}
+
 int btf_ext_visit_type_ids(struct btf_ext *btf_ext, type_id_visit_fn visit, void *ctx)
 {
 	const struct btf_ext_info *seg;
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index 7e7e686008c62..80f3d346db334 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -508,6 +508,30 @@ struct bpf_line_info_min {
 	__u32	line_col;
 };
 
+enum btf_field_iter_kind {
+	BTF_FIELD_ITER_IDS,
+	BTF_FIELD_ITER_STRS,
+};
+
+struct btf_field_desc {
+	/* once-per-type offsets */
+	int t_cnt, t_offs[2];
+	/* member struct size, or zero, if no members */
+	int m_sz;
+	/* repeated per-member offsets */
+	int m_cnt, m_offs[1];
+};
+
+struct btf_field_iter {
+	struct btf_field_desc desc;
+	void *p;
+	int m_idx;
+	int off_idx;
+	int vlen;
+};
+
+int btf_field_iter_init(struct btf_field_iter *it, struct btf_type *t, enum btf_field_iter_kind iter_kind);
+__u32 *btf_field_iter_next(struct btf_field_iter *it);
 
 typedef int (*type_id_visit_fn)(__u32 *type_id, void *ctx);
 typedef int (*str_off_visit_fn)(__u32 *str_off, void *ctx);
-- 
GitLab


From 2bce2c1cb2f0acbf619737a10575f99df0c43984 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Tue, 4 Jun 2024 17:16:26 -0700
Subject: [PATCH 816/950] libbpf: Make use of BTF field iterator in BPF linker
 code

Switch all BPF linker code dealing with iterating BTF type ID and string
offset fields to new btf_field_iter facilities.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: Alan Maguire <alan.maguire@oracle.com>
Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/bpf/20240605001629.4061937-3-andrii@kernel.org
---
 tools/lib/bpf/btf.c             |  4 +--
 tools/lib/bpf/libbpf_internal.h |  4 +--
 tools/lib/bpf/linker.c          | 58 ++++++++++++++++++++-------------
 3 files changed, 40 insertions(+), 26 deletions(-)

diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 50ff8b6eaf366..d72260ac26a52 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -5267,7 +5267,7 @@ __u32 *btf_field_iter_next(struct btf_field_iter *it)
 		return NULL;
 
 	if (it->m_idx < 0) {
-		if (it->off_idx < it->desc.t_cnt)
+		if (it->off_idx < it->desc.t_off_cnt)
 			return it->p + it->desc.t_offs[it->off_idx++];
 		/* move to per-member iteration */
 		it->m_idx = 0;
@@ -5281,7 +5281,7 @@ __u32 *btf_field_iter_next(struct btf_field_iter *it)
 		return NULL;
 	}
 
-	if (it->off_idx >= it->desc.m_cnt) {
+	if (it->off_idx >= it->desc.m_off_cnt) {
 		/* exhausted this member's fields, go to the next member */
 		it->m_idx++;
 		it->p += it->desc.m_sz;
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index 80f3d346db334..96c0b0993f8bc 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -515,11 +515,11 @@ enum btf_field_iter_kind {
 
 struct btf_field_desc {
 	/* once-per-type offsets */
-	int t_cnt, t_offs[2];
+	int t_off_cnt, t_offs[2];
 	/* member struct size, or zero, if no members */
 	int m_sz;
 	/* repeated per-member offsets */
-	int m_cnt, m_offs[1];
+	int m_off_cnt, m_offs[1];
 };
 
 struct btf_field_iter {
diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c
index 0d4be829551b5..fa11a671da3e0 100644
--- a/tools/lib/bpf/linker.c
+++ b/tools/lib/bpf/linker.c
@@ -957,19 +957,33 @@ static int check_btf_str_off(__u32 *str_off, void *ctx)
 static int linker_sanity_check_btf(struct src_obj *obj)
 {
 	struct btf_type *t;
-	int i, n, err = 0;
+	int i, n, err;
 
 	if (!obj->btf)
 		return 0;
 
 	n = btf__type_cnt(obj->btf);
 	for (i = 1; i < n; i++) {
+		struct btf_field_iter it;
+		__u32 *type_id, *str_off;
+
 		t = btf_type_by_id(obj->btf, i);
 
-		err = err ?: btf_type_visit_type_ids(t, check_btf_type_id, obj->btf);
-		err = err ?: btf_type_visit_str_offs(t, check_btf_str_off, obj->btf);
+		err = btf_field_iter_init(&it, t, BTF_FIELD_ITER_IDS);
 		if (err)
 			return err;
+		while ((type_id = btf_field_iter_next(&it))) {
+			if (*type_id >= n)
+				return -EINVAL;
+		}
+
+		err = btf_field_iter_init(&it, t, BTF_FIELD_ITER_STRS);
+		if (err)
+			return err;
+		while ((str_off = btf_field_iter_next(&it))) {
+			if (!btf__str_by_offset(obj->btf, *str_off))
+				return -EINVAL;
+		}
 	}
 
 	return 0;
@@ -2234,26 +2248,10 @@ static int linker_fixup_btf(struct src_obj *obj)
 	return 0;
 }
 
-static int remap_type_id(__u32 *type_id, void *ctx)
-{
-	int *id_map = ctx;
-	int new_id = id_map[*type_id];
-
-	/* Error out if the type wasn't remapped. Ignore VOID which stays VOID. */
-	if (new_id == 0 && *type_id != 0) {
-		pr_warn("failed to find new ID mapping for original BTF type ID %u\n", *type_id);
-		return -EINVAL;
-	}
-
-	*type_id = id_map[*type_id];
-
-	return 0;
-}
-
 static int linker_append_btf(struct bpf_linker *linker, struct src_obj *obj)
 {
 	const struct btf_type *t;
-	int i, j, n, start_id, id;
+	int i, j, n, start_id, id, err;
 	const char *name;
 
 	if (!obj->btf)
@@ -2324,9 +2322,25 @@ static int linker_append_btf(struct bpf_linker *linker, struct src_obj *obj)
 	n = btf__type_cnt(linker->btf);
 	for (i = start_id; i < n; i++) {
 		struct btf_type *dst_t = btf_type_by_id(linker->btf, i);
+		struct btf_field_iter it;
+		__u32 *type_id;
 
-		if (btf_type_visit_type_ids(dst_t, remap_type_id, obj->btf_type_map))
-			return -EINVAL;
+		err = btf_field_iter_init(&it, dst_t, BTF_FIELD_ITER_IDS);
+		if (err)
+			return err;
+
+		while ((type_id = btf_field_iter_next(&it))) {
+			int new_id = obj->btf_type_map[*type_id];
+
+			/* Error out if the type wasn't remapped. Ignore VOID which stays VOID. */
+			if (new_id == 0 && *type_id != 0) {
+				pr_warn("failed to find new ID mapping for original BTF type ID %u\n",
+					*type_id);
+				return -EINVAL;
+			}
+
+			*type_id = obj->btf_type_map[*type_id];
+		}
 	}
 
 	/* Rewrite VAR/FUNC underlying types (i.e., FUNC's FUNC_PROTO and VAR's
-- 
GitLab


From c2641123696b572a3b059e1b45777317ba9f9086 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Tue, 4 Jun 2024 17:16:27 -0700
Subject: [PATCH 817/950] libbpf: Make use of BTF field iterator in BTF
 handling code

Use new BTF field iterator logic to replace all the callback-based
visitor calls. There is still a .BTF.ext callback-based visitor APIs
that should be converted, which will happens as a follow up.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: Alan Maguire <alan.maguire@oracle.com>
Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/bpf/20240605001629.4061937-4-andrii@kernel.org
---
 tools/lib/bpf/btf.c | 76 ++++++++++++++++++++++++++++++++-------------
 1 file changed, 54 insertions(+), 22 deletions(-)

diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index d72260ac26a52..0190fd819f58b 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -1739,9 +1739,8 @@ struct btf_pipe {
 	struct hashmap *str_off_map; /* map string offsets from src to dst */
 };
 
-static int btf_rewrite_str(__u32 *str_off, void *ctx)
+static int btf_rewrite_str(struct btf_pipe *p, __u32 *str_off)
 {
-	struct btf_pipe *p = ctx;
 	long mapped_off;
 	int off, err;
 
@@ -1774,7 +1773,9 @@ static int btf_rewrite_str(__u32 *str_off, void *ctx)
 int btf__add_type(struct btf *btf, const struct btf *src_btf, const struct btf_type *src_type)
 {
 	struct btf_pipe p = { .src = src_btf, .dst = btf };
+	struct btf_field_iter it;
 	struct btf_type *t;
+	__u32 *str_off;
 	int sz, err;
 
 	sz = btf_type_size(src_type);
@@ -1791,26 +1792,17 @@ int btf__add_type(struct btf *btf, const struct btf *src_btf, const struct btf_t
 
 	memcpy(t, src_type, sz);
 
-	err = btf_type_visit_str_offs(t, btf_rewrite_str, &p);
+	err = btf_field_iter_init(&it, t, BTF_FIELD_ITER_STRS);
 	if (err)
 		return libbpf_err(err);
 
-	return btf_commit_type(btf, sz);
-}
-
-static int btf_rewrite_type_ids(__u32 *type_id, void *ctx)
-{
-	struct btf *btf = ctx;
-
-	if (!*type_id) /* nothing to do for VOID references */
-		return 0;
+	while ((str_off = btf_field_iter_next(&it))) {
+		err = btf_rewrite_str(&p, str_off);
+		if (err)
+			return libbpf_err(err);
+	}
 
-	/* we haven't updated btf's type count yet, so
-	 * btf->start_id + btf->nr_types - 1 is the type ID offset we should
-	 * add to all newly added BTF types
-	 */
-	*type_id += btf->start_id + btf->nr_types - 1;
-	return 0;
+	return btf_commit_type(btf, sz);
 }
 
 static size_t btf_dedup_identity_hash_fn(long key, void *ctx);
@@ -1858,6 +1850,9 @@ int btf__add_btf(struct btf *btf, const struct btf *src_btf)
 	memcpy(t, src_btf->types_data, data_sz);
 
 	for (i = 0; i < cnt; i++) {
+		struct btf_field_iter it;
+		__u32 *type_id, *str_off;
+
 		sz = btf_type_size(t);
 		if (sz < 0) {
 			/* unlikely, has to be corrupted src_btf */
@@ -1869,15 +1864,31 @@ int btf__add_btf(struct btf *btf, const struct btf *src_btf)
 		*off = t - btf->types_data;
 
 		/* add, dedup, and remap strings referenced by this BTF type */
-		err = btf_type_visit_str_offs(t, btf_rewrite_str, &p);
+		err = btf_field_iter_init(&it, t, BTF_FIELD_ITER_STRS);
 		if (err)
 			goto err_out;
+		while ((str_off = btf_field_iter_next(&it))) {
+			err = btf_rewrite_str(&p, str_off);
+			if (err)
+				goto err_out;
+		}
 
 		/* remap all type IDs referenced from this BTF type */
-		err = btf_type_visit_type_ids(t, btf_rewrite_type_ids, btf);
+		err = btf_field_iter_init(&it, t, BTF_FIELD_ITER_IDS);
 		if (err)
 			goto err_out;
 
+		while ((type_id = btf_field_iter_next(&it))) {
+			if (!*type_id) /* nothing to do for VOID references */
+				continue;
+
+			/* we haven't updated btf's type count yet, so
+			 * btf->start_id + btf->nr_types - 1 is the type ID offset we should
+			 * add to all newly added BTF types
+			 */
+			*type_id += btf->start_id + btf->nr_types - 1;
+		}
+
 		/* go to next type data and type offset index entry */
 		t += sz;
 		off++;
@@ -3453,11 +3464,19 @@ static int btf_for_each_str_off(struct btf_dedup *d, str_off_visit_fn fn, void *
 	int i, r;
 
 	for (i = 0; i < d->btf->nr_types; i++) {
+		struct btf_field_iter it;
 		struct btf_type *t = btf_type_by_id(d->btf, d->btf->start_id + i);
+		__u32 *str_off;
 
-		r = btf_type_visit_str_offs(t, fn, ctx);
+		r = btf_field_iter_init(&it, t, BTF_FIELD_ITER_STRS);
 		if (r)
 			return r;
+
+		while ((str_off = btf_field_iter_next(&it))) {
+			r = fn(str_off, ctx);
+			if (r)
+				return r;
+		}
 	}
 
 	if (!d->btf_ext)
@@ -4919,10 +4938,23 @@ static int btf_dedup_remap_types(struct btf_dedup *d)
 
 	for (i = 0; i < d->btf->nr_types; i++) {
 		struct btf_type *t = btf_type_by_id(d->btf, d->btf->start_id + i);
+		struct btf_field_iter it;
+		__u32 *type_id;
 
-		r = btf_type_visit_type_ids(t, btf_dedup_remap_type_id, d);
+		r = btf_field_iter_init(&it, t, BTF_FIELD_ITER_IDS);
 		if (r)
 			return r;
+
+		while ((type_id = btf_field_iter_next(&it))) {
+			__u32 resolved_id, new_id;
+
+			resolved_id = resolve_type_id(d, *type_id);
+			new_id = d->hypot_map[resolved_id];
+			if (new_id > BTF_MAX_NR_TYPES)
+				return -EINVAL;
+
+			*type_id = new_id;
+		}
 	}
 
 	if (!d->btf_ext)
-- 
GitLab


From e1a8630291fde2a0edac2955e3df48587dac9906 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Tue, 4 Jun 2024 17:16:28 -0700
Subject: [PATCH 818/950] bpftool: Use BTF field iterator in btfgen

Switch bpftool's code which is using libbpf-internal
btf_type_visit_type_ids() helper to new btf_field_iter functionality.

This makes bpftool code simpler, but also unblocks removing libbpf's
btf_type_visit_type_ids() helper completely.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: Alan Maguire <alan.maguire@oracle.com>
Reviewed-by: Quentin Monnet <qmo@kernel.org>
Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/bpf/20240605001629.4061937-5-andrii@kernel.org
---
 tools/bpf/bpftool/gen.c | 16 ++++++----------
 1 file changed, 6 insertions(+), 10 deletions(-)

diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c
index b3979ddc01895..d244a7de387e7 100644
--- a/tools/bpf/bpftool/gen.c
+++ b/tools/bpf/bpftool/gen.c
@@ -2379,15 +2379,6 @@ out:
 	return err;
 }
 
-static int btfgen_remap_id(__u32 *type_id, void *ctx)
-{
-	unsigned int *ids = ctx;
-
-	*type_id = ids[*type_id];
-
-	return 0;
-}
-
 /* Generate BTF from relocation information previously recorded */
 static struct btf *btfgen_get_btf(struct btfgen_info *info)
 {
@@ -2467,10 +2458,15 @@ static struct btf *btfgen_get_btf(struct btfgen_info *info)
 	/* second pass: fix up type ids */
 	for (i = 1; i < btf__type_cnt(btf_new); i++) {
 		struct btf_type *btf_type = (struct btf_type *) btf__type_by_id(btf_new, i);
+		struct btf_field_iter it;
+		__u32 *type_id;
 
-		err = btf_type_visit_type_ids(btf_type, btfgen_remap_id, ids);
+		err = btf_field_iter_init(&it, btf_type, BTF_FIELD_ITER_IDS);
 		if (err)
 			goto err_out;
+
+		while ((type_id = btf_field_iter_next(&it)))
+			*type_id = ids[*type_id];
 	}
 
 	free(ids);
-- 
GitLab


From 072088704433f75dacf9e33179dd7a81f0a238d4 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Tue, 4 Jun 2024 17:16:29 -0700
Subject: [PATCH 819/950] libbpf: Remove callback-based type/string BTF field
 visitor helpers

Now that all libbpf/bpftool code switched to btf_field_iter, remove
btf_type_visit_type_ids() and btf_type_visit_str_offs() callback-based
helpers as not needed anymore.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: Alan Maguire <alan.maguire@oracle.com>
Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/bpf/20240605001629.4061937-6-andrii@kernel.org
---
 tools/lib/bpf/btf.c             | 130 --------------------------------
 tools/lib/bpf/libbpf_internal.h |   2 -
 2 files changed, 132 deletions(-)

diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 0190fd819f58b..775ca55a541ca 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -5035,136 +5035,6 @@ struct btf *btf__load_module_btf(const char *module_name, struct btf *vmlinux_bt
 	return btf__parse_split(path, vmlinux_btf);
 }
 
-int btf_type_visit_type_ids(struct btf_type *t, type_id_visit_fn visit, void *ctx)
-{
-	int i, n, err;
-
-	switch (btf_kind(t)) {
-	case BTF_KIND_INT:
-	case BTF_KIND_FLOAT:
-	case BTF_KIND_ENUM:
-	case BTF_KIND_ENUM64:
-		return 0;
-
-	case BTF_KIND_FWD:
-	case BTF_KIND_CONST:
-	case BTF_KIND_VOLATILE:
-	case BTF_KIND_RESTRICT:
-	case BTF_KIND_PTR:
-	case BTF_KIND_TYPEDEF:
-	case BTF_KIND_FUNC:
-	case BTF_KIND_VAR:
-	case BTF_KIND_DECL_TAG:
-	case BTF_KIND_TYPE_TAG:
-		return visit(&t->type, ctx);
-
-	case BTF_KIND_ARRAY: {
-		struct btf_array *a = btf_array(t);
-
-		err = visit(&a->type, ctx);
-		err = err ?: visit(&a->index_type, ctx);
-		return err;
-	}
-
-	case BTF_KIND_STRUCT:
-	case BTF_KIND_UNION: {
-		struct btf_member *m = btf_members(t);
-
-		for (i = 0, n = btf_vlen(t); i < n; i++, m++) {
-			err = visit(&m->type, ctx);
-			if (err)
-				return err;
-		}
-		return 0;
-	}
-
-	case BTF_KIND_FUNC_PROTO: {
-		struct btf_param *m = btf_params(t);
-
-		err = visit(&t->type, ctx);
-		if (err)
-			return err;
-		for (i = 0, n = btf_vlen(t); i < n; i++, m++) {
-			err = visit(&m->type, ctx);
-			if (err)
-				return err;
-		}
-		return 0;
-	}
-
-	case BTF_KIND_DATASEC: {
-		struct btf_var_secinfo *m = btf_var_secinfos(t);
-
-		for (i = 0, n = btf_vlen(t); i < n; i++, m++) {
-			err = visit(&m->type, ctx);
-			if (err)
-				return err;
-		}
-		return 0;
-	}
-
-	default:
-		return -EINVAL;
-	}
-}
-
-int btf_type_visit_str_offs(struct btf_type *t, str_off_visit_fn visit, void *ctx)
-{
-	int i, n, err;
-
-	err = visit(&t->name_off, ctx);
-	if (err)
-		return err;
-
-	switch (btf_kind(t)) {
-	case BTF_KIND_STRUCT:
-	case BTF_KIND_UNION: {
-		struct btf_member *m = btf_members(t);
-
-		for (i = 0, n = btf_vlen(t); i < n; i++, m++) {
-			err = visit(&m->name_off, ctx);
-			if (err)
-				return err;
-		}
-		break;
-	}
-	case BTF_KIND_ENUM: {
-		struct btf_enum *m = btf_enum(t);
-
-		for (i = 0, n = btf_vlen(t); i < n; i++, m++) {
-			err = visit(&m->name_off, ctx);
-			if (err)
-				return err;
-		}
-		break;
-	}
-	case BTF_KIND_ENUM64: {
-		struct btf_enum64 *m = btf_enum64(t);
-
-		for (i = 0, n = btf_vlen(t); i < n; i++, m++) {
-			err = visit(&m->name_off, ctx);
-			if (err)
-				return err;
-		}
-		break;
-	}
-	case BTF_KIND_FUNC_PROTO: {
-		struct btf_param *m = btf_params(t);
-
-		for (i = 0, n = btf_vlen(t); i < n; i++, m++) {
-			err = visit(&m->name_off, ctx);
-			if (err)
-				return err;
-		}
-		break;
-	}
-	default:
-		break;
-	}
-
-	return 0;
-}
-
 int btf_field_iter_init(struct btf_field_iter *it, struct btf_type *t, enum btf_field_iter_kind iter_kind)
 {
 	it->p = NULL;
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index 96c0b0993f8bc..e2f06609c6244 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -535,8 +535,6 @@ __u32 *btf_field_iter_next(struct btf_field_iter *it);
 
 typedef int (*type_id_visit_fn)(__u32 *type_id, void *ctx);
 typedef int (*str_off_visit_fn)(__u32 *str_off, void *ctx);
-int btf_type_visit_type_ids(struct btf_type *t, type_id_visit_fn visit, void *ctx);
-int btf_type_visit_str_offs(struct btf_type *t, str_off_visit_fn visit, void *ctx);
 int btf_ext_visit_type_ids(struct btf_ext *btf_ext, type_id_visit_fn visit, void *ctx);
 int btf_ext_visit_str_offs(struct btf_ext *btf_ext, str_off_visit_fn visit, void *ctx);
 __s32 btf__find_by_name_kind_own(const struct btf *btf, const char *type_name,
-- 
GitLab


From 229bedbf62b13af5aba6525ad10b62ad38d9ccb5 Mon Sep 17 00:00:00 2001
From: Aleksandr Mishin <amishin@t-argos.ru>
Date: Tue, 4 Jun 2024 13:05:52 +0300
Subject: [PATCH 820/950] net/mlx5: Fix tainted pointer delete is case of flow
 rules creation fail

In case of flow rule creation fail in mlx5_lag_create_port_sel_table(),
instead of previously created rules, the tainted pointer is deleted
deveral times.
Fix this bug by using correct flow rules pointers.

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

Fixes: 352899f384d4 ("net/mlx5: Lag, use buckets in hash mode")
Signed-off-by: Aleksandr Mishin <amishin@t-argos.ru>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://lore.kernel.org/r/20240604100552.25201-1-amishin@t-argos.ru
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c
index c16b462ddedf7..ab2717012b79b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c
@@ -88,9 +88,13 @@ static int mlx5_lag_create_port_sel_table(struct mlx5_lag *ldev,
 								      &dest, 1);
 			if (IS_ERR(lag_definer->rules[idx])) {
 				err = PTR_ERR(lag_definer->rules[idx]);
-				while (i--)
-					while (j--)
+				do {
+					while (j--) {
+						idx = i * ldev->buckets + j;
 						mlx5_del_flow_rules(lag_definer->rules[idx]);
+					}
+					j = ldev->buckets;
+				} while (i--);
 				goto destroy_fg;
 			}
 		}
-- 
GitLab


From c790275b5edf5d8280ae520bda7c1f37da460c00 Mon Sep 17 00:00:00 2001
From: Vadim Fedorenko <vadfed@meta.com>
Date: Tue, 4 Jun 2024 02:19:39 -0700
Subject: [PATCH 821/950] bnxt_en: fix atomic counter for ptp packets

atomic_dec_if_positive returns new value regardless if it is updated or
not. The commit in fixes changed the behavior of the condition to one
that differs from original code. Restore original condition to properly
maintain atomic counter.

Fixes: 165f87691a89 ("bnxt_en: add timestamping statistics support")
Reviewed-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: Vadim Fedorenko <vadfed@meta.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20240604091939.785535-1-vadfed@meta.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 6d9faa78e391c..7dc00c0d89924 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -513,7 +513,7 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
 
 		if (ptp && ptp->tx_tstamp_en && !skb_is_gso(skb)) {
-			if (!atomic_dec_if_positive(&ptp->tx_avail)) {
+			if (atomic_dec_if_positive(&ptp->tx_avail) < 0) {
 				atomic64_inc(&ptp->stats.ts_err);
 				goto tx_no_ts;
 			}
-- 
GitLab


From 1467713eb2244a54c99028a2eacd44f2d1badaf7 Mon Sep 17 00:00:00 2001
From: David Christensen <drc@linux.ibm.com>
Date: Mon, 3 Jun 2024 17:27:41 -0400
Subject: [PATCH 822/950] ionic: advertise 52-bit addressing limitation for
 MSI-X

Current ionic devices only support 52 internal physical address
lines. This is sufficient for x86_64 systems which have similar
limitations but does not apply to all other architectures,
notably IBM POWER (ppc64). To ensure that MSI/MSI-X vectors are
not set outside the physical address limits of the NIC, set the
no_64bit_msi value of the pci_dev structure during device probe.

Signed-off-by: David Christensen <drc@linux.ibm.com>
Reviewed-by: Shannon Nelson <shannon.nelson@amd.com>
Link: https://lore.kernel.org/r/20240603212747.1079134-1-drc@linux.ibm.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c
index 6ba8d4aca0a03..a7146d50f8142 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c
@@ -326,6 +326,11 @@ static int ionic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_out;
 	}
 
+#ifdef CONFIG_PPC64
+	/* Ensure MSI/MSI-X interrupts lie within addressable physical memory */
+	pdev->no_64bit_msi = 1;
+#endif
+
 	err = ionic_setup_one(ionic);
 	if (err)
 		goto err_out;
-- 
GitLab


From f921a58ae20852d188f70842431ce6519c4fdc36 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 4 Jun 2024 18:15:11 +0000
Subject: [PATCH 823/950] net/sched: taprio: always validate
 TCA_TAPRIO_ATTR_PRIOMAP

If one TCA_TAPRIO_ATTR_PRIOMAP attribute has been provided,
taprio_parse_mqprio_opt() must validate it, or userspace
can inject arbitrary data to the kernel, the second time
taprio_change() is called.

First call (with valid attributes) sets dev->num_tc
to a non zero value.

Second call (with arbitrary mqprio attributes)
returns early from taprio_parse_mqprio_opt()
and bad things can happen.

Fixes: a3d43c0d56f1 ("taprio: Add support adding an admin schedule")
Reported-by: Noam Rathaus <noamr@ssd-disclosure.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://lore.kernel.org/r/20240604181511.769870-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/sch_taprio.c | 15 ++++++---------
 1 file changed, 6 insertions(+), 9 deletions(-)

diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 937a0c513c174..b284a06b5a75f 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -1176,16 +1176,13 @@ static int taprio_parse_mqprio_opt(struct net_device *dev,
 {
 	bool allow_overlapping_txqs = TXTIME_ASSIST_IS_ENABLED(taprio_flags);
 
-	if (!qopt && !dev->num_tc) {
-		NL_SET_ERR_MSG(extack, "'mqprio' configuration is necessary");
-		return -EINVAL;
-	}
-
-	/* If num_tc is already set, it means that the user already
-	 * configured the mqprio part
-	 */
-	if (dev->num_tc)
+	if (!qopt) {
+		if (!dev->num_tc) {
+			NL_SET_ERR_MSG(extack, "'mqprio' configuration is necessary");
+			return -EINVAL;
+		}
 		return 0;
+	}
 
 	/* taprio imposes that traffic classes map 1:n to tx queues */
 	if (qopt->num_tc > dev->num_tx_queues) {
-- 
GitLab


From 4978478a688861207503f3baabcc9c1a5ff43cce Mon Sep 17 00:00:00 2001
From: Ronak Doshi <ronak.doshi@broadcom.com>
Date: Fri, 31 May 2024 12:30:46 -0700
Subject: [PATCH 824/950] vmxnet3: prepare for version 9 changes

vmxnet3 is currently at version 7 and this patch initiates the
preparation to accommodate changes for up to version 9. Introduced
utility macros for vmxnet3 version 9 comparison and update Copyright
information.

Signed-off-by: Ronak Doshi <ronak.doshi@broadcom.com>
Acked-by: Guolin Yang <guolin.yang@broadcom.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20240531193050.4132-2-ronak.doshi@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/vmxnet3/Makefile          | 2 +-
 drivers/net/vmxnet3/vmxnet3_defs.h    | 2 +-
 drivers/net/vmxnet3/vmxnet3_drv.c     | 2 +-
 drivers/net/vmxnet3/vmxnet3_ethtool.c | 2 +-
 drivers/net/vmxnet3/vmxnet3_int.h     | 8 +++++++-
 5 files changed, 11 insertions(+), 5 deletions(-)

diff --git a/drivers/net/vmxnet3/Makefile b/drivers/net/vmxnet3/Makefile
index f82870c10205a..59ef494ce2e05 100644
--- a/drivers/net/vmxnet3/Makefile
+++ b/drivers/net/vmxnet3/Makefile
@@ -2,7 +2,7 @@
 #
 # Linux driver for VMware's vmxnet3 ethernet NIC.
 #
-# Copyright (C) 2007-2022, VMware, Inc. All Rights Reserved.
+# Copyright (C) 2007-2024, VMware, Inc. All Rights Reserved.
 #
 # This program is free software; you can redistribute it and/or modify it
 # under the terms of the GNU General Public License as published by the
diff --git a/drivers/net/vmxnet3/vmxnet3_defs.h b/drivers/net/vmxnet3/vmxnet3_defs.h
index 41d6767283a63..67387bb7aa249 100644
--- a/drivers/net/vmxnet3/vmxnet3_defs.h
+++ b/drivers/net/vmxnet3/vmxnet3_defs.h
@@ -1,7 +1,7 @@
 /*
  * Linux driver for VMware's vmxnet3 ethernet NIC.
  *
- * Copyright (C) 2008-2022, VMware, Inc. All Rights Reserved.
+ * Copyright (C) 2008-2024, VMware, Inc. All Rights Reserved.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms of the GNU General Public License as published by the
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index 89ca6e75fcc6b..b3f3136cc8bee 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -1,7 +1,7 @@
 /*
  * Linux driver for VMware's vmxnet3 ethernet NIC.
  *
- * Copyright (C) 2008-2022, VMware, Inc. All Rights Reserved.
+ * Copyright (C) 2008-2024, VMware, Inc. All Rights Reserved.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms of the GNU General Public License as published by the
diff --git a/drivers/net/vmxnet3/vmxnet3_ethtool.c b/drivers/net/vmxnet3/vmxnet3_ethtool.c
index 7e8008d5378ae..471f91c4204a1 100644
--- a/drivers/net/vmxnet3/vmxnet3_ethtool.c
+++ b/drivers/net/vmxnet3/vmxnet3_ethtool.c
@@ -1,7 +1,7 @@
 /*
  * Linux driver for VMware's vmxnet3 ethernet NIC.
  *
- * Copyright (C) 2008-2022, VMware, Inc. All Rights Reserved.
+ * Copyright (C) 2008-2024, VMware, Inc. All Rights Reserved.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms of the GNU General Public License as published by the
diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h
index 915aaf18c4094..2926dfe8514f6 100644
--- a/drivers/net/vmxnet3/vmxnet3_int.h
+++ b/drivers/net/vmxnet3/vmxnet3_int.h
@@ -1,7 +1,7 @@
 /*
  * Linux driver for VMware's vmxnet3 ethernet NIC.
  *
- * Copyright (C) 2008-2022, VMware, Inc. All Rights Reserved.
+ * Copyright (C) 2008-2024, VMware, Inc. All Rights Reserved.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms of the GNU General Public License as published by the
@@ -84,6 +84,8 @@
 	#define VMXNET3_RSS
 #endif
 
+#define VMXNET3_REV_9		8	/* Vmxnet3 Rev. 9 */
+#define VMXNET3_REV_8		7	/* Vmxnet3 Rev. 8 */
 #define VMXNET3_REV_7		6	/* Vmxnet3 Rev. 7 */
 #define VMXNET3_REV_6		5	/* Vmxnet3 Rev. 6 */
 #define VMXNET3_REV_5		4	/* Vmxnet3 Rev. 5 */
@@ -463,6 +465,10 @@ struct vmxnet3_adapter {
 	(adapter->version >= VMXNET3_REV_6 + 1)
 #define VMXNET3_VERSION_GE_7(adapter) \
 	(adapter->version >= VMXNET3_REV_7 + 1)
+#define VMXNET3_VERSION_GE_8(adapter) \
+	(adapter->version >= VMXNET3_REV_8 + 1)
+#define VMXNET3_VERSION_GE_9(adapter) \
+	(adapter->version >= VMXNET3_REV_9 + 1)
 
 /* must be a multiple of VMXNET3_RING_SIZE_ALIGN */
 #define VMXNET3_DEF_TX_RING_SIZE    512
-- 
GitLab


From 4c22fad70256245202f33d6f166bfb47bb634bc3 Mon Sep 17 00:00:00 2001
From: Ronak Doshi <ronak.doshi@broadcom.com>
Date: Fri, 31 May 2024 12:30:47 -0700
Subject: [PATCH 825/950] vmxnet3: add latency measurement support in vmxnet3

This patch enhances vmxnet3 to support latency measurement.
This support will help to track the latency in packet processing
between guest virtual nic driver and host. For this purpose, we
introduce a new timestamp ring in vmxnet3 which will be per Tx/Rx
queue. This ring will be used to carry timestamp of the packets
which will be used to calculate the latency.

User can enable latency measurement using realtime knob in vnic
setting in VCenter.

Signed-off-by: Ronak Doshi <ronak.doshi@broadcom.com>
Acked-by: Guolin Yang <guolin.yang@broadcom.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20240531193050.4132-3-ronak.doshi@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/vmxnet3/vmxnet3_defs.h |  55 ++++++++++-
 drivers/net/vmxnet3/vmxnet3_drv.c  | 150 ++++++++++++++++++++++++++++-
 drivers/net/vmxnet3/vmxnet3_int.h  |  20 ++++
 3 files changed, 220 insertions(+), 5 deletions(-)

diff --git a/drivers/net/vmxnet3/vmxnet3_defs.h b/drivers/net/vmxnet3/vmxnet3_defs.h
index 67387bb7aa249..dcf1cf8e7a864 100644
--- a/drivers/net/vmxnet3/vmxnet3_defs.h
+++ b/drivers/net/vmxnet3/vmxnet3_defs.h
@@ -80,6 +80,8 @@ enum {
 #define VMXNET3_IO_TYPE(addr)           ((addr) >> 24)
 #define VMXNET3_IO_REG(addr)            ((addr) & 0xFFFFFF)
 
+#define VMXNET3_PMC_PSEUDO_TSC  0x10003
+
 enum {
 	VMXNET3_CMD_FIRST_SET = 0xCAFE0000,
 	VMXNET3_CMD_ACTIVATE_DEV = VMXNET3_CMD_FIRST_SET,
@@ -123,6 +125,7 @@ enum {
 	VMXNET3_CMD_GET_RESERVED4,
 	VMXNET3_CMD_GET_MAX_CAPABILITIES,
 	VMXNET3_CMD_GET_DCR0_REG,
+	VMXNET3_CMD_GET_TSRING_DESC_SIZE,
 };
 
 /*
@@ -254,6 +257,24 @@ struct Vmxnet3_RxDesc {
 
 #define VMXNET3_RCD_HDR_INNER_SHIFT  13
 
+struct Vmxnet3TSInfo {
+	u64  tsData:56;
+	u64  tsType:4;
+	u64  tsi:1;      //bit to indicate to set ts
+	u64  pad:3;
+	u64  pad2;
+};
+
+struct Vmxnet3_TxTSDesc {
+	struct Vmxnet3TSInfo ts;
+	u64    pad[14];
+};
+
+struct Vmxnet3_RxTSDesc {
+	struct Vmxnet3TSInfo ts;
+	u64    pad[14];
+};
+
 struct Vmxnet3_RxCompDesc {
 #ifdef __BIG_ENDIAN_BITFIELD
 	u32		ext2:1;
@@ -427,6 +448,13 @@ union Vmxnet3_GenericDesc {
 #define VMXNET3_RXDATA_DESC_SIZE_ALIGN 64
 #define VMXNET3_RXDATA_DESC_SIZE_MASK  (VMXNET3_RXDATA_DESC_SIZE_ALIGN - 1)
 
+/* Rx TS Ring buffer size must be a multiple of 64 bytes */
+#define VMXNET3_RXTS_DESC_SIZE_ALIGN 64
+#define VMXNET3_RXTS_DESC_SIZE_MASK  (VMXNET3_RXTS_DESC_SIZE_ALIGN - 1)
+/* Tx TS Ring buffer size must be a multiple of 64 bytes */
+#define VMXNET3_TXTS_DESC_SIZE_ALIGN 64
+#define VMXNET3_TXTS_DESC_SIZE_MASK  (VMXNET3_TXTS_DESC_SIZE_ALIGN - 1)
+
 /* Max ring size */
 #define VMXNET3_TX_RING_MAX_SIZE   4096
 #define VMXNET3_TC_RING_MAX_SIZE   4096
@@ -439,6 +467,9 @@ union Vmxnet3_GenericDesc {
 
 #define VMXNET3_RXDATA_DESC_MAX_SIZE 2048
 
+#define VMXNET3_TXTS_DESC_MAX_SIZE   256
+#define VMXNET3_RXTS_DESC_MAX_SIZE   256
+
 /* a list of reasons for queue stop */
 
 enum {
@@ -546,6 +577,24 @@ struct Vmxnet3_RxQueueConf {
 };
 
 
+struct Vmxnet3_LatencyConf {
+	u16 sampleRate;
+	u16 pad;
+};
+
+struct Vmxnet3_TxQueueTSConf {
+	__le64  txTSRingBasePA;
+	__le16  txTSRingDescSize; /* size of tx timestamp ring buffer */
+	u16     pad;
+	struct Vmxnet3_LatencyConf latencyConf;
+};
+
+struct Vmxnet3_RxQueueTSConf {
+	__le64  rxTSRingBasePA;
+	__le16  rxTSRingDescSize; /* size of rx timestamp ring buffer */
+	u16     pad[3];
+};
+
 enum vmxnet3_intr_mask_mode {
 	VMXNET3_IMM_AUTO   = 0,
 	VMXNET3_IMM_ACTIVE = 1,
@@ -679,7 +728,8 @@ struct Vmxnet3_TxQueueDesc {
 	/* Driver read after a GET command */
 	struct Vmxnet3_QueueStatus		status;
 	struct UPT1_TxStats			stats;
-	u8					_pad[88]; /* 128 aligned */
+	struct Vmxnet3_TxQueueTSConf            tsConf;
+	u8					_pad[72]; /* 128 aligned */
 };
 
 
@@ -689,7 +739,8 @@ struct Vmxnet3_RxQueueDesc {
 	/* Driver read after a GET commad */
 	struct Vmxnet3_QueueStatus		status;
 	struct UPT1_RxStats			stats;
-	u8				      __pad[88]; /* 128 aligned */
+	struct Vmxnet3_RxQueueTSConf            tsConf;
+	u8				      __pad[72]; /* 128 aligned */
 };
 
 struct Vmxnet3_SetPolling {
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index b3f3136cc8bee..71677115628bd 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -143,6 +143,32 @@ vmxnet3_tq_stop(struct vmxnet3_tx_queue *tq, struct vmxnet3_adapter *adapter)
 	netif_stop_subqueue(adapter->netdev, (tq - adapter->tx_queue));
 }
 
+static u64
+vmxnet3_get_cycles(int pmc)
+{
+#ifdef CONFIG_X86
+	return native_read_pmc(pmc);
+#else
+	return 0;
+#endif
+}
+
+static bool
+vmxnet3_apply_timestamp(struct vmxnet3_tx_queue *tq, u16 rate)
+{
+#ifdef CONFIG_X86
+	if (rate > 0) {
+		if (tq->tsPktCount == 1) {
+			if (rate != 1)
+				tq->tsPktCount = rate;
+			return true;
+		}
+		tq->tsPktCount--;
+	}
+#endif
+	return false;
+}
+
 /* Check if capability is supported by UPT device or
  * UPT is even requested
  */
@@ -498,6 +524,12 @@ vmxnet3_tq_destroy(struct vmxnet3_tx_queue *tq,
 				  tq->data_ring.base, tq->data_ring.basePA);
 		tq->data_ring.base = NULL;
 	}
+	if (tq->ts_ring.base) {
+		dma_free_coherent(&adapter->pdev->dev,
+				  tq->tx_ring.size * tq->tx_ts_desc_size,
+				  tq->ts_ring.base, tq->ts_ring.basePA);
+		tq->ts_ring.base = NULL;
+	}
 	if (tq->comp_ring.base) {
 		dma_free_coherent(&adapter->pdev->dev, tq->comp_ring.size *
 				  sizeof(struct Vmxnet3_TxCompDesc),
@@ -535,6 +567,10 @@ vmxnet3_tq_init(struct vmxnet3_tx_queue *tq,
 	memset(tq->data_ring.base, 0,
 	       tq->data_ring.size * tq->txdata_desc_size);
 
+	if (tq->ts_ring.base)
+		memset(tq->ts_ring.base, 0,
+		       tq->tx_ring.size * tq->tx_ts_desc_size);
+
 	/* reset the tx comp ring contents to 0 and reset comp ring states */
 	memset(tq->comp_ring.base, 0, tq->comp_ring.size *
 	       sizeof(struct Vmxnet3_TxCompDesc));
@@ -573,6 +609,18 @@ vmxnet3_tq_create(struct vmxnet3_tx_queue *tq,
 		goto err;
 	}
 
+	if (tq->tx_ts_desc_size != 0) {
+		tq->ts_ring.base = dma_alloc_coherent(&adapter->pdev->dev,
+						      tq->tx_ring.size * tq->tx_ts_desc_size,
+						      &tq->ts_ring.basePA, GFP_KERNEL);
+		if (!tq->ts_ring.base) {
+			netdev_err(adapter->netdev, "failed to allocate tx ts ring\n");
+			tq->tx_ts_desc_size = 0;
+		}
+	} else {
+		tq->ts_ring.base = NULL;
+	}
+
 	tq->comp_ring.base = dma_alloc_coherent(&adapter->pdev->dev,
 			tq->comp_ring.size * sizeof(struct Vmxnet3_TxCompDesc),
 			&tq->comp_ring.basePA, GFP_KERNEL);
@@ -861,6 +909,11 @@ vmxnet3_map_pkt(struct sk_buff *skb, struct vmxnet3_tx_ctx *ctx,
 	/* set the last buf_info for the pkt */
 	tbi->skb = skb;
 	tbi->sop_idx = ctx->sop_txd - tq->tx_ring.base;
+	if (tq->tx_ts_desc_size != 0) {
+		ctx->ts_txd = (struct Vmxnet3_TxTSDesc *)((u8 *)tq->ts_ring.base +
+							  tbi->sop_idx * tq->tx_ts_desc_size);
+		ctx->ts_txd->ts.tsi = 0;
+	}
 
 	return 0;
 }
@@ -968,7 +1021,7 @@ vmxnet3_parse_hdr(struct sk_buff *skb, struct vmxnet3_tx_queue *tq,
 					       skb_headlen(skb));
 		}
 
-		if (skb->len <= VMXNET3_HDR_COPY_SIZE)
+		if (skb->len <= tq->txdata_desc_size)
 			ctx->copy_size = skb->len;
 
 		/* make sure headers are accessible directly */
@@ -1259,6 +1312,14 @@ vmxnet3_tq_xmit(struct sk_buff *skb, struct vmxnet3_tx_queue *tq,
 		gdesc->txd.tci = skb_vlan_tag_get(skb);
 	}
 
+	if (tq->tx_ts_desc_size != 0 &&
+	    adapter->latencyConf->sampleRate != 0) {
+		if (vmxnet3_apply_timestamp(tq, adapter->latencyConf->sampleRate)) {
+			ctx.ts_txd->ts.tsData = vmxnet3_get_cycles(VMXNET3_PMC_PSEUDO_TSC);
+			ctx.ts_txd->ts.tsi = 1;
+		}
+	}
+
 	/* Ensure that the write to (&gdesc->txd)->gen will be observed after
 	 * all other writes to &gdesc->txd.
 	 */
@@ -1608,6 +1669,15 @@ skip_xdp:
 			skip_page_frags = false;
 			ctx->skb = rbi->skb;
 
+			if (rq->rx_ts_desc_size != 0 && rcd->ext2) {
+				struct Vmxnet3_RxTSDesc *ts_rxd;
+
+				ts_rxd = (struct Vmxnet3_RxTSDesc *)((u8 *)rq->ts_ring.base +
+								     idx * rq->rx_ts_desc_size);
+				ts_rxd->ts.tsData = vmxnet3_get_cycles(VMXNET3_PMC_PSEUDO_TSC);
+				ts_rxd->ts.tsi = 1;
+			}
+
 			rxDataRingUsed =
 				VMXNET3_RX_DATA_RING(adapter, rcd->rqID);
 			len = rxDataRingUsed ? rcd->len : rbi->len;
@@ -2007,6 +2077,13 @@ static void vmxnet3_rq_destroy(struct vmxnet3_rx_queue *rq,
 		rq->data_ring.base = NULL;
 	}
 
+	if (rq->ts_ring.base) {
+		dma_free_coherent(&adapter->pdev->dev,
+				  rq->rx_ring[0].size * rq->rx_ts_desc_size,
+				  rq->ts_ring.base, rq->ts_ring.basePA);
+		rq->ts_ring.base = NULL;
+	}
+
 	if (rq->comp_ring.base) {
 		dma_free_coherent(&adapter->pdev->dev, rq->comp_ring.size
 				  * sizeof(struct Vmxnet3_RxCompDesc),
@@ -2090,6 +2167,10 @@ vmxnet3_rq_init(struct vmxnet3_rx_queue *rq,
 	}
 	vmxnet3_rq_alloc_rx_buf(rq, 1, rq->rx_ring[1].size - 1, adapter);
 
+	if (rq->ts_ring.base)
+		memset(rq->ts_ring.base, 0,
+		       rq->rx_ring[0].size * rq->rx_ts_desc_size);
+
 	/* reset the comp ring */
 	rq->comp_ring.next2proc = 0;
 	memset(rq->comp_ring.base, 0, rq->comp_ring.size *
@@ -2160,6 +2241,21 @@ vmxnet3_rq_create(struct vmxnet3_rx_queue *rq, struct vmxnet3_adapter *adapter)
 		rq->data_ring.desc_size = 0;
 	}
 
+	if (rq->rx_ts_desc_size != 0) {
+		sz = rq->rx_ring[0].size * rq->rx_ts_desc_size;
+		rq->ts_ring.base =
+			dma_alloc_coherent(&adapter->pdev->dev, sz,
+					   &rq->ts_ring.basePA,
+					   GFP_KERNEL);
+		if (!rq->ts_ring.base) {
+			netdev_err(adapter->netdev,
+				   "rx ts ring will be disabled\n");
+			rq->rx_ts_desc_size = 0;
+		}
+	} else {
+		rq->ts_ring.base = NULL;
+	}
+
 	sz = rq->comp_ring.size * sizeof(struct Vmxnet3_RxCompDesc);
 	rq->comp_ring.base = dma_alloc_coherent(&adapter->pdev->dev, sz,
 						&rq->comp_ring.basePA,
@@ -2759,6 +2855,8 @@ vmxnet3_setup_driver_shared(struct vmxnet3_adapter *adapter)
 	struct Vmxnet3_DSDevReadExt *devReadExt = &shared->devReadExt;
 	struct Vmxnet3_TxQueueConf *tqc;
 	struct Vmxnet3_RxQueueConf *rqc;
+	struct Vmxnet3_TxQueueTSConf *tqtsc;
+	struct Vmxnet3_RxQueueTSConf *rqtsc;
 	int i;
 
 	memset(shared, 0, sizeof(*shared));
@@ -2815,6 +2913,11 @@ vmxnet3_setup_driver_shared(struct vmxnet3_adapter *adapter)
 		tqc->compRingSize   = cpu_to_le32(tq->comp_ring.size);
 		tqc->ddLen          = cpu_to_le32(0);
 		tqc->intrIdx        = tq->comp_ring.intr_idx;
+		if (VMXNET3_VERSION_GE_9(adapter)) {
+			tqtsc = &adapter->tqd_start[i].tsConf;
+			tqtsc->txTSRingBasePA = cpu_to_le64(tq->ts_ring.basePA);
+			tqtsc->txTSRingDescSize = cpu_to_le16(tq->tx_ts_desc_size);
+		}
 	}
 
 	/* rx queue settings */
@@ -2837,6 +2940,11 @@ vmxnet3_setup_driver_shared(struct vmxnet3_adapter *adapter)
 			rqc->rxDataRingDescSize =
 				cpu_to_le16(rq->data_ring.desc_size);
 		}
+		if (VMXNET3_VERSION_GE_9(adapter)) {
+			rqtsc = &adapter->rqd_start[i].tsConf;
+			rqtsc->rxTSRingBasePA = cpu_to_le64(rq->ts_ring.basePA);
+			rqtsc->rxTSRingDescSize = cpu_to_le16(rq->rx_ts_desc_size);
+		}
 	}
 
 #ifdef VMXNET3_RSS
@@ -3299,6 +3407,8 @@ vmxnet3_create_queues(struct vmxnet3_adapter *adapter, u32 tx_ring_size,
 		tq->stopped = true;
 		tq->adapter = adapter;
 		tq->qid = i;
+		tq->tx_ts_desc_size = adapter->tx_ts_desc_size;
+		tq->tsPktCount = 1;
 		err = vmxnet3_tq_create(tq, adapter);
 		/*
 		 * Too late to change num_tx_queues. We cannot do away with
@@ -3320,6 +3430,7 @@ vmxnet3_create_queues(struct vmxnet3_adapter *adapter, u32 tx_ring_size,
 		rq->shared = &adapter->rqd_start[i].ctrl;
 		rq->adapter = adapter;
 		rq->data_ring.desc_size = rxdata_desc_size;
+		rq->rx_ts_desc_size = adapter->rx_ts_desc_size;
 		err = vmxnet3_rq_create(rq, adapter);
 		if (err) {
 			if (i == 0) {
@@ -3361,14 +3472,15 @@ vmxnet3_open(struct net_device *netdev)
 	if (VMXNET3_VERSION_GE_3(adapter)) {
 		unsigned long flags;
 		u16 txdata_desc_size;
+		u32 ret;
 
 		spin_lock_irqsave(&adapter->cmd_lock, flags);
 		VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD,
 				       VMXNET3_CMD_GET_TXDATA_DESC_SIZE);
-		txdata_desc_size = VMXNET3_READ_BAR1_REG(adapter,
-							 VMXNET3_REG_CMD);
+		ret = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_CMD);
 		spin_unlock_irqrestore(&adapter->cmd_lock, flags);
 
+		txdata_desc_size = ret & 0xffff;
 		if ((txdata_desc_size < VMXNET3_TXDATA_DESC_MIN_SIZE) ||
 		    (txdata_desc_size > VMXNET3_TXDATA_DESC_MAX_SIZE) ||
 		    (txdata_desc_size & VMXNET3_TXDATA_DESC_SIZE_MASK)) {
@@ -3377,10 +3489,40 @@ vmxnet3_open(struct net_device *netdev)
 		} else {
 			adapter->txdata_desc_size = txdata_desc_size;
 		}
+		if (VMXNET3_VERSION_GE_9(adapter))
+			adapter->rxdata_desc_size = (ret >> 16) & 0xffff;
 	} else {
 		adapter->txdata_desc_size = sizeof(struct Vmxnet3_TxDataDesc);
 	}
 
+	if (VMXNET3_VERSION_GE_9(adapter)) {
+		unsigned long flags;
+		u16 tx_ts_desc_size = 0;
+		u16 rx_ts_desc_size = 0;
+		u32 ret;
+
+		spin_lock_irqsave(&adapter->cmd_lock, flags);
+		VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD,
+				       VMXNET3_CMD_GET_TSRING_DESC_SIZE);
+		ret = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_CMD);
+		spin_unlock_irqrestore(&adapter->cmd_lock, flags);
+		if (ret > 0) {
+			tx_ts_desc_size = (ret & 0xff);
+			rx_ts_desc_size = ((ret >> 16) & 0xff);
+		}
+		if (tx_ts_desc_size > VMXNET3_TXTS_DESC_MAX_SIZE ||
+		    tx_ts_desc_size & VMXNET3_TXTS_DESC_SIZE_MASK)
+			tx_ts_desc_size = 0;
+		if (rx_ts_desc_size > VMXNET3_RXTS_DESC_MAX_SIZE ||
+		    rx_ts_desc_size & VMXNET3_RXTS_DESC_SIZE_MASK)
+			rx_ts_desc_size = 0;
+		adapter->tx_ts_desc_size = tx_ts_desc_size;
+		adapter->rx_ts_desc_size = rx_ts_desc_size;
+	} else {
+		adapter->tx_ts_desc_size = 0;
+		adapter->rx_ts_desc_size = 0;
+	}
+
 	err = vmxnet3_create_queues(adapter,
 				    adapter->tx_ring_size,
 				    adapter->rx_ring_size,
@@ -3992,6 +4134,8 @@ vmxnet3_probe_device(struct pci_dev *pdev,
 	}
 	adapter->rqd_start = (struct Vmxnet3_RxQueueDesc *)(adapter->tqd_start +
 							    adapter->num_tx_queues);
+	if (VMXNET3_VERSION_GE_9(adapter))
+		adapter->latencyConf = &adapter->tqd_start->tsConf.latencyConf;
 
 	adapter->pm_conf = dma_alloc_coherent(&adapter->pdev->dev,
 					      sizeof(struct Vmxnet3_PMConf),
diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h
index 2926dfe8514f6..68358e71526cf 100644
--- a/drivers/net/vmxnet3/vmxnet3_int.h
+++ b/drivers/net/vmxnet3/vmxnet3_int.h
@@ -193,6 +193,11 @@ struct vmxnet3_tx_data_ring {
 	dma_addr_t          basePA;
 };
 
+struct vmxnet3_tx_ts_ring {
+	struct Vmxnet3_TxTSDesc *base;
+	dma_addr_t          basePA;
+};
+
 #define VMXNET3_MAP_NONE	0
 #define VMXNET3_MAP_SINGLE	BIT(0)
 #define VMXNET3_MAP_PAGE	BIT(1)
@@ -245,6 +250,7 @@ struct vmxnet3_tx_ctx {
 	u32 copy_size;       /* # of bytes copied into the data ring */
 	union Vmxnet3_GenericDesc *sop_txd;
 	union Vmxnet3_GenericDesc *eop_txd;
+	struct Vmxnet3_TxTSDesc *ts_txd;
 };
 
 struct vmxnet3_tx_queue {
@@ -254,6 +260,7 @@ struct vmxnet3_tx_queue {
 	struct vmxnet3_cmd_ring         tx_ring;
 	struct vmxnet3_tx_buf_info      *buf_info;
 	struct vmxnet3_tx_data_ring     data_ring;
+	struct vmxnet3_tx_ts_ring       ts_ring;
 	struct vmxnet3_comp_ring        comp_ring;
 	struct Vmxnet3_TxQueueCtrl      *shared;
 	struct vmxnet3_tq_driver_stats  stats;
@@ -262,6 +269,8 @@ struct vmxnet3_tx_queue {
 						    * stopped */
 	int				qid;
 	u16				txdata_desc_size;
+	u16                             tx_ts_desc_size;
+	u16                             tsPktCount;
 } ____cacheline_aligned;
 
 enum vmxnet3_rx_buf_type {
@@ -309,6 +318,11 @@ struct vmxnet3_rx_data_ring {
 	u16 desc_size;
 };
 
+struct vmxnet3_rx_ts_ring {
+	struct Vmxnet3_RxTSDesc *base;
+	dma_addr_t basePA;
+};
+
 struct vmxnet3_rx_queue {
 	char			name[IFNAMSIZ + 8]; /* To identify interrupt */
 	struct vmxnet3_adapter	  *adapter;
@@ -316,6 +330,7 @@ struct vmxnet3_rx_queue {
 	struct vmxnet3_cmd_ring   rx_ring[2];
 	struct vmxnet3_rx_data_ring data_ring;
 	struct vmxnet3_comp_ring  comp_ring;
+	struct vmxnet3_rx_ts_ring ts_ring;
 	struct vmxnet3_rx_ctx     rx_ctx;
 	u32 qid;            /* rqID in RCD for buffer from 1st ring */
 	u32 qid2;           /* rqID in RCD for buffer from 2nd ring */
@@ -325,6 +340,7 @@ struct vmxnet3_rx_queue {
 	struct vmxnet3_rq_driver_stats  stats;
 	struct page_pool *page_pool;
 	struct xdp_rxq_info xdp_rxq;
+	u16                             rx_ts_desc_size;
 } ____cacheline_aligned;
 
 #define VMXNET3_DEVICE_MAX_TX_QUEUES 32
@@ -434,6 +450,10 @@ struct vmxnet3_adapter {
 	u16    rx_prod_offset;
 	u16    rx_prod2_offset;
 	struct bpf_prog __rcu *xdp_bpf_prog;
+	struct Vmxnet3_LatencyConf *latencyConf;
+	/* Size of buffer in the ts ring */
+	u16     tx_ts_desc_size;
+	u16     rx_ts_desc_size;
 };
 
 #define VMXNET3_WRITE_BAR0_REG(adapter, reg, val)  \
-- 
GitLab


From 2e5010fd0c43cb09310bd68efff3d534729a1022 Mon Sep 17 00:00:00 2001
From: Ronak Doshi <ronak.doshi@broadcom.com>
Date: Fri, 31 May 2024 12:30:48 -0700
Subject: [PATCH 826/950] vmxnet3: add command to allow disabling of offloads

This patch adds a new command to disable certain offloads. This
allows user to specify, using VM configuration, if certain offloads
need to be disabled.

Signed-off-by: Ronak Doshi <ronak.doshi@broadcom.com>
Acked-by: Guolin Yang <guolin.yang@broadcom.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20240531193050.4132-4-ronak.doshi@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/vmxnet3/vmxnet3_defs.h |  4 ++++
 drivers/net/vmxnet3/vmxnet3_drv.c  | 19 +++++++++++++++++++
 drivers/net/vmxnet3/vmxnet3_int.h  |  1 +
 3 files changed, 24 insertions(+)

diff --git a/drivers/net/vmxnet3/vmxnet3_defs.h b/drivers/net/vmxnet3/vmxnet3_defs.h
index dcf1cf8e7a864..5c5148768039c 100644
--- a/drivers/net/vmxnet3/vmxnet3_defs.h
+++ b/drivers/net/vmxnet3/vmxnet3_defs.h
@@ -126,6 +126,7 @@ enum {
 	VMXNET3_CMD_GET_MAX_CAPABILITIES,
 	VMXNET3_CMD_GET_DCR0_REG,
 	VMXNET3_CMD_GET_TSRING_DESC_SIZE,
+	VMXNET3_CMD_GET_DISABLED_OFFLOADS,
 };
 
 /*
@@ -912,4 +913,7 @@ struct Vmxnet3_DriverShared {
 /* when new capability is introduced, update VMXNET3_CAP_MAX */
 #define VMXNET3_CAP_MAX                            VMXNET3_CAP_VERSION_7_MAX
 
+#define VMXNET3_OFFLOAD_TSO         BIT(0)
+#define VMXNET3_OFFLOAD_LRO         BIT(1)
+
 #endif /* _VMXNET3_DEFS_H_ */
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index 71677115628bd..e26d223a659fd 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -3645,6 +3645,15 @@ static void
 vmxnet3_declare_features(struct vmxnet3_adapter *adapter)
 {
 	struct net_device *netdev = adapter->netdev;
+	unsigned long flags;
+
+	if (VMXNET3_VERSION_GE_9(adapter)) {
+		spin_lock_irqsave(&adapter->cmd_lock, flags);
+		VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD,
+				       VMXNET3_CMD_GET_DISABLED_OFFLOADS);
+		adapter->disabledOffloads = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_CMD);
+		spin_unlock_irqrestore(&adapter->cmd_lock, flags);
+	}
 
 	netdev->hw_features = NETIF_F_SG | NETIF_F_RXCSUM |
 		NETIF_F_HW_CSUM | NETIF_F_HW_VLAN_CTAG_TX |
@@ -3662,6 +3671,16 @@ vmxnet3_declare_features(struct vmxnet3_adapter *adapter)
 			NETIF_F_GSO_UDP_TUNNEL_CSUM;
 	}
 
+	if (adapter->disabledOffloads & VMXNET3_OFFLOAD_TSO) {
+		netdev->hw_features &= ~(NETIF_F_TSO | NETIF_F_TSO6);
+		netdev->hw_enc_features &= ~(NETIF_F_TSO | NETIF_F_TSO6);
+	}
+
+	if (adapter->disabledOffloads & VMXNET3_OFFLOAD_LRO) {
+		netdev->hw_features &= ~(NETIF_F_LRO);
+		netdev->hw_enc_features &= ~(NETIF_F_LRO);
+	}
+
 	if (VMXNET3_VERSION_GE_7(adapter)) {
 		unsigned long flags;
 
diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h
index 68358e71526cf..31e8db568db2b 100644
--- a/drivers/net/vmxnet3/vmxnet3_int.h
+++ b/drivers/net/vmxnet3/vmxnet3_int.h
@@ -454,6 +454,7 @@ struct vmxnet3_adapter {
 	/* Size of buffer in the ts ring */
 	u16     tx_ts_desc_size;
 	u16     rx_ts_desc_size;
+	u32     disabledOffloads;
 };
 
 #define VMXNET3_WRITE_BAR0_REG(adapter, reg, val)  \
-- 
GitLab


From 63587234d42ad59391cac3619bbb3c9a78c5afaa Mon Sep 17 00:00:00 2001
From: Ronak Doshi <ronak.doshi@broadcom.com>
Date: Fri, 31 May 2024 12:30:49 -0700
Subject: [PATCH 827/950] vmxnet3: update to version 9

With all vmxnet3 version 9 changes incorporated in the vmxnet3 driver,
the driver can configure emulation to run at vmxnet3 version 9, provided
the emulation advertises support for version 9.

Signed-off-by: Ronak Doshi <ronak.doshi@broadcom.com>
Acked-by: Guolin Yang <guolin.yang@broadcom.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20240531193050.4132-5-ronak.doshi@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/vmxnet3/vmxnet3_drv.c | 46 ++++++-------------------------
 drivers/net/vmxnet3/vmxnet3_int.h |  4 +--
 2 files changed, 11 insertions(+), 39 deletions(-)

diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index e26d223a659fd..b16449671b8be 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -3951,7 +3951,7 @@ vmxnet3_probe_device(struct pci_dev *pdev,
 	struct net_device *netdev;
 	struct vmxnet3_adapter *adapter;
 	u8 mac[ETH_ALEN];
-	int size;
+	int size, i;
 	int num_tx_queues;
 	int num_rx_queues;
 	int queues;
@@ -4018,42 +4018,14 @@ vmxnet3_probe_device(struct pci_dev *pdev,
 		goto err_alloc_pci;
 
 	ver = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_VRRS);
-	if (ver & (1 << VMXNET3_REV_7)) {
-		VMXNET3_WRITE_BAR1_REG(adapter,
-				       VMXNET3_REG_VRRS,
-				       1 << VMXNET3_REV_7);
-		adapter->version = VMXNET3_REV_7 + 1;
-	} else if (ver & (1 << VMXNET3_REV_6)) {
-		VMXNET3_WRITE_BAR1_REG(adapter,
-				       VMXNET3_REG_VRRS,
-				       1 << VMXNET3_REV_6);
-		adapter->version = VMXNET3_REV_6 + 1;
-	} else if (ver & (1 << VMXNET3_REV_5)) {
-		VMXNET3_WRITE_BAR1_REG(adapter,
-				       VMXNET3_REG_VRRS,
-				       1 << VMXNET3_REV_5);
-		adapter->version = VMXNET3_REV_5 + 1;
-	} else if (ver & (1 << VMXNET3_REV_4)) {
-		VMXNET3_WRITE_BAR1_REG(adapter,
-				       VMXNET3_REG_VRRS,
-				       1 << VMXNET3_REV_4);
-		adapter->version = VMXNET3_REV_4 + 1;
-	} else if (ver & (1 << VMXNET3_REV_3)) {
-		VMXNET3_WRITE_BAR1_REG(adapter,
-				       VMXNET3_REG_VRRS,
-				       1 << VMXNET3_REV_3);
-		adapter->version = VMXNET3_REV_3 + 1;
-	} else if (ver & (1 << VMXNET3_REV_2)) {
-		VMXNET3_WRITE_BAR1_REG(adapter,
-				       VMXNET3_REG_VRRS,
-				       1 << VMXNET3_REV_2);
-		adapter->version = VMXNET3_REV_2 + 1;
-	} else if (ver & (1 << VMXNET3_REV_1)) {
-		VMXNET3_WRITE_BAR1_REG(adapter,
-				       VMXNET3_REG_VRRS,
-				       1 << VMXNET3_REV_1);
-		adapter->version = VMXNET3_REV_1 + 1;
-	} else {
+	for (i = VMXNET3_REV_9; i >= VMXNET3_REV_1; i--) {
+		if (ver & (1 << i)) {
+			VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_VRRS, 1 << i);
+			adapter->version = i + 1;
+			break;
+		}
+	}
+	if (i < VMXNET3_REV_1) {
 		dev_err(&pdev->dev,
 			"Incompatible h/w version (0x%x) for adapter\n", ver);
 		err = -EBUSY;
diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h
index 31e8db568db2b..9f24d66dbb279 100644
--- a/drivers/net/vmxnet3/vmxnet3_int.h
+++ b/drivers/net/vmxnet3/vmxnet3_int.h
@@ -72,12 +72,12 @@
 /*
  * Version numbers
  */
-#define VMXNET3_DRIVER_VERSION_STRING   "1.7.0.0-k"
+#define VMXNET3_DRIVER_VERSION_STRING   "1.9.0.0-k"
 
 /* Each byte of this 32-bit integer encodes a version number in
  * VMXNET3_DRIVER_VERSION_STRING.
  */
-#define VMXNET3_DRIVER_VERSION_NUM      0x01070000
+#define VMXNET3_DRIVER_VERSION_NUM      0x01090000
 
 #if defined(CONFIG_PCI_MSI)
 	/* RSS only makes sense if MSI-X is supported. */
-- 
GitLab


From 323a359f9b077f382f4483023d096a4d316fd135 Mon Sep 17 00:00:00 2001
From: Karol Kolacinski <karol.kolacinski@intel.com>
Date: Tue, 4 Jun 2024 14:05:27 +0200
Subject: [PATCH 828/950] ptp: Fix error message on failed pin verification

On failed verification of PTP clock pin, error message prints channel
number instead of pin index after "pin", which is incorrect.

Fix error message by adding channel number to the message and printing
pin number instead of channel number.

Fixes: 6092315dfdec ("ptp: introduce programmable pins.")
Signed-off-by: Karol Kolacinski <karol.kolacinski@intel.com>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Link: https://lore.kernel.org/r/20240604120555.16643-1-karol.kolacinski@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/ptp/ptp_chardev.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/ptp/ptp_chardev.c b/drivers/ptp/ptp_chardev.c
index 7513018c9f9ac..2067b0120d083 100644
--- a/drivers/ptp/ptp_chardev.c
+++ b/drivers/ptp/ptp_chardev.c
@@ -85,7 +85,8 @@ int ptp_set_pinfunc(struct ptp_clock *ptp, unsigned int pin,
 	}
 
 	if (info->verify(info, pin, func, chan)) {
-		pr_err("driver cannot use function %u on pin %u\n", func, chan);
+		pr_err("driver cannot use function %u and channel %u on pin %u\n",
+		       func, chan, pin);
 		return -EOPNOTSUPP;
 	}
 
-- 
GitLab


From 955edd872baf29740b714ffa093886918fc9a47b Mon Sep 17 00:00:00 2001
From: Lukasz Majewski <lukma@denx.de>
Date: Mon, 3 Jun 2024 11:33:22 +0200
Subject: [PATCH 829/950] selftests: hsr: Extend the hsr_redbox.sh test to use
 fixed MAC addresses

Fixed MAC addresses help with debugging as last four bytes identify the
network namespace.

Moreover, it allows to mimic the real life setup with for example bridge
having the same MAC address on each port.

Signed-off-by: Lukasz Majewski <lukma@denx.de>
Link: https://lore.kernel.org/r/20240603093322.3150030-2-lukma@denx.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/hsr/hsr_redbox.sh | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/tools/testing/selftests/net/hsr/hsr_redbox.sh b/tools/testing/selftests/net/hsr/hsr_redbox.sh
index 1f36785347c0b..998103502d5d3 100755
--- a/tools/testing/selftests/net/hsr/hsr_redbox.sh
+++ b/tools/testing/selftests/net/hsr/hsr_redbox.sh
@@ -96,6 +96,21 @@ setup_hsr_interfaces()
 	ip -n "${ns4}" link set ns4eth1 up
 	ip -n "${ns5}" link set ns5eth1 up
 
+	ip -net "$ns1" link set address 00:11:22:00:01:01 dev ns1eth1
+	ip -net "$ns1" link set address 00:11:22:00:01:02 dev ns1eth2
+
+	ip -net "$ns2" link set address 00:11:22:00:02:01 dev ns2eth1
+	ip -net "$ns2" link set address 00:11:22:00:02:02 dev ns2eth2
+	ip -net "$ns2" link set address 00:11:22:00:02:03 dev ns2eth3
+
+	ip -net "$ns3" link set address 00:11:22:00:03:11 dev ns3eth1
+	ip -net "$ns3" link set address 00:11:22:00:03:11 dev ns3eth2
+	ip -net "$ns3" link set address 00:11:22:00:03:11 dev ns3eth3
+	ip -net "$ns3" link set address 00:11:22:00:03:11 dev ns3br1
+
+	ip -net "$ns4" link set address 00:11:22:00:04:01 dev ns4eth1
+	ip -net "$ns5" link set address 00:11:22:00:05:01 dev ns5eth1
+
 	ip -net "${ns1}" link add name hsr1 type hsr slave1 ns1eth1 slave2 ns1eth2 supervision 45 version ${HSRv} proto 0
 	ip -net "${ns2}" link add name hsr2 type hsr slave1 ns2eth1 slave2 ns2eth2 interlink ns2eth3 supervision 45 version ${HSRv} proto 0
 
-- 
GitLab


From ed20142ed68c2b8819120508bc029e84d13cfe63 Mon Sep 17 00:00:00 2001
From: Lukasz Majewski <lukma@denx.de>
Date: Mon, 3 Jun 2024 11:33:21 +0200
Subject: [PATCH 830/950] selftests: hsr: Extend the hsr_ping.sh test to use
 fixed MAC addresses

Fixed MAC addresses help with debugging as last four bytes identify the
network namespace.

Signed-off-by: Lukasz Majewski <lukma@denx.de>
Link: https://lore.kernel.org/r/20240603093322.3150030-1-lukma@denx.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/hsr/hsr_ping.sh | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/tools/testing/selftests/net/hsr/hsr_ping.sh b/tools/testing/selftests/net/hsr/hsr_ping.sh
index 3684b813b0f67..f5d207fc770ad 100755
--- a/tools/testing/selftests/net/hsr/hsr_ping.sh
+++ b/tools/testing/selftests/net/hsr/hsr_ping.sh
@@ -152,6 +152,15 @@ setup_hsr_interfaces()
 	ip -net "$ns3" addr add 100.64.0.3/24 dev hsr3
 	ip -net "$ns3" addr add dead:beef:1::3/64 dev hsr3 nodad
 
+	ip -net "$ns1" link set address 00:11:22:00:01:01 dev ns1eth1
+	ip -net "$ns1" link set address 00:11:22:00:01:02 dev ns1eth2
+
+	ip -net "$ns2" link set address 00:11:22:00:02:01 dev ns2eth1
+	ip -net "$ns2" link set address 00:11:22:00:02:02 dev ns2eth2
+
+	ip -net "$ns3" link set address 00:11:22:00:03:01 dev ns3eth1
+	ip -net "$ns3" link set address 00:11:22:00:03:02 dev ns3eth2
+
 	# All Links up
 	ip -net "$ns1" link set ns1eth1 up
 	ip -net "$ns1" link set ns1eth2 up
-- 
GitLab


From 03e4a092be8ce3de7c1baa7ae14e68b64e3ea644 Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Mon, 3 Jun 2024 14:42:30 -0700
Subject: [PATCH 831/950] ice: fix iteration of TLVs in Preserved Fields Area

The ice_get_pfa_module_tlv() function iterates over the Type-Length-Value
structures in the Preserved Fields Area (PFA) of the NVM. This is used by
the driver to access data such as the Part Board Assembly identifier.

The function uses simple logic to iterate over the PFA. First, the pointer
to the PFA in the NVM is read. Then the total length of the PFA is read
from the first word.

A pointer to the first TLV is initialized, and a simple loop iterates over
each TLV. The pointer is moved forward through the NVM until it exceeds the
PFA area.

The logic seems sound, but it is missing a key detail. The Preserved
Fields Area length includes one additional final word. This is documented
in the device data sheet as a dummy word which contains 0xFFFF. All NVMs
have this extra word.

If the driver tries to scan for a TLV that is not in the PFA, it will read
past the size of the PFA. It reads and interprets the last dummy word of
the PFA as a TLV with type 0xFFFF. It then reads the word following the PFA
as a length.

The PFA resides within the Shadow RAM portion of the NVM, which is
relatively small. All of its offsets are within a 16-bit size. The PFA
pointer and TLV pointer are stored by the driver as 16-bit values.

In almost all cases, the word following the PFA will be such that
interpreting it as a length will result in 16-bit arithmetic overflow. Once
overflowed, the new next_tlv value is now below the maximum offset of the
PFA. Thus, the driver will continue to iterate the data as TLVs. In the
worst case, the driver hits on a sequence of reads which loop back to
reading the same offsets in an endless loop.

To fix this, we need to correct the loop iteration check to account for
this extra word at the end of the PFA. This alone is sufficient to resolve
the known cases of this issue in the field. However, it is plausible that
an NVM could be misconfigured or have corrupt data which results in the
same kind of overflow. Protect against this by using check_add_overflow
when calculating both the maximum offset of the TLVs, and when calculating
the next_tlv offset at the end of each loop iteration. This ensures that
the driver will not get stuck in an infinite loop when scanning the PFA.

Fixes: e961b679fb0b ("ice: add board identifier info to devlink .info_get")
Co-developed-by: Paul Greenwalt <paul.greenwalt@intel.com>
Signed-off-by: Paul Greenwalt <paul.greenwalt@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20240603-net-2024-05-30-intel-net-fixes-v2-1-e3563aa89b0c@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/ice/ice_nvm.c | 28 ++++++++++++++++++------
 1 file changed, 21 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_nvm.c b/drivers/net/ethernet/intel/ice/ice_nvm.c
index 84eab92dc03cf..ea7cbdf8492d6 100644
--- a/drivers/net/ethernet/intel/ice/ice_nvm.c
+++ b/drivers/net/ethernet/intel/ice/ice_nvm.c
@@ -440,8 +440,7 @@ int
 ice_get_pfa_module_tlv(struct ice_hw *hw, u16 *module_tlv, u16 *module_tlv_len,
 		       u16 module_type)
 {
-	u16 pfa_len, pfa_ptr;
-	u16 next_tlv;
+	u16 pfa_len, pfa_ptr, next_tlv, max_tlv;
 	int status;
 
 	status = ice_read_sr_word(hw, ICE_SR_PFA_PTR, &pfa_ptr);
@@ -454,11 +453,23 @@ ice_get_pfa_module_tlv(struct ice_hw *hw, u16 *module_tlv, u16 *module_tlv_len,
 		ice_debug(hw, ICE_DBG_INIT, "Failed to read PFA length.\n");
 		return status;
 	}
+
+	/* The Preserved Fields Area contains a sequence of Type-Length-Value
+	 * structures which define its contents. The PFA length includes all
+	 * of the TLVs, plus the initial length word itself, *and* one final
+	 * word at the end after all of the TLVs.
+	 */
+	if (check_add_overflow(pfa_ptr, pfa_len - 1, &max_tlv)) {
+		dev_warn(ice_hw_to_dev(hw), "PFA starts at offset %u. PFA length of %u caused 16-bit arithmetic overflow.\n",
+			 pfa_ptr, pfa_len);
+		return -EINVAL;
+	}
+
 	/* Starting with first TLV after PFA length, iterate through the list
 	 * of TLVs to find the requested one.
 	 */
 	next_tlv = pfa_ptr + 1;
-	while (next_tlv < pfa_ptr + pfa_len) {
+	while (next_tlv < max_tlv) {
 		u16 tlv_sub_module_type;
 		u16 tlv_len;
 
@@ -482,10 +493,13 @@ ice_get_pfa_module_tlv(struct ice_hw *hw, u16 *module_tlv, u16 *module_tlv_len,
 			}
 			return -EINVAL;
 		}
-		/* Check next TLV, i.e. current TLV pointer + length + 2 words
-		 * (for current TLV's type and length)
-		 */
-		next_tlv = next_tlv + tlv_len + 2;
+
+		if (check_add_overflow(next_tlv, 2, &next_tlv) ||
+		    check_add_overflow(next_tlv, tlv_len, &next_tlv)) {
+			dev_warn(ice_hw_to_dev(hw), "TLV of type %u and length 0x%04x caused 16-bit arithmetic overflow. The PFA starts at 0x%04x and has length of 0x%04x\n",
+				 tlv_sub_module_type, tlv_len, pfa_ptr, pfa_len);
+			return -EINVAL;
+		}
 	}
 	/* Module does not exist */
 	return -ENOENT;
-- 
GitLab


From cfa747a66e5da34793ac08c26b814e7709613fab Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Mon, 3 Jun 2024 14:42:31 -0700
Subject: [PATCH 832/950] ice: fix reads from NVM Shadow RAM on E830 and E825-C
 devices

The ice driver reads data from the Shadow RAM portion of the NVM during
initialization, including data used to identify the NVM image and device,
such as the ETRACK ID used to populate devlink dev info fw.bundle.

Currently it is using a fixed offset defined by ICE_CSS_HEADER_LENGTH to
compute the appropriate offset. This worked fine for E810 and E822 devices
which both have CSS header length of 330 words.

Other devices, including both E825-C and E830 devices have different sizes
for their CSS header. The use of a hard coded value results in the driver
reading from the wrong block in the NVM when attempting to access the
Shadow RAM copy. This results in the driver reporting the fw.bundle as 0x0
in both the devlink dev info and ethtool -i output.

The first E830 support was introduced by commit ba20ecb1d1bb ("ice: Hook up
4 E830 devices by adding their IDs") and the first E825-C support was
introducted by commit f64e18944233 ("ice: introduce new E825C devices
family")

The NVM actually contains the CSS header length embedded in it. Remove the
hard coded value and replace it with logic to read the length from the NVM
directly. This is more resilient against all existing and future hardware,
vs looking up the expected values from a table. It ensures the driver will
read from the appropriate place when determining the ETRACK ID value used
for populating the fw.bundle_id and for reporting in ethtool -i.

The CSS header length for both the active and inactive flash bank is stored
in the ice_bank_info structure to avoid unnecessary duplicate work when
accessing multiple words of the Shadow RAM. Both banks are read in the
unlikely event that the header length is different for the NVM in the
inactive bank, rather than being different only by the overall device
family.

Fixes: ba20ecb1d1bb ("ice: Hook up 4 E830 devices by adding their IDs")
Co-developed-by: Paul Greenwalt <paul.greenwalt@intel.com>
Signed-off-by: Paul Greenwalt <paul.greenwalt@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20240603-net-2024-05-30-intel-net-fixes-v2-2-e3563aa89b0c@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/ice/ice_nvm.c  | 88 ++++++++++++++++++++++-
 drivers/net/ethernet/intel/ice/ice_type.h | 14 ++--
 2 files changed, 93 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_nvm.c b/drivers/net/ethernet/intel/ice/ice_nvm.c
index ea7cbdf8492d6..59e8879ac0598 100644
--- a/drivers/net/ethernet/intel/ice/ice_nvm.c
+++ b/drivers/net/ethernet/intel/ice/ice_nvm.c
@@ -374,11 +374,25 @@ ice_read_nvm_module(struct ice_hw *hw, enum ice_bank_select bank, u32 offset, u1
  *
  * Read the specified word from the copy of the Shadow RAM found in the
  * specified NVM module.
+ *
+ * Note that the Shadow RAM copy is always located after the CSS header, and
+ * is aligned to 64-byte (32-word) offsets.
  */
 static int
 ice_read_nvm_sr_copy(struct ice_hw *hw, enum ice_bank_select bank, u32 offset, u16 *data)
 {
-	return ice_read_nvm_module(hw, bank, ICE_NVM_SR_COPY_WORD_OFFSET + offset, data);
+	u32 sr_copy;
+
+	switch (bank) {
+	case ICE_ACTIVE_FLASH_BANK:
+		sr_copy = roundup(hw->flash.banks.active_css_hdr_len, 32);
+		break;
+	case ICE_INACTIVE_FLASH_BANK:
+		sr_copy = roundup(hw->flash.banks.inactive_css_hdr_len, 32);
+		break;
+	}
+
+	return ice_read_nvm_module(hw, bank, sr_copy + offset, data);
 }
 
 /**
@@ -1023,6 +1037,72 @@ static int ice_determine_active_flash_banks(struct ice_hw *hw)
 	return 0;
 }
 
+/**
+ * ice_get_nvm_css_hdr_len - Read the CSS header length from the NVM CSS header
+ * @hw: pointer to the HW struct
+ * @bank: whether to read from the active or inactive flash bank
+ * @hdr_len: storage for header length in words
+ *
+ * Read the CSS header length from the NVM CSS header and add the Authentication
+ * header size, and then convert to words.
+ *
+ * Return: zero on success, or a negative error code on failure.
+ */
+static int
+ice_get_nvm_css_hdr_len(struct ice_hw *hw, enum ice_bank_select bank,
+			u32 *hdr_len)
+{
+	u16 hdr_len_l, hdr_len_h;
+	u32 hdr_len_dword;
+	int status;
+
+	status = ice_read_nvm_module(hw, bank, ICE_NVM_CSS_HDR_LEN_L,
+				     &hdr_len_l);
+	if (status)
+		return status;
+
+	status = ice_read_nvm_module(hw, bank, ICE_NVM_CSS_HDR_LEN_H,
+				     &hdr_len_h);
+	if (status)
+		return status;
+
+	/* CSS header length is in DWORD, so convert to words and add
+	 * authentication header size
+	 */
+	hdr_len_dword = hdr_len_h << 16 | hdr_len_l;
+	*hdr_len = (hdr_len_dword * 2) + ICE_NVM_AUTH_HEADER_LEN;
+
+	return 0;
+}
+
+/**
+ * ice_determine_css_hdr_len - Discover CSS header length for the device
+ * @hw: pointer to the HW struct
+ *
+ * Determine the size of the CSS header at the start of the NVM module. This
+ * is useful for locating the Shadow RAM copy in the NVM, as the Shadow RAM is
+ * always located just after the CSS header.
+ *
+ * Return: zero on success, or a negative error code on failure.
+ */
+static int ice_determine_css_hdr_len(struct ice_hw *hw)
+{
+	struct ice_bank_info *banks = &hw->flash.banks;
+	int status;
+
+	status = ice_get_nvm_css_hdr_len(hw, ICE_ACTIVE_FLASH_BANK,
+					 &banks->active_css_hdr_len);
+	if (status)
+		return status;
+
+	status = ice_get_nvm_css_hdr_len(hw, ICE_INACTIVE_FLASH_BANK,
+					 &banks->inactive_css_hdr_len);
+	if (status)
+		return status;
+
+	return 0;
+}
+
 /**
  * ice_init_nvm - initializes NVM setting
  * @hw: pointer to the HW struct
@@ -1069,6 +1149,12 @@ int ice_init_nvm(struct ice_hw *hw)
 		return status;
 	}
 
+	status = ice_determine_css_hdr_len(hw);
+	if (status) {
+		ice_debug(hw, ICE_DBG_NVM, "Failed to determine Shadow RAM copy offsets.\n");
+		return status;
+	}
+
 	status = ice_get_nvm_ver_info(hw, ICE_ACTIVE_FLASH_BANK, &flash->nvm);
 	if (status) {
 		ice_debug(hw, ICE_DBG_INIT, "Failed to read NVM info.\n");
diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h
index f0796a93f4287..eef397e5baa07 100644
--- a/drivers/net/ethernet/intel/ice/ice_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_type.h
@@ -482,6 +482,8 @@ struct ice_bank_info {
 	u32 orom_size;				/* Size of OROM bank */
 	u32 netlist_ptr;			/* Pointer to 1st Netlist bank */
 	u32 netlist_size;			/* Size of Netlist bank */
+	u32 active_css_hdr_len;			/* Active CSS header length */
+	u32 inactive_css_hdr_len;		/* Inactive CSS header length */
 	enum ice_flash_bank nvm_bank;		/* Active NVM bank */
 	enum ice_flash_bank orom_bank;		/* Active OROM bank */
 	enum ice_flash_bank netlist_bank;	/* Active Netlist bank */
@@ -1087,17 +1089,13 @@ struct ice_aq_get_set_rss_lut_params {
 #define ICE_SR_SECTOR_SIZE_IN_WORDS	0x800
 
 /* CSS Header words */
+#define ICE_NVM_CSS_HDR_LEN_L			0x02
+#define ICE_NVM_CSS_HDR_LEN_H			0x03
 #define ICE_NVM_CSS_SREV_L			0x14
 #define ICE_NVM_CSS_SREV_H			0x15
 
-/* Length of CSS header section in words */
-#define ICE_CSS_HEADER_LENGTH			330
-
-/* Offset of Shadow RAM copy in the NVM bank area. */
-#define ICE_NVM_SR_COPY_WORD_OFFSET		roundup(ICE_CSS_HEADER_LENGTH, 32)
-
-/* Size in bytes of Option ROM trailer */
-#define ICE_NVM_OROM_TRAILER_LENGTH		(2 * ICE_CSS_HEADER_LENGTH)
+/* Length of Authentication header section in words */
+#define ICE_NVM_AUTH_HEADER_LEN			0x08
 
 /* The Link Topology Netlist section is stored as a series of words. It is
  * stored in the NVM as a TLV, with the first two words containing the type
-- 
GitLab


From adbf5a42341f6ea038d3626cd4437d9f0ad0b2dd Mon Sep 17 00:00:00 2001
From: Larysa Zaremba <larysa.zaremba@intel.com>
Date: Mon, 3 Jun 2024 14:42:32 -0700
Subject: [PATCH 833/950] ice: remove af_xdp_zc_qps bitmap

Referenced commit has introduced a bitmap to distinguish between ZC and
copy-mode AF_XDP queues, because xsk_get_pool_from_qid() does not do this
for us.

