diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 815191dd03c3..30b9ea6d62b0 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -2795,7 +2795,7 @@ void bond_loadbalance_arp_mon(struct work_struct *work)
 	 */
 	bond_for_each_slave(bond, slave, i) {
 		if (slave->link != BOND_LINK_UP) {
-			if (time_before_eq(jiffies, slave->dev->trans_start + delta_in_ticks) &&
+			if (time_before_eq(jiffies, dev_trans_start(slave->dev) + delta_in_ticks) &&
 			    time_before_eq(jiffies, slave->dev->last_rx + delta_in_ticks)) {
 
 				slave->link  = BOND_LINK_UP;
@@ -2827,7 +2827,7 @@ void bond_loadbalance_arp_mon(struct work_struct *work)
 			 * when the source ip is 0, so don't take the link down
 			 * if we don't know our ip yet
 			 */
-			if (time_after_eq(jiffies, slave->dev->trans_start + 2*delta_in_ticks) ||
+			if (time_after_eq(jiffies, dev_trans_start(slave->dev) + 2*delta_in_ticks) ||
 			    (time_after_eq(jiffies, slave->dev->last_rx + 2*delta_in_ticks))) {
 
 				slave->link  = BOND_LINK_DOWN;
@@ -2938,7 +2938,7 @@ static int bond_ab_arp_inspect(struct bonding *bond, int delta_in_ticks)
 		 *    the bond has an IP address)
 		 */
 		if ((slave->state == BOND_STATE_ACTIVE) &&
-		    (time_after_eq(jiffies, slave->dev->trans_start +
+		    (time_after_eq(jiffies, dev_trans_start(slave->dev) +
 				    2 * delta_in_ticks) ||
 		      (time_after_eq(jiffies, slave_last_rx(bond, slave)
 				     + 2 * delta_in_ticks)))) {
@@ -2982,7 +2982,7 @@ static void bond_ab_arp_commit(struct bonding *bond, int delta_in_ticks)
 			write_lock_bh(&bond->curr_slave_lock);
 
 			if (!bond->curr_active_slave &&
-			    time_before_eq(jiffies, slave->dev->trans_start +
+			    time_before_eq(jiffies, dev_trans_start(slave->dev) +
 					   delta_in_ticks)) {
 				slave->link = BOND_LINK_UP;
 				bond_change_active_slave(bond, slave);
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 2af89b662cad..cd547d04a8ce 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -470,6 +470,10 @@ struct netdev_queue {
  */
 	spinlock_t		_xmit_lock ____cacheline_aligned_in_smp;
 	int			xmit_lock_owner;
+	/*
+	 * please use this field instead of dev->trans_start
+	 */
+	unsigned long		trans_start;
 } ____cacheline_aligned_in_smp;
 
 
@@ -819,6 +823,11 @@ struct net_device
  * One part is mostly used on xmit path (device)
  */
 	/* These may be needed for future network-power-down code. */
+
+	/*
+	 * trans_start here is expensive for high speed devices on SMP,
+	 * please use netdev_queue->trans_start instead.
+	 */
 	unsigned long		trans_start;	/* Time (in jiffies) of last Tx	*/
 
 	int			watchdog_timeo; /* used by dev_watchdog() */
@@ -1541,6 +1550,8 @@ static inline int netif_carrier_ok(const struct net_device *dev)
 	return !test_bit(__LINK_STATE_NOCARRIER, &dev->state);
 }
 
+extern unsigned long dev_trans_start(struct net_device *dev);
+
 extern void __netdev_watchdog_up(struct net_device *dev);
 
 extern void netif_carrier_on(struct net_device *dev);
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 5f5efe4e6072..27d03816ec3e 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -196,6 +196,21 @@ void __qdisc_run(struct Qdisc *q)
 	clear_bit(__QDISC_STATE_RUNNING, &q->state);
 }
 
+unsigned long dev_trans_start(struct net_device *dev)
+{
+	unsigned long val, res = dev->trans_start;
+	unsigned int i;
+
+	for (i = 0; i < dev->num_tx_queues; i++) {
+		val = netdev_get_tx_queue(dev, i)->trans_start;
+		if (val && time_after(val, res))
+			res = val;
+	}
+	dev->trans_start = res;
+	return res;
+}
+EXPORT_SYMBOL(dev_trans_start);
+
 static void dev_watchdog(unsigned long arg)
 {
 	struct net_device *dev = (struct net_device *)arg;
@@ -205,25 +220,30 @@ static void dev_watchdog(unsigned long arg)
 		if (netif_device_present(dev) &&
 		    netif_running(dev) &&
 		    netif_carrier_ok(dev)) {
-			int some_queue_stopped = 0;
+			int some_queue_timedout = 0;
 			unsigned int i;
+			unsigned long trans_start;
 
 			for (i = 0; i < dev->num_tx_queues; i++) {
 				struct netdev_queue *txq;
 
 				txq = netdev_get_tx_queue(dev, i);
-				if (netif_tx_queue_stopped(txq)) {
-					some_queue_stopped = 1;
+				/*
+				 * old device drivers set dev->trans_start
+				 */
+				trans_start = txq->trans_start ? : dev->trans_start;
+				if (netif_tx_queue_stopped(txq) &&
+				    time_after(jiffies, (trans_start +
+							 dev->watchdog_timeo))) {
+					some_queue_timedout = 1;
 					break;
 				}
 			}
 
-			if (some_queue_stopped &&
-			    time_after(jiffies, (dev->trans_start +
-						 dev->watchdog_timeo))) {
+			if (some_queue_timedout) {
 				char drivername[64];
-				WARN_ONCE(1, KERN_INFO "NETDEV WATCHDOG: %s (%s): transmit timed out\n",
-				       dev->name, netdev_drivername(dev, drivername, 64));
+				WARN_ONCE(1, KERN_INFO "NETDEV WATCHDOG: %s (%s): transmit queue %u timed out\n",
+				       dev->name, netdev_drivername(dev, drivername, 64), i);
 				dev->netdev_ops->ndo_tx_timeout(dev);
 			}
 			if (!mod_timer(&dev->watchdog_timer,
@@ -602,8 +622,10 @@ static void transition_one_qdisc(struct net_device *dev,
 		clear_bit(__QDISC_STATE_DEACTIVATED, &new_qdisc->state);
 
 	rcu_assign_pointer(dev_queue->qdisc, new_qdisc);
-	if (need_watchdog_p && new_qdisc != &noqueue_qdisc)
+	if (need_watchdog_p && new_qdisc != &noqueue_qdisc) {
+		dev_queue->trans_start = 0;
 		*need_watchdog_p = 1;
+	}
 }
 
 void dev_activate(struct net_device *dev)