[PATCH v4 3/3] wifi: rtw88: ps: trigger firmware recovery only after consecutive LPS leave failures on PCI

[Kalpesh Solanki]

A single timeout in rtw_fw_leave_lps_check() does not always indicate a
frozen firmware; in noisy RF environments or during beacon loss, the
802.11 null data frame ACK can be delayed or dropped. Immediately
triggering firmware recovery and a full hardware restart on a single
timeout causes unnecessary disconnections and kernel warning traces on
idle links.

Follow rtw89 by introducing a consecutive failure counter (ps_hang_cnt)
and only triggering rtw_fw_recovery() after RTW_PS_HANG_MAX_CNT (3)
consecutive failures. Reset the counter to 0 on every successful LPS
leave and in rtw_core_start() so that cold starts and hardware restarts
always begin with a clean slate.

Additionally, rtw_fw_recovery() clears keys via rtw_iterate_keys_atomic()
under a spinlock. On USB and SDIO, register writes in key clearing sleep
(via usb_control_msg() and sdio_claim_host()), which would trigger a
BUG: scheduling while atomic if executed. Because USB and SDIO do not
support firmware recovery, restrict rtw_fw_recovery() to PCI devices
via rtw_hci_type().

Signed-off-by: Kalpesh Solanki <skalpesh942@xxxxxxxxx>
---
 drivers/net/wireless/realtek/rtw88/main.c | 5 +++++
 drivers/net/wireless/realtek/rtw88/main.h | 1 +
 drivers/net/wireless/realtek/rtw88/ps.c   | 7 +++++++
 drivers/net/wireless/realtek/rtw88/ps.h   | 1 +
 4 files changed, 14 insertions(+)

diff --git a/drivers/net/wireless/realtek/rtw88/main.c b/drivers/net/wireless/realtek/rtw88/main.c
index a74f199a93a..7009f8ae3e5 100644
--- a/drivers/net/wireless/realtek/rtw88/main.c
+++ b/drivers/net/wireless/realtek/rtw88/main.c
@@ -638,6 +638,9 @@ static void rtw_reset_vif_iter(void *data, u8 *mac, struct ieee80211_vif *vif)
 
 void rtw_fw_recovery(struct rtw_dev *rtwdev)
 {
+	if (rtw_hci_type(rtwdev) != RTW_HCI_TYPE_PCIE)
+		return;
+
 	if (!test_bit(RTW_FLAG_RESTARTING, rtwdev->flags))
 		ieee80211_queue_work(rtwdev->hw, &rtwdev->fw_recovery_work);
 }
@@ -1536,6 +1539,8 @@ int rtw_core_start(struct rtw_dev *rtwdev)
 
 	set_bit(RTW_FLAG_RUNNING, rtwdev->flags);
 
+	rtwdev->ps_hang_cnt = 0;
+
 	return 0;
 }
 
diff --git a/drivers/net/wireless/realtek/rtw88/main.h b/drivers/net/wireless/realtek/rtw88/main.h
index 6ecbeb4ffe4..525f17590ad 100644
--- a/drivers/net/wireless/realtek/rtw88/main.h
+++ b/drivers/net/wireless/realtek/rtw88/main.h
@@ -2113,6 +2113,7 @@ struct rtw_dev {
 	/* lps power state & handler work */
 	struct rtw_lps_conf lps_conf;
 	bool ps_enabled;
+	u8 ps_hang_cnt;
 	bool beacon_loss;
 	struct completion lps_leave_check;
 
diff --git a/drivers/net/wireless/realtek/rtw88/ps.c b/drivers/net/wireless/realtek/rtw88/ps.c
index add5a20b843..fa3a4e476cf 100644
--- a/drivers/net/wireless/realtek/rtw88/ps.c
+++ b/drivers/net/wireless/realtek/rtw88/ps.c
@@ -166,6 +166,13 @@ static void rtw_fw_leave_lps_check(struct rtw_dev *rtwdev)
 		rtw_write32_clr(rtwdev, REG_TCR, BIT_PWRMGT_HWDATA_EN);
 		rtw_warn(rtwdev, "firmware failed to leave lps state\n");
 		rtw_fw_dump_dbg_info(rtwdev);
+
+		rtwdev->ps_hang_cnt++;
+		if (rtw_hci_type(rtwdev) == RTW_HCI_TYPE_PCIE &&
+		    rtwdev->ps_hang_cnt >= RTW_PS_HANG_MAX_CNT)
+			rtw_fw_recovery(rtwdev);
+	} else {
+		rtwdev->ps_hang_cnt = 0;
 	}
 }
 
diff --git a/drivers/net/wireless/realtek/rtw88/ps.h b/drivers/net/wireless/realtek/rtw88/ps.h
index 5ae83d2526c..b088fad7cd8 100644
--- a/drivers/net/wireless/realtek/rtw88/ps.h
+++ b/drivers/net/wireless/realtek/rtw88/ps.h
@@ -14,6 +14,7 @@
 
 #define LEAVE_LPS_TRY_CNT	5
 #define LEAVE_LPS_TIMEOUT	msecs_to_jiffies(100)
+#define RTW_PS_HANG_MAX_CNT	3
 
 int rtw_enter_ips(struct rtw_dev *rtwdev);
 int rtw_leave_ips(struct rtw_dev *rtwdev);
-- 
2.53.0