The bitmap would be especially useful when restoring previous state after
rebuild, if only it was not reallocated in the process. This leads to e.g.
xdpsock dying after changing number of queues.

Instead of preserving the bitmap during the rebuild, remove it completely
and distinguish between ZC and copy-mode queues based on the presence of
a device associated with the pool.

Fixes: e102db780e1c ("ice: track AF_XDP ZC enabled queues in bitmap")
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Chandan Kumar Rout <chandanx.rout@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20240603-net-2024-05-30-intel-net-fixes-v2-3-e3563aa89b0c@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/ice/ice.h     | 32 ++++++++++++++++--------
 drivers/net/ethernet/intel/ice/ice_lib.c |  8 ------
 drivers/net/ethernet/intel/ice/ice_xsk.c | 13 +++++-----
 3 files changed, 27 insertions(+), 26 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 6ad8002b22e14..5e51cb84b6006 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -409,7 +409,6 @@ struct ice_vsi {
 	struct ice_tc_cfg tc_cfg;
 	struct bpf_prog *xdp_prog;
 	struct ice_tx_ring **xdp_rings;	 /* XDP ring array */
-	unsigned long *af_xdp_zc_qps;	 /* tracks AF_XDP ZC enabled qps */
 	u16 num_xdp_txq;		 /* Used XDP queues */
 	u8 xdp_mapping_mode;		 /* ICE_MAP_MODE_[CONTIG|SCATTER] */
 
@@ -746,6 +745,25 @@ static inline void ice_set_ring_xdp(struct ice_tx_ring *ring)
 	ring->flags |= ICE_TX_FLAGS_RING_XDP;
 }
 
+/**
+ * ice_get_xp_from_qid - get ZC XSK buffer pool bound to a queue ID
+ * @vsi: pointer to VSI
+ * @qid: index of a queue to look at XSK buff pool presence
+ *
+ * Return: A pointer to xsk_buff_pool structure if there is a buffer pool
+ * attached and configured as zero-copy, NULL otherwise.
+ */
+static inline struct xsk_buff_pool *ice_get_xp_from_qid(struct ice_vsi *vsi,
+							u16 qid)
+{
+	struct xsk_buff_pool *pool = xsk_get_pool_from_qid(vsi->netdev, qid);
+
+	if (!ice_is_xdp_ena_vsi(vsi))
+		return NULL;
+
+	return (pool && pool->dev) ? pool : NULL;
+}
+
 /**
  * ice_xsk_pool - get XSK buffer pool bound to a ring
  * @ring: Rx ring to use
@@ -758,10 +776,7 @@ static inline struct xsk_buff_pool *ice_xsk_pool(struct ice_rx_ring *ring)
 	struct ice_vsi *vsi = ring->vsi;
 	u16 qid = ring->q_index;
 
-	if (!ice_is_xdp_ena_vsi(vsi) || !test_bit(qid, vsi->af_xdp_zc_qps))
-		return NULL;
-
-	return xsk_get_pool_from_qid(vsi->netdev, qid);
+	return ice_get_xp_from_qid(vsi, qid);
 }
 
 /**
@@ -786,12 +801,7 @@ static inline void ice_tx_xsk_pool(struct ice_vsi *vsi, u16 qid)
 	if (!ring)
 		return;
 
-	if (!ice_is_xdp_ena_vsi(vsi) || !test_bit(qid, vsi->af_xdp_zc_qps)) {
-		ring->xsk_pool = NULL;
-		return;
-	}
-
-	ring->xsk_pool = xsk_get_pool_from_qid(vsi->netdev, qid);
+	ring->xsk_pool = ice_get_xp_from_qid(vsi, qid);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 5371e91f6bbb4..c0a7ff6c7e877 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -114,14 +114,8 @@ static int ice_vsi_alloc_arrays(struct ice_vsi *vsi)
 	if (!vsi->q_vectors)
 		goto err_vectors;
 
-	vsi->af_xdp_zc_qps = bitmap_zalloc(max_t(int, vsi->alloc_txq, vsi->alloc_rxq), GFP_KERNEL);
-	if (!vsi->af_xdp_zc_qps)
-		goto err_zc_qps;
-
 	return 0;
 
-err_zc_qps:
-	devm_kfree(dev, vsi->q_vectors);
 err_vectors:
 	devm_kfree(dev, vsi->rxq_map);
 err_rxq_map:
@@ -309,8 +303,6 @@ static void ice_vsi_free_arrays(struct ice_vsi *vsi)
 
 	dev = ice_pf_to_dev(pf);
 
-	bitmap_free(vsi->af_xdp_zc_qps);
-	vsi->af_xdp_zc_qps = NULL;
 	/* free the ring and vector containers */
 	devm_kfree(dev, vsi->q_vectors);
 	vsi->q_vectors = NULL;
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index 7541f223bf4f6..a65955eb23c0b 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -269,7 +269,6 @@ static int ice_xsk_pool_disable(struct ice_vsi *vsi, u16 qid)
 	if (!pool)
 		return -EINVAL;
 
-	clear_bit(qid, vsi->af_xdp_zc_qps);
 	xsk_pool_dma_unmap(pool, ICE_RX_DMA_ATTR);
 
 	return 0;
@@ -300,8 +299,6 @@ ice_xsk_pool_enable(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid)
 	if (err)
 		return err;
 
-	set_bit(qid, vsi->af_xdp_zc_qps);
-
 	return 0;
 }
 
@@ -349,11 +346,13 @@ ice_realloc_rx_xdp_bufs(struct ice_rx_ring *rx_ring, bool pool_present)
 int ice_realloc_zc_buf(struct ice_vsi *vsi, bool zc)
 {
 	struct ice_rx_ring *rx_ring;
-	unsigned long q;
+	uint i;
+
+	ice_for_each_rxq(vsi, i) {
+		rx_ring = vsi->rx_rings[i];
+		if (!rx_ring->xsk_pool)
+			continue;
 
-	for_each_set_bit(q, vsi->af_xdp_zc_qps,
-			 max_t(int, vsi->alloc_txq, vsi->alloc_rxq)) {
-		rx_ring = vsi->rx_rings[q];
 		if (ice_realloc_rx_xdp_bufs(rx_ring, zc))
 			return -ENOMEM;
 	}
-- 
GitLab


From 744d197162c2070a6045a71e2666ed93a57cc65d Mon Sep 17 00:00:00 2001
From: Larysa Zaremba <larysa.zaremba@intel.com>
Date: Mon, 3 Jun 2024 14:42:33 -0700
Subject: [PATCH 834/950] ice: add flag to distinguish reset from .ndo_bpf in
 XDP rings config

Commit 6624e780a577 ("ice: split ice_vsi_setup into smaller functions")
has placed ice_vsi_free_q_vectors() after ice_destroy_xdp_rings() in
the rebuild process. The behaviour of the XDP rings config functions is
context-dependent, so the change of order has led to
ice_destroy_xdp_rings() doing additional work and removing XDP prog, when
it was supposed to be preserved.

Also, dependency on the PF state reset flags creates an additional,
fortunately less common problem:

* PFR is requested e.g. by tx_timeout handler
* .ndo_bpf() is asked to delete the program, calls ice_destroy_xdp_rings(),
  but reset flag is set, so rings are destroyed without deleting the
  program
* ice_vsi_rebuild tries to delete non-existent XDP rings, because the
  program is still on the VSI
* system crashes

With a similar race, when requested to attach a program,
ice_prepare_xdp_rings() can actually skip setting the program in the VSI
and nevertheless report success.

Instead of reverting to the old order of function calls, add an enum
argument to both ice_prepare_xdp_rings() and ice_destroy_xdp_rings() in
order to distinguish between calls from rebuild and .ndo_bpf().

Fixes: efc2214b6047 ("ice: Add support for XDP")
Reviewed-by: Igor Bagnucki <igor.bagnucki@intel.com>
Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Chandan Kumar Rout <chandanx.rout@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20240603-net-2024-05-30-intel-net-fixes-v2-4-e3563aa89b0c@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/ice/ice.h      | 11 +++++++++--
 drivers/net/ethernet/intel/ice/ice_lib.c  |  5 +++--
 drivers/net/ethernet/intel/ice/ice_main.c | 22 ++++++++++++----------
 3 files changed, 24 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 5e51cb84b6006..a5de6ef9c07ef 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -930,9 +930,16 @@ int ice_down(struct ice_vsi *vsi);
 int ice_down_up(struct ice_vsi *vsi);
 int ice_vsi_cfg_lan(struct ice_vsi *vsi);
 struct ice_vsi *ice_lb_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi);
+
+enum ice_xdp_cfg {
+	ICE_XDP_CFG_FULL,	/* Fully apply new config in .ndo_bpf() */
+	ICE_XDP_CFG_PART,	/* Save/use part of config in VSI rebuild */
+};
+
 int ice_vsi_determine_xdp_res(struct ice_vsi *vsi);
-int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog);
-int ice_destroy_xdp_rings(struct ice_vsi *vsi);
+int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog,
+			  enum ice_xdp_cfg cfg_type);
+int ice_destroy_xdp_rings(struct ice_vsi *vsi, enum ice_xdp_cfg cfg_type);
 int
 ice_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 	     u32 flags);
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index c0a7ff6c7e877..dd8b374823eec 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -2285,7 +2285,8 @@ static int ice_vsi_cfg_def(struct ice_vsi *vsi)
 			ret = ice_vsi_determine_xdp_res(vsi);
 			if (ret)
 				goto unroll_vector_base;
-			ret = ice_prepare_xdp_rings(vsi, vsi->xdp_prog);
+			ret = ice_prepare_xdp_rings(vsi, vsi->xdp_prog,
+						    ICE_XDP_CFG_PART);
 			if (ret)
 				goto unroll_vector_base;
 		}
@@ -2429,7 +2430,7 @@ void ice_vsi_decfg(struct ice_vsi *vsi)
 		/* return value check can be skipped here, it always returns
 		 * 0 if reset is in progress
 		 */
-		ice_destroy_xdp_rings(vsi);
+		ice_destroy_xdp_rings(vsi, ICE_XDP_CFG_PART);
 
 	ice_vsi_clear_rings(vsi);
 	ice_vsi_free_q_vectors(vsi);
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index f60c022f79609..2a270aacd24a9 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -2711,10 +2711,12 @@ static void ice_vsi_assign_bpf_prog(struct ice_vsi *vsi, struct bpf_prog *prog)
  * ice_prepare_xdp_rings - Allocate, configure and setup Tx rings for XDP
  * @vsi: VSI to bring up Tx rings used by XDP
  * @prog: bpf program that will be assigned to VSI
+ * @cfg_type: create from scratch or restore the existing configuration
  *
  * Return 0 on success and negative value on error
  */
-int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog)
+int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog,
+			  enum ice_xdp_cfg cfg_type)
 {
 	u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 };
 	int xdp_rings_rem = vsi->num_xdp_txq;
@@ -2790,7 +2792,7 @@ int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog)
 	 * taken into account at the end of ice_vsi_rebuild, where
 	 * ice_cfg_vsi_lan is being called
 	 */
-	if (ice_is_reset_in_progress(pf->state))
+	if (cfg_type == ICE_XDP_CFG_PART)
 		return 0;
 
 	/* tell the Tx scheduler that right now we have
@@ -2842,22 +2844,21 @@ err_map_xdp:
 /**
  * ice_destroy_xdp_rings - undo the configuration made by ice_prepare_xdp_rings
  * @vsi: VSI to remove XDP rings
+ * @cfg_type: disable XDP permanently or allow it to be restored later
  *
  * Detach XDP rings from irq vectors, clean up the PF bitmap and free
  * resources
  */
-int ice_destroy_xdp_rings(struct ice_vsi *vsi)
+int ice_destroy_xdp_rings(struct ice_vsi *vsi, enum ice_xdp_cfg cfg_type)
 {
 	u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 };
 	struct ice_pf *pf = vsi->back;
 	int i, v_idx;
 
 	/* q_vectors are freed in reset path so there's no point in detaching
-	 * rings; in case of rebuild being triggered not from reset bits
-	 * in pf->state won't be set, so additionally check first q_vector
-	 * against NULL
+	 * rings
 	 */
-	if (ice_is_reset_in_progress(pf->state) || !vsi->q_vectors[0])
+	if (cfg_type == ICE_XDP_CFG_PART)
 		goto free_qmap;
 
 	ice_for_each_q_vector(vsi, v_idx) {
@@ -2898,7 +2899,7 @@ free_qmap:
 	if (static_key_enabled(&ice_xdp_locking_key))
 		static_branch_dec(&ice_xdp_locking_key);
 
-	if (ice_is_reset_in_progress(pf->state) || !vsi->q_vectors[0])
+	if (cfg_type == ICE_XDP_CFG_PART)
 		return 0;
 
 	ice_vsi_assign_bpf_prog(vsi, NULL);
@@ -3009,7 +3010,8 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog,
 		if (xdp_ring_err) {
 			NL_SET_ERR_MSG_MOD(extack, "Not enough Tx resources for XDP");
 		} else {
-			xdp_ring_err = ice_prepare_xdp_rings(vsi, prog);
+			xdp_ring_err = ice_prepare_xdp_rings(vsi, prog,
+							     ICE_XDP_CFG_FULL);
 			if (xdp_ring_err)
 				NL_SET_ERR_MSG_MOD(extack, "Setting up XDP Tx resources failed");
 		}
@@ -3020,7 +3022,7 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog,
 			NL_SET_ERR_MSG_MOD(extack, "Setting up XDP Rx resources failed");
 	} else if (ice_is_xdp_ena_vsi(vsi) && !prog) {
 		xdp_features_clear_redirect_target(vsi->netdev);
-		xdp_ring_err = ice_destroy_xdp_rings(vsi);
+		xdp_ring_err = ice_destroy_xdp_rings(vsi, ICE_XDP_CFG_FULL);
 		if (xdp_ring_err)
 			NL_SET_ERR_MSG_MOD(extack, "Freeing XDP Tx resources failed");
 		/* reallocate Rx queues that were used for zero-copy */
-- 
GitLab


From f3df4044254c98128890b512bf19cc05588f1fe5 Mon Sep 17 00:00:00 2001
From: Larysa Zaremba <larysa.zaremba@intel.com>
Date: Mon, 3 Jun 2024 14:42:34 -0700
Subject: [PATCH 835/950] ice: map XDP queues to vectors in
 ice_vsi_map_rings_to_vectors()

ice_pf_dcb_recfg() re-maps queues to vectors with
ice_vsi_map_rings_to_vectors(), which does not restore the previous
state for XDP queues. This leads to no AF_XDP traffic after rebuild.

Map XDP queues to vectors in ice_vsi_map_rings_to_vectors().
Also, move the code around, so XDP queues are mapped independently only
through .ndo_bpf().

Fixes: 6624e780a577 ("ice: split ice_vsi_setup into smaller functions")
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Chandan Kumar Rout <chandanx.rout@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20240603-net-2024-05-30-intel-net-fixes-v2-5-e3563aa89b0c@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/ice/ice.h      |  1 +
 drivers/net/ethernet/intel/ice/ice_base.c |  3 +
 drivers/net/ethernet/intel/ice/ice_lib.c  | 14 ++--
 drivers/net/ethernet/intel/ice/ice_main.c | 96 ++++++++++++++---------
 4 files changed, 68 insertions(+), 46 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index a5de6ef9c07ef..99a75a59078ef 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -940,6 +940,7 @@ int ice_vsi_determine_xdp_res(struct ice_vsi *vsi);
 int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog,
 			  enum ice_xdp_cfg cfg_type);
 int ice_destroy_xdp_rings(struct ice_vsi *vsi, enum ice_xdp_cfg cfg_type);
+void ice_map_xdp_rings(struct ice_vsi *vsi);
 int
 ice_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 	     u32 flags);
diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index 687f6cb2b917a..5d396c1a77314 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -842,6 +842,9 @@ void ice_vsi_map_rings_to_vectors(struct ice_vsi *vsi)
 		}
 		rx_rings_rem -= rx_rings_per_v;
 	}
+
+	if (ice_is_xdp_ena_vsi(vsi))
+		ice_map_xdp_rings(vsi);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index dd8b374823eec..7629b0190578b 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -2274,13 +2274,6 @@ static int ice_vsi_cfg_def(struct ice_vsi *vsi)
 		if (ret)
 			goto unroll_vector_base;
 
-		ice_vsi_map_rings_to_vectors(vsi);
-
-		/* Associate q_vector rings to napi */
-		ice_vsi_set_napi_queues(vsi);
-
-		vsi->stat_offsets_loaded = false;
-
 		if (ice_is_xdp_ena_vsi(vsi)) {
 			ret = ice_vsi_determine_xdp_res(vsi);
 			if (ret)
@@ -2291,6 +2284,13 @@ static int ice_vsi_cfg_def(struct ice_vsi *vsi)
 				goto unroll_vector_base;
 		}
 
+		ice_vsi_map_rings_to_vectors(vsi);
+
+		/* Associate q_vector rings to napi */
+		ice_vsi_set_napi_queues(vsi);
+
+		vsi->stat_offsets_loaded = false;
+
 		/* ICE_VSI_CTRL does not need RSS so skip RSS processing */
 		if (vsi->type != ICE_VSI_CTRL)
 			/* Do not exit if configuring RSS had an issue, at
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 2a270aacd24a9..1b61ca3a6eb6e 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -2707,6 +2707,60 @@ static void ice_vsi_assign_bpf_prog(struct ice_vsi *vsi, struct bpf_prog *prog)
 		bpf_prog_put(old_prog);
 }
 
+static struct ice_tx_ring *ice_xdp_ring_from_qid(struct ice_vsi *vsi, int qid)
+{
+	struct ice_q_vector *q_vector;
+	struct ice_tx_ring *ring;
+
+	if (static_key_enabled(&ice_xdp_locking_key))
+		return vsi->xdp_rings[qid % vsi->num_xdp_txq];
+
+	q_vector = vsi->rx_rings[qid]->q_vector;
+	ice_for_each_tx_ring(ring, q_vector->tx)
+		if (ice_ring_is_xdp(ring))
+			return ring;
+
+	return NULL;
+}
+
+/**
+ * ice_map_xdp_rings - Map XDP rings to interrupt vectors
+ * @vsi: the VSI with XDP rings being configured
+ *
+ * Map XDP rings to interrupt vectors and perform the configuration steps
+ * dependent on the mapping.
+ */
+void ice_map_xdp_rings(struct ice_vsi *vsi)
+{
+	int xdp_rings_rem = vsi->num_xdp_txq;
+	int v_idx, q_idx;
+
+	/* follow the logic from ice_vsi_map_rings_to_vectors */
+	ice_for_each_q_vector(vsi, v_idx) {
+		struct ice_q_vector *q_vector = vsi->q_vectors[v_idx];
+		int xdp_rings_per_v, q_id, q_base;
+
+		xdp_rings_per_v = DIV_ROUND_UP(xdp_rings_rem,
+					       vsi->num_q_vectors - v_idx);
+		q_base = vsi->num_xdp_txq - xdp_rings_rem;
+
+		for (q_id = q_base; q_id < (q_base + xdp_rings_per_v); q_id++) {
+			struct ice_tx_ring *xdp_ring = vsi->xdp_rings[q_id];
+
+			xdp_ring->q_vector = q_vector;
+			xdp_ring->next = q_vector->tx.tx_ring;
+			q_vector->tx.tx_ring = xdp_ring;
+		}
+		xdp_rings_rem -= xdp_rings_per_v;
+	}
+
+	ice_for_each_rxq(vsi, q_idx) {
+		vsi->rx_rings[q_idx]->xdp_ring = ice_xdp_ring_from_qid(vsi,
+								       q_idx);
+		ice_tx_xsk_pool(vsi, q_idx);
+	}
+}
+
 /**
  * ice_prepare_xdp_rings - Allocate, configure and setup Tx rings for XDP
  * @vsi: VSI to bring up Tx rings used by XDP
@@ -2719,7 +2773,6 @@ int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog,
 			  enum ice_xdp_cfg cfg_type)
 {
 	u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 };
-	int xdp_rings_rem = vsi->num_xdp_txq;
 	struct ice_pf *pf = vsi->back;
 	struct ice_qs_cfg xdp_qs_cfg = {
 		.qs_mutex = &pf->avail_q_mutex,
@@ -2732,8 +2785,7 @@ int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog,
 		.mapping_mode = ICE_VSI_MAP_CONTIG
 	};
 	struct device *dev;
-	int i, v_idx;
-	int status;
+	int status, i;
 
 	dev = ice_pf_to_dev(pf);
 	vsi->xdp_rings = devm_kcalloc(dev, vsi->num_xdp_txq,
@@ -2752,42 +2804,6 @@ int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog,
 	if (ice_xdp_alloc_setup_rings(vsi))
 		goto clear_xdp_rings;
 
-	/* follow the logic from ice_vsi_map_rings_to_vectors */
-	ice_for_each_q_vector(vsi, v_idx) {
-		struct ice_q_vector *q_vector = vsi->q_vectors[v_idx];
-		int xdp_rings_per_v, q_id, q_base;
-
-		xdp_rings_per_v = DIV_ROUND_UP(xdp_rings_rem,
-					       vsi->num_q_vectors - v_idx);
-		q_base = vsi->num_xdp_txq - xdp_rings_rem;
-
-		for (q_id = q_base; q_id < (q_base + xdp_rings_per_v); q_id++) {
-			struct ice_tx_ring *xdp_ring = vsi->xdp_rings[q_id];
-
-			xdp_ring->q_vector = q_vector;
-			xdp_ring->next = q_vector->tx.tx_ring;
-			q_vector->tx.tx_ring = xdp_ring;
-		}
-		xdp_rings_rem -= xdp_rings_per_v;
-	}
-
-	ice_for_each_rxq(vsi, i) {
-		if (static_key_enabled(&ice_xdp_locking_key)) {
-			vsi->rx_rings[i]->xdp_ring = vsi->xdp_rings[i % vsi->num_xdp_txq];
-		} else {
-			struct ice_q_vector *q_vector = vsi->rx_rings[i]->q_vector;
-			struct ice_tx_ring *ring;
-
-			ice_for_each_tx_ring(ring, q_vector->tx) {
-				if (ice_ring_is_xdp(ring)) {
-					vsi->rx_rings[i]->xdp_ring = ring;
-					break;
-				}
-			}
-		}
-		ice_tx_xsk_pool(vsi, i);
-	}
-
 	/* omit the scheduler update if in reset path; XDP queues will be
 	 * taken into account at the end of ice_vsi_rebuild, where
 	 * ice_cfg_vsi_lan is being called
@@ -2795,6 +2811,8 @@ int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog,
 	if (cfg_type == ICE_XDP_CFG_PART)
 		return 0;
 
+	ice_map_xdp_rings(vsi);
+
 	/* tell the Tx scheduler that right now we have
 	 * additional queues
 	 */
-- 
GitLab


From 7d67d11fbe194f71298263f48e33ae2afa38197e Mon Sep 17 00:00:00 2001
From: Sasha Neftin <sasha.neftin@intel.com>
Date: Mon, 3 Jun 2024 14:42:35 -0700
Subject: [PATCH 836/950] igc: Fix Energy Efficient Ethernet support
 declaration

The commit 01cf893bf0f4 ("net: intel: i40e/igc: Remove setting Autoneg in
EEE capabilities") removed SUPPORTED_Autoneg field but left inappropriate
ethtool_keee structure initialization. When "ethtool --show <device>"
(get_eee) invoke, the 'ethtool_keee' structure was accidentally overridden.
Remove the 'ethtool_keee' overriding and add EEE declaration as per IEEE
specification that allows reporting Energy Efficient Ethernet capabilities.

Examples:
Before fix:
ethtool --show-eee enp174s0
EEE settings for enp174s0:
	EEE status: not supported

After fix:
EEE settings for enp174s0:
	EEE status: disabled
	Tx LPI: disabled
	Supported EEE link modes:  100baseT/Full
	                           1000baseT/Full
	                           2500baseT/Full

Fixes: 01cf893bf0f4 ("net: intel: i40e/igc: Remove setting Autoneg in EEE capabilities")
Suggested-by: Dima Ruinskiy <dima.ruinskiy@intel.com>
Signed-off-by: Sasha Neftin <sasha.neftin@intel.com>
Tested-by: Naama Meir <naamax.meir@linux.intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20240603-net-2024-05-30-intel-net-fixes-v2-6-e3563aa89b0c@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/igc/igc_ethtool.c | 9 +++++++--
 drivers/net/ethernet/intel/igc/igc_main.c    | 4 ++++
 2 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c
index f2c4f1966bb04..0cd2bd695db1d 100644
--- a/drivers/net/ethernet/intel/igc/igc_ethtool.c
+++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c
@@ -1629,12 +1629,17 @@ static int igc_ethtool_get_eee(struct net_device *netdev,
 	struct igc_hw *hw = &adapter->hw;
 	u32 eeer;
 
+	linkmode_set_bit(ETHTOOL_LINK_MODE_2500baseT_Full_BIT,
+			 edata->supported);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
+			 edata->supported);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT,
+			 edata->supported);
+
 	if (hw->dev_spec._base.eee_enable)
 		mii_eee_cap1_mod_linkmode_t(edata->advertised,
 					    adapter->eee_advert);
 
-	*edata = adapter->eee;
-
 	eeer = rd32(IGC_EEER);
 
 	/* EEE status on negotiated link */
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 12f004f46082c..305e05294a265 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -12,6 +12,7 @@
 #include <linux/bpf_trace.h>
 #include <net/xdp_sock_drv.h>
 #include <linux/pci.h>
+#include <linux/mdio.h>
 
 #include <net/ipv6.h>
 
@@ -4975,6 +4976,9 @@ void igc_up(struct igc_adapter *adapter)
 	/* start the watchdog. */
 	hw->mac.get_link_status = true;
 	schedule_work(&adapter->watchdog_task);
+
+	adapter->eee_advert = MDIO_EEE_100TX | MDIO_EEE_1000T |
+			      MDIO_EEE_2_5GT;
 }
 
 /**
-- 
GitLab


From 4e92d247418c36ed35e9d98b153637828f9882a3 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@nvidia.com>
Date: Tue, 4 Jun 2024 00:22:06 +0300
Subject: [PATCH 837/950] net/mlx5e: SHAMPO, Use net_prefetch API

Let the SHAMPO functions use the net-specific prefetch API,
similar to all other usages.

Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://lore.kernel.org/r/20240603212219.1037656-2-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index b5333da20e8a7..369d101bf03c7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -2212,8 +2212,8 @@ mlx5e_skb_from_cqe_shampo(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
 	if (likely(frag_size <= BIT(MLX5E_SHAMPO_LOG_MAX_HEADER_ENTRY_SIZE))) {
 		/* build SKB around header */
 		dma_sync_single_range_for_cpu(rq->pdev, head->addr, 0, frag_size, rq->buff.map_dir);
-		prefetchw(hdr);
-		prefetch(data);
+		net_prefetchw(hdr);
+		net_prefetch(data);
 		skb = mlx5e_build_linear_skb(rq, hdr, frag_size, rx_headroom, head_size, 0);
 
 		if (unlikely(!skb))
@@ -2230,7 +2230,7 @@ mlx5e_skb_from_cqe_shampo(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
 			return NULL;
 		}
 
-		prefetchw(skb->data);
+		net_prefetchw(skb->data);
 		mlx5e_copy_skb_header(rq, skb, head->frag_page->page, head->addr,
 				      head_offset + rx_headroom,
 				      rx_headroom, head_size);
-- 
GitLab


From 70bd03b89f20b9bbe51a7f73c4950565a17a45f7 Mon Sep 17 00:00:00 2001
From: Dragos Tatulea <dtatulea@nvidia.com>
Date: Tue, 4 Jun 2024 00:22:07 +0300
Subject: [PATCH 838/950] net/mlx5e: SHAMPO, Fix incorrect page release

Under the following conditions:
1) No skb created yet
2) header_size == 0 (no SHAMPO header)
3) header_index + 1 % MLX5E_SHAMPO_WQ_HEADER_PER_PAGE == 0 (this is the
   last page fragment of a SHAMPO header page)

a new skb is formed with a page that is NOT a SHAMPO header page (it
is a regular data page). Further down in the same function
(mlx5e_handle_rx_cqe_mpwrq_shampo()), a SHAMPO header page from
header_index is released. This is wrong and it leads to SHAMPO header
pages being released more than once.

Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://lore.kernel.org/r/20240603212219.1037656-3-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 369d101bf03c7..1ddfa00f923fb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -2369,7 +2369,8 @@ static void mlx5e_handle_rx_cqe_mpwrq_shampo(struct mlx5e_rq *rq, struct mlx5_cq
 	if (flush)
 		mlx5e_shampo_flush_skb(rq, cqe, match);
 free_hd_entry:
-	mlx5e_free_rx_shampo_hd_entry(rq, header_index);
+	if (likely(head_size))
+		mlx5e_free_rx_shampo_hd_entry(rq, header_index);
 mpwrq_cqe_out:
 	if (likely(wi->consumed_strides < rq->mpwqe.num_strides))
 		return;
-- 
GitLab


From fba8334721e266f92079632598e46e5f89082f30 Mon Sep 17 00:00:00 2001
From: Dragos Tatulea <dtatulea@nvidia.com>
Date: Tue, 4 Jun 2024 00:22:08 +0300
Subject: [PATCH 839/950] net/mlx5e: SHAMPO, Fix invalid WQ linked list unlink

When all the strides in a WQE have been consumed, the WQE is unlinked
from the WQ linked list (mlx5_wq_ll_pop()). For SHAMPO, it is possible
to receive CQEs with 0 consumed strides for the same WQE even after the
WQE is fully consumed and unlinked. This triggers an additional unlink
for the same wqe which corrupts the linked list.

Fix this scenario by accepting 0 sized consumed strides without
unlinking the WQE again.

Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://lore.kernel.org/r/20240603212219.1037656-4-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 1ddfa00f923fb..b3ef0dd237298 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -2375,6 +2375,9 @@ mpwrq_cqe_out:
 	if (likely(wi->consumed_strides < rq->mpwqe.num_strides))
 		return;
 
+	if (unlikely(!cstrides))
+		return;
+
 	wq  = &rq->mpwqe.wq;
 	wqe = mlx5_wq_ll_get_wqe(wq, wqe_id);
 	mlx5_wq_ll_pop(wq, cqe->wqe_id, &wqe->next.next_wqe_index);
-- 
GitLab


From a64bbd8c286fa67319df73ce842e3f6c7b08b6f6 Mon Sep 17 00:00:00 2001
From: Dragos Tatulea <dtatulea@nvidia.com>
Date: Tue, 4 Jun 2024 00:22:09 +0300
Subject: [PATCH 840/950] net/mlx5e: SHAMPO, Fix FCS config when HW GRO on

For the following scenario:

ethtool --features eth3 rx-gro-hw on
ethtool --features eth3 rx-fcs on
ethtool --features eth3 rx-fcs off

... there is a firmware error because the driver enables HW GRO first
while FCS is still enabled.

This patch fixes this by swapping the order of HW GRO and FCS for this
specific case. Take LRO into consideration as well for consistency.

Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://lore.kernel.org/r/20240603212219.1037656-5-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index c53c99dde5587..d0808dbe69d34 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -4259,13 +4259,19 @@ int mlx5e_set_features(struct net_device *netdev, netdev_features_t features)
 #define MLX5E_HANDLE_FEATURE(feature, handler) \
 	mlx5e_handle_feature(netdev, &oper_features, feature, handler)
 
-	err |= MLX5E_HANDLE_FEATURE(NETIF_F_LRO, set_feature_lro);
-	err |= MLX5E_HANDLE_FEATURE(NETIF_F_GRO_HW, set_feature_hw_gro);
+	if (features & (NETIF_F_GRO_HW | NETIF_F_LRO)) {
+		err |= MLX5E_HANDLE_FEATURE(NETIF_F_RXFCS, set_feature_rx_fcs);
+		err |= MLX5E_HANDLE_FEATURE(NETIF_F_LRO, set_feature_lro);
+		err |= MLX5E_HANDLE_FEATURE(NETIF_F_GRO_HW, set_feature_hw_gro);
+	} else {
+		err |= MLX5E_HANDLE_FEATURE(NETIF_F_LRO, set_feature_lro);
+		err |= MLX5E_HANDLE_FEATURE(NETIF_F_GRO_HW, set_feature_hw_gro);
+		err |= MLX5E_HANDLE_FEATURE(NETIF_F_RXFCS, set_feature_rx_fcs);
+	}
 	err |= MLX5E_HANDLE_FEATURE(NETIF_F_HW_VLAN_CTAG_FILTER,
 				    set_feature_cvlan_filter);
 	err |= MLX5E_HANDLE_FEATURE(NETIF_F_HW_TC, set_feature_hw_tc);
 	err |= MLX5E_HANDLE_FEATURE(NETIF_F_RXALL, set_feature_rx_all);
-	err |= MLX5E_HANDLE_FEATURE(NETIF_F_RXFCS, set_feature_rx_fcs);
 	err |= MLX5E_HANDLE_FEATURE(NETIF_F_HW_VLAN_CTAG_RX, set_feature_rx_vlan);
 #ifdef CONFIG_MLX5_EN_ARFS
 	err |= MLX5E_HANDLE_FEATURE(NETIF_F_NTUPLE, set_feature_arfs);
-- 
GitLab


From 083dbb54c4809bcd56c5c09360ee8c7760a55d71 Mon Sep 17 00:00:00 2001
From: Dragos Tatulea <dtatulea@nvidia.com>
Date: Tue, 4 Jun 2024 00:22:10 +0300
Subject: [PATCH 841/950] net/mlx5e: SHAMPO, Disable gso_size for non GRO
 packets

When HW GRO is enabled, forwarding of packets is broken due to gso_size
being set incorrectly on non GRO packets.

Non GRO packets have a skb GRO count of 1. mlx5 always sets gso_size on
the skb, even for non GRO packets. It leans on the fact that gso_size is
normally reset in napi_gro_complete(). But this happens only for packets
from GRO'able protocols (TCP/UDP) that have a gro_receive() handler.

The problematic scenarios are:

1) Non GRO protocol packets are received, validate_xmit_skb() will drop
   them (see EPROTONOSUPPORT in skb_mac_gso_segment()). The fix for
   this case would be to not set gso_size at all for SHAMPO packets with
   header size 0.

2) Packets from a GRO'ed protocol (TCP) are received but immediately
   flushed because they are not GRO'able (TCP SYN for example).
   mlx5e_shampo_update_hdr(), which updates the remaining GRO state on
   the skb, is not called because skb GRO count is 1. The fix here would
   be to always call mlx5e_shampo_update_hdr(), regardless of skb GRO
   count. But this call is expensive

The unified fix for both cases is to reset gso_size before calling
napi_gro_receive(). It is a change that is more effective (no call to
mlx5e_shampo_update_hdr() necessary) and simple (smallest code
footprint).

Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://lore.kernel.org/r/20240603212219.1037656-6-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index b3ef0dd237298..a13fa760f948a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -2267,6 +2267,8 @@ mlx5e_shampo_flush_skb(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, bool match)
 		mlx5e_shampo_align_fragment(skb, rq->mpwqe.log_stride_sz);
 	if (NAPI_GRO_CB(skb)->count > 1)
 		mlx5e_shampo_update_hdr(rq, cqe, match);
+	else
+		skb_shinfo(skb)->gso_size = 0;
 	napi_gro_receive(rq->cq.napi, skb);
 	rq->hw_gro_data->skb = NULL;
 }
-- 
GitLab


From e839ac9a89cb3bf1aa1652676fa3d6c79810e55d Mon Sep 17 00:00:00 2001
From: Dragos Tatulea <dtatulea@nvidia.com>
Date: Tue, 4 Jun 2024 00:22:11 +0300
Subject: [PATCH 842/950] net/mlx5e: SHAMPO, Simplify header page release in
 teardown

The function that releases SHAMPO header pages (mlx5e_shampo_dealloc_hd)
has some complicated logic that comes from the fact that it is called
twice during teardown:
1) To release the posted header pages that didn't get any completions.
2) To release all remaining header pages.

This flow is not necessary: all header pages can be released from the
driver side in one go. Furthermore, the above flow is buggy. Taking the
8 headers per page example:
1) Release fragments 5-7. Page will be released.
2) Release remaining fragments 0-4. The bits in the header will indicate
   that the page needs releasing. But this is incorrect: page was
   released in step 1.

This patch releases all header pages in one go. This simplifies the
header page cleanup function. For consistency, the datapath header
page release API (mlx5e_free_rx_shampo_hd_entry()) is used.

Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://lore.kernel.org/r/20240603212219.1037656-7-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h  |  2 +-
 .../net/ethernet/mellanox/mlx5/core/en_main.c | 12 +---
 .../net/ethernet/mellanox/mlx5/core/en_rx.c   | 61 +++++--------------
 3 files changed, 17 insertions(+), 58 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index e85fb71bf0b46..ff326601d4a4b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -1014,7 +1014,7 @@ void mlx5e_build_ptys2ethtool_map(void);
 bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev, u8 page_shift,
 					    enum mlx5e_mpwrq_umr_mode umr_mode);
 
-void mlx5e_shampo_dealloc_hd(struct mlx5e_rq *rq, u16 len, u16 start, bool close);
+void mlx5e_shampo_dealloc_hd(struct mlx5e_rq *rq);
 void mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats);
 void mlx5e_fold_sw_stats64(struct mlx5e_priv *priv, struct rtnl_link_stats64 *s);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index d0808dbe69d34..d21a87ddc934b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1208,15 +1208,6 @@ void mlx5e_free_rx_missing_descs(struct mlx5e_rq *rq)
 		head = mlx5_wq_ll_get_wqe_next_ix(wq, head);
 	}
 
-	if (test_bit(MLX5E_RQ_STATE_SHAMPO, &rq->state)) {
-		u16 len;
-
-		len = (rq->mpwqe.shampo->pi - rq->mpwqe.shampo->ci) &
-		      (rq->mpwqe.shampo->hd_per_wq - 1);
-		mlx5e_shampo_dealloc_hd(rq, len, rq->mpwqe.shampo->ci, false);
-		rq->mpwqe.shampo->pi = rq->mpwqe.shampo->ci;
-	}
-
 	rq->mpwqe.actual_wq_head = wq->head;
 	rq->mpwqe.umr_in_progress = 0;
 	rq->mpwqe.umr_completed = 0;
@@ -1244,8 +1235,7 @@ void mlx5e_free_rx_descs(struct mlx5e_rq *rq)
 		}
 
 		if (test_bit(MLX5E_RQ_STATE_SHAMPO, &rq->state))
-			mlx5e_shampo_dealloc_hd(rq, rq->mpwqe.shampo->hd_per_wq,
-						0, true);
+			mlx5e_shampo_dealloc_hd(rq);
 	} else {
 		struct mlx5_wq_cyc *wq = &rq->wqe.wq;
 		u16 missing = mlx5_wq_cyc_missing(wq);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index a13fa760f948a..bb59ee0b15673 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -839,44 +839,28 @@ err:
 	return err;
 }
 
-/* This function is responsible to dealloc SHAMPO header buffer.
- * close == true specifies that we are in the middle of closing RQ operation so
- * we go over all the entries and if they are not in use we free them,
- * otherwise we only go over a specific range inside the header buffer that are
- * not in use.
- */
-void mlx5e_shampo_dealloc_hd(struct mlx5e_rq *rq, u16 len, u16 start, bool close)
+static void
+mlx5e_free_rx_shampo_hd_entry(struct mlx5e_rq *rq, u16 header_index)
 {
 	struct mlx5e_shampo_hd *shampo = rq->mpwqe.shampo;
-	struct mlx5e_frag_page *deleted_page = NULL;
-	int hd_per_wq = shampo->hd_per_wq;
-	struct mlx5e_dma_info *hd_info;
-	int i, index = start;
-
-	for (i = 0; i < len; i++, index++) {
-		if (index == hd_per_wq)
-			index = 0;
-
-		if (close && !test_bit(index, shampo->bitmap))
-			continue;
+	u64 addr = shampo->info[header_index].addr;
 
-		hd_info = &shampo->info[index];
-		hd_info->addr = ALIGN_DOWN(hd_info->addr, PAGE_SIZE);
-		if (hd_info->frag_page && hd_info->frag_page != deleted_page) {
-			deleted_page = hd_info->frag_page;
-			mlx5e_page_release_fragmented(rq, hd_info->frag_page);
-		}
+	if (((header_index + 1) & (MLX5E_SHAMPO_WQ_HEADER_PER_PAGE - 1)) == 0) {
+		struct mlx5e_dma_info *dma_info = &shampo->info[header_index];
 
-		hd_info->frag_page = NULL;
+		dma_info->addr = ALIGN_DOWN(addr, PAGE_SIZE);
+		mlx5e_page_release_fragmented(rq, dma_info->frag_page);
 	}
+	clear_bit(header_index, shampo->bitmap);
+}
 
-	if (start + len > hd_per_wq) {
-		len -= hd_per_wq - start;
-		bitmap_clear(shampo->bitmap, start, hd_per_wq - start);
-		start = 0;
-	}
+void mlx5e_shampo_dealloc_hd(struct mlx5e_rq *rq)
+{
+	struct mlx5e_shampo_hd *shampo = rq->mpwqe.shampo;
+	int i;
 
-	bitmap_clear(shampo->bitmap, start, len);
+	for_each_set_bit(i, shampo->bitmap, rq->mpwqe.shampo->hd_per_wq)
+		mlx5e_free_rx_shampo_hd_entry(rq, i);
 }
 
 static void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
@@ -2281,21 +2265,6 @@ mlx5e_hw_gro_skb_has_enough_space(struct sk_buff *skb, u16 data_bcnt)
 	return PAGE_SIZE * nr_frags + data_bcnt <= GRO_LEGACY_MAX_SIZE;
 }
 
-static void
-mlx5e_free_rx_shampo_hd_entry(struct mlx5e_rq *rq, u16 header_index)
-{
-	struct mlx5e_shampo_hd *shampo = rq->mpwqe.shampo;
-	u64 addr = shampo->info[header_index].addr;
-
-	if (((header_index + 1) & (MLX5E_SHAMPO_WQ_HEADER_PER_PAGE - 1)) == 0) {
-		struct mlx5e_dma_info *dma_info = &shampo->info[header_index];
-
-		dma_info->addr = ALIGN_DOWN(addr, PAGE_SIZE);
-		mlx5e_page_release_fragmented(rq, dma_info->frag_page);
-	}
-	bitmap_clear(shampo->bitmap, header_index, 1);
-}
-
 static void mlx5e_handle_rx_cqe_mpwrq_shampo(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 {
 	u16 data_bcnt		= mpwrq_get_cqe_byte_cnt(cqe) - cqe->shampo.header_size;
-- 
GitLab


From d34d7d1973c4d1125c430a9612d97bfc10cf6382 Mon Sep 17 00:00:00 2001
From: Dragos Tatulea <dtatulea@nvidia.com>
Date: Tue, 4 Jun 2024 00:22:12 +0300
Subject: [PATCH 843/950] net/mlx5e: SHAMPO, Specialize mlx5e_fill_skb_data()

mlx5e_fill_skb_data() used to have multiple callers. But after the XDP
multibuf refactoring from commit 2cb0e27d43b4 ("net/mlx5e: RX, Prepare
non-linear striding RQ for XDP multi-buffer support") the SHAMPO code
path is the only caller.

Take advantage of this and specialize the function:
- Drop the redundant check.
- Assume that data_bcnt is > 0. This is needed in a downstream patch.

Rename the function as well to make things clear.

Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Suggested-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://lore.kernel.org/r/20240603212219.1037656-8-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/mellanox/mlx5/core/en_rx.c   | 25 ++++++++-----------
 1 file changed, 11 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index bb59ee0b15673..1e3a5b2afeae5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -1948,21 +1948,16 @@ const struct mlx5e_rx_handlers mlx5e_rx_handlers_rep = {
 #endif
 
 static void
-mlx5e_fill_skb_data(struct sk_buff *skb, struct mlx5e_rq *rq,
-		    struct mlx5e_frag_page *frag_page,
-		    u32 data_bcnt, u32 data_offset)
+mlx5e_shampo_fill_skb_data(struct sk_buff *skb, struct mlx5e_rq *rq,
+			   struct mlx5e_frag_page *frag_page,
+			   u32 data_bcnt, u32 data_offset)
 {
 	net_prefetchw(skb->data);
 
-	while (data_bcnt) {
+	do {
 		/* Non-linear mode, hence non-XSK, which always uses PAGE_SIZE. */
 		u32 pg_consumed_bytes = min_t(u32, PAGE_SIZE - data_offset, data_bcnt);
-		unsigned int truesize;
-
-		if (test_bit(MLX5E_RQ_STATE_SHAMPO, &rq->state))
-			truesize = pg_consumed_bytes;
-		else
-			truesize = ALIGN(pg_consumed_bytes, BIT(rq->mpwqe.log_stride_sz));
+		unsigned int truesize = pg_consumed_bytes;
 
 		frag_page->frags++;
 		mlx5e_add_skb_frag(rq, skb, frag_page->page, data_offset,
@@ -1971,7 +1966,7 @@ mlx5e_fill_skb_data(struct sk_buff *skb, struct mlx5e_rq *rq,
 		data_bcnt -= pg_consumed_bytes;
 		data_offset = 0;
 		frag_page++;
-	}
+	} while (data_bcnt);
 }
 
 static struct sk_buff *
@@ -2330,10 +2325,12 @@ static void mlx5e_handle_rx_cqe_mpwrq_shampo(struct mlx5e_rq *rq, struct mlx5_cq
 	}
 
 	if (likely(head_size)) {
-		struct mlx5e_frag_page *frag_page;
+		if (data_bcnt) {
+			struct mlx5e_frag_page *frag_page;
 
-		frag_page = &wi->alloc_units.frag_pages[page_idx];
-		mlx5e_fill_skb_data(*skb, rq, frag_page, data_bcnt, data_offset);
+			frag_page = &wi->alloc_units.frag_pages[page_idx];
+			mlx5e_shampo_fill_skb_data(*skb, rq, frag_page, data_bcnt, data_offset);
+		}
 	}
 
 	mlx5e_shampo_complete_rx_cqe(rq, cqe, cqe_bcnt, *skb);
-- 
GitLab


From f5a699e00f045856b55a60ebf57e367fca389910 Mon Sep 17 00:00:00 2001
From: Yoray Zack <yorayz@nvidia.com>
Date: Tue, 4 Jun 2024 00:22:13 +0300
Subject: [PATCH 844/950] net/mlx5e: SHAMPO, Skipping on duplicate flush of the
 same SHAMPO SKB

SHAMPO SKB can be flushed in mlx5e_shampo_complete_rx_cqe().
If the SKB was flushed, rq->hw_gro_data->skb was also set to NULL.

We can skip on flushing the SKB in mlx5e_shampo_flush_skb
if rq->hw_gro_data->skb == NULL.

Signed-off-by: Yoray Zack <yorayz@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://lore.kernel.org/r/20240603212219.1037656-9-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 1e3a5b2afeae5..3f76c33aada04 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -2334,7 +2334,7 @@ static void mlx5e_handle_rx_cqe_mpwrq_shampo(struct mlx5e_rq *rq, struct mlx5_cq
 	}
 
 	mlx5e_shampo_complete_rx_cqe(rq, cqe, cqe_bcnt, *skb);
-	if (flush)
+	if (flush && rq->hw_gro_data->skb)
 		mlx5e_shampo_flush_skb(rq, cqe, match);
 free_hd_entry:
 	if (likely(head_size))
-- 
GitLab


From 8f9eb8bb5c5af846a8b1729bd7778d08ca852379 Mon Sep 17 00:00:00 2001
From: Dragos Tatulea <dtatulea@nvidia.com>
Date: Tue, 4 Jun 2024 00:22:14 +0300
Subject: [PATCH 845/950] net/mlx5e: SHAMPO, Make GRO counters more precise

Don't count non GRO packets. A non GRO packet is a packet with
a GRO cb count of 1.

Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://lore.kernel.org/r/20240603212219.1037656-10-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../ethernet/mellanox/mlx5/counters.rst             | 10 ++++++----
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c     | 13 ++++++++-----
 2 files changed, 14 insertions(+), 9 deletions(-)

diff --git a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/counters.rst b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/counters.rst
index fed821ef9b094..7ed010dbe4696 100644
--- a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/counters.rst
+++ b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/counters.rst
@@ -189,17 +189,19 @@ the software port.
 
    * - `rx[i]_gro_packets`
      - Number of received packets processed using hardware-accelerated GRO. The
-       number of hardware GRO offloaded packets received on ring i.
+       number of hardware GRO offloaded packets received on ring i. Only true GRO
+       packets are counted: only packets that are in an SKB with a GRO count > 1.
      - Acceleration
 
    * - `rx[i]_gro_bytes`
      - Number of received bytes processed using hardware-accelerated GRO. The
-       number of hardware GRO offloaded bytes received on ring i.
+       number of hardware GRO offloaded bytes received on ring i. Only true GRO
+       packets are counted: only packets that are in an SKB with a GRO count > 1.
      - Acceleration
 
    * - `rx[i]_gro_skbs`
-     - The number of receive SKBs constructed while performing
-       hardware-accelerated GRO.
+     - The number of GRO SKBs constructed from hardware-accelerated GRO. Only SKBs
+       with a GRO count > 1 are counted.
      - Informative
 
    * - `rx[i]_gro_match_packets`
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 3f76c33aada04..79b486d5475d9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -1596,9 +1596,7 @@ static void mlx5e_shampo_complete_rx_cqe(struct mlx5e_rq *rq,
 	struct mlx5e_rq_stats *stats = rq->stats;
 
 	stats->packets++;
-	stats->gro_packets++;
 	stats->bytes += cqe_bcnt;
-	stats->gro_bytes += cqe_bcnt;
 	if (NAPI_GRO_CB(skb)->count != 1)
 		return;
 	mlx5e_build_rx_skb(cqe, cqe_bcnt, rq, skb);
@@ -2240,14 +2238,19 @@ mlx5e_shampo_flush_skb(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, bool match)
 {
 	struct sk_buff *skb = rq->hw_gro_data->skb;
 	struct mlx5e_rq_stats *stats = rq->stats;
+	u16 gro_count = NAPI_GRO_CB(skb)->count;
 
-	stats->gro_skbs++;
 	if (likely(skb_shinfo(skb)->nr_frags))
 		mlx5e_shampo_align_fragment(skb, rq->mpwqe.log_stride_sz);
-	if (NAPI_GRO_CB(skb)->count > 1)
+	if (gro_count > 1) {
+		stats->gro_skbs++;
+		stats->gro_packets += gro_count;
+		stats->gro_bytes += skb->data_len + skb_headlen(skb) * gro_count;
+
 		mlx5e_shampo_update_hdr(rq, cqe, match);
-	else
+	} else {
 		skb_shinfo(skb)->gso_size = 0;
+	}
 	napi_gro_receive(rq->cq.napi, skb);
 	rq->hw_gro_data->skb = NULL;
 }
-- 
GitLab


From 16f448d47a86825a421fc1211336454c42c5254f Mon Sep 17 00:00:00 2001
From: Dragos Tatulea <dtatulea@nvidia.com>
Date: Tue, 4 Jun 2024 00:22:15 +0300
Subject: [PATCH 846/950] net/mlx5e: SHAMPO, Drop rx_gro_match_packets counter

After modifying rx_gro_packets to be more accurate, the
rx_gro_match_packets counter is redundant.

Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://lore.kernel.org/r/20240603212219.1037656-11-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../device_drivers/ethernet/mellanox/mlx5/counters.rst       | 5 -----
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c              | 2 --
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.c           | 3 ---
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.h           | 2 --
 4 files changed, 12 deletions(-)

diff --git a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/counters.rst b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/counters.rst
index 7ed010dbe4696..18638a8e7c73f 100644
--- a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/counters.rst
+++ b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/counters.rst
@@ -204,11 +204,6 @@ the software port.
        with a GRO count > 1 are counted.
      - Informative
 
-   * - `rx[i]_gro_match_packets`
-     - Number of received packets processed using hardware-accelerated GRO that
-       met the flow table match criteria.
-     - Informative
-
    * - `rx[i]_gro_large_hds`
      - Number of receive packets using hardware-accelerated GRO that have large
        headers that require additional memory to be allocated.
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 79b486d5475d9..7ab7215843b68 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -2296,8 +2296,6 @@ static void mlx5e_handle_rx_cqe_mpwrq_shampo(struct mlx5e_rq *rq, struct mlx5_cq
 		goto mpwrq_cqe_out;
 	}
 
-	stats->gro_match_packets += match;
-
 	if (*skb && (!match || !(mlx5e_hw_gro_skb_has_enough_space(*skb, data_bcnt)))) {
 		match = false;
 		mlx5e_shampo_flush_skb(rq, cqe, match);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index e1ed214e86517..a3c79da1525bd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -141,7 +141,6 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_gro_packets) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_gro_bytes) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_gro_skbs) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_gro_match_packets) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_gro_large_hds) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_ecn_mark) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_removed_vlan_packets) },
@@ -343,7 +342,6 @@ static void mlx5e_stats_grp_sw_update_stats_rq_stats(struct mlx5e_sw_stats *s,
 	s->rx_gro_packets             += rq_stats->gro_packets;
 	s->rx_gro_bytes               += rq_stats->gro_bytes;
 	s->rx_gro_skbs                += rq_stats->gro_skbs;
-	s->rx_gro_match_packets       += rq_stats->gro_match_packets;
 	s->rx_gro_large_hds           += rq_stats->gro_large_hds;
 	s->rx_ecn_mark                += rq_stats->ecn_mark;
 	s->rx_removed_vlan_packets    += rq_stats->removed_vlan_packets;
@@ -2057,7 +2055,6 @@ static const struct counter_desc rq_stats_desc[] = {
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, gro_packets) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, gro_bytes) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, gro_skbs) },
-	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, gro_match_packets) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, gro_large_hds) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, ecn_mark) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, removed_vlan_packets) },
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 650732288616d..25daae526caa7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -153,7 +153,6 @@ struct mlx5e_sw_stats {
 	u64 rx_gro_packets;
 	u64 rx_gro_bytes;
 	u64 rx_gro_skbs;
-	u64 rx_gro_match_packets;
 	u64 rx_gro_large_hds;
 	u64 rx_mcast_packets;
 	u64 rx_ecn_mark;
@@ -352,7 +351,6 @@ struct mlx5e_rq_stats {
 	u64 gro_packets;
 	u64 gro_bytes;
 	u64 gro_skbs;
-	u64 gro_match_packets;
 	u64 gro_large_hds;
 	u64 mcast_packets;
 	u64 ecn_mark;
-- 
GitLab


From e95c5b9e89126703de8212ed8e50b185a1f970bb Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@nvidia.com>
Date: Tue, 4 Jun 2024 00:22:16 +0300
Subject: [PATCH 847/950] net/mlx5e: SHAMPO, Add header-only ethtool counters
 for header data split

Count the number of header-only packets and bytes from SHAMPO.

Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://lore.kernel.org/r/20240603212219.1037656-12-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../device_drivers/ethernet/mellanox/mlx5/counters.rst   | 9 +++++++++
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c          | 3 +++
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.c       | 4 ++++
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.h       | 4 ++++
 4 files changed, 20 insertions(+)

diff --git a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/counters.rst b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/counters.rst
index 18638a8e7c73f..3bd72577af9ae 100644
--- a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/counters.rst
+++ b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/counters.rst
@@ -209,6 +209,15 @@ the software port.
        headers that require additional memory to be allocated.
      - Informative
 
+   * - `rx[i]_hds_nodata_packets`
+     - Number of header only packets in header/data split mode [#accel]_.
+     - Informative
+
+   * - `rx[i]_hds_nodata_bytes`
+     - Number of bytes for header only packets in header/data split mode
+       [#accel]_.
+     - Informative
+
    * - `rx[i]_lro_packets`
      - The number of LRO packets received on ring i [#accel]_.
      - Acceleration
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 7ab7215843b68..3af4f70de3348 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -2331,6 +2331,9 @@ static void mlx5e_handle_rx_cqe_mpwrq_shampo(struct mlx5e_rq *rq, struct mlx5_cq
 
 			frag_page = &wi->alloc_units.frag_pages[page_idx];
 			mlx5e_shampo_fill_skb_data(*skb, rq, frag_page, data_bcnt, data_offset);
+		} else {
+			stats->hds_nodata_packets++;
+			stats->hds_nodata_bytes += head_size;
 		}
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index a3c79da1525bd..db1cac68292f3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -343,6 +343,8 @@ static void mlx5e_stats_grp_sw_update_stats_rq_stats(struct mlx5e_sw_stats *s,
 	s->rx_gro_bytes               += rq_stats->gro_bytes;
 	s->rx_gro_skbs                += rq_stats->gro_skbs;
 	s->rx_gro_large_hds           += rq_stats->gro_large_hds;
+	s->rx_hds_nodata_packets      += rq_stats->hds_nodata_packets;
+	s->rx_hds_nodata_bytes        += rq_stats->hds_nodata_bytes;
 	s->rx_ecn_mark                += rq_stats->ecn_mark;
 	s->rx_removed_vlan_packets    += rq_stats->removed_vlan_packets;
 	s->rx_csum_none               += rq_stats->csum_none;
@@ -2056,6 +2058,8 @@ static const struct counter_desc rq_stats_desc[] = {
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, gro_bytes) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, gro_skbs) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, gro_large_hds) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, hds_nodata_packets) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, hds_nodata_bytes) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, ecn_mark) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, removed_vlan_packets) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, wqe_err) },
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 25daae526caa7..4c5858c1dd829 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -154,6 +154,8 @@ struct mlx5e_sw_stats {
 	u64 rx_gro_bytes;
 	u64 rx_gro_skbs;
 	u64 rx_gro_large_hds;
+	u64 rx_hds_nodata_packets;
+	u64 rx_hds_nodata_bytes;
 	u64 rx_mcast_packets;
 	u64 rx_ecn_mark;
 	u64 rx_removed_vlan_packets;
@@ -352,6 +354,8 @@ struct mlx5e_rq_stats {
 	u64 gro_bytes;
 	u64 gro_skbs;
 	u64 gro_large_hds;
+	u64 hds_nodata_packets;
+	u64 hds_nodata_bytes;
 	u64 mcast_packets;
 	u64 ecn_mark;
 	u64 removed_vlan_packets;
-- 
GitLab


From 758191c9ea7bcc45dd99398a538ae4ab27c4029e Mon Sep 17 00:00:00 2001
From: Yoray Zack <yorayz@nvidia.com>
Date: Tue, 4 Jun 2024 00:22:17 +0300
Subject: [PATCH 848/950] net/mlx5e: SHAMPO, Use KSMs instead of KLMs

KSM Mkey is KLM Mkey with a fixed buffer size. Due to this fact,
it is a faster mechanism than KLM.

SHAMPO feature used KLMs Mkeys for memory mappings of its headers buffer.
As it used KLMs with the same buffer size for each entry,
we can use KSMs instead.

This commit changes the Mkeys that map the SHAMPO headers buffer
from KLMs to KSMs.

Signed-off-by: Yoray Zack <yorayz@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://lore.kernel.org/r/20240603212219.1037656-13-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h  | 20 +-----
 .../ethernet/mellanox/mlx5/core/en/params.c   | 12 ++--
 .../net/ethernet/mellanox/mlx5/core/en/txrx.h | 19 ++++++
 .../net/ethernet/mellanox/mlx5/core/en_main.c | 21 +++---
 .../net/ethernet/mellanox/mlx5/core/en_rx.c   | 65 +++++++++----------
 include/linux/mlx5/device.h                   |  1 +
 6 files changed, 71 insertions(+), 67 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index ff326601d4a4b..bec784d25d7be 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -80,6 +80,7 @@ struct page_pool;
 				 SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
 
 #define MLX5E_RX_MAX_HEAD (256)
+#define MLX5E_SHAMPO_LOG_HEADER_ENTRY_SIZE (8)
 #define MLX5E_SHAMPO_LOG_MAX_HEADER_ENTRY_SIZE (9)
 #define MLX5E_SHAMPO_WQ_HEADER_PER_PAGE (PAGE_SIZE >> MLX5E_SHAMPO_LOG_MAX_HEADER_ENTRY_SIZE)
 #define MLX5E_SHAMPO_WQ_BASE_HEAD_ENTRY_SIZE (64)
@@ -146,25 +147,6 @@ struct page_pool;
 #define MLX5E_TX_XSK_POLL_BUDGET       64
 #define MLX5E_SQ_RECOVER_MIN_INTERVAL  500 /* msecs */
 
-#define MLX5E_KLM_UMR_WQE_SZ(sgl_len)\
-	(sizeof(struct mlx5e_umr_wqe) +\
-	(sizeof(struct mlx5_klm) * (sgl_len)))
-
-#define MLX5E_KLM_UMR_WQEBBS(klm_entries) \
-	(DIV_ROUND_UP(MLX5E_KLM_UMR_WQE_SZ(klm_entries), MLX5_SEND_WQE_BB))
-
-#define MLX5E_KLM_UMR_DS_CNT(klm_entries)\
-	(DIV_ROUND_UP(MLX5E_KLM_UMR_WQE_SZ(klm_entries), MLX5_SEND_WQE_DS))
-
-#define MLX5E_KLM_MAX_ENTRIES_PER_WQE(wqe_size)\
-	(((wqe_size) - sizeof(struct mlx5e_umr_wqe)) / sizeof(struct mlx5_klm))
-
-#define MLX5E_KLM_ENTRIES_PER_WQE(wqe_size)\
-	ALIGN_DOWN(MLX5E_KLM_MAX_ENTRIES_PER_WQE(wqe_size), MLX5_UMR_KLM_NUM_ENTRIES_ALIGNMENT)
-
-#define MLX5E_MAX_KLM_PER_WQE(mdev) \
-	MLX5E_KLM_ENTRIES_PER_WQE(MLX5_SEND_WQE_BB * mlx5e_get_max_sq_aligned_wqebbs(mdev))
-
 #define mlx5e_state_dereference(priv, p) \
 	rcu_dereference_protected((p), lockdep_is_held(&(priv)->state_lock))
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
index ec819dfc98be2..6c9ccccca81e2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
@@ -1071,18 +1071,18 @@ static u32 mlx5e_shampo_icosq_sz(struct mlx5_core_dev *mdev,
 				 struct mlx5e_params *params,
 				 struct mlx5e_rq_param *rq_param)
 {
-	int max_num_of_umr_per_wqe, max_hd_per_wqe, max_klm_per_umr, rest;
+	int max_num_of_umr_per_wqe, max_hd_per_wqe, max_ksm_per_umr, rest;
 	void *wqc = MLX5_ADDR_OF(rqc, rq_param->rqc, wq);
 	int wq_size = BIT(MLX5_GET(wq, wqc, log_wq_sz));
 	u32 wqebbs;
 
-	max_klm_per_umr = MLX5E_MAX_KLM_PER_WQE(mdev);
+	max_ksm_per_umr = MLX5E_MAX_KSM_PER_WQE(mdev);
 	max_hd_per_wqe = mlx5e_shampo_hd_per_wqe(mdev, params, rq_param);
-	max_num_of_umr_per_wqe = max_hd_per_wqe / max_klm_per_umr;
-	rest = max_hd_per_wqe % max_klm_per_umr;
-	wqebbs = MLX5E_KLM_UMR_WQEBBS(max_klm_per_umr) * max_num_of_umr_per_wqe;
+	max_num_of_umr_per_wqe = max_hd_per_wqe / max_ksm_per_umr;
+	rest = max_hd_per_wqe % max_ksm_per_umr;
+	wqebbs = MLX5E_KSM_UMR_WQEBBS(max_ksm_per_umr) * max_num_of_umr_per_wqe;
 	if (rest)
-		wqebbs += MLX5E_KLM_UMR_WQEBBS(rest);
+		wqebbs += MLX5E_KSM_UMR_WQEBBS(rest);
 	wqebbs *= wq_size;
 	return wqebbs;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
index 879d698b61193..d1f0f868d494e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
@@ -34,6 +34,25 @@
 
 #define MLX5E_RX_ERR_CQE(cqe) (get_cqe_opcode(cqe) != MLX5_CQE_RESP_SEND)
 
+#define MLX5E_KSM_UMR_WQE_SZ(sgl_len)\
+	(sizeof(struct mlx5e_umr_wqe) +\
+	(sizeof(struct mlx5_ksm) * (sgl_len)))
+
+#define MLX5E_KSM_UMR_WQEBBS(ksm_entries) \
+	(DIV_ROUND_UP(MLX5E_KSM_UMR_WQE_SZ(ksm_entries), MLX5_SEND_WQE_BB))
+
+#define MLX5E_KSM_UMR_DS_CNT(ksm_entries)\
+	(DIV_ROUND_UP(MLX5E_KSM_UMR_WQE_SZ(ksm_entries), MLX5_SEND_WQE_DS))
+
+#define MLX5E_KSM_MAX_ENTRIES_PER_WQE(wqe_size)\
+	(((wqe_size) - sizeof(struct mlx5e_umr_wqe)) / sizeof(struct mlx5_ksm))
+
+#define MLX5E_KSM_ENTRIES_PER_WQE(wqe_size)\
+	ALIGN_DOWN(MLX5E_KSM_MAX_ENTRIES_PER_WQE(wqe_size), MLX5_UMR_KSM_NUM_ENTRIES_ALIGNMENT)
+
+#define MLX5E_MAX_KSM_PER_WQE(mdev) \
+	MLX5E_KSM_ENTRIES_PER_WQE(MLX5_SEND_WQE_BB * mlx5e_get_max_sq_aligned_wqebbs(mdev))
+
 static inline
 ktime_t mlx5e_cqe_ts_to_ns(cqe_ts_to_ns func, struct mlx5_clock *clock, u64 cqe_ts)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index d21a87ddc934b..2a3e0de51f0e4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -504,8 +504,8 @@ static int mlx5e_create_umr_mkey(struct mlx5_core_dev *mdev,
 	return err;
 }
 
-static int mlx5e_create_umr_klm_mkey(struct mlx5_core_dev *mdev,
-				     u64 nentries,
+static int mlx5e_create_umr_ksm_mkey(struct mlx5_core_dev *mdev,
+				     u64 nentries, u8 log_entry_size,
 				     u32 *umr_mkey)
 {
 	int inlen;
@@ -525,12 +525,13 @@ static int mlx5e_create_umr_klm_mkey(struct mlx5_core_dev *mdev,
 	MLX5_SET(mkc, mkc, umr_en, 1);
 	MLX5_SET(mkc, mkc, lw, 1);
 	MLX5_SET(mkc, mkc, lr, 1);
-	MLX5_SET(mkc, mkc, access_mode_1_0, MLX5_MKC_ACCESS_MODE_KLMS);
+	MLX5_SET(mkc, mkc, access_mode_1_0, MLX5_MKC_ACCESS_MODE_KSM);
 	mlx5e_mkey_set_relaxed_ordering(mdev, mkc);
 	MLX5_SET(mkc, mkc, qpn, 0xffffff);
 	MLX5_SET(mkc, mkc, pd, mdev->mlx5e_res.hw_objs.pdn);
 	MLX5_SET(mkc, mkc, translations_octword_size, nentries);
-	MLX5_SET(mkc, mkc, length64, 1);
+	MLX5_SET(mkc, mkc, log_page_size, log_entry_size);
+	MLX5_SET64(mkc, mkc, len, nentries << log_entry_size);
 	err = mlx5_core_create_mkey(mdev, umr_mkey, in, inlen);
 
 	kvfree(in);
@@ -565,14 +566,16 @@ static int mlx5e_create_rq_umr_mkey(struct mlx5_core_dev *mdev, struct mlx5e_rq
 static int mlx5e_create_rq_hd_umr_mkey(struct mlx5_core_dev *mdev,
 				       struct mlx5e_rq *rq)
 {
-	u32 max_klm_size = BIT(MLX5_CAP_GEN(mdev, log_max_klm_list_size));
+	u32 max_ksm_size = BIT(MLX5_CAP_GEN(mdev, log_max_klm_list_size));
 
-	if (max_klm_size < rq->mpwqe.shampo->hd_per_wq) {
-		mlx5_core_err(mdev, "max klm list size 0x%x is smaller than shampo header buffer list size 0x%x\n",
-			      max_klm_size, rq->mpwqe.shampo->hd_per_wq);
+	if (max_ksm_size < rq->mpwqe.shampo->hd_per_wq) {
+		mlx5_core_err(mdev, "max ksm list size 0x%x is smaller than shampo header buffer list size 0x%x\n",
+			      max_ksm_size, rq->mpwqe.shampo->hd_per_wq);
 		return -EINVAL;
 	}
-	return mlx5e_create_umr_klm_mkey(mdev, rq->mpwqe.shampo->hd_per_wq,
+
+	return mlx5e_create_umr_ksm_mkey(mdev, rq->mpwqe.shampo->hd_per_wq,
+					 MLX5E_SHAMPO_LOG_HEADER_ENTRY_SIZE,
 					 &rq->mpwqe.shampo->mkey);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 3af4f70de3348..f1fbf60d0356e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -619,25 +619,25 @@ static int bitmap_find_window(unsigned long *bitmap, int len,
 	return min(len, count);
 }
 
-static void build_klm_umr(struct mlx5e_icosq *sq, struct mlx5e_umr_wqe *umr_wqe,
-			  __be32 key, u16 offset, u16 klm_len, u16 wqe_bbs)
+static void build_ksm_umr(struct mlx5e_icosq *sq, struct mlx5e_umr_wqe *umr_wqe,
+			  __be32 key, u16 offset, u16 ksm_len)
 {
-	memset(umr_wqe, 0, offsetof(struct mlx5e_umr_wqe, inline_klms));
+	memset(umr_wqe, 0, offsetof(struct mlx5e_umr_wqe, inline_ksms));
 	umr_wqe->ctrl.opmod_idx_opcode =
 		cpu_to_be32((sq->pc << MLX5_WQE_CTRL_WQE_INDEX_SHIFT) |
 			     MLX5_OPCODE_UMR);
 	umr_wqe->ctrl.umr_mkey = key;
 	umr_wqe->ctrl.qpn_ds = cpu_to_be32((sq->sqn << MLX5_WQE_CTRL_QPN_SHIFT)
-					    | MLX5E_KLM_UMR_DS_CNT(klm_len));
+					    | MLX5E_KSM_UMR_DS_CNT(ksm_len));
 	umr_wqe->uctrl.flags = MLX5_UMR_TRANSLATION_OFFSET_EN | MLX5_UMR_INLINE;
 	umr_wqe->uctrl.xlt_offset = cpu_to_be16(offset);
-	umr_wqe->uctrl.xlt_octowords = cpu_to_be16(klm_len);
+	umr_wqe->uctrl.xlt_octowords = cpu_to_be16(ksm_len);
 	umr_wqe->uctrl.mkey_mask     = cpu_to_be64(MLX5_MKEY_MASK_FREE);
 }
 
 static int mlx5e_build_shampo_hd_umr(struct mlx5e_rq *rq,
 				     struct mlx5e_icosq *sq,
-				     u16 klm_entries, u16 index)
+				     u16 ksm_entries, u16 index)
 {
 	struct mlx5e_shampo_hd *shampo = rq->mpwqe.shampo;
 	u16 entries, pi, header_offset, err, wqe_bbs, new_entries;
@@ -650,20 +650,20 @@ static int mlx5e_build_shampo_hd_umr(struct mlx5e_rq *rq,
 	int headroom, i;
 
 	headroom = rq->buff.headroom;
-	new_entries = klm_entries - (shampo->pi & (MLX5_UMR_KLM_NUM_ENTRIES_ALIGNMENT - 1));
-	entries = ALIGN(klm_entries, MLX5_UMR_KLM_NUM_ENTRIES_ALIGNMENT);
-	wqe_bbs = MLX5E_KLM_UMR_WQEBBS(entries);
+	new_entries = ksm_entries - (shampo->pi & (MLX5_UMR_KSM_NUM_ENTRIES_ALIGNMENT - 1));
+	entries = ALIGN(ksm_entries, MLX5_UMR_KSM_NUM_ENTRIES_ALIGNMENT);
+	wqe_bbs = MLX5E_KSM_UMR_WQEBBS(entries);
 	pi = mlx5e_icosq_get_next_pi(sq, wqe_bbs);
 	umr_wqe = mlx5_wq_cyc_get_wqe(&sq->wq, pi);
-	build_klm_umr(sq, umr_wqe, shampo->key, index, entries, wqe_bbs);
+	build_ksm_umr(sq, umr_wqe, shampo->key, index, entries);
 
 	frag_page = &shampo->pages[page_index];
 
 	for (i = 0; i < entries; i++, index++) {
 		dma_info = &shampo->info[index];
-		if (i >= klm_entries || (index < shampo->pi && shampo->pi - index <
-					 MLX5_UMR_KLM_NUM_ENTRIES_ALIGNMENT))
-			goto update_klm;
+		if (i >= ksm_entries || (index < shampo->pi && shampo->pi - index <
+					 MLX5_UMR_KSM_NUM_ENTRIES_ALIGNMENT))
+			goto update_ksm;
 		header_offset = (index & (MLX5E_SHAMPO_WQ_HEADER_PER_PAGE - 1)) <<
 			MLX5E_SHAMPO_LOG_MAX_HEADER_ENTRY_SIZE;
 		if (!(header_offset & (PAGE_SIZE - 1))) {
@@ -683,12 +683,11 @@ static int mlx5e_build_shampo_hd_umr(struct mlx5e_rq *rq,
 			dma_info->frag_page = frag_page;
 		}
 
-update_klm:
-		umr_wqe->inline_klms[i].bcount =
-			cpu_to_be32(MLX5E_RX_MAX_HEAD);
-		umr_wqe->inline_klms[i].key    = cpu_to_be32(lkey);
-		umr_wqe->inline_klms[i].va     =
-			cpu_to_be64(dma_info->addr + headroom);
+update_ksm:
+		umr_wqe->inline_ksms[i] = (struct mlx5_ksm) {
+			.key = cpu_to_be32(lkey),
+			.va  = cpu_to_be64(dma_info->addr + headroom),
+		};
 	}
 
 	sq->db.wqe_info[pi] = (struct mlx5e_icosq_wqe_info) {
@@ -720,37 +719,37 @@ err_unmap:
 static int mlx5e_alloc_rx_hd_mpwqe(struct mlx5e_rq *rq)
 {
 	struct mlx5e_shampo_hd *shampo = rq->mpwqe.shampo;
-	u16 klm_entries, num_wqe, index, entries_before;
+	u16 ksm_entries, num_wqe, index, entries_before;
 	struct mlx5e_icosq *sq = rq->icosq;
-	int i, err, max_klm_entries, len;
+	int i, err, max_ksm_entries, len;
 
-	max_klm_entries = MLX5E_MAX_KLM_PER_WQE(rq->mdev);
-	klm_entries = bitmap_find_window(shampo->bitmap,
+	max_ksm_entries = MLX5E_MAX_KSM_PER_WQE(rq->mdev);
+	ksm_entries = bitmap_find_window(shampo->bitmap,
 					 shampo->hd_per_wqe,
 					 shampo->hd_per_wq, shampo->pi);
-	if (!klm_entries)
+	if (!ksm_entries)
 		return 0;
 
-	klm_entries += (shampo->pi & (MLX5_UMR_KLM_NUM_ENTRIES_ALIGNMENT - 1));
-	index = ALIGN_DOWN(shampo->pi, MLX5_UMR_KLM_NUM_ENTRIES_ALIGNMENT);
+	ksm_entries += (shampo->pi & (MLX5_UMR_KSM_NUM_ENTRIES_ALIGNMENT - 1));
+	index = ALIGN_DOWN(shampo->pi, MLX5_UMR_KSM_NUM_ENTRIES_ALIGNMENT);
 	entries_before = shampo->hd_per_wq - index;
 
-	if (unlikely(entries_before < klm_entries))
-		num_wqe = DIV_ROUND_UP(entries_before, max_klm_entries) +
-			  DIV_ROUND_UP(klm_entries - entries_before, max_klm_entries);
+	if (unlikely(entries_before < ksm_entries))
+		num_wqe = DIV_ROUND_UP(entries_before, max_ksm_entries) +
+			  DIV_ROUND_UP(ksm_entries - entries_before, max_ksm_entries);
 	else
-		num_wqe = DIV_ROUND_UP(klm_entries, max_klm_entries);
+		num_wqe = DIV_ROUND_UP(ksm_entries, max_ksm_entries);
 
 	for (i = 0; i < num_wqe; i++) {
-		len = (klm_entries > max_klm_entries) ? max_klm_entries :
-							klm_entries;
+		len = (ksm_entries > max_ksm_entries) ? max_ksm_entries :
+							ksm_entries;
 		if (unlikely(index + len > shampo->hd_per_wq))
 			len = shampo->hd_per_wq - index;
 		err = mlx5e_build_shampo_hd_umr(rq, sq, len, index);
 		if (unlikely(err))
 			return err;
 		index = (index + len) & (rq->mpwqe.shampo->hd_per_wq - 1);
-		klm_entries -= len;
+		ksm_entries -= len;
 	}
 
 	return 0;
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index d7bb31d9a4463..da09bfaa7b813 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -294,6 +294,7 @@ enum {
 #define MLX5_UMR_FLEX_ALIGNMENT 0x40
 #define MLX5_UMR_MTT_NUM_ENTRIES_ALIGNMENT (MLX5_UMR_FLEX_ALIGNMENT / sizeof(struct mlx5_mtt))
 #define MLX5_UMR_KLM_NUM_ENTRIES_ALIGNMENT (MLX5_UMR_FLEX_ALIGNMENT / sizeof(struct mlx5_klm))
+#define MLX5_UMR_KSM_NUM_ENTRIES_ALIGNMENT (MLX5_UMR_FLEX_ALIGNMENT / sizeof(struct mlx5_ksm))
 
 #define MLX5_USER_INDEX_LEN (MLX5_FLD_SZ_BYTES(qpc, user_index) * 8)
 
-- 
GitLab


From 99be56171fa9ffea494dfe3d4a7f6e7e51630c2e Mon Sep 17 00:00:00 2001
From: Yoray Zack <yorayz@nvidia.com>
Date: Tue, 4 Jun 2024 00:22:18 +0300
Subject: [PATCH 849/950] net/mlx5e: SHAMPO, Re-enable HW-GRO

Add back HW-GRO to the reported features.

As the current implementation of HW-GRO uses KSMs with a
specific fixed buffer size (256B) to map its headers buffer,
we reported the feature only if the NIC is supporting KSM and
the minimum value for buffer size is below the requested one.

iperf3 bandwidth comparison:
+---------+--------+--------+-----------+
| streams | SW GRO | HW GRO | Unit      |
|---------+--------+--------+-----------|
| 1       | 36     | 42     | Gbits/sec |
| 4       | 34     | 39     | Gbits/sec |
| 8       | 31     | 35     | Gbits/sec |
+---------+--------+--------+-----------+

A downstream patch will add skb fragment coalescing which will improve
performance considerably.

