wifi: mac80211: Proper mark iTXQs for resumption

commit 4444bc2116 upstream.

When a running wake_tx_queue() call is aborted due to a hw queue stop
the corresponding iTXQ is not always correctly marked for resumption:
wake_tx_push_queue() can stops the queue run without setting
@IEEE80211_TXQ_STOP_NETIF_TX.

Without the @IEEE80211_TXQ_STOP_NETIF_TX flag __ieee80211_wake_txqs()
will not schedule a new queue run and remaining frames in the queue get
stuck till another frame is queued to it.

Fix the issue for all drivers - also the ones with custom wake_tx_queue
callbacks - by moving the logic into ieee80211_tx_dequeue() and drop the
redundant @txqs_stopped.

@IEEE80211_TXQ_STOP_NETIF_TX is also renamed to @IEEE80211_TXQ_DIRTY to
better describe the flag.

Fixes: c850e31f79 ("wifi: mac80211: add internal handler for wake_tx_queue")
Signed-off-by: Alexander Wetzel <alexander@wetzel-home.de>
Link: https://lore.kernel.org/r/20221230121850.218810-1-alexander@wetzel-home.de
Cc: stable@vger.kernel.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

include/net/mac80211.h

@@ -1827,8 +1827,6 @@ struct ieee80211_vif_cfg {
  * @drv_priv: data area for driver use, will always be aligned to
  *	sizeof(void \*).
  * @txq: the multicast data TX queue (if driver uses the TXQ abstraction)
- * @txqs_stopped: per AC flag to indicate that intermediate TXQs are stopped,
- *	protected by fq->lock.
  * @offload_flags: 802.3 -> 802.11 enapsulation offload flags, see
  *	&enum ieee80211_offload_flags.
  * @mbssid_tx_vif: Pointer to the transmitting interface if MBSSID is enabled.
@@ -1857,8 +1855,6 @@ struct ieee80211_vif {
 	bool probe_req_reg;
 	bool rx_mcast_action_reg;
 
-	bool txqs_stopped[IEEE80211_NUM_ACS];
-
 	struct ieee80211_vif *mbssid_tx_vif;
 
 	/* must be last */

net/mac80211/debugfs_sta.c

@@ -167,7 +167,7 @@ static ssize_t sta_aqm_read(struct file *file, char __user *userbuf,
 			continue;
 		txqi = to_txq_info(sta->sta.txq[i]);
 		p += scnprintf(p, bufsz + buf - p,
-			       "%d %d %u %u %u %u %u %u %u %u %u 0x%lx(%s%s%s)\n",
+			       "%d %d %u %u %u %u %u %u %u %u %u 0x%lx(%s%s%s%s)\n",
 			       txqi->txq.tid,
 			       txqi->txq.ac,
 			       txqi->tin.backlog_bytes,
@@ -182,7 +182,8 @@ static ssize_t sta_aqm_read(struct file *file, char __user *userbuf,
 			       txqi->flags,
 			       test_bit(IEEE80211_TXQ_STOP, &txqi->flags) ? "STOP" : "RUN",
 			       test_bit(IEEE80211_TXQ_AMPDU, &txqi->flags) ? " AMPDU" : "",
-			       test_bit(IEEE80211_TXQ_NO_AMSDU, &txqi->flags) ? " NO-AMSDU" : "");
+			       test_bit(IEEE80211_TXQ_NO_AMSDU, &txqi->flags) ? " NO-AMSDU" : "",
+			       test_bit(IEEE80211_TXQ_DIRTY, &txqi->flags) ? " DIRTY" : "");
 	}
 
 	rcu_read_unlock();

net/mac80211/driver-ops.h

@@ -1183,7 +1183,7 @@ static inline void drv_wake_tx_queue(struct ieee80211_local *local,
 
 	/* In reconfig don't transmit now, but mark for waking later */
 	if (local->in_reconfig) {
-		set_bit(IEEE80211_TXQ_STOP_NETIF_TX, &txq->flags);
+		set_bit(IEEE80211_TXQ_DIRTY, &txq->flags);
 		return;
 	}
 

net/mac80211/ieee80211_i.h

@@ -836,7 +836,7 @@ enum txq_info_flags {
 	IEEE80211_TXQ_STOP,
 	IEEE80211_TXQ_AMPDU,
 	IEEE80211_TXQ_NO_AMSDU,
-	IEEE80211_TXQ_STOP_NETIF_TX,
+	IEEE80211_TXQ_DIRTY,
 };
 
