[PATCH 17/24] ath9k: fix queue stopping threshold

["Luis R. Rodriguez" <lrodriguez@atheros.com>]

From: Felix Fietkau <nbd@openwrt.org>

ath9k tries to prevent WMM queue tx buffer starvation caused by
traffic on different queues by limiting the number of pending frames
in a tx queue (tracked in the ath_buf structure). This had a leak
issue, because the a skb can be reassigned to a different ath_buf
in the tx path, causing the pending frame counter to become inaccurate.

To fix this, track the number of frames in an array in the softc,
using the mac80211 queue mapping as index.

Signed-off-by: Felix Fietkau <nbd@openwrt.org>
---
 drivers/net/wireless/ath/ath9k/ath9k.h |    3 +-
 drivers/net/wireless/ath/ath9k/xmit.c  |   53 +++++++++++++++++--------------
 2 files changed, 30 insertions(+), 26 deletions(-)

diff --git a/drivers/net/wireless/ath/ath9k/ath9k.h b/drivers/net/wireless/ath/ath9k/ath9k.h
index 6aa8fa6..1a19aea 100644
--- a/drivers/net/wireless/ath/ath9k/ath9k.h
+++ b/drivers/net/wireless/ath/ath9k/ath9k.h
@@ -207,7 +207,6 @@ struct ath_txq {
 	struct list_head txq_fifo_pending;
 	u8 txq_headidx;
 	u8 txq_tailidx;
-	int pending_frames;
 };
 
 struct ath_atx_ac {
@@ -245,7 +244,6 @@ struct ath_buf {
 	struct ath_buf_state bf_state;
 	dma_addr_t bf_dmacontext;
 	struct ath_wiphy *aphy;
-	struct ath_txq *txq;
 };
 
 struct ath_atx_tid {
@@ -296,6 +294,7 @@ struct ath_tx {
 	struct list_head txbuf;
 	struct ath_txq txq[ATH9K_NUM_TX_QUEUES];
 	struct ath_descdma txdma;
+	int pending_frames[WME_NUM_AC];
 };
 
 struct ath_rx_edma {
diff --git a/drivers/net/wireless/ath/ath9k/xmit.c b/drivers/net/wireless/ath/ath9k/xmit.c
index 9bff6c5..875b8b4 100644
--- a/drivers/net/wireless/ath/ath9k/xmit.c
+++ b/drivers/net/wireless/ath/ath9k/xmit.c
@@ -1760,7 +1760,7 @@ int ath_tx_start(struct ieee80211_hw *hw, struct sk_buff *skb,
 	struct ath_common *common = ath9k_hw_common(sc->sc_ah);
 	struct ath_txq *txq = txctl->txq;
 	struct ath_buf *bf;
-	int r;
+	int q, r;
 
 	bf = ath_tx_get_buffer(sc);
 	if (!bf) {
@@ -1768,14 +1768,6 @@ int ath_tx_start(struct ieee80211_hw *hw, struct sk_buff *skb,
 		return -1;
 	}
 
-	bf->txq = txctl->txq;
-	spin_lock_bh(&bf->txq->axq_lock);
-	if (++bf->txq->pending_frames > ATH_MAX_QDEPTH && !txq->stopped) {
-		ath_mac80211_stop_queue(sc, skb_get_queue_mapping(skb));
-		txq->stopped = 1;
-	}
-	spin_unlock_bh(&bf->txq->axq_lock);
-
 	r = ath_tx_setup_buffer(hw, bf, skb, txctl);
 	if (unlikely(r)) {
 		ath_print(common, ATH_DBG_FATAL, "TX mem alloc failure\n");
@@ -1796,6 +1788,17 @@ int ath_tx_start(struct ieee80211_hw *hw, struct sk_buff *skb,
 		return r;
 	}
 
+	q = skb_get_queue_mapping(skb);
+	if (q >= 4)
+		q = 0;
+
+	spin_lock_bh(&txq->axq_lock);
+	if (++sc->tx.pending_frames[q] > ATH_MAX_QDEPTH && !txq->stopped) {
+		ath_mac80211_stop_queue(sc, skb_get_queue_mapping(skb));
+		txq->stopped = 1;
+	}
+	spin_unlock_bh(&txq->axq_lock);
+
 	ath_tx_start_dma(sc, bf, txctl);
 
 	return 0;
@@ -1865,7 +1868,7 @@ static void ath_tx_complete(struct ath_softc *sc, struct sk_buff *skb,
 	struct ieee80211_tx_info *tx_info = IEEE80211_SKB_CB(skb);
 	struct ath_common *common = ath9k_hw_common(sc->sc_ah);
 	struct ieee80211_hdr * hdr = (struct ieee80211_hdr *)skb->data;
-	int padpos, padsize;
+	int q, padpos, padsize;
 
 	ath_print(common, ATH_DBG_XMIT, "TX complete: skb: %p\n", skb);
 
@@ -1904,8 +1907,16 @@ static void ath_tx_complete(struct ath_softc *sc, struct sk_buff *skb,
 
 	if (unlikely(tx_info->pad[0] & ATH_TX_INFO_FRAME_TYPE_INTERNAL))
 		ath9k_tx_status(hw, skb);
-	else
+	else {
+		q = skb_get_queue_mapping(skb);
+		if (q >= 4)
+			q = 0;
+
+		if (--sc->tx.pending_frames[q] < 0)
+			sc->tx.pending_frames[q] = 0;
+
 		ieee80211_tx_status(hw, skb);
+	}
 }
 
 static void ath_tx_complete_buf(struct ath_softc *sc, struct ath_buf *bf,
@@ -1926,13 +1937,6 @@ static void ath_tx_complete_buf(struct ath_softc *sc, struct ath_buf *bf,
 			tx_flags |= ATH_TX_XRETRY;
 	}
 
-	if (bf->txq) {
-		spin_lock_bh(&bf->txq->axq_lock);
-		bf->txq->pending_frames--;
-		spin_unlock_bh(&bf->txq->axq_lock);
-		bf->txq = NULL;
-	}
-
 	dma_unmap_single(sc->dev, bf->bf_dmacontext, skb->len, DMA_TO_DEVICE);
 	ath_tx_complete(sc, skb, bf->aphy, tx_flags);
 	ath_debug_stat_tx(sc, txq, bf, ts);
@@ -2020,13 +2024,14 @@ static void ath_wake_mac80211_queue(struct ath_softc *sc, struct ath_txq *txq)
 {
 	int qnum;
 
+	qnum = ath_get_mac80211_qnum(txq->axq_class, sc);
+	if (qnum == -1)
+		return;
+
 	spin_lock_bh(&txq->axq_lock);
-	if (txq->stopped && txq->pending_frames < ATH_MAX_QDEPTH) {
-		qnum = ath_get_mac80211_qnum(txq->axq_class, sc);
-		if (qnum != -1) {
-			ath_mac80211_start_queue(sc, qnum);
-			txq->stopped = 0;
-		}
+	if (txq->stopped && sc->tx.pending_frames[qnum] < ATH_MAX_QDEPTH) {
+		ath_mac80211_start_queue(sc, qnum);
+		txq->stopped = 0;
 	}
 	spin_unlock_bh(&txq->axq_lock);
 }
-- 
1.6.3.3