Benchmark details:
VM based setup
CPU: Intel(R) Xeon(R) Platinum 8380 CPU, 24 cores
NIC: ConnectX-7 100GbE
iperf3 and irq running on same CPU over a single receive queue

Signed-off-by: Yoray Zack <yorayz@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://lore.kernel.org/r/20240603212219.1037656-14-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/mellanox/mlx5/core/en_main.c | 26 +++++++++++++++++++
 include/linux/mlx5/mlx5_ifc.h                 | 16 ++++++++----
 2 files changed, 37 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 2a3e0de51f0e4..44a64d062e422 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -74,6 +74,27 @@
 #include "lib/devcom.h"
 #include "lib/sd.h"
 
+static bool mlx5e_hw_gro_supported(struct mlx5_core_dev *mdev)
+{
+	if (!MLX5_CAP_GEN(mdev, shampo))
+		return false;
+
+	/* Our HW-GRO implementation relies on "KSM Mkey" for
+	 * SHAMPO headers buffer mapping
+	 */
+	if (!MLX5_CAP_GEN(mdev, fixed_buffer_size))
+		return false;
+
+	if (!MLX5_CAP_GEN_2(mdev, min_mkey_log_entity_size_fixed_buffer_valid))
+		return false;
+
+	if (MLX5_CAP_GEN_2(mdev, min_mkey_log_entity_size_fixed_buffer) >
+	    MLX5E_SHAMPO_LOG_HEADER_ENTRY_SIZE)
+		return false;
+
+	return true;
+}
+
 bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev, u8 page_shift,
 					    enum mlx5e_mpwrq_umr_mode umr_mode)
 {
@@ -5331,6 +5352,11 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 	netdev->hw_features      |= NETIF_F_HW_VLAN_CTAG_FILTER;
 	netdev->hw_features      |= NETIF_F_HW_VLAN_STAG_TX;
 
+	if (mlx5e_hw_gro_supported(mdev) &&
+	    mlx5e_check_fragmented_striding_rq_cap(mdev, PAGE_SHIFT,
+						   MLX5E_MPWRQ_UMR_MODE_ALIGNED))
+		netdev->hw_features    |= NETIF_F_GRO_HW;
+
 	if (mlx5e_tunnel_any_tx_proto_supported(mdev)) {
 		netdev->hw_enc_features |= NETIF_F_HW_CSUM;
 		netdev->hw_enc_features |= NETIF_F_TSO;
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 5df52e15f7d6c..17acd0f3ca8ed 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1526,8 +1526,7 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         ts_cqe_to_dest_cqn[0x1];
 	u8         reserved_at_b3[0x6];
 	u8         go_back_n[0x1];
-	u8         shampo[0x1];
-	u8         reserved_at_bb[0x5];
+	u8         reserved_at_ba[0x6];
 
 	u8         max_sgl_for_optimized_performance[0x8];
 	u8         log_max_cq_sz[0x8];
@@ -1744,7 +1743,9 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         reserved_at_280[0x10];
 	u8         max_wqe_sz_sq[0x10];
 
-	u8         reserved_at_2a0[0x10];
+	u8         reserved_at_2a0[0xb];
+	u8         shampo[0x1];
+	u8         reserved_at_2ac[0x4];
 	u8         max_wqe_sz_rq[0x10];
 
 	u8         max_flow_counter_31_16[0x10];
@@ -2017,7 +2018,8 @@ struct mlx5_ifc_cmd_hca_cap_2_bits {
 	u8	   reserved_at_250[0x10];
 
 	u8	   reserved_at_260[0x120];
-	u8	   reserved_at_380[0x10];
+	u8	   reserved_at_380[0xb];
+	u8	   min_mkey_log_entity_size_fixed_buffer[0x5];
 	u8	   ec_vf_vport_base[0x10];
 
 	u8	   reserved_at_3a0[0x10];
@@ -2029,7 +2031,11 @@ struct mlx5_ifc_cmd_hca_cap_2_bits {
 	u8	   pcc_ifa2[0x1];
 	u8	   reserved_at_3f1[0xf];
 
-	u8	   reserved_at_400[0x400];
+	u8	   reserved_at_400[0x1];
+	u8	   min_mkey_log_entity_size_fixed_buffer_valid[0x1];
+	u8	   reserved_at_402[0x1e];
+
+	u8	   reserved_at_420[0x3e0];
 };
 
 enum mlx5_ifc_flow_destination_type {
-- 
GitLab


From 14ae2fd12be8c5089e43fee8a21cd8631699b97a Mon Sep 17 00:00:00 2001
From: Dragos Tatulea <dtatulea@nvidia.com>
Date: Tue, 4 Jun 2024 00:22:19 +0300
Subject: [PATCH 850/950] net/mlx5e: SHAMPO, Coalesce skb fragments to page
 size

When doing hardware GRO (SHAMPO), the driver puts each data payload of a
packet from the wire into one skb fragment. TCP Zero-Copy expects page
sized skb fragments to be able to do it's page-flipping magic. With the
current way of arranging fragments by the driver, only specific MTUs
(page sized multiple + header size) will yield such page sized fragments
in a high percentage.

This change improves payload arrangement in the skb for hardware GRO by
coalescing payloads into a single skb fragment when possible.

To demonstrate the fix, running tcp_mmap with a MTU of 1500 yields:
- Before:  0 % bytes mmap'ed
- After : 81 % bytes mmap'ed

More importantly, coalescing considerably improves the HW GRO performance.
Here are the results for a iperf3 bandwidth benchmark:
+---------+--------+--------+------------------------+-----------+
| streams | SW GRO | HW GRO | HW GRO with coalescing | Unit      |
|---------+--------+--------+------------------------+-----------|
| 1       | 36     | 42     | 57                     | Gbits/sec |
| 4       | 34     | 39     | 50                     | Gbits/sec |
| 8       | 31     | 35     | 43                     | Gbits/sec |
+---------+--------+--------+------------------------+-----------+

Benchmark details:
VM based setup
CPU: Intel(R) Xeon(R) Platinum 8380 CPU, 24 cores
NIC: ConnectX-7 100GbE
iperf3 and irq running on same CPU over a single receive queue

Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://lore.kernel.org/r/20240603212219.1037656-15-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/mellanox/mlx5/core/en_rx.c   | 19 +++++++++++++------
 1 file changed, 13 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index f1fbf60d0356e..43f018567fafc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -523,15 +523,23 @@ mlx5e_add_skb_shared_info_frag(struct mlx5e_rq *rq, struct skb_shared_info *sinf
 
 static inline void
 mlx5e_add_skb_frag(struct mlx5e_rq *rq, struct sk_buff *skb,
-		   struct page *page, u32 frag_offset, u32 len,
+		   struct mlx5e_frag_page *frag_page,
+		   u32 frag_offset, u32 len,
 		   unsigned int truesize)
 {
-	dma_addr_t addr = page_pool_get_dma_addr(page);
+	dma_addr_t addr = page_pool_get_dma_addr(frag_page->page);
+	u8 next_frag = skb_shinfo(skb)->nr_frags;
 
 	dma_sync_single_for_cpu(rq->pdev, addr + frag_offset, len,
 				rq->buff.map_dir);
-	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
-			page, frag_offset, len, truesize);
+
+	if (skb_can_coalesce(skb, next_frag, frag_page->page, frag_offset)) {
+		skb_coalesce_rx_frag(skb, next_frag - 1, len, truesize);
+	} else {
+		frag_page->frags++;
+		skb_add_rx_frag(skb, next_frag, frag_page->page,
+				frag_offset, len, truesize);
+	}
 }
 
 static inline void
@@ -1956,8 +1964,7 @@ mlx5e_shampo_fill_skb_data(struct sk_buff *skb, struct mlx5e_rq *rq,
 		u32 pg_consumed_bytes = min_t(u32, PAGE_SIZE - data_offset, data_bcnt);
 		unsigned int truesize = pg_consumed_bytes;
 
-		frag_page->frags++;
-		mlx5e_add_skb_frag(rq, skb, frag_page->page, data_offset,
+		mlx5e_add_skb_frag(rq, skb, frag_page, data_offset,
 				   pg_consumed_bytes, truesize);
 
 		data_bcnt -= pg_consumed_bytes;
-- 
GitLab


From 118e640af30c1355cfea1eeaa2960dc9331ee3db Mon Sep 17 00:00:00 2001
From: Paul Barker <paul.barker.ct@bp.renesas.com>
Date: Tue, 4 Jun 2024 08:28:19 +0100
Subject: [PATCH 851/950] net: ravb: Simplify poll & receive functions

We don't need to pass the work budget to ravb_rx() by reference, it's
cleaner to pass this by value and return the amount of work done. This
allows us to simplify the ravb_poll() function and use the common
`work_done` variable name seen in other network drivers for consistency
and ease of understanding.

This is a pure refactor and should not affect behaviour.

Signed-off-by: Paul Barker <paul.barker.ct@bp.renesas.com>
Reviewed-by: Sergey Shtylyov <s.shtylyov@omp.ru>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/renesas/ravb.h      |  2 +-
 drivers/net/ethernet/renesas/ravb_main.c | 27 +++++++++++-------------
 2 files changed, 13 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/renesas/ravb.h b/drivers/net/ethernet/renesas/ravb.h
index b48935ec7e28d..71de2a7aa27cd 100644
--- a/drivers/net/ethernet/renesas/ravb.h
+++ b/drivers/net/ethernet/renesas/ravb.h
@@ -1039,7 +1039,7 @@ struct ravb_ptp {
 };
 
 struct ravb_hw_info {
-	bool (*receive)(struct net_device *ndev, int *quota, int q);
+	int (*receive)(struct net_device *ndev, int budget, int q);
 	void (*set_rate)(struct net_device *ndev);
 	int (*set_feature)(struct net_device *ndev, netdev_features_t features);
 	int (*dmac_init)(struct net_device *ndev);
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index 4d100283c30fb..193ad05383a8d 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -759,7 +759,7 @@ static struct sk_buff *ravb_get_skb_gbeth(struct net_device *ndev, int entry,
 }
 
 /* Packet receive function for Gigabit Ethernet */
-static bool ravb_rx_gbeth(struct net_device *ndev, int *quota, int q)
+static int ravb_rx_gbeth(struct net_device *ndev, int budget, int q)
 {
 	struct ravb_private *priv = netdev_priv(ndev);
 	const struct ravb_hw_info *info = priv->info;
@@ -781,7 +781,7 @@ static bool ravb_rx_gbeth(struct net_device *ndev, int *quota, int q)
 	for (i = 0; i < limit; i++, priv->cur_rx[q]++) {
 		entry = priv->cur_rx[q] % priv->num_rx_ring[q];
 		desc = &priv->rx_ring[q].desc[entry];
-		if (rx_packets == *quota || desc->die_dt == DT_FEMPTY)
+		if (rx_packets == budget || desc->die_dt == DT_FEMPTY)
 			break;
 
 		/* Descriptor type must be checked before all other reads */
@@ -882,12 +882,11 @@ static bool ravb_rx_gbeth(struct net_device *ndev, int *quota, int q)
 	}
 
 	stats->rx_packets += rx_packets;
-	*quota -= rx_packets;
-	return *quota == 0;
+	return rx_packets;
 }
 
 /* Packet receive function for Ethernet AVB */
-static bool ravb_rx_rcar(struct net_device *ndev, int *quota, int q)
+static int ravb_rx_rcar(struct net_device *ndev, int budget, int q)
 {
 	struct ravb_private *priv = netdev_priv(ndev);
 	const struct ravb_hw_info *info = priv->info;
@@ -906,7 +905,7 @@ static bool ravb_rx_rcar(struct net_device *ndev, int *quota, int q)
 	for (i = 0; i < limit; i++, priv->cur_rx[q]++) {
 		entry = priv->cur_rx[q] % priv->num_rx_ring[q];
 		desc = &priv->rx_ring[q].ex_desc[entry];
-		if (rx_packets == *quota || desc->die_dt == DT_FEMPTY)
+		if (rx_packets == budget || desc->die_dt == DT_FEMPTY)
 			break;
 
 		/* Descriptor type must be checked before all other reads */
@@ -992,17 +991,16 @@ static bool ravb_rx_rcar(struct net_device *ndev, int *quota, int q)
 	}
 
 	stats->rx_packets += rx_packets;
-	*quota -= rx_packets;
-	return *quota == 0;
+	return rx_packets;
 }
 
 /* Packet receive function for Ethernet AVB */
-static bool ravb_rx(struct net_device *ndev, int *quota, int q)
+static int ravb_rx(struct net_device *ndev, int budget, int q)
 {
 	struct ravb_private *priv = netdev_priv(ndev);
 	const struct ravb_hw_info *info = priv->info;
 
-	return info->receive(ndev, quota, q);
+	return info->receive(ndev, budget, q);
 }
 
 static void ravb_rcv_snd_disable(struct net_device *ndev)
@@ -1319,13 +1317,12 @@ static int ravb_poll(struct napi_struct *napi, int budget)
 	unsigned long flags;
 	int q = napi - priv->napi;
 	int mask = BIT(q);
-	int quota = budget;
-	bool unmask;
+	int work_done;
 
 	/* Processing RX Descriptor Ring */
 	/* Clear RX interrupt */
 	ravb_write(ndev, ~(mask | RIS0_RESERVED), RIS0);
-	unmask = !ravb_rx(ndev, &quota, q);
+	work_done = ravb_rx(ndev, budget, q);
 
 	/* Processing TX Descriptor Ring */
 	spin_lock_irqsave(&priv->lock, flags);
@@ -1344,7 +1341,7 @@ static int ravb_poll(struct napi_struct *napi, int budget)
 	if (priv->rx_fifo_errors != ndev->stats.rx_fifo_errors)
 		ndev->stats.rx_fifo_errors = priv->rx_fifo_errors;
 
-	if (!unmask)
+	if (work_done == budget)
 		goto out;
 
 	napi_complete(napi);
@@ -1361,7 +1358,7 @@ static int ravb_poll(struct napi_struct *napi, int budget)
 	spin_unlock_irqrestore(&priv->lock, flags);
 
 out:
-	return budget - quota;
+	return work_done;
 }
 
 static void ravb_set_duplex_gbeth(struct net_device *ndev)
-- 
GitLab


From b0e0e20dc60e9e37b7e5bc71f0c912f66ad75529 Mon Sep 17 00:00:00 2001
From: Paul Barker <paul.barker.ct@bp.renesas.com>
Date: Tue, 4 Jun 2024 08:28:20 +0100
Subject: [PATCH 852/950] net: ravb: Align poll function with NAPI docs

Align ravb_poll() with the documentation in
`Documentation/networking/kapi.rst` and
`Documentation/networking/napi.rst`.

The documentation says that we should prefer napi_complete_done() over
napi_complete(), and using the former allows us to properly support busy
polling. We should ensure that napi_complete_done() is only called if
the work budget has not been exhausted, and we should only re-arm
interrupts if it returns true.

Signed-off-by: Paul Barker <paul.barker.ct@bp.renesas.com>
Reviewed-by: Sergey Shtylyov <s.shtylyov@omp.ru>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/renesas/ravb_main.c | 26 ++++++++++--------------
 1 file changed, 11 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index 193ad05383a8d..472aa80002bef 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -1341,23 +1341,19 @@ static int ravb_poll(struct napi_struct *napi, int budget)
 	if (priv->rx_fifo_errors != ndev->stats.rx_fifo_errors)
 		ndev->stats.rx_fifo_errors = priv->rx_fifo_errors;
 
-	if (work_done == budget)
-		goto out;
-
-	napi_complete(napi);
-
-	/* Re-enable RX/TX interrupts */
-	spin_lock_irqsave(&priv->lock, flags);
-	if (!info->irq_en_dis) {
-		ravb_modify(ndev, RIC0, mask, mask);
-		ravb_modify(ndev, TIC,  mask, mask);
-	} else {
-		ravb_write(ndev, mask, RIE0);
-		ravb_write(ndev, mask, TIE);
+	if (work_done < budget && napi_complete_done(napi, work_done)) {
+		/* Re-enable RX/TX interrupts */
+		spin_lock_irqsave(&priv->lock, flags);
+		if (!info->irq_en_dis) {
+			ravb_modify(ndev, RIC0, mask, mask);
+			ravb_modify(ndev, TIC,  mask, mask);
+		} else {
+			ravb_write(ndev, mask, RIE0);
+			ravb_write(ndev, mask, TIE);
+		}
+		spin_unlock_irqrestore(&priv->lock, flags);
 	}
-	spin_unlock_irqrestore(&priv->lock, flags);
 
-out:
 	return work_done;
 }
 
-- 
GitLab


From 37a01c12e9e89fe2545657d7b42ca2de9c780c45 Mon Sep 17 00:00:00 2001
From: Paul Barker <paul.barker.ct@bp.renesas.com>
Date: Tue, 4 Jun 2024 08:28:21 +0100
Subject: [PATCH 853/950] net: ravb: Refactor RX ring refill

To reduce code duplication, we add a new RX ring refill function which
can handle both the initial RX ring population (which was split between
ravb_ring_init() and ravb_ring_format()) and the RX ring refill after
polling (in ravb_rx()).

Signed-off-by: Paul Barker <paul.barker.ct@bp.renesas.com>
Reviewed-by: Sergey Shtylyov <s.shtylyov@omp.ru>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/renesas/ravb_main.c | 150 +++++++++--------------
 1 file changed, 57 insertions(+), 93 deletions(-)

diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index 472aa80002bef..63d03929e3f5e 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -317,35 +317,43 @@ static void ravb_ring_free(struct net_device *ndev, int q)
 	priv->tx_skb[q] = NULL;
 }
 
-static void ravb_rx_ring_format(struct net_device *ndev, int q)
+static u32
+ravb_rx_ring_refill(struct net_device *ndev, int q, u32 count, gfp_t gfp_mask)
 {
 	struct ravb_private *priv = netdev_priv(ndev);
+	const struct ravb_hw_info *info = priv->info;
 	struct ravb_rx_desc *rx_desc;
-	unsigned int rx_ring_size;
 	dma_addr_t dma_addr;
-	unsigned int i;
+	u32 i, entry;
 
-	rx_ring_size = priv->info->rx_desc_size * priv->num_rx_ring[q];
-	memset(priv->rx_ring[q].raw, 0, rx_ring_size);
-	/* Build RX ring buffer */
-	for (i = 0; i < priv->num_rx_ring[q]; i++) {
-		/* RX descriptor */
-		rx_desc = ravb_rx_get_desc(priv, q, i);
-		rx_desc->ds_cc = cpu_to_le16(priv->info->rx_max_desc_use);
-		dma_addr = dma_map_single(ndev->dev.parent, priv->rx_skb[q][i]->data,
-					  priv->info->rx_max_frame_size,
-					  DMA_FROM_DEVICE);
-		/* We just set the data size to 0 for a failed mapping which
-		 * should prevent DMA from happening...
-		 */
-		if (dma_mapping_error(ndev->dev.parent, dma_addr))
-			rx_desc->ds_cc = cpu_to_le16(0);
-		rx_desc->dptr = cpu_to_le32(dma_addr);
+	for (i = 0; i < count; i++) {
+		entry = (priv->dirty_rx[q] + i) % priv->num_rx_ring[q];
+		rx_desc = ravb_rx_get_desc(priv, q, entry);
+		rx_desc->ds_cc = cpu_to_le16(info->rx_max_desc_use);
+
+		if (!priv->rx_skb[q][entry]) {
+			priv->rx_skb[q][entry] = ravb_alloc_skb(ndev, info,
+								gfp_mask);
+			if (!priv->rx_skb[q][entry])
+				break;
+			dma_addr = dma_map_single(ndev->dev.parent,
+						  priv->rx_skb[q][entry]->data,
+						  priv->info->rx_max_frame_size,
+						  DMA_FROM_DEVICE);
+			skb_checksum_none_assert(priv->rx_skb[q][entry]);
+			/* We just set the data size to 0 for a failed mapping
+			 * which should prevent DMA from happening...
+			 */
+			if (dma_mapping_error(ndev->dev.parent, dma_addr))
+				rx_desc->ds_cc = cpu_to_le16(0);
+			rx_desc->dptr = cpu_to_le32(dma_addr);
+		}
+		/* Descriptor type must be set after all the above writes */
+		dma_wmb();
 		rx_desc->die_dt = DT_FEMPTY;
 	}
-	rx_desc = ravb_rx_get_desc(priv, q, i);
-	rx_desc->dptr = cpu_to_le32((u32)priv->rx_desc_dma[q]);
-	rx_desc->die_dt = DT_LINKFIX; /* type */
+
+	return i;
 }
 
 /* Format skb and descriptor buffer for Ethernet AVB */
@@ -353,6 +361,7 @@ static void ravb_ring_format(struct net_device *ndev, int q)
 {
 	struct ravb_private *priv = netdev_priv(ndev);
 	unsigned int num_tx_desc = priv->num_tx_desc;
+	struct ravb_rx_desc *rx_desc;
 	struct ravb_tx_desc *tx_desc;
 	struct ravb_desc *desc;
 	unsigned int tx_ring_size = sizeof(*tx_desc) * priv->num_tx_ring[q] *
@@ -364,7 +373,13 @@ static void ravb_ring_format(struct net_device *ndev, int q)
 	priv->dirty_rx[q] = 0;
 	priv->dirty_tx[q] = 0;
 
-	ravb_rx_ring_format(ndev, q);
+	/* Regular RX descriptors have already been initialized by
+	 * ravb_rx_ring_refill(), we just need to initialize the final link
+	 * descriptor.
+	 */
+	rx_desc = ravb_rx_get_desc(priv, q, priv->num_rx_ring[q]);
+	rx_desc->dptr = cpu_to_le32((u32)priv->rx_desc_dma[q]);
+	rx_desc->die_dt = DT_LINKFIX; /* type */
 
 	memset(priv->tx_ring[q], 0, tx_ring_size);
 	/* Build TX ring buffer */
@@ -408,11 +423,9 @@ static void *ravb_alloc_rx_desc(struct net_device *ndev, int q)
 static int ravb_ring_init(struct net_device *ndev, int q)
 {
 	struct ravb_private *priv = netdev_priv(ndev);
-	const struct ravb_hw_info *info = priv->info;
 	unsigned int num_tx_desc = priv->num_tx_desc;
 	unsigned int ring_size;
-	struct sk_buff *skb;
-	unsigned int i;
+	u32 num_filled;
 
 	/* Allocate RX and TX skb rings */
 	priv->rx_skb[q] = kcalloc(priv->num_rx_ring[q],
@@ -422,12 +435,18 @@ static int ravb_ring_init(struct net_device *ndev, int q)
 	if (!priv->rx_skb[q] || !priv->tx_skb[q])
 		goto error;
 
-	for (i = 0; i < priv->num_rx_ring[q]; i++) {
-		skb = ravb_alloc_skb(ndev, info, GFP_KERNEL);
-		if (!skb)
-			goto error;
-		priv->rx_skb[q][i] = skb;
-	}
+	/* Allocate all RX descriptors. */
+	if (!ravb_alloc_rx_desc(ndev, q))
+		goto error;
+
+	/* Populate RX ring buffer. */
+	priv->dirty_rx[q] = 0;
+	ring_size = priv->info->rx_desc_size * priv->num_rx_ring[q];
+	memset(priv->rx_ring[q].raw, 0, ring_size);
+	num_filled = ravb_rx_ring_refill(ndev, q, priv->num_rx_ring[q],
+					 GFP_KERNEL);
+	if (num_filled != priv->num_rx_ring[q])
+		goto error;
 
 	if (num_tx_desc > 1) {
 		/* Allocate rings for the aligned buffers */
@@ -437,12 +456,6 @@ static int ravb_ring_init(struct net_device *ndev, int q)
 			goto error;
 	}
 
-	/* Allocate all RX descriptors. */
-	if (!ravb_alloc_rx_desc(ndev, q))
-		goto error;
-
-	priv->dirty_rx[q] = 0;
-
 	/* Allocate all TX descriptors. */
 	ring_size = sizeof(struct ravb_tx_desc) *
 		    (priv->num_tx_ring[q] * num_tx_desc + 1);
@@ -762,11 +775,9 @@ static struct sk_buff *ravb_get_skb_gbeth(struct net_device *ndev, int entry,
 static int ravb_rx_gbeth(struct net_device *ndev, int budget, int q)
 {
 	struct ravb_private *priv = netdev_priv(ndev);
-	const struct ravb_hw_info *info = priv->info;
 	struct net_device_stats *stats;
 	struct ravb_rx_desc *desc;
 	struct sk_buff *skb;
-	dma_addr_t dma_addr;
 	int rx_packets = 0;
 	u8  desc_status;
 	u16 desc_len;
@@ -854,32 +865,9 @@ static int ravb_rx_gbeth(struct net_device *ndev, int budget, int q)
 	}
 
 	/* Refill the RX ring buffers. */
-	for (; priv->cur_rx[q] - priv->dirty_rx[q] > 0; priv->dirty_rx[q]++) {
-		entry = priv->dirty_rx[q] % priv->num_rx_ring[q];
-		desc = &priv->rx_ring[q].desc[entry];
-		desc->ds_cc = cpu_to_le16(priv->info->rx_max_desc_use);
-
-		if (!priv->rx_skb[q][entry]) {
-			skb = ravb_alloc_skb(ndev, info, GFP_ATOMIC);
-			if (!skb)
-				break;
-			dma_addr = dma_map_single(ndev->dev.parent,
-						  skb->data,
-						  priv->info->rx_max_frame_size,
-						  DMA_FROM_DEVICE);
-			skb_checksum_none_assert(skb);
-			/* We just set the data size to 0 for a failed mapping
-			 * which should prevent DMA  from happening...
-			 */
-			if (dma_mapping_error(ndev->dev.parent, dma_addr))
-				desc->ds_cc = cpu_to_le16(0);
-			desc->dptr = cpu_to_le32(dma_addr);
-			priv->rx_skb[q][entry] = skb;
-		}
-		/* Descriptor type must be set after all the above writes */
-		dma_wmb();
-		desc->die_dt = DT_FEMPTY;
-	}
+	priv->dirty_rx[q] += ravb_rx_ring_refill(ndev, q,
+						 priv->cur_rx[q] - priv->dirty_rx[q],
+						 GFP_ATOMIC);
 
 	stats->rx_packets += rx_packets;
 	return rx_packets;
@@ -889,12 +877,10 @@ static int ravb_rx_gbeth(struct net_device *ndev, int budget, int q)
 static int ravb_rx_rcar(struct net_device *ndev, int budget, int q)
 {
 	struct ravb_private *priv = netdev_priv(ndev);
-	const struct ravb_hw_info *info = priv->info;
 	struct net_device_stats *stats = &priv->stats[q];
 	struct ravb_ex_rx_desc *desc;
 	unsigned int limit, i;
 	struct sk_buff *skb;
-	dma_addr_t dma_addr;
 	struct timespec64 ts;
 	int rx_packets = 0;
 	u8  desc_status;
@@ -964,31 +950,9 @@ static int ravb_rx_rcar(struct net_device *ndev, int budget, int q)
 	}
 
 	/* Refill the RX ring buffers. */
-	for (; priv->cur_rx[q] - priv->dirty_rx[q] > 0; priv->dirty_rx[q]++) {
-		entry = priv->dirty_rx[q] % priv->num_rx_ring[q];
-		desc = &priv->rx_ring[q].ex_desc[entry];
-		desc->ds_cc = cpu_to_le16(priv->info->rx_max_desc_use);
-
-		if (!priv->rx_skb[q][entry]) {
-			skb = ravb_alloc_skb(ndev, info, GFP_ATOMIC);
-			if (!skb)
-				break;	/* Better luck next round. */
-			dma_addr = dma_map_single(ndev->dev.parent, skb->data,
-						  priv->info->rx_max_frame_size,
-						  DMA_FROM_DEVICE);
-			skb_checksum_none_assert(skb);
-			/* We just set the data size to 0 for a failed mapping
-			 * which should prevent DMA  from happening...
-			 */
-			if (dma_mapping_error(ndev->dev.parent, dma_addr))
-				desc->ds_cc = cpu_to_le16(0);
-			desc->dptr = cpu_to_le32(dma_addr);
-			priv->rx_skb[q][entry] = skb;
-		}
-		/* Descriptor type must be set after all the above writes */
-		dma_wmb();
-		desc->die_dt = DT_FEMPTY;
-	}
+	priv->dirty_rx[q] += ravb_rx_ring_refill(ndev, q,
+						 priv->cur_rx[q] - priv->dirty_rx[q],
+						 GFP_ATOMIC);
 
 	stats->rx_packets += rx_packets;
 	return rx_packets;
-- 
GitLab


From 3ee43f09cb2cd7643d5a4bfbc78a9f75f6a563af Mon Sep 17 00:00:00 2001
From: Paul Barker <paul.barker.ct@bp.renesas.com>
Date: Tue, 4 Jun 2024 08:28:22 +0100
Subject: [PATCH 854/950] net: ravb: Refactor GbEth RX code path

We can reduce code duplication in ravb_rx_gbeth().

Signed-off-by: Paul Barker <paul.barker.ct@bp.renesas.com>
Reviewed-by: Sergey Shtylyov <s.shtylyov@omp.ru>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/renesas/ravb_main.c | 59 +++++++++++++-----------
 1 file changed, 32 insertions(+), 27 deletions(-)

diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index 63d03929e3f5e..e8c3f48b213d9 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -819,47 +819,52 @@ static int ravb_rx_gbeth(struct net_device *ndev, int budget, int q)
 				stats->rx_missed_errors++;
 		} else {
 			die_dt = desc->die_dt & 0xF0;
+			skb = ravb_get_skb_gbeth(ndev, entry, desc);
 			switch (die_dt) {
 			case DT_FSINGLE:
-				skb = ravb_get_skb_gbeth(ndev, entry, desc);
-				skb_put(skb, desc_len);
-				skb->protocol = eth_type_trans(skb, ndev);
-				if (ndev->features & NETIF_F_RXCSUM)
-					ravb_rx_csum_gbeth(skb);
-				napi_gro_receive(&priv->napi[q], skb);
-				rx_packets++;
-				stats->rx_bytes += desc_len;
-				break;
 			case DT_FSTART:
-				priv->rx_1st_skb = ravb_get_skb_gbeth(ndev, entry, desc);
-				skb_put(priv->rx_1st_skb, desc_len);
+				/* Start of packet: Set initial data length. */
+				skb_put(skb, desc_len);
+
+				/* Save this skb if the packet spans multiple
+				 * descriptors.
+				 */
+				if (die_dt == DT_FSTART)
+					priv->rx_1st_skb = skb;
 				break;
+
 			case DT_FMID:
-				skb = ravb_get_skb_gbeth(ndev, entry, desc);
-				skb_copy_to_linear_data_offset(priv->rx_1st_skb,
-							       priv->rx_1st_skb->len,
-							       skb->data,
-							       desc_len);
-				skb_put(priv->rx_1st_skb, desc_len);
-				dev_kfree_skb(skb);
-				break;
 			case DT_FEND:
-				skb = ravb_get_skb_gbeth(ndev, entry, desc);
+				/* Continuing a packet: Move data into the saved
+				 * skb.
+				 */
 				skb_copy_to_linear_data_offset(priv->rx_1st_skb,
 							       priv->rx_1st_skb->len,
 							       skb->data,
 							       desc_len);
 				skb_put(priv->rx_1st_skb, desc_len);
 				dev_kfree_skb(skb);
-				priv->rx_1st_skb->protocol =
-					eth_type_trans(priv->rx_1st_skb, ndev);
+
+				/* Set skb to point at the whole packet so that
+				 * we only need one code path for finishing a
+				 * packet.
+				 */
+				skb = priv->rx_1st_skb;
+			}
+
+			switch (die_dt) {
+			case DT_FSINGLE:
+			case DT_FEND:
+				/* Finishing a packet: Determine protocol &
+				 * checksum, hand off to NAPI and update our
+				 * stats.
+				 */
+				skb->protocol = eth_type_trans(skb, ndev);
 				if (ndev->features & NETIF_F_RXCSUM)
-					ravb_rx_csum_gbeth(priv->rx_1st_skb);
-				stats->rx_bytes += priv->rx_1st_skb->len;
-				napi_gro_receive(&priv->napi[q],
-						 priv->rx_1st_skb);
+					ravb_rx_csum_gbeth(skb);
+				stats->rx_bytes += skb->len;
+				napi_gro_receive(&priv->napi[q], skb);
 				rx_packets++;
-				break;
 			}
 		}
 	}
-- 
GitLab


From 7b39c1814ce3bcdf95d026bbb27322218840a27d Mon Sep 17 00:00:00 2001
From: Paul Barker <paul.barker.ct@bp.renesas.com>
Date: Tue, 4 Jun 2024 08:28:23 +0100
Subject: [PATCH 855/950] net: ravb: Enable SW IRQ Coalescing for GbEth

Software IRQ Coalescing is required to improve network stack performance
in the RZ/G2L SoC family and the RZ/G3S SoC, i.e. the SoCs which use the
GbEth IP.

This patch gives the following improvements during testing with iperf3:

  * RZ/G2L:
    * TCP RX: same bandwidth with -6% CPU load (76% -> 71%)
    * UDP RX: same bandwidth with -10% CPU load (99% -> 89%)

  * RZ/G2UL:
    * UDP RX: +4200% bandwidth (1.23Mbps -> 53Mbps)

  * RZ/G3S:
    * UDP RX: +425% bandwidth (1.23Mbps -> 6.46Mbps)

The improvement of UDP RX bandwidth for the single core SoCs (RZ/G2UL &
RZ/G3S) is particularly critical.

Signed-off-by: Paul Barker <paul.barker.ct@bp.renesas.com>
Reviewed-by: Sergey Shtylyov <s.shtylyov@omp.ru>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/renesas/ravb.h      | 1 +
 drivers/net/ethernet/renesas/ravb_main.c | 4 ++++
 2 files changed, 5 insertions(+)

diff --git a/drivers/net/ethernet/renesas/ravb.h b/drivers/net/ethernet/renesas/ravb.h
index 71de2a7aa27cd..6a7aa7dd17e6c 100644
--- a/drivers/net/ethernet/renesas/ravb.h
+++ b/drivers/net/ethernet/renesas/ravb.h
@@ -1054,6 +1054,7 @@ struct ravb_hw_info {
 	u32 rx_max_desc_use;
 	u32 rx_desc_size;
 	unsigned aligned_tx: 1;
+	unsigned coalesce_irqs:1;	/* Needs software IRQ coalescing */
 
 	/* hardware features */
 	unsigned internal_delay:1;	/* AVB-DMAC has internal delays */
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index e8c3f48b213d9..2c24cb0271af4 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -2667,6 +2667,7 @@ static const struct ravb_hw_info gbeth_hw_info = {
 	.rx_max_desc_use = 4080,
 	.rx_desc_size = sizeof(struct ravb_rx_desc),
 	.aligned_tx = 1,
+	.coalesce_irqs = 1,
 	.tx_counters = 1,
 	.carrier_counters = 1,
 	.half_duplex = 1,
@@ -2943,6 +2944,9 @@ static int ravb_probe(struct platform_device *pdev)
 	if (info->nc_queues)
 		netif_napi_add(ndev, &priv->napi[RAVB_NC], ravb_poll);
 
+	if (info->coalesce_irqs)
+		netdev_sw_irq_coalesce_default_on(ndev);
+
 	/* Network device register */
 	error = register_netdev(ndev);
 	if (error)
-- 
GitLab


From 65c482bc226ab25a7884ee6fd1cc09bb08cbd1be Mon Sep 17 00:00:00 2001
From: Paul Barker <paul.barker.ct@bp.renesas.com>
Date: Tue, 4 Jun 2024 08:28:24 +0100
Subject: [PATCH 856/950] net: ravb: Use NAPI threaded mode on 1-core CPUs with
 GbEth IP

NAPI Threaded mode (along with the previously enabled SW IRQ Coalescing)
is required to improve network stack performance for single core SoCs
using the GbEth IP (currently the RZ/G2L SoC family and the RZ/G3S SoC).

This patch gives the following improvements during testing with iperf3.

  * RZ/G2UL:
    * TCP TX: +32% bandwidth (638Mbps -> 841Mbps)
    * TXP RX: +8.8% bandwidth (667Mbps -> 726Mbps)
    * UDP RX: +104% bandwidth (53Mbps -> 108Mbps)

  * RZ/G3S:
    * TCP TX: 29% bandwidth (529Mbps -> 681Mbps)
    * UDP RX: +1290% bandwidth (6.46Mbps -> 90Mbps)

  * RZ/Five:
    * UDP RX: Test no longer crashes (0 -> 20 Mbps)

This patch gives the following reductions in performance in the same
testing:

  * RZ/G2UL:
    * UDP TX: -7.5% bandwidth (594Mbps -> 549Mbps)

  * RZ/G3S:
    * UDP TX: -5% bandwidth (625Mbps -> 594Mbps)

These losses are considered acceptable given the benefits shown above.
If UDP TX bandwidth must be maximised for a particular use case, NAPI
threaded mode can be disabled at runtime via sysfs writes.

The improvement of UDP RX bandwidth for the single core SoCs (RZ/G2UL &
RZ/G3S) is particularly critical.

Signed-off-by: Paul Barker <paul.barker.ct@bp.renesas.com>
Reviewed-by: Sergey Shtylyov <s.shtylyov@omp.ru>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/renesas/ravb_main.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index 2c24cb0271af4..c89bb38492b48 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -2944,8 +2944,11 @@ static int ravb_probe(struct platform_device *pdev)
 	if (info->nc_queues)
 		netif_napi_add(ndev, &priv->napi[RAVB_NC], ravb_poll);
 
-	if (info->coalesce_irqs)
+	if (info->coalesce_irqs) {
 		netdev_sw_irq_coalesce_default_on(ndev);
+		if (num_present_cpus() == 1)
+			dev_set_threaded(ndev, true);
+	}
 
 	/* Network device register */
 	error = register_netdev(ndev);
-- 
GitLab


From 966726324b7b14009216fda33b47e0bc003944c6 Mon Sep 17 00:00:00 2001
From: Paul Barker <paul.barker.ct@bp.renesas.com>
Date: Tue, 4 Jun 2024 08:28:25 +0100
Subject: [PATCH 857/950] net: ravb: Allocate RX buffers via page pool

This patch makes multiple changes that can't be separated:

  1) Allocate plain RX buffers via a page pool instead of allocating
     SKBs, then use build_skb() when a packet is received.
  2) For GbEth IP, reduce the RX buffer size to 2kB.
  3) For GbEth IP, merge packets which span more than one RX descriptor
     as SKB fragments instead of copying data.

Implementing (1) without (2) would require the use of an order-1 page
pool (instead of an order-0 page pool split into page fragments) for
GbEth.

Implementing (2) without (3) would leave us no space to re-assemble
packets which span more than one RX descriptor.

Implementing (3) without (1) would not be possible as the network stack
expects to use put_page() or page_pool_put_page() to free SKB fragments
after an SKB is consumed.

RX checksum offload support is adjusted to handle both linear and
nonlinear (fragmented) packets.

This patch gives the following improvements during testing with iperf3.

  * RZ/G2L:
    * TCP RX: same bandwidth at -43% CPU load (70% -> 40%)
    * UDP RX: same bandwidth at -17% CPU load (88% -> 74%)

  * RZ/G2UL:
    * TCP RX: +30% bandwidth (726Mbps -> 941Mbps)
    * UDP RX: +417% bandwidth (108Mbps -> 558Mbps)

  * RZ/G3S:
    * TCP RX: +64% bandwidth (562Mbps -> 920Mbps)
    * UDP RX: +420% bandwidth (90Mbps -> 468Mbps)

  * RZ/Five:
    * TCP RX: +217% bandwidth (145Mbps -> 459Mbps)
    * UDP RX: +470% bandwidth (20Mbps -> 114Mbps)

There is no significant impact on bandwidth or CPU load in testing on
RZ/G2H or R-Car M3N.

Signed-off-by: Paul Barker <paul.barker.ct@bp.renesas.com>
Reviewed-by: Sergey Shtylyov <s.shtylyov@omp.ru>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/renesas/ravb.h      |  11 +-
 drivers/net/ethernet/renesas/ravb_main.c | 260 +++++++++++++++--------
 2 files changed, 175 insertions(+), 96 deletions(-)

diff --git a/drivers/net/ethernet/renesas/ravb.h b/drivers/net/ethernet/renesas/ravb.h
index 6a7aa7dd17e6c..6b2444d31fcc3 100644
--- a/drivers/net/ethernet/renesas/ravb.h
+++ b/drivers/net/ethernet/renesas/ravb.h
@@ -19,6 +19,7 @@
 #include <linux/phy.h>
 #include <linux/platform_device.h>
 #include <linux/ptp_clock_kernel.h>
+#include <net/page_pool/types.h>
 
 #define BE_TX_RING_SIZE	64	/* TX ring size for Best Effort */
 #define BE_RX_RING_SIZE	1024	/* RX ring size for Best Effort */
@@ -1051,7 +1052,7 @@ struct ravb_hw_info {
 	int stats_len;
 	u32 tccr_mask;
 	u32 rx_max_frame_size;
-	u32 rx_max_desc_use;
+	u32 rx_buffer_size;
 	u32 rx_desc_size;
 	unsigned aligned_tx: 1;
 	unsigned coalesce_irqs:1;	/* Needs software IRQ coalescing */
@@ -1071,6 +1072,11 @@ struct ravb_hw_info {
 	unsigned half_duplex:1;		/* E-MAC supports half duplex mode */
 };
 
+struct ravb_rx_buffer {
+	struct page *page;
+	unsigned int offset;
+};
+
 struct ravb_private {
 	struct net_device *ndev;
 	struct platform_device *pdev;
@@ -1094,7 +1100,8 @@ struct ravb_private {
 	struct ravb_tx_desc *tx_ring[NUM_TX_QUEUE];
 	void *tx_align[NUM_TX_QUEUE];
 	struct sk_buff *rx_1st_skb;
-	struct sk_buff **rx_skb[NUM_RX_QUEUE];
+	struct page_pool *rx_pool[NUM_RX_QUEUE];
+	struct ravb_rx_buffer *rx_buffers[NUM_RX_QUEUE];
 	struct sk_buff **tx_skb[NUM_TX_QUEUE];
 	u32 rx_over_errors;
 	u32 rx_fifo_errors;
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index c89bb38492b48..c1546b916e4ef 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -30,6 +30,7 @@
 #include <linux/reset.h>
 #include <linux/math64.h>
 #include <net/ip.h>
+#include <net/page_pool/helpers.h>
 
 #include "ravb.h"
 
@@ -113,25 +114,6 @@ static void ravb_set_rate_rcar(struct net_device *ndev)
 	}
 }
 
-static struct sk_buff *
-ravb_alloc_skb(struct net_device *ndev, const struct ravb_hw_info *info,
-	       gfp_t gfp_mask)
-{
-	struct sk_buff *skb;
-	u32 reserve;
-
-	skb = __netdev_alloc_skb(ndev, info->rx_max_frame_size + RAVB_ALIGN - 1,
-				 gfp_mask);
-	if (!skb)
-		return NULL;
-
-	reserve = (unsigned long)skb->data & (RAVB_ALIGN - 1);
-	if (reserve)
-		skb_reserve(skb, RAVB_ALIGN - reserve);
-
-	return skb;
-}
-
 /* Get MAC address from the MAC address registers
  *
  * Ethernet AVB device doesn't have ROM for MAC address.
@@ -257,21 +239,10 @@ static void ravb_rx_ring_free(struct net_device *ndev, int q)
 {
 	struct ravb_private *priv = netdev_priv(ndev);
 	unsigned int ring_size;
-	unsigned int i;
 
 	if (!priv->rx_ring[q].raw)
 		return;
 
-	for (i = 0; i < priv->num_rx_ring[q]; i++) {
-		struct ravb_rx_desc *desc = ravb_rx_get_desc(priv, q, i);
-
-		if (!dma_mapping_error(ndev->dev.parent,
-				       le32_to_cpu(desc->dptr)))
-			dma_unmap_single(ndev->dev.parent,
-					 le32_to_cpu(desc->dptr),
-					 priv->info->rx_max_frame_size,
-					 DMA_FROM_DEVICE);
-	}
 	ring_size = priv->info->rx_desc_size * (priv->num_rx_ring[q] + 1);
 	dma_free_coherent(ndev->dev.parent, ring_size, priv->rx_ring[q].raw,
 			  priv->rx_desc_dma[q]);
@@ -298,13 +269,16 @@ static void ravb_ring_free(struct net_device *ndev, int q)
 		priv->tx_ring[q] = NULL;
 	}
 
-	/* Free RX skb ringbuffer */
-	if (priv->rx_skb[q]) {
-		for (i = 0; i < priv->num_rx_ring[q]; i++)
-			dev_kfree_skb(priv->rx_skb[q][i]);
+	/* Free RX buffers */
+	for (i = 0; i < priv->num_rx_ring[q]; i++) {
+		if (priv->rx_buffers[q][i].page)
+			page_pool_put_page(priv->rx_pool[q],
+					   priv->rx_buffers[q][i].page,
+					   0, true);
 	}
-	kfree(priv->rx_skb[q]);
-	priv->rx_skb[q] = NULL;
+	kfree(priv->rx_buffers[q]);
+	priv->rx_buffers[q] = NULL;
+	page_pool_destroy(priv->rx_pool[q]);
 
 	/* Free aligned TX buffers */
 	kfree(priv->tx_align[q]);
@@ -317,36 +291,57 @@ static void ravb_ring_free(struct net_device *ndev, int q)
 	priv->tx_skb[q] = NULL;
 }
 
+static int
+ravb_alloc_rx_buffer(struct net_device *ndev, int q, u32 entry, gfp_t gfp_mask,
+		     struct ravb_rx_desc *rx_desc)
+{
+	struct ravb_private *priv = netdev_priv(ndev);
+	const struct ravb_hw_info *info = priv->info;
+	struct ravb_rx_buffer *rx_buff;
+	dma_addr_t dma_addr;
+	unsigned int size;
+
+	rx_buff = &priv->rx_buffers[q][entry];
+	size = info->rx_buffer_size;
+	rx_buff->page = page_pool_alloc(priv->rx_pool[q], &rx_buff->offset,
+					&size, gfp_mask);
+	if (unlikely(!rx_buff->page)) {
+		/* We just set the data size to 0 for a failed mapping which
+		 * should prevent DMA from happening...
+		 */
+		rx_desc->ds_cc = cpu_to_le16(0);
+		return -ENOMEM;
+	}
+
+	dma_addr = page_pool_get_dma_addr(rx_buff->page) + rx_buff->offset;
+	dma_sync_single_for_device(ndev->dev.parent, dma_addr,
+				   info->rx_buffer_size, DMA_FROM_DEVICE);
+	rx_desc->dptr = cpu_to_le32(dma_addr);
+
+	/* The end of the RX buffer is used to store skb shared data, so we need
+	 * to ensure that the hardware leaves enough space for this.
+	 */
+	rx_desc->ds_cc = cpu_to_le16(info->rx_buffer_size -
+				     SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) -
+				     ETH_FCS_LEN + sizeof(__sum16));
+	return 0;
+}
+
 static u32
 ravb_rx_ring_refill(struct net_device *ndev, int q, u32 count, gfp_t gfp_mask)
 {
 	struct ravb_private *priv = netdev_priv(ndev);
-	const struct ravb_hw_info *info = priv->info;
 	struct ravb_rx_desc *rx_desc;
-	dma_addr_t dma_addr;
 	u32 i, entry;
 
 	for (i = 0; i < count; i++) {
 		entry = (priv->dirty_rx[q] + i) % priv->num_rx_ring[q];
 		rx_desc = ravb_rx_get_desc(priv, q, entry);
-		rx_desc->ds_cc = cpu_to_le16(info->rx_max_desc_use);
 
-		if (!priv->rx_skb[q][entry]) {
-			priv->rx_skb[q][entry] = ravb_alloc_skb(ndev, info,
-								gfp_mask);
-			if (!priv->rx_skb[q][entry])
+		if (!priv->rx_buffers[q][entry].page) {
+			if (unlikely(ravb_alloc_rx_buffer(ndev, q, entry,
+							  gfp_mask, rx_desc)))
 				break;
-			dma_addr = dma_map_single(ndev->dev.parent,
-						  priv->rx_skb[q][entry]->data,
-						  priv->info->rx_max_frame_size,
-						  DMA_FROM_DEVICE);
-			skb_checksum_none_assert(priv->rx_skb[q][entry]);
-			/* We just set the data size to 0 for a failed mapping
-			 * which should prevent DMA from happening...
-			 */
-			if (dma_mapping_error(ndev->dev.parent, dma_addr))
-				rx_desc->ds_cc = cpu_to_le16(0);
-			rx_desc->dptr = cpu_to_le32(dma_addr);
 		}
 		/* Descriptor type must be set after all the above writes */
 		dma_wmb();
@@ -424,15 +419,32 @@ static int ravb_ring_init(struct net_device *ndev, int q)
 {
 	struct ravb_private *priv = netdev_priv(ndev);
 	unsigned int num_tx_desc = priv->num_tx_desc;
+	struct page_pool_params params = {
+		.order = 0,
+		.flags = PP_FLAG_DMA_MAP,
+		.pool_size = priv->num_rx_ring[q],
+		.nid = NUMA_NO_NODE,
+		.dev = ndev->dev.parent,
+		.dma_dir = DMA_FROM_DEVICE,
+	};
 	unsigned int ring_size;
 	u32 num_filled;
 
-	/* Allocate RX and TX skb rings */
-	priv->rx_skb[q] = kcalloc(priv->num_rx_ring[q],
-				  sizeof(*priv->rx_skb[q]), GFP_KERNEL);
+	/* Allocate RX page pool and buffers */
+	priv->rx_pool[q] = page_pool_create(&params);
+	if (IS_ERR(priv->rx_pool[q]))
+		goto error;
+
+	/* Allocate RX buffers */
+	priv->rx_buffers[q] = kcalloc(priv->num_rx_ring[q],
+				      sizeof(*priv->rx_buffers[q]), GFP_KERNEL);
+	if (!priv->rx_buffers[q])
+		goto error;
+
+	/* Allocate TX skb rings */
 	priv->tx_skb[q] = kcalloc(priv->num_tx_ring[q],
 				  sizeof(*priv->tx_skb[q]), GFP_KERNEL);
-	if (!priv->rx_skb[q] || !priv->tx_skb[q])
+	if (!priv->tx_skb[q])
 		goto error;
 
 	/* Allocate all RX descriptors. */
@@ -719,7 +731,9 @@ static void ravb_get_tx_tstamp(struct net_device *ndev)
 
 static void ravb_rx_csum_gbeth(struct sk_buff *skb)
 {
+	struct skb_shared_info *shinfo = skb_shinfo(skb);
 	__wsum csum_ip_hdr, csum_proto;
+	skb_frag_t *last_frag;
 	u8 *hw_csum;
 
 	/* The hardware checksum status is contained in sizeof(__sum16) * 2 = 4
@@ -729,12 +743,24 @@ static void ravb_rx_csum_gbeth(struct sk_buff *skb)
 	if (unlikely(skb->len < sizeof(__sum16) * 2))
 		return;
 
-	hw_csum = skb_tail_pointer(skb) - sizeof(__sum16);
+	if (skb_is_nonlinear(skb)) {
+		last_frag = &shinfo->frags[shinfo->nr_frags - 1];
+		hw_csum = skb_frag_address(last_frag) +
+			  skb_frag_size(last_frag);
+	} else {
+		hw_csum = skb_tail_pointer(skb);
+	}
+
+	hw_csum -= sizeof(__sum16);
 	csum_proto = csum_unfold((__force __sum16)get_unaligned_le16(hw_csum));
 
 	hw_csum -= sizeof(__sum16);
 	csum_ip_hdr = csum_unfold((__force __sum16)get_unaligned_le16(hw_csum));
-	skb_trim(skb, skb->len - 2 * sizeof(__sum16));
+
+	if (skb_is_nonlinear(skb))
+		skb_frag_size_sub(last_frag, 2 * sizeof(__sum16));
+	else
+		skb_trim(skb, skb->len - 2 * sizeof(__sum16));
 
 	/* TODO: IPV6 Rx checksum */
 	if (skb->protocol == htons(ETH_P_IP) && !csum_ip_hdr && !csum_proto)
@@ -756,25 +782,11 @@ static void ravb_rx_csum(struct sk_buff *skb)
 	skb_trim(skb, skb->len - sizeof(__sum16));
 }
 
-static struct sk_buff *ravb_get_skb_gbeth(struct net_device *ndev, int entry,
-					  struct ravb_rx_desc *desc)
-{
-	struct ravb_private *priv = netdev_priv(ndev);
-	struct sk_buff *skb;
-
-	skb = priv->rx_skb[RAVB_BE][entry];
-	priv->rx_skb[RAVB_BE][entry] = NULL;
-	dma_unmap_single(ndev->dev.parent, le32_to_cpu(desc->dptr),
-			 ALIGN(priv->info->rx_max_frame_size, 16),
-			 DMA_FROM_DEVICE);
-
-	return skb;
-}
-
 /* Packet receive function for Gigabit Ethernet */
 static int ravb_rx_gbeth(struct net_device *ndev, int budget, int q)
 {
 	struct ravb_private *priv = netdev_priv(ndev);
+	const struct ravb_hw_info *info = priv->info;
 	struct net_device_stats *stats;
 	struct ravb_rx_desc *desc;
 	struct sk_buff *skb;
@@ -818,12 +830,30 @@ static int ravb_rx_gbeth(struct net_device *ndev, int budget, int q)
 			if (desc_status & MSC_CEEF)
 				stats->rx_missed_errors++;
 		} else {
+			struct ravb_rx_buffer *rx_buff;
+			void *rx_addr;
+
+			rx_buff = &priv->rx_buffers[q][entry];
+			rx_addr = page_address(rx_buff->page) + rx_buff->offset;
 			die_dt = desc->die_dt & 0xF0;
-			skb = ravb_get_skb_gbeth(ndev, entry, desc);
+			dma_sync_single_for_cpu(ndev->dev.parent,
+						le32_to_cpu(desc->dptr),
+						desc_len, DMA_FROM_DEVICE);
+
 			switch (die_dt) {
 			case DT_FSINGLE:
 			case DT_FSTART:
 				/* Start of packet: Set initial data length. */
+				skb = napi_build_skb(rx_addr,
+						     info->rx_buffer_size);
+				if (unlikely(!skb)) {
+					stats->rx_errors++;
+					page_pool_put_page(priv->rx_pool[q],
+							   rx_buff->page, 0,
+							   true);
+					goto refill;
+				}
+				skb_mark_for_recycle(skb);
 				skb_put(skb, desc_len);
 
 				/* Save this skb if the packet spans multiple
@@ -835,15 +865,30 @@ static int ravb_rx_gbeth(struct net_device *ndev, int budget, int q)
 
 			case DT_FMID:
 			case DT_FEND:
-				/* Continuing a packet: Move data into the saved
-				 * skb.
+				/* Continuing a packet: Add this buffer as an RX
+				 * frag.
+				 */
+
+				/* rx_1st_skb will be NULL if napi_build_skb()
+				 * failed for the first descriptor of a
+				 * multi-descriptor packet.
 				 */
-				skb_copy_to_linear_data_offset(priv->rx_1st_skb,
-							       priv->rx_1st_skb->len,
-							       skb->data,
-							       desc_len);
-				skb_put(priv->rx_1st_skb, desc_len);
-				dev_kfree_skb(skb);
+				if (unlikely(!priv->rx_1st_skb)) {
+					stats->rx_errors++;
+					page_pool_put_page(priv->rx_pool[q],
+							   rx_buff->page, 0,
+							   true);
+
+					/* We may find a DT_FSINGLE or DT_FSTART
+					 * descriptor in the queue which we can
+					 * process, so don't give up yet.
+					 */
+					continue;
+				}
+				skb_add_rx_frag(priv->rx_1st_skb,
+						skb_shinfo(priv->rx_1st_skb)->nr_frags,
+						rx_buff->page, rx_buff->offset,
+						desc_len, info->rx_buffer_size);
 
 				/* Set skb to point at the whole packet so that
 				 * we only need one code path for finishing a
@@ -865,10 +910,19 @@ static int ravb_rx_gbeth(struct net_device *ndev, int budget, int q)
 				stats->rx_bytes += skb->len;
 				napi_gro_receive(&priv->napi[q], skb);
 				rx_packets++;
+
+				/* Clear rx_1st_skb so that it will only be
+				 * non-NULL when valid.
+				 */
+				priv->rx_1st_skb = NULL;
 			}
+
+			/* Mark this RX buffer as consumed. */
+			rx_buff->page = NULL;
 		}
 	}
 
+refill:
 	/* Refill the RX ring buffers. */
 	priv->dirty_rx[q] += ravb_rx_ring_refill(ndev, q,
 						 priv->cur_rx[q] - priv->dirty_rx[q],
@@ -882,6 +936,7 @@ static int ravb_rx_gbeth(struct net_device *ndev, int budget, int q)
 static int ravb_rx_rcar(struct net_device *ndev, int budget, int q)
 {
 	struct ravb_private *priv = netdev_priv(ndev);
+	const struct ravb_hw_info *info = priv->info;
 	struct net_device_stats *stats = &priv->stats[q];
 	struct ravb_ex_rx_desc *desc;
 	unsigned int limit, i;
@@ -924,12 +979,23 @@ static int ravb_rx_rcar(struct net_device *ndev, int budget, int q)
 				stats->rx_missed_errors++;
 		} else {
 			u32 get_ts = priv->tstamp_rx_ctrl & RAVB_RXTSTAMP_TYPE;
-
-			skb = priv->rx_skb[q][entry];
-			priv->rx_skb[q][entry] = NULL;
-			dma_unmap_single(ndev->dev.parent, le32_to_cpu(desc->dptr),
-					 priv->info->rx_max_frame_size,
-					 DMA_FROM_DEVICE);
+			struct ravb_rx_buffer *rx_buff;
+			void *rx_addr;
+
+			rx_buff = &priv->rx_buffers[q][entry];
+			rx_addr = page_address(rx_buff->page) + rx_buff->offset;
+			dma_sync_single_for_cpu(ndev->dev.parent,
+						le32_to_cpu(desc->dptr),
+						pkt_len, DMA_FROM_DEVICE);
+
+			skb = napi_build_skb(rx_addr, info->rx_buffer_size);
+			if (unlikely(!skb)) {
+				stats->rx_errors++;
+				page_pool_put_page(priv->rx_pool[q],
+						   rx_buff->page, 0, true);
+				break;
+			}
+			skb_mark_for_recycle(skb);
 			get_ts &= (q == RAVB_NC) ?
 					RAVB_RXTSTAMP_TYPE_V2_L2_EVENT :
 					~RAVB_RXTSTAMP_TYPE_V2_L2_EVENT;
@@ -951,6 +1017,9 @@ static int ravb_rx_rcar(struct net_device *ndev, int budget, int q)
 			napi_gro_receive(&priv->napi[q], skb);
 			rx_packets++;
 			stats->rx_bytes += pkt_len;
+
+			/* Mark this RX buffer as consumed. */
+			rx_buff->page = NULL;
 		}
 	}
 
@@ -2596,7 +2665,8 @@ static const struct ravb_hw_info ravb_gen3_hw_info = {
 	.stats_len = ARRAY_SIZE(ravb_gstrings_stats),
 	.tccr_mask = TCCR_TSRQ0 | TCCR_TSRQ1 | TCCR_TSRQ2 | TCCR_TSRQ3,
 	.rx_max_frame_size = SZ_2K,
-	.rx_max_desc_use = SZ_2K - ETH_FCS_LEN + sizeof(__sum16),
+	.rx_buffer_size = SZ_2K +
+			  SKB_DATA_ALIGN(sizeof(struct skb_shared_info)),
 	.rx_desc_size = sizeof(struct ravb_ex_rx_desc),
 	.internal_delay = 1,
 	.tx_counters = 1,
@@ -2620,7 +2690,8 @@ static const struct ravb_hw_info ravb_gen2_hw_info = {
 	.stats_len = ARRAY_SIZE(ravb_gstrings_stats),
 	.tccr_mask = TCCR_TSRQ0 | TCCR_TSRQ1 | TCCR_TSRQ2 | TCCR_TSRQ3,
 	.rx_max_frame_size = SZ_2K,
-	.rx_max_desc_use = SZ_2K - ETH_FCS_LEN + sizeof(__sum16),
+	.rx_buffer_size = SZ_2K +
+			  SKB_DATA_ALIGN(sizeof(struct skb_shared_info)),
 	.rx_desc_size = sizeof(struct ravb_ex_rx_desc),
 	.aligned_tx = 1,
 	.gptp = 1,
@@ -2641,7 +2712,8 @@ static const struct ravb_hw_info ravb_rzv2m_hw_info = {
 	.stats_len = ARRAY_SIZE(ravb_gstrings_stats),
 	.tccr_mask = TCCR_TSRQ0 | TCCR_TSRQ1 | TCCR_TSRQ2 | TCCR_TSRQ3,
 	.rx_max_frame_size = SZ_2K,
-	.rx_max_desc_use = SZ_2K - ETH_FCS_LEN + sizeof(__sum16),
+	.rx_buffer_size = SZ_2K +
+			  SKB_DATA_ALIGN(sizeof(struct skb_shared_info)),
 	.rx_desc_size = sizeof(struct ravb_ex_rx_desc),
 	.multi_irqs = 1,
 	.err_mgmt_irqs = 1,
@@ -2664,7 +2736,7 @@ static const struct ravb_hw_info gbeth_hw_info = {
 	.stats_len = ARRAY_SIZE(ravb_gstrings_stats_gbeth),
 	.tccr_mask = TCCR_TSRQ0,
 	.rx_max_frame_size = SZ_8K,
-	.rx_max_desc_use = 4080,
+	.rx_buffer_size = SZ_2K,
 	.rx_desc_size = sizeof(struct ravb_rx_desc),
 	.aligned_tx = 1,
 	.coalesce_irqs = 1,
-- 
GitLab


From b0c9a26435413b81799047a7be53255640432547 Mon Sep 17 00:00:00 2001
From: Aleksandr Mishin <amishin@t-argos.ru>
Date: Tue, 4 Jun 2024 11:25:00 +0300
Subject: [PATCH 858/950] net: wwan: iosm: Fix tainted pointer delete is case
 of region creation fail

In case of region creation fail in ipc_devlink_create_region(), previously
created regions delete process starts from tainted pointer which actually
holds error code value.
Fix this bug by decreasing region index before delete.

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

Fixes: 4dcd183fbd67 ("net: wwan: iosm: devlink registration")
Signed-off-by: Aleksandr Mishin <amishin@t-argos.ru>
Acked-by: Sergey Ryazanov <ryazanov.s.a@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20240604082500.20769-1-amishin@t-argos.ru
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/wwan/iosm/iosm_ipc_devlink.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wwan/iosm/iosm_ipc_devlink.c b/drivers/net/wwan/iosm/iosm_ipc_devlink.c
index bef6819986e93..33d6342124bc3 100644
--- a/drivers/net/wwan/iosm/iosm_ipc_devlink.c
+++ b/drivers/net/wwan/iosm/iosm_ipc_devlink.c
@@ -211,7 +211,7 @@ static int ipc_devlink_create_region(struct iosm_devlink *devlink)
 			rc = PTR_ERR(devlink->cd_regions[i]);
 			dev_err(devlink->dev, "Devlink region fail,err %d", rc);
 			/* Delete previously created regions */
-			for ( ; i >= 0; i--)
+			for (i--; i >= 0; i--)
 				devlink_region_destroy(devlink->cd_regions[i]);
 			goto region_create_fail;
 		}
-- 
GitLab


From b4cb4a1391dcdc640c4ade003aaf0ee19cc8d509 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 4 Jun 2024 11:16:03 +0000
Subject: [PATCH 859/950] net: use unrcu_pointer() helper
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Toke mentioned unrcu_pointer() existence, allowing
to remove some of the ugly casts we have when using
xchg() for rcu protected pointers.

Also make inet_rcv_compat const.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Toke Høiland-Jørgensen <toke@redhat.com>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Link: https://lore.kernel.org/r/20240604111603.45871-1-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/net/sock.h       | 2 +-
 net/core/gen_estimator.c | 2 +-
 net/core/sock_diag.c     | 8 +++-----
 net/ipv4/cipso_ipv4.c    | 2 +-
 net/ipv4/tcp.c           | 2 +-
 net/ipv4/tcp_fastopen.c  | 7 ++++---
 net/ipv4/udp.c           | 2 +-
 net/ipv6/af_inet6.c      | 2 +-
 net/ipv6/ip6_fib.c       | 2 +-
 net/ipv6/ipv6_sockglue.c | 3 +--
 net/ipv6/route.c         | 6 +++---
 net/sched/act_api.c      | 2 +-
 12 files changed, 19 insertions(+), 21 deletions(-)

diff --git a/include/net/sock.h b/include/net/sock.h
index 953c8dc4e259e..b30ea0c342a65 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2095,7 +2095,7 @@ sk_dst_set(struct sock *sk, struct dst_entry *dst)
 
 	sk_tx_queue_clear(sk);
 	WRITE_ONCE(sk->sk_dst_pending_confirm, 0);
-	old_dst = xchg((__force struct dst_entry **)&sk->sk_dst_cache, dst);
+	old_dst = unrcu_pointer(xchg(&sk->sk_dst_cache, RCU_INITIALIZER(dst)));
 	dst_release(old_dst);
 }
 
diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c
index fae9c4694186e..412816076b8bc 100644
--- a/net/core/gen_estimator.c
+++ b/net/core/gen_estimator.c
@@ -206,7 +206,7 @@ void gen_kill_estimator(struct net_rate_estimator __rcu **rate_est)
 {
 	struct net_rate_estimator *est;
 
-	est = xchg((__force struct net_rate_estimator **)rate_est, NULL);
+	est = unrcu_pointer(xchg(rate_est, NULL));
 	if (est) {
 		timer_shutdown_sync(&est->timer);
 		kfree_rcu(est, rcu);
diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c
index 6541228380252..a08eed9b9142e 100644
--- a/net/core/sock_diag.c
+++ b/net/core/sock_diag.c
@@ -18,7 +18,7 @@
 
 static const struct sock_diag_handler __rcu *sock_diag_handlers[AF_MAX];
 
-static struct sock_diag_inet_compat __rcu *inet_rcv_compat;
+static const struct sock_diag_inet_compat __rcu *inet_rcv_compat;
 
 static struct workqueue_struct *broadcast_wq;
 
@@ -187,8 +187,7 @@ void sock_diag_broadcast_destroy(struct sock *sk)
 
 void sock_diag_register_inet_compat(const struct sock_diag_inet_compat *ptr)
 {
-	xchg((__force const struct sock_diag_inet_compat **)&inet_rcv_compat,
-	     ptr);
+	xchg(&inet_rcv_compat, RCU_INITIALIZER(ptr));
 }
 EXPORT_SYMBOL_GPL(sock_diag_register_inet_compat);
 
@@ -196,8 +195,7 @@ void sock_diag_unregister_inet_compat(const struct sock_diag_inet_compat *ptr)
 {
 	const struct sock_diag_inet_compat *old;
 
-	old = xchg((__force const struct sock_diag_inet_compat **)&inet_rcv_compat,
-		   NULL);
+	old = unrcu_pointer(xchg(&inet_rcv_compat, NULL));
 	WARN_ON_ONCE(old != ptr);
 }
 EXPORT_SYMBOL_GPL(sock_diag_unregister_inet_compat);
diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index dd6d460150580..3a95c0f13ce33 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -1953,7 +1953,7 @@ int cipso_v4_req_setattr(struct request_sock *req,
 	buf = NULL;
 
 	req_inet = inet_rsk(req);
-	opt = xchg((__force struct ip_options_rcu **)&req_inet->ireq_opt, opt);
+	opt = unrcu_pointer(xchg(&req_inet->ireq_opt, RCU_INITIALIZER(opt)));
 	if (opt)
 		kfree_rcu(opt, rcu);
 
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index fa43aaacd92bc..f727bc8d82a6d 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3081,7 +3081,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	icsk->icsk_ack.rcv_mss = TCP_MIN_MSS;
 	memset(&tp->rx_opt, 0, sizeof(tp->rx_opt));
 	__sk_dst_reset(sk);
-	dst_release(xchg((__force struct dst_entry **)&sk->sk_rx_dst, NULL));
+	dst_release(unrcu_pointer(xchg(&sk->sk_rx_dst, NULL)));
 	tcp_saved_syn_free(tp);
 	tp->compressed_ack = 0;
 	tp->segs_in = 0;
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 8ed54e7334a9c..0f523cbfe329e 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -49,7 +49,7 @@ void tcp_fastopen_ctx_destroy(struct net *net)
 {
 	struct tcp_fastopen_context *ctxt;
 
-	ctxt = xchg((__force struct tcp_fastopen_context **)&net->ipv4.tcp_fastopen_ctx, NULL);
+	ctxt = unrcu_pointer(xchg(&net->ipv4.tcp_fastopen_ctx, NULL));
 
 	if (ctxt)
 		call_rcu(&ctxt->rcu, tcp_fastopen_ctx_free);
@@ -80,9 +80,10 @@ int tcp_fastopen_reset_cipher(struct net *net, struct sock *sk,
 
 	if (sk) {
 		q = &inet_csk(sk)->icsk_accept_queue.fastopenq;
-		octx = xchg((__force struct tcp_fastopen_context **)&q->ctx, ctx);
+		octx = unrcu_pointer(xchg(&q->ctx, RCU_INITIALIZER(ctx)));
 	} else {
-		octx = xchg((__force struct tcp_fastopen_context **)&net->ipv4.tcp_fastopen_ctx, ctx);
+		octx = unrcu_pointer(xchg(&net->ipv4.tcp_fastopen_ctx,
+					  RCU_INITIALIZER(ctx)));
 	}
 
 	if (octx)
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 189c9113fe9a1..c9ca6d285347b 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2230,7 +2230,7 @@ bool udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst)
 	struct dst_entry *old;
 
 	if (dst_hold_safe(dst)) {
-		old = xchg((__force struct dst_entry **)&sk->sk_rx_dst, dst);
+		old = unrcu_pointer(xchg(&sk->sk_rx_dst, RCU_INITIALIZER(dst)));
 		dst_release(old);
 		return old != dst;
 	}
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 8041dc181bd42..e03fb9a1dbeb4 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -509,7 +509,7 @@ void inet6_cleanup_sock(struct sock *sk)
 
 	/* Free tx options */
 
-	opt = xchg((__force struct ipv6_txoptions **)&np->opt, NULL);
+	opt = unrcu_pointer(xchg(&np->opt, NULL));
 	if (opt) {
 		atomic_sub(opt->tot_len, &sk->sk_omem_alloc);
 		txopt_put(opt);
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 31d77885bcae3..15f9abe506562 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -984,7 +984,7 @@ static void __fib6_drop_pcpu_from(struct fib6_nh *fib6_nh,
 		if (pcpu_rt && rcu_access_pointer(pcpu_rt->from) == match) {
 			struct fib6_info *from;
 
-			from = xchg((__force struct fib6_info **)&pcpu_rt->from, NULL);
+			from = unrcu_pointer(xchg(&pcpu_rt->from, NULL));
 			fib6_info_release(from);
 		}
 	}
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index d4c28ec1bc517..cd342d5015c6f 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -111,8 +111,7 @@ struct ipv6_txoptions *ipv6_update_options(struct sock *sk,
 			icsk->icsk_sync_mss(sk, icsk->icsk_pmtu_cookie);
 		}
 	}
-	opt = xchg((__force struct ipv6_txoptions **)&inet6_sk(sk)->opt,
-		   opt);
+	opt = unrcu_pointer(xchg(&inet6_sk(sk)->opt, RCU_INITIALIZER(opt)));
 	sk_dst_reset(sk);
 
 	return opt;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 12f647d0fec0f..ae6fbdf8995df 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -368,7 +368,7 @@ static void ip6_dst_destroy(struct dst_entry *dst)
 		in6_dev_put(idev);
 	}
 
-	from = xchg((__force struct fib6_info **)&rt->from, NULL);
+	from = unrcu_pointer(xchg(&rt->from, NULL));
 	fib6_info_release(from);
 }
 
@@ -1437,7 +1437,7 @@ static struct rt6_info *rt6_make_pcpu_route(struct net *net,
 	if (res->f6i->fib6_destroying) {
 		struct fib6_info *from;
 
-		from = xchg((__force struct fib6_info **)&pcpu_rt->from, NULL);
+		from = unrcu_pointer(xchg(&pcpu_rt->from, NULL));
 		fib6_info_release(from);
 	}
 
@@ -1466,7 +1466,7 @@ static void rt6_remove_exception(struct rt6_exception_bucket *bucket,
 	/* purge completely the exception to allow releasing the held resources:
 	 * some [sk] cache may keep the dst around for unlimited time
 	 */
-	from = xchg((__force struct fib6_info **)&rt6_ex->rt6i->from, NULL);
+	from = unrcu_pointer(xchg(&rt6_ex->rt6i->from, NULL));
 	fib6_info_release(from);
 	dst_dev_put(&rt6_ex->rt6i->dst);
 
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 9ee622fb1160f..7458b31544262 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -62,7 +62,7 @@ static void tcf_set_action_cookie(struct tc_cookie __rcu **old_cookie,
 {
 	struct tc_cookie *old;
 
-	old = xchg((__force struct tc_cookie **)old_cookie, new_cookie);
+	old = unrcu_pointer(xchg(old_cookie, RCU_INITIALIZER(new_cookie)));
 	if (old)
 		call_rcu(&old->rcu, tcf_free_cookie_rcu);
 }
-- 
GitLab


From 98aa546af5e4f180439c82da403cc77926d3953b Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 4 Jun 2024 16:51:50 +0000
Subject: [PATCH 860/950] inet: remove (struct uncached_list)->quarantine

This list is used to tranfert dst that are handled by
rt_flush_dev() and rt6_uncached_list_flush_dev() out
of the per-cpu lists.

But quarantine list is not used later.

If we simply use list_del_init(&rt->dst.rt_uncached),
this also removes the dst from per-cpu list.

This patch also makes the future calls to rt_del_uncached_list()
and rt6_uncached_list_del() faster, because no spinlock
acquisition is needed anymore.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20240604165150.726382-1-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/ipv4/route.c | 4 +---
 net/ipv6/route.c | 5 +----
 2 files changed, 2 insertions(+), 7 deletions(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index b3073d1c8f8f7..cb0bdf34ed50c 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1481,7 +1481,6 @@ static bool rt_cache_route(struct fib_nh_common *nhc, struct rtable *rt)
 struct uncached_list {
 	spinlock_t		lock;
 	struct list_head	head;
-	struct list_head	quarantine;
 };
 
 static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt_uncached_list);
@@ -1532,7 +1531,7 @@ void rt_flush_dev(struct net_device *dev)
 			rt->dst.dev = blackhole_netdev;
 			netdev_ref_replace(dev, blackhole_netdev,
 					   &rt->dst.dev_tracker, GFP_ATOMIC);
-			list_move(&rt->dst.rt_uncached, &ul->quarantine);
+			list_del_init(&rt->dst.rt_uncached);
 		}
 		spin_unlock_bh(&ul->lock);
 	}
@@ -3661,7 +3660,6 @@ int __init ip_rt_init(void)
 		struct uncached_list *ul = &per_cpu(rt_uncached_list, cpu);
 
 		INIT_LIST_HEAD(&ul->head);
-		INIT_LIST_HEAD(&ul->quarantine);
 		spin_lock_init(&ul->lock);
 	}
 #ifdef CONFIG_IP_ROUTE_CLASSID
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index ae6fbdf8995df..ec5b59b221ef8 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -131,7 +131,6 @@ static struct fib6_info *rt6_get_route_info(struct net *net,
 struct uncached_list {
 	spinlock_t		lock;
 	struct list_head	head;
-	struct list_head	quarantine;
 };
 
 static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt6_uncached_list);
@@ -189,8 +188,7 @@ static void rt6_uncached_list_flush_dev(struct net_device *dev)
 				handled = true;
 			}
 			if (handled)
-				list_move(&rt->dst.rt_uncached,
-					  &ul->quarantine);
+				list_del_init(&rt->dst.rt_uncached);
 		}
 		spin_unlock_bh(&ul->lock);
 	}
@@ -6755,7 +6753,6 @@ int __init ip6_route_init(void)
 		struct uncached_list *ul = per_cpu_ptr(&rt6_uncached_list, cpu);
 
 		INIT_LIST_HEAD(&ul->head);
-		INIT_LIST_HEAD(&ul->quarantine);
 		spin_lock_init(&ul->lock);
 	}
 
-- 
GitLab


From 26bfb8b57063f52b867f9b6c8d1742fcb5bd656c Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Tue, 4 Jun 2024 09:52:27 -0700
Subject: [PATCH 861/950] af_unix: Set sk->sk_state under unix_state_lock() for
 truly disconencted peer.

When a SOCK_DGRAM socket connect()s to another socket, the both sockets'
sk->sk_state are changed to TCP_ESTABLISHED so that we can register them
to BPF SOCKMAP.

When the socket disconnects from the peer by connect(AF_UNSPEC), the state
is set back to TCP_CLOSE.

Then, the peer's state is also set to TCP_CLOSE, but the update is done
locklessly and unconditionally.

Let's say socket A connect()ed to B, B connect()ed to C, and A disconnects
from B.

After the first two connect()s, all three sockets' sk->sk_state are
TCP_ESTABLISHED:

  $ ss -xa
  Netid State  Recv-Q Send-Q  Local Address:Port  Peer Address:PortProcess
  u_dgr ESTAB  0      0       @A 641              * 642
  u_dgr ESTAB  0      0       @B 642              * 643
  u_dgr ESTAB  0      0       @C 643              * 0

And after the disconnect, B's state is TCP_CLOSE even though it's still
connected to C and C's state is TCP_ESTABLISHED.

  $ ss -xa
  Netid State  Recv-Q Send-Q  Local Address:Port  Peer Address:PortProcess
  u_dgr UNCONN 0      0       @A 641              * 0
  u_dgr UNCONN 0      0       @B 642              * 643
  u_dgr ESTAB  0      0       @C 643              * 0

In this case, we cannot register B to SOCKMAP.

So, when a socket disconnects from the peer, we should not set TCP_CLOSE to
the peer if the peer is connected to yet another socket, and this must be
done under unix_state_lock().

Note that we use WRITE_ONCE() for sk->sk_state as there are many lockless
readers.  These data-races will be fixed in the following patches.

Fixes: 83301b5367a9 ("af_unix: Set TCP_ESTABLISHED for datagram sockets too")
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/unix/af_unix.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 25b49efc0926b..b162164b7a420 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -570,7 +570,6 @@ static void unix_dgram_disconnected(struct sock *sk, struct sock *other)
 			sk_error_report(other);
 		}
 	}
-	other->sk_state = TCP_CLOSE;
 }
 
 static void unix_sock_destructor(struct sock *sk)
@@ -1424,8 +1423,15 @@ restart:
 
 		unix_state_double_unlock(sk, other);
 
-		if (other != old_peer)
+		if (other != old_peer) {
 			unix_dgram_disconnected(sk, old_peer);
+
+			unix_state_lock(old_peer);
+			if (!unix_peer(old_peer))
+				WRITE_ONCE(old_peer->sk_state, TCP_CLOSE);
+			unix_state_unlock(old_peer);
+		}
+
 		sock_put(old_peer);
 	} else {
 		unix_peer(sk) = other;
-- 
GitLab


From 942238f9735a4a4ebf8274b218d9a910158941d1 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Tue, 4 Jun 2024 09:52:28 -0700
Subject: [PATCH 862/950] af_unix: Annodate data-races around sk->sk_state for
 writers.

sk->sk_state is changed under unix_state_lock(), but it's read locklessly
in many places.

This patch adds WRITE_ONCE() on the writer side.

We will add READ_ONCE() to the lockless readers in the following patches.

Fixes: 83301b5367a9 ("af_unix: Set TCP_ESTABLISHED for datagram sockets too")
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/unix/af_unix.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index b162164b7a420..424d021a4d7d7 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -616,7 +616,7 @@ static void unix_release_sock(struct sock *sk, int embrion)
 	u->path.dentry = NULL;
 	u->path.mnt = NULL;
 	state = sk->sk_state;
-	sk->sk_state = TCP_CLOSE;
+	WRITE_ONCE(sk->sk_state, TCP_CLOSE);
 
 	skpair = unix_peer(sk);
 	unix_peer(sk) = NULL;
@@ -738,7 +738,8 @@ static int unix_listen(struct socket *sock, int backlog)
 	if (backlog > sk->sk_max_ack_backlog)
 		wake_up_interruptible_all(&u->peer_wait);
 	sk->sk_max_ack_backlog	= backlog;
-	sk->sk_state		= TCP_LISTEN;
+	WRITE_ONCE(sk->sk_state, TCP_LISTEN);
+
 	/* set credentials so connect can copy them */
 	init_peercred(sk);
 	err = 0;
@@ -1401,7 +1402,8 @@ restart:
 		if (err)
 			goto out_unlock;
 
-		sk->sk_state = other->sk_state = TCP_ESTABLISHED;
+		WRITE_ONCE(sk->sk_state, TCP_ESTABLISHED);
+		WRITE_ONCE(other->sk_state, TCP_ESTABLISHED);
 	} else {
 		/*
 		 *	1003.1g breaking connected state with AF_UNSPEC
@@ -1418,7 +1420,7 @@ restart:
 
 		unix_peer(sk) = other;
 		if (!other)
-			sk->sk_state = TCP_CLOSE;
+			WRITE_ONCE(sk->sk_state, TCP_CLOSE);
 		unix_dgram_peer_wake_disconnect_wakeup(sk, old_peer);
 
 		unix_state_double_unlock(sk, other);
@@ -1639,7 +1641,7 @@ restart:
 	copy_peercred(sk, other);
 
 	sock->state	= SS_CONNECTED;
-	sk->sk_state	= TCP_ESTABLISHED;
+	WRITE_ONCE(sk->sk_state, TCP_ESTABLISHED);
 	sock_hold(newsk);
 
 	smp_mb__after_atomic();	/* sock_hold() does an atomic_inc() */
@@ -2050,7 +2052,7 @@ restart_locked:
 			unix_peer(sk) = NULL;
 			unix_dgram_peer_wake_disconnect_wakeup(sk, other);
 
-			sk->sk_state = TCP_CLOSE;
+			WRITE_ONCE(sk->sk_state, TCP_CLOSE);
 			unix_state_unlock(sk);
 
 			unix_dgram_disconnected(sk, other);
-- 
GitLab


From 3a0f38eb285c8c2eead4b3230c7ac2983707599d Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Tue, 4 Jun 2024 09:52:29 -0700
Subject: [PATCH 863/950] af_unix: Annotate data-race of sk->sk_state in
 unix_inq_len().

ioctl(SIOCINQ) calls unix_inq_len() that checks sk->sk_state first
and returns -EINVAL if it's TCP_LISTEN.

