[PATCH ath-next 2/8] wifi: ath10k: wake blocked waiters when entering WEDGED state

[Kang Yang]

Commit c256a94d1b1b ("wifi: ath10k: shutdown driver when
hardware is unreliable") added a fail-count based transition
to ATH10K_STATE_WEDGED after repeated recovery failures.

When recovery starts, ath10k_core_restart() sets
ATH10K_FLAG_CRASH_FLUSH and wakes waiters already blocked at
the time the failure is detected. However, additional waits
may be created later while the recovery attempt is still in
progress.

If recovery ultimately fails and the device transitions to
ATH10K_STATE_WEDGED, those later waiters continue sleeping
until their individual timeouts expire even though no further
progress is possible.

On suspend/resume, these extra wait timeouts consume watchdog
budget. Crash logs show cases where one or two such timeouts
are enough to cause the suspend watchdog to fire before the
driver finishes shutting down.

Apply the same CRASH_FLUSH, queue-stop and waiter wakeup
handling when entering ATH10K_STATE_WEDGED so blocked callers
fail immediately once the driver gives up.

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

Fixes: c256a94d1b1b ("wifi: ath10k: shutdown driver when hardware is unreliable")
Signed-off-by: Kang Yang <kang.yang at oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath10k/core.c | 43 +++++++++++++++++++++++-----------
 1 file changed, 29 insertions(+), 14 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/core.c b/drivers/net/wireless/ath/ath10k/core.c
index ad087e64db9f..be516dc32c1d 100644
--- a/drivers/net/wireless/ath/ath10k/core.c
+++ b/drivers/net/wireless/ath/ath10k/core.c
@@ -2491,6 +2491,32 @@ static int ath10k_init_hw_params(struct ath10k *ar)
 	return 0;
 }
 
+static void ath10k_core_wake_all_waiters(struct ath10k *ar)
+{
+	complete(&ar->scan.started);
+	complete(&ar->scan.completed);
+	complete(&ar->scan.on_channel);
+	complete(&ar->offchan_tx_completed);
+	complete(&ar->install_key_done);
+	complete(&ar->vdev_setup_done);
+	complete(&ar->vdev_delete_done);
+	complete(&ar->thermal.wmi_sync);
+	complete(&ar->bss_survey_done);
+	wake_up(&ar->htt.empty_tx_wq);
+	wake_up(&ar->wmi.tx_credits_wq);
+	wake_up(&ar->peer_mapping_wq);
+}
+
+static void ath10k_core_enter_wedged(struct ath10k *ar)
+{
+	ar->state = ATH10K_STATE_WEDGED;
+
+	set_bit(ATH10K_FLAG_CRASH_FLUSH, &ar->dev_flags);
+
+	ieee80211_stop_queues(ar->hw);
+	ath10k_core_wake_all_waiters(ar);
+}
+
 static void ath10k_core_recovery_check_work(struct work_struct *work)
 {
 	struct ath10k *ar = container_of(work, struct ath10k, recovery_check_work);
@@ -2516,7 +2542,7 @@ static void ath10k_core_recovery_check_work(struct work_struct *work)
 	if (fail_count >= ATH10K_RECOVERY_MAX_FAIL_COUNT) {
 		ath10k_err(ar, "consecutive fail %d times, will shutdown driver!",
 			   fail_count);
-		ar->state = ATH10K_STATE_WEDGED;
+		ath10k_core_enter_wedged(ar);
 	}
 }
 
@@ -2591,18 +2617,7 @@ static void ath10k_core_restart(struct work_struct *work)
 
 	ieee80211_stop_queues(ar->hw);
 	ath10k_drain_tx(ar);
-	complete(&ar->scan.started);
-	complete(&ar->scan.completed);
-	complete(&ar->scan.on_channel);
-	complete(&ar->offchan_tx_completed);
-	complete(&ar->install_key_done);
-	complete(&ar->vdev_setup_done);
-	complete(&ar->vdev_delete_done);
-	complete(&ar->thermal.wmi_sync);
-	complete(&ar->bss_survey_done);
-	wake_up(&ar->htt.empty_tx_wq);
-	wake_up(&ar->wmi.tx_credits_wq);
-	wake_up(&ar->peer_mapping_wq);
+	ath10k_core_wake_all_waiters(ar);
 
 	/* TODO: We can have one instance of cancelling coverage_class_work by
 	 * moving it to ath10k_halt(), so that both stop() and restart() would
@@ -2630,7 +2645,7 @@ static void ath10k_core_restart(struct work_struct *work)
 		/* hw restart might be requested from multiple places */
 		break;
 	case ATH10K_STATE_RESTARTED:
-		ar->state = ATH10K_STATE_WEDGED;
+		ath10k_core_enter_wedged(ar);
 		fallthrough;
 	case ATH10K_STATE_WEDGED:
 		ath10k_warn(ar, "device is wedged, will not restart\n");

-- 
2.34.1