diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index b3591e4a514c..b35301b0c7b6 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -80,7 +80,8 @@ struct Qdisc {
 	struct gnet_stats_basic_packed bstats;
 	unsigned long		__state;
 	struct gnet_stats_queue	qstats;
-	struct rcu_head     rcu_head;
+	struct rcu_head		rcu_head;
+	spinlock_t		busylock;
 };
 
 static inline bool qdisc_is_running(struct Qdisc *qdisc)
diff --git a/net/core/dev.c b/net/core/dev.c
index 2733226d90b2..ffca5c1066fa 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2040,8 +2040,18 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 				 struct netdev_queue *txq)
 {
 	spinlock_t *root_lock = qdisc_lock(q);
+	bool contended = qdisc_is_running(q);
 	int rc;
 
+	/*
+	 * Heuristic to force contended enqueues to serialize on a
+	 * separate lock before trying to get qdisc main lock.
+	 * This permits __QDISC_STATE_RUNNING owner to get the lock more often
+	 * and dequeue packets faster.
+	 */
+	if (unlikely(contended))
+		spin_lock(&q->busylock);
+
 	spin_lock(root_lock);
 	if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) {
 		kfree_skb(skb);
@@ -2056,19 +2066,30 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 		if (!(dev->priv_flags & IFF_XMIT_DST_RELEASE))
 			skb_dst_force(skb);
 		__qdisc_update_bstats(q, skb->len);
-		if (sch_direct_xmit(skb, q, dev, txq, root_lock))
+		if (sch_direct_xmit(skb, q, dev, txq, root_lock)) {
+			if (unlikely(contended)) {
+				spin_unlock(&q->busylock);
+				contended = false;
+			}
 			__qdisc_run(q);
-		else
+		} else
 			qdisc_run_end(q);
 
 		rc = NET_XMIT_SUCCESS;
 	} else {
 		skb_dst_force(skb);
 		rc = qdisc_enqueue_root(skb, q);
-		qdisc_run(q);
+		if (qdisc_run_begin(q)) {
+			if (unlikely(contended)) {
+				spin_unlock(&q->busylock);
+				contended = false;
+			}
+			__qdisc_run(q);
+		}
 	}
 	spin_unlock(root_lock);
-
+	if (unlikely(contended))
+		spin_unlock(&q->busylock);
 	return rc;
 }
 
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 37b86eab6779..d20fcd2a5519 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -561,6 +561,7 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
 
 	INIT_LIST_HEAD(&sch->list);
 	skb_queue_head_init(&sch->q);
+	spin_lock_init(&sch->busylock);
 	sch->ops = ops;
 	sch->enqueue = ops->enqueue;
 	sch->dequeue = ops->dequeue;