diff mbox

[RFC,1/2] ath9k: work around AR_CFG 0xdeadbeef chip hang

Message ID 20161114144226.15748-1-sven.eckelmann@open-mesh.com (mailing list archive)
State RFC
Delegated to: Kalle Valo
Headers show

Commit Message

Sven Eckelmann Nov. 14, 2016, 2:42 p.m. UTC 
From: Simon Wunderlich <simon.wunderlich@open-mesh.com>

QCA 802.11n chips (especially AR9330/AR9340) sometimes end up in a state in
which a read of AR_CFG always returns 0xdeadbeef. This should not happen
when when the power_mode of the device is ATH9K_PM_AWAKE.

This problem is not yet detected by any other workaround in ath9k. No way
is known to reproduce the problem easily.

Signed-off-by: Simon Wunderlich <simon.wunderlich@open-mesh.com>
[sven.eckelmann@open-mesh.com: port to recent ath9k, add commit message]
Signed-off-by: Sven Eckelmann <sven.eckelmann@open-mesh.com>
---
This was discussed 4 years ago on the OpenWrt mailing list. The most
relevant post is
https://lists.openwrt.org/pipermail/openwrt-devel/2012-September/016708.html
---
 drivers/net/wireless/ath/ath9k/ath9k.h |  3 +++
 drivers/net/wireless/ath/ath9k/debug.c |  1 +
 drivers/net/wireless/ath/ath9k/debug.h |  1 +
 drivers/net/wireless/ath/ath9k/init.c  |  1 +
 drivers/net/wireless/ath/ath9k/link.c  | 33 +++++++++++++++++++++++++++++++++
 drivers/net/wireless/ath/ath9k/main.c  |  4 ++++
 6 files changed, 43 insertions(+)

Comments

Kalle Valo Nov. 16, 2016, 4:16 p.m. UTC | #1 
Sven Eckelmann <sven.eckelmann@open-mesh.com> writes:

> From: Simon Wunderlich <simon.wunderlich@open-mesh.com>
>
> QCA 802.11n chips (especially AR9330/AR9340) sometimes end up in a state in
> which a read of AR_CFG always returns 0xdeadbeef. This should not happen
> when when the power_mode of the device is ATH9K_PM_AWAKE.
>
> This problem is not yet detected by any other workaround in ath9k. No way
> is known to reproduce the problem easily.
>
> Signed-off-by: Simon Wunderlich <simon.wunderlich@open-mesh.com>
> [sven.eckelmann@open-mesh.com: port to recent ath9k, add commit message]
> Signed-off-by: Sven Eckelmann <sven.eckelmann@open-mesh.com>

[...]

> +void ath_hw_hang_work(struct work_struct *work)
> +{
> +	struct ath_softc *sc = container_of(work, struct ath_softc,
> +					    hw_hang_work.work);
> +
> +	if (ath_hw_hang_deadbeef(sc))
> +		goto requeue_worker;
> +
> +requeue_worker:
> +	ieee80211_queue_delayed_work(sc->hw, &sc->hw_hang_work,
> +				     msecs_to_jiffies(ATH_HANG_WORK_INTERVAL));
> +}

