ath9k: Switch to using mac80211 intermediate software queues.

This switches ath9k over to using the mac80211 intermediate software
queueing mechanism for data packets. It removes the queueing inside the
driver, except for the retry queue, and instead pulls from mac80211 when
a packet is needed. The retry queue is used to store a packet that was
pulled but can't be sent immediately.

The old code path in ath_tx_start that would queue packets has been
removed completely, as has the qlen limit tunables (since there's no
longer a queue in the driver to limit).

The mac80211 intermediate software queues offer significant latency
reductions, and this patch allows ath9k to realise them. The exact gains
from this varies with the test scenario, but in an access point scenario
we have seen latency reductions ranging from 1/3 to as much as an order
of magnitude. We also achieve slightly better aggregation.

Median latency (ping) figures with this patch applied at the access point,
with two high-rate stations and one low-rate station (HT20 5Ghz), running
a Flent rtt_fair_var_up test with one TCP flow and one ping flow going to
each station:

                                 Fast station        Slow station
Default pfifo_fast qdisc:            430.4 ms            638.7 ms
fq_codel qdisc on iface:              35.5 ms            211.8 ms
This patch set:                       22.4 ms             38.2 ms

Median aggregation sizes over the same test:

Default pfifo_fast qdisc:            9.5 pkts            1.9 pkts
fq_codel qdisc on iface:            11.2 pkts            1.9 pkts
This patch set:                     13.9 pkts            1.9 pkts

This patch is based on Tim's original patch set, but reworked quite
thoroughly.

Cc: Tim Shepard <shep@alum.mit.edu>
Cc: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Toke Høiland-Jørgensen <toke@toke.dk>
Signed-off-by: Kalle Valo <kvalo@qca.qualcomm.com>

1 files changed, 134 insertions, 204 deletions

diff --git a/drivers/net/wireless/ath/ath9k/xmit.c b/drivers/net/wireless/ath/ath9k/xmit.c
index 52bfbb988611..486afa98a5b8 100644
--- a/drivers/net/wireless/ath/ath9k/xmit.c
+++ b/drivers/net/wireless/ath/ath9k/xmit.c
@@ -67,6 +67,8 @@ static struct ath_buf *ath_tx_setup_buffer(struct ath_softc *sc,
 					   struct ath_txq *txq,
 					   struct ath_atx_tid *tid,
 					   struct sk_buff *skb);
+static int ath_tx_prepare(struct ieee80211_hw *hw, struct sk_buff *skb,
+			  struct ath_tx_control *txctl);
 
 enum {
 	MCS_HT20,
@@ -137,6 +139,26 @@ static void ath_tx_queue_tid(struct ath_softc *sc, struct ath_txq *txq,
 		list_add_tail(&tid->list, list);
 }
 
+void ath9k_wake_tx_queue(struct ieee80211_hw *hw, struct ieee80211_txq *queue)
+{
+	struct ath_softc *sc = hw->priv;
+	struct ath_common *common = ath9k_hw_common(sc->sc_ah);
+	struct ath_atx_tid *tid = (struct ath_atx_tid *) queue->drv_priv;
+	struct ath_txq *txq = tid->txq;
+
+	ath_dbg(common, QUEUE, "Waking TX queue: %pM (%d)\n",
+		queue->sta ? queue->sta->addr : queue->vif->addr,
+		tid->tidno);
+
+	ath_txq_lock(sc, txq);
+
+	tid->has_queued = true;
+	ath_tx_queue_tid(sc, txq, tid);
+	ath_txq_schedule(sc, txq);
+
+	ath_txq_unlock(sc, txq);
+}
+
 static struct ath_frame_info *get_frame_info(struct sk_buff *skb)
 {
 	struct ieee80211_tx_info *tx_info = IEEE80211_SKB_CB(skb);
@@ -164,7 +186,6 @@ static void ath_set_rates(struct ieee80211_vif *vif, struct ieee80211_sta *sta,
 static void ath_txq_skb_done(struct ath_softc *sc, struct ath_txq *txq,
 			     struct sk_buff *skb)
 {
-	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
 	struct ath_frame_info *fi = get_frame_info(skb);
 	int q = fi->txq;
 
@@ -175,14 +196,6 @@ static void ath_txq_skb_done(struct ath_softc *sc, struct ath_txq *txq,
 	if (WARN_ON(--txq->pending_frames < 0))
 		txq->pending_frames = 0;
 
