ath9k: Add workaround to recover from failed channel changes

It looks like channel change may fail in some cases and end up leaving
the hardware in state where it cannot transmit any frames. Add a
workaround to recover from this state if we detect that wiphy
selection is failing due to wiphys not leaving PAUSING state.
Signed-off-by: NJouni Malinen <jouni.malinen@atheros.com>
Signed-off-by: NJohn W. Linville <linville@tuxdriver.com>

drivers/net/wireless/ath9k/ath9k.h

@@ -567,6 +567,8 @@ struct ath_softc {
 	int chan_is_ht;
 	struct ath_wiphy *next_wiphy;
 	struct work_struct chan_work;
+	int wiphy_select_failures;
+	unsigned long wiphy_select_first_fail;
 
 	struct tasklet_struct intr_tq;
 	struct tasklet_struct bcon_tasklet;
@@ -665,6 +667,8 @@ void ath9k_update_ichannel(struct ath_softc *sc, struct ieee80211_hw *hw,
 void ath_update_chainmask(struct ath_softc *sc, int is_ht);
 int ath_set_channel(struct ath_softc *sc, struct ieee80211_hw *hw,
 		    struct ath9k_channel *hchan);
+void ath_radio_enable(struct ath_softc *sc);
+void ath_radio_disable(struct ath_softc *sc);
 
 #ifdef CONFIG_PCI
 int ath_pci_init(void);

drivers/net/wireless/ath9k/main.c

@@ -1090,7 +1090,7 @@ static void ath_init_leds(struct ath_softc *sc)
 /*	Rfkill	   */
 /*******************/
 
-static void ath_radio_enable(struct ath_softc *sc)
+void ath_radio_enable(struct ath_softc *sc)
 {
 	struct ath_hw *ah = sc->sc_ah;
 	struct ieee80211_channel *channel = sc->hw->conf.channel;
@@ -1131,7 +1131,7 @@ static void ath_radio_enable(struct ath_softc *sc)
 	ath9k_ps_restore(sc);
 }
 
-static void ath_radio_disable(struct ath_softc *sc)
+void ath_radio_disable(struct ath_softc *sc)
 {
 	struct ath_hw *ah = sc->sc_ah;
 	struct ieee80211_channel *channel = sc->hw->conf.channel;

drivers/net/wireless/ath9k/virtual.c

@@ -432,6 +432,18 @@ int ath9k_wiphy_unpause(struct ath_wiphy *aphy)
 	return ret;
 }
 
+static void __ath9k_wiphy_mark_all_paused(struct ath_softc *sc)
+{
+	int i;
+	if (sc->pri_wiphy->state != ATH_WIPHY_INACTIVE)
+		sc->pri_wiphy->state = ATH_WIPHY_PAUSED;
+	for (i = 0; i < sc->num_sec_wiphy; i++) {
+		if (sc->sec_wiphy[i] &&
+		    sc->sec_wiphy[i]->state != ATH_WIPHY_INACTIVE)
+			sc->sec_wiphy[i]->state = ATH_WIPHY_PAUSED;
+	}
+}
+
 /* caller must hold wiphy_lock */
 static void __ath9k_wiphy_pause_all(struct ath_softc *sc)
 {
@@ -452,9 +464,34 @@ int ath9k_wiphy_select(struct ath_wiphy *aphy)
 
 	spin_lock_bh(&sc->wiphy_lock);
 	if (__ath9k_wiphy_pausing(sc)) {
+		if (sc->wiphy_select_failures == 0)
+			sc->wiphy_select_first_fail = jiffies;
+		sc->wiphy_select_failures++;
+		if (time_after(jiffies, sc->wiphy_select_first_fail + HZ / 2))
+		{
+			printk(KERN_DEBUG "ath9k: Previous wiphy select timed "
+			       "out; disable/enable hw to recover\n");
+			__ath9k_wiphy_mark_all_paused(sc);
+			/*
+			 * TODO: this workaround to fix hardware is unlikely to
+			 * be specific to virtual wiphy changes. It can happen
+			 * on normal channel change, too, and as such, this
+			 * should really be made more generic. For example,
+			 * tricker radio disable/enable on GTT interrupt burst
+			 * (say, 10 GTT interrupts received without any TX
+			 * frame being completed)
+			 */
+			spin_unlock_bh(&sc->wiphy_lock);
+			ath_radio_disable(sc);
+			ath_radio_enable(sc);
+			queue_work(aphy->sc->hw->workqueue,
+				   &aphy->sc->chan_work);
+			return -EBUSY; /* previous select still in progress */
+		}
 		spin_unlock_bh(&sc->wiphy_lock);
 		return -EBUSY; /* previous select still in progress */
 	}
+	sc->wiphy_select_failures = 0;
 
 	/* Store the new channel */
 	sc->chan_idx = aphy->chan_idx;