Commit 670d4949 authored by Aaradhana Sahu's avatar Aaradhana Sahu Committed by Kalle Valo

wifi: ath12k: Fix WARN_ON during firmware crash in split-phy

Whenever firmware is crashed in split-phy below WARN_ON() triggered:

WARNING: CPU: 3 PID: 82 at net/mac80211/driver-ops.c:41 drv_stop+0xac/0xbc
Modules linked in: ath12k qmi_helpers
CPU: 3 PID: 82 Comm: kworker/3:2 Tainted: G      D W          6.9.0-next-20240520-00113-gd981a3784e15 #39
Hardware name: Qualcomm Technologies, Inc. IPQ9574/AP-AL02-C9 (DT)
Workqueue: events_freezable ieee80211_restart_work
pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--)
pc : drv_stop+0xac/0xbc
lr : ieee80211_stop_device+0x54/0x64
sp : ffff8000848dbb20
x29: ffff8000848dbb20 x28: 0000000000000790 x27: ffff000014d78900
x26: ffff000014d791f8 x25: ffff000007f0d9b0 x24: 0000000000000018
x23: 0000000000000001 x22: 0000000000000000 x21: ffff000014d78e10
x20: ffff800081dc0000 x19: ffff000014d78900 x18: ffffffffffffffff
x17: ffff7fffbca84000 x16: ffff800083fe0000 x15: ffff800081dc0b48
x14: 0000000000000076 x13: 0000000000000076 x12: 0000000000000001
x11: 0000000000000000 x10: 0000000000000a60 x9 : ffff8000848db980
x8 : ffff000000dddfc0 x7 : 0000000000000400 x6 : ffff800083b012d8
x5 : ffff800083b012d8 x4 : 0000000000000000 x3 : ffff000014d78398
x2 : 0000000000000000 x1 : 0000000000000000 x0 : ffff000014d78900
Call trace:
 drv_stop+0xac/0xbc
 ieee80211_stop_device+0x54/0x64
 ieee80211_do_stop+0x5a0/0x790
 ieee80211_stop+0x4c/0x178
 __dev_close_many+0xb0/0x150
 dev_close_many+0x88/0x130
 dev_close.part.171+0x44/0x74
 dev_close+0x1c/0x28
 cfg80211_shutdown_all_interfaces+0x44/0xfc
 ieee80211_restart_work+0xfc/0x14c
 process_scheduled_works+0x18c/0x2dc
 worker_thread+0x13c/0x314
 kthread+0x118/0x124
 ret_from_fork+0x10/0x20
---[ end trace 0000000000000000 ]---

The warning in question is from drv_stop():

	if (WARN_ON(!local->started))
		return;

The sequence of WARN_ON() is:
Thread 1:
-Firmware crash calls ath12k_core_reset().
-Call ieee80211_restart_hw() inside
 ath12k_core_post_reconfigure_recovery() which schedules worker
 for both hardware.
-Wait for completion of ab->recovery_start.

Thread 2 (worker thread):
-One hardware acquires rtnl_lock() inside ieee80211_restart_hw() and
 calls ath12k_mac_wait_reconfigure() into ath12k_mac_op_start().
-Hardware is waiting for ab->reconfigure_complete but at this time
 recovery_start_count value is 1 because another worker thread
 (local->restart_work) is still waiting for rtnl_lock().
 recovery_start_count is not equal to number of radios
 (2 in split-phy). So ab->recovery_start complete does not set
 due to this, thread 1 is still waiting and not able to perform
 hif power down up and firmware reload.
-Wait timeout happens for ab->reconfigure_complete and comeback
 to caller (ath12k_mac_op_start()) and sends WMI command to
 crashed firmware and gets error.
-This returns error to drv_start() and local->started is set to false.
-Hardware calls cfg80211_shutdown_all_interfaces() after receiving error
 inside ieee80211_restart_work() and goes to drv_stop(), here we trigger
 WARN_ON as local->started is false.

To fix this issue call ieee80211_restart_hw() after firmware has been
reloaded. Now, each hardware can send WMI command to firmware
successfully. With this fix we don't need to wait for
ab->recovery_start completion so remove
ath12k_mac_wait_reconfigure().