-	if (txq->stopped &&
-	    txq->pending_frames < sc->tx.txq_max_pending[q]) {
-		if (ath9k_is_chanctx_enabled())
-			ieee80211_wake_queue(sc->hw, info->hw_queue);
-		else
-			ieee80211_wake_queue(sc->hw, q);
-		txq->stopped = false;
-	}
 }
 
 static struct ath_atx_tid *
@@ -192,9 +205,48 @@ ath_get_skb_tid(struct ath_softc *sc, struct ath_node *an, struct sk_buff *skb)
 	return ATH_AN_2_TID(an, tidno);
 }
 
+static struct sk_buff *
+ath_tid_pull(struct ath_atx_tid *tid)
+{
+	struct ieee80211_txq *txq = container_of((void*)tid, struct ieee80211_txq, drv_priv);
+	struct ath_softc *sc = tid->an->sc;
+	struct ieee80211_hw *hw = sc->hw;
+	struct ath_tx_control txctl = {
+		.txq = tid->txq,
+		.sta = tid->an->sta,
+	};
+	struct sk_buff *skb;
+	struct ath_frame_info *fi;
+	int q;
+
+	if (!tid->has_queued)
+		return NULL;
+
+	skb = ieee80211_tx_dequeue(hw, txq);
+	if (!skb) {
+		tid->has_queued = false;
+		return NULL;
+	}
+
+	if (ath_tx_prepare(hw, skb, &txctl)) {
+		ieee80211_free_txskb(hw, skb);
+		return NULL;
+	}
+
+	q = skb_get_queue_mapping(skb);
+	if (tid->txq == sc->tx.txq_map[q]) {
+		fi = get_frame_info(skb);
+		fi->txq = q;
+		++tid->txq->pending_frames;
+	}
+
+	return skb;
+ }
+
+
 static bool ath_tid_has_buffered(struct ath_atx_tid *tid)
 {
-	return !skb_queue_empty(&tid->buf_q) || !skb_queue_empty(&tid->retry_q);
+	return !skb_queue_empty(&tid->retry_q) || tid->has_queued;
 }
 
 static struct sk_buff *ath_tid_dequeue(struct ath_atx_tid *tid)
@@ -203,46 +255,11 @@ static struct sk_buff *ath_tid_dequeue(struct ath_atx_tid *tid)
 
 	skb = __skb_dequeue(&tid->retry_q);
 	if (!skb)
-		skb = __skb_dequeue(&tid->buf_q);
+		skb = ath_tid_pull(tid);
 
 	return skb;
 }
 
-/*
- * ath_tx_tid_change_state:
- * - clears a-mpdu flag of previous session
- * - force sequence number allocation to fix next BlockAck Window
- */
-static void
-ath_tx_tid_change_state(struct ath_softc *sc, struct ath_atx_tid *tid)
-{
-	struct ath_txq *txq = tid->txq;
-	struct ieee80211_tx_info *tx_info;
-	struct sk_buff *skb, *tskb;
-	struct ath_buf *bf;
-	struct ath_frame_info *fi;
-
-	skb_queue_walk_safe(&tid->buf_q, skb, tskb) {
-		fi = get_frame_info(skb);
-		bf = fi->bf;
-
-		tx_info = IEEE80211_SKB_CB(skb);
-		tx_info->flags &= ~IEEE80211_TX_CTL_AMPDU;
-
-		if (bf)
-			continue;
-
-		bf = ath_tx_setup_buffer(sc, txq, tid, skb);
-		if (!bf) {
-			__skb_unlink(skb, &tid->buf_q);
-			ath_txq_skb_done(sc, txq, skb);
-			ieee80211_free_txskb(sc->hw, skb);
-			continue;
-		}
-	}
-
-}
-
 static void ath_tx_flush_tid(struct ath_softc *sc, struct ath_atx_tid *tid)
 {
 	struct ath_txq *txq = tid->txq;
@@ -883,20 +900,16 @@ static int ath_compute_num_delims(struct ath_softc *sc, struct ath_atx_tid *tid,
 
 static struct ath_buf *
 ath_tx_get_tid_subframe(struct ath_softc *sc, struct ath_txq *txq,
-			struct ath_atx_tid *tid, struct sk_buff_head **q)
+			struct ath_atx_tid *tid)
 {
 	struct ieee80211_tx_info *tx_info;
 	struct ath_frame_info *fi;
-	struct sk_buff *skb;
+	struct sk_buff *skb, *first_skb = NULL;
 	struct ath_buf *bf;
 	u16 seqno;
 
 	while (1) {
-		*q = &tid->retry_q;
-		if (skb_queue_empty(*q))
-			*q = &tid->buf_q;
-
-		skb = skb_peek(*q);
+		skb = ath_tid_dequeue(tid);
 		if (!skb)
 			break;
 
