wifi: mt76: mt7921e: fix race issue between reset and suspend/resume

It is unexpected that the reset work is running simultaneously with
the suspend or resume context and it is possible that reset work is still
running even after mt7921 is suspended if we don't fix the race issue.

Thus, the suspend procedure should be waiting until the reset is completed
at the beginning and ignore the subsequent the reset requests.

In case there is an error that happens during either suspend or resume
handler, we will schedule a reset task to recover the error before
returning the error code to ensure we can immediately fix the error there.

Fixes: 0c1ce988 ("mt76: mt7921: add wifi reset support")
Co-developed-by: YN Chen <YN.Chen@mediatek.com>
Signed-off-by: YN Chen <YN.Chen@mediatek.com>
Signed-off-by: Sean Wang <sean.wang@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>

drivers/net/wireless/mediatek/mt76/mt7921/mac.c

@@ -800,6 +800,7 @@ void mt7921_mac_reset_work(struct work_struct *work)
 void mt7921_reset(struct mt76_dev *mdev)
 {
 	struct mt7921_dev *dev = container_of(mdev, struct mt7921_dev, mt76);
+	struct mt76_connac_pm *pm = &dev->pm;
 
 	if (!dev->hw_init_done)
 		return;
@@ -807,8 +808,12 @@ void mt7921_reset(struct mt76_dev *mdev)
 	if (dev->hw_full_reset)
 		return;
 
+	if (pm->suspended)
+		return;
+
 	queue_work(dev->mt76.wq, &dev->reset_work);
 }
+EXPORT_SYMBOL_GPL(mt7921_reset);
 
 void mt7921_mac_update_mib_stats(struct mt7921_phy *phy)
 {

drivers/net/wireless/mediatek/mt76/mt7921/pci.c

@@ -363,6 +363,7 @@ static int mt7921_pci_suspend(struct device *device)
 	int i, err;
 
 	pm->suspended = true;
+	flush_work(&dev->reset_work);
 	cancel_delayed_work_sync(&pm->ps_work);
 	cancel_work_sync(&pm->wake_work);
 
@@ -424,6 +425,9 @@ static int mt7921_pci_suspend(struct device *device)
 restore_suspend:
 	pm->suspended = false;
 
+	if (err < 0)
+		mt7921_reset(&dev->mt76);
+
 	return err;
 }
 
@@ -437,7 +441,7 @@ static int mt7921_pci_resume(struct device *device)
 
 	err = mt7921_mcu_drv_pmctrl(dev);
 	if (err < 0)
-		return err;
+		goto failed;
 
 	mt7921_wpdma_reinit_cond(dev);
 
@@ -467,11 +471,12 @@ static int mt7921_pci_resume(struct device *device)
 		mt76_connac_mcu_set_deep_sleep(&dev->mt76, false);
 
 	err = mt76_connac_mcu_set_hif_suspend(mdev, false);
-	if (err)
-		return err;
-
+failed:
 	pm->suspended = false;
 
+	if (err < 0)
+		mt7921_reset(&dev->mt76);
+
 	return err;
 }