 /**

net/mac80211/tx.c

@@ -3709,13 +3709,15 @@ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw,
 	struct ieee80211_local *local = hw_to_local(hw);
 	struct txq_info *txqi = container_of(txq, struct txq_info, txq);
 	struct ieee80211_hdr *hdr;
-	struct sk_buff *skb = NULL;
 	struct fq *fq = &local->fq;
 	struct fq_tin *tin = &txqi->tin;
 	struct ieee80211_tx_info *info;
 	struct ieee80211_tx_data tx;
+	struct sk_buff *skb;
 	ieee80211_tx_result r;
 	struct ieee80211_vif *vif = txq->vif;
+	int q = vif->hw_queue[txq->ac];
+	bool q_stopped;
 
 	WARN_ON_ONCE(softirq_count() == 0);
 
@@ -3723,17 +3725,22 @@ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw,
 		return NULL;
 
 begin:
+	skb = NULL;
+	spin_lock(&local->queue_stop_reason_lock);
+	q_stopped = local->queue_stop_reasons[q];
+	spin_unlock(&local->queue_stop_reason_lock);
+
+	if (unlikely(q_stopped)) {
+		/* mark for waking later */
+		set_bit(IEEE80211_TXQ_DIRTY, &txqi->flags);
+		return NULL;
+	}
+
 	spin_lock_bh(&fq->lock);
 
-	if (test_bit(IEEE80211_TXQ_STOP, &txqi->flags) ||
-	    test_bit(IEEE80211_TXQ_STOP_NETIF_TX, &txqi->flags))
+	if (unlikely(test_bit(IEEE80211_TXQ_STOP, &txqi->flags)))
 		goto out;
 
-	if (vif->txqs_stopped[txq->ac]) {
-		set_bit(IEEE80211_TXQ_STOP_NETIF_TX, &txqi->flags);
-		goto out;
-	}
-
 	/* Make sure fragments stay together. */
 	skb = __skb_dequeue(&txqi->frags);
 	if (unlikely(skb)) {

net/mac80211/util.c

@@ -301,8 +301,6 @@ static void __ieee80211_wake_txqs(struct ieee80211_sub_if_data *sdata, int ac)
 	local_bh_disable();
 	spin_lock(&fq->lock);
 
-	sdata->vif.txqs_stopped[ac] = false;
-
 	if (!test_bit(SDATA_STATE_RUNNING, &sdata->state))
 		goto out;
 
@@ -324,7 +322,7 @@ static void __ieee80211_wake_txqs(struct ieee80211_sub_if_data *sdata, int ac)
 			if (ac != txq->ac)
 				continue;
 
-			if (!test_and_clear_bit(IEEE80211_TXQ_STOP_NETIF_TX,
+			if (!test_and_clear_bit(IEEE80211_TXQ_DIRTY,
 						&txqi->flags))
 				continue;
 
@@ -339,7 +337,7 @@ static void __ieee80211_wake_txqs(struct ieee80211_sub_if_data *sdata, int ac)
 
 	txqi = to_txq_info(vif->txq);
 
-	if (!test_and_clear_bit(IEEE80211_TXQ_STOP_NETIF_TX, &txqi->flags) ||
+	if (!test_and_clear_bit(IEEE80211_TXQ_DIRTY, &txqi->flags) ||
 	    (ps && atomic_read(&ps->num_sta_ps)) || ac != vif->txq->ac)
 		goto out;
 
@@ -537,16 +535,10 @@ static void __ieee80211_stop_queue(struct ieee80211_hw *hw, int queue,
 			continue;
 
 		for (ac = 0; ac < n_acs; ac++) {
-			if (sdata->vif.hw_queue[ac] == queue ||
-			    sdata->vif.cab_queue == queue) {
-				if (!local->ops->wake_tx_queue) {
-					netif_stop_subqueue(sdata->dev, ac);
-					continue;
-				}
-				spin_lock(&local->fq.lock);
-				sdata->vif.txqs_stopped[ac] = true;
-				spin_unlock(&local->fq.lock);
-			}
+			if (!local->ops->wake_tx_queue &&
+			    (sdata->vif.hw_queue[ac] == queue ||
+			     sdata->vif.cab_queue == queue))
+				netif_stop_subqueue(sdata->dev, ac);
 		}
 	}
 	rcu_read_unlock();