@@ -908,7 +921,6 @@ ath_tx_get_tid_subframe(struct ath_softc *sc, struct ath_txq *txq,
 			bf->bf_state.stale = false;
 
 		if (!bf) {
-			__skb_unlink(skb, *q);
 			ath_txq_skb_done(sc, txq, skb);
 			ieee80211_free_txskb(sc->hw, skb);
 			continue;
@@ -937,8 +949,20 @@ ath_tx_get_tid_subframe(struct ath_softc *sc, struct ath_txq *txq,
 		seqno = bf->bf_state.seqno;
 
 		/* do not step over block-ack window */
-		if (!BAW_WITHIN(tid->seq_start, tid->baw_size, seqno))
+		if (!BAW_WITHIN(tid->seq_start, tid->baw_size, seqno)) {
+			__skb_queue_tail(&tid->retry_q, skb);
+
+			/* If there are other skbs in the retry q, they are
+			 * probably within the BAW, so loop immediately to get
+			 * one of them. Otherwise the queue can get stuck. */
+			if (!skb_queue_is_first(&tid->retry_q, skb) &&
+			    !WARN_ON(skb == first_skb)) {
+				if(!first_skb) /* infinite loop prevention */
+					first_skb = skb;
+				continue;
+			}
 			break;
+		}
 
 		if (tid->bar_index > ATH_BA_INDEX(tid->seq_start, seqno)) {
 			struct ath_tx_status ts = {};
@@ -946,7 +970,6 @@ ath_tx_get_tid_subframe(struct ath_softc *sc, struct ath_txq *txq,
 
 			INIT_LIST_HEAD(&bf_head);
 			list_add(&bf->list, &bf_head);
-			__skb_unlink(skb, *q);
 			ath_tx_update_baw(sc, tid, seqno);
 			ath_tx_complete_buf(sc, bf, txq, &bf_head, NULL, &ts, 0);
 			continue;
@@ -958,11 +981,10 @@ ath_tx_get_tid_subframe(struct ath_softc *sc, struct ath_txq *txq,
 	return NULL;
 }
 
-static bool
+static int
 ath_tx_form_aggr(struct ath_softc *sc, struct ath_txq *txq,
 		 struct ath_atx_tid *tid, struct list_head *bf_q,
-		 struct ath_buf *bf_first, struct sk_buff_head *tid_q,
-		 int *aggr_len)
+		 struct ath_buf *bf_first)
 {
 #define PADBYTES(_len) ((4 - ((_len) % 4)) % 4)
 	struct ath_buf *bf = bf_first, *bf_prev = NULL;
@@ -972,12 +994,13 @@ ath_tx_form_aggr(struct ath_softc *sc, struct ath_txq *txq,
 	struct ieee80211_tx_info *tx_info;
 	struct ath_frame_info *fi;
 	struct sk_buff *skb;
-	bool closed = false;
+
 
 	bf = bf_first;
 	aggr_limit = ath_lookup_rate(sc, bf, tid);
 
-	do {
+	while (bf)
+	{
 		skb = bf->bf_mpdu;
 		fi = get_frame_info(skb);
 
@@ -986,12 +1009,12 @@ ath_tx_form_aggr(struct ath_softc *sc, struct ath_txq *txq,
 		if (nframes) {
 			if (aggr_limit < al + bpad + al_delta ||
 			    ath_lookup_legacy(bf) || nframes >= h_baw)
-				break;
+				goto stop;
 
 			tx_info = IEEE80211_SKB_CB(bf->bf_mpdu);
 			if ((tx_info->flags & IEEE80211_TX_CTL_RATE_CTRL_PROBE) ||
 			    !(tx_info->flags & IEEE80211_TX_CTL_AMPDU))
-				break;
+				goto stop;
 		}
 