Then, for SOCK_STREAM sockets, unix_inq_len() returns the number of
bytes in recvq.

However, unix_inq_len() does not hold unix_state_lock(), and the
concurrent listen() might change the state after checking sk->sk_state.

If the race occurs, 0 is returned for the listener, instead of -EINVAL,
because the length of skb with embryo is 0.

We could hold unix_state_lock() in unix_inq_len(), but it's overkill
given the result is true for pre-listen() TCP_CLOSE state.

So, let's use READ_ONCE() for sk->sk_state in unix_inq_len().

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/unix/af_unix.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 424d021a4d7d7..b37b53767b29b 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -3017,7 +3017,7 @@ long unix_inq_len(struct sock *sk)
 	struct sk_buff *skb;
 	long amount = 0;
 
-	if (sk->sk_state == TCP_LISTEN)
+	if (READ_ONCE(sk->sk_state) == TCP_LISTEN)
 		return -EINVAL;
 
 	spin_lock(&sk->sk_receive_queue.lock);
-- 
GitLab


From eb0718fb3e97ad0d6f4529b810103451c90adf94 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Tue, 4 Jun 2024 09:52:30 -0700
Subject: [PATCH 864/950] af_unix: Annotate data-races around sk->sk_state in
 unix_write_space() and poll().

unix_poll() and unix_dgram_poll() read sk->sk_state locklessly and
calls unix_writable() which also reads sk->sk_state without holding
unix_state_lock().

Let's use READ_ONCE() in unix_poll() and unix_dgram_poll() and pass
it to unix_writable().

While at it, we remove TCP_SYN_SENT check in unix_dgram_poll() as
that state does not exist for AF_UNIX socket since the code was added.

Fixes: 1586a5877db9 ("af_unix: do not report POLLOUT on listeners")
Fixes: 3c73419c09a5 ("af_unix: fix 'poll for write'/ connected DGRAM sockets")
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/unix/af_unix.c | 25 ++++++++++++-------------
 1 file changed, 12 insertions(+), 13 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index b37b53767b29b..3bacf47cb94de 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -530,9 +530,9 @@ static int unix_dgram_peer_wake_me(struct sock *sk, struct sock *other)
 	return 0;
 }
 
-static int unix_writable(const struct sock *sk)
+static int unix_writable(const struct sock *sk, unsigned char state)
 {
-	return sk->sk_state != TCP_LISTEN &&
+	return state != TCP_LISTEN &&
 	       (refcount_read(&sk->sk_wmem_alloc) << 2) <= sk->sk_sndbuf;
 }
 
@@ -541,7 +541,7 @@ static void unix_write_space(struct sock *sk)
 	struct socket_wq *wq;
 
 	rcu_read_lock();
-	if (unix_writable(sk)) {
+	if (unix_writable(sk, READ_ONCE(sk->sk_state))) {
 		wq = rcu_dereference(sk->sk_wq);
 		if (skwq_has_sleeper(wq))
 			wake_up_interruptible_sync_poll(&wq->wait,
@@ -3129,12 +3129,14 @@ static int unix_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned lon
 static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wait)
 {
 	struct sock *sk = sock->sk;
+	unsigned char state;
 	__poll_t mask;
 	u8 shutdown;
 
 	sock_poll_wait(file, sock, wait);
 	mask = 0;
 	shutdown = READ_ONCE(sk->sk_shutdown);
+	state = READ_ONCE(sk->sk_state);
 
 	/* exceptional events? */
 	if (READ_ONCE(sk->sk_err))
@@ -3156,14 +3158,14 @@ static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wa
 
 	/* Connection-based need to check for termination and startup */
 	if ((sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) &&
-	    sk->sk_state == TCP_CLOSE)
+	    state == TCP_CLOSE)
 		mask |= EPOLLHUP;
 
 	/*
 	 * we set writable also when the other side has shut down the
 	 * connection. This prevents stuck sockets.
 	 */
-	if (unix_writable(sk))
+	if (unix_writable(sk, state))
 		mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND;
 
 	return mask;
@@ -3174,12 +3176,14 @@ static __poll_t unix_dgram_poll(struct file *file, struct socket *sock,
 {
 	struct sock *sk = sock->sk, *other;
 	unsigned int writable;
+	unsigned char state;
 	__poll_t mask;
 	u8 shutdown;
 
 	sock_poll_wait(file, sock, wait);
 	mask = 0;
 	shutdown = READ_ONCE(sk->sk_shutdown);
+	state = READ_ONCE(sk->sk_state);
 
 	/* exceptional events? */
 	if (READ_ONCE(sk->sk_err) ||
@@ -3199,19 +3203,14 @@ static __poll_t unix_dgram_poll(struct file *file, struct socket *sock,
 		mask |= EPOLLIN | EPOLLRDNORM;
 
 	/* Connection-based need to check for termination and startup */
-	if (sk->sk_type == SOCK_SEQPACKET) {
-		if (sk->sk_state == TCP_CLOSE)
-			mask |= EPOLLHUP;
-		/* connection hasn't started yet? */
-		if (sk->sk_state == TCP_SYN_SENT)
-			return mask;
-	}
+	if (sk->sk_type == SOCK_SEQPACKET && state == TCP_CLOSE)
+		mask |= EPOLLHUP;
 
 	/* No write status requested, avoid expensive OUT tests. */
 	if (!(poll_requested_events(wait) & (EPOLLWRBAND|EPOLLWRNORM|EPOLLOUT)))
 		return mask;
 
-	writable = unix_writable(sk);
+	writable = unix_writable(sk, state);
 	if (writable) {
 		unix_state_lock(sk);
 
-- 
GitLab


From a9bf9c7dc6a5899c01cb8f6e773a66315a5cd4b7 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Tue, 4 Jun 2024 09:52:31 -0700
Subject: [PATCH 865/950] af_unix: Annotate data-race of sk->sk_state in
 unix_stream_connect().

As small optimisation, unix_stream_connect() prefetches the client's
sk->sk_state without unix_state_lock() and checks if it's TCP_CLOSE.

Later, sk->sk_state is checked again under unix_state_lock().

Let's use READ_ONCE() for the first check and TCP_CLOSE directly for
the second check.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/unix/af_unix.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 3bacf47cb94de..84552826530df 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1481,7 +1481,6 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr,
 	struct sk_buff *skb = NULL;
 	long timeo;
 	int err;
-	int st;
 
 	err = unix_validate_addr(sunaddr, addr_len);
 	if (err)
@@ -1571,9 +1570,7 @@ restart:
 
 	   Well, and we have to recheck the state after socket locked.
 	 */
-	st = sk->sk_state;
-
-	switch (st) {
+	switch (READ_ONCE(sk->sk_state)) {
 	case TCP_CLOSE:
 		/* This is ok... continue with connect */
 		break;
@@ -1588,7 +1585,7 @@ restart:
 
 	unix_state_lock_nested(sk, U_LOCK_SECOND);
 
-	if (sk->sk_state != st) {
+	if (sk->sk_state != TCP_CLOSE) {
 		unix_state_unlock(sk);
 		unix_state_unlock(other);
 		sock_put(other);
-- 
GitLab


From 1b536948e805aab61a48c5aa5db10c9afee880bd Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Tue, 4 Jun 2024 09:52:32 -0700
Subject: [PATCH 866/950] af_unix: Annotate data-race of sk->sk_state in
 unix_accept().

Once sk->sk_state is changed to TCP_LISTEN, it never changes.

unix_accept() takes the advantage and reads sk->sk_state without
holding unix_state_lock().

Let's use READ_ONCE() there.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/unix/af_unix.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 84552826530df..4763c26ae480a 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1710,7 +1710,7 @@ static int unix_accept(struct socket *sock, struct socket *newsock,
 		goto out;
 
 	arg->err = -EINVAL;
-	if (sk->sk_state != TCP_LISTEN)
+	if (READ_ONCE(sk->sk_state) != TCP_LISTEN)
 		goto out;
 
 	/* If socket state is TCP_LISTEN it cannot change (for now...),
-- 
GitLab


From 8a34d4e8d9742a24f74998f45a6a98edd923319b Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Tue, 4 Jun 2024 09:52:33 -0700
Subject: [PATCH 867/950] af_unix: Annotate data-races around sk->sk_state in
 sendmsg() and recvmsg().

The following functions read sk->sk_state locklessly and proceed only if
the state is TCP_ESTABLISHED.

  * unix_stream_sendmsg
  * unix_stream_read_generic
  * unix_seqpacket_sendmsg
  * unix_seqpacket_recvmsg

Let's use READ_ONCE() there.

Fixes: a05d2ad1c1f3 ("af_unix: Only allow recv on connected seqpacket sockets.")
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/unix/af_unix.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 4763c26ae480a..4ef9c21783a5a 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2226,7 +2226,7 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 	}
 
 	if (msg->msg_namelen) {
-		err = sk->sk_state == TCP_ESTABLISHED ? -EISCONN : -EOPNOTSUPP;
+		err = READ_ONCE(sk->sk_state) == TCP_ESTABLISHED ? -EISCONN : -EOPNOTSUPP;
 		goto out_err;
 	} else {
 		err = -ENOTCONN;
@@ -2340,7 +2340,7 @@ static int unix_seqpacket_sendmsg(struct socket *sock, struct msghdr *msg,
 	if (err)
 		return err;
 
-	if (sk->sk_state != TCP_ESTABLISHED)
+	if (READ_ONCE(sk->sk_state) != TCP_ESTABLISHED)
 		return -ENOTCONN;
 
 	if (msg->msg_namelen)
@@ -2354,7 +2354,7 @@ static int unix_seqpacket_recvmsg(struct socket *sock, struct msghdr *msg,
 {
 	struct sock *sk = sock->sk;
 
-	if (sk->sk_state != TCP_ESTABLISHED)
+	if (READ_ONCE(sk->sk_state) != TCP_ESTABLISHED)
 		return -ENOTCONN;
 
 	return unix_dgram_recvmsg(sock, msg, size, flags);
@@ -2683,7 +2683,7 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state,
 	size_t size = state->size;
 	unsigned int last_len;
 
-	if (unlikely(sk->sk_state != TCP_ESTABLISHED)) {
+	if (unlikely(READ_ONCE(sk->sk_state) != TCP_ESTABLISHED)) {
 		err = -EINVAL;
 		goto out;
 	}
-- 
GitLab


From af4c733b6b1aded4dc808fafece7dfe6e9d2ebb3 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Tue, 4 Jun 2024 09:52:34 -0700
Subject: [PATCH 868/950] af_unix: Annotate data-race of sk->sk_state in
 unix_stream_read_skb().

unix_stream_read_skb() is called from sk->sk_data_ready() context
where unix_state_lock() is not held.

Let's use READ_ONCE() there.

Fixes: 77462de14a43 ("af_unix: Add read_sock for stream socket types")
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/unix/af_unix.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 4ef9c21783a5a..e7b74207aa3bd 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2659,7 +2659,7 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk,
 
 static int unix_stream_read_skb(struct sock *sk, skb_read_actor_t recv_actor)
 {
-	if (unlikely(sk->sk_state != TCP_ESTABLISHED))
+	if (unlikely(READ_ONCE(sk->sk_state) != TCP_ESTABLISHED))
 		return -ENOTCONN;
 
 	return unix_read_skb(sk, recv_actor);
-- 
GitLab


From 0aa3be7b3e1f8f997312cc4705f8165e02806f8f Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Tue, 4 Jun 2024 09:52:35 -0700
Subject: [PATCH 869/950] af_unix: Annotate data-races around sk->sk_state in
 UNIX_DIAG.

While dumping AF_UNIX sockets via UNIX_DIAG, sk->sk_state is read
locklessly.

Let's use READ_ONCE() there.

Note that the result could be inconsistent if the socket is dumped
during the state change.  This is common for other SOCK_DIAG and
similar interfaces.

Fixes: c9da99e6475f ("unix_diag: Fixup RQLEN extension report")
Fixes: 2aac7a2cb0d9 ("unix_diag: Pending connections IDs NLA")
Fixes: 45a96b9be6ec ("unix_diag: Dumping all sockets core")
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/unix/diag.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/unix/diag.c b/net/unix/diag.c
index ae39538c5042b..116cf508aea4a 100644
--- a/net/unix/diag.c
+++ b/net/unix/diag.c
@@ -65,7 +65,7 @@ static int sk_diag_dump_icons(struct sock *sk, struct sk_buff *nlskb)
 	u32 *buf;
 	int i;
 
-	if (sk->sk_state == TCP_LISTEN) {
+	if (READ_ONCE(sk->sk_state) == TCP_LISTEN) {
 		spin_lock(&sk->sk_receive_queue.lock);
 
 		attr = nla_reserve(nlskb, UNIX_DIAG_ICONS,
@@ -103,7 +103,7 @@ static int sk_diag_show_rqlen(struct sock *sk, struct sk_buff *nlskb)
 {
 	struct unix_diag_rqlen rql;
 
-	if (sk->sk_state == TCP_LISTEN) {
+	if (READ_ONCE(sk->sk_state) == TCP_LISTEN) {
 		rql.udiag_rqueue = sk->sk_receive_queue.qlen;
 		rql.udiag_wqueue = sk->sk_max_ack_backlog;
 	} else {
@@ -136,7 +136,7 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_r
 	rep = nlmsg_data(nlh);
 	rep->udiag_family = AF_UNIX;
 	rep->udiag_type = sk->sk_type;
-	rep->udiag_state = sk->sk_state;
+	rep->udiag_state = READ_ONCE(sk->sk_state);
 	rep->pad = 0;
 	rep->udiag_ino = sk_ino;
 	sock_diag_save_cookie(sk, rep->udiag_cookie);
@@ -215,7 +215,7 @@ static int unix_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
 		sk_for_each(sk, &net->unx.table.buckets[slot]) {
 			if (num < s_num)
 				goto next;
-			if (!(req->udiag_states & (1 << sk->sk_state)))
+			if (!(req->udiag_states & (1 << READ_ONCE(sk->sk_state))))
 				goto next;
 			if (sk_diag_dump(sk, skb, req, sk_user_ns(skb->sk),
 					 NETLINK_CB(cb->skb).portid,
-- 
GitLab


From b0632e53e0da8054e36bc973f0eec69d30f1b7c6 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Tue, 4 Jun 2024 09:52:36 -0700
Subject: [PATCH 870/950] af_unix: Annotate data-races around sk->sk_sndbuf.

sk_setsockopt() changes sk->sk_sndbuf under lock_sock(), but it's
not used in af_unix.c.

Let's use READ_ONCE() to read sk->sk_sndbuf in unix_writable(),
unix_dgram_sendmsg(), and unix_stream_sendmsg().

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/unix/af_unix.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index e7b74207aa3bd..de2a5e334a88e 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -533,7 +533,7 @@ static int unix_dgram_peer_wake_me(struct sock *sk, struct sock *other)
 static int unix_writable(const struct sock *sk, unsigned char state)
 {
 	return state != TCP_LISTEN &&
-	       (refcount_read(&sk->sk_wmem_alloc) << 2) <= sk->sk_sndbuf;
+		(refcount_read(&sk->sk_wmem_alloc) << 2) <= READ_ONCE(sk->sk_sndbuf);
 }
 
 static void unix_write_space(struct sock *sk)
@@ -1967,7 +1967,7 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
 	}
 
 	err = -EMSGSIZE;
-	if (len > sk->sk_sndbuf - 32)
+	if (len > READ_ONCE(sk->sk_sndbuf) - 32)
 		goto out;
 
 	if (len > SKB_MAX_ALLOC) {
@@ -2247,7 +2247,7 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 						   &err, 0);
 		} else {
 			/* Keep two messages in the pipe so it schedules better */
-			size = min_t(int, size, (sk->sk_sndbuf >> 1) - 64);
+			size = min_t(int, size, (READ_ONCE(sk->sk_sndbuf) >> 1) - 64);
 
 			/* allow fallback to order-0 allocations */
 			size = min_t(int, size, SKB_MAX_HEAD(0) + UNIX_SKB_FRAGS_SZ);
-- 
GitLab


From bd9f2d05731f6a112d0c7391a0d537bfc588dbe6 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Tue, 4 Jun 2024 09:52:37 -0700
Subject: [PATCH 871/950] af_unix: Annotate data-race of
 net->unx.sysctl_max_dgram_qlen.

net->unx.sysctl_max_dgram_qlen is exposed as a sysctl knob and can be
changed concurrently.

Let's use READ_ONCE() in unix_create1().

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/unix/af_unix.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index de2a5e334a88e..623ee39657e23 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -976,7 +976,7 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern,
 	sk->sk_hash		= unix_unbound_hash(sk);
 	sk->sk_allocation	= GFP_KERNEL_ACCOUNT;
 	sk->sk_write_space	= unix_write_space;
-	sk->sk_max_ack_backlog	= net->unx.sysctl_max_dgram_qlen;
+	sk->sk_max_ack_backlog	= READ_ONCE(net->unx.sysctl_max_dgram_qlen);
 	sk->sk_destruct		= unix_sock_destructor;
 	u = unix_sk(sk);
 	u->listener = NULL;
-- 
GitLab


From 45d872f0e65593176d880ec148f41ad7c02e40a7 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Tue, 4 Jun 2024 09:52:38 -0700
Subject: [PATCH 872/950] af_unix: Use unix_recvq_full_lockless() in
 unix_stream_connect().

Once sk->sk_state is changed to TCP_LISTEN, it never changes.

unix_accept() takes advantage of this characteristics; it does not
hold the listener's unix_state_lock() and only acquires recvq lock
to pop one skb.

It means unix_state_lock() does not prevent the queue length from
changing in unix_stream_connect().

Thus, we need to use unix_recvq_full_lockless() to avoid data-race.

Now we remove unix_recvq_full() as no one uses it.

Note that we can remove READ_ONCE() for sk->sk_max_ack_backlog in
unix_recvq_full_lockless() because of the following reasons:

  (1) For SOCK_DGRAM, it is a written-once field in unix_create1()

  (2) For SOCK_STREAM and SOCK_SEQPACKET, it is changed under the
      listener's unix_state_lock() in unix_listen(), and we hold
      the lock in unix_stream_connect()

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/unix/af_unix.c | 10 ++--------
 1 file changed, 2 insertions(+), 8 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 623ee39657e23..eb3ba3448ed34 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -221,15 +221,9 @@ static inline int unix_may_send(struct sock *sk, struct sock *osk)
 	return unix_peer(osk) == NULL || unix_our_peer(sk, osk);
 }
 
-static inline int unix_recvq_full(const struct sock *sk)
-{
-	return skb_queue_len(&sk->sk_receive_queue) > sk->sk_max_ack_backlog;
-}
-
 static inline int unix_recvq_full_lockless(const struct sock *sk)
 {
-	return skb_queue_len_lockless(&sk->sk_receive_queue) >
-		READ_ONCE(sk->sk_max_ack_backlog);
+	return skb_queue_len_lockless(&sk->sk_receive_queue) > sk->sk_max_ack_backlog;
 }
 
 struct sock *unix_peer_get(struct sock *s)
@@ -1545,7 +1539,7 @@ restart:
 	if (other->sk_shutdown & RCV_SHUTDOWN)
 		goto out_unlock;
 
-	if (unix_recvq_full(other)) {
+	if (unix_recvq_full_lockless(other)) {
 		err = -EAGAIN;
 		if (!timeo)
 			goto out_unlock;
-- 
GitLab


From 83690b82d228b3570565ebd0b41873933238b97f Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Tue, 4 Jun 2024 09:52:39 -0700
Subject: [PATCH 873/950] af_unix: Use skb_queue_empty_lockless() in
 unix_release_sock().

If the socket type is SOCK_STREAM or SOCK_SEQPACKET, unix_release_sock()
checks the length of the peer socket's recvq under unix_state_lock().

However, unix_stream_read_generic() calls skb_unlink() after releasing
the lock.  Also, for SOCK_SEQPACKET, __skb_try_recv_datagram() unlinks
skb without unix_state_lock().

Thues, unix_state_lock() does not protect qlen.

Let's use skb_queue_empty_lockless() in unix_release_sock().

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/unix/af_unix.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index eb3ba3448ed34..80846279de9f3 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -631,7 +631,7 @@ static void unix_release_sock(struct sock *sk, int embrion)
 			unix_state_lock(skpair);
 			/* No more writes */
 			WRITE_ONCE(skpair->sk_shutdown, SHUTDOWN_MASK);
-			if (!skb_queue_empty(&sk->sk_receive_queue) || embrion)
+			if (!skb_queue_empty_lockless(&sk->sk_receive_queue) || embrion)
 				WRITE_ONCE(skpair->sk_err, ECONNRESET);
 			unix_state_unlock(skpair);
 			skpair->sk_state_change(skpair);
-- 
GitLab


From 5d915e584d8408211d4567c22685aae8820bfc55 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Tue, 4 Jun 2024 09:52:40 -0700
Subject: [PATCH 874/950] af_unix: Use skb_queue_len_lockless() in
 sk_diag_show_rqlen().

We can dump the socket queue length via UNIX_DIAG by specifying
UDIAG_SHOW_RQLEN.

If sk->sk_state is TCP_LISTEN, we return the recv queue length,
but here we do not hold recvq lock.

Let's use skb_queue_len_lockless() in sk_diag_show_rqlen().

Fixes: c9da99e6475f ("unix_diag: Fixup RQLEN extension report")
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/unix/diag.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/unix/diag.c b/net/unix/diag.c
index 116cf508aea4a..321336f91a0af 100644
--- a/net/unix/diag.c
+++ b/net/unix/diag.c
@@ -104,7 +104,7 @@ static int sk_diag_show_rqlen(struct sock *sk, struct sk_buff *nlskb)
 	struct unix_diag_rqlen rql;
 
 	if (READ_ONCE(sk->sk_state) == TCP_LISTEN) {
-		rql.udiag_rqueue = sk->sk_receive_queue.qlen;
+		rql.udiag_rqueue = skb_queue_len_lockless(&sk->sk_receive_queue);
 		rql.udiag_wqueue = sk->sk_max_ack_backlog;
 	} else {
 		rql.udiag_rqueue = (u32) unix_inq_len(sk);
-- 
GitLab


From efaf24e30ec39ebbea9112227485805a48b0ceb1 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Tue, 4 Jun 2024 09:52:41 -0700
Subject: [PATCH 875/950] af_unix: Annotate data-race of sk->sk_shutdown in
 sk_diag_fill().

While dumping sockets via UNIX_DIAG, we do not hold unix_state_lock().

Let's use READ_ONCE() to read sk->sk_shutdown.

Fixes: e4e541a84863 ("sock-diag: Report shutdown for inet and unix sockets (v2)")
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/unix/diag.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/unix/diag.c b/net/unix/diag.c
index 321336f91a0af..937edf4afed41 100644
--- a/net/unix/diag.c
+++ b/net/unix/diag.c
@@ -165,7 +165,7 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_r
 	    sock_diag_put_meminfo(sk, skb, UNIX_DIAG_MEMINFO))
 		goto out_nlmsg_trim;
 
-	if (nla_put_u8(skb, UNIX_DIAG_SHUTDOWN, sk->sk_shutdown))
+	if (nla_put_u8(skb, UNIX_DIAG_SHUTDOWN, READ_ONCE(sk->sk_shutdown)))
 		goto out_nlmsg_trim;
 
 	if ((req->udiag_show & UDIAG_SHOW_UID) &&
-- 
GitLab


From b01e1c030770ff3b4fe37fc7cc6bca03f594133f Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 4 Jun 2024 19:35:49 +0000
Subject: [PATCH 876/950] ipv6: fix possible race in __fib6_drop_pcpu_from()

syzbot found a race in __fib6_drop_pcpu_from() [1]

If compiler reads more than once (*ppcpu_rt),
second read could read NULL, if another cpu clears
the value in rt6_get_pcpu_route().

Add a READ_ONCE() to prevent this race.

Also add rcu_read_lock()/rcu_read_unlock() because
we rely on RCU protection while dereferencing pcpu_rt.

[1]

Oops: general protection fault, probably for non-canonical address 0xdffffc0000000012: 0000 [#1] PREEMPT SMP KASAN PTI
KASAN: null-ptr-deref in range [0x0000000000000090-0x0000000000000097]
CPU: 0 PID: 7543 Comm: kworker/u8:17 Not tainted 6.10.0-rc1-syzkaller-00013-g2bfcfd584ff5 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 04/02/2024
Workqueue: netns cleanup_net
 RIP: 0010:__fib6_drop_pcpu_from.part.0+0x10a/0x370 net/ipv6/ip6_fib.c:984
Code: f8 48 c1 e8 03 80 3c 28 00 0f 85 16 02 00 00 4d 8b 3f 4d 85 ff 74 31 e8 74 a7 fa f7 49 8d bf 90 00 00 00 48 89 f8 48 c1 e8 03 <80> 3c 28 00 0f 85 1e 02 00 00 49 8b 87 90 00 00 00 48 8b 0c 24 48
RSP: 0018:ffffc900040df070 EFLAGS: 00010206
RAX: 0000000000000012 RBX: 0000000000000001 RCX: ffffffff89932e16
RDX: ffff888049dd1e00 RSI: ffffffff89932d7c RDI: 0000000000000091
RBP: dffffc0000000000 R08: 0000000000000005 R09: 0000000000000007
R10: 0000000000000001 R11: 0000000000000006 R12: ffff88807fa080b8
R13: fffffbfff1a9a07d R14: ffffed100ff41022 R15: 0000000000000001
FS:  0000000000000000(0000) GS:ffff8880b9200000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000001b32c26000 CR3: 000000005d56e000 CR4: 00000000003526f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 <TASK>
  __fib6_drop_pcpu_from net/ipv6/ip6_fib.c:966 [inline]
  fib6_drop_pcpu_from net/ipv6/ip6_fib.c:1027 [inline]
  fib6_purge_rt+0x7f2/0x9f0 net/ipv6/ip6_fib.c:1038
  fib6_del_route net/ipv6/ip6_fib.c:1998 [inline]
  fib6_del+0xa70/0x17b0 net/ipv6/ip6_fib.c:2043
  fib6_clean_node+0x426/0x5b0 net/ipv6/ip6_fib.c:2205
  fib6_walk_continue+0x44f/0x8d0 net/ipv6/ip6_fib.c:2127
  fib6_walk+0x182/0x370 net/ipv6/ip6_fib.c:2175
  fib6_clean_tree+0xd7/0x120 net/ipv6/ip6_fib.c:2255
  __fib6_clean_all+0x100/0x2d0 net/ipv6/ip6_fib.c:2271
  rt6_sync_down_dev net/ipv6/route.c:4906 [inline]
  rt6_disable_ip+0x7ed/0xa00 net/ipv6/route.c:4911
  addrconf_ifdown.isra.0+0x117/0x1b40 net/ipv6/addrconf.c:3855
  addrconf_notify+0x223/0x19e0 net/ipv6/addrconf.c:3778
  notifier_call_chain+0xb9/0x410 kernel/notifier.c:93
  call_netdevice_notifiers_info+0xbe/0x140 net/core/dev.c:1992
  call_netdevice_notifiers_extack net/core/dev.c:2030 [inline]
  call_netdevice_notifiers net/core/dev.c:2044 [inline]
  dev_close_many+0x333/0x6a0 net/core/dev.c:1585
  unregister_netdevice_many_notify+0x46d/0x19f0 net/core/dev.c:11193
  unregister_netdevice_many net/core/dev.c:11276 [inline]
  default_device_exit_batch+0x85b/0xae0 net/core/dev.c:11759
  ops_exit_list+0x128/0x180 net/core/net_namespace.c:178
  cleanup_net+0x5b7/0xbf0 net/core/net_namespace.c:640
  process_one_work+0x9fb/0x1b60 kernel/workqueue.c:3231
  process_scheduled_works kernel/workqueue.c:3312 [inline]
  worker_thread+0x6c8/0xf70 kernel/workqueue.c:3393
  kthread+0x2c1/0x3a0 kernel/kthread.c:389
  ret_from_fork+0x45/0x80 arch/x86/kernel/process.c:147
  ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244

Fixes: d52d3997f843 ("ipv6: Create percpu rt6_info")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/r/20240604193549.981839-1-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/ipv6/ip6_fib.c | 6 +++++-
 net/ipv6/route.c   | 1 +
 2 files changed, 6 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 31d77885bcae3..6e57c03e3255f 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -966,6 +966,7 @@ static void __fib6_drop_pcpu_from(struct fib6_nh *fib6_nh,
 	if (!fib6_nh->rt6i_pcpu)
 		return;
 
+	rcu_read_lock();
 	/* release the reference to this fib entry from
 	 * all of its cached pcpu routes
 	 */
@@ -974,7 +975,9 @@ static void __fib6_drop_pcpu_from(struct fib6_nh *fib6_nh,
 		struct rt6_info *pcpu_rt;
 
 		ppcpu_rt = per_cpu_ptr(fib6_nh->rt6i_pcpu, cpu);
-		pcpu_rt = *ppcpu_rt;
+
+		/* Paired with xchg() in rt6_get_pcpu_route() */
+		pcpu_rt = READ_ONCE(*ppcpu_rt);
 
 		/* only dropping the 'from' reference if the cached route
 		 * is using 'match'. The cached pcpu_rt->from only changes
@@ -988,6 +991,7 @@ static void __fib6_drop_pcpu_from(struct fib6_nh *fib6_nh,
 			fib6_info_release(from);
 		}
 	}
+	rcu_read_unlock();
 }
 
 struct fib6_nh_pcpu_arg {
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index a504b88ec06b5..f083d9faba6b1 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1409,6 +1409,7 @@ static struct rt6_info *rt6_get_pcpu_route(const struct fib6_result *res)
 		struct rt6_info *prev, **p;
 
 		p = this_cpu_ptr(res->nh->rt6i_pcpu);
+		/* Paired with READ_ONCE() in __fib6_drop_pcpu_from() */
 		prev = xchg(p, NULL);
 		if (prev) {
 			dst_dev_put(&prev->dst);
-- 
GitLab


From 9b6a30febddf4857cb4c367f5294bb6118340e30 Mon Sep 17 00:00:00 2001
From: Jason Xing <kernelxing@tencent.com>
Date: Wed, 5 Jun 2024 10:29:32 +0800
Subject: [PATCH 877/950] net: allow rps/rfs related configs to be switched

After John Sperbeck reported a compile error if the CONFIG_RFS_ACCEL
is off, I found that I cannot easily enable/disable the config
because of lack of the prompt when using 'make menuconfig'. Therefore,
I decided to change rps/rfc related configs altogether.

Signed-off-by: Jason Xing <kernelxing@tencent.com>
Link: https://lore.kernel.org/r/20240605022932.33703-1-kerneljasonxing@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/Kconfig | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/net/Kconfig b/net/Kconfig
index f0a8692496ffa..9fe65fa26e48c 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -290,15 +290,21 @@ config MAX_SKB_FRAGS
 	  If unsure, say 17.
 
 config RPS
-	bool
+	bool "Receive packet steering"
 	depends on SMP && SYSFS
 	default y
+	help
+	  Software receive side packet steering (RPS) distributes the
+	  load of received packet processing across multiple CPUs.
 
 config RFS_ACCEL
-	bool
+	bool "Hardware acceleration of RFS"
 	depends on RPS
 	select CPU_RMAP
 	default y
+	help
+	  Allowing drivers for multiqueue hardware with flow filter tables to
+	  accelerate RFS.
 
 config SOCK_RX_QUEUE_MAPPING
 	bool
@@ -351,7 +357,7 @@ config BPF_STREAM_PARSER
 	  BPF_MAP_TYPE_SOCKMAP.
 
 config NET_FLOW_LIMIT
-	bool
+	bool "Net flow limit"
 	depends on RPS
 	default y
 	help
-- 
GitLab


From 0dcc53abf58d572d34c5313de85f607cd33fc691 Mon Sep 17 00:00:00 2001
From: Su Hui <suhui@nfschina.com>
Date: Wed, 5 Jun 2024 11:47:43 +0800
Subject: [PATCH 878/950] net: ethtool: fix the error condition in
 ethtool_get_phy_stats_ethtool()

Clang static checker (scan-build) warning:
net/ethtool/ioctl.c:line 2233, column 2
Called function pointer is null (null dereference).

Return '-EOPNOTSUPP' when 'ops->get_ethtool_phy_stats' is NULL to fix
this typo error.

Fixes: 201ed315f967 ("net/ethtool/ioctl: split ethtool_get_phy_stats into multiple helpers")
Signed-off-by: Su Hui <suhui@nfschina.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Hariprasad Kelam <hkelam@marvell.com>
Link: https://lore.kernel.org/r/20240605034742.921751-1-suhui@nfschina.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/ethtool/ioctl.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index 5a55270aa86e8..e645d751a5e89 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -2220,7 +2220,7 @@ static int ethtool_get_phy_stats_ethtool(struct net_device *dev,
 	const struct ethtool_ops *ops = dev->ethtool_ops;
 	int n_stats, ret;
 
-	if (!ops || !ops->get_sset_count || ops->get_ethtool_phy_stats)
+	if (!ops || !ops->get_sset_count || !ops->get_ethtool_phy_stats)
 		return -EOPNOTSUPP;
 
 	n_stats = ops->get_sset_count(dev, ETH_SS_PHY_STATS);
-- 
GitLab


From 5f0d0649c83f72399c19b18591ea1413ca94c015 Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Wed, 5 Jun 2024 09:15:40 +0200
Subject: [PATCH 879/950] mptcp: use mptcp_win_from_space helper

The MPTCP dedicated win_from_space helper mptcp_win_from_space() is defined
in protocol.h, use it in mptcp_rcv_space_adjust() instead of using the TCP
one. Here scaling_ratio is the same as msk->scaling_ratio.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/mptcp/protocol.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 7d44196ec5b63..546c80c6702a5 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2046,7 +2046,7 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied)
 		if (rcvbuf > sk->sk_rcvbuf) {
 			u32 window_clamp;
 
-			window_clamp = __tcp_win_from_space(scaling_ratio, rcvbuf);
+			window_clamp = mptcp_win_from_space(sk, rcvbuf);
 			WRITE_ONCE(sk->sk_rcvbuf, rcvbuf);
 
 			/* Make subflows follow along.  If we do not do this, we
-- 
GitLab


From 5cdedad62eaba22c45b9c45c8199bacd461afd87 Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Wed, 5 Jun 2024 09:15:41 +0200
Subject: [PATCH 880/950] mptcp: add mptcp_space_from_win helper

As a wrapper of __tcp_space_from_win(), this patch adds a MPTCP dedicated
space_from_win helper mptcp_space_from_win() in protocol.h to paired with
mptcp_win_from_space().

Use it instead of __tcp_space_from_win() in both mptcp_rcv_space_adjust()
and mptcp_set_rcvlowat().

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/mptcp/protocol.c | 2 +-
 net/mptcp/protocol.h | 5 +++++
 net/mptcp/sockopt.c  | 2 +-
 3 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 546c80c6702a5..7ce11bee3b79e 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2040,7 +2040,7 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied)
 		do_div(grow, msk->rcvq_space.space);
 		rcvwin += (grow << 1);
 
-		rcvbuf = min_t(u64, __tcp_space_from_win(scaling_ratio, rcvwin),
+		rcvbuf = min_t(u64, mptcp_space_from_win(sk, rcvwin),
 			       READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]));
 
 		if (rcvbuf > sk->sk_rcvbuf) {
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 7aa47e2dd52b1..b11a4e50d52b6 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -386,6 +386,11 @@ static inline int mptcp_win_from_space(const struct sock *sk, int space)
 	return __tcp_win_from_space(mptcp_sk(sk)->scaling_ratio, space);
 }
 
+static inline int mptcp_space_from_win(const struct sock *sk, int win)
+{
+	return __tcp_space_from_win(mptcp_sk(sk)->scaling_ratio, win);
+}
+
 static inline int __mptcp_space(const struct sock *sk)
 {
 	return mptcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf) - __mptcp_rmem(sk));
diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
index f9a4fb17b5b78..2026a9a36f804 100644
--- a/net/mptcp/sockopt.c
+++ b/net/mptcp/sockopt.c
@@ -1579,7 +1579,7 @@ int mptcp_set_rcvlowat(struct sock *sk, int val)
 	if (sk->sk_userlocks & SOCK_RCVBUF_LOCK)
 		return 0;
 
-	space = __tcp_space_from_win(mptcp_sk(sk)->scaling_ratio, val);
+	space = mptcp_space_from_win(sk, val);
 	if (space <= sk->sk_rcvbuf)
 		return 0;
 
-- 
GitLab


From 92f74c1e05b044b51398d6d4a85e659e4384f2cb Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Wed, 5 Jun 2024 09:15:42 +0200
Subject: [PATCH 881/950] mptcp: refer to 'MPTCP' socket in comments

We used to call it 'master' socket at the early stages of MPTCP
development, but the correct wording is 'MPTCP' socket opposed to 'TCP
subflows': convert the last 3 comments to use a more appropriate term.

Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/mptcp/protocol.c | 4 ++--
 net/mptcp/subflow.c  | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 7ce11bee3b79e..ead0bf63cf95b 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2202,7 +2202,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		if (skb_queue_empty(&msk->receive_queue) && __mptcp_move_skbs(msk))
 			continue;
 
-		/* only the master socket status is relevant here. The exit
+		/* only the MPTCP socket status is relevant here. The exit
 		 * conditions mirror closely tcp_recvmsg()
 		 */
 		if (copied >= target)
@@ -3521,7 +3521,7 @@ void mptcp_subflow_process_delegated(struct sock *ssk, long status)
 static int mptcp_hash(struct sock *sk)
 {
 	/* should never be called,
-	 * we hash the TCP subflows not the master socket
+	 * we hash the TCP subflows not the MPTCP socket
 	 */
 	WARN_ON_ONCE(1);
 	return 0;
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 612c38570a642..39e2cbdf38019 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -1719,7 +1719,7 @@ int mptcp_subflow_create_socket(struct sock *sk, unsigned short family,
 	mptcp_sockopt_sync_locked(mptcp_sk(sk), sf->sk);
 	release_sock(sf->sk);
 
-	/* the newly created socket really belongs to the owning MPTCP master
+	/* the newly created socket really belongs to the owning MPTCP
 	 * socket, even if for additional subflows the allocation is performed
 	 * by a kernel workqueue. Adjust inode references, so that the
 	 * procfs/diag interfaces really show this one belonging to the correct
-- 
GitLab


From c34506406dd5cfb352f8c53bb6a1b9535c0905dd Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 5 Jun 2024 07:15:51 +0000
Subject: [PATCH 882/950] tcp: small changes in reqsk_put() and reqsk_free()

In reqsk_free(), use DEBUG_NET_WARN_ON_ONCE()
instead of WARN_ON_ONCE() for a condition which never fired.

In reqsk_put() directly call __reqsk_free(), there is no
point checking rsk_refcnt again right after a transition to zero.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/net/request_sock.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/net/request_sock.h b/include/net/request_sock.h
index ebcb8896bffc1..a8f82216c6287 100644
--- a/include/net/request_sock.h
+++ b/include/net/request_sock.h
@@ -172,14 +172,14 @@ static inline void __reqsk_free(struct request_sock *req)
 
 static inline void reqsk_free(struct request_sock *req)
 {
-	WARN_ON_ONCE(refcount_read(&req->rsk_refcnt) != 0);
+	DEBUG_NET_WARN_ON_ONCE(refcount_read(&req->rsk_refcnt) != 0);
 	__reqsk_free(req);
 }
 
 static inline void reqsk_put(struct request_sock *req)
 {
 	if (refcount_dec_and_test(&req->rsk_refcnt))
-		reqsk_free(req);
+		__reqsk_free(req);
 }
 
 /*
-- 
GitLab


From adbe695a9765fb704d2ac0d3e284f28bcc8b5bf3 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 5 Jun 2024 07:15:52 +0000
Subject: [PATCH 883/950] tcp: move inet_reqsk_alloc() close to
 inet_reqsk_clone()

inet_reqsk_alloc() does not belong to tcp_input.c,
move it to inet_connection_sock.c instead.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/ipv4/inet_connection_sock.c | 25 +++++++++++++++++++++++++
 net/ipv4/tcp_input.c            | 25 -------------------------
 2 files changed, 25 insertions(+), 25 deletions(-)

diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index d81f74ce0f02e..a9d2e63089100 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -911,6 +911,31 @@ int inet_rtx_syn_ack(const struct sock *parent, struct request_sock *req)
 }
 EXPORT_SYMBOL(inet_rtx_syn_ack);
 
+struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops,
+				      struct sock *sk_listener,
+				      bool attach_listener)
+{
+	struct request_sock *req = reqsk_alloc(ops, sk_listener,
+					       attach_listener);
+
+	if (req) {
+		struct inet_request_sock *ireq = inet_rsk(req);
+
+		ireq->ireq_opt = NULL;
+#if IS_ENABLED(CONFIG_IPV6)
+		ireq->pktopts = NULL;
+#endif
+		atomic64_set(&ireq->ir_cookie, 0);
+		ireq->ireq_state = TCP_NEW_SYN_RECV;
+		write_pnet(&ireq->ireq_net, sock_net(sk_listener));
+		ireq->ireq_family = sk_listener->sk_family;
+		req->timeout = TCP_TIMEOUT_INIT;
+	}
+
+	return req;
+}
+EXPORT_SYMBOL(inet_reqsk_alloc);
+
 static struct request_sock *inet_reqsk_clone(struct request_sock *req,
 					     struct sock *sk)
 {
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 212b6fd0caf76..eb187450e4d76 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -6986,31 +6986,6 @@ static void tcp_openreq_init(struct request_sock *req,
 #endif
 }
 
-struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops,
-				      struct sock *sk_listener,
-				      bool attach_listener)
-{
-	struct request_sock *req = reqsk_alloc(ops, sk_listener,
-					       attach_listener);
-
-	if (req) {
-		struct inet_request_sock *ireq = inet_rsk(req);
-
-		ireq->ireq_opt = NULL;
-#if IS_ENABLED(CONFIG_IPV6)
-		ireq->pktopts = NULL;
-#endif
-		atomic64_set(&ireq->ir_cookie, 0);
-		ireq->ireq_state = TCP_NEW_SYN_RECV;
-		write_pnet(&ireq->ireq_net, sock_net(sk_listener));
-		ireq->ireq_family = sk_listener->sk_family;
-		req->timeout = TCP_TIMEOUT_INIT;
-	}
-
-	return req;
-}
-EXPORT_SYMBOL(inet_reqsk_alloc);
-
 /*
  * Return true if a syncookie should be sent
  */
-- 
GitLab


From 6971d21672827a701c5ea180891b7ea6cf06f6a7 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 5 Jun 2024 07:15:53 +0000
Subject: [PATCH 884/950] tcp: move reqsk_alloc() to inet_connection_sock.c

reqsk_alloc() has a single caller, no need to expose it
in include/net/request_sock.h.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/net/request_sock.h      | 33 ---------------------------------
 net/ipv4/inet_connection_sock.c | 33 +++++++++++++++++++++++++++++++++
 2 files changed, 33 insertions(+), 33 deletions(-)

diff --git a/include/net/request_sock.h b/include/net/request_sock.h
index a8f82216c6287..b07b1cd14e9f4 100644
--- a/include/net/request_sock.h
+++ b/include/net/request_sock.h
@@ -128,39 +128,6 @@ static inline struct sock *skb_steal_sock(struct sk_buff *skb,
 	return sk;
 }
 
-static inline struct request_sock *
-reqsk_alloc_noprof(const struct request_sock_ops *ops, struct sock *sk_listener,
-	    bool attach_listener)
-{
-	struct request_sock *req;
-
-	req = kmem_cache_alloc_noprof(ops->slab, GFP_ATOMIC | __GFP_NOWARN);
-	if (!req)
-		return NULL;
-	req->rsk_listener = NULL;
-	if (attach_listener) {
-		if (unlikely(!refcount_inc_not_zero(&sk_listener->sk_refcnt))) {
-			kmem_cache_free(ops->slab, req);
-			return NULL;
-		}
-		req->rsk_listener = sk_listener;
-	}
-	req->rsk_ops = ops;
-	req_to_sk(req)->sk_prot = sk_listener->sk_prot;
-	sk_node_init(&req_to_sk(req)->sk_node);
-	sk_tx_queue_clear(req_to_sk(req));
-	req->saved_syn = NULL;
-	req->syncookie = 0;
-	req->timeout = 0;
-	req->num_timeout = 0;
-	req->num_retrans = 0;
-	req->sk = NULL;
-	refcount_set(&req->rsk_refcnt, 0);
-
-	return req;
-}
-#define reqsk_alloc(...)	alloc_hooks(reqsk_alloc_noprof(__VA_ARGS__))
-
 static inline void __reqsk_free(struct request_sock *req)
 {
 	req->rsk_ops->destructor(req);
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index a9d2e63089100..7ced569778ab4 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -911,6 +911,39 @@ int inet_rtx_syn_ack(const struct sock *parent, struct request_sock *req)
 }
 EXPORT_SYMBOL(inet_rtx_syn_ack);
 
+static struct request_sock *
+reqsk_alloc_noprof(const struct request_sock_ops *ops, struct sock *sk_listener,
+		   bool attach_listener)
+{
+	struct request_sock *req;
+
+	req = kmem_cache_alloc_noprof(ops->slab, GFP_ATOMIC | __GFP_NOWARN);
+	if (!req)
+		return NULL;
+	req->rsk_listener = NULL;
+	if (attach_listener) {
+		if (unlikely(!refcount_inc_not_zero(&sk_listener->sk_refcnt))) {
+			kmem_cache_free(ops->slab, req);
+			return NULL;
+		}
+		req->rsk_listener = sk_listener;
+	}
+	req->rsk_ops = ops;
+	req_to_sk(req)->sk_prot = sk_listener->sk_prot;
+	sk_node_init(&req_to_sk(req)->sk_node);
+	sk_tx_queue_clear(req_to_sk(req));
+	req->saved_syn = NULL;
+	req->syncookie = 0;
+	req->timeout = 0;
+	req->num_timeout = 0;
+	req->num_retrans = 0;
+	req->sk = NULL;
+	refcount_set(&req->rsk_refcnt, 0);
+
+	return req;
+}
+#define reqsk_alloc(...)	alloc_hooks(reqsk_alloc_noprof(__VA_ARGS__))
+
 struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops,
 				      struct sock *sk_listener,
 				      bool attach_listener)
-- 
GitLab


From 7015843afcaf68c132784c89528dfddc0005e483 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Wed, 5 Jun 2024 13:12:03 -0700
Subject: [PATCH 885/950] selftests/bpf: Fix send_signal test with nested
 CONFIG_PARAVIRT

Alexei reported that send_signal test may fail with nested CONFIG_PARAVIRT
configs. In this particular case, the base VM is AMD with 166 cpus, and I
run selftests with regular qemu on top of that and indeed send_signal test
failed. I also tried with an Intel box with 80 cpus and there is no issue.

The main qemu command line includes:

  -enable-kvm -smp 16 -cpu host

The failure log looks like:

  $ ./test_progs -t send_signal
  [   48.501588] watchdog: BUG: soft lockup - CPU#9 stuck for 26s! [test_progs:2225]
  [   48.503622] Modules linked in: bpf_testmod(O)
  [   48.503622] CPU: 9 PID: 2225 Comm: test_progs Tainted: G           O       6.9.0-08561-g2c1713a8f1c9-dirty #69
  [   48.507629] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.15.0-0-g2dd4b9b3f840-prebuilt.qemu.org 04/01/2014
  [   48.511635] RIP: 0010:handle_softirqs+0x71/0x290
  [   48.511635] Code: [...] 10 0a 00 00 00 31 c0 65 66 89 05 d5 f4 fa 7e fb bb ff ff ff ff <49> c7 c2 cb
  [   48.518527] RSP: 0018:ffffc90000310fa0 EFLAGS: 00000246
  [   48.519579] RAX: 0000000000000000 RBX: 00000000ffffffff RCX: 00000000000006e0
  [   48.522526] RDX: 0000000000000006 RSI: ffff88810791ae80 RDI: 0000000000000000
  [   48.523587] RBP: ffffc90000fabc88 R08: 00000005a0af4f7f R09: 0000000000000000
  [   48.525525] R10: 0000000561d2f29c R11: 0000000000006534 R12: 0000000000000280
  [   48.528525] R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000
  [   48.528525] FS:  00007f2f2885cd00(0000) GS:ffff888237c40000(0000) knlGS:0000000000000000
  [   48.531600] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  [   48.535520] CR2: 00007f2f287059f0 CR3: 0000000106a28002 CR4: 00000000003706f0
  [   48.537538] Call Trace:
  [   48.537538]  <IRQ>
  [   48.537538]  ? watchdog_timer_fn+0x1cd/0x250
  [   48.539590]  ? lockup_detector_update_enable+0x50/0x50
  [   48.539590]  ? __hrtimer_run_queues+0xff/0x280
  [   48.542520]  ? hrtimer_interrupt+0x103/0x230
  [   48.544524]  ? __sysvec_apic_timer_interrupt+0x4f/0x140
  [   48.545522]  ? sysvec_apic_timer_interrupt+0x3a/0x90
  [   48.547612]  ? asm_sysvec_apic_timer_interrupt+0x1a/0x20
  [   48.547612]  ? handle_softirqs+0x71/0x290
  [   48.547612]  irq_exit_rcu+0x63/0x80
  [   48.551585]  sysvec_apic_timer_interrupt+0x75/0x90
  [   48.552521]  </IRQ>
  [   48.553529]  <TASK>
  [   48.553529]  asm_sysvec_apic_timer_interrupt+0x1a/0x20
  [   48.555609] RIP: 0010:finish_task_switch.isra.0+0x90/0x260
  [   48.556526] Code: [...] 9f 58 0a 00 00 48 85 db 0f 85 89 01 00 00 4c 89 ff e8 53 d9 bd 00 fb 66 90 <4d> 85 ed 74
  [   48.562524] RSP: 0018:ffffc90000fabd38 EFLAGS: 00000282
  [   48.563589] RAX: 0000000000000000 RBX: 0000000000000000 RCX: ffffffff83385620
  [   48.563589] RDX: ffff888237c73ae4 RSI: 0000000000000000 RDI: ffff888237c6fd00
  [   48.568521] RBP: ffffc90000fabd68 R08: 0000000000000000 R09: 0000000000000000
  [   48.569528] R10: 0000000000000001 R11: 0000000000000000 R12: ffff8881009d0000
  [   48.573525] R13: ffff8881024e5400 R14: ffff88810791ae80 R15: ffff888237c6fd00
  [   48.575614]  ? finish_task_switch.isra.0+0x8d/0x260
  [   48.576523]  __schedule+0x364/0xac0
  [   48.577535]  schedule+0x2e/0x110
  [   48.578555]  pipe_read+0x301/0x400
  [   48.579589]  ? destroy_sched_domains_rcu+0x30/0x30
  [   48.579589]  vfs_read+0x2b3/0x2f0
  [   48.579589]  ksys_read+0x8b/0xc0
  [   48.583590]  do_syscall_64+0x3d/0xc0
  [   48.583590]  entry_SYSCALL_64_after_hwframe+0x4b/0x53
  [   48.586525] RIP: 0033:0x7f2f28703fa1
  [   48.587592] Code: [...] 00 00 00 0f 1f 44 00 00 f3 0f 1e fa 80 3d c5 23 14 00 00 74 13 31 c0 0f 05 <48> 3d 00 f0
  [   48.593534] RSP: 002b:00007ffd90f8cf88 EFLAGS: 00000246 ORIG_RAX: 0000000000000000
  [   48.595589] RAX: ffffffffffffffda RBX: 00007ffd90f8d5e8 RCX: 00007f2f28703fa1
  [   48.595589] RDX: 0000000000000001 RSI: 00007ffd90f8cfb0 RDI: 0000000000000006
  [   48.599592] RBP: 00007ffd90f8d2f0 R08: 0000000000000064 R09: 0000000000000000
  [   48.602527] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
  [   48.603589] R13: 00007ffd90f8d608 R14: 00007f2f288d8000 R15: 0000000000f6bdb0
  [   48.605527]  </TASK>

In the test, two processes are communicating through pipe. Further debugging
with strace found that the above splat is triggered as read() syscall could
not receive the data even if the corresponding write() syscall in another
process successfully wrote data into the pipe.

The failed subtest is "send_signal_perf". The corresponding perf event has
sample_period 1 and config PERF_COUNT_SW_CPU_CLOCK. sample_period 1 means every
overflow event will trigger a call to the BPF program. So I suspect this may
overwhelm the system. So I increased the sample_period to 100,000 and the test
passed. The sample_period 10,000 still has the test failed.

In other parts of selftest, e.g., [1], sample_freq is used instead. So I
decided to use sample_freq = 1,000 since the test can pass as well.

  [1] https://lore.kernel.org/bpf/20240604070700.3032142-1-song@kernel.org/

Reported-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20240605201203.2603846-1-yonghong.song@linux.dev
---
 tools/testing/selftests/bpf/prog_tests/send_signal.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/send_signal.c b/tools/testing/selftests/bpf/prog_tests/send_signal.c
index 920aee41bd58c..6cc69900b3106 100644
--- a/tools/testing/selftests/bpf/prog_tests/send_signal.c
+++ b/tools/testing/selftests/bpf/prog_tests/send_signal.c
@@ -156,7 +156,8 @@ static void test_send_signal_tracepoint(bool signal_thread)
 static void test_send_signal_perf(bool signal_thread)
 {
 	struct perf_event_attr attr = {
-		.sample_period = 1,
+		.freq = 1,
+		.sample_freq = 1000,
 		.type = PERF_TYPE_SOFTWARE,
 		.config = PERF_COUNT_SW_CPU_CLOCK,
 	};
-- 
GitLab


From b24862bac7b5db326716ad07bbff7b6ee3b09a59 Mon Sep 17 00:00:00 2001
From: Alan Maguire <alan.maguire@oracle.com>
Date: Wed, 5 Jun 2024 16:33:14 +0100
Subject: [PATCH 886/950] selftests/bpf: Add btf_field_iter selftests

The added selftests verify that for every BTF kind we iterate correctly
over consituent strings and ids.

Signed-off-by: Alan Maguire <alan.maguire@oracle.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20240605153314.3727466-1-alan.maguire@oracle.com
---
 .../selftests/bpf/prog_tests/btf_field_iter.c | 161 ++++++++++++++++++
 1 file changed, 161 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/btf_field_iter.c

diff --git a/tools/testing/selftests/bpf/prog_tests/btf_field_iter.c b/tools/testing/selftests/bpf/prog_tests/btf_field_iter.c
new file mode 100644
index 0000000000000..32159d3eb281b
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/btf_field_iter.c
@@ -0,0 +1,161 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024, Oracle and/or its affiliates. */
+
+#include <test_progs.h>
+#include <bpf/btf.h>
+#include "btf_helpers.h"
+#include "bpf/libbpf_internal.h"
+
+struct field_data {
+	__u32 ids[5];
+	const char *strs[5];
+} fields[] = {
+	{ .ids = {},		.strs = {} },
+	{ .ids = {},		.strs = { "int" } },
+	{ .ids = {},		.strs = { "int64" } },
+	{ .ids = { 1 },		.strs = { "" } },
+	{ .ids = { 2, 1 },	.strs = { "" } },
+	{ .ids = { 3, 1 },	.strs = { "s1", "f1", "f2" } },
+	{ .ids = { 1, 5 },	.strs = { "u1", "f1", "f2" } },
+	{ .ids = {},		.strs = { "e1", "v1", "v2" } },
+	{ .ids = {},		.strs = { "fw1" } },
+	{ .ids = { 1 },		.strs = { "t" } },
+	{ .ids = { 2 },		.strs = { "" } },
+	{ .ids = { 1 },		.strs = { "" } },
+	{ .ids = { 3 },		.strs = { "" } },
+	{ .ids = { 1, 1, 3 },	.strs = { "", "p1", "p2" } },
+	{ .ids = { 13 },	.strs = { "func" } },
+	{ .ids = { 1 },		.strs = { "var1" } },
+	{ .ids = { 3 },		.strs = { "var2" } },
+	{ .ids = {},		.strs = { "float" } },
+	{ .ids = { 11 },	.strs = { "decltag" } },
+	{ .ids = { 6 },		.strs = { "typetag" } },
+	{ .ids = {},		.strs = { "e64", "eval1", "eval2", "eval3" } },
+	{ .ids = { 15, 16 },	.strs = { "datasec1" } }
+
+};
+
+/* Fabricate BTF with various types and check BTF field iteration finds types,
+ * strings expected.
+ */
+void test_btf_field_iter(void)
+{
+	struct btf *btf = NULL;
+	int id;
+
+	btf = btf__new_empty();
+	if (!ASSERT_OK_PTR(btf, "empty_btf"))
+		return;
+
+	btf__add_int(btf, "int", 4, BTF_INT_SIGNED);	/* [1] int */
+	btf__add_int(btf, "int64", 8, BTF_INT_SIGNED);	/* [2] int64 */
+	btf__add_ptr(btf, 1);				/* [3] int * */
+	btf__add_array(btf, 1, 2, 3);			/* [4] int64[3] */
+	btf__add_struct(btf, "s1", 12);			/* [5] struct s1 { */
+	btf__add_field(btf, "f1", 3, 0, 0);		/*      int *f1; */
+	btf__add_field(btf, "f2", 1, 0, 0);		/*	int f2; */
+							/* } */
+	btf__add_union(btf, "u1", 12);			/* [6] union u1 { */
+	btf__add_field(btf, "f1", 1, 0, 0);		/*	int f1; */
+	btf__add_field(btf, "f2", 5, 0, 0);		/*	struct s1 f2; */
+							/* } */
+	btf__add_enum(btf, "e1", 4);			/* [7] enum e1 { */
+	btf__add_enum_value(btf, "v1", 1);		/*	v1 = 1; */
+	btf__add_enum_value(btf, "v2", 2);		/*	v2 = 2; */
+							/* } */
+
+	btf__add_fwd(btf, "fw1", BTF_FWD_STRUCT);	/* [8] struct fw1; */
+	btf__add_typedef(btf, "t", 1);			/* [9] typedef int t; */
+	btf__add_volatile(btf, 2);			/* [10] volatile int64; */
+	btf__add_const(btf, 1);				/* [11] const int; */
+	btf__add_restrict(btf, 3);			/* [12] restrict int *; */
+	btf__add_func_proto(btf, 1);			/* [13] int (*)(int p1, int *p2); */
+	btf__add_func_param(btf, "p1", 1);
+	btf__add_func_param(btf, "p2", 3);
+
+	btf__add_func(btf, "func", BTF_FUNC_GLOBAL, 13);/* [14] int func(int p1, int *p2); */
+	btf__add_var(btf, "var1", BTF_VAR_STATIC, 1);	/* [15] static int var1; */
+	btf__add_var(btf, "var2", BTF_VAR_STATIC, 3);	/* [16] static int *var2; */
+	btf__add_float(btf, "float", 4);		/* [17] float; */
+	btf__add_decl_tag(btf, "decltag", 11, -1);	/* [18] decltag const int; */
+	btf__add_type_tag(btf, "typetag", 6);		/* [19] typetag union u1; */
+	btf__add_enum64(btf, "e64", 8, true);		/* [20] enum { */
+	btf__add_enum64_value(btf, "eval1", 1000);	/*	 eval1 = 1000, */
+	btf__add_enum64_value(btf, "eval2", 2000);	/*	 eval2 = 2000, */
+	btf__add_enum64_value(btf, "eval3", 3000);	/*	 eval3 = 3000 */
+							/* } */
+	btf__add_datasec(btf, "datasec1", 12);		/* [21] datasec datasec1 */
+	btf__add_datasec_var_info(btf, 15, 0, 4);
+	btf__add_datasec_var_info(btf, 16, 4, 8);
+
+	VALIDATE_RAW_BTF(
+		btf,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] INT 'int64' size=8 bits_offset=0 nr_bits=64 encoding=SIGNED",
+		"[3] PTR '(anon)' type_id=1",
+		"[4] ARRAY '(anon)' type_id=2 index_type_id=1 nr_elems=3",
+		"[5] STRUCT 's1' size=12 vlen=2\n"
+		"\t'f1' type_id=3 bits_offset=0\n"
+		"\t'f2' type_id=1 bits_offset=0",
+		"[6] UNION 'u1' size=12 vlen=2\n"
+		"\t'f1' type_id=1 bits_offset=0\n"
+		"\t'f2' type_id=5 bits_offset=0",
+		"[7] ENUM 'e1' encoding=UNSIGNED size=4 vlen=2\n"
+		"\t'v1' val=1\n"
+		"\t'v2' val=2",
+		"[8] FWD 'fw1' fwd_kind=struct",
+		"[9] TYPEDEF 't' type_id=1",
+		"[10] VOLATILE '(anon)' type_id=2",
+		"[11] CONST '(anon)' type_id=1",
+		"[12] RESTRICT '(anon)' type_id=3",
+		"[13] FUNC_PROTO '(anon)' ret_type_id=1 vlen=2\n"
+		"\t'p1' type_id=1\n"
+		"\t'p2' type_id=3",
+		"[14] FUNC 'func' type_id=13 linkage=global",
+		"[15] VAR 'var1' type_id=1, linkage=static",
+		"[16] VAR 'var2' type_id=3, linkage=static",
+		"[17] FLOAT 'float' size=4",
+		"[18] DECL_TAG 'decltag' type_id=11 component_idx=-1",
+		"[19] TYPE_TAG 'typetag' type_id=6",
+		"[20] ENUM64 'e64' encoding=SIGNED size=8 vlen=3\n"
+		"\t'eval1' val=1000\n"
+		"\t'eval2' val=2000\n"
+		"\t'eval3' val=3000",
+		"[21] DATASEC 'datasec1' size=12 vlen=2\n"
+		"\ttype_id=15 offset=0 size=4\n"
+		"\ttype_id=16 offset=4 size=8");
+
+	for (id = 1; id < btf__type_cnt(btf); id++) {
+		struct btf_type *t = btf_type_by_id(btf, id);
+		struct btf_field_iter it_strs, it_ids;
+		int str_idx = 0, id_idx = 0;
+		__u32 *next_str, *next_id;
+
+		if (!ASSERT_OK_PTR(t, "btf_type_by_id"))
+			break;
+		if (!ASSERT_OK(btf_field_iter_init(&it_strs, t, BTF_FIELD_ITER_STRS),
+			       "iter_init_strs"))
+			break;
+		if (!ASSERT_OK(btf_field_iter_init(&it_ids, t, BTF_FIELD_ITER_IDS),
+			       "iter_init_ids"))
+			break;
+		while ((next_str = btf_field_iter_next(&it_strs))) {
+			const char *str = btf__str_by_offset(btf, *next_str);
+
+			if (!ASSERT_OK(strcmp(fields[id].strs[str_idx], str), "field_str_match"))
+				break;
+			str_idx++;
+		}
+		/* ensure no more strings are expected */
+		ASSERT_EQ(fields[id].strs[str_idx], NULL, "field_str_cnt");
+
+		while ((next_id = btf_field_iter_next(&it_ids))) {
+			if (!ASSERT_EQ(*next_id, fields[id].ids[id_idx], "field_id_match"))
+				break;
+			id_idx++;
+		}
+		/* ensure no more ids are expected */
+		ASSERT_EQ(fields[id].ids[id_idx], 0, "field_id_cnt");
+	}
+	btf__free(btf);
+}
-- 
GitLab


From 41b02ea4c0adfcc6761fbfed42c3ce6b6412d881 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Wed, 5 Jun 2024 11:21:16 +0200
Subject: [PATCH 887/950] selftests: net: lib: support errexit with busywait

If errexit is enabled ('set -e'), loopy_wait -- or busywait and others
using it -- will stop after the first failure.

Note that if the returned status of loopy_wait is checked, and even if
errexit is enabled, Bash will not stop at the first error.

Fixes: 25ae948b4478 ("selftests/net: add lib.sh")
Cc: stable@vger.kernel.org
Acked-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Reviewed-by: Hangbin Liu <liuhangbin@gmail.com>
Link: https://lore.kernel.org/r/20240605-upstream-net-20240605-selftests-net-lib-fixes-v1-1-b3afadd368c9@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/lib.sh | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh
index edc030e81a464..a422e10d3d3a0 100644
--- a/tools/testing/selftests/net/lib.sh
+++ b/tools/testing/selftests/net/lib.sh
@@ -67,9 +67,7 @@ loopy_wait()
 	while true
 	do
 		local out
-		out=$("$@")
-		local ret=$?
-		if ((!ret)); then
+		if out=$("$@"); then
 			echo -n "$out"
 			return 0
 		fi
-- 
GitLab


From 79322174bcc780b99795cb89d237b26006a8b94b Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Wed, 5 Jun 2024 11:21:17 +0200
Subject: [PATCH 888/950] selftests: net: lib: avoid error removing empty netns
 name

If there is an error to create the first netns with 'setup_ns()',
'cleanup_ns()' will be called with an empty string as first parameter.

The consequences is that 'cleanup_ns()' will try to delete an invalid
netns, and wait 20 seconds if the netns list is empty.

Instead of just checking if the name is not empty, convert the string
separated by spaces to an array. Manipulating the array is cleaner, and
calling 'cleanup_ns()' with an empty array will be a no-op.

Fixes: 25ae948b4478 ("selftests/net: add lib.sh")
Cc: stable@vger.kernel.org
Acked-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Hangbin Liu <liuhangbin@gmail.com>
Link: https://lore.kernel.org/r/20240605-upstream-net-20240605-selftests-net-lib-fixes-v1-2-b3afadd368c9@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/lib.sh | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh
index a422e10d3d3a0..e2f51102d7e1e 100644
--- a/tools/testing/selftests/net/lib.sh
+++ b/tools/testing/selftests/net/lib.sh
@@ -15,7 +15,7 @@ ksft_xfail=2
 ksft_skip=4
 
 # namespace list created by setup_ns
-NS_LIST=""
+NS_LIST=()
 
 ##############################################################################
 # Helpers
@@ -137,6 +137,7 @@ cleanup_ns()
 	fi
 
 	for ns in "$@"; do
+		[ -z "${ns}" ] && continue
 		ip netns delete "${ns}" &> /dev/null
 		if ! busywait $BUSYWAIT_TIMEOUT ip netns list \| grep -vq "^$ns$" &> /dev/null; then
 			echo "Warn: Failed to remove namespace $ns"
@@ -150,7 +151,7 @@ cleanup_ns()
 
 cleanup_all_ns()
 {
-	cleanup_ns $NS_LIST
+	cleanup_ns "${NS_LIST[@]}"
 }
 
 # setup netns with given names as prefix. e.g
@@ -159,7 +160,7 @@ setup_ns()
 {
 	local ns=""
 	local ns_name=""
-	local ns_list=""
+	local ns_list=()
 	local ns_exist=
 	for ns_name in "$@"; do
 		# Some test may setup/remove same netns multi times
@@ -175,13 +176,13 @@ setup_ns()
 
 		if ! ip netns add "$ns"; then
 			echo "Failed to create namespace $ns_name"
-			cleanup_ns "$ns_list"
+			cleanup_ns "${ns_list[@]}"
 			return $ksft_skip
 		fi
 		ip -n "$ns" link set lo up
-		! $ns_exist && ns_list="$ns_list $ns"
+		! $ns_exist && ns_list+=("$ns")
 	done
-	NS_LIST="$NS_LIST $ns_list"
+	NS_LIST+=("${ns_list[@]}")
 }
 
 tc_rule_stats_get()
-- 
GitLab


From 84a8bc3ec225b28067b168e9410e452c83d706da Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Wed, 5 Jun 2024 11:21:18 +0200
Subject: [PATCH 889/950] selftests: net: lib: set 'i' as local

Without this, the 'i' variable declared before could be overridden by
accident, e.g.

  for i in "${@}"; do
      __ksft_status_merge "${i}"  ## 'i' has been modified
      foo "${i}"                  ## using 'i' with an unexpected value
  done

After a quick look, it looks like 'i' is currently not used after having
been modified in __ksft_status_merge(), but still, better be safe than
sorry. I saw this while modifying the same file, not because I suspected
an issue somewhere.

Fixes: 596c8819cb78 ("selftests: forwarding: Have RET track kselftest framework constants")
Acked-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Reviewed-by: Hangbin Liu <liuhangbin@gmail.com>
Link: https://lore.kernel.org/r/20240605-upstream-net-20240605-selftests-net-lib-fixes-v1-3-b3afadd368c9@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/lib.sh | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh
index e2f51102d7e1e..9155c914c064f 100644
--- a/tools/testing/selftests/net/lib.sh
+++ b/tools/testing/selftests/net/lib.sh
@@ -27,6 +27,7 @@ __ksft_status_merge()
 	local -A weights
 	local weight=0
 
+	local i
 	for i in "$@"; do
 		weights[$i]=$((weight++))
 	done
-- 
GitLab


From 08ac454e258e38813afb906650f19acce3afd982 Mon Sep 17 00:00:00 2001
From: Mykyta Yatsenko <yatsenko@meta.com>
Date: Wed, 5 Jun 2024 18:51:35 +0100
Subject: [PATCH 890/950] libbpf: Auto-attach struct_ops BPF maps in BPF
 skeleton

Similarly to `bpf_program`, support `bpf_map` automatic attachment in
`bpf_object__attach_skeleton`. Currently only struct_ops maps could be
attached.

On bpftool side, code-generate links in skeleton struct for struct_ops maps.
Similarly to `bpf_program_skeleton`, set links in `bpf_map_skeleton`.

On libbpf side, extend `bpf_map` with new `autoattach` field to support
enabling or disabling autoattach functionality, introducing
getter/setter for this field.

`bpf_object__(attach|detach)_skeleton` is extended with
attaching/detaching struct_ops maps logic.

Signed-off-by: Mykyta Yatsenko <yatsenko@meta.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20240605175135.117127-1-yatsenko@meta.com
---
 tools/bpf/bpftool/gen.c  | 36 +++++++++++++++++++---
 tools/lib/bpf/libbpf.c   | 64 ++++++++++++++++++++++++++++++++++++++--
 tools/lib/bpf/libbpf.h   | 18 +++++++++++
 tools/lib/bpf/libbpf.map |  2 ++
 4 files changed, 113 insertions(+), 7 deletions(-)

diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c
index d244a7de387e7..4a4eedfcd4792 100644
--- a/tools/bpf/bpftool/gen.c
+++ b/tools/bpf/bpftool/gen.c
@@ -848,7 +848,7 @@ out:
 }
 
 static void
-codegen_maps_skeleton(struct bpf_object *obj, size_t map_cnt, bool mmaped)
+codegen_maps_skeleton(struct bpf_object *obj, size_t map_cnt, bool mmaped, bool populate_links)
 {
 	struct bpf_map *map;
 	char ident[256];
@@ -888,6 +888,14 @@ codegen_maps_skeleton(struct bpf_object *obj, size_t map_cnt, bool mmaped)
 			printf("\ts->maps[%zu].mmaped = (void **)&obj->%s;\n",
 				i, ident);
 		}
+
+		if (populate_links && bpf_map__type(map) == BPF_MAP_TYPE_STRUCT_OPS) {
+			codegen("\
+				\n\
+					s->maps[%zu].link = &obj->links.%s;\n\
+				",
+				i, ident);
+		}
 		i++;
 	}
 }
@@ -1141,7 +1149,7 @@ static void gen_st_ops_shadow_init(struct btf *btf, struct bpf_object *obj)
 static int do_skeleton(int argc, char **argv)
 {
 	char header_guard[MAX_OBJ_NAME_LEN + sizeof("__SKEL_H__")];
-	size_t map_cnt = 0, prog_cnt = 0, file_sz, mmap_sz;
+	size_t map_cnt = 0, prog_cnt = 0, attach_map_cnt = 0, file_sz, mmap_sz;
 	DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts);
 	char obj_name[MAX_OBJ_NAME_LEN] = "", *obj_data;
 	struct bpf_object *obj = NULL;
@@ -1225,6 +1233,10 @@ static int do_skeleton(int argc, char **argv)
 			      bpf_map__name(map));
 			continue;
 		}
+
+		if (bpf_map__type(map) == BPF_MAP_TYPE_STRUCT_OPS)
+			attach_map_cnt++;
+
 		map_cnt++;
 	}
 	bpf_object__for_each_program(prog, obj) {
@@ -1297,6 +1309,9 @@ static int do_skeleton(int argc, char **argv)
 				       bpf_program__name(prog));
 		}
 		printf("\t} progs;\n");
+	}
+
+	if (prog_cnt + attach_map_cnt) {
 		printf("\tstruct {\n");
 		bpf_object__for_each_program(prog, obj) {
 			if (use_loader)
@@ -1306,6 +1321,19 @@ static int do_skeleton(int argc, char **argv)
 				printf("\t\tstruct bpf_link *%s;\n",
 				       bpf_program__name(prog));
 		}
+
+		bpf_object__for_each_map(map, obj) {
+			if (!get_map_ident(map, ident, sizeof(ident)))
+				continue;
+			if (bpf_map__type(map) != BPF_MAP_TYPE_STRUCT_OPS)
+				continue;
+
+			if (use_loader)
+				printf("t\tint %s_fd;\n", ident);
+			else
+				printf("\t\tstruct bpf_link *%s;\n", ident);
+		}
+
 		printf("\t} links;\n");
 	}
 
@@ -1448,7 +1476,7 @@ static int do_skeleton(int argc, char **argv)
 		obj_name
 	);
 
-	codegen_maps_skeleton(obj, map_cnt, true /*mmaped*/);
+	codegen_maps_skeleton(obj, map_cnt, true /*mmaped*/, true /*links*/);
 	codegen_progs_skeleton(obj, prog_cnt, true /*populate_links*/);
 
 	codegen("\
@@ -1786,7 +1814,7 @@ static int do_subskeleton(int argc, char **argv)
 		}
 	}
 
-	codegen_maps_skeleton(obj, map_cnt, false /*mmaped*/);
+	codegen_maps_skeleton(obj, map_cnt, false /*mmaped*/, false /*links*/);
 	codegen_progs_skeleton(obj, prog_cnt, false /*links*/);
 
 	codegen("\
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index d1627a2ca30bb..4a28fac4908a6 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -572,6 +572,7 @@ struct bpf_map {
 	bool pinned;
 	bool reused;
 	bool autocreate;
+	bool autoattach;
 	__u64 map_extra;
 };
 
@@ -1400,6 +1401,7 @@ static int init_struct_ops_maps(struct bpf_object *obj, const char *sec_name,
 		map->def.value_size = type->size;
 		map->def.max_entries = 1;
 		map->def.map_flags = strcmp(sec_name, STRUCT_OPS_LINK_SEC) == 0 ? BPF_F_LINK : 0;
+		map->autoattach = true;
 
 		map->st_ops = calloc(1, sizeof(*map->st_ops));
 		if (!map->st_ops)
@@ -4819,6 +4821,20 @@ int bpf_map__set_autocreate(struct bpf_map *map, bool autocreate)
 	return 0;
 }
 
+int bpf_map__set_autoattach(struct bpf_map *map, bool autoattach)
+{
+	if (!bpf_map__is_struct_ops(map))
+		return libbpf_err(-EINVAL);
+
+	map->autoattach = autoattach;
+	return 0;
+}
+
+bool bpf_map__autoattach(const struct bpf_map *map)
+{
+	return map->autoattach;
+}
+
 int bpf_map__reuse_fd(struct bpf_map *map, int fd)
 {
 	struct bpf_map_info info;
@@ -12900,8 +12916,10 @@ struct bpf_link *bpf_map__attach_struct_ops(const struct bpf_map *map)
 	__u32 zero = 0;
 	int err, fd;
 
-	if (!bpf_map__is_struct_ops(map))
+	if (!bpf_map__is_struct_ops(map)) {
+		pr_warn("map '%s': can't attach non-struct_ops map\n", map->name);
 		return libbpf_err_ptr(-EINVAL);
+	}
 
 	if (map->fd < 0) {
 		pr_warn("map '%s': can't attach BPF map without FD (was it created?)\n", map->name);
@@ -13945,6 +13963,35 @@ int bpf_object__attach_skeleton(struct bpf_object_skeleton *s)
 		 */
 	}
 
+	/* Skeleton is created with earlier version of bpftool
+	 * which does not support auto-attachment
+	 */
+	if (s->map_skel_sz < sizeof(struct bpf_map_skeleton))
+		return 0;
+
+	for (i = 0; i < s->map_cnt; i++) {
+		struct bpf_map *map = *s->maps[i].map;
+		struct bpf_link **link = s->maps[i].link;
+
+		if (!map->autocreate || !map->autoattach)
+			continue;
+
+		if (*link)
+			continue;
+
+		/* only struct_ops maps can be attached */
+		if (!bpf_map__is_struct_ops(map))
+			continue;
+		*link = bpf_map__attach_struct_ops(map);
+
+		if (!*link) {
+			err = -errno;
+			pr_warn("map '%s': failed to auto-attach: %d\n",
+				bpf_map__name(map), err);
+			return libbpf_err(err);
+		}
+	}
+
 	return 0;
 }
 
@@ -13958,6 +14005,18 @@ void bpf_object__detach_skeleton(struct bpf_object_skeleton *s)
 		bpf_link__destroy(*link);
 		*link = NULL;
 	}
+
+	if (s->map_skel_sz < sizeof(struct bpf_map_skeleton))
+		return;
+
+	for (i = 0; i < s->map_cnt; i++) {
+		struct bpf_link **link = s->maps[i].link;
+
+		if (link) {
+			bpf_link__destroy(*link);
+			*link = NULL;
+		}
+	}
 }
 
 void bpf_object__destroy_skeleton(struct bpf_object_skeleton *s)
@@ -13965,8 +14024,7 @@ void bpf_object__destroy_skeleton(struct bpf_object_skeleton *s)
 	if (!s)
 		return;
 
-	if (s->progs)
-		bpf_object__detach_skeleton(s);
+	bpf_object__detach_skeleton(s);
 	if (s->obj)
 		bpf_object__close(*s->obj);
 	free(s->maps);
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 26e4e35528c53..64a6a3d323e37 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -978,6 +978,23 @@ bpf_object__prev_map(const struct bpf_object *obj, const struct bpf_map *map);
 LIBBPF_API int bpf_map__set_autocreate(struct bpf_map *map, bool autocreate);
 LIBBPF_API bool bpf_map__autocreate(const struct bpf_map *map);
 
+/**
+ * @brief **bpf_map__set_autoattach()** sets whether libbpf has to auto-attach
+ * map during BPF skeleton attach phase.
+ * @param map the BPF map instance
+ * @param autoattach whether to attach map during BPF skeleton attach phase
+ * @return 0 on success; negative error code, otherwise
+ */
+LIBBPF_API int bpf_map__set_autoattach(struct bpf_map *map, bool autoattach);
+
+/**
+ * @brief **bpf_map__autoattach()** returns whether BPF map is configured to
+ * auto-attach during BPF skeleton attach phase.
+ * @param map the BPF map instance
+ * @return true if map is set to auto-attach during skeleton attach phase; false, otherwise
+ */
+LIBBPF_API bool bpf_map__autoattach(const struct bpf_map *map);
+
 /**
  * @brief **bpf_map__fd()** gets the file descriptor of the passed
  * BPF map
@@ -1672,6 +1689,7 @@ struct bpf_map_skeleton {
 	const char *name;
 	struct bpf_map **map;
 	void **mmaped;
+	struct bpf_link **link;
 };
 
 struct bpf_prog_skeleton {
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index c1ce8aa3520bf..40595233dc7fb 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -419,6 +419,8 @@ LIBBPF_1.4.0 {
 
 LIBBPF_1.5.0 {
 	global:
+		bpf_map__autoattach;
+		bpf_map__set_autoattach;
 		bpf_program__attach_sockmap;
 		ring__consume_n;
 		ring_buffer__consume_n;
-- 
GitLab


From 9abdfd8a212332c64f6d0a27fc2ad69e9e0335d1 Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Thu, 30 May 2024 15:41:08 +0800
Subject: [PATCH 891/950] selftests/bpf: Use connect_to_fd_opts in do_test in
 bpf_tcp_ca

This patch uses connect_to_fd_opts() instead of using connect_fd_to_fd()
and settcpca() in do_test() in prog_tests/bpf_tcp_ca.c to accept a struct
network_helper_opts argument.

Then define a dctcp dedicated post_socket_cb callback stg_post_socket_cb(),
invoking both settcpca() and bpf_map_update_elem() in it, and set it in
test_dctcp(). For passing map_fd into stg_post_socket_cb() callback, a new
member map_fd is added in struct cb_opts.

Add another "const struct network_helper_opts *cli_opts" to do_test() to
separate it from the server "opts".

