1 files changed, 45 insertions, 7 deletions

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index f7a6e14491fb..c99ffe9cc88f 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -36,8 +36,16 @@ struct qdisc_rate_table {
 enum qdisc_state_t {
 	__QDISC_STATE_SCHED,
 	__QDISC_STATE_DEACTIVATED,
+	__QDISC_STATE_MISSED,
+	__QDISC_STATE_DRAINING,
 };
 
+#define QDISC_STATE_MISSED	BIT(__QDISC_STATE_MISSED)
+#define QDISC_STATE_DRAINING	BIT(__QDISC_STATE_DRAINING)
+
+#define QDISC_STATE_NON_EMPTY	(QDISC_STATE_MISSED | \
+					QDISC_STATE_DRAINING)
+
 struct qdisc_size_table {
 	struct rcu_head		rcu;
 	struct list_head	list;
@@ -109,8 +117,6 @@ struct Qdisc {
 	spinlock_t		busylock ____cacheline_aligned_in_smp;
 	spinlock_t		seqlock;
 
-	/* for NOLOCK qdisc, true if there are no enqueued skbs */
-	bool			empty;
 	struct rcu_head		rcu;
 
 	/* private data */
@@ -144,6 +150,11 @@ static inline bool qdisc_is_running(struct Qdisc *qdisc)
 	return (raw_read_seqcount(&qdisc->running) & 1) ? true : false;
 }
 
+static inline bool nolock_qdisc_is_empty(const struct Qdisc *qdisc)
+{
+	return !(READ_ONCE(qdisc->state) & QDISC_STATE_NON_EMPTY);
+}
+
 static inline bool qdisc_is_percpu_stats(const struct Qdisc *q)
 {
 	return q->flags & TCQ_F_CPUSTATS;
@@ -152,16 +163,37 @@ static inline bool qdisc_is_percpu_stats(const struct Qdisc *q)
 static inline bool qdisc_is_empty(const struct Qdisc *qdisc)
 {
 	if (qdisc_is_percpu_stats(qdisc))
-		return READ_ONCE(qdisc->empty);
+		return nolock_qdisc_is_empty(qdisc);
 	return !READ_ONCE(qdisc->q.qlen);
 }
 
 static inline bool qdisc_run_begin(struct Qdisc *qdisc)
 {
 	if (qdisc->flags & TCQ_F_NOLOCK) {
-		if (!spin_trylock(&qdisc->seqlock))
+		if (spin_trylock(&qdisc->seqlock))
+			return true;
+
+		/* If the MISSED flag is set, it means other thread has
+		 * set the MISSED flag before second spin_trylock(), so
+		 * we can return false here to avoid multi cpus doing
+		 * the set_bit() and second spin_trylock() concurrently.
+		 */
+		if (test_bit(__QDISC_STATE_MISSED, &qdisc->state))
 			return false;
-		WRITE_ONCE(qdisc->empty, false);
+
+		/* Set the MISSED flag before the second spin_trylock(),
+		 * if the second spin_trylock() return false, it means
+		 * other cpu holding the lock will do dequeuing for us
+		 * or it will see the MISSED flag set after releasing
+		 * lock and reschedule the net_tx_action() to do the
+		 * dequeuing.
+		 */
+		set_bit(__QDISC_STATE_MISSED, &qdisc->state);
+
+		/* Retry again in case other CPU may not see the new flag
+		 * after it releases the lock at the end of qdisc_run_end().
+		 */
+		return spin_trylock(&qdisc->seqlock);
 	} else if (qdisc_is_running(qdisc)) {
 		return false;
 	}
@@ -175,9 +207,15 @@ static inline bool qdisc_run_begin(struct Qdisc *qdisc)
 
 static inline void qdisc_run_end(struct Qdisc *qdisc)
 {
-	write_seqcount_end(&qdisc->running);
-	if (qdisc->flags & TCQ_F_NOLOCK)
+	if (qdisc->flags & TCQ_F_NOLOCK) {
 		spin_unlock(&qdisc->seqlock);
+
+		if (unlikely(test_bit(__QDISC_STATE_MISSED,
+				      &qdisc->state)))
+			__netif_schedule(qdisc);
+	} else {
+		write_seqcount_end(&qdisc->running);
+	}
 }
 
 static inline bool qdisc_may_bulk(const struct Qdisc *qdisc)