 		/* add padding for previous frame to aggregation length */
@@ -1013,20 +1036,18 @@ ath_tx_form_aggr(struct ath_softc *sc, struct ath_txq *txq,
 			ath_tx_addto_baw(sc, tid, bf);
 		bf->bf_state.ndelim = ndelim;
 
-		__skb_unlink(skb, tid_q);
 		list_add_tail(&bf->list, bf_q);
 		if (bf_prev)
 			bf_prev->bf_next = bf;
 
 		bf_prev = bf;
 
-		bf = ath_tx_get_tid_subframe(sc, txq, tid, &tid_q);
-		if (!bf) {
-			closed = true;
-			break;
-		}
-	} while (ath_tid_has_buffered(tid));
-
+		bf = ath_tx_get_tid_subframe(sc, txq, tid);
+	}
+	goto finish;
+stop:
+	__skb_queue_tail(&tid->retry_q, bf->bf_mpdu);
+finish:
 	bf = bf_first;
 	bf->bf_lastbf = bf_prev;
 
@@ -1037,9 +1058,7 @@ ath_tx_form_aggr(struct ath_softc *sc, struct ath_txq *txq,
 		TX_STAT_INC(txq->axq_qnum, a_aggr);
 	}
 
-	*aggr_len = al;
-
-	return closed;
+	return al;
 #undef PADBYTES
 }
 
@@ -1416,18 +1435,15 @@ static void ath_tx_fill_desc(struct ath_softc *sc, struct ath_buf *bf,
 static void
 ath_tx_form_burst(struct ath_softc *sc, struct ath_txq *txq,
 		  struct ath_atx_tid *tid, struct list_head *bf_q,
-		  struct ath_buf *bf_first, struct sk_buff_head *tid_q)
+		  struct ath_buf *bf_first)
 {
 	struct ath_buf *bf = bf_first, *bf_prev = NULL;
-	struct sk_buff *skb;
 	int nframes = 0;
 
 	do {
 		struct ieee80211_tx_info *tx_info;
-		skb = bf->bf_mpdu;
 
 		nframes++;
-		__skb_unlink(skb, tid_q);
 		list_add_tail(&bf->list, bf_q);
 		if (bf_prev)
 			bf_prev->bf_next = bf;
@@ -1436,13 +1452,15 @@ ath_tx_form_burst(struct ath_softc *sc, struct ath_txq *txq,
 		if (nframes >= 2)
 			break;
 
-		bf = ath_tx_get_tid_subframe(sc, txq, tid, &tid_q);
+		bf = ath_tx_get_tid_subframe(sc, txq, tid);
 		if (!bf)
 			break;
 
 		tx_info = IEEE80211_SKB_CB(bf->bf_mpdu);
-		if (tx_info->flags & IEEE80211_TX_CTL_AMPDU)
+		if (tx_info->flags & IEEE80211_TX_CTL_AMPDU) {
+			__skb_queue_tail(&tid->retry_q, bf->bf_mpdu);
 			break;
+		}
 
 		ath_set_rates(tid->an->vif, tid->an->sta, bf);
 	} while (1);
@@ -1453,34 +1471,33 @@ static bool ath_tx_sched_aggr(struct ath_softc *sc, struct ath_txq *txq,
 {
 	struct ath_buf *bf;
 	struct ieee80211_tx_info *tx_info;
-	struct sk_buff_head *tid_q;
 	struct list_head bf_q;
 	int aggr_len = 0;
-	bool aggr, last = true;
+	bool aggr;
 
 	if (!ath_tid_has_buffered(tid))
 		return false;
 
 	INIT_LIST_HEAD(&bf_q);
 
-	bf = ath_tx_get_tid_subframe(sc, txq, tid, &tid_q);
+	bf = ath_tx_get_tid_subframe(sc, txq, tid);
 	if (!bf)
 		return false;
 
 	tx_info = IEEE80211_SKB_CB(bf->bf_mpdu);
 	aggr = !!(tx_info->flags & IEEE80211_TX_CTL_AMPDU);
 	if ((aggr && txq->axq_ampdu_depth >= ATH_AGGR_MIN_QDEPTH) ||
-		(!aggr && txq->axq_depth >= ATH_NON_AGGR_MIN_QDEPTH)) {
+	    (!aggr && txq->axq_depth >= ATH_NON_AGGR_MIN_QDEPTH)) {
+		__skb_queue_tail(&tid->retry_q, bf->bf_mpdu);
 		*stop = true;
 		return false;
 	}
 