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/876ec90430865bc468e3b7f6fb2648420b075548.1717054461.git.tanggeliang@kylinos.cn
---
 .../selftests/bpf/prog_tests/bpf_tcp_ca.c     | 61 +++++++++++--------
 1 file changed, 34 insertions(+), 27 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
index ebc7d46168801..2f9d373feb0a8 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
@@ -25,6 +25,7 @@ static int expected_stg = 0xeB9F;
 
 struct cb_opts {
 	const char *cc;
+	int map_fd;
 };
 
 static int settcpca(int fd, const char *tcp_ca)
@@ -39,9 +40,9 @@ static int settcpca(int fd, const char *tcp_ca)
 }
 
 static void do_test(const struct network_helper_opts *opts,
+		    const struct network_helper_opts *cli_opts,
 		    const struct bpf_map *sk_stg_map)
 {
-	struct cb_opts *cb_opts = (struct cb_opts *)opts->cb_opts;
 	int lfd = -1, fd = -1;
 	int err;
 
@@ -49,25 +50,9 @@ static void do_test(const struct network_helper_opts *opts,
 	if (!ASSERT_NEQ(lfd, -1, "socket"))
 		return;
 
-	fd = socket(AF_INET6, SOCK_STREAM, 0);
-	if (!ASSERT_NEQ(fd, -1, "socket")) {
-		close(lfd);
-		return;
-	}
-
-	if (settcpca(fd, cb_opts->cc))
-		goto done;
-
-	if (sk_stg_map) {
-		err = bpf_map_update_elem(bpf_map__fd(sk_stg_map), &fd,
-					  &expected_stg, BPF_NOEXIST);
-		if (!ASSERT_OK(err, "bpf_map_update_elem(sk_stg_map)"))
-			goto done;
-	}
-
 	/* connect to server */
-	err = connect_fd_to_fd(fd, lfd, 0);
-	if (!ASSERT_NEQ(err, -1, "connect"))
+	fd = connect_to_fd_opts(lfd, cli_opts);
+	if (!ASSERT_NEQ(fd, -1, "connect_to_fd_opts"))
 		goto done;
 
 	if (sk_stg_map) {
@@ -116,7 +101,7 @@ static void test_cubic(void)
 		return;
 	}
 
-	do_test(&opts, NULL);
+	do_test(&opts, &opts, NULL);
 
 	ASSERT_EQ(cubic_skel->bss->bpf_cubic_acked_called, 1, "pkts_acked called");
 
@@ -124,6 +109,23 @@ static void test_cubic(void)
 	bpf_cubic__destroy(cubic_skel);
 }
 
+static int stg_post_socket_cb(int fd, void *opts)
+{
+	struct cb_opts *cb_opts = (struct cb_opts *)opts;
+	int err;
+
+	err = settcpca(fd, cb_opts->cc);
+	if (err)
+		return err;
+
+	err = bpf_map_update_elem(cb_opts->map_fd, &fd,
+				  &expected_stg, BPF_NOEXIST);
+	if (!ASSERT_OK(err, "bpf_map_update_elem(sk_stg_map)"))
+		return err;
+
+	return 0;
+}
+
 static void test_dctcp(void)
 {
 	struct cb_opts cb_opts = {
@@ -133,6 +135,10 @@ static void test_dctcp(void)
 		.post_socket_cb	= cc_cb,
 		.cb_opts	= &cb_opts,
 	};
+	struct network_helper_opts cli_opts = {
+		.post_socket_cb	= stg_post_socket_cb,
+		.cb_opts	= &cb_opts,
+	};
 	struct bpf_dctcp *dctcp_skel;
 	struct bpf_link *link;
 
@@ -146,7 +152,8 @@ static void test_dctcp(void)
 		return;
 	}
 
-	do_test(&opts, dctcp_skel->maps.sk_stg_map);
+	cb_opts.map_fd = bpf_map__fd(dctcp_skel->maps.sk_stg_map);
+	do_test(&opts, &cli_opts, dctcp_skel->maps.sk_stg_map);
 	ASSERT_EQ(dctcp_skel->bss->stg_result, expected_stg, "stg_result");
 
 	bpf_link__destroy(link);
@@ -350,14 +357,14 @@ static void test_update_ca(void)
 	link = bpf_map__attach_struct_ops(skel->maps.ca_update_1);
 	ASSERT_OK_PTR(link, "attach_struct_ops");
 
-	do_test(&opts, NULL);
+	do_test(&opts, &opts, NULL);
 	saved_ca1_cnt = skel->bss->ca1_cnt;
 	ASSERT_GT(saved_ca1_cnt, 0, "ca1_ca1_cnt");
 
 	err = bpf_link__update_map(link, skel->maps.ca_update_2);
 	ASSERT_OK(err, "update_map");
 
-	do_test(&opts, NULL);
+	do_test(&opts, &opts, NULL);
 	ASSERT_EQ(skel->bss->ca1_cnt, saved_ca1_cnt, "ca2_ca1_cnt");
 	ASSERT_GT(skel->bss->ca2_cnt, 0, "ca2_ca2_cnt");
 
@@ -386,14 +393,14 @@ static void test_update_wrong(void)
 	link = bpf_map__attach_struct_ops(skel->maps.ca_update_1);
 	ASSERT_OK_PTR(link, "attach_struct_ops");
 
-	do_test(&opts, NULL);
+	do_test(&opts, &opts, NULL);
 	saved_ca1_cnt = skel->bss->ca1_cnt;
 	ASSERT_GT(saved_ca1_cnt, 0, "ca1_ca1_cnt");
 
 	err = bpf_link__update_map(link, skel->maps.ca_wrong);
 	ASSERT_ERR(err, "update_map");
 
-	do_test(&opts, NULL);
+	do_test(&opts, &opts, NULL);
 	ASSERT_GT(skel->bss->ca1_cnt, saved_ca1_cnt, "ca2_ca1_cnt");
 
 	bpf_link__destroy(link);
@@ -423,7 +430,7 @@ static void test_mixed_links(void)
 	link = bpf_map__attach_struct_ops(skel->maps.ca_update_1);
 	ASSERT_OK_PTR(link, "attach_struct_ops");
 
-	do_test(&opts, NULL);
+	do_test(&opts, &opts, NULL);
 	ASSERT_GT(skel->bss->ca1_cnt, 0, "ca1_ca1_cnt");
 
 	err = bpf_link__update_map(link, skel->maps.ca_no_link);
@@ -530,7 +537,7 @@ static void test_cc_cubic(void)
 		return;
 	}
 
-	do_test(&opts, NULL);
+	do_test(&opts, &opts, NULL);
 
 	bpf_link__destroy(link);
 	bpf_cc_cubic__destroy(cc_cubic_skel);
-- 
GitLab


From fee97d0c9a14b5dd5cce0ec1df3a54a6b963f40c Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Thu, 30 May 2024 15:41:09 +0800
Subject: [PATCH 892/950] selftests/bpf: Add start_test helper in bpf_tcp_ca

For moving the "if (sk_stg_map)" block out of do_test(), extract the
code before this block as a new function start_test(). It creates
server-side and client-side sockets and returns them to the caller.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/48f2921ff9be958f5d3d28fe6bb7269a61cafa9f.1717054461.git.tanggeliang@kylinos.cn
---
 .../selftests/bpf/prog_tests/bpf_tcp_ca.c     | 42 +++++++++++++++----
 1 file changed, 33 insertions(+), 9 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
index 2f9d373feb0a8..794651ce0629a 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
@@ -39,6 +39,34 @@ static int settcpca(int fd, const char *tcp_ca)
 	return 0;
 }
 
+static bool start_test(char *addr_str,
+		       const struct network_helper_opts *srv_opts,
+		       const struct network_helper_opts *cli_opts,
+		       int *srv_fd, int *cli_fd)
+{
+	*srv_fd = start_server_str(AF_INET6, SOCK_STREAM, addr_str, 0, srv_opts);
+	if (!ASSERT_NEQ(*srv_fd, -1, "start_server_str"))
+		goto err;
+
+	/* connect to server */
+	*cli_fd = connect_to_fd_opts(*srv_fd, cli_opts);
+	if (!ASSERT_NEQ(*cli_fd, -1, "connect_to_fd_opts"))
+		goto err;
+
+	return true;
+
+err:
+	if (*srv_fd != -1) {
+		close(*srv_fd);
+		*srv_fd = -1;
+	}
+	if (*cli_fd != -1) {
+		close(*cli_fd);
+		*cli_fd = -1;
+	}
+	return false;
+}
+
 static void do_test(const struct network_helper_opts *opts,
 		    const struct network_helper_opts *cli_opts,
 		    const struct bpf_map *sk_stg_map)
@@ -46,13 +74,7 @@ static void do_test(const struct network_helper_opts *opts,
 	int lfd = -1, fd = -1;
 	int err;
 
-	lfd = start_server_str(AF_INET6, SOCK_STREAM, NULL, 0, opts);
-	if (!ASSERT_NEQ(lfd, -1, "socket"))
-		return;
-
-	/* connect to server */
-	fd = connect_to_fd_opts(lfd, cli_opts);
-	if (!ASSERT_NEQ(fd, -1, "connect_to_fd_opts"))
+	if (!start_test(NULL, opts, cli_opts, &lfd, &fd))
 		goto done;
 
 	if (sk_stg_map) {
@@ -68,8 +90,10 @@ static void do_test(const struct network_helper_opts *opts,
 	ASSERT_OK(send_recv_data(lfd, fd, total_bytes), "send_recv_data");
 
 done:
-	close(lfd);
-	close(fd);
+	if (lfd != -1)
+		close(lfd);
+	if (fd != -1)
+		close(fd);
 }
 
 static int cc_cb(int fd, void *opts)
-- 
GitLab


From 224eeb5598c30ee835dc9fea4c7ad85a8fb7eda4 Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Thu, 30 May 2024 15:41:10 +0800
Subject: [PATCH 893/950] selftests/bpf: Use start_test in test_dctcp_fallback
 in bpf_tcp_ca

The newly added helper start_test() can be used in test_dctcp_fallback()
too, to replace start_server_str() and connect_to_fd_opts(). In that
way, two network_helper_opts srv_opts and cli_opts are used instead of
the previously shared opts.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/792ca3bb013fa06e618176da02d75e4f79a76733.1717054461.git.tanggeliang@kylinos.cn
---
 .../selftests/bpf/prog_tests/bpf_tcp_ca.c     | 20 +++++++++----------
 1 file changed, 9 insertions(+), 11 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
index 794651ce0629a..d10217169ff8a 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
@@ -229,17 +229,22 @@ static void test_invalid_license(void)
 static void test_dctcp_fallback(void)
 {
 	int err, lfd = -1, cli_fd = -1, srv_fd = -1;
-	struct network_helper_opts opts = {
-		.post_socket_cb	= cc_cb,
-	};
 	struct bpf_dctcp *dctcp_skel;
 	struct bpf_link *link = NULL;
 	struct cb_opts dctcp = {
 		.cc = "bpf_dctcp",
 	};
+	struct network_helper_opts srv_opts = {
+		.post_socket_cb = cc_cb,
+		.cb_opts = &dctcp,
+	};
 	struct cb_opts cubic = {
 		.cc = "cubic",
 	};
+	struct network_helper_opts cli_opts = {
+		.post_socket_cb = cc_cb,
+		.cb_opts = &cubic,
+	};
 	char srv_cc[16];
 	socklen_t cc_len = sizeof(srv_cc);
 
@@ -254,14 +259,7 @@ static void test_dctcp_fallback(void)
 	if (!ASSERT_OK_PTR(link, "dctcp link"))
 		goto done;
 
-	opts.cb_opts = &dctcp;
-	lfd = start_server_str(AF_INET6, SOCK_STREAM, "::1", 0, &opts);
-	if (!ASSERT_GE(lfd, 0, "lfd"))
-		goto done;
-
-	opts.cb_opts = &cubic;
-	cli_fd = connect_to_fd_opts(lfd, &opts);
-	if (!ASSERT_GE(cli_fd, 0, "cli_fd"))
+	if (!start_test("::1", &srv_opts, &cli_opts, &lfd, &cli_fd))
 		goto done;
 
 	srv_fd = accept(lfd, NULL, 0);
-- 
GitLab


From cd984b2ed62423eb3daceacb21d651115a612af6 Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Thu, 30 May 2024 15:41:11 +0800
Subject: [PATCH 894/950] selftests/bpf: Use start_test in test_dctcp in
 bpf_tcp_ca

The "if (sk_stg_map)" block in do_test() is only used by test_dctcp(),
it makes sense to move it from do_test() into test_dctcp(). Then
do_test() can be used by other tests except test_dctcp().

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/9938916627b9810c877e5c03a621bc0ba5acf5c5.1717054461.git.tanggeliang@kylinos.cn
---
 .../selftests/bpf/prog_tests/bpf_tcp_ca.c     | 27 ++++++++++---------
 1 file changed, 15 insertions(+), 12 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
index d10217169ff8a..1b27d0232cbd4 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
@@ -72,21 +72,10 @@ static void do_test(const struct network_helper_opts *opts,
 		    const struct bpf_map *sk_stg_map)
 {
 	int lfd = -1, fd = -1;
-	int err;
 
 	if (!start_test(NULL, opts, cli_opts, &lfd, &fd))
 		goto done;
 
-	if (sk_stg_map) {
-		int tmp_stg;
-
-		err = bpf_map_lookup_elem(bpf_map__fd(sk_stg_map), &fd,
-					  &tmp_stg);
-		if (!ASSERT_ERR(err, "bpf_map_lookup_elem(sk_stg_map)") ||
-				!ASSERT_EQ(errno, ENOENT, "bpf_map_lookup_elem(sk_stg_map)"))
-			goto done;
-	}
-
 	ASSERT_OK(send_recv_data(lfd, fd, total_bytes), "send_recv_data");
 
 done:
@@ -163,6 +152,7 @@ static void test_dctcp(void)
 		.post_socket_cb	= stg_post_socket_cb,
 		.cb_opts	= &cb_opts,
 	};
+	int lfd = -1, fd = -1, tmp_stg, err;
 	struct bpf_dctcp *dctcp_skel;
 	struct bpf_link *link;
 
@@ -177,11 +167,24 @@ static void test_dctcp(void)
 	}
 
 	cb_opts.map_fd = bpf_map__fd(dctcp_skel->maps.sk_stg_map);
-	do_test(&opts, &cli_opts, dctcp_skel->maps.sk_stg_map);
+	if (!start_test(NULL, &opts, &cli_opts, &lfd, &fd))
+		goto done;
+
+	err = bpf_map_lookup_elem(cb_opts.map_fd, &fd, &tmp_stg);
+	if (!ASSERT_ERR(err, "bpf_map_lookup_elem(sk_stg_map)") ||
+			!ASSERT_EQ(errno, ENOENT, "bpf_map_lookup_elem(sk_stg_map)"))
+		goto done;
+
+	ASSERT_OK(send_recv_data(lfd, fd, total_bytes), "send_recv_data");
 	ASSERT_EQ(dctcp_skel->bss->stg_result, expected_stg, "stg_result");
 
+done:
 	bpf_link__destroy(link);
 	bpf_dctcp__destroy(dctcp_skel);
+	if (lfd != -1)
+		close(lfd);
+	if (fd != -1)
+		close(fd);
 }
 
 static char *err_str;
-- 
GitLab


From f85af9d955ac9601174e1c64f4b3308c1cae4a7e Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Thu, 30 May 2024 15:41:12 +0800
Subject: [PATCH 895/950] selftests/bpf: Drop useless arguments of do_test in
 bpf_tcp_ca

bpf_map_lookup_elem() has been removed from do_test(), it makes the
sk_stg_map argument of do_test() useless. In addition, two exactly the
same opts are passed in all the places where do_test() is invoked, so
cli_opts argument can be dropped too.

This patch drops these two useless arguments of do_test() in bpf_tcp_ca.c.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/7056eab111d78a05bce29d2821228dc93f240de4.1717054461.git.tanggeliang@kylinos.cn
---
 .../selftests/bpf/prog_tests/bpf_tcp_ca.c     | 20 +++++++++----------
 1 file changed, 9 insertions(+), 11 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
index 1b27d0232cbd4..67358adf5db3a 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
@@ -67,13 +67,11 @@ err:
 	return false;
 }
 
-static void do_test(const struct network_helper_opts *opts,
-		    const struct network_helper_opts *cli_opts,
-		    const struct bpf_map *sk_stg_map)
+static void do_test(const struct network_helper_opts *opts)
 {
 	int lfd = -1, fd = -1;
 
-	if (!start_test(NULL, opts, cli_opts, &lfd, &fd))
+	if (!start_test(NULL, opts, opts, &lfd, &fd))
 		goto done;
 
 	ASSERT_OK(send_recv_data(lfd, fd, total_bytes), "send_recv_data");
@@ -114,7 +112,7 @@ static void test_cubic(void)
 		return;
 	}
 
-	do_test(&opts, &opts, NULL);
+	do_test(&opts);
 
 	ASSERT_EQ(cubic_skel->bss->bpf_cubic_acked_called, 1, "pkts_acked called");
 
@@ -382,14 +380,14 @@ static void test_update_ca(void)
 	link = bpf_map__attach_struct_ops(skel->maps.ca_update_1);
 	ASSERT_OK_PTR(link, "attach_struct_ops");
 
-	do_test(&opts, &opts, NULL);
+	do_test(&opts);
 	saved_ca1_cnt = skel->bss->ca1_cnt;
 	ASSERT_GT(saved_ca1_cnt, 0, "ca1_ca1_cnt");
 
 	err = bpf_link__update_map(link, skel->maps.ca_update_2);
 	ASSERT_OK(err, "update_map");
 
-	do_test(&opts, &opts, NULL);
+	do_test(&opts);
 	ASSERT_EQ(skel->bss->ca1_cnt, saved_ca1_cnt, "ca2_ca1_cnt");
 	ASSERT_GT(skel->bss->ca2_cnt, 0, "ca2_ca2_cnt");
 
@@ -418,14 +416,14 @@ static void test_update_wrong(void)
 	link = bpf_map__attach_struct_ops(skel->maps.ca_update_1);
 	ASSERT_OK_PTR(link, "attach_struct_ops");
 
-	do_test(&opts, &opts, NULL);
+	do_test(&opts);
 	saved_ca1_cnt = skel->bss->ca1_cnt;
 	ASSERT_GT(saved_ca1_cnt, 0, "ca1_ca1_cnt");
 
 	err = bpf_link__update_map(link, skel->maps.ca_wrong);
 	ASSERT_ERR(err, "update_map");
 
-	do_test(&opts, &opts, NULL);
+	do_test(&opts);
 	ASSERT_GT(skel->bss->ca1_cnt, saved_ca1_cnt, "ca2_ca1_cnt");
 
 	bpf_link__destroy(link);
@@ -455,7 +453,7 @@ static void test_mixed_links(void)
 	link = bpf_map__attach_struct_ops(skel->maps.ca_update_1);
 	ASSERT_OK_PTR(link, "attach_struct_ops");
 
-	do_test(&opts, &opts, NULL);
+	do_test(&opts);
 	ASSERT_GT(skel->bss->ca1_cnt, 0, "ca1_ca1_cnt");
 
 	err = bpf_link__update_map(link, skel->maps.ca_no_link);
@@ -562,7 +560,7 @@ static void test_cc_cubic(void)
 		return;
 	}
 
-	do_test(&opts, &opts, NULL);
+	do_test(&opts);
 
 	bpf_link__destroy(link);
 	bpf_cc_cubic__destroy(cc_cubic_skel);
-- 
GitLab


From cb6cf0820f22ca36dc8f95cf1bd196e5ec24e69d Mon Sep 17 00:00:00 2001
From: Milan Broz <gmazyland@gmail.com>
Date: Wed, 5 Jun 2024 17:33:40 +0200
Subject: [PATCH 896/950] r8152: Set NET_ADDR_STOLEN if using passthru MAC

Some docks support MAC pass-through - MAC address
is taken from another device.

Driver should indicate that with NET_ADDR_STOLEN flag.

This should help to avoid collisions if network interface
names are generated with MAC policy.

Reported and discussed here
https://github.com/systemd/systemd/issues/33104

Signed-off-by: Milan Broz <gmazyland@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://lore.kernel.org/r/20240605153340.25694-1-gmazyland@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/r8152.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 09fe70bc45d48..15e12f46d0ea2 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -1774,6 +1774,7 @@ static int vendor_mac_passthru_addr_read(struct r8152 *tp, struct sockaddr *sa)
 		goto amacout;
 	}
 	memcpy(sa->sa_data, buf, 6);
+	tp->netdev->addr_assign_type = NET_ADDR_STOLEN;
 	netif_info(tp, probe, tp->netdev,
 		   "Using pass-thru MAC addr %pM\n", sa->sa_data);
 
-- 
GitLab


From a999973236543f0b8f6daeaa7ecba7488c3a593b Mon Sep 17 00:00:00 2001
From: MD Danish Anwar <danishanwar@ti.com>
Date: Wed, 5 Jun 2024 15:22:23 +0530
Subject: [PATCH 897/950] net: ti: icssg-prueth: Add multicast filtering
 support

Add multicast filtering support for ICSSG Driver. Multicast addresses will
be updated by __dev_mc_sync() API. icssg_prueth_add_macst () and
icssg_prueth_del_mcast() will be sync and unsync APIs for the driver
respectively.

To add a mac_address for a port, driver needs to call icssg_fdb_add_del()
and pass the mac_address and BIT(port_id) to the API. The ICSSG firmware
will then configure the rules and allow filtering.

If a mac_address is added to port0 and the same mac_address needs to be
added for port1, driver needs to pass BIT(port0) | BIT(port1) to the
icssg_fdb_add_del() API. If driver just pass BIT(port1) then the entry for
port0 will be overwritten / lost. This is a design constraint on the
firmware side.

To overcome this in the driver, to add any mac_address for let's say portX
driver first checks if the same mac_address is already added for any other
port. If yes driver calls icssg_fdb_add_del() with BIT(portX) |
BIT(other_existing_port). If not, driver calls icssg_fdb_add_del() with
BIT(portX).

The same thing is applicable for deleting mac_addresses as well. This
logic is in icssg_prueth_add_mcast / icssg_prueth_del_mcast APIs.

Signed-off-by: MD Danish Anwar <danishanwar@ti.com>
Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/icssg/icssg_prueth.c | 38 +++++++++++++++++---
 1 file changed, 34 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
index 6e65aa0977d40..e13835100754f 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
@@ -439,6 +439,37 @@ const struct icss_iep_clockops prueth_iep_clockops = {
 	.perout_enable = prueth_perout_enable,
 };
 
+static int icssg_prueth_add_mcast(struct net_device *ndev, const u8 *addr)
+{
+	struct prueth_emac *emac = netdev_priv(ndev);
+	int port_mask = BIT(emac->port_id);
+
+	port_mask |= icssg_fdb_lookup(emac, addr, 0);
+	icssg_fdb_add_del(emac, addr, 0, port_mask, true);
+	icssg_vtbl_modify(emac, 0, port_mask, port_mask, true);
+
+	return 0;
+}
+
+static int icssg_prueth_del_mcast(struct net_device *ndev, const u8 *addr)
+{
+	struct prueth_emac *emac = netdev_priv(ndev);
+	int port_mask = BIT(emac->port_id);
+	int other_port_mask;
+
+	other_port_mask = port_mask ^ icssg_fdb_lookup(emac, addr, 0);
+
+	icssg_fdb_add_del(emac, addr, 0, port_mask, false);
+	icssg_vtbl_modify(emac, 0, port_mask, port_mask, false);
+
+	if (other_port_mask) {
+		icssg_fdb_add_del(emac, addr, 0, other_port_mask, true);
+		icssg_vtbl_modify(emac, 0, other_port_mask, other_port_mask, true);
+	}
+
+	return 0;
+}
+
 /**
  * emac_ndo_open - EMAC device open
  * @ndev: network adapter device
@@ -599,6 +630,8 @@ static int emac_ndo_stop(struct net_device *ndev)
 
 	icssg_class_disable(prueth->miig_rt, prueth_emac_slice(emac));
 
+	__dev_mc_unsync(ndev, icssg_prueth_del_mcast);
+
 	atomic_set(&emac->tdown_cnt, emac->tx_ch_num);
 	/* ensure new tdown_cnt value is visible */
 	smp_mb__after_atomic();
@@ -675,10 +708,7 @@ static void emac_ndo_set_rx_mode_work(struct work_struct *work)
 		return;
 	}
 
-	if (!netdev_mc_empty(ndev)) {
-		emac_set_port_state(emac, ICSSG_EMAC_PORT_MC_FLOODING_ENABLE);
-		return;
-	}
+	__dev_mc_sync(ndev, icssg_prueth_add_mcast, icssg_prueth_del_mcast);
 }
 
 /**
-- 
GitLab


From 3e61103b2f7887af0be402a79b9c70425ceba3e3 Mon Sep 17 00:00:00 2001
From: David Wei <dw@davidwei.uk>
Date: Wed, 5 Jun 2024 09:19:24 -0700
Subject: [PATCH 898/950] page_pool: remove WARN_ON() with OR

Having an OR in WARN_ON() makes me sad because it's impossible to tell
which condition is true when triggered.

Split a WARN_ON() with an OR in page_pool_disable_direct_recycling().

Signed-off-by: David Wei <dw@davidwei.uk>
Reviewed-by: Mina Almasry <almasrymina@google.com>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/page_pool.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index f4444b4e39e63..3927a0a7fa9a8 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -1027,8 +1027,8 @@ static void page_pool_disable_direct_recycling(struct page_pool *pool)
 	/* To avoid races with recycling and additional barriers make sure
 	 * pool and NAPI are unlinked when NAPI is disabled.
 	 */
-	WARN_ON(!test_bit(NAPI_STATE_SCHED, &pool->p.napi->state) ||
-		READ_ONCE(pool->p.napi->list_owner) != -1);
+	WARN_ON(!test_bit(NAPI_STATE_SCHED, &pool->p.napi->state));
+	WARN_ON(READ_ONCE(pool->p.napi->list_owner) != -1);
 
 	WRITE_ONCE(pool->p.napi, NULL);
 }
-- 
GitLab


From 924ee531754827bf23eacf35e6408a7f44fb9021 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 5 Jun 2024 10:16:44 -0700
Subject: [PATCH 899/950] tools: ynl: make user space policies const

Dan, who's working on C++ YNL, pointed out that the C code
does not make policies const. Sprinkle some 'const's around.

Reported-by: Dan Melnic <dmm@meta.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Donald Hunter <donald.hunter@gmail.com>
Reviewed-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/net/ynl/lib/ynl-priv.h |  8 ++++----
 tools/net/ynl/lib/ynl.c      | 10 +++++-----
 tools/net/ynl/lib/ynl.h      |  2 +-
 tools/net/ynl/ynl-gen-c.py   |  6 +++---
 4 files changed, 13 insertions(+), 13 deletions(-)

diff --git a/tools/net/ynl/lib/ynl-priv.h b/tools/net/ynl/lib/ynl-priv.h
index 80791c34730c9..3c09a7bbfba59 100644
--- a/tools/net/ynl/lib/ynl-priv.h
+++ b/tools/net/ynl/lib/ynl-priv.h
@@ -45,17 +45,17 @@ struct ynl_policy_attr {
 	enum ynl_policy_type type;
 	unsigned int len;
 	const char *name;
-	struct ynl_policy_nest *nest;
+	const struct ynl_policy_nest *nest;
 };
 
 struct ynl_policy_nest {
 	unsigned int max_attr;
-	struct ynl_policy_attr *table;
+	const struct ynl_policy_attr *table;
 };
 
 struct ynl_parse_arg {
 	struct ynl_sock *ys;
-	struct ynl_policy_nest *rsp_policy;
+	const struct ynl_policy_nest *rsp_policy;
 	void *data;
 };
 
@@ -119,7 +119,7 @@ struct ynl_dump_state {
 };
 
 struct ynl_ntf_info {
-	struct ynl_policy_nest *policy;
+	const struct ynl_policy_nest *policy;
 	ynl_parse_cb_t cb;
 	size_t alloc_sz;
 	void (*free)(struct ynl_ntf_base_type *ntf);
diff --git a/tools/net/ynl/lib/ynl.c b/tools/net/ynl/lib/ynl.c
index 4b9c091fc86b5..fcb18a5a6d709 100644
--- a/tools/net/ynl/lib/ynl.c
+++ b/tools/net/ynl/lib/ynl.c
@@ -46,7 +46,7 @@
 
 /* -- Netlink boiler plate */
 static int
-ynl_err_walk_report_one(struct ynl_policy_nest *policy, unsigned int type,
+ynl_err_walk_report_one(const struct ynl_policy_nest *policy, unsigned int type,
 			char *str, int str_sz, int *n)
 {
 	if (!policy) {
@@ -75,8 +75,8 @@ ynl_err_walk_report_one(struct ynl_policy_nest *policy, unsigned int type,
 
 static int
 ynl_err_walk(struct ynl_sock *ys, void *start, void *end, unsigned int off,
-	     struct ynl_policy_nest *policy, char *str, int str_sz,
-	     struct ynl_policy_nest **nest_pol)
+	     const struct ynl_policy_nest *policy, char *str, int str_sz,
+	     const struct ynl_policy_nest **nest_pol)
 {
 	unsigned int astart_off, aend_off;
 	const struct nlattr *attr;
@@ -206,7 +206,7 @@ ynl_ext_ack_check(struct ynl_sock *ys, const struct nlmsghdr *nlh,
 		bad_attr[n] = '\0';
 	}
 	if (tb[NLMSGERR_ATTR_MISS_TYPE]) {
-		struct ynl_policy_nest *nest_pol = NULL;
+		const struct ynl_policy_nest *nest_pol = NULL;
 		unsigned int n, off, type;
 		void *start, *end;
 		int n2;
@@ -296,7 +296,7 @@ static int ynl_cb_done(const struct nlmsghdr *nlh, struct ynl_parse_arg *yarg)
 
 int ynl_attr_validate(struct ynl_parse_arg *yarg, const struct nlattr *attr)
 {
-	struct ynl_policy_attr *policy;
+	const struct ynl_policy_attr *policy;
 	unsigned int type, len;
 	unsigned char *data;
 
diff --git a/tools/net/ynl/lib/ynl.h b/tools/net/ynl/lib/ynl.h
index eef7c6324ed48..6cd570b283eab 100644
--- a/tools/net/ynl/lib/ynl.h
+++ b/tools/net/ynl/lib/ynl.h
@@ -76,7 +76,7 @@ struct ynl_sock {
 	struct ynl_ntf_base_type **ntf_last_next;
 
 	struct nlmsghdr *nlh;
-	struct ynl_policy_nest *req_policy;
+	const struct ynl_policy_nest *req_policy;
 	unsigned char *tx_buf;
 	unsigned char *rx_buf;
 	unsigned char raw_buf[];
diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py
index a42d62b23ee00..374ca5e86e24d 100755
--- a/tools/net/ynl/ynl-gen-c.py
+++ b/tools/net/ynl/ynl-gen-c.py
@@ -1507,12 +1507,12 @@ def print_dump_prototype(ri):
 
 
 def put_typol_fwd(cw, struct):
-    cw.p(f'extern struct ynl_policy_nest {struct.render_name}_nest;')
+    cw.p(f'extern const struct ynl_policy_nest {struct.render_name}_nest;')
 
 
 def put_typol(cw, struct):
     type_max = struct.attr_set.max_name
-    cw.block_start(line=f'struct ynl_policy_attr {struct.render_name}_policy[{type_max} + 1] =')
+    cw.block_start(line=f'const struct ynl_policy_attr {struct.render_name}_policy[{type_max} + 1] =')
 
     for _, arg in struct.member_list():
         arg.attr_typol(cw)
@@ -1520,7 +1520,7 @@ def put_typol(cw, struct):
     cw.block_end(line=';')
     cw.nl()
 
-    cw.block_start(line=f'struct ynl_policy_nest {struct.render_name}_nest =')
+    cw.block_start(line=f'const struct ynl_policy_nest {struct.render_name}_nest =')
     cw.p(f'.max_attr = {type_max},')
     cw.p(f'.table = {struct.render_name}_policy,')
     cw.block_end(line=';')
-- 
GitLab


From 28f961f9d5b7c3d9b9f93cc59e54477ba1278cf9 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Thu, 6 Jun 2024 17:23:44 +0300
Subject: [PATCH 900/950] dmaengine: ti: k3-udma-glue: clean up return in
 k3_udma_glue_rx_get_irq()

Currently the k3_udma_glue_rx_get_irq() function returns either negative
error codes or zero on error.  Generally, in the kernel, zero means
success so this be confusing and has caused bugs in the past.  Also the
"tx" version of this function only returns negative error codes.  Let's
clean this "rx" function so both functions match.

This patch has no effect on runtime.

Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Acked-by: Peter Ujfalusi <peter.ujfalusi@gmail.com>
Acked-by: Vinod Koul <vkoul@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/dma/ti/k3-udma-glue.c                | 3 +++
 drivers/net/ethernet/ti/am65-cpsw-nuss.c     | 4 ++--
 drivers/net/ethernet/ti/icssg/icssg_common.c | 4 +---
 3 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/dma/ti/k3-udma-glue.c b/drivers/dma/ti/k3-udma-glue.c
index c9b93055dc9d3..b96b448a0e69d 100644
--- a/drivers/dma/ti/k3-udma-glue.c
+++ b/drivers/dma/ti/k3-udma-glue.c
@@ -1531,6 +1531,9 @@ int k3_udma_glue_rx_get_irq(struct k3_udma_glue_rx_channel *rx_chn,
 		flow->virq = k3_ringacc_get_ring_irq_num(flow->ringrx);
 	}
 
+	if (!flow->virq)
+		return -ENXIO;
+
 	return flow->virq;
 }
 EXPORT_SYMBOL_GPL(k3_udma_glue_rx_get_irq);
diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
index e6f87ac394fe6..81d9f21086ec9 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
@@ -2424,10 +2424,10 @@ static int am65_cpsw_nuss_init_rx_chns(struct am65_cpsw_common *common)
 
 		rx_chn->irq = k3_udma_glue_rx_get_irq(rx_chn->rx_chn, i);
 
-		if (rx_chn->irq <= 0) {
+		if (rx_chn->irq < 0) {
 			dev_err(dev, "Failed to get rx dma irq %d\n",
 				rx_chn->irq);
-			ret = -ENXIO;
+			ret = rx_chn->irq;
 			goto err;
 		}
 	}
diff --git a/drivers/net/ethernet/ti/icssg/icssg_common.c b/drivers/net/ethernet/ti/icssg/icssg_common.c
index 873126dfc1734..2f716c0d70607 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_common.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_common.c
@@ -440,9 +440,7 @@ int prueth_init_rx_chns(struct prueth_emac *emac,
 			fdqring_id = k3_udma_glue_rx_flow_get_fdq_id(rx_chn->rx_chn,
 								     i);
 		ret = k3_udma_glue_rx_get_irq(rx_chn->rx_chn, i);
-		if (ret <= 0) {
-			if (!ret)
-				ret = -ENXIO;
+		if (ret < 0) {
 			netdev_err(ndev, "Failed to get rx dma irq");
 			goto fail;
 		}
-- 
GitLab


From c1e156ae50ee520baf4e560b1284677ddfcea974 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 6 Jun 2024 16:49:38 +0200
Subject: [PATCH 901/950] lib: objagg: Fix spelling

Fixes: 0a020d416d0a ("lib: introduce initial implementation of object aggregation manager")
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Amit Cohen <amcohen@nvidia.com>
Tested-by: Alexander Zubkov <green@qrator.net>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 lib/objagg.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/objagg.c b/lib/objagg.c
index 1e248629ed643..955538c902236 100644
--- a/lib/objagg.c
+++ b/lib/objagg.c
@@ -421,7 +421,7 @@ static struct objagg_obj *__objagg_obj_get(struct objagg *objagg, void *obj)
  *
  * There are 3 main options this function wraps:
  * 1) The object according to "obj" already exist. In that case
- *    the reference counter is incrementes and the object is returned.
+ *    the reference counter is incremented and the object is returned.
  * 2) The object does not exist, but it can be aggregated within
  *    another object. In that case, user ops->delta_create() is called
  *    to obtain delta data and a new object is created with returned
-- 
GitLab


From 2aad28ec4543f4c3154f904bcd817e649ffb0ba6 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 6 Jun 2024 16:49:39 +0200
Subject: [PATCH 902/950] lib: test_objagg: Fix spelling

Fixes: 0a020d416d0a ("lib: introduce initial implementation of object aggregation manager")
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Amit Cohen <amcohen@nvidia.com>
Tested-by: Alexander Zubkov <green@qrator.net>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 lib/test_objagg.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/test_objagg.c b/lib/test_objagg.c
index c0c957c506354..d34df4306b874 100644
--- a/lib/test_objagg.c
+++ b/lib/test_objagg.c
@@ -60,7 +60,7 @@ static struct objagg_obj *world_obj_get(struct world *world,
 	if (!world->key_refs[key_id_index(key_id)]) {
 		world->objagg_objs[key_id_index(key_id)] = objagg_obj;
 	} else if (world->objagg_objs[key_id_index(key_id)] != objagg_obj) {
-		pr_err("Key %u: God another object for the same key.\n",
+		pr_err("Key %u: Got another object for the same key.\n",
 		       key_id);
 		err = -EINVAL;
 		goto err_key_id_check;
-- 
GitLab


From 06fcdf2494068ceb29686657f8e5d15084e6e0c3 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 6 Jun 2024 16:49:40 +0200
Subject: [PATCH 903/950] mlxsw: spectrum_acl_atcam: Fix wrong comment

The key is encoded, not encrypted.

Fixes: c22291f7cf45 ("mlxsw: spectrum: acl: Implement delta for ERP")
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Amit Cohen <amcohen@nvidia.com>
Tested-by: Alexander Zubkov <green@qrator.net>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
index 4b713832fdd55..a7473e782b56f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
@@ -491,7 +491,7 @@ __mlxsw_sp_acl_atcam_entry_add(struct mlxsw_sp *mlxsw_sp,
 	       sizeof(aentry->enc_key));
 
 	/* Compute all needed delta information and clear the delta bits
-	 * from the encrypted key.
+	 * from the encoded key.
 	 */
 	delta = mlxsw_sp_acl_erp_delta(aentry->erp_mask);
 	aentry->delta_info.start = mlxsw_sp_acl_erp_delta_start(delta);
-- 
GitLab


From b4a3a89fffcdf09702b1f161b914e52abca1894d Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 6 Jun 2024 16:49:41 +0200
Subject: [PATCH 904/950] lib: objagg: Fix general protection fault

The library supports aggregation of objects into other objects only if
the parent object does not have a parent itself. That is, nesting is not
supported.

Aggregation happens in two cases: Without and with hints, where hints
are a pre-computed recommendation on how to aggregate the provided
objects.

Nesting is not possible in the first case due to a check that prevents
it, but in the second case there is no check because the assumption is
that nesting cannot happen when creating objects based on hints. The
violation of this assumption leads to various warnings and eventually to
a general protection fault [1].

Before fixing the root cause, error out when nesting happens and warn.

[1]
general protection fault, probably for non-canonical address 0xdead000000000d90: 0000 [#1] PREEMPT SMP PTI
CPU: 1 PID: 1083 Comm: kworker/1:9 Tainted: G        W          6.9.0-rc6-custom-gd9b4f1cca7fb #7
Hardware name: Mellanox Technologies Ltd. MSN3700/VMOD0005, BIOS 5.11 01/06/2019
Workqueue: mlxsw_core mlxsw_sp_acl_tcam_vregion_rehash_work
RIP: 0010:mlxsw_sp_acl_erp_bf_insert+0x25/0x80
[...]
Call Trace:
 <TASK>
 mlxsw_sp_acl_atcam_entry_add+0x256/0x3c0
 mlxsw_sp_acl_tcam_entry_create+0x5e/0xa0
 mlxsw_sp_acl_tcam_vchunk_migrate_one+0x16b/0x270
 mlxsw_sp_acl_tcam_vregion_rehash_work+0xbe/0x510
 process_one_work+0x151/0x370
 worker_thread+0x2cb/0x3e0
 kthread+0xd0/0x100
 ret_from_fork+0x34/0x50
 ret_from_fork_asm+0x1a/0x30
 </TASK>

Fixes: 9069a3817d82 ("lib: objagg: implement optimization hints assembly and use hints for object creation")
Reported-by: Alexander Zubkov <green@qrator.net>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Amit Cohen <amcohen@nvidia.com>
Tested-by: Alexander Zubkov <green@qrator.net>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 lib/objagg.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/lib/objagg.c b/lib/objagg.c
index 955538c902236..0f99ea5f53717 100644
--- a/lib/objagg.c
+++ b/lib/objagg.c
@@ -167,6 +167,9 @@ static int objagg_obj_parent_assign(struct objagg *objagg,
 {
 	void *delta_priv;
 
+	if (WARN_ON(!objagg_obj_is_root(parent)))
+		return -EINVAL;
+
 	delta_priv = objagg->ops->delta_create(objagg->priv, parent->obj,
 					       objagg_obj->obj);
 	if (IS_ERR(delta_priv))
-- 
GitLab


From 97d833ceb27dc19f8777d63f90be4a27b5daeedf Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 6 Jun 2024 16:49:42 +0200
Subject: [PATCH 905/950] mlxsw: spectrum_acl_erp: Fix object nesting warning

ACLs in Spectrum-2 and newer ASICs can reside in the algorithmic TCAM
(A-TCAM) or in the ordinary circuit TCAM (C-TCAM). The former can
contain more ACLs (i.e., tc filters), but the number of masks in each
region (i.e., tc chain) is limited.

In order to mitigate the effects of the above limitation, the device
allows filters to share a single mask if their masks only differ in up
to 8 consecutive bits. For example, dst_ip/25 can be represented using
dst_ip/24 with a delta of 1 bit. The C-TCAM does not have a limit on the
number of masks being used (and therefore does not support mask
aggregation), but can contain a limited number of filters.

The driver uses the "objagg" library to perform the mask aggregation by
passing it objects that consist of the filter's mask and whether the
filter is to be inserted into the A-TCAM or the C-TCAM since filters in
different TCAMs cannot share a mask.

The set of created objects is dependent on the insertion order of the
filters and is not necessarily optimal. Therefore, the driver will
periodically ask the library to compute a more optimal set ("hints") by
looking at all the existing objects.

When the library asks the driver whether two objects can be aggregated
the driver only compares the provided masks and ignores the A-TCAM /
C-TCAM indication. This is the right thing to do since the goal is to
move as many filters as possible to the A-TCAM. The driver also forbids
two identical masks from being aggregated since this can only happen if
one was intentionally put in the C-TCAM to avoid a conflict in the
A-TCAM.

The above can result in the following set of hints:

H1: {mask X, A-TCAM} -> H2: {mask Y, A-TCAM} // X is Y + delta
H3: {mask Y, C-TCAM} -> H4: {mask Z, A-TCAM} // Y is Z + delta

After getting the hints from the library the driver will start migrating
filters from one region to another while consulting the computed hints
and instructing the device to perform a lookup in both regions during
the transition.

Assuming a filter with mask X is being migrated into the A-TCAM in the
new region, the hints lookup will return H1. Since H2 is the parent of
H1, the library will try to find the object associated with it and
create it if necessary in which case another hints lookup (recursive)
will be performed. This hints lookup for {mask Y, A-TCAM} will either
return H2 or H3 since the driver passes the library an object comparison
function that ignores the A-TCAM / C-TCAM indication.

This can eventually lead to nested objects which are not supported by
the library [1].

Fix by removing the object comparison function from both the driver and
the library as the driver was the only user. That way the lookup will
only return exact matches.

I do not have a reliable reproducer that can reproduce the issue in a
timely manner, but before the fix the issue would reproduce in several
minutes and with the fix it does not reproduce in over an hour.

Note that the current usefulness of the hints is limited because they
include the C-TCAM indication and represent aggregation that cannot
actually happen. This will be addressed in net-next.

[1]
WARNING: CPU: 0 PID: 153 at lib/objagg.c:170 objagg_obj_parent_assign+0xb5/0xd0
Modules linked in:
CPU: 0 PID: 153 Comm: kworker/0:18 Not tainted 6.9.0-rc6-custom-g70fbc2c1c38b #42
Hardware name: Mellanox Technologies Ltd. MSN3700C/VMOD0008, BIOS 5.11 10/10/2018
Workqueue: mlxsw_core mlxsw_sp_acl_tcam_vregion_rehash_work
RIP: 0010:objagg_obj_parent_assign+0xb5/0xd0
[...]
Call Trace:
 <TASK>
 __objagg_obj_get+0x2bb/0x580
 objagg_obj_get+0xe/0x80
 mlxsw_sp_acl_erp_mask_get+0xb5/0xf0
 mlxsw_sp_acl_atcam_entry_add+0xe8/0x3c0
 mlxsw_sp_acl_tcam_entry_create+0x5e/0xa0
 mlxsw_sp_acl_tcam_vchunk_migrate_one+0x16b/0x270
 mlxsw_sp_acl_tcam_vregion_rehash_work+0xbe/0x510
 process_one_work+0x151/0x370

Fixes: 9069a3817d82 ("lib: objagg: implement optimization hints assembly and use hints for object creation")
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Amit Cohen <amcohen@nvidia.com>
Tested-by: Alexander Zubkov <green@qrator.net>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/mellanox/mlxsw/spectrum_acl_erp.c    | 13 -------------
 include/linux/objagg.h                            |  1 -
 lib/objagg.c                                      | 15 ---------------
 3 files changed, 29 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
index d231f4d2888be..9eee229303cce 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
@@ -1217,18 +1217,6 @@ static bool mlxsw_sp_acl_erp_delta_check(void *priv, const void *parent_obj,
 	return err ? false : true;
 }
 
-static int mlxsw_sp_acl_erp_hints_obj_cmp(const void *obj1, const void *obj2)
-{
-	const struct mlxsw_sp_acl_erp_key *key1 = obj1;
-	const struct mlxsw_sp_acl_erp_key *key2 = obj2;
-
-	/* For hints purposes, two objects are considered equal
-	 * in case the masks are the same. Does not matter what
-	 * the "ctcam" value is.
-	 */
-	return memcmp(key1->mask, key2->mask, sizeof(key1->mask));
-}
-
 static void *mlxsw_sp_acl_erp_delta_create(void *priv, void *parent_obj,
 					   void *obj)
 {
@@ -1308,7 +1296,6 @@ static void mlxsw_sp_acl_erp_root_destroy(void *priv, void *root_priv)
 static const struct objagg_ops mlxsw_sp_acl_erp_objagg_ops = {
 	.obj_size = sizeof(struct mlxsw_sp_acl_erp_key),
 	.delta_check = mlxsw_sp_acl_erp_delta_check,
-	.hints_obj_cmp = mlxsw_sp_acl_erp_hints_obj_cmp,
 	.delta_create = mlxsw_sp_acl_erp_delta_create,
 	.delta_destroy = mlxsw_sp_acl_erp_delta_destroy,
 	.root_create = mlxsw_sp_acl_erp_root_create,
diff --git a/include/linux/objagg.h b/include/linux/objagg.h
index 78021777df462..6df5b887dc547 100644
--- a/include/linux/objagg.h
+++ b/include/linux/objagg.h
@@ -8,7 +8,6 @@ struct objagg_ops {
 	size_t obj_size;
 	bool (*delta_check)(void *priv, const void *parent_obj,
 			    const void *obj);
-	int (*hints_obj_cmp)(const void *obj1, const void *obj2);
 	void * (*delta_create)(void *priv, void *parent_obj, void *obj);
 	void (*delta_destroy)(void *priv, void *delta_priv);
 	void * (*root_create)(void *priv, void *obj, unsigned int root_id);
diff --git a/lib/objagg.c b/lib/objagg.c
index 0f99ea5f53717..363e43e849ac3 100644
--- a/lib/objagg.c
+++ b/lib/objagg.c
@@ -906,20 +906,6 @@ static const struct objagg_opt_algo *objagg_opt_algos[] = {
 	[OBJAGG_OPT_ALGO_SIMPLE_GREEDY] = &objagg_opt_simple_greedy,
 };
 
-static int objagg_hints_obj_cmp(struct rhashtable_compare_arg *arg,
-				const void *obj)
-{
-	struct rhashtable *ht = arg->ht;
-	struct objagg_hints *objagg_hints =
-			container_of(ht, struct objagg_hints, node_ht);
-	const struct objagg_ops *ops = objagg_hints->ops;
-	const char *ptr = obj;
-
-	ptr += ht->p.key_offset;
-	return ops->hints_obj_cmp ? ops->hints_obj_cmp(ptr, arg->key) :
-				    memcmp(ptr, arg->key, ht->p.key_len);
-}
-
 /**
  * objagg_hints_get - obtains hints instance
  * @objagg:		objagg instance
@@ -958,7 +944,6 @@ struct objagg_hints *objagg_hints_get(struct objagg *objagg,
 				offsetof(struct objagg_hints_node, obj);
 	objagg_hints->ht_params.head_offset =
 				offsetof(struct objagg_hints_node, ht_node);
-	objagg_hints->ht_params.obj_cmpfn = objagg_hints_obj_cmp;
 
 	err = rhashtable_init(&objagg_hints->node_ht, &objagg_hints->ht_params);
 	if (err)
-- 
GitLab


From 75d8d7a63065b18df9555dbaab0b42d4c6f20943 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 6 Jun 2024 16:49:43 +0200
Subject: [PATCH 906/950] mlxsw: spectrum_acl: Fix ACL scale regression and
 firmware errors

ACLs that reside in the algorithmic TCAM (A-TCAM) in Spectrum-2 and
newer ASICs can share the same mask if their masks only differ in up to
8 consecutive bits. For example, consider the following filters:

 # tc filter add dev swp1 ingress pref 1 proto ip flower dst_ip 192.0.2.0/24 action drop
 # tc filter add dev swp1 ingress pref 1 proto ip flower dst_ip 198.51.100.128/25 action drop

The second filter can use the same mask as the first (dst_ip/24) with a
delta of 1 bit.

However, the above only works because the two filters have different
values in the common unmasked part (dst_ip/24). When entries have the
same value in the common unmasked part they create undesired collisions
in the device since many entries now have the same key. This leads to
firmware errors such as [1] and to a reduced scale.

Fix by adjusting the hash table key to only include the value in the
common unmasked part. That is, without including the delta bits. That
way the driver will detect the collision during filter insertion and
spill the filter into the circuit TCAM (C-TCAM).

Add a test case that fails without the fix and adjust existing cases
that check C-TCAM spillage according to the above limitation.

[1]
mlxsw_spectrum2 0000:06:00.0: EMAD reg access failed (tid=3379b18a00003394,reg_id=3027(ptce3),type=write,status=8(resource not available))

Fixes: c22291f7cf45 ("mlxsw: spectrum: acl: Implement delta for ERP")
Reported-by: Alexander Zubkov <green@qrator.net>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Amit Cohen <amcohen@nvidia.com>
Tested-by: Alexander Zubkov <green@qrator.net>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../mellanox/mlxsw/spectrum_acl_atcam.c       | 18 +++---
 .../mlxsw/spectrum_acl_bloom_filter.c         |  2 +-
 .../mellanox/mlxsw/spectrum_acl_tcam.h        |  9 +--
 .../drivers/net/mlxsw/spectrum-2/tc_flower.sh | 55 +++++++++++++++++--
 4 files changed, 63 insertions(+), 21 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
index a7473e782b56f..07cb1e26ca3eb 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
@@ -391,7 +391,8 @@ mlxsw_sp_acl_atcam_region_entry_insert(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		return err;
 
-	lkey_id = aregion->ops->lkey_id_get(aregion, aentry->enc_key, erp_id);
+	lkey_id = aregion->ops->lkey_id_get(aregion, aentry->ht_key.enc_key,
+					    erp_id);
 	if (IS_ERR(lkey_id))
 		return PTR_ERR(lkey_id);
 	aentry->lkey_id = lkey_id;
@@ -399,7 +400,7 @@ mlxsw_sp_acl_atcam_region_entry_insert(struct mlxsw_sp *mlxsw_sp,
 	kvdl_index = mlxsw_afa_block_first_kvdl_index(rulei->act_block);
 	mlxsw_reg_ptce3_pack(ptce3_pl, true, MLXSW_REG_PTCE3_OP_WRITE_WRITE,
 			     priority, region->tcam_region_info,
-			     aentry->enc_key, erp_id,
+			     aentry->ht_key.enc_key, erp_id,
 			     aentry->delta_info.start,
 			     aentry->delta_info.mask,
 			     aentry->delta_info.value,
@@ -428,7 +429,7 @@ mlxsw_sp_acl_atcam_region_entry_remove(struct mlxsw_sp *mlxsw_sp,
 
 	mlxsw_reg_ptce3_pack(ptce3_pl, false, MLXSW_REG_PTCE3_OP_WRITE_WRITE, 0,
 			     region->tcam_region_info,
-			     aentry->enc_key, erp_id,
+			     aentry->ht_key.enc_key, erp_id,
 			     aentry->delta_info.start,
 			     aentry->delta_info.mask,
 			     aentry->delta_info.value,
@@ -457,7 +458,7 @@ mlxsw_sp_acl_atcam_region_entry_action_replace(struct mlxsw_sp *mlxsw_sp,
 	kvdl_index = mlxsw_afa_block_first_kvdl_index(rulei->act_block);
 	mlxsw_reg_ptce3_pack(ptce3_pl, true, MLXSW_REG_PTCE3_OP_WRITE_UPDATE,
 			     priority, region->tcam_region_info,
-			     aentry->enc_key, erp_id,
+			     aentry->ht_key.enc_key, erp_id,
 			     aentry->delta_info.start,
 			     aentry->delta_info.mask,
 			     aentry->delta_info.value,
@@ -480,15 +481,13 @@ __mlxsw_sp_acl_atcam_entry_add(struct mlxsw_sp *mlxsw_sp,
 	int err;
 
 	mlxsw_afk_encode(afk, region->key_info, &rulei->values,
-			 aentry->ht_key.full_enc_key, mask);
+			 aentry->ht_key.enc_key, mask);
 
 	erp_mask = mlxsw_sp_acl_erp_mask_get(aregion, mask, false);
 	if (IS_ERR(erp_mask))
 		return PTR_ERR(erp_mask);
 	aentry->erp_mask = erp_mask;
 	aentry->ht_key.erp_id = mlxsw_sp_acl_erp_mask_erp_id(erp_mask);
-	memcpy(aentry->enc_key, aentry->ht_key.full_enc_key,
-	       sizeof(aentry->enc_key));
 
 	/* Compute all needed delta information and clear the delta bits
 	 * from the encoded key.
@@ -497,9 +496,8 @@ __mlxsw_sp_acl_atcam_entry_add(struct mlxsw_sp *mlxsw_sp,
 	aentry->delta_info.start = mlxsw_sp_acl_erp_delta_start(delta);
 	aentry->delta_info.mask = mlxsw_sp_acl_erp_delta_mask(delta);
 	aentry->delta_info.value =
-		mlxsw_sp_acl_erp_delta_value(delta,
-					     aentry->ht_key.full_enc_key);
-	mlxsw_sp_acl_erp_delta_clear(delta, aentry->enc_key);
+		mlxsw_sp_acl_erp_delta_value(delta, aentry->ht_key.enc_key);
+	mlxsw_sp_acl_erp_delta_clear(delta, aentry->ht_key.enc_key);
 
 	/* Add rule to the list of A-TCAM rules, assuming this
 	 * rule is intended to A-TCAM. In case this rule does
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c
index 95f63fcf4ba1f..a54eedb69a3f5 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c
@@ -249,7 +249,7 @@ __mlxsw_sp_acl_bf_key_encode(struct mlxsw_sp_acl_atcam_region *aregion,
 		memcpy(chunk + pad_bytes, &erp_region_id,
 		       sizeof(erp_region_id));
 		memcpy(chunk + key_offset,
-		       &aentry->enc_key[chunk_key_offsets[chunk_index]],
+		       &aentry->ht_key.enc_key[chunk_key_offsets[chunk_index]],
 		       chunk_key_len);
 		chunk += chunk_len;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
index 79a1d86065125..010204f73ea46 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
@@ -167,9 +167,9 @@ struct mlxsw_sp_acl_atcam_region {
 };
 
 struct mlxsw_sp_acl_atcam_entry_ht_key {
-	char full_enc_key[MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN]; /* Encoded
-								 * key.
-								 */
+	char enc_key[MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN]; /* Encoded key, minus
+							    * delta bits.
+							    */
 	u8 erp_id;
 };
 
@@ -181,9 +181,6 @@ struct mlxsw_sp_acl_atcam_entry {
 	struct rhash_head ht_node;
 	struct list_head list; /* Member in entries_list */
 	struct mlxsw_sp_acl_atcam_entry_ht_key ht_key;
-	char enc_key[MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN]; /* Encoded key,
-							    * minus delta bits.
-							    */
 	struct {
 		u16 start;
 		u8 mask;
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh
index 31252bc8775e0..4994bea5daf80 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh
@@ -11,7 +11,7 @@ ALL_TESTS="single_mask_test identical_filters_test two_masks_test \
 	multiple_masks_test ctcam_edge_cases_test delta_simple_test \
 	delta_two_masks_one_key_test delta_simple_rehash_test \
 	bloom_simple_test bloom_complex_test bloom_delta_test \
-	max_erp_entries_test max_group_size_test"
+	max_erp_entries_test max_group_size_test collision_test"
 NUM_NETIFS=2
 source $lib_dir/lib.sh
 source $lib_dir/tc_common.sh
@@ -457,7 +457,7 @@ delta_two_masks_one_key_test()
 {
 	# If 2 keys are the same and only differ in mask in a way that
 	# they belong under the same ERP (second is delta of the first),
-	# there should be no C-TCAM spill.
+	# there should be C-TCAM spill.
 
 	RET=0
 
@@ -474,8 +474,8 @@ delta_two_masks_one_key_test()
 	tp_record "mlxsw:*" "tc filter add dev $h2 ingress protocol ip \
 		   pref 2 handle 102 flower $tcflags dst_ip 192.0.2.2 \
 		   action drop"
-	tp_check_hits "mlxsw:mlxsw_sp_acl_atcam_entry_add_ctcam_spill" 0
-	check_err $? "incorrect C-TCAM spill while inserting the second rule"
+	tp_check_hits "mlxsw:mlxsw_sp_acl_atcam_entry_add_ctcam_spill" 1
+	check_err $? "C-TCAM spill did not happen while inserting the second rule"
 
 	$MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
 		-t ip -q
@@ -1087,6 +1087,53 @@ max_group_size_test()
 	log_test "max ACL group size test ($tcflags). max size $max_size"
 }
 
+collision_test()
+{
+	# Filters cannot share an eRP if in the common unmasked part (i.e.,
+	# without the delta bits) they have the same values. If the driver does
+	# not prevent such configuration (by spilling into the C-TCAM), then
+	# multiple entries will be present in the device with the same key,
+	# leading to collisions and a reduced scale.
+	#
+	# Create such a scenario and make sure all the filters are successfully
+	# added.
+
+	RET=0
+
+	local ret
+
+	if [[ "$tcflags" != "skip_sw" ]]; then
+		return 0;
+	fi
+
+	# Add a single dst_ip/24 filter and multiple dst_ip/32 filters that all
+	# have the same values in the common unmasked part (dst_ip/24).
+
+	tc filter add dev $h2 ingress pref 1 proto ipv4 handle 101 \
+		flower $tcflags dst_ip 198.51.100.0/24 \
+		action drop
+
+	for i in {0..255}; do
+		tc filter add dev $h2 ingress pref 2 proto ipv4 \
+			handle $((102 + i)) \
+			flower $tcflags dst_ip 198.51.100.${i}/32 \
+			action drop
+		ret=$?
+		[[ $ret -ne 0 ]] && break
+	done
+
+	check_err $ret "failed to add all the filters"
+
+	for i in {255..0}; do
+		tc filter del dev $h2 ingress pref 2 proto ipv4 \
+			handle $((102 + i)) flower
+	done
+
+	tc filter del dev $h2 ingress pref 1 proto ipv4 handle 101 flower
+
+	log_test "collision test ($tcflags)"
+}
+
 setup_prepare()
 {
 	h1=${NETIFS[p1]}
-- 
GitLab


From b334b924c9b709bc969644fb5c406f5c9d01dceb Mon Sep 17 00:00:00 2001
From: Valentin Schneider <vschneid@redhat.com>
Date: Thu, 6 Jun 2024 17:11:37 +0200
Subject: [PATCH 907/950] net: tcp/dccp: prepare for tw_timer un-pinning

The TCP timewait timer is proving to be problematic for setups where
scheduler CPU isolation is achieved at runtime via cpusets (as opposed to
statically via isolcpus=domains).

What happens there is a CPU goes through tcp_time_wait(), arming the
time_wait timer, then gets isolated. TCP_TIMEWAIT_LEN later, the timer
fires, causing interference for the now-isolated CPU. This is conceptually
similar to the issue described in commit e02b93124855 ("workqueue: Unbind
kworkers before sending them to exit()")

Move inet_twsk_schedule() to within inet_twsk_hashdance(), with the ehash
lock held. Expand the lock's critical section from inet_twsk_kill() to
inet_twsk_deschedule_put(), serializing the scheduling vs descheduling of
the timer. IOW, this prevents the following race:

			     tcp_time_wait()
			       inet_twsk_hashdance()
  inet_twsk_deschedule_put()
    del_timer_sync()
			       inet_twsk_schedule()

Thanks to Paolo Abeni for suggesting to leverage the ehash lock.

This also restores a comment from commit ec94c2696f0b ("tcp/dccp: avoid
one atomic operation for timewait hashdance") as inet_twsk_hashdance() had
a "Step 1" and "Step 3" comment, but the "Step 2" had gone missing.

inet_twsk_deschedule_put() now acquires the ehash spinlock to synchronize
with inet_twsk_hashdance_schedule().

To ease possible regression search, actual un-pin is done in next patch.

Link: https://lore.kernel.org/all/ZPhpfMjSiHVjQkTk@localhost.localdomain/
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Valentin Schneider <vschneid@redhat.com>
Co-developed-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_timewait_sock.h |  6 ++--
 net/dccp/minisocks.c             |  3 +-
 net/ipv4/inet_timewait_sock.c    | 52 +++++++++++++++++++++++++++-----
 net/ipv4/tcp_ipv4.c              |  2 +-
 net/ipv4/tcp_minisocks.c         |  3 +-
 5 files changed, 52 insertions(+), 14 deletions(-)

diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h
index 2a536eea9424e..5b43d220243de 100644
--- a/include/net/inet_timewait_sock.h
+++ b/include/net/inet_timewait_sock.h
@@ -93,8 +93,10 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk,
 					   struct inet_timewait_death_row *dr,
 					   const int state);
 
-void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
-			 struct inet_hashinfo *hashinfo);
+void inet_twsk_hashdance_schedule(struct inet_timewait_sock *tw,
+				  struct sock *sk,
+				  struct inet_hashinfo *hashinfo,
+				  int timeo);
 
 void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo,
 			  bool rearm);
diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c
index 251a57cf58223..deb52d7d31b48 100644
--- a/net/dccp/minisocks.c
+++ b/net/dccp/minisocks.c
@@ -59,11 +59,10 @@ void dccp_time_wait(struct sock *sk, int state, int timeo)
 		 * we complete the initialization.
 		 */
 		local_bh_disable();
-		inet_twsk_schedule(tw, timeo);
 		/* Linkage updates.
 		 * Note that access to tw after this point is illegal.
 		 */
-		inet_twsk_hashdance(tw, sk, &dccp_hashinfo);
+		inet_twsk_hashdance_schedule(tw, sk, &dccp_hashinfo, timeo);
 		local_bh_enable();
 	} else {
 		/* Sorry, if we're out of memory, just CLOSE this
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index e28075f0006e3..628d33a41ce5f 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -96,9 +96,13 @@ static void inet_twsk_add_node_rcu(struct inet_timewait_sock *tw,
  * Enter the time wait state. This is called with locally disabled BH.
  * Essentially we whip up a timewait bucket, copy the relevant info into it
  * from the SK, and mess with hash chains and list linkage.
+ *
+ * The caller must not access @tw anymore after this function returns.
  */
-void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
-			   struct inet_hashinfo *hashinfo)
+void inet_twsk_hashdance_schedule(struct inet_timewait_sock *tw,
+				  struct sock *sk,
+				  struct inet_hashinfo *hashinfo,
+				  int timeo)
 {
 	const struct inet_sock *inet = inet_sk(sk);
 	const struct inet_connection_sock *icsk = inet_csk(sk);
@@ -129,26 +133,33 @@ void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
 
 	spin_lock(lock);
 
+	/* Step 2: Hash TW into tcp ehash chain */
 	inet_twsk_add_node_rcu(tw, &ehead->chain);
 
 	/* Step 3: Remove SK from hash chain */
 	if (__sk_nulls_del_node_init_rcu(sk))
 		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
 
-	spin_unlock(lock);
 
+	/* Ensure above writes are committed into memory before updating the
+	 * refcount.
+	 * Provides ordering vs later refcount_inc().
+	 */
+	smp_wmb();
 	/* tw_refcnt is set to 3 because we have :
 	 * - one reference for bhash chain.
 	 * - one reference for ehash chain.
 	 * - one reference for timer.
-	 * We can use atomic_set() because prior spin_lock()/spin_unlock()
-	 * committed into memory all tw fields.
 	 * Also note that after this point, we lost our implicit reference
 	 * so we are not allowed to use tw anymore.
 	 */
 	refcount_set(&tw->tw_refcnt, 3);
+
+	inet_twsk_schedule(tw, timeo);
+
+	spin_unlock(lock);
 }
-EXPORT_SYMBOL_GPL(inet_twsk_hashdance);
+EXPORT_SYMBOL_GPL(inet_twsk_hashdance_schedule);
 
 static void tw_timer_handler(struct timer_list *t)
 {
@@ -217,7 +228,34 @@ EXPORT_SYMBOL_GPL(inet_twsk_alloc);
  */
 void inet_twsk_deschedule_put(struct inet_timewait_sock *tw)
 {
-	if (del_timer_sync(&tw->tw_timer))
+	struct inet_hashinfo *hashinfo = tw->tw_dr->hashinfo;
+	spinlock_t *lock = inet_ehash_lockp(hashinfo, tw->tw_hash);
+
+	/* inet_twsk_purge() walks over all sockets, including tw ones,
+	 * and removes them via inet_twsk_deschedule_put() after a
+	 * refcount_inc_not_zero().
+	 *
+	 * inet_twsk_hashdance_schedule() must (re)init the refcount before
+	 * arming the timer, i.e. inet_twsk_purge can obtain a reference to
+	 * a twsk that did not yet schedule the timer.
+	 *
+	 * The ehash lock synchronizes these two:
+	 * After acquiring the lock, the timer is always scheduled (else
+	 * timer_shutdown returns false), because hashdance_schedule releases
+	 * the ehash lock only after completing the timer initialization.
+	 *
+	 * Without grabbing the ehash lock, we get:
+	 * 1) cpu x sets twsk refcount to 3
+	 * 2) cpu y bumps refcount to 4
+	 * 3) cpu y calls inet_twsk_deschedule_put() and shuts timer down
+	 * 4) cpu x tries to start timer, but mod_timer is a noop post-shutdown
+	 * -> timer refcount is never decremented.
+	 */
+	spin_lock(lock);
+	/*  Makes sure hashdance_schedule() has completed */
+	spin_unlock(lock);
+
+	if (timer_shutdown_sync(&tw->tw_timer))
 		inet_twsk_kill(tw);
 	inet_twsk_put(tw);
 }
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 3613e08ca7949..e61c7c9747454 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -157,7 +157,7 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
 	if (ts_recent_stamp &&
 	    (!twp || (reuse && time_after32(ktime_get_seconds(),
 					    ts_recent_stamp)))) {
-		/* inet_twsk_hashdance() sets sk_refcnt after putting twsk
+		/* inet_twsk_hashdance_schedule() sets sk_refcnt after putting twsk
 		 * and releasing the bucket lock.
 		 */
 		if (unlikely(!refcount_inc_not_zero(&sktw->sk_refcnt)))
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 4c894e540730a..fc9a850ed9bd8 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -350,11 +350,10 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 		 * we complete the initialization.
 		 */
 		local_bh_disable();
-		inet_twsk_schedule(tw, timeo);
 		/* Linkage updates.
 		 * Note that access to tw after this point is illegal.
 		 */
-		inet_twsk_hashdance(tw, sk, net->ipv4.tcp_death_row.hashinfo);
+		inet_twsk_hashdance_schedule(tw, sk, net->ipv4.tcp_death_row.hashinfo, timeo);
 		local_bh_enable();
 	} else {
 		/* Sorry, if we're out of memory, just CLOSE this
-- 
GitLab


From c75ad7c759ccead1be462d4cec42bd4ad3578989 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Thu, 6 Jun 2024 17:11:38 +0200
Subject: [PATCH 908/950] net: tcp: un-pin the tw_timer

After previous patch, even if timer fires immediately on another CPU,
context that schedules the timer now holds the ehash spinlock, so timer
cannot reap tw socket until ehash lock is released.

BH disable is moved into hashdance_schedule.

Signed-off-by: Florian Westphal <fw@strlen.de>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/minisocks.c          | 6 ------
 net/ipv4/inet_timewait_sock.c | 6 ++++--
 net/ipv4/tcp_minisocks.c      | 6 ------
 3 files changed, 4 insertions(+), 14 deletions(-)

diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c
index deb52d7d31b48..fecc8190064f8 100644
--- a/net/dccp/minisocks.c
+++ b/net/dccp/minisocks.c
@@ -54,16 +54,10 @@ void dccp_time_wait(struct sock *sk, int state, int timeo)
 		if (state == DCCP_TIME_WAIT)
 			timeo = DCCP_TIMEWAIT_LEN;
 
-		/* tw_timer is pinned, so we need to make sure BH are disabled
-		 * in following section, otherwise timer handler could run before
-		 * we complete the initialization.
-		 */
-		local_bh_disable();
 		/* Linkage updates.
 		 * Note that access to tw after this point is illegal.
 		 */
 		inet_twsk_hashdance_schedule(tw, sk, &dccp_hashinfo, timeo);
-		local_bh_enable();
 	} else {
 		/* Sorry, if we're out of memory, just CLOSE this
 		 * socket up.  We've got bigger problems than
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index 628d33a41ce5f..b2d97c816c990 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -93,7 +93,7 @@ static void inet_twsk_add_node_rcu(struct inet_timewait_sock *tw,
 }
 
 /*
- * Enter the time wait state. This is called with locally disabled BH.
+ * Enter the time wait state.
  * Essentially we whip up a timewait bucket, copy the relevant info into it
  * from the SK, and mess with hash chains and list linkage.
  *
@@ -118,6 +118,7 @@ void inet_twsk_hashdance_schedule(struct inet_timewait_sock *tw,
 			hashinfo->bhash_size)];
 	bhead2 = inet_bhashfn_portaddr(hashinfo, sk, twsk_net(tw), inet->inet_num);
 
+	local_bh_disable();
 	spin_lock(&bhead->lock);
 	spin_lock(&bhead2->lock);
 
@@ -158,6 +159,7 @@ void inet_twsk_hashdance_schedule(struct inet_timewait_sock *tw,
 	inet_twsk_schedule(tw, timeo);
 
 	spin_unlock(lock);
+	local_bh_enable();
 }
 EXPORT_SYMBOL_GPL(inet_twsk_hashdance_schedule);
 
@@ -203,7 +205,7 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk,
 		tw->tw_prot	    = sk->sk_prot_creator;
 		atomic64_set(&tw->tw_cookie, atomic64_read(&sk->sk_cookie));
 		twsk_net_set(tw, sock_net(sk));
-		timer_setup(&tw->tw_timer, tw_timer_handler, TIMER_PINNED);
+		timer_setup(&tw->tw_timer, tw_timer_handler, 0);
 		/*
 		 * Because we use RCU lookups, we should not set tw_refcnt
 		 * to a non null value before everything is setup for this
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index fc9a850ed9bd8..bc67f6b9efae4 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -345,16 +345,10 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 		if (state == TCP_TIME_WAIT)
 			timeo = TCP_TIMEWAIT_LEN;
 
-		/* tw_timer is pinned, so we need to make sure BH are disabled
-		 * in following section, otherwise timer handler could run before
-		 * we complete the initialization.
-		 */
-		local_bh_disable();
 		/* Linkage updates.
 		 * Note that access to tw after this point is illegal.
 		 */
 		inet_twsk_hashdance_schedule(tw, sk, net->ipv4.tcp_death_row.hashinfo, timeo);
-		local_bh_enable();
 	} else {
 		/* Sorry, if we're out of memory, just CLOSE this
 		 * socket up.  We've got bigger problems than
-- 
GitLab


From f81d0dd2fde35fd1acc30b3f4de6aaf57d514551 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Thu, 6 Jun 2024 17:11:39 +0200
Subject: [PATCH 909/950] tcp: move inet_twsk_schedule helper out of header

Its no longer used outside inet_timewait_sock.c, so move it there.

Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_timewait_sock.h | 5 -----
 net/ipv4/inet_timewait_sock.c    | 5 +++++
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h
index 5b43d220243de..f88b682690127 100644
--- a/include/net/inet_timewait_sock.h
+++ b/include/net/inet_timewait_sock.h
@@ -101,11 +101,6 @@ void inet_twsk_hashdance_schedule(struct inet_timewait_sock *tw,
 void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo,
 			  bool rearm);
 
-static inline void inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo)
-{
-	__inet_twsk_schedule(tw, timeo, false);
-}
-
 static inline void inet_twsk_reschedule(struct inet_timewait_sock *tw, int timeo)
 {
 	__inet_twsk_schedule(tw, timeo, true);
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index b2d97c816c990..337390ba85b40 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -92,6 +92,11 @@ static void inet_twsk_add_node_rcu(struct inet_timewait_sock *tw,
 	hlist_nulls_add_head_rcu(&tw->tw_node, list);
 }
 
+static void inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo)
+{
+	__inet_twsk_schedule(tw, timeo, false);
+}
+
 /*
  * Enter the time wait state.
  * Essentially we whip up a timewait bucket, copy the relevant info into it
-- 
GitLab


From c917b26e1686b99f18a3c9fbce508a7c264c6706 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Thu, 6 Jun 2024 19:15:49 +0300
Subject: [PATCH 910/950] net: dsa: hellcreek: Replace kernel.h with what is
 used

kernel.h is included solely for some other existing headers.
Include them directly and get rid of kernel.h.

While at it, sort headers alphabetically for easier maintenance.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Kurt Kanzenbach <kurt@linutronix.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/hirschmann/hellcreek.h | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/net/dsa/hirschmann/hellcreek.h b/drivers/net/dsa/hirschmann/hellcreek.h
index 6874cb9dc3614..9c2ed2ba79dac 100644
--- a/drivers/net/dsa/hirschmann/hellcreek.h
+++ b/drivers/net/dsa/hirschmann/hellcreek.h
@@ -12,14 +12,16 @@
 
 #include <linux/bitmap.h>
 #include <linux/bitops.h>
+#include <linux/container_of.h>
 #include <linux/device.h>
-#include <linux/kernel.h>
-#include <linux/mutex.h>
-#include <linux/workqueue.h>
 #include <linux/leds.h>
+#include <linux/mutex.h>
 #include <linux/platform_data/hirschmann-hellcreek.h>
 #include <linux/ptp_clock_kernel.h>
 #include <linux/timecounter.h>
+#include <linux/types.h>
+#include <linux/workqueue.h>
+
 #include <net/dsa.h>
 #include <net/pkt_sched.h>
 
-- 
GitLab


From 5380d64f8d766576ac5c0f627418b2d0e1d2641f Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 6 Jun 2024 12:29:05 -0700
Subject: [PATCH 911/950] rtnetlink: move rtnl_lock handling out of af_netlink

Now that we have an intermediate layer of code for handling
rtnl-level netlink dump quirks, we can move the rtnl_lock
taking there.

For dump handlers with RTNL_FLAG_DUMP_SPLIT_NLM_DONE we can
avoid taking rtnl_lock just to generate NLM_DONE, once again.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c     | 9 +++++++--
 net/netlink/af_netlink.c | 2 --
 2 files changed, 7 insertions(+), 4 deletions(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 4668d67180407..eabfc8290f5e2 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -6486,6 +6486,7 @@ static int rtnl_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 static int rtnl_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 {
+	const bool needs_lock = !(cb->flags & RTNL_FLAG_DUMP_UNLOCKED);
 	rtnl_dumpit_func dumpit = cb->data;
 	int err;
 
@@ -6495,7 +6496,11 @@ static int rtnl_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 	if (!dumpit)
 		return 0;
 
+	if (needs_lock)
+		rtnl_lock();
 	err = dumpit(skb, cb);
+	if (needs_lock)
+		rtnl_unlock();
 
 	/* Old dump handlers used to send NLM_DONE as in a separate recvmsg().
 	 * Some applications which parse netlink manually depend on this.
@@ -6515,7 +6520,8 @@ static int rtnetlink_dump_start(struct sock *ssk, struct sk_buff *skb,
 				const struct nlmsghdr *nlh,
 				struct netlink_dump_control *control)
 {
-	if (control->flags & RTNL_FLAG_DUMP_SPLIT_NLM_DONE) {
+	if (control->flags & RTNL_FLAG_DUMP_SPLIT_NLM_DONE ||
+	    !(control->flags & RTNL_FLAG_DUMP_UNLOCKED)) {
 		WARN_ON(control->data);
 		control->data = control->dump;
 		control->dump = rtnl_dumpit;
@@ -6703,7 +6709,6 @@ static int __net_init rtnetlink_net_init(struct net *net)
 	struct netlink_kernel_cfg cfg = {
 		.groups		= RTNLGRP_MAX,
 		.input		= rtnetlink_rcv,
-		.cb_mutex	= &rtnl_mutex,
 		.flags		= NL_CFG_F_NONROOT_RECV,
 		.bind		= rtnetlink_bind,
 	};
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index fa9c090cf629e..8bbbe75e75dbe 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2330,8 +2330,6 @@ static int netlink_dump(struct sock *sk, bool lock_taken)
 
 		cb->extack = &extack;
 
-		if (cb->flags & RTNL_FLAG_DUMP_UNLOCKED)
-			extra_mutex = NULL;
 		if (extra_mutex)
 			mutex_lock(extra_mutex);
 		nlk->dump_done_errno = cb->dump(skb, cb);
-- 
GitLab


From 5fbf57a937f418fe204f9dbb7735e91984f4ee6a Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 6 Jun 2024 12:29:06 -0700
Subject: [PATCH 912/950] net: netlink: remove the cb_mutex "injection" from
 netlink core

Back in 2007, in commit af65bdfce98d ("[NETLINK]: Switch cb_lock spinlock
to mutex and allow to override it") netlink core was extended to allow
subsystems to replace the dump mutex lock with its own lock.

The mechanism was used by rtnetlink to take rtnl_lock but it isn't
sufficiently flexible for other users. Over the 17 years since
it was added no other user appeared. Since rtnetlink needs conditional
locking now, and doesn't use it either, axe this feature complete.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netlink.h  |  1 -
 net/netlink/af_netlink.c | 18 +++---------------
 2 files changed, 3 insertions(+), 16 deletions(-)

diff --git a/include/linux/netlink.h b/include/linux/netlink.h
index 5df7340d4dabc..b332c2048c755 100644
--- a/include/linux/netlink.h
+++ b/include/linux/netlink.h
@@ -47,7 +47,6 @@ struct netlink_kernel_cfg {
 	unsigned int	groups;
 	unsigned int	flags;
 	void		(*input)(struct sk_buff *skb);
-	struct mutex	*cb_mutex;
 	int		(*bind)(struct net *net, int group);
 	void		(*unbind)(struct net *net, int group);
 	void            (*release) (struct sock *sk, unsigned long *groups);
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 8bbbe75e75dbe..0b7a89db3ab74 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -636,8 +636,7 @@ static struct proto netlink_proto = {
 };
 
 static int __netlink_create(struct net *net, struct socket *sock,
-			    struct mutex *dump_cb_mutex, int protocol,
-			    int kern)
+			    int protocol, int kern)
 {
 	struct sock *sk;
 	struct netlink_sock *nlk;
@@ -655,7 +654,6 @@ static int __netlink_create(struct net *net, struct socket *sock,
 	lockdep_set_class_and_name(&nlk->nl_cb_mutex,
 					   nlk_cb_mutex_keys + protocol,
 					   nlk_cb_mutex_key_strings[protocol]);
-	nlk->dump_cb_mutex = dump_cb_mutex;
 	init_waitqueue_head(&nlk->wait);
 
 	sk->sk_destruct = netlink_sock_destruct;
@@ -667,7 +665,6 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol,
 			  int kern)
 {
 	struct module *module = NULL;
-	struct mutex *cb_mutex;
 	struct netlink_sock *nlk;
 	int (*bind)(struct net *net, int group);
 	void (*unbind)(struct net *net, int group);
@@ -696,7 +693,6 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol,
 		module = nl_table[protocol].module;
 	else
 		err = -EPROTONOSUPPORT;
-	cb_mutex = nl_table[protocol].cb_mutex;
 	bind = nl_table[protocol].bind;
 	unbind = nl_table[protocol].unbind;
 	release = nl_table[protocol].release;
@@ -705,7 +701,7 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol,
 	if (err < 0)
 		goto out;
 
-	err = __netlink_create(net, sock, cb_mutex, protocol, kern);
+	err = __netlink_create(net, sock, protocol, kern);
 	if (err < 0)
 		goto out_module;
 
@@ -2016,7 +2012,6 @@ __netlink_kernel_create(struct net *net, int unit, struct module *module,
 	struct sock *sk;
 	struct netlink_sock *nlk;
 	struct listeners *listeners = NULL;
-	struct mutex *cb_mutex = cfg ? cfg->cb_mutex : NULL;
 	unsigned int groups;
 
 	BUG_ON(!nl_table);
@@ -2027,7 +2022,7 @@ __netlink_kernel_create(struct net *net, int unit, struct module *module,
 	if (sock_create_lite(PF_NETLINK, SOCK_DGRAM, unit, &sock))
 		return NULL;
 
-	if (__netlink_create(net, sock, cb_mutex, unit, 1) < 0)
+	if (__netlink_create(net, sock, unit, 1) < 0)
 		goto out_sock_release_nosk;
 
 	sk = sock->sk;
@@ -2055,7 +2050,6 @@ __netlink_kernel_create(struct net *net, int unit, struct module *module,
 	if (!nl_table[unit].registered) {
 		nl_table[unit].groups = groups;
 		rcu_assign_pointer(nl_table[unit].listeners, listeners);
-		nl_table[unit].cb_mutex = cb_mutex;
 		nl_table[unit].module = module;
 		if (cfg) {
 			nl_table[unit].bind = cfg->bind;
@@ -2326,15 +2320,9 @@ static int netlink_dump(struct sock *sk, bool lock_taken)
 	netlink_skb_set_owner_r(skb, sk);
 
 	if (nlk->dump_done_errno > 0) {
-		struct mutex *extra_mutex = nlk->dump_cb_mutex;
-
 		cb->extack = &extack;
 
-		if (extra_mutex)
-			mutex_lock(extra_mutex);
 		nlk->dump_done_errno = cb->dump(skb, cb);
-		if (extra_mutex)
-			mutex_unlock(extra_mutex);
 
 		/* EMSGSIZE plus something already in the skb means
 		 * that there's more to dump but current skb has filled up.
-- 
GitLab


From 77f7541248fcfcc79afff68ff9acf1f09ab8e1e4 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Marek=20Beh=C3=BAn?= <kabel@kernel.org>
Date: Wed, 5 Jun 2024 15:33:28 +0200
Subject: [PATCH 913/950] net: dsa: deduplicate code adding / deleting the port
 address to fdb
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The sequence
  if (dsa_switch_supports_uc_filtering(ds))
    dsa_port_standalone_host_fdb_add(dp, addr, 0);
  if (!ether_addr_equal(addr, conduit->dev_addr))
    dev_uc_add(conduit, addr);
is executed both in dsa_user_open() and dsa_user_set_mac_addr().

