From: Ben Greear <greearb@xxxxxxxxxxxxxxx>
We see TX lockups on ar9380 NICs when running 32 stations
each with a 56kbps stream of MTU sized UDP packets.
We see lockups on the AP and also on the station, seems
random which hits first.
The test case further involves a programmable attenuator,
and the attenuation is taken from -30 to -85 signal level
in steps of 10db. Each step runs for 1 minute before
increasing the attenuation. The problem normally
shows up around signal level of -70 (noise is reported
as around -95).
When the lockup hits, it is typically on a single queue
(BE). The symptom is that there is no obvious transmit
activity on that queue, the acq-depth and axq-ampdu-depth
are zero, the queue is stopped, and the pending-frames is
at or above the maximum allowed. The VO queue continues
to function, and RX logic functions fine.
Just resetting the chip does not fix the problem: The
pending-frames usually stays at max. So, this patch also
adds hacks to force pending-frames to zero. It also
quietens some warnings about pending-frame underruns
because sometimes, the tx status does appear many seconds
later.
Finally, the reset fixup code is logged at ath_err because
I think everyone should be aware of events like this.
We see the same problem with ath9k rate control and
minstrel-ht. We have not tested other ath9k chipsets
in this manner.
Small numbers of high-speed stations do not hit this
problem, or at least not in our test cases.
Signed-off-by: Ben Greear <greearb@xxxxxxxxxxxxxxx>
---
drivers/net/wireless/ath/ath9k/ath9k.h | 2 ++
drivers/net/wireless/ath/ath9k/link.c | 30 ++++++++++++++++++++++++++++--
drivers/net/wireless/ath/ath9k/main.c | 5 +++--
drivers/net/wireless/ath/ath9k/xmit.c | 15 ++++++++++++++-
4 files changed, 47 insertions(+), 5 deletions(-)
diff --git a/drivers/net/wireless/ath/ath9k/ath9k.h b/drivers/net/wireless/ath/ath9k/ath9k.h
index d7897dcf..cc8d560 100644
--- a/drivers/net/wireless/ath/ath9k/ath9k.h
+++ b/drivers/net/wireless/ath/ath9k/ath9k.h
@@ -194,6 +194,7 @@ struct ath_txq {
u32 axq_ampdu_depth;
bool stopped;
bool axq_tx_inprogress;
+ bool clear_pending_frames_on_flush;
struct list_head axq_acq;
struct list_head txq_fifo[ATH_TXFIFO_DEPTH];
u8 txq_headidx;
@@ -684,6 +685,7 @@ struct ath_softc {
u16 curtxpow;
bool ps_enabled;
bool ps_idle;
+ bool reset_force_noretry;
short nbcnvifs;
short nvifs;
unsigned long ps_usecount;
diff --git a/drivers/net/wireless/ath/ath9k/link.c b/drivers/net/wireless/ath/ath9k/link.c
index 7b88b9c..b59565c 100644
--- a/drivers/net/wireless/ath/ath9k/link.c
+++ b/drivers/net/wireless/ath/ath9k/link.c
@@ -38,18 +38,44 @@ void ath_tx_complete_poll_work(struct work_struct *work)
if (txq->axq_depth) {
if (txq->axq_tx_inprogress) {
needreset = true;
+ ath_err(ath9k_hw_common(sc->sc_ah),
+ "tx hung, queue: %i axq-depth: %i, ampdu-depth: %i resetting the chip\n",
+ i, txq->axq_depth,
+ txq->axq_ampdu_depth);
ath_txq_unlock(sc, txq);
break;
} else {
txq->axq_tx_inprogress = true;
}
+ } else {
+ /* Check for software TX hang. It seems
+ * sometimes pending-frames is not properly
+ * decremented, and the tx queue hangs.
+ * Considered hung if: axq-depth is zero,
+ * ampdu-depth is zero, queue-is-stopped,
+ * and we have pending frames.
+ */
+ if (txq->stopped &&
+ (txq->axq_ampdu_depth == 0) &&
+ (txq->pending_frames > 0)) {
+ if (txq->axq_tx_inprogress) {
+ ath_err(ath9k_hw_common(sc->sc_ah),
+ "soft tx hang: queue: %i pending-frames: %i, resetting chip\n",
+ i, txq->pending_frames);
+ needreset = true;
+ txq->clear_pending_frames_on_flush = true;
+ sc->reset_force_noretry = true;
+ ath_txq_unlock(sc, txq);
+ break;
+ } else {
+ txq->axq_tx_inprogress = true;
+ }
+ }
}
ath_txq_unlock_complete(sc, txq);
}
if (needreset) {
- ath_dbg(ath9k_hw_common(sc->sc_ah), RESET,
- "tx hung, resetting the chip\n");
ath9k_queue_reset(sc, RESET_TYPE_TX_HANG);
return;
}
diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c
index 5c8758d..0de0e50 100644
--- a/drivers/net/wireless/ath/ath9k/main.c
+++ b/drivers/net/wireless/ath/ath9k/main.c
@@ -587,8 +587,9 @@ void ath9k_queue_reset(struct ath_softc *sc, enum ath_reset_type type)
void ath_reset_work(struct work_struct *work)
{
struct ath_softc *sc = container_of(work, struct ath_softc, hw_reset_work);
-
- ath_reset(sc, true);
+ bool retry_tx = !sc->reset_force_noretry;
+ sc->reset_force_noretry = false;
+ ath_reset(sc, retry_tx);
}
/**********************/
diff --git a/drivers/net/wireless/ath/ath9k/xmit.c b/drivers/net/wireless/ath/ath9k/xmit.c
index 741918a..093c77e 100644
--- a/drivers/net/wireless/ath/ath9k/xmit.c
+++ b/drivers/net/wireless/ath/ath9k/xmit.c
@@ -1543,6 +1543,15 @@ void ath_draintxq(struct ath_softc *sc, struct ath_txq *txq, bool retry_tx)
if ((sc->sc_ah->caps.hw_caps & ATH9K_HW_CAP_HT) && !retry_tx)
ath_txq_drain_pending_buffers(sc, txq);
+ if (txq->clear_pending_frames_on_flush && (txq->pending_frames != 0)) {
+ ath_err(ath9k_hw_common(sc->sc_ah),
+ "Pending frames still exist on txq: %i after drain: %i axq-depth: %i ampdu-depth: %i\n",
+ txq->mac80211_qnum, txq->pending_frames, txq->axq_depth,
+ txq->axq_ampdu_depth);
+ txq->pending_frames = 0;
+ }
+ txq->clear_pending_frames_on_flush = false;
+
ath_txq_unlock_complete(sc, txq);
}
@@ -2066,8 +2075,12 @@ static void ath_tx_complete(struct ath_softc *sc, struct sk_buff *skb,
q = skb_get_queue_mapping(skb);
if (txq == sc->tx.txq_map[q]) {
- if (WARN_ON(--txq->pending_frames < 0))
+ if (--txq->pending_frames < 0) {
+ if (net_ratelimit())
+ ath_err(common, "txq: %p had negative pending_frames, q: %i\n",
+ txq, q);
txq->pending_frames = 0;
+ }
if (txq->stopped &&
txq->pending_frames < sc->tx.txq_max_pending[q]) {
--
1.7.3.4
--
To unsubscribe from this list: send the line "unsubscribe linux-wireless" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
