1 files changed, 81 insertions, 8 deletions

diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 44991ea726fc..d9ac60ffe927 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -35,6 +35,27 @@
 const struct Qdisc_ops *default_qdisc_ops = &pfifo_fast_ops;
 EXPORT_SYMBOL(default_qdisc_ops);
 
+static void qdisc_maybe_clear_missed(struct Qdisc *q,
+				     const struct netdev_queue *txq)
+{
+	clear_bit(__QDISC_STATE_MISSED, &q->state);
+
+	/* Make sure the below netif_xmit_frozen_or_stopped()
+	 * checking happens after clearing STATE_MISSED.
+	 */
+	smp_mb__after_atomic();
+
+	/* Checking netif_xmit_frozen_or_stopped() again to
+	 * make sure STATE_MISSED is set if the STATE_MISSED
+	 * set by netif_tx_wake_queue()'s rescheduling of
+	 * net_tx_action() is cleared by the above clear_bit().
+	 */
+	if (!netif_xmit_frozen_or_stopped(txq))
+		set_bit(__QDISC_STATE_MISSED, &q->state);
+	else
+		set_bit(__QDISC_STATE_DRAINING, &q->state);
+}
+
 /* Main transmission queue. */
 
 /* Modifications to data participating in scheduling must be protected with
@@ -74,6 +95,7 @@ static inline struct sk_buff *__skb_dequeue_bad_txq(struct Qdisc *q)
 			}
 		} else {
 			skb = SKB_XOFF_MAGIC;
+			qdisc_maybe_clear_missed(q, txq);
 		}
 	}
 
@@ -144,9 +166,13 @@ static inline void dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q)
 
 		skb = next;
 	}
-	if (lock)
+
+	if (lock) {
 		spin_unlock(lock);
-	__netif_schedule(q);
+		set_bit(__QDISC_STATE_MISSED, &q->state);
+	} else {
+		__netif_schedule(q);
+	}
 }
 
 static void try_bulk_dequeue_skb(struct Qdisc *q,
@@ -242,6 +268,7 @@ static struct sk_buff *dequeue_skb(struct Qdisc *q, bool *validate,
 			}
 		} else {
 			skb = NULL;
+			qdisc_maybe_clear_missed(q, txq);
 		}
 		if (lock)
 			spin_unlock(lock);
@@ -251,8 +278,10 @@ validate:
 	*validate = true;
 
 	if ((q->flags & TCQ_F_ONETXQUEUE) &&
-	    netif_xmit_frozen_or_stopped(txq))
+	    netif_xmit_frozen_or_stopped(txq)) {
+		qdisc_maybe_clear_missed(q, txq);
 		return skb;
+	}
 
 	skb = qdisc_dequeue_skb_bad_txq(q);
 	if (unlikely(skb)) {
@@ -311,6 +340,8 @@ bool sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q,
 		HARD_TX_LOCK(dev, txq, smp_processor_id());
 		if (!netif_xmit_frozen_or_stopped(txq))
 			skb = dev_hard_start_xmit(skb, dev, txq, &ret);
+		else
+			qdisc_maybe_clear_missed(q, txq);
 
 		HARD_TX_UNLOCK(dev, txq);
 	} else {
@@ -384,7 +415,11 @@ void __qdisc_run(struct Qdisc *q)
 	while (qdisc_restart(q, &packets)) {
 		quota -= packets;
 		if (quota <= 0) {
-			__netif_schedule(q);
+			if (q->flags & TCQ_F_NOLOCK)
+				set_bit(__QDISC_STATE_MISSED, &q->state);
+			else
+				__netif_schedule(q);
+
 			break;
 		}
 	}
@@ -515,6 +550,24 @@ void netif_carrier_off(struct net_device *dev)
 }
 EXPORT_SYMBOL(netif_carrier_off);
 
+/**
+ *	netif_carrier_event - report carrier state event
+ *	@dev: network device
+ *
+ * Device has detected a carrier event but the carrier state wasn't changed.
+ * Use in drivers when querying carrier state asynchronously, to avoid missing
+ * events (link flaps) if link recovers before it's queried.
+ */
+void netif_carrier_event(struct net_device *dev)
+{
+	if (dev->reg_state == NETREG_UNINITIALIZED)
+		return;
+	atomic_inc(&dev->carrier_up_count);
+	atomic_inc(&dev->carrier_down_count);
+	linkwatch_fire_event(dev);
+}
+EXPORT_SYMBOL_GPL(netif_carrier_event);
+
 /* "NOOP" scheduler: the best scheduler, recommended for all interfaces
    under all circumstances. It is difficult to invent anything faster or
    cheaper.
@@ -640,8 +693,10 @@ static struct sk_buff *pfifo_fast_dequeue(struct Qdisc *qdisc)
 {
 	struct pfifo_fast_priv *priv = qdisc_priv(qdisc);
 	struct sk_buff *skb = NULL;
+	bool need_retry = true;
 	int band;
 
+retry:
 	for (band = 0; band < PFIFO_FAST_BANDS && !skb; band++) {
 		struct skb_array *q = band2list(priv, band);
 
@@ -652,8 +707,24 @@ static struct sk_buff *pfifo_fast_dequeue(struct Qdisc *qdisc)
 	}
 	if (likely(skb)) {
 		qdisc_update_stats_at_dequeue(qdisc, skb);
-	} else {
-		WRITE_ONCE(qdisc->empty, true);
+	} else if (need_retry &&
+		   READ_ONCE(qdisc->state) & QDISC_STATE_NON_EMPTY) {
+		/* Delay clearing the STATE_MISSED here to reduce
+		 * the overhead of the second spin_trylock() in
+		 * qdisc_run_begin() and __netif_schedule() calling
+		 * in qdisc_run_end().
+		 */
+		clear_bit(__QDISC_STATE_MISSED, &qdisc->state);
+		clear_bit(__QDISC_STATE_DRAINING, &qdisc->state);
+
+		/* Make sure dequeuing happens after clearing
+		 * STATE_MISSED.
+		 */
+		smp_mb__after_atomic();
+
+		need_retry = false;
+
+		goto retry;
 	}
 
 	return skb;
@@ -854,7 +925,6 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
 	sch->enqueue = ops->enqueue;
 	sch->dequeue = ops->dequeue;
 	sch->dev_queue = dev_queue;
-	sch->empty = true;
 	dev_hold(dev);
 	refcount_set(&sch->refcnt, 1);
 
@@ -1158,8 +1228,11 @@ static void dev_reset_queue(struct net_device *dev,
 	qdisc_reset(qdisc);
 
 	spin_unlock_bh(qdisc_lock(qdisc));
-	if (nolock)
+	if (nolock) {
+		clear_bit(__QDISC_STATE_MISSED, &qdisc->state);
+		clear_bit(__QDISC_STATE_DRAINING, &qdisc->state);
 		spin_unlock_bh(&qdisc->seqlock);
+	}
 }
 
 static bool some_qdisc_is_busy(struct net_device *dev)