 	ath_set_rates(tid->an->vif, tid->an->sta, bf);
 	if (aggr)
-		last = ath_tx_form_aggr(sc, txq, tid, &bf_q, bf,
-					tid_q, &aggr_len);
+		aggr_len = ath_tx_form_aggr(sc, txq, tid, &bf_q, bf);
 	else
-		ath_tx_form_burst(sc, txq, tid, &bf_q, bf, tid_q);
+		ath_tx_form_burst(sc, txq, tid, &bf_q, bf);
 
 	if (list_empty(&bf_q))
 		return false;
@@ -1523,9 +1540,6 @@ int ath_tx_aggr_start(struct ath_softc *sc, struct ieee80211_sta *sta,
 		an->mpdudensity = density;
 	}
 
-	/* force sequence number allocation for pending frames */
-	ath_tx_tid_change_state(sc, txtid);
-
 	txtid->active = true;
 	*ssn = txtid->seq_start = txtid->seq_next;
 	txtid->bar_index = -1;
@@ -1550,7 +1564,6 @@ void ath_tx_aggr_stop(struct ath_softc *sc, struct ieee80211_sta *sta, u16 tid)
 	ath_txq_lock(sc, txq);
 	txtid->active = false;
 	ath_tx_flush_tid(sc, txtid);
-	ath_tx_tid_change_state(sc, txtid);
 	ath_txq_unlock_complete(sc, txq);
 }
 
@@ -1560,14 +1573,12 @@ void ath_tx_aggr_sleep(struct ieee80211_sta *sta, struct ath_softc *sc,
 	struct ath_common *common = ath9k_hw_common(sc->sc_ah);
 	struct ath_atx_tid *tid;
 	struct ath_txq *txq;
-	bool buffered;
 	int tidno;
 
 	ath_dbg(common, XMIT, "%s called\n", __func__);
 
-	for (tidno = 0, tid = &an->tid[tidno];
-	     tidno < IEEE80211_NUM_TIDS; tidno++, tid++) {
-
+	for (tidno = 0; tidno < IEEE80211_NUM_TIDS; tidno++) {
+		tid = ath_node_to_tid(an, tidno);
 		txq = tid->txq;
 
 		ath_txq_lock(sc, txq);
@@ -1577,13 +1588,12 @@ void ath_tx_aggr_sleep(struct ieee80211_sta *sta, struct ath_softc *sc,
 			continue;
 		}
 
-		buffered = ath_tid_has_buffered(tid);
+		if (!skb_queue_empty(&tid->retry_q))
+			ieee80211_sta_set_buffered(sta, tid->tidno, true);
 
 		list_del_init(&tid->list);
 
 		ath_txq_unlock(sc, txq);
-
-		ieee80211_sta_set_buffered(sta, tidno, buffered);
 	}
 }
 
@@ -1596,49 +1606,20 @@ void ath_tx_aggr_wakeup(struct ath_softc *sc, struct ath_node *an)
 
 	ath_dbg(common, XMIT, "%s called\n", __func__);
 
-	for (tidno = 0, tid = &an->tid[tidno];
-	     tidno < IEEE80211_NUM_TIDS; tidno++, tid++) {
-
+	for (tidno = 0; tidno < IEEE80211_NUM_TIDS; tidno++) {
+		tid = ath_node_to_tid(an, tidno);
 		txq = tid->txq;
 
 		ath_txq_lock(sc, txq);
 		tid->clear_ps_filter = true;
-
 		if (ath_tid_has_buffered(tid)) {
 			ath_tx_queue_tid(sc, txq, tid);
 			ath_txq_schedule(sc, txq);
 		}
-
 		ath_txq_unlock_complete(sc, txq);
 	}
 }
 
