1 files changed, 107 insertions, 59 deletions

diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 3b0f62095803..a9aadc4e6858 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -409,7 +409,7 @@ static inline bool qdisc_restart(struct Qdisc *q, int *packets)
 
 void __qdisc_run(struct Qdisc *q)
 {
-	int quota = dev_tx_weight;
+	int quota = READ_ONCE(dev_tx_weight);
 	int packets;
 
 	while (qdisc_restart(q, &packets)) {
@@ -427,16 +427,12 @@ void __qdisc_run(struct Qdisc *q)
 
 unsigned long dev_trans_start(struct net_device *dev)
 {
-	unsigned long val, res;
+	unsigned long res = READ_ONCE(netdev_get_tx_queue(dev, 0)->trans_start);
+	unsigned long val;
 	unsigned int i;
 
-	if (is_vlan_dev(dev))
-		dev = vlan_dev_real_dev(dev);
-	else if (netif_is_macvlan(dev))
-		dev = macvlan_dev_real_dev(dev);
-	res = netdev_get_tx_queue(dev, 0)->trans_start;
 	for (i = 1; i < dev->num_tx_queues; i++) {
-		val = netdev_get_tx_queue(dev, i)->trans_start;
+		val = READ_ONCE(netdev_get_tx_queue(dev, i)->trans_start);
 		if (val && time_after(val, res))
 			res = val;
 	}
@@ -445,11 +441,63 @@ unsigned long dev_trans_start(struct net_device *dev)
 }
 EXPORT_SYMBOL(dev_trans_start);
 
+static void netif_freeze_queues(struct net_device *dev)
+{
+	unsigned int i;
+	int cpu;
+
+	cpu = smp_processor_id();
+	for (i = 0; i < dev->num_tx_queues; i++) {
+		struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
+
+		/* We are the only thread of execution doing a
+		 * freeze, but we have to grab the _xmit_lock in
+		 * order to synchronize with threads which are in
+		 * the ->hard_start_xmit() handler and already
+		 * checked the frozen bit.
+		 */
+		__netif_tx_lock(txq, cpu);
+		set_bit(__QUEUE_STATE_FROZEN, &txq->state);
+		__netif_tx_unlock(txq);
+	}
+}
+
+void netif_tx_lock(struct net_device *dev)
+{
+	spin_lock(&dev->tx_global_lock);
+	netif_freeze_queues(dev);
+}
+EXPORT_SYMBOL(netif_tx_lock);
+
+static void netif_unfreeze_queues(struct net_device *dev)
+{
+	unsigned int i;
+
+	for (i = 0; i < dev->num_tx_queues; i++) {
+		struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
+
+		/* No need to grab the _xmit_lock here.  If the
+		 * queue is not stopped for another reason, we
+		 * force a schedule.
+		 */
+		clear_bit(__QUEUE_STATE_FROZEN, &txq->state);
+		netif_schedule_queue(txq);
+	}
+}
+
+void netif_tx_unlock(struct net_device *dev)
+{
+	netif_unfreeze_queues(dev);
+	spin_unlock(&dev->tx_global_lock);
+}
+EXPORT_SYMBOL(netif_tx_unlock);
+
 static void dev_watchdog(struct timer_list *t)
 {
 	struct net_device *dev = from_timer(dev, t, watchdog_timer);
+	bool release = true;
 
-	netif_tx_lock(dev);
+	spin_lock(&dev->tx_global_lock);
 	if (!qdisc_tx_is_noop(dev)) {
 		if (netif_device_present(dev) &&
 		    netif_running(dev) &&
@@ -462,31 +510,34 @@ static void dev_watchdog(struct timer_list *t)
 				struct netdev_queue *txq;
 
 				txq = netdev_get_tx_queue(dev, i);
-				trans_start = txq->trans_start;
+				trans_start = READ_ONCE(txq->trans_start);
 				if (netif_xmit_stopped(txq) &&
 				    time_after(jiffies, (trans_start +
 							 dev->watchdog_timeo))) {
 					some_queue_timedout = 1;
-					txq->trans_timeout++;
+					atomic_long_inc(&txq->trans_timeout);
 					break;
 				}
 			}
 
-			if (some_queue_timedout) {
+			if (unlikely(some_queue_timedout)) {
 				trace_net_dev_xmit_timeout(dev, i);
 				WARN_ONCE(1, KERN_INFO "NETDEV WATCHDOG: %s (%s): transmit queue %u timed out\n",
 				       dev->name, netdev_drivername(dev), i);
+				netif_freeze_queues(dev);
 				dev->netdev_ops->ndo_tx_timeout(dev, i);
+				netif_unfreeze_queues(dev);
 			}
 			if (!mod_timer(&dev->watchdog_timer,
 				       round_jiffies(jiffies +
 						     dev->watchdog_timeo)))
-				dev_hold(dev);
+				release = false;
 		}
 	}
-	netif_tx_unlock(dev);
+	spin_unlock(&dev->tx_global_lock);
 
