diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index e01d57692c9a76f530b89cbc0b9e9443ae3c8ced..fa1a6f45dc416173f8b6d853f9ce0c5fa3565bc7 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -556,6 +556,7 @@ void dev_deactivate(struct net_device *dev)
 {
 	struct Qdisc *qdisc;
 	struct sk_buff *skb;
+	int running;
 
 	spin_lock_bh(&dev->queue_lock);
 	qdisc = dev->qdisc;
@@ -571,12 +572,31 @@ void dev_deactivate(struct net_device *dev)
 
 	dev_watchdog_down(dev);
 
-	/* Wait for outstanding dev_queue_xmit calls. */
+	/* Wait for outstanding qdisc-less dev_queue_xmit calls. */
 	synchronize_rcu();
 
 	/* Wait for outstanding qdisc_run calls. */
-	while (test_bit(__LINK_STATE_QDISC_RUNNING, &dev->state))
-		yield();
+	do {
+		while (test_bit(__LINK_STATE_QDISC_RUNNING, &dev->state))
+			yield();
+
+		/*
+		 * Double-check inside queue lock to ensure that all effects
+		 * of the queue run are visible when we return.
+		 */
+		spin_lock_bh(&dev->queue_lock);
+		running = test_bit(__LINK_STATE_QDISC_RUNNING, &dev->state);
+		spin_unlock_bh(&dev->queue_lock);
+
+		/*
+		 * The running flag should never be set at this point because
+		 * we've already set dev->qdisc to noop_qdisc *inside* the same
+		 * pair of spin locks.  That is, if any qdisc_run starts after
+		 * our initial test it should see the noop_qdisc and then
+		 * clear the RUNNING bit before dropping the queue lock.  So
+		 * if it is set here then we've found a bug.
+		 */
+	} while (WARN_ON_ONCE(running));
 }
 
 void dev_init_scheduler(struct net_device *dev)