The goto doesn't make any sense, either me or the function is missing
something :)
Sven Eckelmann Nov. 17, 2016, 7:23 a.m. UTC | #2 
On Mittwoch, 16. November 2016 16:16:42 CET Valo, Kalle wrote:
> Sven Eckelmann <sven.eckelmann@open-mesh.com> writes:
> 
> > From: Simon Wunderlich <simon.wunderlich@open-mesh.com>
> >
> > QCA 802.11n chips (especially AR9330/AR9340) sometimes end up in a state in
> > which a read of AR_CFG always returns 0xdeadbeef. This should not happen
> > when when the power_mode of the device is ATH9K_PM_AWAKE.
> >
> > This problem is not yet detected by any other workaround in ath9k. No way
> > is known to reproduce the problem easily.
> >
> > Signed-off-by: Simon Wunderlich <simon.wunderlich@open-mesh.com>
> > [sven.eckelmann@open-mesh.com: port to recent ath9k, add commit message]
> > Signed-off-by: Sven Eckelmann <sven.eckelmann@open-mesh.com>
> 
> [...]
> 
> > +void ath_hw_hang_work(struct work_struct *work)
> > +{
> > +	struct ath_softc *sc = container_of(work, struct ath_softc,
> > +					    hw_hang_work.work);
> > +
> > +	if (ath_hw_hang_deadbeef(sc))
> > +		goto requeue_worker;
> > +
> > +requeue_worker:
> > +	ieee80211_queue_delayed_work(sc->hw, &sc->hw_hang_work,
> > +				     msecs_to_jiffies(ATH_HANG_WORK_INTERVAL));
> > +}
> 
> The goto doesn't make any sense, either me or the function is missing
> something :)
> 
> 

It is just for the next patch. And yes, could be done differently.

Kind regards,
	Sven
diff mbox

Patch

diff --git a/drivers/net/wireless/ath/ath9k/ath9k.h b/drivers/net/wireless/ath/ath9k/ath9k.h
index 26fc8ec..9c6fee7 100644
--- a/drivers/net/wireless/ath/ath9k/ath9k.h
+++ b/drivers/net/wireless/ath/ath9k/ath9k.h
@@ -710,11 +710,13 @@  void ath9k_csa_update(struct ath_softc *sc);
 #define ATH_ANI_MAX_SKIP_COUNT    10
 #define ATH_PAPRD_TIMEOUT         100 /* msecs */
 #define ATH_PLL_WORK_INTERVAL     100
+#define ATH_HANG_WORK_INTERVAL    30000
 
 void ath_tx_complete_poll_work(struct work_struct *work);
 void ath_reset_work(struct work_struct *work);
 bool ath_hw_check(struct ath_softc *sc);
 void ath_hw_pll_work(struct work_struct *work);
+void ath_hw_hang_work(struct work_struct *work);
 void ath_paprd_calibrate(struct work_struct *work);
 void ath_ani_calibrate(unsigned long data);
 void ath_start_ani(struct ath_softc *sc);
@@ -1014,6 +1016,7 @@  struct ath_softc {
 #endif
 	struct delayed_work tx_complete_work;
 	struct delayed_work hw_pll_work;
+	struct delayed_work hw_hang_work;
 	struct timer_list sleep_timer;
 
 #ifdef CONFIG_ATH9K_BTCOEX_SUPPORT
diff --git a/drivers/net/wireless/ath/ath9k/debug.c b/drivers/net/wireless/ath/ath9k/debug.c
index c56e40f..608b370 100644
--- a/drivers/net/wireless/ath/ath9k/debug.c
+++ b/drivers/net/wireless/ath/ath9k/debug.c
@@ -767,6 +767,7 @@  static int read_file_reset(struct seq_file *file, void *data)
 		[RESET_TYPE_CALIBRATION] = "Calibration error",
 		[RESET_TX_DMA_ERROR] = "Tx DMA stop error",
 		[RESET_RX_DMA_ERROR] = "Rx DMA stop error",
+		[RESET_TYPE_DEADBEEF] = "deadbeef hang",
 	};
 	int i;
 
diff --git a/drivers/net/wireless/ath/ath9k/debug.h b/drivers/net/wireless/ath/ath9k/debug.h
index cd68c5f..0d77abbf6 100644
--- a/drivers/net/wireless/ath/ath9k/debug.h
+++ b/drivers/net/wireless/ath/ath9k/debug.h
@@ -52,6 +52,7 @@  enum ath_reset_type {
 	RESET_TYPE_CALIBRATION,
 	RESET_TX_DMA_ERROR,
 	RESET_RX_DMA_ERROR,
+	RESET_TYPE_DEADBEEF,
 	__RESET_TYPE_MAX
 };
 
