diff --git a/net/core/dev.c b/net/core/dev.c
index 2733226..ffca5c10 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2040,8 +2040,18 @@
 				 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 @@
 		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;
 }