-void ath_tx_aggr_resume(struct ath_softc *sc, struct ieee80211_sta *sta,
-			u16 tidno)
-{
-	struct ath_common *common = ath9k_hw_common(sc->sc_ah);
-	struct ath_atx_tid *tid;
-	struct ath_node *an;
-	struct ath_txq *txq;
-
-	ath_dbg(common, XMIT, "%s called\n", __func__);
-
-	an = (struct ath_node *)sta->drv_priv;
-	tid = ATH_AN_2_TID(an, tidno);
-	txq = tid->txq;
-
-	ath_txq_lock(sc, txq);
-
-	tid->baw_size = IEEE80211_MIN_AMPDU_BUF << sta->ht_cap.ampdu_factor;
-
-	if (ath_tid_has_buffered(tid)) {
-		ath_tx_queue_tid(sc, txq, tid);
-		ath_txq_schedule(sc, txq);
-	}
-
-	ath_txq_unlock_complete(sc, txq);
-}
-
 void ath9k_release_buffered_frames(struct ieee80211_hw *hw,
 				   struct ieee80211_sta *sta,
 				   u16 tids, int nframes,
@@ -1651,7 +1632,6 @@ void ath9k_release_buffered_frames(struct ieee80211_hw *hw,
 	struct ieee80211_tx_info *info;
 	struct list_head bf_q;
 	struct ath_buf *bf_tail = NULL, *bf;
-	struct sk_buff_head *tid_q;
 	int sent = 0;
 	int i;
 
@@ -1666,11 +1646,10 @@ void ath9k_release_buffered_frames(struct ieee80211_hw *hw,
 
 		ath_txq_lock(sc, tid->txq);
 		while (nframes > 0) {
-			bf = ath_tx_get_tid_subframe(sc, sc->tx.uapsdq, tid, &tid_q);
+			bf = ath_tx_get_tid_subframe(sc, sc->tx.uapsdq, tid);
 			if (!bf)
 				break;
 
-			__skb_unlink(bf->bf_mpdu, tid_q);
 			list_add_tail(&bf->list, &bf_q);
 			ath_set_rates(tid->an->vif, tid->an->sta, bf);
 			if (bf_isampdu(bf)) {
@@ -1685,7 +1664,7 @@ void ath9k_release_buffered_frames(struct ieee80211_hw *hw,
 			sent++;
 			TX_STAT_INC(txq->axq_qnum, a_queued_hw);
 
-			if (an->sta && !ath_tid_has_buffered(tid))
+			if (an->sta && skb_queue_empty(&tid->retry_q))
 				ieee80211_sta_set_buffered(an->sta, i, false);
 		}
 		ath_txq_unlock_complete(sc, tid->txq);
@@ -1914,13 +1893,7 @@ bool ath_drain_all_txq(struct ath_softc *sc)
 		if (!ATH_TXQ_SETUP(sc, i))
 			continue;
 
-		/*
-		 * The caller will resume queues with ieee80211_wake_queues.
-		 * Mark the queue as not stopped to prevent ath_tx_complete
-		 * from waking the queue too early.
-		 */
 		txq = &sc->tx.txq[i];
-		txq->stopped = false;
 		ath_draintxq(sc, txq);
 	}
 
@@ -2319,16 +2292,14 @@ int ath_tx_start(struct ieee80211_hw *hw, struct sk_buff *skb,
 	struct ath_softc *sc = hw->priv;
 	struct ath_txq *txq = txctl->txq;
 	struct ath_atx_tid *tid = NULL;
+	struct ath_node *an = NULL;
 	struct ath_buf *bf;
-	bool queue, skip_uapsd = false, ps_resp;
+	bool ps_resp;
 	int q, ret;
 
 	if (vif)
 		avp = (void *)vif->drv_priv;
 
-	if (info->flags & IEEE80211_TX_CTL_TX_OFFCHAN)
-		txctl->force_channel = true;
-
 	ps_resp = !!(info->control.flags & IEEE80211_TX_CTRL_PS_RESPONSE);
 
 	ret = ath_tx_prepare(hw, skb, txctl);
@@ -2343,63 +2314,18 @@ int ath_tx_start(struct ieee80211_hw *hw, struct sk_buff *skb,
 
 	q = skb_get_queue_mapping(skb);
 