Its reverse is executed both in dsa_user_close() and
dsa_user_set_mac_addr().

Refactor these sequences into new functions dsa_user_host_uc_install()
and dsa_user_host_uc_uninstall().

Signed-off-by: Marek Behún <kabel@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/user.c | 91 ++++++++++++++++++++++++++------------------------
 1 file changed, 47 insertions(+), 44 deletions(-)

diff --git a/net/dsa/user.c b/net/dsa/user.c
index 867c5fe9a4daf..efbb34c711cb9 100644
--- a/net/dsa/user.c
+++ b/net/dsa/user.c
@@ -355,60 +355,82 @@ static int dsa_user_get_iflink(const struct net_device *dev)
 	return READ_ONCE(dsa_user_to_conduit(dev)->ifindex);
 }
 
-static int dsa_user_open(struct net_device *dev)
+static int dsa_user_host_uc_install(struct net_device *dev, const u8 *addr)
 {
 	struct net_device *conduit = dsa_user_to_conduit(dev);
 	struct dsa_port *dp = dsa_user_to_port(dev);
 	struct dsa_switch *ds = dp->ds;
 	int err;
 
-	err = dev_open(conduit, NULL);
-	if (err < 0) {
-		netdev_err(dev, "failed to open conduit %s\n", conduit->name);
-		goto out;
-	}
-
 	if (dsa_switch_supports_uc_filtering(ds)) {
-		err = dsa_port_standalone_host_fdb_add(dp, dev->dev_addr, 0);
+		err = dsa_port_standalone_host_fdb_add(dp, addr, 0);
 		if (err)
 			goto out;
 	}
 
-	if (!ether_addr_equal(dev->dev_addr, conduit->dev_addr)) {
-		err = dev_uc_add(conduit, dev->dev_addr);
+	if (!ether_addr_equal(addr, conduit->dev_addr)) {
+		err = dev_uc_add(conduit, addr);
 		if (err < 0)
 			goto del_host_addr;
 	}
 
-	err = dsa_port_enable_rt(dp, dev->phydev);
-	if (err)
-		goto del_unicast;
-
 	return 0;
 
-del_unicast:
-	if (!ether_addr_equal(dev->dev_addr, conduit->dev_addr))
-		dev_uc_del(conduit, dev->dev_addr);
 del_host_addr:
 	if (dsa_switch_supports_uc_filtering(ds))
-		dsa_port_standalone_host_fdb_del(dp, dev->dev_addr, 0);
+		dsa_port_standalone_host_fdb_del(dp, addr, 0);
 out:
 	return err;
 }
 
-static int dsa_user_close(struct net_device *dev)
+static void dsa_user_host_uc_uninstall(struct net_device *dev)
 {
 	struct net_device *conduit = dsa_user_to_conduit(dev);
 	struct dsa_port *dp = dsa_user_to_port(dev);
 	struct dsa_switch *ds = dp->ds;
 
-	dsa_port_disable_rt(dp);
-
 	if (!ether_addr_equal(dev->dev_addr, conduit->dev_addr))
 		dev_uc_del(conduit, dev->dev_addr);
 
 	if (dsa_switch_supports_uc_filtering(ds))
 		dsa_port_standalone_host_fdb_del(dp, dev->dev_addr, 0);
+}
+
+static int dsa_user_open(struct net_device *dev)
+{
+	struct net_device *conduit = dsa_user_to_conduit(dev);
+	struct dsa_port *dp = dsa_user_to_port(dev);
+	int err;
+
+	err = dev_open(conduit, NULL);
+	if (err < 0) {
+		netdev_err(dev, "failed to open conduit %s\n", conduit->name);
+		goto out;
+	}
+
+	err = dsa_user_host_uc_install(dev, dev->dev_addr);
+	if (err)
+		goto out;
+
+	err = dsa_port_enable_rt(dp, dev->phydev);
+	if (err)
+		goto out_del_host_uc;
+
+	return 0;
+
+out_del_host_uc:
+	dsa_user_host_uc_uninstall(dev);
+out:
+	return err;
+}
+
+static int dsa_user_close(struct net_device *dev)
+{
+	struct dsa_port *dp = dsa_user_to_port(dev);
+
+	dsa_port_disable_rt(dp);
+
+	dsa_user_host_uc_uninstall(dev);
 
 	return 0;
 }
@@ -448,7 +470,6 @@ static void dsa_user_set_rx_mode(struct net_device *dev)
 
 static int dsa_user_set_mac_address(struct net_device *dev, void *a)
 {
-	struct net_device *conduit = dsa_user_to_conduit(dev);
 	struct dsa_port *dp = dsa_user_to_port(dev);
 	struct dsa_switch *ds = dp->ds;
 	struct sockaddr *addr = a;
@@ -470,34 +491,16 @@ static int dsa_user_set_mac_address(struct net_device *dev, void *a)
 	if (!(dev->flags & IFF_UP))
 		goto out_change_dev_addr;
 
-	if (dsa_switch_supports_uc_filtering(ds)) {
-		err = dsa_port_standalone_host_fdb_add(dp, addr->sa_data, 0);
-		if (err)
-			return err;
-	}
-
-	if (!ether_addr_equal(addr->sa_data, conduit->dev_addr)) {
-		err = dev_uc_add(conduit, addr->sa_data);
-		if (err < 0)
-			goto del_unicast;
-	}
-
-	if (!ether_addr_equal(dev->dev_addr, conduit->dev_addr))
-		dev_uc_del(conduit, dev->dev_addr);
+	err = dsa_user_host_uc_install(dev, addr->sa_data);
+	if (err)
+		return err;
 
-	if (dsa_switch_supports_uc_filtering(ds))
-		dsa_port_standalone_host_fdb_del(dp, dev->dev_addr, 0);
+	dsa_user_host_uc_uninstall(dev);
 
 out_change_dev_addr:
 	eth_hw_addr_set(dev, addr->sa_data);
 
 	return 0;
-
-del_unicast:
-	if (dsa_switch_supports_uc_filtering(ds))
-		dsa_port_standalone_host_fdb_del(dp, addr->sa_data, 0);
-
-	return err;
 }
 
 struct dsa_user_dump_ctx {
-- 
GitLab


From eef8e906aea270f4b8912a0b51403b80aec54d30 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Marek=20Beh=C3=BAn?= <kabel@kernel.org>
Date: Wed, 5 Jun 2024 15:33:29 +0200
Subject: [PATCH 914/950] net: dsa: update the unicast MAC address when
 changing conduit
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When changing DSA user interface conduit while the user interface is up,
DSA exhibits different behavior in comparison to when the interface is
down. This different behavior concerns the primary unicast MAC address
stored in the port standalone FDB and in the conduit device UC database.

If we put a switch port down while changing the conduit with
  ip link set sw0p0 down
  ip link set sw0p0 type dsa conduit conduit1
  ip link set sw0p0 up
we delete the address in dsa_user_close() and install the (possibly
different) address in dsa_user_open().

But when changing the conduit on the fly, the old address is not
deleted and the new one is not installed.

Since we explicitly want to support live-changing the conduit, uninstall
the old address before calling dsa_port_assign_conduit() and install the
(possibly different) new address after the call.

Because conduit change might also trigger address change (the user
interface is supposed to inherit the conduit interface MAC address if no
address is defined in hardware (dp->mac is a zero address)), move the
eth_hw_addr_inherit() call from dsa_user_change_conduit() to
dsa_port_change_conduit(), just before installing the new address.

Although this is in theory a flaw in DSA core, it needs not be
backported, since there is currently no DSA driver that can be affected
by this. The only DSA driver that supports changing conduit is felix,
and, as explained by Vladimir Oltean [1]:

  There are 2 reasons why with felix the bug does not manifest itself.

  First is because both the 'ocelot' and the alternate 'ocelot-8021q'
  tagging protocols have the 'promisc_on_conduit = true' flag. So the
  unicast address doesn't have to be in the conduit's RX filter -
  neither the old or the new conduit.

  Second, dsa_user_host_uc_install() theoretically leaves behind host
  FDB entries installed towards the wrong (old) CPU port. But in
  felix_fdb_add(), we treat any FDB entry requested towards any CPU port
  as if it was a multicast FDB entry programmed towards _all_ CPU ports.
  For that reason, it is installed towards the port mask of the PGID_CPU
  port group ID:

	if (dsa_port_is_cpu(dp))
		port = PGID_CPU;

Therefore no Fixes tag for this change.

[1] https://lore.kernel.org/netdev/20240507201827.47suw4fwcjrbungy@skbuf/
Signed-off-by: Marek Behún <kabel@kernel.org>
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Tested-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/port.c | 40 ++++++++++++++++++++++++++++++++++++++++
 net/dsa/user.c | 10 ++--------
 net/dsa/user.h |  2 ++
 3 files changed, 44 insertions(+), 8 deletions(-)

diff --git a/net/dsa/port.c b/net/dsa/port.c
index e23db9507546b..25258b33e59e0 100644
--- a/net/dsa/port.c
+++ b/net/dsa/port.c
@@ -1467,10 +1467,34 @@ int dsa_port_change_conduit(struct dsa_port *dp, struct net_device *conduit,
 	 */
 	dsa_user_unsync_ha(dev);
 
+	/* If live-changing, we also need to uninstall the user device address
+	 * from the port FDB and the conduit interface.
+	 */
+	if (dev->flags & IFF_UP)
+		dsa_user_host_uc_uninstall(dev);
+
 	err = dsa_port_assign_conduit(dp, conduit, extack, true);
 	if (err)
 		goto rewind_old_addrs;
 
+	/* If the port doesn't have its own MAC address and relies on the DSA
+	 * conduit's one, inherit it again from the new DSA conduit.
+	 */
+	if (is_zero_ether_addr(dp->mac))
+		eth_hw_addr_inherit(dev, conduit);
+
+	/* If live-changing, we need to install the user device address to the
+	 * port FDB and the conduit interface.
+	 */
+	if (dev->flags & IFF_UP) {
+		err = dsa_user_host_uc_install(dev, dev->dev_addr);
+		if (err) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Failed to install host UC address");
+			goto rewind_addr_inherit;
+		}
+	}
+
 	dsa_user_sync_ha(dev);
 
 	if (vlan_filtering) {
@@ -1500,10 +1524,26 @@ rewind_new_vlan:
 rewind_new_addrs:
 	dsa_user_unsync_ha(dev);
 
+	if (dev->flags & IFF_UP)
+		dsa_user_host_uc_uninstall(dev);
+
+rewind_addr_inherit:
+	if (is_zero_ether_addr(dp->mac))
+		eth_hw_addr_inherit(dev, old_conduit);
+
 	dsa_port_assign_conduit(dp, old_conduit, NULL, false);
 
 /* Restore the objects on the old CPU port */
 rewind_old_addrs:
+	if (dev->flags & IFF_UP) {
+		tmp = dsa_user_host_uc_install(dev, dev->dev_addr);
+		if (tmp) {
+			dev_err(ds->dev,
+				"port %d failed to restore host UC address: %pe\n",
+				dp->index, ERR_PTR(tmp));
+		}
+	}
+
 	dsa_user_sync_ha(dev);
 
 	if (vlan_filtering) {
diff --git a/net/dsa/user.c b/net/dsa/user.c
index efbb34c711cb9..e8f56a40b6141 100644
--- a/net/dsa/user.c
+++ b/net/dsa/user.c
@@ -355,7 +355,7 @@ static int dsa_user_get_iflink(const struct net_device *dev)
 	return READ_ONCE(dsa_user_to_conduit(dev)->ifindex);
 }
 
-static int dsa_user_host_uc_install(struct net_device *dev, const u8 *addr)
+int dsa_user_host_uc_install(struct net_device *dev, const u8 *addr)
 {
 	struct net_device *conduit = dsa_user_to_conduit(dev);
 	struct dsa_port *dp = dsa_user_to_port(dev);
@@ -383,7 +383,7 @@ out:
 	return err;
 }
 
-static void dsa_user_host_uc_uninstall(struct net_device *dev)
+void dsa_user_host_uc_uninstall(struct net_device *dev)
 {
 	struct net_device *conduit = dsa_user_to_conduit(dev);
 	struct dsa_port *dp = dsa_user_to_port(dev);
@@ -2882,12 +2882,6 @@ int dsa_user_change_conduit(struct net_device *dev, struct net_device *conduit,
 			    ERR_PTR(err));
 	}
 
-	/* If the port doesn't have its own MAC address and relies on the DSA
-	 * conduit's one, inherit it again from the new DSA conduit.
-	 */
-	if (is_zero_ether_addr(dp->mac))
-		eth_hw_addr_inherit(dev, conduit);
-
 	return 0;
 
 out_revert_conduit_link:
diff --git a/net/dsa/user.h b/net/dsa/user.h
index 996069130beae..016884bead3cd 100644
--- a/net/dsa/user.h
+++ b/net/dsa/user.h
@@ -42,6 +42,8 @@ int dsa_user_suspend(struct net_device *user_dev);
 int dsa_user_resume(struct net_device *user_dev);
 int dsa_user_register_notifier(void);
 void dsa_user_unregister_notifier(void);
+int dsa_user_host_uc_install(struct net_device *dev, const u8 *addr);
+void dsa_user_host_uc_uninstall(struct net_device *dev);
 void dsa_user_sync_ha(struct net_device *dev);
 void dsa_user_unsync_ha(struct net_device *dev);
 void dsa_user_setup_tagger(struct net_device *user);
-- 
GitLab


From 2ebb87f45b3c6adc97b29291102ecb97274f913f Mon Sep 17 00:00:00 2001
From: Jeff Johnson <quic_jjohnson@quicinc.com>
Date: Fri, 7 Jun 2024 11:56:56 -0700
Subject: [PATCH 915/950] isdn: add missing MODULE_DESCRIPTION() macros

make allmodconfig && make W=1 C=1 reports:
WARNING: modpost: missing MODULE_DESCRIPTION() in drivers/isdn/hardware/mISDN/hfcpci.o
WARNING: modpost: missing MODULE_DESCRIPTION() in drivers/isdn/hardware/mISDN/hfcmulti.o
WARNING: modpost: missing MODULE_DESCRIPTION() in drivers/isdn/hardware/mISDN/hfcsusb.o
WARNING: modpost: missing MODULE_DESCRIPTION() in drivers/isdn/hardware/mISDN/avmfritz.o
WARNING: modpost: missing MODULE_DESCRIPTION() in drivers/isdn/hardware/mISDN/speedfax.o
WARNING: modpost: missing MODULE_DESCRIPTION() in drivers/isdn/hardware/mISDN/mISDNinfineon.o
WARNING: modpost: missing MODULE_DESCRIPTION() in drivers/isdn/hardware/mISDN/w6692.o
WARNING: modpost: missing MODULE_DESCRIPTION() in drivers/isdn/hardware/mISDN/netjet.o
WARNING: modpost: missing MODULE_DESCRIPTION() in drivers/isdn/hardware/mISDN/mISDNipac.o
WARNING: modpost: missing MODULE_DESCRIPTION() in drivers/isdn/hardware/mISDN/mISDNisar.o
WARNING: modpost: missing MODULE_DESCRIPTION() in drivers/isdn/mISDN/mISDN_core.o
WARNING: modpost: missing MODULE_DESCRIPTION() in drivers/isdn/mISDN/mISDN_dsp.o
WARNING: modpost: missing MODULE_DESCRIPTION() in drivers/isdn/mISDN/l1oip.o

Add the missing invocations of the MODULE_DESCRIPTION() macro.

Signed-off-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Link: https://lore.kernel.org/r/20240607-md-drivers-isdn-v1-1-81fb7001bc3a@quicinc.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/isdn/hardware/mISDN/avmfritz.c      | 1 +
 drivers/isdn/hardware/mISDN/hfcmulti.c      | 1 +
 drivers/isdn/hardware/mISDN/hfcpci.c        | 1 +
 drivers/isdn/hardware/mISDN/hfcsusb.c       | 1 +
 drivers/isdn/hardware/mISDN/mISDNinfineon.c | 1 +
 drivers/isdn/hardware/mISDN/mISDNipac.c     | 1 +
 drivers/isdn/hardware/mISDN/mISDNisar.c     | 1 +
 drivers/isdn/hardware/mISDN/netjet.c        | 1 +
 drivers/isdn/hardware/mISDN/speedfax.c      | 1 +
 drivers/isdn/hardware/mISDN/w6692.c         | 1 +
 drivers/isdn/mISDN/core.c                   | 1 +
 drivers/isdn/mISDN/dsp_core.c               | 1 +
 drivers/isdn/mISDN/l1oip_core.c             | 1 +
 13 files changed, 13 insertions(+)

diff --git a/drivers/isdn/hardware/mISDN/avmfritz.c b/drivers/isdn/hardware/mISDN/avmfritz.c
index f68569bfef7a7..509b362d6465d 100644
--- a/drivers/isdn/hardware/mISDN/avmfritz.c
+++ b/drivers/isdn/hardware/mISDN/avmfritz.c
@@ -159,6 +159,7 @@ set_debug(const char *val, const struct kernel_param *kp)
 }
 
 MODULE_AUTHOR("Karsten Keil");
+MODULE_DESCRIPTION("mISDN driver for AVM FRITZ!CARD PCI ISDN cards");
 MODULE_LICENSE("GPL v2");
 MODULE_VERSION(AVMFRITZ_REV);
 module_param_call(debug, set_debug, param_get_uint, &debug, S_IRUGO | S_IWUSR);
diff --git a/drivers/isdn/hardware/mISDN/hfcmulti.c b/drivers/isdn/hardware/mISDN/hfcmulti.c
index 2e5cb9dde3ec5..0d2928d8aeae8 100644
--- a/drivers/isdn/hardware/mISDN/hfcmulti.c
+++ b/drivers/isdn/hardware/mISDN/hfcmulti.c
@@ -221,6 +221,7 @@ static uint	hwid = HWID_NONE;
 static int	HFC_cnt, E1_cnt, bmask_cnt, Port_cnt, PCM_cnt = 99;
 
 MODULE_AUTHOR("Andreas Eversberg");
+MODULE_DESCRIPTION("mISDN driver for hfc-4s/hfc-8s/hfc-e1 based cards");
 MODULE_LICENSE("GPL");
 MODULE_VERSION(HFC_MULTI_VERSION);
 module_param(debug, uint, S_IRUGO | S_IWUSR);
diff --git a/drivers/isdn/hardware/mISDN/hfcpci.c b/drivers/isdn/hardware/mISDN/hfcpci.c
index fe391de1aba32..ce7bccc9faa39 100644
--- a/drivers/isdn/hardware/mISDN/hfcpci.c
+++ b/drivers/isdn/hardware/mISDN/hfcpci.c
@@ -48,6 +48,7 @@ static struct timer_list hfc_tl;
 static unsigned long hfc_jiffies;
 
 MODULE_AUTHOR("Karsten Keil");
+MODULE_DESCRIPTION("mISDN driver for CCD's hfc-pci based cards");
 MODULE_LICENSE("GPL");
 module_param(debug, uint, S_IRUGO | S_IWUSR);
 module_param(poll, uint, S_IRUGO | S_IWUSR);
diff --git a/drivers/isdn/hardware/mISDN/hfcsusb.c b/drivers/isdn/hardware/mISDN/hfcsusb.c
index b82b89888a5e0..e54419a4e731f 100644
--- a/drivers/isdn/hardware/mISDN/hfcsusb.c
+++ b/drivers/isdn/hardware/mISDN/hfcsusb.c
@@ -31,6 +31,7 @@ static DEFINE_RWLOCK(HFClock);
 
 
 MODULE_AUTHOR("Martin Bachem");
+MODULE_DESCRIPTION("mISDN driver for Colognechip HFC-S USB chip");
 MODULE_LICENSE("GPL");
 module_param(debug, uint, S_IRUGO | S_IWUSR);
 module_param(poll, int, 0);
diff --git a/drivers/isdn/hardware/mISDN/mISDNinfineon.c b/drivers/isdn/hardware/mISDN/mISDNinfineon.c
index 88d592bafdb02..30876a0127118 100644
--- a/drivers/isdn/hardware/mISDN/mISDNinfineon.c
+++ b/drivers/isdn/hardware/mISDN/mISDNinfineon.c
@@ -245,6 +245,7 @@ set_debug(const char *val, const struct kernel_param *kp)
 }
 
 MODULE_AUTHOR("Karsten Keil");
+MODULE_DESCRIPTION("mISDN driver for cards based on Infineon ISDN chipsets");
 MODULE_LICENSE("GPL v2");
 MODULE_VERSION(INFINEON_REV);
 module_param_call(debug, set_debug, param_get_uint, &debug, S_IRUGO | S_IWUSR);
diff --git a/drivers/isdn/hardware/mISDN/mISDNipac.c b/drivers/isdn/hardware/mISDN/mISDNipac.c
index 4f8d85bb3ce18..d0b7271fbda1a 100644
--- a/drivers/isdn/hardware/mISDN/mISDNipac.c
+++ b/drivers/isdn/hardware/mISDN/mISDNipac.c
@@ -21,6 +21,7 @@
 
 MODULE_AUTHOR("Karsten Keil");
 MODULE_VERSION(ISAC_REV);
+MODULE_DESCRIPTION("mISDN driver for ISAC specific functions");
 MODULE_LICENSE("GPL v2");
 
 #define ReadISAC(is, o)		(is->read_reg(is->dch.hw, o + is->off))
diff --git a/drivers/isdn/hardware/mISDN/mISDNisar.c b/drivers/isdn/hardware/mISDN/mISDNisar.c
index 48b3d43e25022..b3e03c4105448 100644
--- a/drivers/isdn/hardware/mISDN/mISDNisar.c
+++ b/drivers/isdn/hardware/mISDN/mISDNisar.c
@@ -22,6 +22,7 @@
 #define ISAR_REV	"2.1"
 
 MODULE_AUTHOR("Karsten Keil");
+MODULE_DESCRIPTION("mISDN driver for ISAR (Siemens PSB 7110) specific functions");
 MODULE_LICENSE("GPL v2");
 MODULE_VERSION(ISAR_REV);
 
diff --git a/drivers/isdn/hardware/mISDN/netjet.c b/drivers/isdn/hardware/mISDN/netjet.c
index 566c790a9481d..d163850c295e7 100644
--- a/drivers/isdn/hardware/mISDN/netjet.c
+++ b/drivers/isdn/hardware/mISDN/netjet.c
@@ -114,6 +114,7 @@ set_debug(const char *val, const struct kernel_param *kp)
 }
 
 MODULE_AUTHOR("Karsten Keil");
+MODULE_DESCRIPTION("mISDN driver for NETJet cards");
 MODULE_LICENSE("GPL v2");
 MODULE_VERSION(NETJET_REV);
 module_param_call(debug, set_debug, param_get_uint, &debug, S_IRUGO | S_IWUSR);
diff --git a/drivers/isdn/hardware/mISDN/speedfax.c b/drivers/isdn/hardware/mISDN/speedfax.c
index b530c78eca8ee..0c405261d9406 100644
--- a/drivers/isdn/hardware/mISDN/speedfax.c
+++ b/drivers/isdn/hardware/mISDN/speedfax.c
@@ -97,6 +97,7 @@ set_debug(const char *val, const struct kernel_param *kp)
 }
 
 MODULE_AUTHOR("Karsten Keil");
+MODULE_DESCRIPTION("mISDN driver for Sedlbauer Speedfax+ cards");
 MODULE_LICENSE("GPL v2");
 MODULE_VERSION(SPEEDFAX_REV);
 MODULE_FIRMWARE("isdn/ISAR.BIN");
diff --git a/drivers/isdn/hardware/mISDN/w6692.c b/drivers/isdn/hardware/mISDN/w6692.c
index f3b8db7b48fe0..ee69212ac351b 100644
--- a/drivers/isdn/hardware/mISDN/w6692.c
+++ b/drivers/isdn/hardware/mISDN/w6692.c
@@ -101,6 +101,7 @@ set_debug(const char *val, const struct kernel_param *kp)
 }
 
 MODULE_AUTHOR("Karsten Keil");
+MODULE_DESCRIPTION("mISDN driver for Winbond w6692 based cards");
 MODULE_LICENSE("GPL v2");
 MODULE_VERSION(W6692_REV);
 module_param_call(debug, set_debug, param_get_uint, &debug, S_IRUGO | S_IWUSR);
diff --git a/drivers/isdn/mISDN/core.c b/drivers/isdn/mISDN/core.c
index ab8513a7acd52..e34a7a46754e8 100644
--- a/drivers/isdn/mISDN/core.c
+++ b/drivers/isdn/mISDN/core.c
@@ -14,6 +14,7 @@
 static u_int debug;
 
 MODULE_AUTHOR("Karsten Keil");
+MODULE_DESCRIPTION("Modular ISDN core driver");
 MODULE_LICENSE("GPL");
 module_param(debug, uint, S_IRUGO | S_IWUSR);
 
diff --git a/drivers/isdn/mISDN/dsp_core.c b/drivers/isdn/mISDN/dsp_core.c
index fae95f1666883..753232e9fc36a 100644
--- a/drivers/isdn/mISDN/dsp_core.c
+++ b/drivers/isdn/mISDN/dsp_core.c
@@ -172,6 +172,7 @@ module_param(debug, uint, S_IRUGO | S_IWUSR);
 module_param(options, uint, S_IRUGO | S_IWUSR);
 module_param(poll, uint, S_IRUGO | S_IWUSR);
 module_param(dtmfthreshold, uint, S_IRUGO | S_IWUSR);
+MODULE_DESCRIPTION("mISDN driver for Digital Audio Processing of transparent data");
 MODULE_LICENSE("GPL");
 
 /*int spinnest = 0;*/
diff --git a/drivers/isdn/mISDN/l1oip_core.c b/drivers/isdn/mISDN/l1oip_core.c
index f010b35a05313..a5ad88a960d0e 100644
--- a/drivers/isdn/mISDN/l1oip_core.c
+++ b/drivers/isdn/mISDN/l1oip_core.c
@@ -245,6 +245,7 @@ static int debug;
 static int ulaw;
 
 MODULE_AUTHOR("Andreas Eversberg");
+MODULE_DESCRIPTION("mISDN driver for tunneling layer 1 over IP");
 MODULE_LICENSE("GPL");
 module_param_array(type, uint, NULL, S_IRUGO | S_IWUSR);
 module_param_array(codec, uint, NULL, S_IRUGO | S_IWUSR);
-- 
GitLab


From a2fe35df41c4cfce44f9f87d417cbd44a27b7362 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 7 Jun 2024 14:22:32 -0700
Subject: [PATCH 916/950] net: intel: Use *-y instead of *-objs in Makefile

*-objs suffix is reserved rather for (user-space) host programs while
usually *-y suffix is used for kernel drivers (although *-objs works
for that purpose for now).

Let's correct the old usages of *-objs in Makefiles.

Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Reviewed-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20240607-next-2024-06-03-intel-next-batch-v3-1-d1470cee3347@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/e1000/Makefile   | 2 +-
 drivers/net/ethernet/intel/e1000e/Makefile  | 7 +++----
 drivers/net/ethernet/intel/i40e/Makefile    | 2 +-
 drivers/net/ethernet/intel/iavf/Makefile    | 5 ++---
 drivers/net/ethernet/intel/igb/Makefile     | 6 +++---
 drivers/net/ethernet/intel/igbvf/Makefile   | 6 +-----
 drivers/net/ethernet/intel/igc/Makefile     | 6 +++---
 drivers/net/ethernet/intel/ixgbe/Makefile   | 8 ++++----
 drivers/net/ethernet/intel/ixgbevf/Makefile | 6 +-----
 drivers/net/ethernet/intel/libeth/Makefile  | 2 +-
 drivers/net/ethernet/intel/libie/Makefile   | 2 +-
 11 files changed, 21 insertions(+), 31 deletions(-)

diff --git a/drivers/net/ethernet/intel/e1000/Makefile b/drivers/net/ethernet/intel/e1000/Makefile
index 314c52d44b7c5..79491dec47e19 100644
--- a/drivers/net/ethernet/intel/e1000/Makefile
+++ b/drivers/net/ethernet/intel/e1000/Makefile
@@ -7,4 +7,4 @@
 
 obj-$(CONFIG_E1000) += e1000.o
 
-e1000-objs := e1000_main.o e1000_hw.o e1000_ethtool.o e1000_param.o
+e1000-y := e1000_main.o e1000_hw.o e1000_ethtool.o e1000_param.o
diff --git a/drivers/net/ethernet/intel/e1000e/Makefile b/drivers/net/ethernet/intel/e1000e/Makefile
index 0baa15503c381..18f22b6374d51 100644
--- a/drivers/net/ethernet/intel/e1000e/Makefile
+++ b/drivers/net/ethernet/intel/e1000e/Makefile
@@ -10,7 +10,6 @@ subdir-ccflags-y += -I$(src)
 
 obj-$(CONFIG_E1000E) += e1000e.o
 
-e1000e-objs := 82571.o ich8lan.o 80003es2lan.o \
-	       mac.o manage.o nvm.o phy.o \
-	       param.o ethtool.o netdev.o ptp.o
-
+e1000e-y := 82571.o ich8lan.o 80003es2lan.o \
+	    mac.o manage.o nvm.o phy.o \
+	    param.o ethtool.o netdev.o ptp.o
diff --git a/drivers/net/ethernet/intel/i40e/Makefile b/drivers/net/ethernet/intel/i40e/Makefile
index cad93f323bd52..9faa4339a76c3 100644
--- a/drivers/net/ethernet/intel/i40e/Makefile
+++ b/drivers/net/ethernet/intel/i40e/Makefile
@@ -10,7 +10,7 @@ subdir-ccflags-y += -I$(src)
 
 obj-$(CONFIG_I40E) += i40e.o
 
-i40e-objs := i40e_main.o \
+i40e-y := i40e_main.o \
 	i40e_ethtool.o	\
 	i40e_adminq.o	\
 	i40e_common.o	\
diff --git a/drivers/net/ethernet/intel/iavf/Makefile b/drivers/net/ethernet/intel/iavf/Makefile
index 2d154a4e2fd76..356ac9faa5bf9 100644
--- a/drivers/net/ethernet/intel/iavf/Makefile
+++ b/drivers/net/ethernet/intel/iavf/Makefile
@@ -11,6 +11,5 @@ subdir-ccflags-y += -I$(src)
 
 obj-$(CONFIG_IAVF) += iavf.o
 
-iavf-objs := iavf_main.o iavf_ethtool.o iavf_virtchnl.o iavf_fdir.o \
-	     iavf_adv_rss.o \
-	     iavf_txrx.o iavf_common.o iavf_adminq.o
+iavf-y := iavf_main.o iavf_ethtool.o iavf_virtchnl.o iavf_fdir.o \
+	  iavf_adv_rss.o iavf_txrx.o iavf_common.o iavf_adminq.o
diff --git a/drivers/net/ethernet/intel/igb/Makefile b/drivers/net/ethernet/intel/igb/Makefile
index 394c1e0656b9e..463c0d26b9d43 100644
--- a/drivers/net/ethernet/intel/igb/Makefile
+++ b/drivers/net/ethernet/intel/igb/Makefile
@@ -6,6 +6,6 @@
 
 obj-$(CONFIG_IGB) += igb.o
 
-igb-objs := igb_main.o igb_ethtool.o e1000_82575.o \
-	    e1000_mac.o e1000_nvm.o e1000_phy.o e1000_mbx.o \
-	    e1000_i210.o igb_ptp.o igb_hwmon.o
+igb-y := igb_main.o igb_ethtool.o e1000_82575.o \
+	 e1000_mac.o e1000_nvm.o e1000_phy.o e1000_mbx.o \
+	 e1000_i210.o igb_ptp.o igb_hwmon.o
diff --git a/drivers/net/ethernet/intel/igbvf/Makefile b/drivers/net/ethernet/intel/igbvf/Makefile
index afd3e36eae757..902711d5e6916 100644
--- a/drivers/net/ethernet/intel/igbvf/Makefile
+++ b/drivers/net/ethernet/intel/igbvf/Makefile
@@ -6,8 +6,4 @@
 
 obj-$(CONFIG_IGBVF) += igbvf.o
 
-igbvf-objs := vf.o \
-              mbx.o \
-              ethtool.o \
-              netdev.o
-
+igbvf-y := vf.o mbx.o ethtool.o netdev.o
diff --git a/drivers/net/ethernet/intel/igc/Makefile b/drivers/net/ethernet/intel/igc/Makefile
index ebffd3054285c..efc5e7983dad9 100644
--- a/drivers/net/ethernet/intel/igc/Makefile
+++ b/drivers/net/ethernet/intel/igc/Makefile
@@ -6,7 +6,7 @@
 #
 
 obj-$(CONFIG_IGC) += igc.o
-igc-$(CONFIG_IGC_LEDS) += igc_leds.o
 
-igc-objs := igc_main.o igc_mac.o igc_i225.o igc_base.o igc_nvm.o igc_phy.o \
-igc_diag.o igc_ethtool.o igc_ptp.o igc_dump.o igc_tsn.o igc_xdp.o
+igc-y := igc_main.o igc_mac.o igc_i225.o igc_base.o igc_nvm.o igc_phy.o \
+	 igc_diag.o igc_ethtool.o igc_ptp.o igc_dump.o igc_tsn.o igc_xdp.o
+igc-$(CONFIG_IGC_LEDS) += igc_leds.o
diff --git a/drivers/net/ethernet/intel/ixgbe/Makefile b/drivers/net/ethernet/intel/ixgbe/Makefile
index 4fb0d9e3f2da2..965e5ce1b3267 100644
--- a/drivers/net/ethernet/intel/ixgbe/Makefile
+++ b/drivers/net/ethernet/intel/ixgbe/Makefile
@@ -6,10 +6,10 @@
 
 obj-$(CONFIG_IXGBE) += ixgbe.o
 
-ixgbe-objs := ixgbe_main.o ixgbe_common.o ixgbe_ethtool.o \
-              ixgbe_82599.o ixgbe_82598.o ixgbe_phy.o ixgbe_sriov.o \
-              ixgbe_mbx.o ixgbe_x540.o ixgbe_x550.o ixgbe_lib.o ixgbe_ptp.o \
-              ixgbe_xsk.o
+ixgbe-y := ixgbe_main.o ixgbe_common.o ixgbe_ethtool.o \
+           ixgbe_82599.o ixgbe_82598.o ixgbe_phy.o ixgbe_sriov.o \
+           ixgbe_mbx.o ixgbe_x540.o ixgbe_x550.o ixgbe_lib.o ixgbe_ptp.o \
+           ixgbe_xsk.o
 
 ixgbe-$(CONFIG_IXGBE_DCB) +=  ixgbe_dcb.o ixgbe_dcb_82598.o \
                               ixgbe_dcb_82599.o ixgbe_dcb_nl.o
diff --git a/drivers/net/ethernet/intel/ixgbevf/Makefile b/drivers/net/ethernet/intel/ixgbevf/Makefile
index 186a4bb24fdea..01d3e892f3fa7 100644
--- a/drivers/net/ethernet/intel/ixgbevf/Makefile
+++ b/drivers/net/ethernet/intel/ixgbevf/Makefile
@@ -6,9 +6,5 @@
 
 obj-$(CONFIG_IXGBEVF) += ixgbevf.o
 
-ixgbevf-objs := vf.o \
-                mbx.o \
-                ethtool.o \
-                ixgbevf_main.o
+ixgbevf-y := vf.o mbx.o ethtool.o ixgbevf_main.o
 ixgbevf-$(CONFIG_IXGBEVF_IPSEC) += ipsec.o
-
diff --git a/drivers/net/ethernet/intel/libeth/Makefile b/drivers/net/ethernet/intel/libeth/Makefile
index cb99203d1dd20..52492b0811326 100644
--- a/drivers/net/ethernet/intel/libeth/Makefile
+++ b/drivers/net/ethernet/intel/libeth/Makefile
@@ -3,4 +3,4 @@
 
 obj-$(CONFIG_LIBETH)		+= libeth.o
 
-libeth-objs			+= rx.o
+libeth-y			:= rx.o
diff --git a/drivers/net/ethernet/intel/libie/Makefile b/drivers/net/ethernet/intel/libie/Makefile
index bf42c5aeeedda..ffd27fab916a6 100644
--- a/drivers/net/ethernet/intel/libie/Makefile
+++ b/drivers/net/ethernet/intel/libie/Makefile
@@ -3,4 +3,4 @@
 
 obj-$(CONFIG_LIBIE)	+= libie.o
 
-libie-objs		+= rx.o
+libie-y			:= rx.o
-- 
GitLab


From 1d4ce389da2b84e0e24aad5e83fe9c742adc3f99 Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Fri, 7 Jun 2024 14:22:33 -0700
Subject: [PATCH 917/950] ice: add and use roundup_u64 instead of open coding
 equivalent

In ice_ptp_cfg_clkout(), the ice driver needs to calculate the nearest next
second of a current time value specified in nanoseconds. It implements this
using div64_u64, because the time value is a u64. It could use div_u64
since NSEC_PER_SEC is smaller than 32-bits.

Ideally this would be implemented directly with roundup(), but that can't
work on all platforms due to a division which requires using the specific
macros and functions due to platform restrictions, and to ensure that the
most appropriate and fast instructions are used.

The kernel doesn't currently provide any 64-bit equivalents for doing
roundup. Attempting to use roundup() on a 32-bit platform will result in a
link failure due to not having a direct 64-bit division.

The closest equivalent for this is DIV64_U64_ROUND_UP, which does a
division always rounding up. However, this only computes the division, and
forces use of the div64_u64 in cases where the divisor is a 32bit value and
could make use of div_u64.

Introduce DIV_U64_ROUND_UP based on div_u64, and then use it to implement
roundup_u64 which takes a u64 input value and a u32 rounding value.

The name roundup_u64 matches the naming scheme of div_u64, and future
patches could implement roundup64_u64 if they need to round by a multiple
that is greater than 32-bits.

Replace the logic in ice_ptp.c which does this equivalent with the newly
added roundup_u64.

Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20240607-next-2024-06-03-intel-next-batch-v3-2-d1470cee3347@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/ice/ice_ptp.c |  3 +--
 include/linux/math64.h                   | 28 ++++++++++++++++++++++++
 2 files changed, 29 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c
index adbb9cffe20c2..b7ab6fdf710d2 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.c
@@ -1773,8 +1773,7 @@ static int ice_ptp_cfg_clkout(struct ice_pf *pf, unsigned int chan,
 	 * maintaining phase
 	 */
 	if (start_time < current_time)
-		start_time = div64_u64(current_time + NSEC_PER_SEC - 1,
-				       NSEC_PER_SEC) * NSEC_PER_SEC + phase;
+		start_time = roundup_u64(current_time, NSEC_PER_SEC) + phase;
 
 	if (ice_is_e810(hw))
 		start_time -= E810_OUT_PROP_DELAY_NS;
diff --git a/include/linux/math64.h b/include/linux/math64.h
index d34def7f9a8cd..6aaccc1626ab4 100644
--- a/include/linux/math64.h
+++ b/include/linux/math64.h
@@ -297,6 +297,19 @@ u64 mul_u64_u64_div_u64(u64 a, u64 mul, u64 div);
 #define DIV64_U64_ROUND_UP(ll, d)	\
 	({ u64 _tmp = (d); div64_u64((ll) + _tmp - 1, _tmp); })
 
+/**
+ * DIV_U64_ROUND_UP - unsigned 64bit divide with 32bit divisor rounded up
+ * @ll: unsigned 64bit dividend
+ * @d: unsigned 32bit divisor
+ *
+ * Divide unsigned 64bit dividend by unsigned 32bit divisor
+ * and round up.
+ *
+ * Return: dividend / divisor rounded up
+ */
+#define DIV_U64_ROUND_UP(ll, d)		\
+	({ u32 _tmp = (d); div_u64((ll) + _tmp - 1, _tmp); })
+
 /**
  * DIV64_U64_ROUND_CLOSEST - unsigned 64bit divide with 64bit divisor rounded to nearest integer
  * @dividend: unsigned 64bit dividend
@@ -342,4 +355,19 @@ u64 mul_u64_u64_div_u64(u64 a, u64 mul, u64 div);
 		div_s64((__x - (__d / 2)), __d);	\
 }							\
 )
+
+/**
+ * roundup_u64 - Round up a 64bit value to the next specified 32bit multiple
+ * @x: the value to up
+ * @y: 32bit multiple to round up to
+ *
+ * Rounds @x to the next multiple of @y. For 32bit @x values, see roundup and
+ * the faster round_up() for powers of 2.
+ *
+ * Return: rounded up value.
+ */
+static inline u64 roundup_u64(u64 x, u32 y)
+{
+	return DIV_U64_ROUND_UP(x, y) * y;
+}
 #endif /* _LINUX_MATH64_H */
-- 
GitLab


From dee55767dc8ca3fc6127a792e2a8b69c5e03fdd2 Mon Sep 17 00:00:00 2001
From: Michal Schmidt <mschmidt@redhat.com>
Date: Fri, 7 Jun 2024 14:22:34 -0700
Subject: [PATCH 918/950] ice: use irq_update_affinity_hint()

irq_set_affinity_hint() is deprecated. Use irq_update_affinity_hint()
instead. This removes the side-effect of actually applying the affinity.

The driver does not really need to worry about spreading its IRQs across
CPUs. The core code already takes care of that.
On the contrary, when the driver applies affinities by itself, it breaks
the users' expectations:
 1. The user configures irqbalance with IRQBALANCE_BANNED_CPULIST in
    order to prevent IRQs from being moved to certain CPUs that run a
    real-time workload.
 2. ice reconfigures VSIs at runtime due to a MIB change
    (ice_dcb_process_lldp_set_mib_change). Reopening a VSI resets the
    affinity in ice_vsi_req_irq_msix().
 3. ice has no idea about irqbalance's config, so it may move an IRQ to
    a banned CPU. The real-time workload suffers unacceptable latency.

I am not sure if updating the affinity hints is at all useful, because
irqbalance ignores them since 2016 ([1]), but at least it's harmless.

This ice change is similar to i40e commit d34c54d1739c ("i40e: Use
irq_update_affinity_hint()").

[1] https://github.com/Irqbalance/irqbalance/commit/dcc411e7bfdd

Signed-off-by: Michal Schmidt <mschmidt@redhat.com>
Reviewed-by: Sunil Goutham <sgoutham@marvell.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20240607-next-2024-06-03-intel-next-batch-v3-3-d1470cee3347@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/ice/ice_lib.c  | 4 ++--
 drivers/net/ethernet/intel/ice/ice_main.c | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 7629b0190578b..f559e60992fa5 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -2580,8 +2580,8 @@ void ice_vsi_free_irq(struct ice_vsi *vsi)
 		if (!IS_ENABLED(CONFIG_RFS_ACCEL))
 			irq_set_affinity_notifier(irq_num, NULL);
 
-		/* clear the affinity_mask in the IRQ descriptor */
-		irq_set_affinity_hint(irq_num, NULL);
+		/* clear the affinity_hint in the IRQ descriptor */
+		irq_update_affinity_hint(irq_num, NULL);
 		synchronize_irq(irq_num);
 		devm_free_irq(ice_pf_to_dev(pf), irq_num, vsi->q_vectors[i]);
 	}
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 1b61ca3a6eb6e..7d9a4e856f619 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -2607,7 +2607,7 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename)
 		}
 
 		/* assign the mask for this irq */
-		irq_set_affinity_hint(irq_num, &q_vector->affinity_mask);
+		irq_update_affinity_hint(irq_num, &q_vector->affinity_mask);
 	}
 
 	err = ice_set_cpu_rx_rmap(vsi);
@@ -2625,7 +2625,7 @@ free_q_irqs:
 		irq_num = vsi->q_vectors[vector]->irq.virq;
 		if (!IS_ENABLED(CONFIG_RFS_ACCEL))
 			irq_set_affinity_notifier(irq_num, NULL);
-		irq_set_affinity_hint(irq_num, NULL);
+		irq_update_affinity_hint(irq_num, NULL);
 		devm_free_irq(dev, irq_num, &vsi->q_vectors[vector]);
 	}
 	return err;
-- 
GitLab


From 98b303c9bf05dae932efbd71e18d81f6c64f20d8 Mon Sep 17 00:00:00 2001
From: Kenta Tada <tadakentaso@gmail.com>
Date: Fri, 7 Jun 2024 20:17:04 +0900
Subject: [PATCH 919/950] bpftool: Query only cgroup-related attach types

When CONFIG_NETKIT=y,
bpftool-cgroup shows error even if the cgroup's path is correct:

$ bpftool cgroup tree /sys/fs/cgroup
CgroupPath
ID       AttachType      AttachFlags     Name
Error: can't query bpf programs attached to /sys/fs/cgroup: No such device or address

>From strace and kernel tracing, I found netkit returned ENXIO and this command failed.
I think this AttachType(BPF_NETKIT_PRIMARY) is not relevant to cgroup.

bpftool-cgroup should query just only cgroup-related attach types.

v2->v3:
  - removed an unnecessary check

v1->v2:
  - used an array of cgroup attach types

Signed-off-by: Kenta Tada <tadakentaso@gmail.com>
Reviewed-by: Quentin Monnet <qmo@kernel.org>
Link: https://lore.kernel.org/r/20240607111704.6716-1-tadakentaso@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/bpf/bpftool/cgroup.c | 40 ++++++++++++++++++++++++++++++++++----
 1 file changed, 36 insertions(+), 4 deletions(-)

diff --git a/tools/bpf/bpftool/cgroup.c b/tools/bpf/bpftool/cgroup.c
index af6898c0f388b..9af426d432993 100644
--- a/tools/bpf/bpftool/cgroup.c
+++ b/tools/bpf/bpftool/cgroup.c
@@ -19,6 +19,38 @@
 
 #include "main.h"
 
+static const int cgroup_attach_types[] = {
+	BPF_CGROUP_INET_INGRESS,
+	BPF_CGROUP_INET_EGRESS,
+	BPF_CGROUP_INET_SOCK_CREATE,
+	BPF_CGROUP_INET_SOCK_RELEASE,
+	BPF_CGROUP_INET4_BIND,
+	BPF_CGROUP_INET6_BIND,
+	BPF_CGROUP_INET4_POST_BIND,
+	BPF_CGROUP_INET6_POST_BIND,
+	BPF_CGROUP_INET4_CONNECT,
+	BPF_CGROUP_INET6_CONNECT,
+	BPF_CGROUP_UNIX_CONNECT,
+	BPF_CGROUP_INET4_GETPEERNAME,
+	BPF_CGROUP_INET6_GETPEERNAME,
+	BPF_CGROUP_UNIX_GETPEERNAME,
+	BPF_CGROUP_INET4_GETSOCKNAME,
+	BPF_CGROUP_INET6_GETSOCKNAME,
+	BPF_CGROUP_UNIX_GETSOCKNAME,
+	BPF_CGROUP_UDP4_SENDMSG,
+	BPF_CGROUP_UDP6_SENDMSG,
+	BPF_CGROUP_UNIX_SENDMSG,
+	BPF_CGROUP_UDP4_RECVMSG,
+	BPF_CGROUP_UDP6_RECVMSG,
+	BPF_CGROUP_UNIX_RECVMSG,
+	BPF_CGROUP_SOCK_OPS,
+	BPF_CGROUP_DEVICE,
+	BPF_CGROUP_SYSCTL,
+	BPF_CGROUP_GETSOCKOPT,
+	BPF_CGROUP_SETSOCKOPT,
+	BPF_LSM_CGROUP
+};
+
 #define HELP_SPEC_ATTACH_FLAGS						\
 	"ATTACH_FLAGS := { multi | override }"
 
@@ -183,13 +215,13 @@ static int count_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type)
 
 static int cgroup_has_attached_progs(int cgroup_fd)
 {
-	enum bpf_attach_type type;
+	unsigned int i = 0;
 	bool no_prog = true;
 
-	for (type = 0; type < __MAX_BPF_ATTACH_TYPE; type++) {
-		int count = count_attached_bpf_progs(cgroup_fd, type);
+	for (i = 0; i < ARRAY_SIZE(cgroup_attach_types); i++) {
+		int count = count_attached_bpf_progs(cgroup_fd, cgroup_attach_types[i]);
 
-		if (count < 0 && errno != EINVAL)
+		if (count < 0)
 			return -1;
 
 		if (count > 0) {
-- 
GitLab


From ebb79e96f1ea454fbcc8fe27dfe44e751bd74b4b Mon Sep 17 00:00:00 2001
From: Daniel Xu <dxu@dxuuu.xyz>
Date: Wed, 12 Jun 2024 09:58:25 -0600
Subject: [PATCH 920/950] kbuild: bpf: Tell pahole to DECL_TAG kfuncs

With [0], pahole can now discover kfuncs and inject DECL_TAG
into BTF. With this commit, we will start shipping said DECL_TAGs
to downstream consumers if pahole supports it.

This is useful for feature probing kfuncs as well as generating
compilable prototypes. This is particularly important as kfuncs
do not have stable ABI.

[0]: https://git.kernel.org/pub/scm/devel/pahole/pahole.git/commit/?id=72e88f29c6f7e14201756e65bd66157427a61aaf

Signed-off-by: Daniel Xu <dxu@dxuuu.xyz>
Link: https://lore.kernel.org/r/324aac5c627bddb80d9968c30df6382846994cc8.1718207789.git.dxu@dxuuu.xyz
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 scripts/Makefile.btf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/Makefile.btf b/scripts/Makefile.btf
index bca8a8f26ea4c..2597e3d4d6e01 100644
--- a/scripts/Makefile.btf
+++ b/scripts/Makefile.btf
@@ -19,7 +19,7 @@ pahole-flags-$(call test-ge, $(pahole-ver), 125)	+= --skip_encoding_btf_inconsis
 else
 
 # Switch to using --btf_features for v1.26 and later.
-pahole-flags-$(call test-ge, $(pahole-ver), 126)  = -j --btf_features=encode_force,var,float,enum64,decl_tag,type_tag,optimized_func,consistent_func
+pahole-flags-$(call test-ge, $(pahole-ver), 126)  = -j --btf_features=encode_force,var,float,enum64,decl_tag,type_tag,optimized_func,consistent_func,decl_tag_kfuncs
 
 endif
 
-- 
GitLab


From 718135f5bd24ec10ff38aa0294a7da0a7b99fa89 Mon Sep 17 00:00:00 2001
From: Daniel Xu <dxu@dxuuu.xyz>
Date: Wed, 12 Jun 2024 09:58:26 -0600
Subject: [PATCH 921/950] bpf: selftests: Fix bpf_iter_task_vma_new() prototype

bpf_iter_task_vma_new() is defined as taking a u64 as its 3rd argument.
u64 is a unsigned long long. bpf_experimental.h was defining the
prototype as unsigned long.

Fix by using __u64.

Signed-off-by: Daniel Xu <dxu@dxuuu.xyz>
Link: https://lore.kernel.org/r/fab4509bfee914f539166a91c3ff41e949f3df30.1718207789.git.dxu@dxuuu.xyz
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/bpf_experimental.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/bpf_experimental.h b/tools/testing/selftests/bpf/bpf_experimental.h
index 3d9e4b8c6b81a..8ee7a00b7c828 100644
--- a/tools/testing/selftests/bpf/bpf_experimental.h
+++ b/tools/testing/selftests/bpf/bpf_experimental.h
@@ -163,7 +163,7 @@ struct bpf_iter_task_vma;
 
 extern int bpf_iter_task_vma_new(struct bpf_iter_task_vma *it,
 				 struct task_struct *task,
-				 unsigned long addr) __ksym;
+				 __u64 addr) __ksym;
 extern struct vm_area_struct *bpf_iter_task_vma_next(struct bpf_iter_task_vma *it) __ksym;
 extern void bpf_iter_task_vma_destroy(struct bpf_iter_task_vma *it) __ksym;
 
-- 
GitLab


From dff96e4f5078c6c61fc6c36dddf27b124c4318fc Mon Sep 17 00:00:00 2001
From: Daniel Xu <dxu@dxuuu.xyz>
Date: Wed, 12 Jun 2024 09:58:27 -0600
Subject: [PATCH 922/950] bpf: selftests: Fix fentry test kfunc prototypes

Some prototypes in progs/get_func_ip_test.c were not in line with how the
actual kfuncs are defined in net/bpf/test_run.c. This causes compilation
errors when kfunc prototypes are generated from BTF.

Fix by aligning with actual kfunc definitions.

Also remove two unused prototypes.

Signed-off-by: Daniel Xu <dxu@dxuuu.xyz>
Link: https://lore.kernel.org/r/1e68870e7626b7b9c6420e65076b307fc404a2f0.1718207789.git.dxu@dxuuu.xyz
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/progs/get_func_ip_test.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/bpf/progs/get_func_ip_test.c b/tools/testing/selftests/bpf/progs/get_func_ip_test.c
index 8956eb78a2260..2011cacdeb183 100644
--- a/tools/testing/selftests/bpf/progs/get_func_ip_test.c
+++ b/tools/testing/selftests/bpf/progs/get_func_ip_test.c
@@ -5,13 +5,12 @@
 
 char _license[] SEC("license") = "GPL";
 
-extern const void bpf_fentry_test1 __ksym;
+extern int bpf_fentry_test1(int a) __ksym;
+extern int bpf_modify_return_test(int a, int *b) __ksym;
+
 extern const void bpf_fentry_test2 __ksym;
 extern const void bpf_fentry_test3 __ksym;
 extern const void bpf_fentry_test4 __ksym;
-extern const void bpf_modify_return_test __ksym;
-extern const void bpf_fentry_test6 __ksym;
-extern const void bpf_fentry_test7 __ksym;
 
 extern bool CONFIG_X86_KERNEL_IBT __kconfig __weak;
 
-- 
GitLab


From 89f0b1abac497c47d0851b780abecc756c1e8734 Mon Sep 17 00:00:00 2001
From: Daniel Xu <dxu@dxuuu.xyz>
Date: Wed, 12 Jun 2024 09:58:28 -0600
Subject: [PATCH 923/950] bpf: selftests: Fix bpf_cpumask_first_zero() kfunc
 prototype

The prototype in progs/nested_trust_common.h is not in line with how the
actual kfuncs are defined in kernel/bpf/cpumask.c. This causes compilation
errors when kfunc prototypes are generated from BTF.

Fix by aligning with actual kfunc definitions.

Signed-off-by: Daniel Xu <dxu@dxuuu.xyz>
Link: https://lore.kernel.org/r/437936a4e554b02e04566dd6e3f0a5d08370cc8c.1718207789.git.dxu@dxuuu.xyz
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/progs/nested_trust_common.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/progs/nested_trust_common.h b/tools/testing/selftests/bpf/progs/nested_trust_common.h
index 83d33931136ea..1784b496be2ec 100644
--- a/tools/testing/selftests/bpf/progs/nested_trust_common.h
+++ b/tools/testing/selftests/bpf/progs/nested_trust_common.h
@@ -7,6 +7,6 @@
 #include <stdbool.h>
 
 bool bpf_cpumask_test_cpu(unsigned int cpu, const struct cpumask *cpumask) __ksym;
-bool bpf_cpumask_first_zero(const struct cpumask *cpumask) __ksym;
+__u32 bpf_cpumask_first_zero(const struct cpumask *cpumask) __ksym;
 
 #endif /* _NESTED_TRUST_COMMON_H */
-- 
GitLab


From ac42f636dc11b2e8d6dea9dd5bb10a39c7bec342 Mon Sep 17 00:00:00 2001
From: Daniel Xu <dxu@dxuuu.xyz>
Date: Wed, 12 Jun 2024 09:58:29 -0600
Subject: [PATCH 924/950] bpf: selftests: Fix bpf_map_sum_elem_count() kfunc
 prototype

The prototype in progs/map_percpu_stats.c is not in line with how the
actual kfuncs are defined in kernel/bpf/map_iter.c. This causes
compilation errors when kfunc prototypes are generated from BTF.

Fix by aligning with actual kfunc definitions.

Signed-off-by: Daniel Xu <dxu@dxuuu.xyz>
Link: https://lore.kernel.org/r/0497e11a71472dcb71ada7c90ad691523ae87c3b.1718207789.git.dxu@dxuuu.xyz
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/progs/map_percpu_stats.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/progs/map_percpu_stats.c b/tools/testing/selftests/bpf/progs/map_percpu_stats.c
index 10b2325c17207..63245785eb69e 100644
--- a/tools/testing/selftests/bpf/progs/map_percpu_stats.c
+++ b/tools/testing/selftests/bpf/progs/map_percpu_stats.c
@@ -7,7 +7,7 @@
 
 __u32 target_id;
 
-__s64 bpf_map_sum_elem_count(struct bpf_map *map) __ksym;
+__s64 bpf_map_sum_elem_count(const struct bpf_map *map) __ksym;
 
 SEC("iter/bpf_map")
 int dump_bpf_map(struct bpf_iter__bpf_map *ctx)
-- 
GitLab


From 2b8dd87332cd2782b5b3f0c423bd6693e487ed30 Mon Sep 17 00:00:00 2001
From: Daniel Xu <dxu@dxuuu.xyz>
Date: Wed, 12 Jun 2024 09:58:30 -0600
Subject: [PATCH 925/950] bpf: Make bpf_session_cookie() kfunc return long *

We will soon be generating kfunc prototypes from BTF. As part of that,
we need to align the manual signatures in bpf_kfuncs.h with the actual
kfunc definitions. There is currently a conflicting signature for
bpf_session_cookie() w.r.t. return type.

The original intent was to return long * and not __u64 *. You can see
evidence of that intent in a3a5113393cc ("selftests/bpf: Add kprobe
session cookie test").

Fix conflict by changing kfunc definition.

Fixes: 5c919acef851 ("bpf: Add support for kprobe session cookie")
Signed-off-by: Daniel Xu <dxu@dxuuu.xyz>
Link: https://lore.kernel.org/r/7043e1c251ab33151d6e3830f8ea1902ed2604ac.1718207789.git.dxu@dxuuu.xyz
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/trace/bpf_trace.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index d1daeab1bbc14..bc16e21a2a443 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -3527,7 +3527,7 @@ __bpf_kfunc bool bpf_session_is_return(void)
 	return session_ctx->is_return;
 }
 
-__bpf_kfunc __u64 *bpf_session_cookie(void)
+__bpf_kfunc long *bpf_session_cookie(void)
 {
 	struct bpf_session_run_ctx *session_ctx;
 
-- 
GitLab


From 0ce089cbdc6a393bf9ad04964427852800503a58 Mon Sep 17 00:00:00 2001
From: Daniel Xu <dxu@dxuuu.xyz>
Date: Wed, 12 Jun 2024 09:58:31 -0600
Subject: [PATCH 926/950] bpf: selftests: Namespace struct_opt callbacks in
 bpf_dctcp

With generated kfunc prototypes, the existing callback names will
conflict. Fix by namespacing with a bpf_ prefix.

Signed-off-by: Daniel Xu <dxu@dxuuu.xyz>
Link: https://lore.kernel.org/r/efe7aadad8a054e5aeeba94b1d2e4502eee09d7a.1718207789.git.dxu@dxuuu.xyz
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/progs/bpf_dctcp.c | 36 +++++++++----------
 1 file changed, 18 insertions(+), 18 deletions(-)

diff --git a/tools/testing/selftests/bpf/progs/bpf_dctcp.c b/tools/testing/selftests/bpf/progs/bpf_dctcp.c
index 3c9ffe3403123..02f552e7fd4d0 100644
--- a/tools/testing/selftests/bpf/progs/bpf_dctcp.c
+++ b/tools/testing/selftests/bpf/progs/bpf_dctcp.c
@@ -65,7 +65,7 @@ static void dctcp_reset(const struct tcp_sock *tp, struct bpf_dctcp *ca)
 }
 
 SEC("struct_ops")
-void BPF_PROG(dctcp_init, struct sock *sk)
+void BPF_PROG(bpf_dctcp_init, struct sock *sk)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
 	struct bpf_dctcp *ca = inet_csk_ca(sk);
@@ -77,7 +77,7 @@ void BPF_PROG(dctcp_init, struct sock *sk)
 				   (void *)fallback, sizeof(fallback)) == -EBUSY)
 			ebusy_cnt++;
 
-		/* Switch back to myself and the recurred dctcp_init()
+		/* Switch back to myself and the recurred bpf_dctcp_init()
 		 * will get -EBUSY for all bpf_setsockopt(TCP_CONGESTION),
 		 * except the last "cdg" one.
 		 */
@@ -112,7 +112,7 @@ void BPF_PROG(dctcp_init, struct sock *sk)
 }
 
 SEC("struct_ops")
-__u32 BPF_PROG(dctcp_ssthresh, struct sock *sk)
+__u32 BPF_PROG(bpf_dctcp_ssthresh, struct sock *sk)
 {
 	struct bpf_dctcp *ca = inet_csk_ca(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
@@ -122,7 +122,7 @@ __u32 BPF_PROG(dctcp_ssthresh, struct sock *sk)
 }
 
 SEC("struct_ops")
-void BPF_PROG(dctcp_update_alpha, struct sock *sk, __u32 flags)
+void BPF_PROG(bpf_dctcp_update_alpha, struct sock *sk, __u32 flags)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
 	struct bpf_dctcp *ca = inet_csk_ca(sk);
@@ -161,12 +161,12 @@ static void dctcp_react_to_loss(struct sock *sk)
 }
 
 SEC("struct_ops")
-void BPF_PROG(dctcp_state, struct sock *sk, __u8 new_state)
+void BPF_PROG(bpf_dctcp_state, struct sock *sk, __u8 new_state)
 {
 	if (new_state == TCP_CA_Recovery &&
 	    new_state != BPF_CORE_READ_BITFIELD(inet_csk(sk), icsk_ca_state))
 		dctcp_react_to_loss(sk);
-	/* We handle RTO in dctcp_cwnd_event to ensure that we perform only
+	/* We handle RTO in bpf_dctcp_cwnd_event to ensure that we perform only
 	 * one loss-adjustment per RTT.
 	 */
 }
@@ -208,7 +208,7 @@ static void dctcp_ece_ack_update(struct sock *sk, enum tcp_ca_event evt,
 }
 
 SEC("struct_ops")
-void BPF_PROG(dctcp_cwnd_event, struct sock *sk, enum tcp_ca_event ev)
+void BPF_PROG(bpf_dctcp_cwnd_event, struct sock *sk, enum tcp_ca_event ev)
 {
 	struct bpf_dctcp *ca = inet_csk_ca(sk);
 
@@ -227,7 +227,7 @@ void BPF_PROG(dctcp_cwnd_event, struct sock *sk, enum tcp_ca_event ev)
 }
 
 SEC("struct_ops")
-__u32 BPF_PROG(dctcp_cwnd_undo, struct sock *sk)
+__u32 BPF_PROG(bpf_dctcp_cwnd_undo, struct sock *sk)
 {
 	const struct bpf_dctcp *ca = inet_csk_ca(sk);
 
@@ -237,28 +237,28 @@ __u32 BPF_PROG(dctcp_cwnd_undo, struct sock *sk)
 extern void tcp_reno_cong_avoid(struct sock *sk, __u32 ack, __u32 acked) __ksym;
 
 SEC("struct_ops")
-void BPF_PROG(dctcp_cong_avoid, struct sock *sk, __u32 ack, __u32 acked)
+void BPF_PROG(bpf_dctcp_cong_avoid, struct sock *sk, __u32 ack, __u32 acked)
 {
 	tcp_reno_cong_avoid(sk, ack, acked);
 }
 
 SEC(".struct_ops")
 struct tcp_congestion_ops dctcp_nouse = {
-	.init		= (void *)dctcp_init,
-	.set_state	= (void *)dctcp_state,
+	.init		= (void *)bpf_dctcp_init,
+	.set_state	= (void *)bpf_dctcp_state,
 	.flags		= TCP_CONG_NEEDS_ECN,
 	.name		= "bpf_dctcp_nouse",
 };
 
 SEC(".struct_ops")
 struct tcp_congestion_ops dctcp = {
-	.init		= (void *)dctcp_init,
-	.in_ack_event   = (void *)dctcp_update_alpha,
-	.cwnd_event	= (void *)dctcp_cwnd_event,
-	.ssthresh	= (void *)dctcp_ssthresh,
-	.cong_avoid	= (void *)dctcp_cong_avoid,
-	.undo_cwnd	= (void *)dctcp_cwnd_undo,
-	.set_state	= (void *)dctcp_state,
+	.init		= (void *)bpf_dctcp_init,
+	.in_ack_event   = (void *)bpf_dctcp_update_alpha,
+	.cwnd_event	= (void *)bpf_dctcp_cwnd_event,
+	.ssthresh	= (void *)bpf_dctcp_ssthresh,
+	.cong_avoid	= (void *)bpf_dctcp_cong_avoid,
+	.undo_cwnd	= (void *)bpf_dctcp_cwnd_undo,
+	.set_state	= (void *)bpf_dctcp_state,
 	.flags		= TCP_CONG_NEEDS_ECN,
 	.name		= "bpf_dctcp",
 };
-- 
GitLab


From ec209ad86324de84ef66990f0e9df0851e45e054 Mon Sep 17 00:00:00 2001
From: Daniel Xu <dxu@dxuuu.xyz>
Date: Wed, 12 Jun 2024 09:58:32 -0600
Subject: [PATCH 927/950] bpf: verifier: Relax caller requirements for kfunc
 projection type args

Currently, if a kfunc accepts a projection type as an argument (eg
struct __sk_buff *), the caller must exactly provide exactly the same
type with provable provenance.

However in practice, kfuncs that accept projection types _must_ cast to
the underlying type before use b/c projection type layouts are
completely made up. Thus, it is ok to relax the verifier rules around
implicit conversions.

We will use this functionality in the next commit when we align kfuncs
to user-facing types.

Signed-off-by: Daniel Xu <dxu@dxuuu.xyz>
Link: https://lore.kernel.org/r/e2c025cb09ccfd4af1ec9e18284dc3cecff7514d.1718207789.git.dxu@dxuuu.xyz
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/btf.h   |  1 +
 kernel/bpf/btf.c      | 13 ++++++++++---
 kernel/bpf/verifier.c | 10 +++++++++-
 3 files changed, 20 insertions(+), 4 deletions(-)

diff --git a/include/linux/btf.h b/include/linux/btf.h
index f9e56fd12a9fd..56d91daacdba3 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -531,6 +531,7 @@ s32 btf_find_dtor_kfunc(struct btf *btf, u32 btf_id);
 int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dtors, u32 add_cnt,
 				struct module *owner);
 struct btf_struct_meta *btf_find_struct_meta(const struct btf *btf, u32 btf_id);
+bool btf_is_projection_of(const char *pname, const char *tname);
 bool btf_is_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf,
 			   const struct btf_type *t, enum bpf_prog_type prog_type,
 			   int arg);
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 7928d920056f7..ce47079682176 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -5820,6 +5820,15 @@ static int find_kern_ctx_type_id(enum bpf_prog_type prog_type)
 	return ctx_type->type;
 }
 
+bool btf_is_projection_of(const char *pname, const char *tname)
+{
+	if (strcmp(pname, "__sk_buff") == 0 && strcmp(tname, "sk_buff") == 0)
+		return true;
+	if (strcmp(pname, "xdp_md") == 0 && strcmp(tname, "xdp_buff") == 0)
+		return true;
+	return false;
+}
+
 bool btf_is_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf,
 			  const struct btf_type *t, enum bpf_prog_type prog_type,
 			  int arg)
@@ -5882,9 +5891,7 @@ again:
 	 * int socket_filter_bpf_prog(struct __sk_buff *skb)
 	 * { // no fields of skb are ever used }
 	 */
-	if (strcmp(ctx_tname, "__sk_buff") == 0 && strcmp(tname, "sk_buff") == 0)
-		return true;
-	if (strcmp(ctx_tname, "xdp_md") == 0 && strcmp(tname, "xdp_buff") == 0)
+	if (btf_is_projection_of(ctx_tname, tname))
 		return true;
 	if (strcmp(ctx_tname, tname)) {
 		/* bpf_user_pt_regs_t is a typedef, so resolve it to
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 20ac9cfd54dd7..dcac6119d8102 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -11265,6 +11265,8 @@ static int process_kf_arg_ptr_to_btf_id(struct bpf_verifier_env *env,
 	bool strict_type_match = false;
 	const struct btf *reg_btf;
 	const char *reg_ref_tname;
+	bool taking_projection;
+	bool struct_same;
 	u32 reg_ref_id;
 
 	if (base_type(reg->type) == PTR_TO_BTF_ID) {
@@ -11308,7 +11310,13 @@ static int process_kf_arg_ptr_to_btf_id(struct bpf_verifier_env *env,
 
 	reg_ref_t = btf_type_skip_modifiers(reg_btf, reg_ref_id, &reg_ref_id);
 	reg_ref_tname = btf_name_by_offset(reg_btf, reg_ref_t->name_off);
-	if (!btf_struct_ids_match(&env->log, reg_btf, reg_ref_id, reg->off, meta->btf, ref_id, strict_type_match)) {
+	struct_same = btf_struct_ids_match(&env->log, reg_btf, reg_ref_id, reg->off, meta->btf, ref_id, strict_type_match);
+	/* If kfunc is accepting a projection type (ie. __sk_buff), it cannot
+	 * actually use it -- it must cast to the underlying type. So we allow
+	 * caller to pass in the underlying type.
+	 */
+	taking_projection = btf_is_projection_of(ref_tname, reg_ref_tname);
+	if (!taking_projection && !struct_same) {
 		verbose(env, "kernel function %s args#%d expected pointer to %s %s but R%d has a pointer to %s %s\n",
 			meta->func_name, argno, btf_type_str(ref_t), ref_tname, argno + 1,
 			btf_type_str(reg_ref_t), reg_ref_tname);
-- 
GitLab


From cce4c40b960673f9e020835def310f1e89d3a940 Mon Sep 17 00:00:00 2001
From: Daniel Xu <dxu@dxuuu.xyz>
Date: Wed, 12 Jun 2024 09:58:33 -0600
Subject: [PATCH 928/950] bpf: treewide: Align kfunc signatures to prog
 point-of-view

Previously, kfunc declarations in bpf_kfuncs.h (and others) used "user
facing" types for kfuncs prototypes while the actual kfunc definitions
used "kernel facing" types. More specifically: bpf_dynptr vs
bpf_dynptr_kern, __sk_buff vs sk_buff, and xdp_md vs xdp_buff.

It wasn't an issue before, as the verifier allows aliased types.
However, since we are now generating kfunc prototypes in vmlinux.h (in
addition to keeping bpf_kfuncs.h around), this conflict creates
compilation errors.

Fix this conflict by using "user facing" types in kfunc definitions.
This results in more casts, but otherwise has no additional runtime
cost.

Note, similar to 5b268d1ebcdc ("bpf: Have bpf_rdonly_cast() take a const
pointer"), we also make kfuncs take const arguments where appropriate in
order to make the kfunc more permissive.

Signed-off-by: Daniel Xu <dxu@dxuuu.xyz>
Link: https://lore.kernel.org/r/b58346a63a0e66bc9b7504da751b526b0b189a67.1718207789.git.dxu@dxuuu.xyz
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 fs/verity/measure.c                           |  5 ++-
 include/linux/bpf.h                           |  8 ++--
 kernel/bpf/crypto.c                           | 24 ++++++++----
 kernel/bpf/helpers.c                          | 39 +++++++++++++------
 kernel/bpf/verifier.c                         |  2 +-
 kernel/trace/bpf_trace.c                      | 15 ++++---
 net/core/filter.c                             | 32 +++++++++------
 .../selftests/bpf/progs/ip_check_defrag.c     | 10 ++---
 .../bpf/progs/verifier_netfilter_ctx.c        |  6 +--
 9 files changed, 88 insertions(+), 53 deletions(-)

diff --git a/fs/verity/measure.c b/fs/verity/measure.c
index 3969d54158d12..175d2f1bc0893 100644
--- a/fs/verity/measure.c
+++ b/fs/verity/measure.c
@@ -111,14 +111,15 @@ __bpf_kfunc_start_defs();
 /**
  * bpf_get_fsverity_digest: read fsverity digest of file
  * @file: file to get digest from
- * @digest_ptr: (out) dynptr for struct fsverity_digest
+ * @digest_p: (out) dynptr for struct fsverity_digest
  *
  * Read fsverity_digest of *file* into *digest_ptr*.
  *
  * Return: 0 on success, a negative value on error.
  */
-__bpf_kfunc int bpf_get_fsverity_digest(struct file *file, struct bpf_dynptr_kern *digest_ptr)
+__bpf_kfunc int bpf_get_fsverity_digest(struct file *file, struct bpf_dynptr *digest_p)
 {
+	struct bpf_dynptr_kern *digest_ptr = (struct bpf_dynptr_kern *)digest_p;
 	const struct inode *inode = file_inode(file);
 	u32 dynptr_sz = __bpf_dynptr_size(digest_ptr);
 	struct fsverity_digest *arg;
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index a834f4b761bc5..f636b4998bf71 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -3265,8 +3265,8 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type,
 				struct bpf_insn *insn_buf,
 				struct bpf_prog *prog,
 				u32 *target_size);
-int bpf_dynptr_from_skb_rdonly(struct sk_buff *skb, u64 flags,
-			       struct bpf_dynptr_kern *ptr);
+int bpf_dynptr_from_skb_rdonly(struct __sk_buff *skb, u64 flags,
+			       struct bpf_dynptr *ptr);
 #else
 static inline bool bpf_sock_common_is_valid_access(int off, int size,
 						   enum bpf_access_type type,
@@ -3288,8 +3288,8 @@ static inline u32 bpf_sock_convert_ctx_access(enum bpf_access_type type,
 {
 	return 0;
 }
-static inline int bpf_dynptr_from_skb_rdonly(struct sk_buff *skb, u64 flags,
-					     struct bpf_dynptr_kern *ptr)
+static inline int bpf_dynptr_from_skb_rdonly(struct __sk_buff *skb, u64 flags,
+					     struct bpf_dynptr *ptr)
 {
 	return -EOPNOTSUPP;
 }
diff --git a/kernel/bpf/crypto.c b/kernel/bpf/crypto.c
index 2bee4af91e383..3c1de0e5c0bd3 100644
--- a/kernel/bpf/crypto.c
+++ b/kernel/bpf/crypto.c
@@ -311,11 +311,15 @@ static int bpf_crypto_crypt(const struct bpf_crypto_ctx *ctx,
  * Decrypts provided buffer using IV data and the crypto context. Crypto context must be configured.
  */
 __bpf_kfunc int bpf_crypto_decrypt(struct bpf_crypto_ctx *ctx,
-				   const struct bpf_dynptr_kern *src,
-				   const struct bpf_dynptr_kern *dst,
-				   const struct bpf_dynptr_kern *siv)
+				   const struct bpf_dynptr *src,
+				   const struct bpf_dynptr *dst,
+				   const struct bpf_dynptr *siv)
 {
-	return bpf_crypto_crypt(ctx, src, dst, siv, true);
+	const struct bpf_dynptr_kern *src_kern = (struct bpf_dynptr_kern *)src;
+	const struct bpf_dynptr_kern *dst_kern = (struct bpf_dynptr_kern *)dst;
+	const struct bpf_dynptr_kern *siv_kern = (struct bpf_dynptr_kern *)siv;
+
+	return bpf_crypto_crypt(ctx, src_kern, dst_kern, siv_kern, true);
 }
 
 /**
@@ -328,11 +332,15 @@ __bpf_kfunc int bpf_crypto_decrypt(struct bpf_crypto_ctx *ctx,
  * Encrypts provided buffer using IV data and the crypto context. Crypto context must be configured.
  */
 __bpf_kfunc int bpf_crypto_encrypt(struct bpf_crypto_ctx *ctx,
-				   const struct bpf_dynptr_kern *src,
-				   const struct bpf_dynptr_kern *dst,
-				   const struct bpf_dynptr_kern *siv)
+				   const struct bpf_dynptr *src,
+				   const struct bpf_dynptr *dst,
+				   const struct bpf_dynptr *siv)
 {
-	return bpf_crypto_crypt(ctx, src, dst, siv, false);
+	const struct bpf_dynptr_kern *src_kern = (struct bpf_dynptr_kern *)src;
+	const struct bpf_dynptr_kern *dst_kern = (struct bpf_dynptr_kern *)dst;
+	const struct bpf_dynptr_kern *siv_kern = (struct bpf_dynptr_kern *)siv;
+
+	return bpf_crypto_crypt(ctx, src_kern, dst_kern, siv_kern, false);
 }
 
 __bpf_kfunc_end_defs();
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 6f1abcb4b0840..3ac521c48bbae 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -2459,9 +2459,10 @@ __bpf_kfunc struct task_struct *bpf_task_from_pid(s32 pid)
  * provided buffer, with its contents containing the data, if unable to obtain
  * direct pointer)
  */
-__bpf_kfunc void *bpf_dynptr_slice(const struct bpf_dynptr_kern *ptr, u32 offset,
+__bpf_kfunc void *bpf_dynptr_slice(const struct bpf_dynptr *p, u32 offset,
 				   void *buffer__opt, u32 buffer__szk)
 {
+	const struct bpf_dynptr_kern *ptr = (struct bpf_dynptr_kern *)p;
 	enum bpf_dynptr_type type;
 	u32 len = buffer__szk;
 	int err;
@@ -2543,9 +2544,11 @@ __bpf_kfunc void *bpf_dynptr_slice(const struct bpf_dynptr_kern *ptr, u32 offset
  * provided buffer, with its contents containing the data, if unable to obtain
  * direct pointer)
  */
-__bpf_kfunc void *bpf_dynptr_slice_rdwr(const struct bpf_dynptr_kern *ptr, u32 offset,
+__bpf_kfunc void *bpf_dynptr_slice_rdwr(const struct bpf_dynptr *p, u32 offset,
 					void *buffer__opt, u32 buffer__szk)
 {
+	const struct bpf_dynptr_kern *ptr = (struct bpf_dynptr_kern *)p;
+
 	if (!ptr->data || __bpf_dynptr_is_rdonly(ptr))
 		return NULL;
 
@@ -2571,11 +2574,12 @@ __bpf_kfunc void *bpf_dynptr_slice_rdwr(const struct bpf_dynptr_kern *ptr, u32 o
 	 * will be copied out into the buffer and the user will need to call
 	 * bpf_dynptr_write() to commit changes.
 	 */
-	return bpf_dynptr_slice(ptr, offset, buffer__opt, buffer__szk);
+	return bpf_dynptr_slice(p, offset, buffer__opt, buffer__szk);
 }
 
-__bpf_kfunc int bpf_dynptr_adjust(struct bpf_dynptr_kern *ptr, u32 start, u32 end)
+__bpf_kfunc int bpf_dynptr_adjust(const struct bpf_dynptr *p, u32 start, u32 end)
 {
+	struct bpf_dynptr_kern *ptr = (struct bpf_dynptr_kern *)p;
 	u32 size;
 
 	if (!ptr->data || start > end)
@@ -2592,36 +2596,45 @@ __bpf_kfunc int bpf_dynptr_adjust(struct bpf_dynptr_kern *ptr, u32 start, u32 en
 	return 0;
 }
 
-__bpf_kfunc bool bpf_dynptr_is_null(struct bpf_dynptr_kern *ptr)
+__bpf_kfunc bool bpf_dynptr_is_null(const struct bpf_dynptr *p)
 {
+	struct bpf_dynptr_kern *ptr = (struct bpf_dynptr_kern *)p;
+
 	return !ptr->data;
 }
 
-__bpf_kfunc bool bpf_dynptr_is_rdonly(struct bpf_dynptr_kern *ptr)
+__bpf_kfunc bool bpf_dynptr_is_rdonly(const struct bpf_dynptr *p)
 {
+	struct bpf_dynptr_kern *ptr = (struct bpf_dynptr_kern *)p;
+
 	if (!ptr->data)
 		return false;
 
 	return __bpf_dynptr_is_rdonly(ptr);
 }
 
-__bpf_kfunc __u32 bpf_dynptr_size(const struct bpf_dynptr_kern *ptr)
+__bpf_kfunc __u32 bpf_dynptr_size(const struct bpf_dynptr *p)
 {
+	struct bpf_dynptr_kern *ptr = (struct bpf_dynptr_kern *)p;
+
 	if (!ptr->data)
 		return -EINVAL;
 
 	return __bpf_dynptr_size(ptr);
 }
 
-__bpf_kfunc int bpf_dynptr_clone(struct bpf_dynptr_kern *ptr,
-				 struct bpf_dynptr_kern *clone__uninit)
+__bpf_kfunc int bpf_dynptr_clone(const struct bpf_dynptr *p,
+				 struct bpf_dynptr *clone__uninit)
 {
+	struct bpf_dynptr_kern *clone = (struct bpf_dynptr_kern *)clone__uninit;
+	struct bpf_dynptr_kern *ptr = (struct bpf_dynptr_kern *)p;
+
 	if (!ptr->data) {
-		bpf_dynptr_set_null(clone__uninit);
+		bpf_dynptr_set_null(clone);
 		return -EINVAL;
 	}
 
-	*clone__uninit = *ptr;
+	*clone = *ptr;
 
 	return 0;
 }
@@ -2986,7 +2999,9 @@ late_initcall(kfunc_init);
  */
 const void *__bpf_dynptr_data(const struct bpf_dynptr_kern *ptr, u32 len)
 {
-	return bpf_dynptr_slice(ptr, 0, NULL, len);
+	const struct bpf_dynptr *p = (struct bpf_dynptr *)ptr;
+
+	return bpf_dynptr_slice(p, 0, NULL, len);
 }
 
 /* Get a pointer to dynptr data up to len bytes for read write access. If
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index dcac6119d8102..acc9dd8308078 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -10914,7 +10914,7 @@ enum {
 };
 
 BTF_ID_LIST(kf_arg_btf_ids)
-BTF_ID(struct, bpf_dynptr_kern)
+BTF_ID(struct, bpf_dynptr)
 BTF_ID(struct, bpf_list_head)
 BTF_ID(struct, bpf_list_node)
 BTF_ID(struct, bpf_rb_root)
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index bc16e21a2a443..4b3fda4562999 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1369,8 +1369,8 @@ __bpf_kfunc void bpf_key_put(struct bpf_key *bkey)
 #ifdef CONFIG_SYSTEM_DATA_VERIFICATION
 /**
  * bpf_verify_pkcs7_signature - verify a PKCS#7 signature
- * @data_ptr: data to verify
- * @sig_ptr: signature of the data
+ * @data_p: data to verify
+ * @sig_p: signature of the data
  * @trusted_keyring: keyring with keys trusted for signature verification
  *
  * Verify the PKCS#7 signature *sig_ptr* against the supplied *data_ptr*
@@ -1378,10 +1378,12 @@ __bpf_kfunc void bpf_key_put(struct bpf_key *bkey)
  *
  * Return: 0 on success, a negative value on error.
  */
-__bpf_kfunc int bpf_verify_pkcs7_signature(struct bpf_dynptr_kern *data_ptr,
-			       struct bpf_dynptr_kern *sig_ptr,
+__bpf_kfunc int bpf_verify_pkcs7_signature(struct bpf_dynptr *data_p,
+			       struct bpf_dynptr *sig_p,
 			       struct bpf_key *trusted_keyring)
 {
+	struct bpf_dynptr_kern *data_ptr = (struct bpf_dynptr_kern *)data_p;
+	struct bpf_dynptr_kern *sig_ptr = (struct bpf_dynptr_kern *)sig_p;
 	const void *data, *sig;
 	u32 data_len, sig_len;
 	int ret;
@@ -1444,7 +1446,7 @@ __bpf_kfunc_start_defs();
  * bpf_get_file_xattr - get xattr of a file
  * @file: file to get xattr from
  * @name__str: name of the xattr
- * @value_ptr: output buffer of the xattr value
+ * @value_p: output buffer of the xattr value
  *
  * Get xattr *name__str* of *file* and store the output in *value_ptr*.
  *
@@ -1453,8 +1455,9 @@ __bpf_kfunc_start_defs();
  * Return: 0 on success, a negative value on error.
  */
 __bpf_kfunc int bpf_get_file_xattr(struct file *file, const char *name__str,
-				   struct bpf_dynptr_kern *value_ptr)
+				   struct bpf_dynptr *value_p)
 {
+	struct bpf_dynptr_kern *value_ptr = (struct bpf_dynptr_kern *)value_p;
 	struct dentry *dentry;
 	u32 value_len;
 	void *value;
diff --git a/net/core/filter.c b/net/core/filter.c
index 7c46ecba3b01b..73722790cee34 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -11859,28 +11859,34 @@ bpf_sk_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 }
 
 __bpf_kfunc_start_defs();
-__bpf_kfunc int bpf_dynptr_from_skb(struct sk_buff *skb, u64 flags,
-				    struct bpf_dynptr_kern *ptr__uninit)
+__bpf_kfunc int bpf_dynptr_from_skb(struct __sk_buff *s, u64 flags,
+				    struct bpf_dynptr *ptr__uninit)
 {
+	struct bpf_dynptr_kern *ptr = (struct bpf_dynptr_kern *)ptr__uninit;
+	struct sk_buff *skb = (struct sk_buff *)s;
+
 	if (flags) {
-		bpf_dynptr_set_null(ptr__uninit);
+		bpf_dynptr_set_null(ptr);
 		return -EINVAL;
 	}
 
-	bpf_dynptr_init(ptr__uninit, skb, BPF_DYNPTR_TYPE_SKB, 0, skb->len);
+	bpf_dynptr_init(ptr, skb, BPF_DYNPTR_TYPE_SKB, 0, skb->len);
 
 	return 0;
 }
 
-__bpf_kfunc int bpf_dynptr_from_xdp(struct xdp_buff *xdp, u64 flags,
-				    struct bpf_dynptr_kern *ptr__uninit)
+__bpf_kfunc int bpf_dynptr_from_xdp(struct xdp_md *x, u64 flags,
+				    struct bpf_dynptr *ptr__uninit)
 {
+	struct bpf_dynptr_kern *ptr = (struct bpf_dynptr_kern *)ptr__uninit;
+	struct xdp_buff *xdp = (struct xdp_buff *)x;
+
 	if (flags) {
-		bpf_dynptr_set_null(ptr__uninit);
+		bpf_dynptr_set_null(ptr);
 		return -EINVAL;
 	}
 
-	bpf_dynptr_init(ptr__uninit, xdp, BPF_DYNPTR_TYPE_XDP, 0, xdp_get_buff_len(xdp));
+	bpf_dynptr_init(ptr, xdp, BPF_DYNPTR_TYPE_XDP, 0, xdp_get_buff_len(xdp));
 
 	return 0;
 }
@@ -11906,10 +11912,11 @@ __bpf_kfunc int bpf_sock_addr_set_sun_path(struct bpf_sock_addr_kern *sa_kern,
 	return 0;
 }
 
-__bpf_kfunc int bpf_sk_assign_tcp_reqsk(struct sk_buff *skb, struct sock *sk,
+__bpf_kfunc int bpf_sk_assign_tcp_reqsk(struct __sk_buff *s, struct sock *sk,
 					struct bpf_tcp_req_attrs *attrs, int attrs__sz)
 {
 #if IS_ENABLED(CONFIG_SYN_COOKIES)
+	struct sk_buff *skb = (struct sk_buff *)s;
 	const struct request_sock_ops *ops;
 	struct inet_request_sock *ireq;
 	struct tcp_request_sock *treq;
@@ -12004,16 +12011,17 @@ __bpf_kfunc int bpf_sk_assign_tcp_reqsk(struct sk_buff *skb, struct sock *sk,
 
 __bpf_kfunc_end_defs();
 
-int bpf_dynptr_from_skb_rdonly(struct sk_buff *skb, u64 flags,
-			       struct bpf_dynptr_kern *ptr__uninit)
+int bpf_dynptr_from_skb_rdonly(struct __sk_buff *skb, u64 flags,
+			       struct bpf_dynptr *ptr__uninit)
 {
+	struct bpf_dynptr_kern *ptr = (struct bpf_dynptr_kern *)ptr__uninit;
 	int err;
 
 	err = bpf_dynptr_from_skb(skb, flags, ptr__uninit);
 	if (err)
 		return err;
 
-	bpf_dynptr_set_rdonly(ptr__uninit);
+	bpf_dynptr_set_rdonly(ptr);
 
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/progs/ip_check_defrag.c b/tools/testing/selftests/bpf/progs/ip_check_defrag.c
index 1c2b6c1616b05..645b2c9f7867c 100644
--- a/tools/testing/selftests/bpf/progs/ip_check_defrag.c
+++ b/tools/testing/selftests/bpf/progs/ip_check_defrag.c
@@ -12,7 +12,7 @@
 #define IP_OFFSET		0x1FFF
 #define NEXTHDR_FRAGMENT	44
 
-extern int bpf_dynptr_from_skb(struct sk_buff *skb, __u64 flags,
+extern int bpf_dynptr_from_skb(struct __sk_buff *skb, __u64 flags,
 			      struct bpf_dynptr *ptr__uninit) __ksym;
 extern void *bpf_dynptr_slice(const struct bpf_dynptr *ptr, uint32_t offset,
 			      void *buffer, uint32_t buffer__sz) __ksym;
@@ -42,7 +42,7 @@ static bool is_frag_v6(struct ipv6hdr *ip6h)
 	return ip6h->nexthdr == NEXTHDR_FRAGMENT;
 }
 
-static int handle_v4(struct sk_buff *skb)
+static int handle_v4(struct __sk_buff *skb)
 {
 	struct bpf_dynptr ptr;
 	u8 iph_buf[20] = {};
@@ -64,7 +64,7 @@ static int handle_v4(struct sk_buff *skb)
 	return NF_ACCEPT;
 }
 
-static int handle_v6(struct sk_buff *skb)
+static int handle_v6(struct __sk_buff *skb)
 {
 	struct bpf_dynptr ptr;
 	struct ipv6hdr *ip6h;
@@ -89,9 +89,9 @@ static int handle_v6(struct sk_buff *skb)
 SEC("netfilter")
 int defrag(struct bpf_nf_ctx *ctx)
 {
-	struct sk_buff *skb = ctx->skb;
+	struct __sk_buff *skb = (struct __sk_buff *)ctx->skb;
 
-	switch (bpf_ntohs(skb->protocol)) {
+	switch (bpf_ntohs(ctx->skb->protocol)) {
 	case ETH_P_IP:
 		return handle_v4(skb);
 	case ETH_P_IPV6:
diff --git a/tools/testing/selftests/bpf/progs/verifier_netfilter_ctx.c b/tools/testing/selftests/bpf/progs/verifier_netfilter_ctx.c
index 65bba330e7e5c..ab9f9f2620edc 100644
--- a/tools/testing/selftests/bpf/progs/verifier_netfilter_ctx.c
+++ b/tools/testing/selftests/bpf/progs/verifier_netfilter_ctx.c
@@ -79,7 +79,7 @@ int with_invalid_ctx_access_test5(struct bpf_nf_ctx *ctx)
 	return NF_ACCEPT;
 }
 
-extern int bpf_dynptr_from_skb(struct sk_buff *skb, __u64 flags,
+extern int bpf_dynptr_from_skb(struct __sk_buff *skb, __u64 flags,
                                struct bpf_dynptr *ptr__uninit) __ksym;
 extern void *bpf_dynptr_slice(const struct bpf_dynptr *ptr, uint32_t offset,
                                    void *buffer, uint32_t buffer__sz) __ksym;
@@ -90,8 +90,8 @@ __success __failure_unpriv
 __retval(0)
 int with_valid_ctx_access_test6(struct bpf_nf_ctx *ctx)
 {
+	struct __sk_buff *skb = (struct __sk_buff *)ctx->skb;
 	const struct nf_hook_state *state = ctx->state;
-	struct sk_buff *skb = ctx->skb;
 	const struct iphdr *iph;
 	const struct tcphdr *th;
 	u8 buffer_iph[20] = {};
@@ -99,7 +99,7 @@ int with_valid_ctx_access_test6(struct bpf_nf_ctx *ctx)
 	struct bpf_dynptr ptr;
 	uint8_t ihl;
 
-	if (skb->len <= 20 || bpf_dynptr_from_skb(skb, 0, &ptr))
+	if (ctx->skb->len <= 20 || bpf_dynptr_from_skb(skb, 0, &ptr))
 		return NF_ACCEPT;
 
 	iph = bpf_dynptr_slice(&ptr, 0, buffer_iph, sizeof(buffer_iph));
-- 
GitLab


From f709124dd72fe7a3f6ba7764b2ed145c55c33e47 Mon Sep 17 00:00:00 2001
From: Daniel Xu <dxu@dxuuu.xyz>
Date: Wed, 12 Jun 2024 09:58:34 -0600
Subject: [PATCH 929/950] bpf: selftests: nf: Opt out of using generated kfunc
 prototypes

The bpf-nf selftests play various games with aliased types such that
folks with CONFIG_NF_CONNTRACK=m/n configs can still build the
selftests. See commits:

1058b6a78db2 ("selftests/bpf: Do not fail build if CONFIG_NF_CONNTRACK=m/n")
92afc5329a5b ("selftests/bpf: Fix build errors if CONFIG_NF_CONNTRACK=m")

Thus, it is simpler if these selftests opt out of using generated kfunc
prototypes. The preprocessor macro this commit uses will be introduced
in the final commit.

Signed-off-by: Daniel Xu <dxu@dxuuu.xyz>
Link: https://lore.kernel.org/r/044a5b10cb3abd0d71cb1c818ee0bfc4a2239332.1718207789.git.dxu@dxuuu.xyz
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/progs/test_bpf_nf.c       | 1 +
 tools/testing/selftests/bpf/progs/test_bpf_nf_fail.c  | 1 +
 tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c | 1 +
 3 files changed, 3 insertions(+)

diff --git a/tools/testing/selftests/bpf/progs/test_bpf_nf.c b/tools/testing/selftests/bpf/progs/test_bpf_nf.c
index 0289d8ce2b80d..f7b330ddd007e 100644
--- a/tools/testing/selftests/bpf/progs/test_bpf_nf.c
+++ b/tools/testing/selftests/bpf/progs/test_bpf_nf.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#define BPF_NO_KFUNC_PROTOTYPES
 #include <vmlinux.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
diff --git a/tools/testing/selftests/bpf/progs/test_bpf_nf_fail.c b/tools/testing/selftests/bpf/progs/test_bpf_nf_fail.c
index 0e4759ab38ff1..a586f087ffeb4 100644
--- a/tools/testing/selftests/bpf/progs/test_bpf_nf_fail.c
+++ b/tools/testing/selftests/bpf/progs/test_bpf_nf_fail.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#define BPF_NO_KFUNC_PROTOTYPES
 #include <vmlinux.h>
 #include <bpf/bpf_tracing.h>
 #include <bpf/bpf_helpers.h>
diff --git a/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c b/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c
index 7ea9785738b5a..f8f5dc9f72b8c 100644
--- a/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c
+++ b/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: LGPL-2.1 OR BSD-2-Clause
 /* Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
 
+#define BPF_NO_KFUNC_PROTOTYPES
 #include "vmlinux.h"
 
 #include <bpf/bpf_helpers.h>
-- 
GitLab


From c567cba34585514f82600a10587c8813c50e3a7c Mon Sep 17 00:00:00 2001
From: Daniel Xu <dxu@dxuuu.xyz>
Date: Wed, 12 Jun 2024 09:58:35 -0600
Subject: [PATCH 930/950] bpf: selftests: xfrm: Opt out of using generated
 kfunc prototypes

The xfrm_info selftest locally defines an aliased type such that folks
with CONFIG_XFRM_INTERFACE=m/n configs can still build the selftests.
See commit aa67961f3243 ("selftests/bpf: Allow building bpf tests with CONFIG_XFRM_INTERFACE=[m|n]").

Thus, it is simpler if this selftest opts out of using enerated kfunc
prototypes. The preprocessor macro this commit uses will be introduced
in the final commit.

Signed-off-by: Daniel Xu <dxu@dxuuu.xyz>
Link: https://lore.kernel.org/r/afe0bb1c50487f52542cdd5230c4aef9e36ce250.1718207789.git.dxu@dxuuu.xyz
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/progs/xfrm_info.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/testing/selftests/bpf/progs/xfrm_info.c b/tools/testing/selftests/bpf/progs/xfrm_info.c
index f6a501fbba2be..a1d9f106c3f06 100644
--- a/tools/testing/selftests/bpf/progs/xfrm_info.c
+++ b/tools/testing/selftests/bpf/progs/xfrm_info.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#define BPF_NO_KFUNC_PROTOTYPES
 #include "vmlinux.h"
 #include "bpf_tracing_net.h"
 #include <bpf/bpf_helpers.h>
-- 
GitLab


From 770abbb5a25a5b767f1c60ba366aea503728e957 Mon Sep 17 00:00:00 2001
From: Daniel Xu <dxu@dxuuu.xyz>
Date: Wed, 12 Jun 2024 09:58:36 -0600
Subject: [PATCH 931/950] bpftool: Support dumping kfunc prototypes from BTF

This patch enables dumping kfunc prototypes from bpftool. This is useful
b/c with this patch, end users will no longer have to manually define
kfunc prototypes. For the kernel tree, this also means we can optionally
drop kfunc prototypes from:

        tools/testing/selftests/bpf/bpf_kfuncs.h
        tools/testing/selftests/bpf/bpf_experimental.h

Example usage:

        $ make PAHOLE=/home/dxu/dev/pahole/build/pahole -j30 vmlinux

        $ ./tools/bpf/bpftool/bpftool btf dump file ./vmlinux format c | rg "__ksym;" | head -3
        extern void cgroup_rstat_updated(struct cgroup *cgrp, int cpu) __weak __ksym;
        extern void cgroup_rstat_flush(struct cgroup *cgrp) __weak __ksym;
        extern struct bpf_key *bpf_lookup_user_key(u32 serial, u64 flags) __weak __ksym;

Signed-off-by: Daniel Xu <dxu@dxuuu.xyz>
Link: https://lore.kernel.org/r/bf6c08f9263c4bd9d10a717de95199d766a13f61.1718207789.git.dxu@dxuuu.xyz
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/bpf/bpftool/btf.c | 55 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 55 insertions(+)

diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c
index af047dedde389..6789c7a4d5ca1 100644
--- a/tools/bpf/bpftool/btf.c
+++ b/tools/bpf/bpftool/btf.c
@@ -20,6 +20,8 @@
 #include "json_writer.h"
 #include "main.h"
 
+#define KFUNC_DECL_TAG		"bpf_kfunc"
+
 static const char * const btf_kind_str[NR_BTF_KINDS] = {
 	[BTF_KIND_UNKN]		= "UNKNOWN",
 	[BTF_KIND_INT]		= "INT",
@@ -461,6 +463,49 @@ static int dump_btf_raw(const struct btf *btf,
 	return 0;
 }
 
+static int dump_btf_kfuncs(struct btf_dump *d, const struct btf *btf)
+{
+	LIBBPF_OPTS(btf_dump_emit_type_decl_opts, opts);
+	int cnt = btf__type_cnt(btf);
+	int i;
+
+	printf("\n/* BPF kfuncs */\n");
+	printf("#ifndef BPF_NO_KFUNC_PROTOTYPES\n");
+
+	for (i = 1; i < cnt; i++) {
+		const struct btf_type *t = btf__type_by_id(btf, i);
+		const char *name;
+		int err;
+
+		if (!btf_is_decl_tag(t))
+			continue;
+
+		if (btf_decl_tag(t)->component_idx != -1)
+			continue;
+
+		name = btf__name_by_offset(btf, t->name_off);
+		if (strncmp(name, KFUNC_DECL_TAG, sizeof(KFUNC_DECL_TAG)))
+			continue;
+
+		t = btf__type_by_id(btf, t->type);
+		if (!btf_is_func(t))
+			continue;
+
+		printf("extern ");
+
+		opts.field_name = btf__name_by_offset(btf, t->name_off);
+		err = btf_dump__emit_type_decl(d, t->type, &opts);
+		if (err)
+			return err;
+
+		printf(" __weak __ksym;\n");
+	}
+
+	printf("#endif\n\n");
+
+	return 0;
+}
+
 static void __printf(2, 0) btf_dump_printf(void *ctx,
 					   const char *fmt, va_list args)
 {
@@ -596,6 +641,12 @@ static int dump_btf_c(const struct btf *btf,
 	printf("#ifndef BPF_NO_PRESERVE_ACCESS_INDEX\n");
 	printf("#pragma clang attribute push (__attribute__((preserve_access_index)), apply_to = record)\n");
 	printf("#endif\n\n");
+	printf("#ifndef __ksym\n");
+	printf("#define __ksym __attribute__((section(\".ksyms\")))\n");
+	printf("#endif\n\n");
+	printf("#ifndef __weak\n");
+	printf("#define __weak __attribute__((weak))\n");
+	printf("#endif\n\n");
 
 	if (root_type_cnt) {
 		for (i = 0; i < root_type_cnt; i++) {
@@ -615,6 +666,10 @@ static int dump_btf_c(const struct btf *btf,
 			if (err)
 				goto done;
 		}
+
+		err = dump_btf_kfuncs(d, btf);
+		if (err)
+			goto done;
 	}
 
 	printf("#ifndef BPF_NO_PRESERVE_ACCESS_INDEX\n");
-- 
GitLab


From a3cfe84cca28f205761a0450016593b0d728165e Mon Sep 17 00:00:00 2001
From: Vadim Fedorenko <vadfed@meta.com>
Date: Thu, 6 Jun 2024 07:58:50 -0700
Subject: [PATCH 932/950] bpf: Add CHECKSUM_COMPLETE to bpf test progs

Add special flag to validate that TC BPF program properly updates
checksum information in skb.

Signed-off-by: Vadim Fedorenko <vadfed@meta.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20240606145851.229116-1-vadfed@meta.com
---
 include/uapi/linux/bpf.h       |  2 ++
 net/bpf/test_run.c             | 28 +++++++++++++++++++++++++++-
 tools/include/uapi/linux/bpf.h |  2 ++
 3 files changed, 31 insertions(+), 1 deletion(-)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 25ea393cf084b..35bcf52dbc652 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1425,6 +1425,8 @@ enum {
 #define BPF_F_TEST_RUN_ON_CPU	(1U << 0)
 /* If set, XDP frames will be transmitted after processing */
 #define BPF_F_TEST_XDP_LIVE_FRAMES	(1U << 1)
+/* If set, apply CHECKSUM_COMPLETE to skb and validate the checksum */
+#define BPF_F_TEST_SKB_CHECKSUM_COMPLETE	(1U << 2)
 
 /* type for BPF_ENABLE_STATS */
 enum bpf_stats_type {
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 36ae54f57bf57..3c965e32fc333 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -983,7 +983,8 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 	void *data;
 	int ret;
 
-	if (kattr->test.flags || kattr->test.cpu || kattr->test.batch_size)
+	if ((kattr->test.flags & ~BPF_F_TEST_SKB_CHECKSUM_COMPLETE) ||
+	    kattr->test.cpu || kattr->test.batch_size)
 		return -EINVAL;
 
 	data = bpf_test_init(kattr, kattr->test.data_size_in,
@@ -1031,6 +1032,7 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 
 	skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN);
 	__skb_put(skb, size);
+
 	if (ctx && ctx->ifindex > 1) {
 		dev = dev_get_by_index(net, ctx->ifindex);
 		if (!dev) {
@@ -1066,9 +1068,19 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 		__skb_push(skb, hh_len);
 	if (is_direct_pkt_access)
 		bpf_compute_data_pointers(skb);
+
 	ret = convert___skb_to_skb(skb, ctx);
 	if (ret)
 		goto out;
+
+	if (kattr->test.flags & BPF_F_TEST_SKB_CHECKSUM_COMPLETE) {
+		const int off = skb_network_offset(skb);
+		int len = skb->len - off;
+
+		skb->csum = skb_checksum(skb, off, len, 0);
+		skb->ip_summed = CHECKSUM_COMPLETE;
+	}
+
 	ret = bpf_test_run(prog, skb, repeat, &retval, &duration, false);
 	if (ret)
 		goto out;
@@ -1083,6 +1095,20 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 		}
 		memset(__skb_push(skb, hh_len), 0, hh_len);
 	}
+
+	if (kattr->test.flags & BPF_F_TEST_SKB_CHECKSUM_COMPLETE) {
+		const int off = skb_network_offset(skb);
+		int len = skb->len - off;
+		__wsum csum;
+
+		csum = skb_checksum(skb, off, len, 0);
+
+		if (csum_fold(skb->csum) != csum_fold(csum)) {
+			ret = -EBADMSG;
+			goto out;
+		}
+	}
+
 	convert_skb_to___skb(skb, ctx);
 
 	size = skb->len;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 25ea393cf084b..35bcf52dbc652 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1425,6 +1425,8 @@ enum {
 #define BPF_F_TEST_RUN_ON_CPU	(1U << 0)
 /* If set, XDP frames will be transmitted after processing */
 #define BPF_F_TEST_XDP_LIVE_FRAMES	(1U << 1)
+/* If set, apply CHECKSUM_COMPLETE to skb and validate the checksum */
+#define BPF_F_TEST_SKB_CHECKSUM_COMPLETE	(1U << 2)
 
 /* type for BPF_ENABLE_STATS */
 enum bpf_stats_type {
-- 
GitLab


From 041c1dc988fdffd5eb0c13f1ce5d1b3b0125f208 Mon Sep 17 00:00:00 2001
From: Vadim Fedorenko <vadfed@meta.com>
Date: Thu, 6 Jun 2024 07:58:51 -0700
Subject: [PATCH 933/950] selftests/bpf: Validate CHECKSUM_COMPLETE option

Adjust skb program test to run with checksum validation.

Signed-off-by: Vadim Fedorenko <vadfed@meta.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20240606145851.229116-2-vadfed@meta.com
---
 .../selftests/bpf/prog_tests/test_skb_pkt_end.c       |  1 +
 tools/testing/selftests/bpf/progs/skb_pkt_end.c       | 11 ++++++++++-
 2 files changed, 11 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/test_skb_pkt_end.c b/tools/testing/selftests/bpf/prog_tests/test_skb_pkt_end.c
index ae93411fd5824..09ca13bdf6ca2 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_skb_pkt_end.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_skb_pkt_end.c
@@ -11,6 +11,7 @@ static int sanity_run(struct bpf_program *prog)
 		.data_in = &pkt_v4,
 		.data_size_in = sizeof(pkt_v4),
 		.repeat = 1,
+		.flags = BPF_F_TEST_SKB_CHECKSUM_COMPLETE,
 	);
 
 	prog_fd = bpf_program__fd(prog);
diff --git a/tools/testing/selftests/bpf/progs/skb_pkt_end.c b/tools/testing/selftests/bpf/progs/skb_pkt_end.c
index db4abd2682fcf..3bb4451524a1a 100644
--- a/tools/testing/selftests/bpf/progs/skb_pkt_end.c
+++ b/tools/testing/selftests/bpf/progs/skb_pkt_end.c
@@ -33,6 +33,8 @@ int main_prog(struct __sk_buff *skb)
 	struct iphdr *ip = NULL;
 	struct tcphdr *tcp;
 	__u8 proto = 0;
+	int urg_ptr;
+	u32 offset;
 
 	if (!(ip = get_iphdr(skb)))
 		goto out;
@@ -48,7 +50,14 @@ int main_prog(struct __sk_buff *skb)
 	if (!tcp)
 		goto out;
 
-	return tcp->urg_ptr;
+	urg_ptr = tcp->urg_ptr;
+
+	/* Checksum validation part */
+	proto++;
+	offset = sizeof(struct ethhdr) + offsetof(struct iphdr, protocol);
+	bpf_skb_store_bytes(skb, offset, &proto, sizeof(proto), BPF_F_RECOMPUTE_CSUM);
+
+	return urg_ptr;
 out:
 	return -1;
 }
-- 
GitLab


From 78746f93e903d022c692b9bb3a3e2570167b2dc2 Mon Sep 17 00:00:00 2001
From: Daniel Xu <dxu@dxuuu.xyz>
Date: Thu, 13 Jun 2024 10:19:25 -0600
Subject: [PATCH 934/950] bpf: Fix bpf_dynptr documentation comments

The function argument names were changed but the doc comment was not.
Fix htmldocs build warning by updating doc comments.

Fixes: cce4c40b9606 ("bpf: treewide: Align kfunc signatures to prog point-of-view")
Signed-off-by: Daniel Xu <dxu@dxuuu.xyz>
Link: https://lore.kernel.org/r/d0b0eb05f91e12e5795966153b11998d3fc1d433.1718295425.git.dxu@dxuuu.xyz
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/helpers.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 3ac521c48bbae..229396172026a 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -2433,7 +2433,7 @@ __bpf_kfunc struct task_struct *bpf_task_from_pid(s32 pid)
 
 /**
  * bpf_dynptr_slice() - Obtain a read-only pointer to the dynptr data.
- * @ptr: The dynptr whose data slice to retrieve
+ * @p: The dynptr whose data slice to retrieve
  * @offset: Offset into the dynptr
  * @buffer__opt: User-provided buffer to copy contents into.  May be NULL
  * @buffer__szk: Size (in bytes) of the buffer if present. This is the
@@ -2504,7 +2504,7 @@ __bpf_kfunc void *bpf_dynptr_slice(const struct bpf_dynptr *p, u32 offset,
 
 /**
  * bpf_dynptr_slice_rdwr() - Obtain a writable pointer to the dynptr data.
- * @ptr: The dynptr whose data slice to retrieve
+ * @p: The dynptr whose data slice to retrieve
  * @offset: Offset into the dynptr
  * @buffer__opt: User-provided buffer to copy contents into. May be NULL
  * @buffer__szk: Size (in bytes) of the buffer if present. This is the
-- 
GitLab


From 6a8260147745fe493d733d4e5f9b327da3720905 Mon Sep 17 00:00:00 2001
From: Daniel Xu <dxu@dxuuu.xyz>
Date: Thu, 13 Jun 2024 10:19:26 -0600
Subject: [PATCH 935/950] bpf: selftests: Do not use generated kfunc prototypes
 for arena progs

When selftests are built with a new enough clang, the arena selftests
opt-in to use LLVM address_space attribute annotations for arena
pointers.

These annotations are not emitted by kfunc prototype generation. This
causes compilation errors when clang sees conflicting prototypes.

Fix by opting arena selftests out of using generated kfunc prototypes.

Fixes: 770abbb5a25a ("bpftool: Support dumping kfunc prototypes from BTF")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/r/202406131810.c1B8hTm8-lkp@intel.com/
Signed-off-by: Daniel Xu <dxu@dxuuu.xyz>
Link: https://lore.kernel.org/r/fc59a617439ceea9ad8dfbb4786843c2169496ae.1718295425.git.dxu@dxuuu.xyz
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/progs/arena_htab.c           | 1 +
 tools/testing/selftests/bpf/progs/arena_list.c           | 1 +
 tools/testing/selftests/bpf/progs/verifier_arena.c       | 1 +
 tools/testing/selftests/bpf/progs/verifier_arena_large.c | 1 +
 4 files changed, 4 insertions(+)

diff --git a/tools/testing/selftests/bpf/progs/arena_htab.c b/tools/testing/selftests/bpf/progs/arena_htab.c
index 1e6ac187a6a0c..cf938cf8c11ea 100644
--- a/tools/testing/selftests/bpf/progs/arena_htab.c
+++ b/tools/testing/selftests/bpf/progs/arena_htab.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#define BPF_NO_KFUNC_PROTOTYPES
 #include <vmlinux.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
diff --git a/tools/testing/selftests/bpf/progs/arena_list.c b/tools/testing/selftests/bpf/progs/arena_list.c
index 93bd0600eba04..3a2ddcacbea6a 100644
--- a/tools/testing/selftests/bpf/progs/arena_list.c
+++ b/tools/testing/selftests/bpf/progs/arena_list.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#define BPF_NO_KFUNC_PROTOTYPES
 #include <vmlinux.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
diff --git a/tools/testing/selftests/bpf/progs/verifier_arena.c b/tools/testing/selftests/bpf/progs/verifier_arena.c
index 93144ae6df741..67509c5d3982a 100644
--- a/tools/testing/selftests/bpf/progs/verifier_arena.c
+++ b/tools/testing/selftests/bpf/progs/verifier_arena.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
 
+#define BPF_NO_KFUNC_PROTOTYPES
 #include <vmlinux.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
diff --git a/tools/testing/selftests/bpf/progs/verifier_arena_large.c b/tools/testing/selftests/bpf/progs/verifier_arena_large.c
index ef66ea460264c..6065f862d9643 100644
--- a/tools/testing/selftests/bpf/progs/verifier_arena_large.c
+++ b/tools/testing/selftests/bpf/progs/verifier_arena_large.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
 
+#define BPF_NO_KFUNC_PROTOTYPES
 #include <vmlinux.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
-- 
GitLab


From a90797993afcb0eaf6bf47a062ff47eb3810a6d5 Mon Sep 17 00:00:00 2001
From: Vadim Fedorenko <vadfed@meta.com>
Date: Thu, 13 Jun 2024 14:18:13 -0700
Subject: [PATCH 936/950] bpf: verifier: make kfuncs args nullalble

Some arguments to kfuncs might be NULL in some cases. But currently it's
not possible to pass NULL to any BTF structures because the check for
the suffix is located after all type checks. Move it to earlier place
to allow nullable args.

Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Vadim Fedorenko <vadfed@meta.com>
Link: https://lore.kernel.org/r/20240613211817.1551967-2-vadfed@meta.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/verifier.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index acc9dd8308078..e857b08e1f2d5 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -11187,6 +11187,9 @@ get_kfunc_ptr_arg_type(struct bpf_verifier_env *env,
 	if (btf_is_prog_ctx_type(&env->log, meta->btf, t, resolve_prog_type(env->prog), argno))
 		return KF_ARG_PTR_TO_CTX;
 
+	if (is_kfunc_arg_nullable(meta->btf, &args[argno]) && register_is_null(reg))
+		return KF_ARG_PTR_TO_NULL;
+
 	if (is_kfunc_arg_alloc_obj(meta->btf, &args[argno]))
 		return KF_ARG_PTR_TO_ALLOC_BTF_ID;
 
@@ -11232,9 +11235,6 @@ get_kfunc_ptr_arg_type(struct bpf_verifier_env *env,
 	if (is_kfunc_arg_callback(env, meta->btf, &args[argno]))
 		return KF_ARG_PTR_TO_CALLBACK;
 
-	if (is_kfunc_arg_nullable(meta->btf, &args[argno]) && register_is_null(reg))
-		return KF_ARG_PTR_TO_NULL;
-
 	if (argno + 1 < nargs &&
 	    (is_kfunc_arg_mem_size(meta->btf, &args[argno + 1], &regs[regno + 1]) ||
 	     is_kfunc_arg_const_mem_size(meta->btf, &args[argno + 1], &regs[regno + 1])))
-- 
GitLab


From 65d6d61d25968d1f13a478a6f303ed8d6b978a77 Mon Sep 17 00:00:00 2001
From: Vadim Fedorenko <vadfed@meta.com>
Date: Thu, 13 Jun 2024 14:18:14 -0700
Subject: [PATCH 937/950] bpf: crypto: make state and IV dynptr nullable

Some ciphers do not require state and IV buffer, but with current
implementation 0-sized dynptr is always needed. With adjustment to
verifier we can provide NULL instead of 0-sized dynptr. Make crypto
kfuncs ready for this.

Reviewed-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Vadim Fedorenko <vadfed@meta.com>
Link: https://lore.kernel.org/r/20240613211817.1551967-3-vadfed@meta.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/crypto.c | 26 +++++++++++++-------------
 1 file changed, 13 insertions(+), 13 deletions(-)

diff --git a/kernel/bpf/crypto.c b/kernel/bpf/crypto.c
index 3c1de0e5c0bd3..94854cd9c4cc3 100644
--- a/kernel/bpf/crypto.c
+++ b/kernel/bpf/crypto.c
@@ -275,7 +275,7 @@ static int bpf_crypto_crypt(const struct bpf_crypto_ctx *ctx,
 	if (__bpf_dynptr_is_rdonly(dst))
 		return -EINVAL;
 
-	siv_len = __bpf_dynptr_size(siv);
+	siv_len = siv ? __bpf_dynptr_size(siv) : 0;
 	src_len = __bpf_dynptr_size(src);
 	dst_len = __bpf_dynptr_size(dst);
 	if (!src_len || !dst_len)
@@ -303,42 +303,42 @@ static int bpf_crypto_crypt(const struct bpf_crypto_ctx *ctx,
 
 /**
  * bpf_crypto_decrypt() - Decrypt buffer using configured context and IV provided.
- * @ctx:	The crypto context being used. The ctx must be a trusted pointer.
- * @src:	bpf_dynptr to the encrypted data. Must be a trusted pointer.
- * @dst:	bpf_dynptr to the buffer where to store the result. Must be a trusted pointer.
- * @siv:	bpf_dynptr to IV data and state data to be used by decryptor.
+ * @ctx:		The crypto context being used. The ctx must be a trusted pointer.
+ * @src:		bpf_dynptr to the encrypted data. Must be a trusted pointer.
+ * @dst:		bpf_dynptr to the buffer where to store the result. Must be a trusted pointer.
+ * @siv__nullable:	bpf_dynptr to IV data and state data to be used by decryptor. May be NULL.
  *
  * Decrypts provided buffer using IV data and the crypto context. Crypto context must be configured.
  */
 __bpf_kfunc int bpf_crypto_decrypt(struct bpf_crypto_ctx *ctx,
 				   const struct bpf_dynptr *src,
 				   const struct bpf_dynptr *dst,
-				   const struct bpf_dynptr *siv)
+				   const struct bpf_dynptr *siv__nullable)
 {
 	const struct bpf_dynptr_kern *src_kern = (struct bpf_dynptr_kern *)src;
 	const struct bpf_dynptr_kern *dst_kern = (struct bpf_dynptr_kern *)dst;
-	const struct bpf_dynptr_kern *siv_kern = (struct bpf_dynptr_kern *)siv;
+	const struct bpf_dynptr_kern *siv_kern = (struct bpf_dynptr_kern *)siv__nullable;
 
 	return bpf_crypto_crypt(ctx, src_kern, dst_kern, siv_kern, true);
 }
 
 /**
  * bpf_crypto_encrypt() - Encrypt buffer using configured context and IV provided.
- * @ctx:	The crypto context being used. The ctx must be a trusted pointer.
- * @src:	bpf_dynptr to the plain data. Must be a trusted pointer.
- * @dst:	bpf_dynptr to buffer where to store the result. Must be a trusted pointer.
- * @siv:	bpf_dynptr to IV data and state data to be used by decryptor.
+ * @ctx:		The crypto context being used. The ctx must be a trusted pointer.
+ * @src:		bpf_dynptr to the plain data. Must be a trusted pointer.
+ * @dst:		bpf_dynptr to the buffer where to store the result. Must be a trusted pointer.
+ * @siv__nullable:	bpf_dynptr to IV data and state data to be used by decryptor. May be NULL.
  *
  * Encrypts provided buffer using IV data and the crypto context. Crypto context must be configured.
  */
 __bpf_kfunc int bpf_crypto_encrypt(struct bpf_crypto_ctx *ctx,
 				   const struct bpf_dynptr *src,
 				   const struct bpf_dynptr *dst,
-				   const struct bpf_dynptr *siv)
+				   const struct bpf_dynptr *siv__nullable)
 {
 	const struct bpf_dynptr_kern *src_kern = (struct bpf_dynptr_kern *)src;
 	const struct bpf_dynptr_kern *dst_kern = (struct bpf_dynptr_kern *)dst;
-	const struct bpf_dynptr_kern *siv_kern = (struct bpf_dynptr_kern *)siv;
+	const struct bpf_dynptr_kern *siv_kern = (struct bpf_dynptr_kern *)siv__nullable;
 
 	return bpf_crypto_crypt(ctx, src_kern, dst_kern, siv_kern, false);
 }
-- 
GitLab


From 9363dc8ddc4e222c4259013ae5428070712910b9 Mon Sep 17 00:00:00 2001
From: Vadim Fedorenko <vadfed@meta.com>
Date: Thu, 13 Jun 2024 14:18:15 -0700
Subject: [PATCH 938/950] selftests: bpf: crypto: use NULL instead of 0-sized
 dynptr

Adjust selftests to use nullable option for state and IV arg.

Reviewed-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Vadim Fedorenko <vadfed@meta.com>
Link: https://lore.kernel.org/r/20240613211817.1551967-4-vadfed@meta.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../testing/selftests/bpf/progs/crypto_sanity.c  | 16 ++++------------
 1 file changed, 4 insertions(+), 12 deletions(-)

diff --git a/tools/testing/selftests/bpf/progs/crypto_sanity.c b/tools/testing/selftests/bpf/progs/crypto_sanity.c
index 1be0a3fa5efd9..645be6cddf36c 100644
--- a/tools/testing/selftests/bpf/progs/crypto_sanity.c
+++ b/tools/testing/selftests/bpf/progs/crypto_sanity.c
@@ -89,7 +89,7 @@ int decrypt_sanity(struct __sk_buff *skb)
 {
 	struct __crypto_ctx_value *v;
 	struct bpf_crypto_ctx *ctx;
-	struct bpf_dynptr psrc, pdst, iv;
+	struct bpf_dynptr psrc, pdst;
 	int err;
 
 	err = skb_dynptr_validate(skb, &psrc);
@@ -114,12 +114,8 @@ int decrypt_sanity(struct __sk_buff *skb)
 	 * production code, a percpu map should be used to store the result.
 	 */
 	bpf_dynptr_from_mem(dst, sizeof(dst), 0, &pdst);
-	/* iv dynptr has to be initialized with 0 size, but proper memory region
-	 * has to be provided anyway
-	 */
-	bpf_dynptr_from_mem(dst, 0, 0, &iv);
 
-	status = bpf_crypto_decrypt(ctx, &psrc, &pdst, &iv);
+	status = bpf_crypto_decrypt(ctx, &psrc, &pdst, NULL);
 
 	return TC_ACT_SHOT;
 }
@@ -129,7 +125,7 @@ int encrypt_sanity(struct __sk_buff *skb)
 {
 	struct __crypto_ctx_value *v;
 	struct bpf_crypto_ctx *ctx;
-	struct bpf_dynptr psrc, pdst, iv;
+	struct bpf_dynptr psrc, pdst;
 	int err;
 
 	status = 0;
@@ -156,12 +152,8 @@ int encrypt_sanity(struct __sk_buff *skb)
 	 * production code, a percpu map should be used to store the result.
 	 */
 	bpf_dynptr_from_mem(dst, sizeof(dst), 0, &pdst);
-	/* iv dynptr has to be initialized with 0 size, but proper memory region
-	 * has to be provided anyway
-	 */
-	bpf_dynptr_from_mem(dst, 0, 0, &iv);
 
-	status = bpf_crypto_encrypt(ctx, &psrc, &pdst, &iv);
+	status = bpf_crypto_encrypt(ctx, &psrc, &pdst, NULL);
 
 	return TC_ACT_SHOT;
 }
-- 
GitLab


From 9b560751f75f7b2484fa22c781be68f4f9fec2b0 Mon Sep 17 00:00:00 2001
From: Vadim Fedorenko <vadfed@meta.com>
Date: Thu, 13 Jun 2024 14:18:16 -0700
Subject: [PATCH 939/950] selftests: bpf: crypto: adjust bench to use nullable
 IV
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The bench shows some improvements, around 4% faster on decrypt.

Before:

Benchmark 'crypto-decrypt' started.
Iter   0 (325.719us): hits    5.105M/s (  5.105M/prod), drops 0.000M/s, total operations    5.105M/s
Iter   1 (-17.295us): hits    5.224M/s (  5.224M/prod), drops 0.000M/s, total operations    5.224M/s
Iter   2 (  5.504us): hits    4.630M/s (  4.630M/prod), drops 0.000M/s, total operations    4.630M/s
Iter   3 (  9.239us): hits    5.148M/s (  5.148M/prod), drops 0.000M/s, total operations    5.148M/s
Iter   4 ( 37.885us): hits    5.198M/s (  5.198M/prod), drops 0.000M/s, total operations    5.198M/s
Iter   5 (-53.282us): hits    5.167M/s (  5.167M/prod), drops 0.000M/s, total operations    5.167M/s
Iter   6 (-17.809us): hits    5.186M/s (  5.186M/prod), drops 0.000M/s, total operations    5.186M/s
Summary: hits    5.092 ± 0.228M/s (  5.092M/prod), drops    0.000 ±0.000M/s, total operations    5.092 ± 0.228M/s

After:

Benchmark 'crypto-decrypt' started.
Iter   0 (268.912us): hits    5.312M/s (  5.312M/prod), drops 0.000M/s, total operations    5.312M/s
Iter   1 (124.869us): hits    5.354M/s (  5.354M/prod), drops 0.000M/s, total operations    5.354M/s
Iter   2 (-36.801us): hits    5.334M/s (  5.334M/prod), drops 0.000M/s, total operations    5.334M/s
Iter   3 (254.628us): hits    5.334M/s (  5.334M/prod), drops 0.000M/s, total operations    5.334M/s
Iter   4 (-77.691us): hits    5.275M/s (  5.275M/prod), drops 0.000M/s, total operations    5.275M/s
Iter   5 (-164.510us): hits    5.313M/s (  5.313M/prod), drops 0.000M/s, total operations    5.313M/s
Iter   6 (-81.376us): hits    5.346M/s (  5.346M/prod), drops 0.000M/s, total operations    5.346M/s
Summary: hits    5.326 ± 0.029M/s (  5.326M/prod), drops    0.000 ±0.000M/s, total operations    5.326 ± 0.029M/s

Reviewed-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Vadim Fedorenko <vadfed@meta.com>
Link: https://lore.kernel.org/r/20240613211817.1551967-5-vadfed@meta.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/progs/crypto_bench.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/bpf/progs/crypto_bench.c b/tools/testing/selftests/bpf/progs/crypto_bench.c
index e61fe08822931..4ac956b26240d 100644
--- a/tools/testing/selftests/bpf/progs/crypto_bench.c
+++ b/tools/testing/selftests/bpf/progs/crypto_bench.c
@@ -57,7 +57,7 @@ int crypto_encrypt(struct __sk_buff *skb)
 {
 	struct __crypto_ctx_value *v;
 	struct bpf_crypto_ctx *ctx;
-	struct bpf_dynptr psrc, pdst, iv;
+	struct bpf_dynptr psrc, pdst;
 
 	v = crypto_ctx_value_lookup();
 	if (!v) {
@@ -73,9 +73,8 @@ int crypto_encrypt(struct __sk_buff *skb)
 
 	bpf_dynptr_from_skb(skb, 0, &psrc);
 	bpf_dynptr_from_mem(dst, len, 0, &pdst);
-	bpf_dynptr_from_mem(dst, 0, 0, &iv);
 
-	status = bpf_crypto_encrypt(ctx, &psrc, &pdst, &iv);
+	status = bpf_crypto_encrypt(ctx, &psrc, &pdst, NULL);
 	__sync_add_and_fetch(&hits, 1);
 
 	return 0;
@@ -84,7 +83,7 @@ int crypto_encrypt(struct __sk_buff *skb)
 SEC("tc")
 int crypto_decrypt(struct __sk_buff *skb)
 {
-	struct bpf_dynptr psrc, pdst, iv;
+	struct bpf_dynptr psrc, pdst;
 	struct __crypto_ctx_value *v;
 	struct bpf_crypto_ctx *ctx;
 
@@ -98,9 +97,8 @@ int crypto_decrypt(struct __sk_buff *skb)
 
 	bpf_dynptr_from_skb(skb, 0, &psrc);
 	bpf_dynptr_from_mem(dst, len, 0, &pdst);
-	bpf_dynptr_from_mem(dst, 0, 0, &iv);
 
-	status = bpf_crypto_decrypt(ctx, &psrc, &pdst, &iv);
+	status = bpf_crypto_decrypt(ctx, &psrc, &pdst, NULL);
 	__sync_add_and_fetch(&hits, 1);
 
 	return 0;
-- 
GitLab


From 2d45ab1eda469c802728d0a74e1601de5e71c098 Mon Sep 17 00:00:00 2001
From: Vadim Fedorenko <vadfed@meta.com>
Date: Thu, 13 Jun 2024 14:18:17 -0700
Subject: [PATCH 940/950] selftests: bpf: add testmod kfunc for nullable params

Add special test to be sure that only __nullable BTF params can be
replaced by NULL. This patch adds fake kfuncs in bpf_testmod to
properly test different params.

Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Vadim Fedorenko <vadfed@meta.com>
Link: https://lore.kernel.org/r/20240613211817.1551967-6-vadfed@meta.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../selftests/bpf/bpf_testmod/bpf_testmod.c   |  6 +++
 .../bpf/bpf_testmod/bpf_testmod_kfunc.h       |  1 +
 .../bpf/prog_tests/kfunc_param_nullable.c     | 11 +++++
 .../bpf/progs/test_kfunc_param_nullable.c     | 43 +++++++++++++++++++
 4 files changed, 61 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/kfunc_param_nullable.c
 create mode 100644 tools/testing/selftests/bpf/progs/test_kfunc_param_nullable.c

diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
index 0a09732cde4b7..49f9a311e49b3 100644
--- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
+++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
@@ -154,6 +154,11 @@ __bpf_kfunc void bpf_kfunc_common_test(void)
 {
 }
 
+__bpf_kfunc void bpf_kfunc_dynptr_test(struct bpf_dynptr *ptr,
+				       struct bpf_dynptr *ptr__nullable)
+{
+}
+
 struct bpf_testmod_btf_type_tag_1 {
 	int a;
 };
@@ -363,6 +368,7 @@ BTF_ID_FLAGS(func, bpf_iter_testmod_seq_new, KF_ITER_NEW)
 BTF_ID_FLAGS(func, bpf_iter_testmod_seq_next, KF_ITER_NEXT | KF_RET_NULL)
 BTF_ID_FLAGS(func, bpf_iter_testmod_seq_destroy, KF_ITER_DESTROY)
 BTF_ID_FLAGS(func, bpf_kfunc_common_test)
+BTF_ID_FLAGS(func, bpf_kfunc_dynptr_test)
 BTF_KFUNCS_END(bpf_testmod_common_kfunc_ids)
 
 static const struct btf_kfunc_id_set bpf_testmod_common_kfunc_set = {
diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod_kfunc.h b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod_kfunc.h
index b0d586a6751fa..f9809517e7fa0 100644
--- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod_kfunc.h
+++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod_kfunc.h
@@ -134,4 +134,5 @@ int bpf_kfunc_call_sock_sendmsg(struct sendmsg_args *args) __ksym;
 int bpf_kfunc_call_kernel_getsockname(struct addr_args *args) __ksym;
 int bpf_kfunc_call_kernel_getpeername(struct addr_args *args) __ksym;
 
+void bpf_kfunc_dynptr_test(struct bpf_dynptr *ptr, struct bpf_dynptr *ptr__nullable) __ksym;
 #endif /* _BPF_TESTMOD_KFUNC_H */
diff --git a/tools/testing/selftests/bpf/prog_tests/kfunc_param_nullable.c b/tools/testing/selftests/bpf/prog_tests/kfunc_param_nullable.c
new file mode 100644
index 0000000000000..c8f4dcaac7c76
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/kfunc_param_nullable.c
@@ -0,0 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/* Copyright (c) 2024 Meta Platforms, Inc */
+
+#include <test_progs.h>
+#include "test_kfunc_param_nullable.skel.h"
+
+void test_kfunc_param_nullable(void)
+{
+	RUN_TESTS(test_kfunc_param_nullable);
+}
diff --git a/tools/testing/selftests/bpf/progs/test_kfunc_param_nullable.c b/tools/testing/selftests/bpf/progs/test_kfunc_param_nullable.c
new file mode 100644
index 0000000000000..7c75e9b8f4554
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_kfunc_param_nullable.c
@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc */
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+#include "bpf_kfuncs.h"
+#include "../bpf_testmod/bpf_testmod_kfunc.h"
+
+SEC("tc")
+int kfunc_dynptr_nullable_test1(struct __sk_buff *skb)
+{
+	struct bpf_dynptr data;
+
+	bpf_dynptr_from_skb(skb, 0, &data);
+	bpf_kfunc_dynptr_test(&data, NULL);
+
+	return 0;
+}
+
+SEC("tc")
+int kfunc_dynptr_nullable_test2(struct __sk_buff *skb)
+{
+	struct bpf_dynptr data;
+
+	bpf_dynptr_from_skb(skb, 0, &data);
+	bpf_kfunc_dynptr_test(&data, &data);
+
+	return 0;
+}
+
+SEC("tc")
+__failure __msg("expected pointer to stack or dynptr_ptr")
+int kfunc_dynptr_nullable_test3(struct __sk_buff *skb)
+{
+	struct bpf_dynptr data;
+
+	bpf_dynptr_from_skb(skb, 0, &data);
+	bpf_kfunc_dynptr_test(NULL, &data);
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
-- 
GitLab


From 124e8c2b1b5d08a10d3a44ed082eaaf98a78c91f Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Wed, 12 Jun 2024 18:38:12 -0700
Subject: [PATCH 941/950] bpf: Relax tuple len requirement for sk helpers.

__bpf_skc_lookup() safely handles incorrect values of tuple len,
hence we can allow zero to be passed as tuple len.
This patch alone doesn't make an observable verifier difference.
It's a trivial improvement that might simplify bpf programs.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/bpf/20240613013815.953-2-alexei.starovoitov@gmail.com
---
 net/core/filter.c | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/net/core/filter.c b/net/core/filter.c
index 73722790cee34..f1c37c85b8580 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -6815,7 +6815,7 @@ static const struct bpf_func_proto bpf_skc_lookup_tcp_proto = {
 	.ret_type	= RET_PTR_TO_SOCK_COMMON_OR_NULL,
 	.arg1_type	= ARG_PTR_TO_CTX,
 	.arg2_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
-	.arg3_type	= ARG_CONST_SIZE,
+	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
 	.arg4_type	= ARG_ANYTHING,
 	.arg5_type	= ARG_ANYTHING,
 };
@@ -6834,7 +6834,7 @@ static const struct bpf_func_proto bpf_sk_lookup_tcp_proto = {
 	.ret_type	= RET_PTR_TO_SOCKET_OR_NULL,
 	.arg1_type	= ARG_PTR_TO_CTX,
 	.arg2_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
-	.arg3_type	= ARG_CONST_SIZE,
+	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
 	.arg4_type	= ARG_ANYTHING,
 	.arg5_type	= ARG_ANYTHING,
 };
@@ -6853,7 +6853,7 @@ static const struct bpf_func_proto bpf_sk_lookup_udp_proto = {
 	.ret_type	= RET_PTR_TO_SOCKET_OR_NULL,
 	.arg1_type	= ARG_PTR_TO_CTX,
 	.arg2_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
-	.arg3_type	= ARG_CONST_SIZE,
+	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
 	.arg4_type	= ARG_ANYTHING,
 	.arg5_type	= ARG_ANYTHING,
 };
@@ -6877,7 +6877,7 @@ static const struct bpf_func_proto bpf_tc_skc_lookup_tcp_proto = {
 	.ret_type	= RET_PTR_TO_SOCK_COMMON_OR_NULL,
 	.arg1_type	= ARG_PTR_TO_CTX,
 	.arg2_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
-	.arg3_type	= ARG_CONST_SIZE,
+	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
 	.arg4_type	= ARG_ANYTHING,
 	.arg5_type	= ARG_ANYTHING,
 };
@@ -6901,7 +6901,7 @@ static const struct bpf_func_proto bpf_tc_sk_lookup_tcp_proto = {
 	.ret_type	= RET_PTR_TO_SOCKET_OR_NULL,
 	.arg1_type	= ARG_PTR_TO_CTX,
 	.arg2_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
-	.arg3_type	= ARG_CONST_SIZE,
+	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
 	.arg4_type	= ARG_ANYTHING,
 	.arg5_type	= ARG_ANYTHING,
 };
@@ -6925,7 +6925,7 @@ static const struct bpf_func_proto bpf_tc_sk_lookup_udp_proto = {
 	.ret_type	= RET_PTR_TO_SOCKET_OR_NULL,
 	.arg1_type	= ARG_PTR_TO_CTX,
 	.arg2_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
-	.arg3_type	= ARG_CONST_SIZE,
+	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
 	.arg4_type	= ARG_ANYTHING,
 	.arg5_type	= ARG_ANYTHING,
 };
@@ -6963,7 +6963,7 @@ static const struct bpf_func_proto bpf_xdp_sk_lookup_udp_proto = {
 	.ret_type       = RET_PTR_TO_SOCKET_OR_NULL,
 	.arg1_type      = ARG_PTR_TO_CTX,
 	.arg2_type      = ARG_PTR_TO_MEM | MEM_RDONLY,
-	.arg3_type      = ARG_CONST_SIZE,
+	.arg3_type      = ARG_CONST_SIZE_OR_ZERO,
 	.arg4_type      = ARG_ANYTHING,
 	.arg5_type      = ARG_ANYTHING,
 };
@@ -6987,7 +6987,7 @@ static const struct bpf_func_proto bpf_xdp_skc_lookup_tcp_proto = {
 	.ret_type       = RET_PTR_TO_SOCK_COMMON_OR_NULL,
 	.arg1_type      = ARG_PTR_TO_CTX,
 	.arg2_type      = ARG_PTR_TO_MEM | MEM_RDONLY,
-	.arg3_type      = ARG_CONST_SIZE,
+	.arg3_type      = ARG_CONST_SIZE_OR_ZERO,
 	.arg4_type      = ARG_ANYTHING,
 	.arg5_type      = ARG_ANYTHING,
 };
@@ -7011,7 +7011,7 @@ static const struct bpf_func_proto bpf_xdp_sk_lookup_tcp_proto = {
 	.ret_type       = RET_PTR_TO_SOCKET_OR_NULL,
 	.arg1_type      = ARG_PTR_TO_CTX,
 	.arg2_type      = ARG_PTR_TO_MEM | MEM_RDONLY,
-	.arg3_type      = ARG_CONST_SIZE,
+	.arg3_type      = ARG_CONST_SIZE_OR_ZERO,
 	.arg4_type      = ARG_ANYTHING,
 	.arg5_type      = ARG_ANYTHING,
 };
@@ -7031,7 +7031,7 @@ static const struct bpf_func_proto bpf_sock_addr_skc_lookup_tcp_proto = {
 	.ret_type	= RET_PTR_TO_SOCK_COMMON_OR_NULL,
 	.arg1_type	= ARG_PTR_TO_CTX,
 	.arg2_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
-	.arg3_type	= ARG_CONST_SIZE,
+	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
 	.arg4_type	= ARG_ANYTHING,
 	.arg5_type	= ARG_ANYTHING,
 };
@@ -7050,7 +7050,7 @@ static const struct bpf_func_proto bpf_sock_addr_sk_lookup_tcp_proto = {
 	.ret_type	= RET_PTR_TO_SOCKET_OR_NULL,
 	.arg1_type	= ARG_PTR_TO_CTX,
 	.arg2_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
-	.arg3_type	= ARG_CONST_SIZE,
+	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
 	.arg4_type	= ARG_ANYTHING,
 	.arg5_type	= ARG_ANYTHING,
 };
@@ -7069,7 +7069,7 @@ static const struct bpf_func_proto bpf_sock_addr_sk_lookup_udp_proto = {
 	.ret_type	= RET_PTR_TO_SOCKET_OR_NULL,
 	.arg1_type	= ARG_PTR_TO_CTX,
 	.arg2_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
-	.arg3_type	= ARG_CONST_SIZE,
+	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
 	.arg4_type	= ARG_ANYTHING,
 	.arg5_type	= ARG_ANYTHING,
 };
-- 
GitLab


From 98d7ca374ba4b39e7535613d40e159f09ca14da2 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Wed, 12 Jun 2024 18:38:13 -0700
Subject: [PATCH 942/950] bpf: Track delta between "linked" registers.

Compilers can generate the code
  r1 = r2
  r1 += 0x1
  if r2 < 1000 goto ...
  use knowledge of r2 range in subsequent r1 operations

So remember constant delta between r2 and r1 and update r1 after 'if' condition.

Unfortunately LLVM still uses this pattern for loops with 'can_loop' construct:
for (i = 0; i < 1000 && can_loop; i++)

The "undo" pass was introduced in LLVM
https://reviews.llvm.org/D121937
to prevent this optimization, but it cannot cover all cases.
Instead of fighting middle end optimizer in BPF backend teach the verifier
about this pattern.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/bpf/20240613013815.953-3-alexei.starovoitov@gmail.com
---
 include/linux/bpf_verifier.h                  | 12 ++-
 kernel/bpf/log.c                              |  4 +-
 kernel/bpf/verifier.c                         | 95 ++++++++++++++++---
 .../testing/selftests/bpf/verifier/precise.c  | 22 ++---
 4 files changed, 109 insertions(+), 24 deletions(-)

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 50aa87f8d77ff..2b54e25d23645 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -73,7 +73,10 @@ enum bpf_iter_state {
 struct bpf_reg_state {
 	/* Ordering of fields matters.  See states_equal() */
 	enum bpf_reg_type type;
-	/* Fixed part of pointer offset, pointer types only */
+	/*
+	 * Fixed part of pointer offset, pointer types only.
+	 * Or constant delta between "linked" scalars with the same ID.
+	 */
 	s32 off;
 	union {
 		/* valid when type == PTR_TO_PACKET */
@@ -167,6 +170,13 @@ struct bpf_reg_state {
 	 * Similarly to dynptrs, we use ID to track "belonging" of a reference
 	 * to a specific instance of bpf_iter.
 	 */
+	/*
+	 * Upper bit of ID is used to remember relationship between "linked"
+	 * registers. Example:
+	 * r1 = r2;    both will have r1->id == r2->id == N
+	 * r1 += 10;   r1->id == N | BPF_ADD_CONST and r1->off == 10
+	 */
+#define BPF_ADD_CONST (1U << 31)
 	u32 id;
 	/* PTR_TO_SOCKET and PTR_TO_TCP_SOCK could be a ptr returned
 	 * from a pointer-cast helper, bpf_sk_fullsock() and
diff --git a/kernel/bpf/log.c b/kernel/bpf/log.c
index 4bd8f17a9f240..3f4ae92e549ff 100644
--- a/kernel/bpf/log.c
+++ b/kernel/bpf/log.c
@@ -708,7 +708,9 @@ static void print_reg_state(struct bpf_verifier_env *env,
 		verbose(env, "%s", btf_type_name(reg->btf, reg->btf_id));
 	verbose(env, "(");
 	if (reg->id)
-		verbose_a("id=%d", reg->id);
+		verbose_a("id=%d", reg->id & ~BPF_ADD_CONST);
+	if (reg->id & BPF_ADD_CONST)
+		verbose(env, "%+d", reg->off);
 	if (reg->ref_obj_id)
 		verbose_a("ref_obj_id=%d", reg->ref_obj_id);
 	if (type_is_non_owning_ref(reg->type))
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index e857b08e1f2d5..dcbbf5f64c5de 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -3991,7 +3991,7 @@ static bool idset_contains(struct bpf_idset *s, u32 id)
 	u32 i;
 
 	for (i = 0; i < s->count; ++i)
-		if (s->ids[i] == id)
+		if (s->ids[i] == (id & ~BPF_ADD_CONST))
 			return true;
 
 	return false;
@@ -4001,7 +4001,7 @@ static int idset_push(struct bpf_idset *s, u32 id)
 {
 	if (WARN_ON_ONCE(s->count >= ARRAY_SIZE(s->ids)))
 		return -EFAULT;
-	s->ids[s->count++] = id;
+	s->ids[s->count++] = id & ~BPF_ADD_CONST;
 	return 0;
 }
 
@@ -4438,8 +4438,20 @@ static bool __is_pointer_value(bool allow_ptr_leaks,
 static void assign_scalar_id_before_mov(struct bpf_verifier_env *env,
 					struct bpf_reg_state *src_reg)
 {
-	if (src_reg->type == SCALAR_VALUE && !src_reg->id &&
-	    !tnum_is_const(src_reg->var_off))
+	if (src_reg->type != SCALAR_VALUE)
+		return;
+
+	if (src_reg->id & BPF_ADD_CONST) {
+		/*
+		 * The verifier is processing rX = rY insn and
+		 * rY->id has special linked register already.
+		 * Cleared it, since multiple rX += const are not supported.
+		 */
+		src_reg->id = 0;
+		src_reg->off = 0;
+	}
+
+	if (!src_reg->id && !tnum_is_const(src_reg->var_off))
 		/* Ensure that src_reg has a valid ID that will be copied to
 		 * dst_reg and then will be used by find_equal_scalars() to
 		 * propagate min/max range.
@@ -14042,6 +14054,7 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 	struct bpf_func_state *state = vstate->frame[vstate->curframe];
 	struct bpf_reg_state *regs = state->regs, *dst_reg, *src_reg;
 	struct bpf_reg_state *ptr_reg = NULL, off_reg = {0};
+	bool alu32 = (BPF_CLASS(insn->code) != BPF_ALU64);
 	u8 opcode = BPF_OP(insn->code);
 	int err;
 
@@ -14064,11 +14077,7 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 
 	if (dst_reg->type != SCALAR_VALUE)
 		ptr_reg = dst_reg;
-	else
-		/* Make sure ID is cleared otherwise dst_reg min/max could be
-		 * incorrectly propagated into other registers by find_equal_scalars()
-		 */
-		dst_reg->id = 0;
+
 	if (BPF_SRC(insn->code) == BPF_X) {
 		src_reg = &regs[insn->src_reg];
 		if (src_reg->type != SCALAR_VALUE) {
@@ -14132,7 +14141,43 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 		verbose(env, "verifier internal error: no src_reg\n");
 		return -EINVAL;
 	}
-	return adjust_scalar_min_max_vals(env, insn, dst_reg, *src_reg);
+	err = adjust_scalar_min_max_vals(env, insn, dst_reg, *src_reg);
+	if (err)
+		return err;
+	/*
+	 * Compilers can generate the code
+	 * r1 = r2
+	 * r1 += 0x1
+	 * if r2 < 1000 goto ...
+	 * use r1 in memory access
+	 * So remember constant delta between r2 and r1 and update r1 after
+	 * 'if' condition.
+	 */
+	if (env->bpf_capable && BPF_OP(insn->code) == BPF_ADD &&
+	    dst_reg->id && is_reg_const(src_reg, alu32)) {
+		u64 val = reg_const_value(src_reg, alu32);
+
+		if ((dst_reg->id & BPF_ADD_CONST) ||
+		    /* prevent overflow in find_equal_scalars() later */
+		    val > (u32)S32_MAX) {
+			/*
+			 * If the register already went through rX += val
+			 * we cannot accumulate another val into rx->off.
+			 */
+			dst_reg->off = 0;
+			dst_reg->id = 0;
+		} else {
+			dst_reg->id |= BPF_ADD_CONST;
+			dst_reg->off = val;
+		}
+	} else {
+		/*
+		 * Make sure ID is cleared otherwise dst_reg min/max could be
+		 * incorrectly propagated into other registers by find_equal_scalars()
+		 */
+		dst_reg->id = 0;
+	}
+	return 0;
 }
 
 /* check validity of 32-bit and 64-bit arithmetic operations */
@@ -15104,12 +15149,36 @@ static bool try_match_pkt_pointers(const struct bpf_insn *insn,
 static void find_equal_scalars(struct bpf_verifier_state *vstate,
 			       struct bpf_reg_state *known_reg)
 {
+	struct bpf_reg_state fake_reg;
 	struct bpf_func_state *state;
 	struct bpf_reg_state *reg;
 
 	bpf_for_each_reg_in_vstate(vstate, state, reg, ({
-		if (reg->type == SCALAR_VALUE && reg->id == known_reg->id)
+		if (reg->type != SCALAR_VALUE || reg == known_reg)
+			continue;
+		if ((reg->id & ~BPF_ADD_CONST) != (known_reg->id & ~BPF_ADD_CONST))
+			continue;
+		if ((!(reg->id & BPF_ADD_CONST) && !(known_reg->id & BPF_ADD_CONST)) ||
+		    reg->off == known_reg->off) {
 			copy_register_state(reg, known_reg);
+		} else {
+			s32 saved_off = reg->off;
+
+			fake_reg.type = SCALAR_VALUE;
+			__mark_reg_known(&fake_reg, (s32)reg->off - (s32)known_reg->off);
+
+			/* reg = known_reg; reg += delta */
+			copy_register_state(reg, known_reg);
+			/*
+			 * Must preserve off, id and add_const flag,
+			 * otherwise another find_equal_scalars() will be incorrect.
+			 */
+			reg->off = saved_off;
+
+			scalar32_min_max_add(reg, &fake_reg);
+			scalar_min_max_add(reg, &fake_reg);
+			reg->var_off = tnum_add(reg->var_off, fake_reg.var_off);
+		}
 	}));
 }
 
@@ -16738,6 +16807,10 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold,
 		}
 		if (!rold->precise && exact == NOT_EXACT)
 			return true;
+		if ((rold->id & BPF_ADD_CONST) != (rcur->id & BPF_ADD_CONST))
+			return false;
+		if ((rold->id & BPF_ADD_CONST) && (rold->off != rcur->off))
+			return false;
 		/* Why check_ids() for scalar registers?
 		 *
 		 * Consider the following BPF code:
diff --git a/tools/testing/selftests/bpf/verifier/precise.c b/tools/testing/selftests/bpf/verifier/precise.c
index 0a9293a572115..90643ccc221d1 100644
--- a/tools/testing/selftests/bpf/verifier/precise.c
+++ b/tools/testing/selftests/bpf/verifier/precise.c
@@ -39,12 +39,12 @@
 	.result = VERBOSE_ACCEPT,
 	.errstr =
 	"mark_precise: frame0: last_idx 26 first_idx 20\
-	mark_precise: frame0: regs=r2 stack= before 25\
-	mark_precise: frame0: regs=r2 stack= before 24\
-	mark_precise: frame0: regs=r2 stack= before 23\
-	mark_precise: frame0: regs=r2 stack= before 22\
-	mark_precise: frame0: regs=r2 stack= before 20\
-	mark_precise: frame0: parent state regs=r2 stack=:\
+	mark_precise: frame0: regs=r2,r9 stack= before 25\
+	mark_precise: frame0: regs=r2,r9 stack= before 24\
+	mark_precise: frame0: regs=r2,r9 stack= before 23\
+	mark_precise: frame0: regs=r2,r9 stack= before 22\
+	mark_precise: frame0: regs=r2,r9 stack= before 20\
+	mark_precise: frame0: parent state regs=r2,r9 stack=:\
 	mark_precise: frame0: last_idx 19 first_idx 10\
 	mark_precise: frame0: regs=r2,r9 stack= before 19\
 	mark_precise: frame0: regs=r9 stack= before 18\
@@ -100,11 +100,11 @@
 	.errstr =
 	"26: (85) call bpf_probe_read_kernel#113\
 	mark_precise: frame0: last_idx 26 first_idx 22\
-	mark_precise: frame0: regs=r2 stack= before 25\
-	mark_precise: frame0: regs=r2 stack= before 24\
-	mark_precise: frame0: regs=r2 stack= before 23\
-	mark_precise: frame0: regs=r2 stack= before 22\
-	mark_precise: frame0: parent state regs=r2 stack=:\
+	mark_precise: frame0: regs=r2,r9 stack= before 25\
+	mark_precise: frame0: regs=r2,r9 stack= before 24\
+	mark_precise: frame0: regs=r2,r9 stack= before 23\
+	mark_precise: frame0: regs=r2,r9 stack= before 22\
+	mark_precise: frame0: parent state regs=r2,r9 stack=:\
 	mark_precise: frame0: last_idx 20 first_idx 20\
 	mark_precise: frame0: regs=r2,r9 stack= before 20\
 	mark_precise: frame0: parent state regs=r2,r9 stack=:\
-- 
GitLab


From 6870bdb3f4f2991193449f9de57109b3e263f55c Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Wed, 12 Jun 2024 18:38:14 -0700
Subject: [PATCH 943/950] bpf: Support can_loop/cond_break on big endian

Add big endian support for can_loop/cond_break macros.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/bpf/20240613013815.953-4-alexei.starovoitov@gmail.com
---
 .../testing/selftests/bpf/bpf_experimental.h  | 28 +++++++++++++++++++
 1 file changed, 28 insertions(+)

diff --git a/tools/testing/selftests/bpf/bpf_experimental.h b/tools/testing/selftests/bpf/bpf_experimental.h
index 8ee7a00b7c828..eede6fc2ccb40 100644
--- a/tools/testing/selftests/bpf/bpf_experimental.h
+++ b/tools/testing/selftests/bpf/bpf_experimental.h
@@ -351,6 +351,7 @@ l_true:												\
 	l_continue:;					\
 	})
 #else
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
 #define can_loop					\
 	({ __label__ l_break, l_continue;		\
 	bool ret = true;				\
@@ -376,6 +377,33 @@ l_true:												\
 	l_break: break;					\
 	l_continue:;					\
 	})
+#else
+#define can_loop					\
+	({ __label__ l_break, l_continue;		\
+	bool ret = true;				\
+	asm volatile goto("1:.byte 0xe5;		\
+		      .byte 0;				\
+		      .long (((%l[l_break] - 1b - 8) / 8) & 0xffff) << 16;	\
+		      .short 0"				\
+		      :::: l_break);			\
+	goto l_continue;				\
+	l_break: ret = false;				\
+	l_continue:;					\
+	ret;						\
+	})
+
+#define cond_break					\
+	({ __label__ l_break, l_continue;		\
+	asm volatile goto("1:.byte 0xe5;		\
+		      .byte 0;				\
+		      .long (((%l[l_break] - 1b - 8) / 8) & 0xffff) << 16;	\
+		      .short 0"				\
+		      :::: l_break);			\
+	goto l_continue;				\
+	l_break: break;					\
+	l_continue:;					\
+	})
+#endif
 #endif
 
 #ifndef bpf_nop_mov
-- 
GitLab


From dedf56d775c0bebbc3003bfb988dddaf0a583c28 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Wed, 12 Jun 2024 18:38:15 -0700
Subject: [PATCH 944/950] selftests/bpf: Add tests for add_const

Improve arena based tests and add several C and asm tests
with specific pattern.
These tests would have failed without add_const verifier support.

Also add several loop_inside_iter*() tests that are not related to add_const,
but nice to have.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20240613013815.953-5-alexei.starovoitov@gmail.com
---
 .../testing/selftests/bpf/progs/arena_htab.c  |  16 +-
 .../bpf/progs/verifier_iterating_callbacks.c  | 236 ++++++++++++++++++
 2 files changed, 249 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/bpf/progs/arena_htab.c b/tools/testing/selftests/bpf/progs/arena_htab.c
index cf938cf8c11ea..81eaa94afeb01 100644
--- a/tools/testing/selftests/bpf/progs/arena_htab.c
+++ b/tools/testing/selftests/bpf/progs/arena_htab.c
@@ -19,25 +19,35 @@ void __arena *htab_for_user;
 bool skip = false;
 
 int zero = 0;
+char __arena arr1[100000];
+char arr2[1000];
 
 SEC("syscall")
 int arena_htab_llvm(void *ctx)
 {
 #if defined(__BPF_FEATURE_ADDR_SPACE_CAST) || defined(BPF_ARENA_FORCE_ASM)
 	struct htab __arena *htab;
+	char __arena *arr = arr1;
 	__u64 i;
 
 	htab = bpf_alloc(sizeof(*htab));
 	cast_kern(htab);
 	htab_init(htab);
 
+	cast_kern(arr);
+
 	/* first run. No old elems in the table */
-	for (i = zero; i < 1000; i++)
+	for (i = zero; i < 100000 && can_loop; i++) {
 		htab_update_elem(htab, i, i);
+		arr[i] = i;
+	}
 
-	/* should replace all elems with new ones */
-	for (i = zero; i < 1000; i++)
+	/* should replace some elems with new ones */
+	for (i = zero; i < 1000 && can_loop; i++) {
 		htab_update_elem(htab, i, i);
+		/* Access mem to make the verifier use bounded loop logic */
+		arr2[i] = i;
+	}
 	cast_user(htab);
 	htab_for_user = htab;
 #else
diff --git a/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c b/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c
index bd676d7e615fd..53679252e8a1d 100644
--- a/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c
+++ b/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c
@@ -405,4 +405,240 @@ int cond_break5(const void *ctx)
 	return cnt1 > 1 && cnt2 > 1 ? 1 : 0;
 }
 
+#define ARR2_SZ 1000
+SEC(".data.arr2")
+char arr2[ARR2_SZ];
+
+SEC("socket")
+__success __flag(BPF_F_TEST_STATE_FREQ)
+int loop_inside_iter(const void *ctx)
+{
+	struct bpf_iter_num it;
+	int *v, sum = 0;
+	__u64 i = 0;
+
+	bpf_iter_num_new(&it, 0, ARR2_SZ);
+	while ((v = bpf_iter_num_next(&it))) {
+		if (i < ARR2_SZ)
+			sum += arr2[i++];
+	}
+	bpf_iter_num_destroy(&it);
+	return sum;
+}
+
+SEC("socket")
+__success __flag(BPF_F_TEST_STATE_FREQ)
+int loop_inside_iter_signed(const void *ctx)
+{
+	struct bpf_iter_num it;
+	int *v, sum = 0;
+	long i = 0;
+
+	bpf_iter_num_new(&it, 0, ARR2_SZ);
+	while ((v = bpf_iter_num_next(&it))) {
+		if (i < ARR2_SZ && i >= 0)
+			sum += arr2[i++];
+	}
+	bpf_iter_num_destroy(&it);
+	return sum;
+}
+
+volatile const int limit = ARR2_SZ;
+
+SEC("socket")
+__success __flag(BPF_F_TEST_STATE_FREQ)
+int loop_inside_iter_volatile_limit(const void *ctx)
+{
+	struct bpf_iter_num it;
+	int *v, sum = 0;
+	__u64 i = 0;
+
+	bpf_iter_num_new(&it, 0, ARR2_SZ);
+	while ((v = bpf_iter_num_next(&it))) {
+		if (i < limit)
+			sum += arr2[i++];
+	}
+	bpf_iter_num_destroy(&it);
+	return sum;
+}
+
+#define ARR_LONG_SZ 1000
+
+SEC(".data.arr_long")
+long arr_long[ARR_LONG_SZ];
+
+SEC("socket")
+__success
+int test1(const void *ctx)
+{
+	long i;
+
+	for (i = 0; i < ARR_LONG_SZ && can_loop; i++)
+		arr_long[i] = i;
+	return 0;
+}
+
+SEC("socket")
+__success
+int test2(const void *ctx)
+{
+	__u64 i;
+
+	for (i = zero; i < ARR_LONG_SZ && can_loop; i++) {
+		barrier_var(i);
+		arr_long[i] = i;
+	}
+	return 0;
+}
+
+SEC(".data.arr_foo")
+struct {
+	int a;
+	int b;
+} arr_foo[ARR_LONG_SZ];
+
+SEC("socket")
+__success
+int test3(const void *ctx)
+{
+	__u64 i;
+
+	for (i = zero; i < ARR_LONG_SZ && can_loop; i++) {
+		barrier_var(i);
+		arr_foo[i].a = i;
+		arr_foo[i].b = i;
+	}
+	return 0;
+}
+
+SEC("socket")
+__success
+int test4(const void *ctx)
+{
+	long i;
+
+	for (i = zero + ARR_LONG_SZ - 1; i < ARR_LONG_SZ && i >= 0 && can_loop; i--) {
+		barrier_var(i);
+		arr_foo[i].a = i;
+		arr_foo[i].b = i;
+	}
+	return 0;
+}
+
+char buf[10] SEC(".data.buf");
+
+SEC("socket")
+__description("check add const")
+__success
+__naked void check_add_const(void)
+{
+	/* typical LLVM generated loop with may_goto */
+	asm volatile ("			\
+	call %[bpf_ktime_get_ns];	\
+	if r0 > 9 goto l1_%=;		\
+l0_%=:	r1 = %[buf];			\
+	r2 = r0;			\
+	r1 += r2;			\
+	r3 = *(u8 *)(r1 +0);		\
+	.byte 0xe5; /* may_goto */	\
+	.byte 0; /* regs */		\
+	.short 4; /* off of l1_%=: */	\
+	.long 0; /* imm */		\
+	r0 = r2;			\
+	r0 += 1;			\
+	if r2 < 9 goto l0_%=;		\
+	exit;				\
+l1_%=:	r0 = 0;				\
+	exit;				\
+"	:
+	: __imm(bpf_ktime_get_ns),
+	  __imm_ptr(buf)
+	: __clobber_common);
+}
+
+SEC("socket")
+__failure
+__msg("*(u8 *)(r7 +0) = r0")
+__msg("invalid access to map value, value_size=10 off=10 size=1")
+__naked void check_add_const_3regs(void)
+{
+	asm volatile (
+	"r6 = %[buf];"
+	"r7 = %[buf];"
+	"call %[bpf_ktime_get_ns];"
+	"r1 = r0;"              /* link r0.id == r1.id == r2.id */
+	"r2 = r0;"
+	"r1 += 1;"              /* r1 == r0+1 */
+	"r2 += 2;"              /* r2 == r0+2 */
+	"if r0 > 8 goto 1f;"    /* r0 range [0, 8]  */
+	"r6 += r1;"             /* r1 range [1, 9]  */
+	"r7 += r2;"             /* r2 range [2, 10] */
+	"*(u8 *)(r6 +0) = r0;"  /* safe, within bounds   */
+	"*(u8 *)(r7 +0) = r0;"  /* unsafe, out of bounds */
+	"1: exit;"
+	:
+	: __imm(bpf_ktime_get_ns),
+	  __imm_ptr(buf)
+	: __clobber_common);
+}
+
+SEC("socket")
+__failure
+__msg("*(u8 *)(r8 -1) = r0")
+__msg("invalid access to map value, value_size=10 off=10 size=1")
+__naked void check_add_const_3regs_2if(void)
+{
+	asm volatile (
+	"r6 = %[buf];"
+	"r7 = %[buf];"
+	"r8 = %[buf];"
+	"call %[bpf_ktime_get_ns];"
+	"if r0 < 2 goto 1f;"
+	"r1 = r0;"              /* link r0.id == r1.id == r2.id */
+	"r2 = r0;"
+	"r1 += 1;"              /* r1 == r0+1 */
+	"r2 += 2;"              /* r2 == r0+2 */
+	"if r2 > 11 goto 1f;"   /* r2 range [0, 11] -> r0 range [-2, 9]; r1 range [-1, 10] */
+	"if r0 s< 0 goto 1f;"   /* r0 range [0, 9] -> r1 range [1, 10]; r2 range [2, 11]; */
+	"r6 += r0;"             /* r0 range [0, 9]  */
+	"r7 += r1;"             /* r1 range [1, 10] */
+	"r8 += r2;"             /* r2 range [2, 11] */
+	"*(u8 *)(r6 +0) = r0;"  /* safe, within bounds   */
+	"*(u8 *)(r7 -1) = r0;"  /* safe */
+	"*(u8 *)(r8 -1) = r0;"  /* unsafe */
+	"1: exit;"
+	:
+	: __imm(bpf_ktime_get_ns),
+	  __imm_ptr(buf)
+	: __clobber_common);
+}
+
+SEC("socket")
+__failure
+__flag(BPF_F_TEST_STATE_FREQ)
+__naked void check_add_const_regsafe_off(void)
+{
+	asm volatile (
+	"r8 = %[buf];"
+	"call %[bpf_ktime_get_ns];"
+	"r6 = r0;"
+	"call %[bpf_ktime_get_ns];"
+	"r7 = r0;"
+	"call %[bpf_ktime_get_ns];"
+	"r1 = r0;"              /* same ids for r1 and r0 */
+	"if r6 > r7 goto 1f;"   /* this jump can't be predicted */
+	"r1 += 1;"              /* r1.off == +1 */
+	"goto 2f;"
+	"1: r1 += 100;"         /* r1.off == +100 */
+	"goto +0;"              /* verify r1.off in regsafe() after this insn */
+	"2: if r0 > 8 goto 3f;" /* r0 range [0,8], r1 range either [1,9] or [100,108]*/
+	"r8 += r1;"
+	"*(u8 *)(r8 +0) = r0;"  /* potentially unsafe, buf size is 10 */
+	"3: exit;"
+	:
+	: __imm(bpf_ktime_get_ns),
+	  __imm_ptr(buf)
+	: __clobber_common);
+}
+
 char _license[] SEC("license") = "GPL";
-- 
GitLab


From 58e185a0dc359a6c1c9eff348d7badfc9f722159 Mon Sep 17 00:00:00 2001
From: Alan Maguire <alan.maguire@oracle.com>
Date: Thu, 13 Jun 2024 10:50:06 +0100
Subject: [PATCH 945/950] libbpf: Add btf__distill_base() creating split BTF
 with distilled base BTF

To support more robust split BTF, adding supplemental context for the
base BTF type ids that split BTF refers to is required.  Without such
references, a simple shuffling of base BTF type ids (without any other
significant change) invalidates the split BTF.  Here the attempt is made
to store additional context to make split BTF more robust.

