[PATCH ath-next v2 5/8] wifi: ath10k: check the recovery deadline on its own timeline

[Kang Yang]

Recovery timeout enforcement currently advances only when
new recovery triggers arrive.

In practice, the interval between triggers is not bounded.
Additional timeout handling, workqueue congestion, or other
recovery-related activities may delay subsequent triggers,
causing the effective recovery timeout to extend well beyond
the intended ATH10K_RECOVERY_DEADLINE_HZ limit.

If recovery becomes stuck and no further trigger is generated,
deadline enforcement may stop progressing entirely.

Convert recovery_check_work() into self-rearming delayed_work
so timeout monitoring follows its own timeline while recovery
is in progress, independent of future recovery triggers.

Tested-on: QCA6174 hw3.2 PCI WLAN.RM.4.4.1-00288-QCARMSWPZ-1
Tested-on: QCA6174 hw3.2 SDIO WLAN.RMH.4.4.1-00189

Signed-off-by: Kang Yang <kang.yang at oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath10k/core.c | 18 ++++++++++--------
 drivers/net/wireless/ath/ath10k/core.h |  2 +-
 drivers/net/wireless/ath/ath10k/mac.c  |  5 ++++-
 3 files changed, 15 insertions(+), 10 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/core.c b/drivers/net/wireless/ath/ath10k/core.c
index 25e9a8f0ec8a..6b6b80242cd1 100644
--- a/drivers/net/wireless/ath/ath10k/core.c
+++ b/drivers/net/wireless/ath/ath10k/core.c
@@ -2525,7 +2525,8 @@ static void ath10k_core_enter_wedged(struct ath10k *ar)
 
 static void ath10k_core_recovery_check_work(struct work_struct *work)
 {
-	struct ath10k *ar = container_of(work, struct ath10k, recovery_check_work);
+	struct ath10k *ar = container_of(work, struct ath10k,
+					 recovery_check_work.work);
 	unsigned long recovery_start = READ_ONCE(ar->recovery_start_jiffies);
 	int fail_count;
 
@@ -2539,9 +2540,6 @@ static void ath10k_core_recovery_check_work(struct work_struct *work)
 	if (!atomic_read(&ar->pending_recovery))
 		return;
 
-	if (!time_after(jiffies, recovery_start + ATH10K_RECOVERY_TIMEOUT_HZ))
-		return;
-
 	/* Record the continuous recovery fail count when recovery is late. */
 	fail_count = atomic_inc_return(&ar->fail_cont_count);
 
@@ -2550,7 +2548,12 @@ static void ath10k_core_recovery_check_work(struct work_struct *work)
 		ath10k_err(ar, "recovery timeout %ums, fail count %d, shutting down driver!",
 			   jiffies_to_msecs(jiffies - recovery_start), fail_count);
 		ath10k_core_enter_wedged(ar);
+		return;
 	}
+
+	/* Keep checking on our own even if no further trigger arrives. */
+	queue_delayed_work(ar->workqueue_aux, &ar->recovery_check_work,
+			   ATH10K_RECOVERY_TIMEOUT_HZ);
 }
 
 void ath10k_core_start_recovery(struct ath10k *ar)
@@ -2571,9 +2574,8 @@ void ath10k_core_start_recovery(struct ath10k *ar)
 	atomic_set(&ar->fail_cont_count, 0);
 	WRITE_ONCE(ar->recovery_start_jiffies, jiffies);
 	queue_work(ar->workqueue, &ar->restart_work);
-
-	/* Start monitoring after publishing the recovery timestamp. */
-	queue_work(ar->workqueue_aux, &ar->recovery_check_work);
+	queue_delayed_work(ar->workqueue_aux, &ar->recovery_check_work,
+			   ATH10K_RECOVERY_TIMEOUT_HZ);
 }
 EXPORT_SYMBOL(ath10k_core_start_recovery);
 
@@ -3755,7 +3757,7 @@ struct ath10k *ath10k_core_create(size_t priv_size, struct device *dev,
 
 	INIT_WORK(&ar->register_work, ath10k_core_register_work);
 	INIT_WORK(&ar->restart_work, ath10k_core_restart);
-	INIT_WORK(&ar->recovery_check_work, ath10k_core_recovery_check_work);
+	INIT_DELAYED_WORK(&ar->recovery_check_work, ath10k_core_recovery_check_work);
 	INIT_WORK(&ar->set_coverage_class_work,
 		  ath10k_core_set_coverage_class_work);
 
diff --git a/drivers/net/wireless/ath/ath10k/core.h b/drivers/net/wireless/ath/ath10k/core.h
index 0319da3ec022..a1ded2cba103 100644
--- a/drivers/net/wireless/ath/ath10k/core.h
+++ b/drivers/net/wireless/ath/ath10k/core.h
@@ -1213,7 +1213,7 @@ struct ath10k {
 
 	struct work_struct register_work;
 	struct work_struct restart_work;
-	struct work_struct recovery_check_work;
+	struct delayed_work recovery_check_work;
 	struct work_struct bundle_tx_work;
 	struct work_struct tx_complete_work;
 
diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c
index 45a3082d5a64..693b935536c2 100644
--- a/drivers/net/wireless/ath/ath10k/mac.c
+++ b/drivers/net/wireless/ath/ath10k/mac.c
@@ -5428,7 +5428,7 @@ static void ath10k_stop(struct ieee80211_hw *hw, bool suspend)
 	cancel_work_sync(&ar->set_coverage_class_work);
 	cancel_delayed_work_sync(&ar->scan.timeout);
 	cancel_work_sync(&ar->restart_work);
-	cancel_work_sync(&ar->recovery_check_work);
+	cancel_delayed_work_sync(&ar->recovery_check_work);
 }
 
 static int ath10k_config_ps(struct ath10k *ar)
@@ -8173,6 +8173,9 @@ static void ath10k_reconfig_complete(struct ieee80211_hw *hw,
 		ar->state = ATH10K_STATE_ON;
 		ieee80211_wake_queues(ar->hw);
 
+		/* Cancel the monitor first so it cannot bump the count after reset. */
+		cancel_delayed_work_sync(&ar->recovery_check_work);
+
 		/* Clear recovery state. */
 		complete(&ar->driver_recovery);
 		atomic_set(&ar->fail_cont_count, 0);

-- 
2.34.1