| Message ID | 20220505034636.29582-1-quic_wgong@quicinc.com |
|---|---|
| State | New |
| Headers | show |
| Series | ath11k: reset 11d state in process of recovery | expand |
Wen Gong <quic_wgong@quicinc.com> wrote: > When doing simulate_fw_crash operation periodically with a short interval > time such as 10 seconds, it is easy happened WMI command timed out for > WMI_SCAN_CHAN_LIST_CMDID in ath11k_reg_update_chan_list(). > > log: > [42287.610053] ath11k_pci 0000:01:00.0: wmi command 12291 timeout > [42287.610064] ath11k_pci 0000:01:00.0: failed to send WMI_SCAN_CHAN_LIST cmd > [42287.610073] ath11k_pci 0000:01:00.0: failed to perform regd update : -11 > > Note that this issue does not occur with a longer interval such as 20 seconds. > > The reason the issue occurs with a shorter interval is the following steps: > 1) Upon initial boot, or after device recovery, the initial hw scan plus > the 11d scan will run, and when 6 GHz support is present, these scans > can take up to 12 seconds to complete, so ath11k_reg_update_chan_list() > is still waiting the completion of ar->completed_11d_scan. > 2) If a simulate_fw_crash operation is received during this time, those > scans do not complete, and ath11k_core_pre_reconfigure_recovery() > complete the ar->completed_11d_scan, then ath11k_reg_update_chan_list() > wakeup and start to send WMI_SCAN_CHAN_LIST_CMDID, but firmware is crashed > at this moment, so wmi timed out occur. > > To address this issue, reset the 11d state during device recovery so that > WMI_SCAN_CHAN_LIST_CMDID does not timed out for short interval time such > as 10 seconds. > > Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-03125-QCAHSPSWPL_V1_V2_SILICONZ_LITE-3 > > Fixes: 1f682dc9fb37 ("ath11k: reduce the wait time of 11d scan and hw scan while add interface") > Signed-off-by: Wen Gong <quic_wgong@quicinc.com> > Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com> Patch applied to ath-next branch of ath.git, thanks. 9497b7880ffd ath11k: reset 11d state in process of recovery
diff --git a/drivers/net/wireless/ath/ath11k/core.c b/drivers/net/wireless/ath/ath11k/core.c index 7e074b7716e7..5dfac931f70b 100644 --- a/drivers/net/wireless/ath/ath11k/core.c +++ b/drivers/net/wireless/ath/ath11k/core.c @@ -1499,6 +1499,7 @@ static void ath11k_core_pre_reconfigure_recovery(struct ath11k_base *ab) ieee80211_stop_queues(ar->hw); ath11k_mac_drain_tx(ar); + ar->state_11d = ATH11K_11D_IDLE; complete(&ar->completed_11d_scan); complete(&ar->scan.started); complete(&ar->scan.completed); diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c index da994d89d69d..44a3a9b1c29f 100644 --- a/drivers/net/wireless/ath/ath11k/mac.c +++ b/drivers/net/wireless/ath/ath11k/mac.c @@ -6155,6 +6155,11 @@ void ath11k_mac_11d_scan_stop(struct ath11k *ar) ath11k_dbg(ar->ab, ATH11K_DBG_MAC, "mac stop 11d vdev id %d\n", ar->vdev_id_11d_scan); + if (ar->state_11d == ATH11K_11D_PREPARING) { + ar->state_11d = ATH11K_11D_IDLE; + complete(&ar->completed_11d_scan); + } + if (ar->vdev_id_11d_scan != ATH11K_11D_INVALID_VDEV_ID) { vdev_id = ar->vdev_id_11d_scan; diff --git a/drivers/net/wireless/ath/ath11k/reg.c b/drivers/net/wireless/ath/ath11k/reg.c index 79ac2142317a..7ee3ff69dfc8 100644 --- a/drivers/net/wireless/ath/ath11k/reg.c +++ b/drivers/net/wireless/ath/ath11k/reg.c @@ -139,6 +139,9 @@ int ath11k_reg_update_chan_list(struct ath11k *ar, bool wait) "reg hw scan wait left time %d\n", left); } + if (ar->state == ATH11K_STATE_RESTARTING) + return 0; + bands = hw->wiphy->bands; for (band = 0; band < NUM_NL80211_BANDS; band++) { if (!bands[band])
When doing simulate_fw_crash operation periodically with a short interval time such as 10 seconds, it is easy happened WMI command timed out for WMI_SCAN_CHAN_LIST_CMDID in ath11k_reg_update_chan_list(). log: [42287.610053] ath11k_pci 0000:01:00.0: wmi command 12291 timeout [42287.610064] ath11k_pci 0000:01:00.0: failed to send WMI_SCAN_CHAN_LIST cmd [42287.610073] ath11k_pci 0000:01:00.0: failed to perform regd update : -11 Note that this issue does not occur with a longer interval such as 20 seconds. The reason the issue occurs with a shorter interval is the following steps: 1) Upon initial boot, or after device recovery, the initial hw scan plus the 11d scan will run, and when 6 GHz support is present, these scans can take up to 12 seconds to complete, so ath11k_reg_update_chan_list() is still waiting the completion of ar->completed_11d_scan. 2) If a simulate_fw_crash operation is received during this time, those scans do not complete, and ath11k_core_pre_reconfigure_recovery() complete the ar->completed_11d_scan, then ath11k_reg_update_chan_list() wakeup and start to send WMI_SCAN_CHAN_LIST_CMDID, but firmware is crashed at this moment, so wmi timed out occur. To address this issue, reset the 11d state during device recovery so that WMI_SCAN_CHAN_LIST_CMDID does not timed out for short interval time such as 10 seconds. Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-03125-QCAHSPSWPL_V1_V2_SILICONZ_LITE-3 Fixes: 1f682dc9fb37 ("ath11k: reduce the wait time of 11d scan and hw scan while add interface") Signed-off-by: Wen Gong <quic_wgong@quicinc.com> --- drivers/net/wireless/ath/ath11k/core.c | 1 + drivers/net/wireless/ath/ath11k/mac.c | 5 +++++ drivers/net/wireless/ath/ath11k/reg.c | 3 +++ 3 files changed, 9 insertions(+) base-commit: 3637b73b8e805d011202e2bf10947f2d206695d4