This context comes in the form of distilled base BTF providing minimal
information (name and - in some cases - size) for base INTs, FLOATs,
STRUCTs, UNIONs, ENUMs and ENUM64s along with modified split BTF that
points at that base and contains any additional types needed (such as
TYPEDEF, PTR and anonymous STRUCT/UNION declarations).  This
information constitutes the minimal BTF representation needed to
disambiguate or remove split BTF references to base BTF.  The rules
are as follows:

- INT, FLOAT, FWD are recorded in full.
- if a named base BTF STRUCT or UNION is referred to from split BTF, it
  will be encoded as a zero-member sized STRUCT/UNION (preserving
  size for later relocation checks).  Only base BTF STRUCT/UNIONs
  that are either embedded in split BTF STRUCT/UNIONs or that have
  multiple STRUCT/UNION instances of the same name will _need_ size
  checks at relocation time, but as it is possible a different set of
  types will be duplicates in the later to-be-resolved base BTF,
  we preserve size information for all named STRUCT/UNIONs.
- if an ENUM[64] is named, a ENUM forward representation (an ENUM
  with no values) of the same size is used.
- in all other cases, the type is added to the new split BTF.

Avoiding struct/union/enum/enum64 expansion is important to keep the
distilled base BTF representation to a minimum size.

When successful, new representations of the distilled base BTF and new
split BTF that refers to it are returned.  Both need to be freed by the
caller.

So to take a simple example, with split BTF with a type referring
to "struct sk_buff", we will generate distilled base BTF with a
0-member STRUCT sk_buff of the appropriate size, and the split BTF
will refer to it instead.

Tools like pahole can utilize such split BTF to populate the .BTF
section (split BTF) and an additional .BTF.base section.  Then
when the split BTF is loaded, the distilled base BTF can be used
to relocate split BTF to reference the current (and possibly changed)
base BTF.

So for example if "struct sk_buff" was id 502 when the split BTF was
originally generated,  we can use the distilled base BTF to see that
id 502 refers to a "struct sk_buff" and replace instances of id 502
with the current (relocated) base BTF sk_buff type id.

Distilled base BTF is small; when building a kernel with all modules
using distilled base BTF as a test, overall module size grew by only
5.3Mb total across ~2700 modules.

Signed-off-by: Alan Maguire <alan.maguire@oracle.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/bpf/20240613095014.357981-2-alan.maguire@oracle.com
---
 tools/lib/bpf/btf.c      | 319 ++++++++++++++++++++++++++++++++++++++-
 tools/lib/bpf/btf.h      |  21 +++
 tools/lib/bpf/libbpf.map |   1 +
 3 files changed, 335 insertions(+), 6 deletions(-)

diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 775ca55a541ca..407ed92b4134d 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -1770,9 +1770,8 @@ static int btf_rewrite_str(struct btf_pipe *p, __u32 *str_off)
 	return 0;
 }
 
-int btf__add_type(struct btf *btf, const struct btf *src_btf, const struct btf_type *src_type)
+static int btf_add_type(struct btf_pipe *p, const struct btf_type *src_type)
 {
-	struct btf_pipe p = { .src = src_btf, .dst = btf };
 	struct btf_field_iter it;
 	struct btf_type *t;
 	__u32 *str_off;
@@ -1783,10 +1782,10 @@ int btf__add_type(struct btf *btf, const struct btf *src_btf, const struct btf_t
 		return libbpf_err(sz);
 
 	/* deconstruct BTF, if necessary, and invalidate raw_data */
-	if (btf_ensure_modifiable(btf))
+	if (btf_ensure_modifiable(p->dst))
 		return libbpf_err(-ENOMEM);
 
-	t = btf_add_type_mem(btf, sz);
+	t = btf_add_type_mem(p->dst, sz);
 	if (!t)
 		return libbpf_err(-ENOMEM);
 
@@ -1797,12 +1796,19 @@ int btf__add_type(struct btf *btf, const struct btf *src_btf, const struct btf_t
 		return libbpf_err(err);
 
 	while ((str_off = btf_field_iter_next(&it))) {
-		err = btf_rewrite_str(&p, str_off);
+		err = btf_rewrite_str(p, str_off);
 		if (err)
 			return libbpf_err(err);
 	}
 
-	return btf_commit_type(btf, sz);
+	return btf_commit_type(p->dst, sz);
+}
+
+int btf__add_type(struct btf *btf, const struct btf *src_btf, const struct btf_type *src_type)
+{
+	struct btf_pipe p = { .src = src_btf, .dst = btf };
+
+	return btf_add_type(&p, src_type);
 }
 
 static size_t btf_dedup_identity_hash_fn(long key, void *ctx);
@@ -5276,3 +5282,304 @@ int btf_ext_visit_str_offs(struct btf_ext *btf_ext, str_off_visit_fn visit, void
 
 	return 0;
 }
+
+struct btf_distill {
+	struct btf_pipe pipe;
+	int *id_map;
+	unsigned int split_start_id;
+	unsigned int split_start_str;
+	int diff_id;
+};
+
+static int btf_add_distilled_type_ids(struct btf_distill *dist, __u32 i)
+{
+	struct btf_type *split_t = btf_type_by_id(dist->pipe.src, i);
+	struct btf_field_iter it;
+	__u32 *id;
+	int err;
+
+	err = btf_field_iter_init(&it, split_t, BTF_FIELD_ITER_IDS);
+	if (err)
+		return err;
+	while ((id = btf_field_iter_next(&it))) {
+		struct btf_type *base_t;
+
+		if (!*id)
+			continue;
+		/* split BTF id, not needed */
+		if (*id >= dist->split_start_id)
+			continue;
+		/* already added ? */
+		if (dist->id_map[*id] > 0)
+			continue;
+
+		/* only a subset of base BTF types should be referenced from
+		 * split BTF; ensure nothing unexpected is referenced.
+		 */
+		base_t = btf_type_by_id(dist->pipe.src, *id);
+		switch (btf_kind(base_t)) {
+		case BTF_KIND_INT:
+		case BTF_KIND_FLOAT:
+		case BTF_KIND_FWD:
+		case BTF_KIND_ARRAY:
+		case BTF_KIND_STRUCT:
+		case BTF_KIND_UNION:
+		case BTF_KIND_TYPEDEF:
+		case BTF_KIND_ENUM:
+		case BTF_KIND_ENUM64:
+		case BTF_KIND_PTR:
+		case BTF_KIND_CONST:
+		case BTF_KIND_RESTRICT:
+		case BTF_KIND_VOLATILE:
+		case BTF_KIND_FUNC_PROTO:
+		case BTF_KIND_TYPE_TAG:
+			dist->id_map[*id] = *id;
+			break;
+		default:
+			pr_warn("unexpected reference to base type[%u] of kind [%u] when creating distilled base BTF.\n",
+				*id, btf_kind(base_t));
+			return -EINVAL;
+		}
+		/* If a base type is used, ensure types it refers to are
+		 * marked as used also; so for example if we find a PTR to INT
+		 * we need both the PTR and INT.
+		 *
+		 * The only exception is named struct/unions, since distilled
+		 * base BTF composite types have no members.
+		 */
+		if (btf_is_composite(base_t) && base_t->name_off)
+			continue;
+		err = btf_add_distilled_type_ids(dist, *id);
+		if (err)
+			return err;
+	}
+	return 0;
+}
+
+static int btf_add_distilled_types(struct btf_distill *dist)
+{
+	bool adding_to_base = dist->pipe.dst->start_id == 1;
+	int id = btf__type_cnt(dist->pipe.dst);
+	struct btf_type *t;
+	int i, err = 0;
+
+
+	/* Add types for each of the required references to either distilled
+	 * base or split BTF, depending on type characteristics.
+	 */
+	for (i = 1; i < dist->split_start_id; i++) {
+		const char *name;
+		int kind;
+
+		if (!dist->id_map[i])
+			continue;
+		t = btf_type_by_id(dist->pipe.src, i);
+		kind = btf_kind(t);
+		name = btf__name_by_offset(dist->pipe.src, t->name_off);
+
+		switch (kind) {
+		case BTF_KIND_INT:
+		case BTF_KIND_FLOAT:
+		case BTF_KIND_FWD:
+			/* Named int, float, fwd are added to base. */
+			if (!adding_to_base)
+				continue;
+			err = btf_add_type(&dist->pipe, t);
+			break;
+		case BTF_KIND_STRUCT:
+		case BTF_KIND_UNION:
+			/* Named struct/union are added to base as 0-vlen
+			 * struct/union of same size.  Anonymous struct/unions
+			 * are added to split BTF as-is.
+			 */
+			if (adding_to_base) {
+				if (!t->name_off)
+					continue;
+				err = btf_add_composite(dist->pipe.dst, kind, name, t->size);
+			} else {
+				if (t->name_off)
+					continue;
+				err = btf_add_type(&dist->pipe, t);
+			}
+			break;
+		case BTF_KIND_ENUM:
+		case BTF_KIND_ENUM64:
+			/* Named enum[64]s are added to base as a sized
+			 * enum; relocation will match with appropriately-named
+			 * and sized enum or enum64.
+			 *
+			 * Anonymous enums are added to split BTF as-is.
+			 */
+			if (adding_to_base) {
+				if (!t->name_off)
+					continue;
+				err = btf__add_enum(dist->pipe.dst, name, t->size);
+			} else {
+				if (t->name_off)
+					continue;
+				err = btf_add_type(&dist->pipe, t);
+			}
+			break;
+		case BTF_KIND_ARRAY:
+		case BTF_KIND_TYPEDEF:
+		case BTF_KIND_PTR:
+		case BTF_KIND_CONST:
+		case BTF_KIND_RESTRICT:
+		case BTF_KIND_VOLATILE:
+		case BTF_KIND_FUNC_PROTO:
+		case BTF_KIND_TYPE_TAG:
+			/* All other types are added to split BTF. */
+			if (adding_to_base)
+				continue;
+			err = btf_add_type(&dist->pipe, t);
+			break;
+		default:
+			pr_warn("unexpected kind when adding base type '%s'[%u] of kind [%u] to distilled base BTF.\n",
+				name, i, kind);
+			return -EINVAL;
+
+		}
+		if (err < 0)
+			break;
+		dist->id_map[i] = id++;
+	}
+	return err;
+}
+
+/* Split BTF ids without a mapping will be shifted downwards since distilled
+ * base BTF is smaller than the original base BTF.  For those that have a
+ * mapping (either to base or updated split BTF), update the id based on
+ * that mapping.
+ */
+static int btf_update_distilled_type_ids(struct btf_distill *dist, __u32 i)
+{
+	struct btf_type *t = btf_type_by_id(dist->pipe.dst, i);
+	struct btf_field_iter it;
+	__u32 *id;
+	int err;
+
+	err = btf_field_iter_init(&it, t, BTF_FIELD_ITER_IDS);
+	if (err)
+		return err;
+	while ((id = btf_field_iter_next(&it))) {
+		if (dist->id_map[*id])
+			*id = dist->id_map[*id];
+		else if (*id >= dist->split_start_id)
+			*id -= dist->diff_id;
+	}
+	return 0;
+}
+
+/* Create updated split BTF with distilled base BTF; distilled base BTF
+ * consists of BTF information required to clarify the types that split
+ * BTF refers to, omitting unneeded details.  Specifically it will contain
+ * base types and memberless definitions of named structs, unions and enumerated
+ * types. Associated reference types like pointers, arrays and anonymous
+ * structs, unions and enumerated types will be added to split BTF.
+ * Size is recorded for named struct/unions to help guide matching to the
+ * target base BTF during later relocation.
+ *
+ * The only case where structs, unions or enumerated types are fully represented
+ * is when they are anonymous; in such cases, the anonymous type is added to
+ * split BTF in full.
+ *
+ * We return newly-created split BTF where the split BTF refers to a newly-created
+ * distilled base BTF. Both must be freed separately by the caller.
+ */
+int btf__distill_base(const struct btf *src_btf, struct btf **new_base_btf,
+		      struct btf **new_split_btf)
+{
+	struct btf *new_base = NULL, *new_split = NULL;
+	const struct btf *old_base;
+	unsigned int n = btf__type_cnt(src_btf);
+	struct btf_distill dist = {};
+	struct btf_type *t;
+	int i, err = 0;
+
+	/* src BTF must be split BTF. */
+	old_base = btf__base_btf(src_btf);
+	if (!new_base_btf || !new_split_btf || !old_base)
+		return libbpf_err(-EINVAL);
+
+	new_base = btf__new_empty();
+	if (!new_base)
+		return libbpf_err(-ENOMEM);
+	dist.id_map = calloc(n, sizeof(*dist.id_map));
+	if (!dist.id_map) {
+		err = -ENOMEM;
+		goto done;
+	}
+	dist.pipe.src = src_btf;
+	dist.pipe.dst = new_base;
+	dist.pipe.str_off_map = hashmap__new(btf_dedup_identity_hash_fn, btf_dedup_equal_fn, NULL);
+	if (IS_ERR(dist.pipe.str_off_map)) {
+		err = -ENOMEM;
+		goto done;
+	}
+	dist.split_start_id = btf__type_cnt(old_base);
+	dist.split_start_str = old_base->hdr->str_len;
+
+	/* Pass over src split BTF; generate the list of base BTF type ids it
+	 * references; these will constitute our distilled BTF set to be
+	 * distributed over base and split BTF as appropriate.
+	 */
+	for (i = src_btf->start_id; i < n; i++) {
+		err = btf_add_distilled_type_ids(&dist, i);
+		if (err < 0)
+			goto done;
+	}
+	/* Next add types for each of the required references to base BTF and split BTF
+	 * in turn.
+	 */
+	err = btf_add_distilled_types(&dist);
+	if (err < 0)
+		goto done;
+
+	/* Create new split BTF with distilled base BTF as its base; the final
+	 * state is split BTF with distilled base BTF that represents enough
+	 * about its base references to allow it to be relocated with the base
+	 * BTF available.
+	 */
+	new_split = btf__new_empty_split(new_base);
+	if (!new_split_btf) {
+		err = -errno;
+		goto done;
+	}
+	dist.pipe.dst = new_split;
+	/* First add all split types */
+	for (i = src_btf->start_id; i < n; i++) {
+		t = btf_type_by_id(src_btf, i);
+		err = btf_add_type(&dist.pipe, t);
+		if (err < 0)
+			goto done;
+	}
+	/* Now add distilled types to split BTF that are not added to base. */
+	err = btf_add_distilled_types(&dist);
+	if (err < 0)
+		goto done;
+
+	/* All split BTF ids will be shifted downwards since there are less base
+	 * BTF ids in distilled base BTF.
+	 */
+	dist.diff_id = dist.split_start_id - btf__type_cnt(new_base);
+
+	n = btf__type_cnt(new_split);
+	/* Now update base/split BTF ids. */
+	for (i = 1; i < n; i++) {
+		err = btf_update_distilled_type_ids(&dist, i);
+		if (err < 0)
+			break;
+	}
+done:
+	free(dist.id_map);
+	hashmap__free(dist.pipe.str_off_map);
+	if (err) {
+		btf__free(new_split);
+		btf__free(new_base);
+		return libbpf_err(err);
+	}
+	*new_base_btf = new_base;
+	*new_split_btf = new_split;
+
+	return 0;
+}
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index 8e6880d91c840..cb08ee9a5a104 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -107,6 +107,27 @@ LIBBPF_API struct btf *btf__new_empty(void);
  */
 LIBBPF_API struct btf *btf__new_empty_split(struct btf *base_btf);
 
+/**
+ * @brief **btf__distill_base()** creates new versions of the split BTF
+ * *src_btf* and its base BTF. The new base BTF will only contain the types
+ * needed to improve robustness of the split BTF to small changes in base BTF.
+ * When that split BTF is loaded against a (possibly changed) base, this
+ * distilled base BTF will help update references to that (possibly changed)
+ * base BTF.
+ *
+ * Both the new split and its associated new base BTF must be freed by
+ * the caller.
+ *
+ * If successful, 0 is returned and **new_base_btf** and **new_split_btf**
+ * will point at new base/split BTF. Both the new split and its associated
+ * new base BTF must be freed by the caller.
+ *
+ * A negative value is returned on error and the thread-local `errno` variable
+ * is set to the error code as well.
+ */
+LIBBPF_API int btf__distill_base(const struct btf *src_btf, struct btf **new_base_btf,
+				 struct btf **new_split_btf);
+
 LIBBPF_API struct btf *btf__parse(const char *path, struct btf_ext **btf_ext);
 LIBBPF_API struct btf *btf__parse_split(const char *path, struct btf *base_btf);
 LIBBPF_API struct btf *btf__parse_elf(const char *path, struct btf_ext **btf_ext);
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 40595233dc7fb..175d1536e070f 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -419,6 +419,7 @@ LIBBPF_1.4.0 {
 
 LIBBPF_1.5.0 {
 	global:
+		btf__distill_base;
 		bpf_map__autoattach;
 		bpf_map__set_autoattach;
 		bpf_program__attach_sockmap;
-- 
GitLab


From eb20e727c4343ad591cff2bef243590c77f62cf1 Mon Sep 17 00:00:00 2001
From: Alan Maguire <alan.maguire@oracle.com>
Date: Thu, 13 Jun 2024 10:50:07 +0100
Subject: [PATCH 946/950] selftests/bpf: Test distilled base, split BTF
 generation

Test generation of split+distilled base BTF, ensuring that

- named base BTF STRUCTs and UNIONs are represented as 0-vlen sized
  STRUCT/UNIONs
- named ENUM[64]s are represented as 0-vlen named ENUM[64]s
- anonymous struct/unions are represented in full in split BTF
- anonymous enums are represented in full in split BTF
- types unreferenced from split BTF are not present in distilled
  base BTF

Also test that with vmlinux BTF and split BTF based upon it,
we only represent needed base types referenced from split BTF
in distilled base.

Signed-off-by: Alan Maguire <alan.maguire@oracle.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/bpf/20240613095014.357981-3-alan.maguire@oracle.com
---
 .../selftests/bpf/prog_tests/btf_distill.c    | 274 ++++++++++++++++++
 1 file changed, 274 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/btf_distill.c

diff --git a/tools/testing/selftests/bpf/prog_tests/btf_distill.c b/tools/testing/selftests/bpf/prog_tests/btf_distill.c
new file mode 100644
index 0000000000000..5c3a387479620
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/btf_distill.c
@@ -0,0 +1,274 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024, Oracle and/or its affiliates. */
+
+#include <test_progs.h>
+#include <bpf/btf.h>
+#include "btf_helpers.h"
+
+/* Fabricate base, split BTF with references to base types needed; then create
+ * split BTF with distilled base BTF and ensure expectations are met:
+ *  - only referenced base types from split BTF are present
+ *  - struct/union/enum are represented as empty unless anonymous, when they
+ *    are represented in full in split BTF
+ */
+static void test_distilled_base(void)
+{
+	struct btf *btf1 = NULL, *btf2 = NULL, *btf3 = NULL, *btf4 = NULL;
+
+	btf1 = btf__new_empty();
+	if (!ASSERT_OK_PTR(btf1, "empty_main_btf"))
+		return;
+
+	btf__add_int(btf1, "int", 4, BTF_INT_SIGNED);	/* [1] int */
+	btf__add_ptr(btf1, 1);				/* [2] ptr to int */
+	btf__add_struct(btf1, "s1", 8);			/* [3] struct s1 { */
+	btf__add_field(btf1, "f1", 2, 0, 0);		/*      int *f1; */
+							/* } */
+	btf__add_struct(btf1, "", 12);			/* [4] struct { */
+	btf__add_field(btf1, "f1", 1, 0, 0);		/*	int f1; */
+	btf__add_field(btf1, "f2", 3, 32, 0);		/*	struct s1 f2; */
+							/* } */
+	btf__add_int(btf1, "unsigned int", 4, 0);	/* [5] unsigned int */
+	btf__add_union(btf1, "u1", 12);			/* [6] union u1 { */
+	btf__add_field(btf1, "f1", 1, 0, 0);		/*	int f1; */
+	btf__add_field(btf1, "f2", 2, 0, 0);		/*	int *f2; */
+							/* } */
+	btf__add_union(btf1, "", 4);			/* [7] union { */
+	btf__add_field(btf1, "f1", 1, 0, 0);		/*	int f1; */
+							/* } */
+	btf__add_enum(btf1, "e1", 4);			/* [8] enum e1 { */
+	btf__add_enum_value(btf1, "v1", 1);		/*	v1 = 1; */
+							/* } */
+	btf__add_enum(btf1, "", 4);			/* [9] enum { */
+	btf__add_enum_value(btf1, "av1", 2);		/*	av1 = 2; */
+							/* } */
+	btf__add_enum64(btf1, "e641", 8, true);		/* [10] enum64 { */
+	btf__add_enum64_value(btf1, "v1", 1024);	/*	v1 = 1024; */
+							/* } */
+	btf__add_enum64(btf1, "", 8, true);		/* [11] enum64 { */
+	btf__add_enum64_value(btf1, "v1", 1025);	/*	v1 = 1025; */
+							/* } */
+	btf__add_struct(btf1, "unneeded", 4);		/* [12] struct unneeded { */
+	btf__add_field(btf1, "f1", 1, 0, 0);		/*	int f1; */
+							/* } */
+	btf__add_struct(btf1, "embedded", 4);		/* [13] struct embedded { */
+	btf__add_field(btf1, "f1", 1, 0, 0);		/*	int f1; */
+							/* } */
+	btf__add_func_proto(btf1, 1);			/* [14] int (*)(int *p1); */
+	btf__add_func_param(btf1, "p1", 1);
+
+	btf__add_array(btf1, 1, 1, 3);			/* [15] int [3]; */
+
+	btf__add_struct(btf1, "from_proto", 4);		/* [16] struct from_proto { */
+	btf__add_field(btf1, "f1", 1, 0, 0);		/*	int f1; */
+							/* } */
+	btf__add_union(btf1, "u1", 4);			/* [17] union u1 { */
+	btf__add_field(btf1, "f1", 1, 0, 0);		/*	 int f1; */
+							/* } */
+	VALIDATE_RAW_BTF(
+		btf1,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] PTR '(anon)' type_id=1",
+		"[3] STRUCT 's1' size=8 vlen=1\n"
+		"\t'f1' type_id=2 bits_offset=0",
+		"[4] STRUCT '(anon)' size=12 vlen=2\n"
+		"\t'f1' type_id=1 bits_offset=0\n"
+		"\t'f2' type_id=3 bits_offset=32",
+		"[5] INT 'unsigned int' size=4 bits_offset=0 nr_bits=32 encoding=(none)",
+		"[6] UNION 'u1' size=12 vlen=2\n"
+		"\t'f1' type_id=1 bits_offset=0\n"
+		"\t'f2' type_id=2 bits_offset=0",
+		"[7] UNION '(anon)' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0",
+		"[8] ENUM 'e1' encoding=UNSIGNED size=4 vlen=1\n"
+		"\t'v1' val=1",
+		"[9] ENUM '(anon)' encoding=UNSIGNED size=4 vlen=1\n"
+		"\t'av1' val=2",
+		"[10] ENUM64 'e641' encoding=SIGNED size=8 vlen=1\n"
+		"\t'v1' val=1024",
+		"[11] ENUM64 '(anon)' encoding=SIGNED size=8 vlen=1\n"
+		"\t'v1' val=1025",
+		"[12] STRUCT 'unneeded' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0",
+		"[13] STRUCT 'embedded' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0",
+		"[14] FUNC_PROTO '(anon)' ret_type_id=1 vlen=1\n"
+		"\t'p1' type_id=1",
+		"[15] ARRAY '(anon)' type_id=1 index_type_id=1 nr_elems=3",
+		"[16] STRUCT 'from_proto' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0",
+		"[17] UNION 'u1' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0");
+
+	btf2 = btf__new_empty_split(btf1);
+	if (!ASSERT_OK_PTR(btf2, "empty_split_btf"))
+		goto cleanup;
+
+	btf__add_ptr(btf2, 3);				/* [18] ptr to struct s1 */
+	/* add ptr to struct anon */
+	btf__add_ptr(btf2, 4);				/* [19] ptr to struct (anon) */
+	btf__add_const(btf2, 6);			/* [20] const union u1 */
+	btf__add_restrict(btf2, 7);			/* [21] restrict union (anon) */
+	btf__add_volatile(btf2, 8);			/* [22] volatile enum e1 */
+	btf__add_typedef(btf2, "et", 9);		/* [23] typedef enum (anon) */
+	btf__add_const(btf2, 10);			/* [24] const enum64 e641 */
+	btf__add_ptr(btf2, 11);				/* [25] restrict enum64 (anon) */
+	btf__add_struct(btf2, "with_embedded", 4);	/* [26] struct with_embedded { */
+	btf__add_field(btf2, "f1", 13, 0, 0);		/*	struct embedded f1; */
+							/* } */
+	btf__add_func(btf2, "fn", BTF_FUNC_STATIC, 14);	/* [27] int fn(int p1); */
+	btf__add_typedef(btf2, "arraytype", 15);	/* [28] typedef int[3] foo; */
+	btf__add_func_proto(btf2, 1);			/* [29] int (*)(struct from proto p1); */
+	btf__add_func_param(btf2, "p1", 16);
+
+	VALIDATE_RAW_BTF(
+		btf2,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] PTR '(anon)' type_id=1",
+		"[3] STRUCT 's1' size=8 vlen=1\n"
+		"\t'f1' type_id=2 bits_offset=0",
+		"[4] STRUCT '(anon)' size=12 vlen=2\n"
+		"\t'f1' type_id=1 bits_offset=0\n"
+		"\t'f2' type_id=3 bits_offset=32",
+		"[5] INT 'unsigned int' size=4 bits_offset=0 nr_bits=32 encoding=(none)",
+		"[6] UNION 'u1' size=12 vlen=2\n"
+		"\t'f1' type_id=1 bits_offset=0\n"
+		"\t'f2' type_id=2 bits_offset=0",
+		"[7] UNION '(anon)' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0",
+		"[8] ENUM 'e1' encoding=UNSIGNED size=4 vlen=1\n"
+		"\t'v1' val=1",
+		"[9] ENUM '(anon)' encoding=UNSIGNED size=4 vlen=1\n"
+		"\t'av1' val=2",
+		"[10] ENUM64 'e641' encoding=SIGNED size=8 vlen=1\n"
+		"\t'v1' val=1024",
+		"[11] ENUM64 '(anon)' encoding=SIGNED size=8 vlen=1\n"
+		"\t'v1' val=1025",
+		"[12] STRUCT 'unneeded' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0",
+		"[13] STRUCT 'embedded' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0",
+		"[14] FUNC_PROTO '(anon)' ret_type_id=1 vlen=1\n"
+		"\t'p1' type_id=1",
+		"[15] ARRAY '(anon)' type_id=1 index_type_id=1 nr_elems=3",
+		"[16] STRUCT 'from_proto' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0",
+		"[17] UNION 'u1' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0",
+		"[18] PTR '(anon)' type_id=3",
+		"[19] PTR '(anon)' type_id=4",
+		"[20] CONST '(anon)' type_id=6",
+		"[21] RESTRICT '(anon)' type_id=7",
+		"[22] VOLATILE '(anon)' type_id=8",
+		"[23] TYPEDEF 'et' type_id=9",
+		"[24] CONST '(anon)' type_id=10",
+		"[25] PTR '(anon)' type_id=11",
+		"[26] STRUCT 'with_embedded' size=4 vlen=1\n"
+		"\t'f1' type_id=13 bits_offset=0",
+		"[27] FUNC 'fn' type_id=14 linkage=static",
+		"[28] TYPEDEF 'arraytype' type_id=15",
+		"[29] FUNC_PROTO '(anon)' ret_type_id=1 vlen=1\n"
+		"\t'p1' type_id=16");
+
+	if (!ASSERT_EQ(0, btf__distill_base(btf2, &btf3, &btf4),
+		       "distilled_base") ||
+	    !ASSERT_OK_PTR(btf3, "distilled_base") ||
+	    !ASSERT_OK_PTR(btf4, "distilled_split") ||
+	    !ASSERT_EQ(8, btf__type_cnt(btf3), "distilled_base_type_cnt"))
+		goto cleanup;
+
+	VALIDATE_RAW_BTF(
+		btf4,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] STRUCT 's1' size=8 vlen=0",
+		"[3] UNION 'u1' size=12 vlen=0",
+		"[4] ENUM 'e1' encoding=UNSIGNED size=4 vlen=0",
+		"[5] ENUM 'e641' encoding=UNSIGNED size=8 vlen=0",
+		"[6] STRUCT 'embedded' size=4 vlen=0",
+		"[7] STRUCT 'from_proto' size=4 vlen=0",
+		/* split BTF; these types should match split BTF above from 17-28, with
+		 * updated type id references
+		 */
+		"[8] PTR '(anon)' type_id=2",
+		"[9] PTR '(anon)' type_id=20",
+		"[10] CONST '(anon)' type_id=3",
+		"[11] RESTRICT '(anon)' type_id=21",
+		"[12] VOLATILE '(anon)' type_id=4",
+		"[13] TYPEDEF 'et' type_id=22",
+		"[14] CONST '(anon)' type_id=5",
+		"[15] PTR '(anon)' type_id=23",
+		"[16] STRUCT 'with_embedded' size=4 vlen=1\n"
+		"\t'f1' type_id=6 bits_offset=0",
+		"[17] FUNC 'fn' type_id=24 linkage=static",
+		"[18] TYPEDEF 'arraytype' type_id=25",
+		"[19] FUNC_PROTO '(anon)' ret_type_id=1 vlen=1\n"
+		"\t'p1' type_id=7",
+		/* split BTF types added from original base BTF below */
+		"[20] STRUCT '(anon)' size=12 vlen=2\n"
+		"\t'f1' type_id=1 bits_offset=0\n"
+		"\t'f2' type_id=2 bits_offset=32",
+		"[21] UNION '(anon)' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0",
+		"[22] ENUM '(anon)' encoding=UNSIGNED size=4 vlen=1\n"
+		"\t'av1' val=2",
+		"[23] ENUM64 '(anon)' encoding=SIGNED size=8 vlen=1\n"
+		"\t'v1' val=1025",
+		"[24] FUNC_PROTO '(anon)' ret_type_id=1 vlen=1\n"
+		"\t'p1' type_id=1",
+		"[25] ARRAY '(anon)' type_id=1 index_type_id=1 nr_elems=3");
+
+cleanup:
+	btf__free(btf4);
+	btf__free(btf3);
+	btf__free(btf2);
+	btf__free(btf1);
+}
+
+/* create split reference BTF from vmlinux + split BTF with a few type references;
+ * ensure the resultant split reference BTF is as expected, containing only types
+ * needed to disambiguate references from split BTF.
+ */
+static void test_distilled_base_vmlinux(void)
+{
+	struct btf *split_btf = NULL, *vmlinux_btf = btf__load_vmlinux_btf();
+	struct btf *split_dist = NULL, *base_dist = NULL;
+	__s32 int_id, myint_id;
+
+	if (!ASSERT_OK_PTR(vmlinux_btf, "load_vmlinux"))
+		return;
+	int_id = btf__find_by_name_kind(vmlinux_btf, "int", BTF_KIND_INT);
+	if (!ASSERT_GT(int_id, 0, "find_int"))
+		goto cleanup;
+	split_btf = btf__new_empty_split(vmlinux_btf);
+	if (!ASSERT_OK_PTR(split_btf, "new_split"))
+		goto cleanup;
+	myint_id = btf__add_typedef(split_btf, "myint", int_id);
+	btf__add_ptr(split_btf, myint_id);
+
+	if (!ASSERT_EQ(btf__distill_base(split_btf, &base_dist, &split_dist), 0,
+		       "distill_vmlinux_base"))
+		goto cleanup;
+
+	if (!ASSERT_OK_PTR(split_dist, "split_distilled") ||
+	    !ASSERT_OK_PTR(base_dist, "base_dist"))
+		goto cleanup;
+	VALIDATE_RAW_BTF(
+		split_dist,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] TYPEDEF 'myint' type_id=1",
+		"[3] PTR '(anon)' type_id=2");
+
+cleanup:
+	btf__free(split_dist);
+	btf__free(base_dist);
+	btf__free(split_btf);
+	btf__free(vmlinux_btf);
+}
+
+void test_btf_distill(void)
+{
+	if (test__start_subtest("distilled_base"))
+		test_distilled_base();
+	if (test__start_subtest("distilled_base_vmlinux"))
+		test_distilled_base_vmlinux();
+}
-- 
GitLab


From 19e00c897d5031bed969dd79af28e899e038009f Mon Sep 17 00:00:00 2001
From: Alan Maguire <alan.maguire@oracle.com>
Date: Thu, 13 Jun 2024 10:50:08 +0100
Subject: [PATCH 947/950] libbpf: Split BTF relocation

Map distilled base BTF type ids referenced in split BTF and their
references to the base BTF passed in, and if the mapping succeeds,
reparent the split BTF to the base BTF.

Relocation is done by first verifying that distilled base BTF
only consists of named INT, FLOAT, ENUM, FWD, STRUCT and
UNION kinds; then we sort these to speed lookups.  Once sorted,
the base BTF is iterated, and for each relevant kind we check
for an equivalent in distilled base BTF.  When found, the
mapping from distilled -> base BTF id and string offset is recorded.
In establishing mappings, we need to ensure we check STRUCT/UNION
size when the STRUCT/UNION is embedded in a split BTF STRUCT/UNION,
and when duplicate names exist for the same STRUCT/UNION.  Otherwise
size is ignored in matching STRUCT/UNIONs.

Once all mappings are established, we can update type ids
and string offsets in split BTF and reparent it to the new base.

Signed-off-by: Alan Maguire <alan.maguire@oracle.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/bpf/20240613095014.357981-4-alan.maguire@oracle.com
---
 tools/lib/bpf/Build             |   2 +-
 tools/lib/bpf/btf.c             |  17 ++
 tools/lib/bpf/btf.h             |  14 +
 tools/lib/bpf/btf_relocate.c    | 506 ++++++++++++++++++++++++++++++++
 tools/lib/bpf/libbpf.map        |   1 +
 tools/lib/bpf/libbpf_internal.h |   3 +
 6 files changed, 542 insertions(+), 1 deletion(-)
 create mode 100644 tools/lib/bpf/btf_relocate.c

diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build
index b6619199a7066..336da6844d425 100644
--- a/tools/lib/bpf/Build
+++ b/tools/lib/bpf/Build
@@ -1,4 +1,4 @@
 libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o str_error.o \
 	    netlink.o bpf_prog_linfo.o libbpf_probes.o hashmap.o \
 	    btf_dump.o ringbuf.o strset.o linker.o gen_loader.o relo_core.o \
-	    usdt.o zip.o elf.o features.o
+	    usdt.o zip.o elf.o features.o btf_relocate.o
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 407ed92b4134d..5e20354fbcfa8 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -5583,3 +5583,20 @@ done:
 
 	return 0;
 }
+
+const struct btf_header *btf_header(const struct btf *btf)
+{
+	return btf->hdr;
+}
+
+void btf_set_base_btf(struct btf *btf, const struct btf *base_btf)
+{
+	btf->base_btf = (struct btf *)base_btf;
+	btf->start_id = btf__type_cnt(base_btf);
+	btf->start_str_off = base_btf->hdr->str_len;
+}
+
+int btf__relocate(struct btf *btf, const struct btf *base_btf)
+{
+	return libbpf_err(btf_relocate(btf, base_btf, NULL));
+}
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index cb08ee9a5a104..8a93120b7385b 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -252,6 +252,20 @@ struct btf_dedup_opts {
 
 LIBBPF_API int btf__dedup(struct btf *btf, const struct btf_dedup_opts *opts);
 
+/**
+ * @brief **btf__relocate()** will check the split BTF *btf* for references
+ * to base BTF kinds, and verify those references are compatible with
+ * *base_btf*; if they are, *btf* is adjusted such that is re-parented to
+ * *base_btf* and type ids and strings are adjusted to accommodate this.
+ *
+ * If successful, 0 is returned and **btf** now has **base_btf** as its
+ * base.
+ *
+ * A negative value is returned on error and the thread-local `errno` variable
+ * is set to the error code as well.
+ */
+LIBBPF_API int btf__relocate(struct btf *btf, const struct btf *base_btf);
+
 struct btf_dump;
 
 struct btf_dump_opts {
diff --git a/tools/lib/bpf/btf_relocate.c b/tools/lib/bpf/btf_relocate.c
new file mode 100644
index 0000000000000..eabb8755f6625
--- /dev/null
+++ b/tools/lib/bpf/btf_relocate.c
@@ -0,0 +1,506 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024, Oracle and/or its affiliates. */
+
+#ifndef _GNU_SOURCE
+#define _GNU_SOURCE
+#endif
+
+#include "btf.h"
+#include "bpf.h"
+#include "libbpf.h"
+#include "libbpf_internal.h"
+
+struct btf;
+
+struct btf_relocate {
+	struct btf *btf;
+	const struct btf *base_btf;
+	const struct btf *dist_base_btf;
+	unsigned int nr_base_types;
+	unsigned int nr_split_types;
+	unsigned int nr_dist_base_types;
+	int dist_str_len;
+	int base_str_len;
+	__u32 *id_map;
+	__u32 *str_map;
+};
+
+/* Set temporarily in relocation id_map if distilled base struct/union is
+ * embedded in a split BTF struct/union; in such a case, size information must
+ * match between distilled base BTF and base BTF representation of type.
+ */
+#define BTF_IS_EMBEDDED ((__u32)-1)
+
+/* <name, size, id> triple used in sorting/searching distilled base BTF. */
+struct btf_name_info {
+	const char *name;
+	/* set when search requires a size match */
+	int needs_size:1,
+	    size:31;
+	__u32 id;
+};
+
+static int btf_relocate_rewrite_type_id(struct btf_relocate *r, __u32 i)
+{
+	struct btf_type *t = btf_type_by_id(r->btf, i);
+	struct btf_field_iter it;
+	__u32 *id;
+	int err;
+
+	err = btf_field_iter_init(&it, t, BTF_FIELD_ITER_IDS);
+	if (err)
+		return err;
+
+	while ((id = btf_field_iter_next(&it)))
+		*id = r->id_map[*id];
+	return 0;
+}
+
+/* Simple string comparison used for sorting within BTF, since all distilled
+ * types are named.  If strings match, and size is non-zero for both elements
+ * fall back to using size for ordering.
+ */
+static int cmp_btf_name_size(const void *n1, const void *n2)
+{
+	const struct btf_name_info *ni1 = n1;
+	const struct btf_name_info *ni2 = n2;
+	int name_diff = strcmp(ni1->name, ni2->name);
+
+	if (!name_diff && ni1->needs_size && ni2->needs_size)
+		return ni2->size - ni1->size;
+	return name_diff;
+}
+
+/* Binary search with a small twist; find leftmost element that matches
+ * so that we can then iterate through all exact matches.  So for example
+ * searching { "a", "bb", "bb", "c" }  we would always match on the
+ * leftmost "bb".
+ */
+static struct btf_name_info *search_btf_name_size(struct btf_name_info *key,
+						  struct btf_name_info *vals,
+						  int nelems)
+{
+	struct btf_name_info *ret = NULL;
+	int high = nelems - 1;
+	int low = 0;
+
+	while (low <= high) {
+		int mid = (low + high)/2;
+		struct btf_name_info *val = &vals[mid];
+		int diff = cmp_btf_name_size(key, val);
+
+		if (diff == 0)
+			ret = val;
+		/* even if found, keep searching for leftmost match */
+		if (diff <= 0)
+			high = mid - 1;
+		else
+			low = mid + 1;
+	}
+	return ret;
+}
+
+/* If a member of a split BTF struct/union refers to a base BTF
+ * struct/union, mark that struct/union id temporarily in the id_map
+ * with BTF_IS_EMBEDDED.  Members can be const/restrict/volatile/typedef
+ * reference types, but if a pointer is encountered, the type is no longer
+ * considered embedded.
+ */
+static int btf_mark_embedded_composite_type_ids(struct btf_relocate *r, __u32 i)
+{
+	struct btf_type *t = btf_type_by_id(r->btf, i);
+	struct btf_field_iter it;
+	__u32 *id;
+	int err;
+
+	if (!btf_is_composite(t))
+		return 0;
+
+	err = btf_field_iter_init(&it, t, BTF_FIELD_ITER_IDS);
+	if (err)
+		return err;
+
+	while ((id = btf_field_iter_next(&it))) {
+		__u32 next_id = *id;
+
+		while (next_id) {
+			t = btf_type_by_id(r->btf, next_id);
+			switch (btf_kind(t)) {
+			case BTF_KIND_CONST:
+			case BTF_KIND_RESTRICT:
+			case BTF_KIND_VOLATILE:
+			case BTF_KIND_TYPEDEF:
+			case BTF_KIND_TYPE_TAG:
+				next_id = t->type;
+				break;
+			case BTF_KIND_ARRAY: {
+				struct btf_array *a = btf_array(t);
+
+				next_id = a->type;
+				break;
+			}
+			case BTF_KIND_STRUCT:
+			case BTF_KIND_UNION:
+				if (next_id < r->nr_dist_base_types)
+					r->id_map[next_id] = BTF_IS_EMBEDDED;
+				next_id = 0;
+				break;
+			default:
+				next_id = 0;
+				break;
+			}
+		}
+	}
+
+	return 0;
+}
+
+/* Build a map from distilled base BTF ids to base BTF ids. To do so, iterate
+ * through base BTF looking up distilled type (using binary search) equivalents.
+ */
+static int btf_relocate_map_distilled_base(struct btf_relocate *r)
+{
+	struct btf_name_info *dist_base_info_sorted, *dist_base_info_sorted_end;
+	struct btf_type *base_t, *dist_t;
+	__u8 *base_name_cnt = NULL;
+	int err = 0;
+	__u32 id;
+
+	/* generate a sort index array of name/type ids sorted by name for
+	 * distilled base BTF to speed name-based lookups.
+	 */
+	dist_base_info_sorted = calloc(r->nr_dist_base_types, sizeof(*dist_base_info_sorted));
+	if (!dist_base_info_sorted) {
+		err = -ENOMEM;
+		goto done;
+	}
+	dist_base_info_sorted_end = dist_base_info_sorted + r->nr_dist_base_types;
+	for (id = 0; id < r->nr_dist_base_types; id++) {
+		dist_t = btf_type_by_id(r->dist_base_btf, id);
+		dist_base_info_sorted[id].name = btf__name_by_offset(r->dist_base_btf,
+								     dist_t->name_off);
+		dist_base_info_sorted[id].id = id;
+		dist_base_info_sorted[id].size = dist_t->size;
+		dist_base_info_sorted[id].needs_size = true;
+	}
+	qsort(dist_base_info_sorted, r->nr_dist_base_types, sizeof(*dist_base_info_sorted),
+	      cmp_btf_name_size);
+
+	/* Mark distilled base struct/union members of split BTF structs/unions
+	 * in id_map with BTF_IS_EMBEDDED; this signals that these types
+	 * need to match both name and size, otherwise embeddding the base
+	 * struct/union in the split type is invalid.
+	 */
+	for (id = r->nr_dist_base_types; id < r->nr_split_types; id++) {
+		err = btf_mark_embedded_composite_type_ids(r, id);
+		if (err)
+			goto done;
+	}
+
+	/* Collect name counts for composite types in base BTF.  If multiple
+	 * instances of a struct/union of the same name exist, we need to use
+	 * size to determine which to map to since name alone is ambiguous.
+	 */
+	base_name_cnt = calloc(r->base_str_len, sizeof(*base_name_cnt));
+	if (!base_name_cnt) {
+		err = -ENOMEM;
+		goto done;
+	}
+	for (id = 1; id < r->nr_base_types; id++) {
+		base_t = btf_type_by_id(r->base_btf, id);
+		if (!btf_is_composite(base_t) || !base_t->name_off)
+			continue;
+		if (base_name_cnt[base_t->name_off] < 255)
+			base_name_cnt[base_t->name_off]++;
+	}
+
+	/* Now search base BTF for matching distilled base BTF types. */
+	for (id = 1; id < r->nr_base_types; id++) {
+		struct btf_name_info *dist_name_info, *dist_name_info_next = NULL;
+		struct btf_name_info base_name_info = {};
+		int dist_kind, base_kind;
+
+		base_t = btf_type_by_id(r->base_btf, id);
+		/* distilled base consists of named types only. */
+		if (!base_t->name_off)
+			continue;
+		base_kind = btf_kind(base_t);
+		base_name_info.id = id;
+		base_name_info.name = btf__name_by_offset(r->base_btf, base_t->name_off);
+		switch (base_kind) {
+		case BTF_KIND_INT:
+		case BTF_KIND_FLOAT:
+		case BTF_KIND_ENUM:
+		case BTF_KIND_ENUM64:
+			/* These types should match both name and size */
+			base_name_info.needs_size = true;
+			base_name_info.size = base_t->size;
+			break;
+		case BTF_KIND_FWD:
+			/* No size considerations for fwds. */
+			break;
+		case BTF_KIND_STRUCT:
+		case BTF_KIND_UNION:
+			/* Size only needs to be used for struct/union if there
+			 * are multiple types in base BTF with the same name.
+			 * If there are multiple _distilled_ types with the same
+			 * name (a very unlikely scenario), that doesn't matter
+			 * unless corresponding _base_ types to match them are
+			 * missing.
+			 */
+			base_name_info.needs_size = base_name_cnt[base_t->name_off] > 1;
+			base_name_info.size = base_t->size;
+			break;
+		default:
+			continue;
+		}
+		/* iterate over all matching distilled base types */
+		for (dist_name_info = search_btf_name_size(&base_name_info, dist_base_info_sorted,
+							   r->nr_dist_base_types);
+		     dist_name_info != NULL; dist_name_info = dist_name_info_next) {
+			/* Are there more distilled matches to process after
+			 * this one?
+			 */
+			dist_name_info_next = dist_name_info + 1;
+			if (dist_name_info_next >= dist_base_info_sorted_end ||
+			    cmp_btf_name_size(&base_name_info, dist_name_info_next))
+				dist_name_info_next = NULL;
+
+			if (!dist_name_info->id || dist_name_info->id > r->nr_dist_base_types) {
+				pr_warn("base BTF id [%d] maps to invalid distilled base BTF id [%d]\n",
+					id, dist_name_info->id);
+				err = -EINVAL;
+				goto done;
+			}
+			dist_t = btf_type_by_id(r->dist_base_btf, dist_name_info->id);
+			dist_kind = btf_kind(dist_t);
+
+			/* Validate that the found distilled type is compatible.
+			 * Do not error out on mismatch as another match may
+			 * occur for an identically-named type.
+			 */
+			switch (dist_kind) {
+			case BTF_KIND_FWD:
+				switch (base_kind) {
+				case BTF_KIND_FWD:
+					if (btf_kflag(dist_t) != btf_kflag(base_t))
+						continue;
+					break;
+				case BTF_KIND_STRUCT:
+					if (btf_kflag(base_t))
+						continue;
+					break;
+				case BTF_KIND_UNION:
+					if (!btf_kflag(base_t))
+						continue;
+					break;
+				default:
+					continue;
+				}
+				break;
+			case BTF_KIND_INT:
+				if (dist_kind != base_kind ||
+				    btf_int_encoding(base_t) != btf_int_encoding(dist_t))
+					continue;
+				break;
+			case BTF_KIND_FLOAT:
+				if (dist_kind != base_kind)
+					continue;
+				break;
+			case BTF_KIND_ENUM:
+				/* ENUM and ENUM64 are encoded as sized ENUM in
+				 * distilled base BTF.
+				 */
+				if (base_kind != dist_kind && base_kind != BTF_KIND_ENUM64)
+					continue;
+				break;
+			case BTF_KIND_STRUCT:
+			case BTF_KIND_UNION:
+				/* size verification is required for embedded
+				 * struct/unions.
+				 */
+				if (r->id_map[dist_name_info->id] == BTF_IS_EMBEDDED &&
+				    base_t->size != dist_t->size)
+					continue;
+				break;
+			default:
+				continue;
+			}
+			if (r->id_map[dist_name_info->id] &&
+			    r->id_map[dist_name_info->id] != BTF_IS_EMBEDDED) {
+				/* we already have a match; this tells us that
+				 * multiple base types of the same name
+				 * have the same size, since for cases where
+				 * multiple types have the same name we match
+				 * on name and size.  In this case, we have
+				 * no way of determining which to relocate
+				 * to in base BTF, so error out.
+				 */
+				pr_warn("distilled base BTF type '%s' [%u], size %u has multiple candidates of the same size (ids [%u, %u]) in base BTF\n",
+					base_name_info.name, dist_name_info->id,
+					base_t->size, id, r->id_map[dist_name_info->id]);
+				err = -EINVAL;
+				goto done;
+			}
+			/* map id and name */
+			r->id_map[dist_name_info->id] = id;
+			r->str_map[dist_t->name_off] = base_t->name_off;
+		}
+	}
+	/* ensure all distilled BTF ids now have a mapping... */
+	for (id = 1; id < r->nr_dist_base_types; id++) {
+		const char *name;
+
+		if (r->id_map[id] && r->id_map[id] != BTF_IS_EMBEDDED)
+			continue;
+		dist_t = btf_type_by_id(r->dist_base_btf, id);
+		name = btf__name_by_offset(r->dist_base_btf, dist_t->name_off);
+		pr_warn("distilled base BTF type '%s' [%d] is not mapped to base BTF id\n",
+			name, id);
+		err = -EINVAL;
+		break;
+	}
+done:
+	free(base_name_cnt);
+	free(dist_base_info_sorted);
+	return err;
+}
+
+/* distilled base should only have named int/float/enum/fwd/struct/union types. */
+static int btf_relocate_validate_distilled_base(struct btf_relocate *r)
+{
+	unsigned int i;
+
+	for (i = 1; i < r->nr_dist_base_types; i++) {
+		struct btf_type *t = btf_type_by_id(r->dist_base_btf, i);
+		int kind = btf_kind(t);
+
+		switch (kind) {
+		case BTF_KIND_INT:
+		case BTF_KIND_FLOAT:
+		case BTF_KIND_ENUM:
+		case BTF_KIND_STRUCT:
+		case BTF_KIND_UNION:
+		case BTF_KIND_FWD:
+			if (t->name_off)
+				break;
+			pr_warn("type [%d], kind [%d] is invalid for distilled base BTF; it is anonymous\n",
+				i, kind);
+			return -EINVAL;
+		default:
+			pr_warn("type [%d] in distilled based BTF has unexpected kind [%d]\n",
+				i, kind);
+			return -EINVAL;
+		}
+	}
+	return 0;
+}
+
+static int btf_relocate_rewrite_strs(struct btf_relocate *r, __u32 i)
+{
+	struct btf_type *t = btf_type_by_id(r->btf, i);
+	struct btf_field_iter it;
+	__u32 *str_off;
+	int off, err;
+
+	err = btf_field_iter_init(&it, t, BTF_FIELD_ITER_STRS);
+	if (err)
+		return err;
+
+	while ((str_off = btf_field_iter_next(&it))) {
+		if (!*str_off)
+			continue;
+		if (*str_off >= r->dist_str_len) {
+			*str_off += r->base_str_len - r->dist_str_len;
+		} else {
+			off = r->str_map[*str_off];
+			if (!off) {
+				pr_warn("string '%s' [offset %u] is not mapped to base BTF",
+					btf__str_by_offset(r->btf, off), *str_off);
+				return -ENOENT;
+			}
+			*str_off = off;
+		}
+	}
+	return 0;
+}
+
+/* If successful, output of relocation is updated BTF with base BTF pointing
+ * at base_btf, and type ids, strings adjusted accordingly.
+ */
+int btf_relocate(struct btf *btf, const struct btf *base_btf, __u32 **id_map)
+{
+	unsigned int nr_types = btf__type_cnt(btf);
+	const struct btf_header *dist_base_hdr;
+	const struct btf_header *base_hdr;
+	struct btf_relocate r = {};
+	int err = 0;
+	__u32 id, i;
+
+	r.dist_base_btf = btf__base_btf(btf);
+	if (!base_btf || r.dist_base_btf == base_btf)
+		return -EINVAL;
+
+	r.nr_dist_base_types = btf__type_cnt(r.dist_base_btf);
+	r.nr_base_types = btf__type_cnt(base_btf);
+	r.nr_split_types = nr_types - r.nr_dist_base_types;
+	r.btf = btf;
+	r.base_btf = base_btf;
+
+	r.id_map = calloc(nr_types, sizeof(*r.id_map));
+	r.str_map = calloc(btf_header(r.dist_base_btf)->str_len, sizeof(*r.str_map));
+	dist_base_hdr = btf_header(r.dist_base_btf);
+	base_hdr = btf_header(r.base_btf);
+	r.dist_str_len = dist_base_hdr->str_len;
+	r.base_str_len = base_hdr->str_len;
+	if (!r.id_map || !r.str_map) {
+		err = -ENOMEM;
+		goto err_out;
+	}
+
+	err = btf_relocate_validate_distilled_base(&r);
+	if (err)
+		goto err_out;
+
+	/* Split BTF ids need to be adjusted as base and distilled base
+	 * have different numbers of types, changing the start id of split
+	 * BTF.
+	 */
+	for (id = r.nr_dist_base_types; id < nr_types; id++)
+		r.id_map[id] = id + r.nr_base_types - r.nr_dist_base_types;
+
+	/* Build a map from distilled base ids to actual base BTF ids; it is used
+	 * to update split BTF id references.  Also build a str_map mapping from
+	 * distilled base BTF names to base BTF names.
+	 */
+	err = btf_relocate_map_distilled_base(&r);
+	if (err)
+		goto err_out;
+
+	/* Next, rewrite type ids in split BTF, replacing split ids with updated
+	 * ids based on number of types in base BTF, and base ids with
+	 * relocated ids from base_btf.
+	 */
+	for (i = 0, id = r.nr_dist_base_types; i < r.nr_split_types; i++, id++) {
+		err = btf_relocate_rewrite_type_id(&r, id);
+		if (err)
+			goto err_out;
+	}
+	/* String offsets now need to be updated using the str_map. */
+	for (i = 0; i < r.nr_split_types; i++) {
+		err = btf_relocate_rewrite_strs(&r, i + r.nr_dist_base_types);
+		if (err)
+			goto err_out;
+	}
+	/* Finally reset base BTF to be base_btf */
+	btf_set_base_btf(btf, base_btf);
+
+	if (id_map) {
+		*id_map = r.id_map;
+		r.id_map = NULL;
+	}
+err_out:
+	free(r.id_map);
+	free(r.str_map);
+	return err;
+}
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 175d1536e070f..8f0d9ea3b1b48 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -420,6 +420,7 @@ LIBBPF_1.4.0 {
 LIBBPF_1.5.0 {
 	global:
 		btf__distill_base;
+		btf__relocate;
 		bpf_map__autoattach;
 		bpf_map__set_autoattach;
 		bpf_program__attach_sockmap;
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index e2f06609c6244..408df59e07719 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -234,6 +234,9 @@ struct btf_type;
 struct btf_type *btf_type_by_id(const struct btf *btf, __u32 type_id);
 const char *btf_kind_str(const struct btf_type *t);
 const struct btf_type *skip_mods_and_typedefs(const struct btf *btf, __u32 id, __u32 *res_id);
+const struct btf_header *btf_header(const struct btf *btf);
+void btf_set_base_btf(struct btf *btf, const struct btf *base_btf);
+int btf_relocate(struct btf *btf, const struct btf *base_btf, __u32 **id_map);
 
 static inline enum btf_func_linkage btf_func_linkage(const struct btf_type *t)
 {
-- 
GitLab


From affdeb50616b190c3236cc2bf116e1b931a43be2 Mon Sep 17 00:00:00 2001
From: Alan Maguire <alan.maguire@oracle.com>
Date: Thu, 13 Jun 2024 10:50:09 +0100
Subject: [PATCH 948/950] selftests/bpf: Extend distilled BTF tests to cover
 BTF relocation

Ensure relocated BTF looks as expected; in this case identical to
original split BTF, with a few duplicate anonymous types added to
split BTF by the relocation process.  Also add relocation tests
for edge cases like missing type in base BTF and multiple types
of the same name.

Signed-off-by: Alan Maguire <alan.maguire@oracle.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/bpf/20240613095014.357981-5-alan.maguire@oracle.com
---
 .../selftests/bpf/prog_tests/btf_distill.c    | 278 ++++++++++++++++++
 1 file changed, 278 insertions(+)

diff --git a/tools/testing/selftests/bpf/prog_tests/btf_distill.c b/tools/testing/selftests/bpf/prog_tests/btf_distill.c
index 5c3a387479620..bfbe795823a29 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_distill.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_distill.c
@@ -217,7 +217,277 @@ static void test_distilled_base(void)
 		"\t'p1' type_id=1",
 		"[25] ARRAY '(anon)' type_id=1 index_type_id=1 nr_elems=3");
 
+	if (!ASSERT_EQ(btf__relocate(btf4, btf1), 0, "relocate_split"))
+		goto cleanup;
+
+	VALIDATE_RAW_BTF(
+		btf4,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] PTR '(anon)' type_id=1",
+		"[3] STRUCT 's1' size=8 vlen=1\n"
+		"\t'f1' type_id=2 bits_offset=0",
+		"[4] STRUCT '(anon)' size=12 vlen=2\n"
+		"\t'f1' type_id=1 bits_offset=0\n"
+		"\t'f2' type_id=3 bits_offset=32",
+		"[5] INT 'unsigned int' size=4 bits_offset=0 nr_bits=32 encoding=(none)",
+		"[6] UNION 'u1' size=12 vlen=2\n"
+		"\t'f1' type_id=1 bits_offset=0\n"
+		"\t'f2' type_id=2 bits_offset=0",
+		"[7] UNION '(anon)' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0",
+		"[8] ENUM 'e1' encoding=UNSIGNED size=4 vlen=1\n"
+		"\t'v1' val=1",
+		"[9] ENUM '(anon)' encoding=UNSIGNED size=4 vlen=1\n"
+		"\t'av1' val=2",
+		"[10] ENUM64 'e641' encoding=SIGNED size=8 vlen=1\n"
+		"\t'v1' val=1024",
+		"[11] ENUM64 '(anon)' encoding=SIGNED size=8 vlen=1\n"
+		"\t'v1' val=1025",
+		"[12] STRUCT 'unneeded' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0",
+		"[13] STRUCT 'embedded' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0",
+		"[14] FUNC_PROTO '(anon)' ret_type_id=1 vlen=1\n"
+		"\t'p1' type_id=1",
+		"[15] ARRAY '(anon)' type_id=1 index_type_id=1 nr_elems=3",
+		"[16] STRUCT 'from_proto' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0",
+		"[17] UNION 'u1' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0",
+		"[18] PTR '(anon)' type_id=3",
+		"[19] PTR '(anon)' type_id=30",
+		"[20] CONST '(anon)' type_id=6",
+		"[21] RESTRICT '(anon)' type_id=31",
+		"[22] VOLATILE '(anon)' type_id=8",
+		"[23] TYPEDEF 'et' type_id=32",
+		"[24] CONST '(anon)' type_id=10",
+		"[25] PTR '(anon)' type_id=33",
+		"[26] STRUCT 'with_embedded' size=4 vlen=1\n"
+		"\t'f1' type_id=13 bits_offset=0",
+		"[27] FUNC 'fn' type_id=34 linkage=static",
+		"[28] TYPEDEF 'arraytype' type_id=35",
+		"[29] FUNC_PROTO '(anon)' ret_type_id=1 vlen=1\n"
+		"\t'p1' type_id=16",
+		/* below here are (duplicate) anon base types added by distill
+		 * process to split BTF.
+		 */
+		"[30] STRUCT '(anon)' size=12 vlen=2\n"
+		"\t'f1' type_id=1 bits_offset=0\n"
+		"\t'f2' type_id=3 bits_offset=32",
+		"[31] UNION '(anon)' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0",
+		"[32] ENUM '(anon)' encoding=UNSIGNED size=4 vlen=1\n"
+		"\t'av1' val=2",
+		"[33] ENUM64 '(anon)' encoding=SIGNED size=8 vlen=1\n"
+		"\t'v1' val=1025",
+		"[34] FUNC_PROTO '(anon)' ret_type_id=1 vlen=1\n"
+		"\t'p1' type_id=1",
+		"[35] ARRAY '(anon)' type_id=1 index_type_id=1 nr_elems=3");
+
+cleanup:
+	btf__free(btf4);
+	btf__free(btf3);
+	btf__free(btf2);
+	btf__free(btf1);
+}
+
+/* ensure we can cope with multiple types with the same name in
+ * distilled base BTF.  In this case because sizes are different,
+ * we can still disambiguate them.
+ */
+static void test_distilled_base_multi(void)
+{
+	struct btf *btf1 = NULL, *btf2 = NULL, *btf3 = NULL, *btf4 = NULL;
+
+	btf1 = btf__new_empty();
+	if (!ASSERT_OK_PTR(btf1, "empty_main_btf"))
+		return;
+	btf__add_int(btf1, "int", 4, BTF_INT_SIGNED);   /* [1] int */
+	btf__add_int(btf1, "int", 8, BTF_INT_SIGNED);	/* [2] int */
+	VALIDATE_RAW_BTF(
+		btf1,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] INT 'int' size=8 bits_offset=0 nr_bits=64 encoding=SIGNED");
+	btf2 = btf__new_empty_split(btf1);
+	if (!ASSERT_OK_PTR(btf2, "empty_split_btf"))
+		goto cleanup;
+	btf__add_ptr(btf2, 1);
+	btf__add_const(btf2, 2);
+	VALIDATE_RAW_BTF(
+		btf2,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] INT 'int' size=8 bits_offset=0 nr_bits=64 encoding=SIGNED",
+		"[3] PTR '(anon)' type_id=1",
+		"[4] CONST '(anon)' type_id=2");
+	if (!ASSERT_EQ(0, btf__distill_base(btf2, &btf3, &btf4),
+		       "distilled_base") ||
+	    !ASSERT_OK_PTR(btf3, "distilled_base") ||
+	    !ASSERT_OK_PTR(btf4, "distilled_split") ||
+	    !ASSERT_EQ(3, btf__type_cnt(btf3), "distilled_base_type_cnt"))
+		goto cleanup;
+	VALIDATE_RAW_BTF(
+		btf3,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] INT 'int' size=8 bits_offset=0 nr_bits=64 encoding=SIGNED");
+	if (!ASSERT_EQ(btf__relocate(btf4, btf1), 0, "relocate_split"))
+		goto cleanup;
+
+	VALIDATE_RAW_BTF(
+		btf4,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] INT 'int' size=8 bits_offset=0 nr_bits=64 encoding=SIGNED",
+		"[3] PTR '(anon)' type_id=1",
+		"[4] CONST '(anon)' type_id=2");
+
+cleanup:
+	btf__free(btf4);
+	btf__free(btf3);
+	btf__free(btf2);
+	btf__free(btf1);
+}
+
+/* If a needed type is not present in the base BTF we wish to relocate
+ * with, btf__relocate() should error our.
+ */
+static void test_distilled_base_missing_err(void)
+{
+	struct btf *btf1 = NULL, *btf2 = NULL, *btf3 = NULL, *btf4 = NULL, *btf5 = NULL;
+
+	btf1 = btf__new_empty();
+	if (!ASSERT_OK_PTR(btf1, "empty_main_btf"))
+		return;
+	btf__add_int(btf1, "int", 4, BTF_INT_SIGNED);   /* [1] int */
+	btf__add_int(btf1, "int", 8, BTF_INT_SIGNED);   /* [2] int */
+	VALIDATE_RAW_BTF(
+		btf1,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] INT 'int' size=8 bits_offset=0 nr_bits=64 encoding=SIGNED");
+	btf2 = btf__new_empty_split(btf1);
+	if (!ASSERT_OK_PTR(btf2, "empty_split_btf"))
+		goto cleanup;
+	btf__add_ptr(btf2, 1);
+	btf__add_const(btf2, 2);
+	VALIDATE_RAW_BTF(
+		btf2,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] INT 'int' size=8 bits_offset=0 nr_bits=64 encoding=SIGNED",
+		"[3] PTR '(anon)' type_id=1",
+		"[4] CONST '(anon)' type_id=2");
+	if (!ASSERT_EQ(0, btf__distill_base(btf2, &btf3, &btf4),
+		       "distilled_base") ||
+	    !ASSERT_OK_PTR(btf3, "distilled_base") ||
+	    !ASSERT_OK_PTR(btf4, "distilled_split") ||
+	    !ASSERT_EQ(3, btf__type_cnt(btf3), "distilled_base_type_cnt"))
+		goto cleanup;
+	VALIDATE_RAW_BTF(
+		btf3,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] INT 'int' size=8 bits_offset=0 nr_bits=64 encoding=SIGNED");
+	btf5 = btf__new_empty();
+	if (!ASSERT_OK_PTR(btf5, "empty_reloc_btf"))
+		return;
+	btf__add_int(btf5, "int", 4, BTF_INT_SIGNED);   /* [1] int */
+	VALIDATE_RAW_BTF(
+		btf5,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED");
+	ASSERT_EQ(btf__relocate(btf4, btf5), -EINVAL, "relocate_split");
+
+cleanup:
+	btf__free(btf5);
+	btf__free(btf4);
+	btf__free(btf3);
+	btf__free(btf2);
+	btf__free(btf1);
+}
+
+/* With 2 types of same size in distilled base BTF, relocation should
+ * fail as we have no means to choose between them.
+ */
+static void test_distilled_base_multi_err(void)
+{
+	struct btf *btf1 = NULL, *btf2 = NULL, *btf3 = NULL, *btf4 = NULL;
+
+	btf1 = btf__new_empty();
+	if (!ASSERT_OK_PTR(btf1, "empty_main_btf"))
+		return;
+	btf__add_int(btf1, "int", 4, BTF_INT_SIGNED);   /* [1] int */
+	btf__add_int(btf1, "int", 4, BTF_INT_SIGNED);   /* [2] int */
+	VALIDATE_RAW_BTF(
+		btf1,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED");
+	btf2 = btf__new_empty_split(btf1);
+	if (!ASSERT_OK_PTR(btf2, "empty_split_btf"))
+		goto cleanup;
+	btf__add_ptr(btf2, 1);
+	btf__add_const(btf2, 2);
+	VALIDATE_RAW_BTF(
+		btf2,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[3] PTR '(anon)' type_id=1",
+		"[4] CONST '(anon)' type_id=2");
+	if (!ASSERT_EQ(0, btf__distill_base(btf2, &btf3, &btf4),
+		       "distilled_base") ||
+	    !ASSERT_OK_PTR(btf3, "distilled_base") ||
+	    !ASSERT_OK_PTR(btf4, "distilled_split") ||
+	    !ASSERT_EQ(3, btf__type_cnt(btf3), "distilled_base_type_cnt"))
+		goto cleanup;
+	VALIDATE_RAW_BTF(
+		btf3,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED");
+	ASSERT_EQ(btf__relocate(btf4, btf1), -EINVAL, "relocate_split");
+cleanup:
+	btf__free(btf4);
+	btf__free(btf3);
+	btf__free(btf2);
+	btf__free(btf1);
+}
+
+/* With 2 types of same size in base BTF, relocation should
+ * fail as we have no means to choose between them.
+ */
+static void test_distilled_base_multi_err2(void)
+{
+	struct btf *btf1 = NULL, *btf2 = NULL, *btf3 = NULL, *btf4 = NULL, *btf5 = NULL;
+
+	btf1 = btf__new_empty();
+	if (!ASSERT_OK_PTR(btf1, "empty_main_btf"))
+		return;
+	btf__add_int(btf1, "int", 4, BTF_INT_SIGNED);   /* [1] int */
+	VALIDATE_RAW_BTF(
+		btf1,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED");
+	btf2 = btf__new_empty_split(btf1);
+	if (!ASSERT_OK_PTR(btf2, "empty_split_btf"))
+		goto cleanup;
+	btf__add_ptr(btf2, 1);
+	VALIDATE_RAW_BTF(
+		btf2,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] PTR '(anon)' type_id=1");
+	if (!ASSERT_EQ(0, btf__distill_base(btf2, &btf3, &btf4),
+		       "distilled_base") ||
+	    !ASSERT_OK_PTR(btf3, "distilled_base") ||
+	    !ASSERT_OK_PTR(btf4, "distilled_split") ||
+	    !ASSERT_EQ(2, btf__type_cnt(btf3), "distilled_base_type_cnt"))
+		goto cleanup;
+	VALIDATE_RAW_BTF(
+		btf3,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED");
+	btf5 = btf__new_empty();
+	if (!ASSERT_OK_PTR(btf5, "empty_reloc_btf"))
+		return;
+	btf__add_int(btf5, "int", 4, BTF_INT_SIGNED);   /* [1] int */
+	btf__add_int(btf5, "int", 4, BTF_INT_SIGNED);   /* [2] int */
+	VALIDATE_RAW_BTF(
+		btf5,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED");
+	ASSERT_EQ(btf__relocate(btf4, btf5), -EINVAL, "relocate_split");
 cleanup:
+	btf__free(btf5);
 	btf__free(btf4);
 	btf__free(btf3);
 	btf__free(btf2);
@@ -269,6 +539,14 @@ void test_btf_distill(void)
 {
 	if (test__start_subtest("distilled_base"))
 		test_distilled_base();
+	if (test__start_subtest("distilled_base_multi"))
+		test_distilled_base_multi();
+	if (test__start_subtest("distilled_base_missing_err"))
+		test_distilled_base_missing_err();
+	if (test__start_subtest("distilled_base_multi_err"))
+		test_distilled_base_multi_err();
+	if (test__start_subtest("distilled_base_multi_err2"))
+		test_distilled_base_multi_err2();
 	if (test__start_subtest("distilled_base_vmlinux"))
 		test_distilled_base_vmlinux();
 }
-- 
GitLab


From c86f180ffc993975fed5907a869fc9b1555d0cfb Mon Sep 17 00:00:00 2001
From: Eduard Zingerman <eddyz87@gmail.com>
Date: Thu, 13 Jun 2024 10:50:10 +0100
Subject: [PATCH 949/950] libbpf: Make btf_parse_elf process .BTF.base
 transparently

Update btf_parse_elf() to check if .BTF.base section is present.
The logic is as follows:

  if .BTF.base section exists:
     distilled_base := btf_new(.BTF.base)
  if distilled_base:
     btf := btf_new(.BTF, .base_btf=distilled_base)
     if base_btf:
        btf_relocate(btf, base_btf)
  else:
     btf := btf_new(.BTF)
  return btf

In other words:
- if .BTF.base section exists, load BTF from it and use it as a base
  for .BTF load;
- if base_btf is specified and .BTF.base section exist, relocate newly
  loaded .BTF against base_btf.

Signed-off-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Alan Maguire <alan.maguire@oracle.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20240613095014.357981-6-alan.maguire@oracle.com
---
 tools/lib/bpf/btf.c | 164 +++++++++++++++++++++++++++++---------------
 tools/lib/bpf/btf.h |   1 +
 2 files changed, 111 insertions(+), 54 deletions(-)

diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 5e20354fbcfa8..ef1b2f573c1bc 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -116,6 +116,9 @@ struct btf {
 	/* whether strings are already deduplicated */
 	bool strs_deduped;
 
+	/* whether base_btf should be freed in btf_free for this instance */
+	bool owns_base;
+
 	/* BTF object FD, if loaded into kernel */
 	int fd;
 
@@ -969,6 +972,8 @@ void btf__free(struct btf *btf)
 	free(btf->raw_data);
 	free(btf->raw_data_swapped);
 	free(btf->type_offs);
+	if (btf->owns_base)
+		btf__free(btf->base_btf);
 	free(btf);
 }
 
@@ -1084,53 +1089,38 @@ struct btf *btf__new_split(const void *data, __u32 size, struct btf *base_btf)
 	return libbpf_ptr(btf_new(data, size, base_btf));
 }
 
-static struct btf *btf_parse_elf(const char *path, struct btf *base_btf,
-				 struct btf_ext **btf_ext)
+struct btf_elf_secs {
+	Elf_Data *btf_data;
+	Elf_Data *btf_ext_data;
+	Elf_Data *btf_base_data;
+};
+
+static int btf_find_elf_sections(Elf *elf, const char *path, struct btf_elf_secs *secs)
 {
-	Elf_Data *btf_data = NULL, *btf_ext_data = NULL;
-	int err = 0, fd = -1, idx = 0;
-	struct btf *btf = NULL;
 	Elf_Scn *scn = NULL;
-	Elf *elf = NULL;
+	Elf_Data *data;
 	GElf_Ehdr ehdr;
 	size_t shstrndx;
+	int idx = 0;
 
-	if (elf_version(EV_CURRENT) == EV_NONE) {
-		pr_warn("failed to init libelf for %s\n", path);
-		return ERR_PTR(-LIBBPF_ERRNO__LIBELF);
-	}
-
-	fd = open(path, O_RDONLY | O_CLOEXEC);
-	if (fd < 0) {
-		err = -errno;
-		pr_warn("failed to open %s: %s\n", path, strerror(errno));
-		return ERR_PTR(err);
-	}
-
-	err = -LIBBPF_ERRNO__FORMAT;
-
-	elf = elf_begin(fd, ELF_C_READ, NULL);
-	if (!elf) {
-		pr_warn("failed to open %s as ELF file\n", path);
-		goto done;
-	}
 	if (!gelf_getehdr(elf, &ehdr)) {
 		pr_warn("failed to get EHDR from %s\n", path);
-		goto done;
+		goto err;
 	}
 
 	if (elf_getshdrstrndx(elf, &shstrndx)) {
 		pr_warn("failed to get section names section index for %s\n",
 			path);
-		goto done;
+		goto err;
 	}
 
 	if (!elf_rawdata(elf_getscn(elf, shstrndx), NULL)) {
 		pr_warn("failed to get e_shstrndx from %s\n", path);
-		goto done;
+		goto err;
 	}
 
 	while ((scn = elf_nextscn(elf, scn)) != NULL) {
+		Elf_Data **field;
 		GElf_Shdr sh;
 		char *name;
 
@@ -1138,42 +1128,102 @@ static struct btf *btf_parse_elf(const char *path, struct btf *base_btf,
 		if (gelf_getshdr(scn, &sh) != &sh) {
 			pr_warn("failed to get section(%d) header from %s\n",
 				idx, path);
-			goto done;
+			goto err;
 		}
 		name = elf_strptr(elf, shstrndx, sh.sh_name);
 		if (!name) {
 			pr_warn("failed to get section(%d) name from %s\n",
 				idx, path);
-			goto done;
+			goto err;
 		}
-		if (strcmp(name, BTF_ELF_SEC) == 0) {
-			btf_data = elf_getdata(scn, 0);
-			if (!btf_data) {
-				pr_warn("failed to get section(%d, %s) data from %s\n",
-					idx, name, path);
-				goto done;
-			}
-			continue;
-		} else if (btf_ext && strcmp(name, BTF_EXT_ELF_SEC) == 0) {
-			btf_ext_data = elf_getdata(scn, 0);
-			if (!btf_ext_data) {
-				pr_warn("failed to get section(%d, %s) data from %s\n",
-					idx, name, path);
-				goto done;
-			}
+
+		if (strcmp(name, BTF_ELF_SEC) == 0)
+			field = &secs->btf_data;
+		else if (strcmp(name, BTF_EXT_ELF_SEC) == 0)
+			field = &secs->btf_ext_data;
+		else if (strcmp(name, BTF_BASE_ELF_SEC) == 0)
+			field = &secs->btf_base_data;
+		else
 			continue;
+
+		data = elf_getdata(scn, 0);
+		if (!data) {
+			pr_warn("failed to get section(%d, %s) data from %s\n",
+				idx, name, path);
+			goto err;
 		}
+		*field = data;
+	}
+
+	return 0;
+
+err:
+	return -LIBBPF_ERRNO__FORMAT;
+}
+
+static struct btf *btf_parse_elf(const char *path, struct btf *base_btf,
+				 struct btf_ext **btf_ext)
+{
+	struct btf_elf_secs secs = {};
+	struct btf *dist_base_btf = NULL;
+	struct btf *btf = NULL;
+	int err = 0, fd = -1;
+	Elf *elf = NULL;
+
+	if (elf_version(EV_CURRENT) == EV_NONE) {
+		pr_warn("failed to init libelf for %s\n", path);
+		return ERR_PTR(-LIBBPF_ERRNO__LIBELF);
+	}
+
+	fd = open(path, O_RDONLY | O_CLOEXEC);
+	if (fd < 0) {
+		err = -errno;
+		pr_warn("failed to open %s: %s\n", path, strerror(errno));
+		return ERR_PTR(err);
 	}
 
-	if (!btf_data) {
+	elf = elf_begin(fd, ELF_C_READ, NULL);
+	if (!elf) {
+		pr_warn("failed to open %s as ELF file\n", path);
+		goto done;
+	}
+
+	err = btf_find_elf_sections(elf, path, &secs);
+	if (err)
+		goto done;
+
+	if (!secs.btf_data) {
 		pr_warn("failed to find '%s' ELF section in %s\n", BTF_ELF_SEC, path);
 		err = -ENODATA;
 		goto done;
 	}
-	btf = btf_new(btf_data->d_buf, btf_data->d_size, base_btf);
-	err = libbpf_get_error(btf);
-	if (err)
+
+	if (secs.btf_base_data) {
+		dist_base_btf = btf_new(secs.btf_base_data->d_buf, secs.btf_base_data->d_size,
+					NULL);
+		if (IS_ERR(dist_base_btf)) {
+			err = PTR_ERR(dist_base_btf);
+			dist_base_btf = NULL;
+			goto done;
+		}
+	}
+
+	btf = btf_new(secs.btf_data->d_buf, secs.btf_data->d_size,
+		      dist_base_btf ?: base_btf);
+	if (IS_ERR(btf)) {
+		err = PTR_ERR(btf);
 		goto done;
+	}
+	if (dist_base_btf && base_btf) {
+		err = btf__relocate(btf, base_btf);
+		if (err)
+			goto done;
+		btf__free(dist_base_btf);
+		dist_base_btf = NULL;
+	}
+
+	if (dist_base_btf)
+		btf->owns_base = true;
 
 	switch (gelf_getclass(elf)) {
 	case ELFCLASS32:
@@ -1187,11 +1237,12 @@ static struct btf *btf_parse_elf(const char *path, struct btf *base_btf,
 		break;
 	}
 
-	if (btf_ext && btf_ext_data) {
-		*btf_ext = btf_ext__new(btf_ext_data->d_buf, btf_ext_data->d_size);
-		err = libbpf_get_error(*btf_ext);
-		if (err)
+	if (btf_ext && secs.btf_ext_data) {
+		*btf_ext = btf_ext__new(secs.btf_ext_data->d_buf, secs.btf_ext_data->d_size);
+		if (IS_ERR(*btf_ext)) {
+			err = PTR_ERR(*btf_ext);
 			goto done;
+		}
 	} else if (btf_ext) {
 		*btf_ext = NULL;
 	}
@@ -1205,6 +1256,7 @@ done:
 
 	if (btf_ext)
 		btf_ext__free(*btf_ext);
+	btf__free(dist_base_btf);
 	btf__free(btf);
 
 	return ERR_PTR(err);
@@ -5598,5 +5650,9 @@ void btf_set_base_btf(struct btf *btf, const struct btf *base_btf)
 
 int btf__relocate(struct btf *btf, const struct btf *base_btf)
 {
-	return libbpf_err(btf_relocate(btf, base_btf, NULL));
+	int err = btf_relocate(btf, base_btf, NULL);
+
+	if (!err)
+		btf->owns_base = false;
+	return libbpf_err(err);
 }
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index 8a93120b7385b..b68d216837a92 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -18,6 +18,7 @@ extern "C" {
 
 #define BTF_ELF_SEC ".BTF"
 #define BTF_EXT_ELF_SEC ".BTF.ext"
+#define BTF_BASE_ELF_SEC ".BTF.base"
 #define MAPS_ELF_SEC ".maps"
 
 struct btf;
-- 
GitLab


From 6ba77385f386053cea2a1cad33717de74a26db4e Mon Sep 17 00:00:00 2001
From: Alan Maguire <alan.maguire@oracle.com>
Date: Thu, 13 Jun 2024 10:50:11 +0100
Subject: [PATCH 950/950] resolve_btfids: Handle presence of .BTF.base section

Now that btf_parse_elf() handles .BTF.base section presence,
we need to ensure that resolve_btfids uses .BTF.base when present
rather than the vmlinux base BTF passed in via the -B option.
Detect .BTF.base section presence and unset the base BTF path
to ensure that BTF ELF parsing will do the right thing.

Signed-off-by: Alan Maguire <alan.maguire@oracle.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Reviewed-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/bpf/20240613095014.357981-7-alan.maguire@oracle.com
---
 tools/bpf/resolve_btfids/main.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/tools/bpf/resolve_btfids/main.c b/tools/bpf/resolve_btfids/main.c
index af393c7dee1f1..936ef95c3d323 100644
--- a/tools/bpf/resolve_btfids/main.c
+++ b/tools/bpf/resolve_btfids/main.c
@@ -409,6 +409,14 @@ static int elf_collect(struct object *obj)
 			obj->efile.idlist       = data;
 			obj->efile.idlist_shndx = idx;
 			obj->efile.idlist_addr  = sh.sh_addr;
+		} else if (!strcmp(name, BTF_BASE_ELF_SEC)) {
+			/* If a .BTF.base section is found, do not resolve
+			 * BTF ids relative to vmlinux; resolve relative
+			 * to the .BTF.base section instead.  btf__parse_split()
+			 * will take care of this once the base BTF it is
+			 * passed is NULL.
+			 */
+			obj->base_btf_path = NULL;
 		}
 
 		if (compressed_section_fix(elf, scn, &sh))
-- 
GitLab