diff --git a/drivers/net/wireless/ath/ath9k/init.c b/drivers/net/wireless/ath/ath9k/init.c
index 368d9b3..9bc7d1c 100644
--- a/drivers/net/wireless/ath/ath9k/init.c
+++ b/drivers/net/wireless/ath/ath9k/init.c
@@ -638,6 +638,7 @@  static int ath9k_init_softc(u16 devid, struct ath_softc *sc,
 	INIT_WORK(&sc->hw_reset_work, ath_reset_work);
 	INIT_WORK(&sc->paprd_work, ath_paprd_calibrate);
 	INIT_DELAYED_WORK(&sc->hw_pll_work, ath_hw_pll_work);
+	INIT_DELAYED_WORK(&sc->hw_hang_work, ath_hw_hang_work);
 
 	ath9k_init_channel_context(sc);
 
diff --git a/drivers/net/wireless/ath/ath9k/link.c b/drivers/net/wireless/ath/ath9k/link.c
index 5ad0fee..ff11d85 100644
--- a/drivers/net/wireless/ath/ath9k/link.c
+++ b/drivers/net/wireless/ath/ath9k/link.c
@@ -138,6 +138,39 @@  void ath_hw_pll_work(struct work_struct *work)
 				     msecs_to_jiffies(ATH_PLL_WORK_INTERVAL));
 }
 
+static bool ath_hw_hang_deadbeef(struct ath_softc *sc)
+{
+	struct ath_common *common = ath9k_hw_common(sc->sc_ah);
+	u32 reg;
+
+	/* check for stucked MAC */
+	ath9k_ps_wakeup(sc);
+	reg = REG_READ(sc->sc_ah, AR_CFG);
+	ath9k_ps_restore(sc);
+
+	if (reg != 0xdeadbeef)
+		return false;
+
+	ath_dbg(common, RESET,
+		"0xdeadbeef hang is detected. Schedule chip reset\n");
+	ath9k_queue_reset(sc, RESET_TYPE_DEADBEEF);
+
+	return true;
+}
+
+void ath_hw_hang_work(struct work_struct *work)
+{
+	struct ath_softc *sc = container_of(work, struct ath_softc,
+					    hw_hang_work.work);
+
+	if (ath_hw_hang_deadbeef(sc))
+		goto requeue_worker;
+
+requeue_worker:
+	ieee80211_queue_delayed_work(sc->hw, &sc->hw_hang_work,
+				     msecs_to_jiffies(ATH_HANG_WORK_INTERVAL));
+}
+
 /*
  * PA Pre-distortion.
  */
diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c
index e9f32b5..4d3e216 100644
--- a/drivers/net/wireless/ath/ath9k/main.c
+++ b/drivers/net/wireless/ath/ath9k/main.c
@@ -183,6 +183,7 @@  static void __ath_cancel_work(struct ath_softc *sc)
 	cancel_work_sync(&sc->paprd_work);
 	cancel_delayed_work_sync(&sc->tx_complete_work);
 	cancel_delayed_work_sync(&sc->hw_pll_work);
+	cancel_delayed_work_sync(&sc->hw_hang_work);
 
 #ifdef CONFIG_ATH9K_BTCOEX_SUPPORT
 	if (ath9k_hw_mci_is_enabled(sc->sc_ah))
@@ -204,6 +205,9 @@  void ath_restart_work(struct ath_softc *sc)
 		ieee80211_queue_delayed_work(sc->hw, &sc->hw_pll_work,
 				     msecs_to_jiffies(ATH_PLL_WORK_INTERVAL));
 
+	ieee80211_queue_delayed_work(sc->hw, &sc->hw_hang_work,
+				     msecs_to_jiffies(ATH_HANG_WORK_INTERVAL));
+
 	ath_start_ani(sc);
 }