-	dev_put(dev);
+	if (release)
+		netdev_put(dev, &dev->watchdog_dev_tracker);
 }
 
 void __netdev_watchdog_up(struct net_device *dev)
@@ -496,7 +547,8 @@ void __netdev_watchdog_up(struct net_device *dev)
 			dev->watchdog_timeo = 5*HZ;
 		if (!mod_timer(&dev->watchdog_timer,
 			       round_jiffies(jiffies + dev->watchdog_timeo)))
-			dev_hold(dev);
+			netdev_hold(dev, &dev->watchdog_dev_tracker,
+				    GFP_ATOMIC);
 	}
 }
 EXPORT_SYMBOL_GPL(__netdev_watchdog_up);
@@ -510,7 +562,7 @@ static void dev_watchdog_down(struct net_device *dev)
 {
 	netif_tx_lock_bh(dev);
 	if (del_timer(&dev->watchdog_timer))
-		dev_put(dev);
+		netdev_put(dev, &dev->watchdog_dev_tracker);
 	netif_tx_unlock_bh(dev);
 }
 
@@ -889,7 +941,6 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
 		goto errout;
 	__skb_queue_head_init(&sch->gso_skb);
 	__skb_queue_head_init(&sch->skb_bad_txq);
-	qdisc_skb_head_init(&sch->q);
 	gnet_stats_basic_sync_init(&sch->bstats);
 	spin_lock_init(&sch->q.lock);
 
@@ -920,7 +971,7 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
 	sch->enqueue = ops->enqueue;
 	sch->dequeue = ops->dequeue;
 	sch->dev_queue = dev_queue;
-	dev_hold(dev);
+	netdev_hold(dev, &sch->dev_tracker, GFP_KERNEL);
 	refcount_set(&sch->refcnt, 1);
 
 	return sch;
@@ -964,22 +1015,14 @@ EXPORT_SYMBOL(qdisc_create_dflt);
 void qdisc_reset(struct Qdisc *qdisc)
 {
 	const struct Qdisc_ops *ops = qdisc->ops;
-	struct sk_buff *skb, *tmp;
 
 	trace_qdisc_reset(qdisc);
 
 	if (ops->reset)
 		ops->reset(qdisc);
 
-	skb_queue_walk_safe(&qdisc->gso_skb, skb, tmp) {
-		__skb_unlink(skb, &qdisc->gso_skb);
-		kfree_skb_list(skb);
-	}
-
-	skb_queue_walk_safe(&qdisc->skb_bad_txq, skb, tmp) {
-		__skb_unlink(skb, &qdisc->skb_bad_txq);
-		kfree_skb_list(skb);
-	}
+	__skb_queue_purge(&qdisc->gso_skb);
+	__skb_queue_purge(&qdisc->skb_bad_txq);
 
 	qdisc->q.qlen = 0;
 	qdisc->qstats.backlog = 0;
@@ -1020,7 +1063,7 @@ static void qdisc_destroy(struct Qdisc *qdisc)
 		ops->destroy(qdisc);
 
 	module_put(ops->owner);
-	dev_put(qdisc_dev(qdisc));
+	netdev_put(qdisc_dev(qdisc), &qdisc->dev_tracker);
 
 	trace_qdisc_destroy(qdisc);
 
@@ -1078,6 +1121,21 @@ struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue,
 }
 EXPORT_SYMBOL(dev_graft_qdisc);
 
+static void shutdown_scheduler_queue(struct net_device *dev,
+				     struct netdev_queue *dev_queue,
+				     void *_qdisc_default)
+{
+	struct Qdisc *qdisc = dev_queue->qdisc_sleeping;
+	struct Qdisc *qdisc_default = _qdisc_default;
+
+	if (qdisc) {
+		rcu_assign_pointer(dev_queue->qdisc, qdisc_default);
+		dev_queue->qdisc_sleeping = qdisc_default;
+
+		qdisc_put(qdisc);
+	}
+}
+
 static void attach_one_default_qdisc(struct net_device *dev,
 				     struct netdev_queue *dev_queue,
 				     void *_unused)
@@ -1109,30 +1167,34 @@ static void attach_default_qdiscs(struct net_device *dev)
 	if (!netif_is_multiqueue(dev) ||
 	    dev->priv_flags & IFF_NO_QUEUE) {
 		netdev_for_each_tx_queue(dev, attach_one_default_qdisc, NULL);
-		dev->qdisc = txq->qdisc_sleeping;
-		qdisc_refcount_inc(dev->qdisc);
+		qdisc = txq->qdisc_sleeping;
+		rcu_assign_pointer(dev->qdisc, qdisc);
+		qdisc_refcount_inc(qdisc);
 	} else {
 		qdisc = qdisc_create_dflt(txq, &mq_qdisc_ops, TC_H_ROOT, NULL);
 		if (qdisc) {
-			dev->qdisc = qdisc;
+			rcu_assign_pointer(dev->qdisc, qdisc);
 			qdisc->ops->attach(qdisc);
 		}
 	}
+	qdisc = rtnl_dereference(dev->qdisc);
 