-	ath_txq_lock(sc, txq);
-	if (txq == sc->tx.txq_map[q]) {
-		fi->txq = q;
-		if (++txq->pending_frames > sc->tx.txq_max_pending[q] &&
-		    !txq->stopped) {
-			if (ath9k_is_chanctx_enabled())
-				ieee80211_stop_queue(sc->hw, info->hw_queue);
-			else
-				ieee80211_stop_queue(sc->hw, q);
-			txq->stopped = true;
-		}
-	}
-
-	queue = ieee80211_is_data_present(hdr->frame_control);
-
-	/* If chanctx, queue all null frames while NOA could be there */
-	if (ath9k_is_chanctx_enabled() &&
-	    ieee80211_is_nullfunc(hdr->frame_control) &&
-	    !txctl->force_channel)
-		queue = true;
-
-	/* Force queueing of all frames that belong to a virtual interface on
-	 * a different channel context, to ensure that they are sent on the
-	 * correct channel.
-	 */
-	if (((avp && avp->chanctx != sc->cur_chan) ||
-	     sc->cur_chan->stopped) && !txctl->force_channel) {
-		if (!txctl->an)
-			txctl->an = &avp->mcast_node;
-		queue = true;
-		skip_uapsd = true;
-	}
-
-	if (txctl->an && queue)
-		tid = ath_get_skb_tid(sc, txctl->an, skb);
-
-	if (!skip_uapsd && ps_resp) {
-		ath_txq_unlock(sc, txq);
+	if (ps_resp)
 		txq = sc->tx.uapsdq;
-		ath_txq_lock(sc, txq);
-	} else if (txctl->an && queue) {
-		WARN_ON(tid->txq != txctl->txq);
 
-		if (info->flags & IEEE80211_TX_CTL_CLEAR_PS_FILT)
-			tid->clear_ps_filter = true;
-
-		/*
-		 * Add this frame to software queue for scheduling later
-		 * for aggregation.
-		 */
-		TX_STAT_INC(txq->axq_qnum, a_queued_sw);
-		__skb_queue_tail(&tid->buf_q, skb);
-		if (!txctl->an->sleeping)
-			ath_tx_queue_tid(sc, txq, tid);
+	if (txctl->sta) {
+		an = (struct ath_node *) sta->drv_priv;
+		tid = ath_get_skb_tid(sc, an, skb);
+	}
 
-		ath_txq_schedule(sc, txq);
-		goto out;
+	ath_txq_lock(sc, txq);
+	if (txq == sc->tx.txq_map[q]) {
+		fi->txq = q;
+		++txq->pending_frames;
 	}
 
 	bf = ath_tx_setup_buffer(sc, txq, tid, skb);
@@ -2892,9 +2818,8 @@ void ath_tx_node_init(struct ath_softc *sc, struct ath_node *an)
 	struct ath_atx_tid *tid;
 	int tidno, acno;
 
-	for (tidno = 0, tid = &an->tid[tidno];
-	     tidno < IEEE80211_NUM_TIDS;
-	     tidno++, tid++) {
+	for (tidno = 0; tidno < IEEE80211_NUM_TIDS; tidno++) {
+		tid = ath_node_to_tid(an, tidno);
 		tid->an        = an;
 		tid->tidno     = tidno;
 		tid->seq_start = tid->seq_next = 0;
@@ -2902,11 +2827,14 @@ void ath_tx_node_init(struct ath_softc *sc, struct ath_node *an)
 		tid->baw_head  = tid->baw_tail = 0;
 		tid->active	   = false;
 		tid->clear_ps_filter = true;
-		__skb_queue_head_init(&tid->buf_q);
+		tid->has_queued  = false;
 		__skb_queue_head_init(&tid->retry_q);
 		INIT_LIST_HEAD(&tid->list);
 		acno = TID_TO_WME_AC(tidno);
 		tid->txq = sc->tx.txq_map[acno];
+
+		if (!an->sta)
+			break; /* just one multicast ath_atx_tid */
 	}
 }
 
@@ -2916,9 +2844,8 @@ void ath_tx_node_cleanup(struct ath_softc *sc, struct ath_node *an)
 	struct ath_txq *txq;
 	int tidno;
 
-	for (tidno = 0, tid = &an->tid[tidno];
-	     tidno < IEEE80211_NUM_TIDS; tidno++, tid++) {
-
+	for (tidno = 0; tidno < IEEE80211_NUM_TIDS; tidno++) {
+		tid = ath_node_to_tid(an, tidno);
 		txq = tid->txq;
 
 		ath_txq_lock(sc, txq);
@@ -2930,6 +2857,9 @@ void ath_tx_node_cleanup(struct ath_softc *sc, struct ath_node *an)
 		tid->active = false;
 
 		ath_txq_unlock(sc, txq);
+
+		if (!an->sta)
+			break; /* just one multicast ath_atx_tid */
 	}
 }