4 files changed, 63 insertions, 9 deletions

diff --git a/drivers/net/wireless/ath/ath10k/core.c b/drivers/net/wireless/ath/ath10k/core.c
index b3294287bce1..7b6812909ab3 100644
--- a/drivers/net/wireless/ath/ath10k/core.c
+++ b/drivers/net/wireless/ath/ath10k/core.c
@@ -2484,12 +2484,50 @@ static int ath10k_init_hw_params(struct ath10k *ar)
 	return 0;
 }
 
+static bool ath10k_core_needs_recovery(struct ath10k *ar)
+{
+	long time_left;
+
+	/* Sometimes the recovery will fail and then the next all recovery fail,
+	 * so avoid infinite recovery.
+	 */
+	if (atomic_read(&ar->fail_cont_count) >= ATH10K_RECOVERY_MAX_FAIL_COUNT) {
+		ath10k_err(ar, "consecutive fail %d times, will shutdown driver!",
+			   atomic_read(&ar->fail_cont_count));
+		ar->state = ATH10K_STATE_WEDGED;
+		return false;
+	}
+
+	ath10k_dbg(ar, ATH10K_DBG_BOOT, "total recovery count: %d", ++ar->recovery_count);
+
+	if (atomic_read(&ar->pending_recovery)) {
+		/* Sometimes it happened another recovery work before the previous one
+		 * completed, then the second recovery work will destroy the previous
+		 * one, thus below is to avoid that.
+		 */
+		time_left = wait_for_completion_timeout(&ar->driver_recovery,
+							ATH10K_RECOVERY_TIMEOUT_HZ);
+		if (time_left) {
+			ath10k_warn(ar, "previous recovery succeeded, skip this!\n");
+			return false;
+		}
+
+		/* Record the continuous recovery fail count when recovery failed. */
+		atomic_inc(&ar->fail_cont_count);
+
+		/* Avoid having multiple recoveries at the same time. */
+		return false;
+	}
+
+	atomic_inc(&ar->pending_recovery);
+
+	return true;
+}
+
 void ath10k_core_start_recovery(struct ath10k *ar)
 {
-	if (test_and_set_bit(ATH10K_FLAG_RESTARTING, &ar->dev_flags)) {
-		ath10k_warn(ar, "already restarting\n");
+	if (!ath10k_core_needs_recovery(ar))
 		return;
-	}
 
 	queue_work(ar->workqueue, &ar->restart_work);
 }
@@ -2525,6 +2563,8 @@ static void ath10k_core_restart(struct work_struct *work)
 	struct ath10k *ar = container_of(work, struct ath10k, restart_work);
 	int ret;
 
+	reinit_completion(&ar->driver_recovery);
+
 	set_bit(ATH10K_FLAG_CRASH_FLUSH, &ar->dev_flags);
 
 	/* Place a barrier to make sure the compiler doesn't reorder
@@ -2589,8 +2629,6 @@ static void ath10k_core_restart(struct work_struct *work)
 	if (ret)
 		ath10k_warn(ar, "failed to send firmware crash dump via devcoredump: %d",
 			    ret);
-
-	complete(&ar->driver_recovery);
 }
 
 static void ath10k_core_set_coverage_class_work(struct work_struct *work)
diff --git a/drivers/net/wireless/ath/ath10k/core.h b/drivers/net/wireless/ath/ath10k/core.h
index 446dca74f06a..85e16c945b5c 100644
--- a/drivers/net/wireless/ath/ath10k/core.h
+++ b/drivers/net/wireless/ath/ath10k/core.h
@@ -4,6 +4,7 @@
  * Copyright (c) 2011-2017 Qualcomm Atheros, Inc.
  * Copyright (c) 2018-2019, The Linux Foundation. All rights reserved.
  * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries.
  */
 
 #ifndef _CORE_H_
@@ -87,6 +88,8 @@
 				  IEEE80211_IFACE_SKIP_SDATA_NOT_IN_DRIVER)
 #define ATH10K_ITER_RESUME_FLAGS (IEEE80211_IFACE_ITER_RESUME_ALL |\
 				  IEEE80211_IFACE_SKIP_SDATA_NOT_IN_DRIVER)
+#define ATH10K_RECOVERY_TIMEOUT_HZ			(5 * HZ)
+#define ATH10K_RECOVERY_MAX_FAIL_COUNT			4
 
 struct ath10k;
 
@@ -865,9 +868,6 @@ enum ath10k_dev_flags {
 	/* Per Station statistics service */
 	ATH10K_FLAG_PEER_STATS,
 
-	/* Indicates that ath10k device is during recovery process and not complete */
-	ATH10K_FLAG_RESTARTING,
-
 	/* protected by conf_mutex */
 	ATH10K_FLAG_NAPI_ENABLED,
 };
@@ -1211,6 +1211,11 @@ struct ath10k {
 	struct work_struct bundle_tx_work;
 	struct work_struct tx_complete_work;
 
+	atomic_t pending_recovery;
+	unsigned int recovery_count;
+	/* continuous recovery fail count */
+	atomic_t fail_cont_count;
+
 	/* cycle count is reported twice for each visited channel during scan.
 	 * access protected by data_lock
 	 */
diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c
index 6b467696bc98..6493731333ab 100644
--- a/drivers/net/wireless/ath/ath10k/mac.c
+++ b/drivers/net/wireless/ath/ath10k/mac.c
@@ -8125,7 +8125,12 @@ static void ath10k_reconfig_complete(struct ieee80211_hw *hw,
 		ath10k_info(ar, "device successfully recovered\n");
 		ar->state = ATH10K_STATE_ON;
 		ieee80211_wake_queues(ar->hw);
-		clear_bit(ATH10K_FLAG_RESTARTING, &ar->dev_flags);
+
+		/* Clear recovery state. */
+		complete(&ar->driver_recovery);
+		atomic_set(&ar->fail_cont_count, 0);
+		atomic_set(&ar->pending_recovery, 0);
+
 		if (ar->hw_params.hw_restart_disconnect) {
 			list_for_each_entry(arvif, &ar->arvifs, list) {
 				if (arvif->is_up && arvif->vdev_type == WMI_VDEV_TYPE_STA)
diff --git a/drivers/net/wireless/ath/ath10k/wmi.c b/drivers/net/wireless/ath/ath10k/wmi.c
index 5e061f7525a6..09066e6aca40 100644
--- a/drivers/net/wireless/ath/ath10k/wmi.c
+++ b/drivers/net/wireless/ath/ath10k/wmi.c
@@ -4,6 +4,7 @@
  * Copyright (c) 2011-2017 Qualcomm Atheros, Inc.
  * Copyright (c) 2018-2019, The Linux Foundation. All rights reserved.
  * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries.
  */
 
 #include <linux/skbuff.h>
@@ -1941,6 +1942,11 @@ int ath10k_wmi_cmd_send(struct ath10k *ar, struct sk_buff *skb, u32 cmd_id)
 	}
 
 	wait_event_timeout(ar->wmi.tx_credits_wq, ({
+		if (ar->state == ATH10K_STATE_WEDGED) {
+			ret = -ESHUTDOWN;
+			ath10k_dbg(ar, ATH10K_DBG_WMI,
+				   "drop wmi command %d, hardware is wedged\n", cmd_id);
+		}
 		/* try to send pending beacons first. they take priority */
 		ath10k_wmi_tx_beacons_nowait(ar);