 	/* Detect default qdisc setup/init failed and fallback to "noqueue" */
-	if (dev->qdisc == &noop_qdisc) {
+	if (qdisc == &noop_qdisc) {
 		netdev_warn(dev, "default qdisc (%s) fail, fallback to %s\n",
 			    default_qdisc_ops->id, noqueue_qdisc_ops.id);
+		netdev_for_each_tx_queue(dev, shutdown_scheduler_queue, &noop_qdisc);
 		dev->priv_flags |= IFF_NO_QUEUE;
 		netdev_for_each_tx_queue(dev, attach_one_default_qdisc, NULL);
-		dev->qdisc = txq->qdisc_sleeping;
-		qdisc_refcount_inc(dev->qdisc);
+		qdisc = txq->qdisc_sleeping;
+		rcu_assign_pointer(dev->qdisc, qdisc);
+		qdisc_refcount_inc(qdisc);
 		dev->priv_flags ^= IFF_NO_QUEUE;
 	}
 
 #ifdef CONFIG_NET_SCHED
-	if (dev->qdisc != &noop_qdisc)
-		qdisc_hash_add(dev->qdisc, false);
+	if (qdisc != &noop_qdisc)
+		qdisc_hash_add(qdisc, false);
 #endif
 }
 
@@ -1148,7 +1210,7 @@ static void transition_one_qdisc(struct net_device *dev,
 
 	rcu_assign_pointer(dev_queue->qdisc, new_qdisc);
 	if (need_watchdog_p) {
-		dev_queue->trans_start = 0;
+		WRITE_ONCE(dev_queue->trans_start, 0);
 		*need_watchdog_p = 1;
 	}
 }
@@ -1162,7 +1224,7 @@ void dev_activate(struct net_device *dev)
 	 * and noqueue_qdisc for virtual interfaces
 	 */
 
-	if (dev->qdisc == &noop_qdisc)
+	if (rtnl_dereference(dev->qdisc) == &noop_qdisc)
 		attach_default_qdiscs(dev);
 
 	if (!netif_carrier_ok(dev))
@@ -1328,7 +1390,7 @@ static int qdisc_change_tx_queue_len(struct net_device *dev,
 void dev_qdisc_change_real_num_tx(struct net_device *dev,
 				  unsigned int new_real_tx)
 {
-	struct Qdisc *qdisc = dev->qdisc;
+	struct Qdisc *qdisc = rtnl_dereference(dev->qdisc);
 
 	if (qdisc->ops->change_real_num_tx)
 		qdisc->ops->change_real_num_tx(qdisc, new_real_tx);
@@ -1392,7 +1454,7 @@ static void dev_init_scheduler_queue(struct net_device *dev,
 
 void dev_init_scheduler(struct net_device *dev)
 {
-	dev->qdisc = &noop_qdisc;
+	rcu_assign_pointer(dev->qdisc, &noop_qdisc);
 	netdev_for_each_tx_queue(dev, dev_init_scheduler_queue, &noop_qdisc);
 	if (dev_ingress_queue(dev))
 		dev_init_scheduler_queue(dev, dev_ingress_queue(dev), &noop_qdisc);
@@ -1400,28 +1462,13 @@ void dev_init_scheduler(struct net_device *dev)
 	timer_setup(&dev->watchdog_timer, dev_watchdog, 0);
 }
 
-static void shutdown_scheduler_queue(struct net_device *dev,
-				     struct netdev_queue *dev_queue,
-				     void *_qdisc_default)
-{
-	struct Qdisc *qdisc = dev_queue->qdisc_sleeping;
-	struct Qdisc *qdisc_default = _qdisc_default;
-
-	if (qdisc) {
-		rcu_assign_pointer(dev_queue->qdisc, qdisc_default);
-		dev_queue->qdisc_sleeping = qdisc_default;
-
-		qdisc_put(qdisc);
-	}
-}
-
 void dev_shutdown(struct net_device *dev)
 {
 	netdev_for_each_tx_queue(dev, shutdown_scheduler_queue, &noop_qdisc);
 	if (dev_ingress_queue(dev))
 		shutdown_scheduler_queue(dev, dev_ingress_queue(dev), &noop_qdisc);
-	qdisc_put(dev->qdisc);
-	dev->qdisc = &noop_qdisc;
+	qdisc_put(rtnl_dereference(dev->qdisc));
+	rcu_assign_pointer(dev->qdisc, &noop_qdisc);
 
 	WARN_ON(timer_pending(&dev->watchdog_timer));
 }
@@ -1474,6 +1521,7 @@ void psched_ratecfg_precompute(struct psched_ratecfg *r,
 {
 	memset(r, 0, sizeof(*r));
 	r->overhead = conf->overhead;
+	r->mpu = conf->mpu;
 	r->rate_bytes_ps = max_t(u64, conf->rate, rate64);
 	r->linklayer = (conf->linklayer & TC_LINKLAYER_MASK);
 	psched_ratecfg_precompute__(r->rate_bytes_ps, &r->mult, &r->shift);