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.0.1-00029-QCAHKSWPL_SILICONZ-1
Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.1.1-00209-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: default avatarAaradhana Sahu <quic_aarasahu@quicinc.com>
Acked-by: default avatarJeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: default avatarKalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240529034405.2863150-1-quic_aarasahu@quicinc.com
parent aa17d384
......@@ -1061,8 +1061,6 @@ static void ath12k_core_post_reconfigure_recovery(struct ath12k_base *ab)
mutex_unlock(&ar->conf_mutex);
}
/* Restart after all the link/radio halt */
ieee80211_restart_hw(ah->hw);
break;
case ATH12K_HW_STATE_OFF:
ath12k_warn(ab,
......@@ -1089,7 +1087,8 @@ static void ath12k_core_post_reconfigure_recovery(struct ath12k_base *ab)
static void ath12k_core_restart(struct work_struct *work)
{
struct ath12k_base *ab = container_of(work, struct ath12k_base, restart_work);
int ret;
struct ath12k_hw *ah;
int ret, i;
ret = ath12k_core_reconfigure_on_crash(ab);
if (ret) {
......@@ -1097,8 +1096,12 @@ static void ath12k_core_restart(struct work_struct *work)
return;
}
if (ab->is_reset)
complete_all(&ab->reconfigure_complete);
if (ab->is_reset) {
for (i = 0; i < ab->num_hw; i++) {
ah = ab->ah[i];
ieee80211_restart_hw(ah->hw);
}
}
complete(&ab->restart_completed);
}
......@@ -1152,20 +1155,14 @@ static void ath12k_core_reset(struct work_struct *work)
ath12k_dbg(ab, ATH12K_DBG_BOOT, "reset starting\n");
ab->is_reset = true;
atomic_set(&ab->recovery_start_count, 0);
reinit_completion(&ab->recovery_start);
atomic_set(&ab->recovery_count, 0);
ath12k_core_pre_reconfigure_recovery(ab);
reinit_completion(&ab->reconfigure_complete);
ath12k_core_post_reconfigure_recovery(ab);
ath12k_dbg(ab, ATH12K_DBG_BOOT, "waiting recovery start...\n");
time_left = wait_for_completion_timeout(&ab->recovery_start,
ATH12K_RECOVER_START_TIMEOUT_HZ);
ath12k_hif_irq_disable(ab);
ath12k_hif_ce_irq_disable(ab);
......@@ -1277,8 +1274,6 @@ struct ath12k_base *ath12k_core_alloc(struct device *dev, size_t priv_size,
mutex_init(&ab->core_lock);
spin_lock_init(&ab->base_lock);
init_completion(&ab->reset_complete);
init_completion(&ab->reconfigure_complete);
init_completion(&ab->recovery_start);
INIT_LIST_HEAD(&ab->peers);
init_waitqueue_head(&ab->peer_mapping_wq);
......
......@@ -849,11 +849,8 @@ struct ath12k_base {
struct work_struct reset_work;
atomic_t reset_count;
atomic_t recovery_count;
atomic_t recovery_start_count;
bool is_reset;
struct completion reset_complete;
struct completion reconfigure_complete;
struct completion recovery_start;
/* continuous recovery fail count */
atomic_t fail_cont_count;
unsigned long reset_fail_timeout;
......
......@@ -5834,28 +5834,6 @@ static int ath12k_mac_config_mon_status_default(struct ath12k *ar, bool enable)
/* TODO: Need to support new monitor mode */
}
static void ath12k_mac_wait_reconfigure(struct ath12k_base *ab)
{
int recovery_start_count;
if (!ab->is_reset)
return;
recovery_start_count = atomic_inc_return(&ab->recovery_start_count);
ath12k_dbg(ab, ATH12K_DBG_MAC, "recovery start count %d\n", recovery_start_count);
if (recovery_start_count == ab->num_radios) {
complete(&ab->recovery_start);
ath12k_dbg(ab, ATH12K_DBG_MAC, "recovery started success\n");
}
ath12k_dbg(ab, ATH12K_DBG_MAC, "waiting reconfigure...\n");
wait_for_completion_timeout(&ab->reconfigure_complete,
ATH12K_RECONFIGURE_TIMEOUT_HZ);
}
static int ath12k_mac_start(struct ath12k *ar)
{
struct ath12k_hw *ah = ar->ah;
......@@ -5987,7 +5965,6 @@ static int ath12k_mac_op_start(struct ieee80211_hw *hw)
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:
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment