1 files changed, 551 insertions, 251 deletions

diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index b741618e4d5..e1543b03e39 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -24,76 +24,66 @@
 #include <linux/init.h>
 #include <linux/rcupdate.h>
 #include <linux/list.h>
+#include <linux/slab.h>
+#include <linux/if_vlan.h>
+#include <net/sch_generic.h>
 #include <net/pkt_sched.h>
+#include <net/dst.h>
+
+/* Qdisc to use by default */
+const struct Qdisc_ops *default_qdisc_ops = &pfifo_fast_ops;
+EXPORT_SYMBOL(default_qdisc_ops);
 
 /* Main transmission queue. */
 
 /* Modifications to data participating in scheduling must be protected with
- * dev->queue_lock spinlock.
+ * qdisc_lock(qdisc) spinlock.
  *
  * The idea is the following:
- * - enqueue, dequeue are serialized via top level device
- *   spinlock dev->queue_lock.
- * - ingress filtering is serialized via top level device
- *   spinlock dev->ingress_lock.
+ * - enqueue, dequeue are serialized via qdisc root lock
+ * - ingress filtering is also serialized via qdisc root lock
  * - updates to tree and tree walking are only done under the rtnl mutex.
  */
 
-void qdisc_lock_tree(struct net_device *dev)
-	__acquires(dev->queue_lock)
-	__acquires(dev->ingress_lock)
-{
-	spin_lock_bh(&dev->queue_lock);
-	spin_lock(&dev->ingress_lock);
-}
-EXPORT_SYMBOL(qdisc_lock_tree);
-
-void qdisc_unlock_tree(struct net_device *dev)
-	__releases(dev->ingress_lock)
-	__releases(dev->queue_lock)
-{
-	spin_unlock(&dev->ingress_lock);
-	spin_unlock_bh(&dev->queue_lock);
-}
-EXPORT_SYMBOL(qdisc_unlock_tree);
-
-static inline int qdisc_qlen(struct Qdisc *q)
-{
-	return q->q.qlen;
-}
-
-static inline int dev_requeue_skb(struct sk_buff *skb, struct net_device *dev,
-				  struct Qdisc *q)
+static inline int dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q)
 {
-	if (unlikely(skb->next))
-		dev->gso_skb = skb;
-	else
-		q->ops->requeue(skb, q);
+	skb_dst_force(skb);
+	q->gso_skb = skb;
+	q->qstats.requeues++;
+	q->q.qlen++;	/* it's still part of the queue */
+	__netif_schedule(q);
 
-	netif_schedule(dev);
 	return 0;
 }
 
-static inline struct sk_buff *dev_dequeue_skb(struct net_device *dev,
-					      struct Qdisc *q)
+static inline struct sk_buff *dequeue_skb(struct Qdisc *q)
 {
-	struct sk_buff *skb;
+	struct sk_buff *skb = q->gso_skb;
+	const struct netdev_queue *txq = q->dev_queue;
 
-	if ((skb = dev->gso_skb))
-		dev->gso_skb = NULL;
-	else
-		skb = q->dequeue(q);
+	if (unlikely(skb)) {
+		/* check the reason of requeuing without tx lock first */
+		txq = netdev_get_tx_queue(txq->dev, skb_get_queue_mapping(skb));
+		if (!netif_xmit_frozen_or_stopped(txq)) {
+			q->gso_skb = NULL;
+			q->q.qlen--;
+		} else
+			skb = NULL;
+	} else {
+		if (!(q->flags & TCQ_F_ONETXQUEUE) || !netif_xmit_frozen_or_stopped(txq))
+			skb = q->dequeue(q);
+	}
 
 	return skb;
 }
 
 static inline int handle_dev_cpu_collision(struct sk_buff *skb,
-					   struct net_device *dev,
+					   struct netdev_queue *dev_queue,
 					   struct Qdisc *q)
 {
 	int ret;
 
-	if (unlikely(dev->xmit_lock_owner == smp_processor_id())) {
+	if (unlikely(dev_queue->xmit_lock_owner == smp_processor_id())) {
 		/*
 		 * Same CPU holding the lock. It may be a transient
 		 * configuration error, when hard_start_xmit() recurses. We
@@ -101,126 +91,182 @@ static inline int handle_dev_cpu_collision(struct sk_buff *skb,
 		 * deadloop is detected. Return OK to try the next skb.
 		 */
 		kfree_skb(skb);
-		if (net_ratelimit())
-			printk(KERN_WARNING "Dead loop on netdevice %s, "
-			       "fix it urgently!\n", dev->name);
+		net_warn_ratelimited("Dead loop on netdevice %s, fix it urgently!\n",
+				     dev_queue->dev->name);
 		ret = qdisc_qlen(q);
 	} else {
 		/*
 		 * Another cpu is holding lock, requeue & delay xmits for
 		 * some time.
 		 */
-		__get_cpu_var(netdev_rx_stat).cpu_collision++;
-		ret = dev_requeue_skb(skb, dev, q);
+		__this_cpu_inc(softnet_data.cpu_collision);
+		ret = dev_requeue_skb(skb, q);
 	}
 
 	return ret;
 }
 
 /*
- * NOTE: Called under dev->queue_lock with locally disabled BH.
- *
- * __LINK_STATE_QDISC_RUNNING guarantees only one CPU can process this
- * device at a time. dev->queue_lock serializes queue accesses for
- * this device AND dev->qdisc pointer itself.
- *
- *  netif_tx_lock serializes accesses to device driver.
- *
- *  dev->queue_lock and netif_tx_lock are mutually exclusive,
- *  if one is grabbed, another must be free.
- *
- * Note, that this procedure can be called by a watchdog timer
+ * Transmit one skb, and handle the return status as required. Holding the
+ * __QDISC_STATE_RUNNING bit guarantees that only one CPU can execute this
+ * function.
  *
  * Returns to the caller:
  *				0  - queue is empty or throttled.
  *				>0 - queue is not empty.
- *
  */
-static inline int qdisc_restart(struct net_device *dev)
+int sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q,
+		    struct net_device *dev, struct netdev_queue *txq,
+		    spinlock_t *root_lock)
 {
-	struct Qdisc *q = dev->qdisc;
-	struct sk_buff *skb;
 	int ret = NETDEV_TX_BUSY;
 
-	/* Dequeue packet */
-	if (unlikely((skb = dev_dequeue_skb(dev, q)) == NULL))
-		return 0;
-
+	/* And release qdisc */
+	spin_unlock(root_lock);
 
-	/* And release queue */
-	spin_unlock(&dev->queue_lock);
+	HARD_TX_LOCK(dev, txq, smp_processor_id());
+	if (!netif_xmit_frozen_or_stopped(txq))
+		ret = dev_hard_start_xmit(skb, dev, txq);
 
-	HARD_TX_LOCK(dev, smp_processor_id());
-	if (!netif_subqueue_stopped(dev, skb))
-		ret = dev_hard_start_xmit(skb, dev);
-	HARD_TX_UNLOCK(dev);
+	HARD_TX_UNLOCK(dev, txq);
 
-	spin_lock(&dev->queue_lock);
-	q = dev->qdisc;
+	spin_lock(root_lock);
 
-	switch (ret) {
-	case NETDEV_TX_OK:
-		/* Driver sent out skb successfully */
+	if (dev_xmit_complete(ret)) {
+		/* Driver sent out skb successfully or skb was consumed */
 		ret = qdisc_qlen(q);
-		break;
-
-	case NETDEV_TX_LOCKED:
+	} else if (ret == NETDEV_TX_LOCKED) {
 		/* Driver try lock failed */
-		ret = handle_dev_cpu_collision(skb, dev, q);
-		break;
-
-	default:
+		ret = handle_dev_cpu_collision(skb, txq, q);
+	} else {
 		/* Driver returned NETDEV_TX_BUSY - requeue skb */
-		if (unlikely (ret != NETDEV_TX_BUSY && net_ratelimit()))
-			printk(KERN_WARNING "BUG %s code %d qlen %d\n",
-			       dev->name, ret, q->q.qlen);
+		if (unlikely(ret != NETDEV_TX_BUSY))
+			net_warn_ratelimited("BUG %s code %d qlen %d\n",
+					     dev->name, ret, q->q.qlen);
 
-		ret = dev_requeue_skb(skb, dev, q);
-		break;
+		ret = dev_requeue_skb(skb, q);
 	}
 
+	if (ret && netif_xmit_frozen_or_stopped(txq))
+		ret = 0;
+
 	return ret;
 }
 
-void __qdisc_run(struct net_device *dev)
+/*
+ * NOTE: Called under qdisc_lock(q) with locally disabled BH.
+ *
+ * __QDISC_STATE_RUNNING guarantees only one CPU can process
+ * this qdisc at a time. qdisc_lock(q) serializes queue accesses for
+ * this queue.
+ *
+ *  netif_tx_lock serializes accesses to device driver.
+ *
+ *  qdisc_lock(q) and netif_tx_lock are mutually exclusive,
+ *  if one is grabbed, another must be free.
+ *
+ * Note, that this procedure can be called by a watchdog timer
+ *
+ * Returns to the caller:
+ *				0  - queue is empty or throttled.
+ *				>0 - queue is not empty.
+ *
+ */
+static inline int qdisc_restart(struct Qdisc *q)
 {
-	unsigned long start_time = jiffies;
+	struct netdev_queue *txq;
+	struct net_device *dev;
+	spinlock_t *root_lock;
+	struct sk_buff *skb;
 
-	while (qdisc_restart(dev)) {
-		if (netif_queue_stopped(dev))
-			break;
+	/* Dequeue packet */
+	skb = dequeue_skb(q);
+	if (unlikely(!skb))
+		return 0;
+	WARN_ON_ONCE(skb_dst_is_noref(skb));
+	root_lock = qdisc_lock(q);
+	dev = qdisc_dev(q);
+	txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb));
+
+	return sch_direct_xmit(skb, q, dev, txq, root_lock);
+}
 
+void __qdisc_run(struct Qdisc *q)
+{
+	int quota = weight_p;
+
+	while (qdisc_restart(q)) {
 		/*
-		 * Postpone processing if
-		 * 1. another process needs the CPU;
-		 * 2. we've been doing it for too long.
+		 * Ordered by possible occurrence: Postpone processing if
+		 * 1. we've exceeded packet quota
+		 * 2. another process needs the CPU;
 		 */
-		if (need_resched() || jiffies != start_time) {
-			netif_schedule(dev);
+		if (--quota <= 0 || need_resched()) {
+			__netif_schedule(q);
 			break;
 		}
 	}
 
-	clear_bit(__LINK_STATE_QDISC_RUNNING, &dev->state);
+	qdisc_run_end(q);
+}
+
+unsigned long dev_trans_start(struct net_device *dev)
+{
+	unsigned long val, res;
+	unsigned int i;
+
+	if (is_vlan_dev(dev))
+		dev = vlan_dev_real_dev(dev);
+	res = dev->trans_start;
+	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;
 
 	netif_tx_lock(dev);
-	if (dev->qdisc != &noop_qdisc) {
+	if (!qdisc_tx_is_noop(dev)) {
 		if (netif_device_present(dev) &&
 		    netif_running(dev) &&
 		    netif_carrier_ok(dev)) {
-			if (netif_queue_stopped(dev) &&
-			    time_after(jiffies, dev->trans_start + dev->watchdog_timeo)) {
+			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);
+				/*
+				 * old device drivers set dev->trans_start
+				 */
+				trans_start = txq->trans_start ? : dev->trans_start;
+				if (netif_xmit_stopped(txq) &&
+				    time_after(jiffies, (trans_start +
+							 dev->watchdog_timeo))) {
+					some_queue_timedout = 1;
+					txq->trans_timeout++;
+					break;
+				}
+			}
 
-				printk(KERN_INFO "NETDEV WATCHDOG: %s: transmit timed out\n",
-				       dev->name);
-				dev->tx_timeout(dev);
+			if (some_queue_timedout) {
+				WARN_ONCE(1, KERN_INFO "NETDEV WATCHDOG: %s (%s): transmit queue %u timed out\n",
+				       dev->name, netdev_drivername(dev), i);
+				dev->netdev_ops->ndo_tx_timeout(dev);
 			}
-			if (!mod_timer(&dev->watchdog_timer, round_jiffies(jiffies + dev->watchdog_timeo)))
+			if (!mod_timer(&dev->watchdog_timer,
+				       round_jiffies(jiffies +
+						     dev->watchdog_timeo)))
 				dev_hold(dev);
 		}
 	}
@@ -231,7 +277,7 @@ static void dev_watchdog(unsigned long arg)
 
 void __netdev_watchdog_up(struct net_device *dev)
 {
-	if (dev->tx_timeout) {
+	if (dev->netdev_ops->ndo_tx_timeout) {
 		if (dev->watchdog_timeo <= 0)
 			dev->watchdog_timeo = 5*HZ;
 		if (!mod_timer(&dev->watchdog_timer,
@@ -262,6 +308,9 @@ static void dev_watchdog_down(struct net_device *dev)
 void netif_carrier_on(struct net_device *dev)
 {
 	if (test_and_clear_bit(__LINK_STATE_NOCARRIER, &dev->state)) {
+		if (dev->reg_state == NETREG_UNINITIALIZED)
+			return;
+		atomic_inc(&dev->carrier_changes);
 		linkwatch_fire_event(dev);
 		if (netif_running(dev))
 			__netdev_watchdog_up(dev);
@@ -277,8 +326,12 @@ EXPORT_SYMBOL(netif_carrier_on);
  */
 void netif_carrier_off(struct net_device *dev)
 {
-	if (!test_and_set_bit(__LINK_STATE_NOCARRIER, &dev->state))
+	if (!test_and_set_bit(__LINK_STATE_NOCARRIER, &dev->state)) {
+		if (dev->reg_state == NETREG_UNINITIALIZED)
+			return;
+		atomic_inc(&dev->carrier_changes);
 		linkwatch_fire_event(dev);
+	}
 }
 EXPORT_SYMBOL(netif_carrier_off);
 
@@ -287,41 +340,40 @@ EXPORT_SYMBOL(netif_carrier_off);
    cheaper.
  */
 
-static int noop_enqueue(struct sk_buff *skb, struct Qdisc * qdisc)
+static int noop_enqueue(struct sk_buff *skb, struct Qdisc *qdisc)
 {
 	kfree_skb(skb);
 	return NET_XMIT_CN;
 }
 
-static struct sk_buff *noop_dequeue(struct Qdisc * qdisc)
+static struct sk_buff *noop_dequeue(struct Qdisc *qdisc)
 {
 	return NULL;
 }
 
-static int noop_requeue(struct sk_buff *skb, struct Qdisc* qdisc)
-{
-	if (net_ratelimit())
-		printk(KERN_DEBUG "%s deferred output. It is buggy.\n",
-		       skb->dev->name);
-	kfree_skb(skb);
-	return NET_XMIT_CN;
-}
-
 struct Qdisc_ops noop_qdisc_ops __read_mostly = {
 	.id		=	"noop",
 	.priv_size	=	0,
 	.enqueue	=	noop_enqueue,
 	.dequeue	=	noop_dequeue,
-	.requeue	=	noop_requeue,
+	.peek		=	noop_dequeue,
 	.owner		=	THIS_MODULE,
 };
 
+static struct netdev_queue noop_netdev_queue = {
+	.qdisc		=	&noop_qdisc,
+	.qdisc_sleeping	=	&noop_qdisc,
+};
+
 struct Qdisc noop_qdisc = {
 	.enqueue	=	noop_enqueue,
 	.dequeue	=	noop_dequeue,
 	.flags		=	TCQ_F_BUILTIN,
 	.ops		=	&noop_qdisc_ops,
 	.list		=	LIST_HEAD_INIT(noop_qdisc.list),
+	.q.lock		=	__SPIN_LOCK_UNLOCKED(noop_qdisc.q.lock),
+	.dev_queue	=	&noop_netdev_queue,
+	.busylock	=	__SPIN_LOCK_UNLOCKED(noop_qdisc.busylock),
 };
 EXPORT_SYMBOL(noop_qdisc);
 
@@ -330,21 +382,31 @@ static struct Qdisc_ops noqueue_qdisc_ops __read_mostly = {
 	.priv_size	=	0,
 	.enqueue	=	noop_enqueue,
 	.dequeue	=	noop_dequeue,
-	.requeue	=	noop_requeue,
+	.peek		=	noop_dequeue,
 	.owner		=	THIS_MODULE,
 };
 
+static struct Qdisc noqueue_qdisc;
+static struct netdev_queue noqueue_netdev_queue = {
+	.qdisc		=	&noqueue_qdisc,
+	.qdisc_sleeping	=	&noqueue_qdisc,
+};
+
 static struct Qdisc noqueue_qdisc = {
 	.enqueue	=	NULL,
 	.dequeue	=	noop_dequeue,
 	.flags		=	TCQ_F_BUILTIN,
 	.ops		=	&noqueue_qdisc_ops,
 	.list		=	LIST_HEAD_INIT(noqueue_qdisc.list),
+	.q.lock		=	__SPIN_LOCK_UNLOCKED(noqueue_qdisc.q.lock),
+	.dev_queue	=	&noqueue_netdev_queue,
+	.busylock	=	__SPIN_LOCK_UNLOCKED(noqueue_qdisc.busylock),
 };
 
 
-static const u8 prio2band[TC_PRIO_MAX+1] =
-	{ 1, 2, 2, 2, 1, 2, 0, 0 , 1, 1, 1, 1, 1, 1, 1, 1 };
+static const u8 prio2band[TC_PRIO_MAX + 1] = {
+	1, 2, 2, 2, 1, 2, 0, 0 , 1, 1, 1, 1, 1, 1, 1, 1
+};
 
 /* 3-band FIFO queue: old style, but should be a bit faster than
    generic prio+fifo combination.
@@ -352,18 +414,38 @@ static const u8 prio2band[TC_PRIO_MAX+1] =
 
 #define PFIFO_FAST_BANDS 3
 
-static inline struct sk_buff_head *prio2list(struct sk_buff *skb,
-					     struct Qdisc *qdisc)
+/*
+ * Private data for a pfifo_fast scheduler containing:
+ * 	- queues for the three band
+ * 	- bitmap indicating which of the bands contain skbs
+ */
+struct pfifo_fast_priv {
+	u32 bitmap;
+	struct sk_buff_head q[PFIFO_FAST_BANDS];
+};
+
+/*
+ * Convert a bitmap to the first band number where an skb is queued, where:
+ * 	bitmap=0 means there are no skbs on any band.
+ * 	bitmap=1 means there is an skb on band 0.
+ *	bitmap=7 means there are skbs on all 3 bands, etc.
+ */
+static const int bitmap2band[] = {-1, 0, 1, 0, 2, 0, 1, 0};
+
+static inline struct sk_buff_head *band2list(struct pfifo_fast_priv *priv,
+					     int band)
 {
-	struct sk_buff_head *list = qdisc_priv(qdisc);
-	return list + prio2band[skb->priority & TC_PRIO_MAX];
+	return priv->q + band;
 }
 
-static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc* qdisc)
+static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc *qdisc)
 {
-	struct sk_buff_head *list = prio2list(skb, qdisc);
+	if (skb_queue_len(&qdisc->q) < qdisc_dev(qdisc)->tx_queue_len) {
+		int band = prio2band[skb->priority & TC_PRIO_MAX];
+		struct pfifo_fast_priv *priv = qdisc_priv(qdisc);
+		struct sk_buff_head *list = band2list(priv, band);
 
-	if (skb_queue_len(list) < qdisc->dev->tx_queue_len) {
+		priv->bitmap |= (1 << band);
 		qdisc->q.qlen++;
 		return __qdisc_enqueue_tail(skb, qdisc, list);
 	}
@@ -371,35 +453,48 @@ static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc* qdisc)
 	return qdisc_drop(skb, qdisc);
 }
 
-static struct sk_buff *pfifo_fast_dequeue(struct Qdisc* qdisc)
+static struct sk_buff *pfifo_fast_dequeue(struct Qdisc *qdisc)
 {
-	int prio;
-	struct sk_buff_head *list = qdisc_priv(qdisc);
+	struct pfifo_fast_priv *priv = qdisc_priv(qdisc);
+	int band = bitmap2band[priv->bitmap];
 
-	for (prio = 0; prio < PFIFO_FAST_BANDS; prio++) {
-		if (!skb_queue_empty(list + prio)) {
-			qdisc->q.qlen--;
-			return __qdisc_dequeue_head(qdisc, list + prio);
-		}
+	if (likely(band >= 0)) {
+		struct sk_buff_head *list = band2list(priv, band);
+		struct sk_buff *skb = __qdisc_dequeue_head(qdisc, list);
+
+		qdisc->q.qlen--;
+		if (skb_queue_empty(list))
+			priv->bitmap &= ~(1 << band);
+
+		return skb;
 	}
 
 	return NULL;
 }
 
-static int pfifo_fast_requeue(struct sk_buff *skb, struct Qdisc* qdisc)
+static struct sk_buff *pfifo_fast_peek(struct Qdisc *qdisc)
 {
-	qdisc->q.qlen++;
-	return __qdisc_requeue(skb, qdisc, prio2list(skb, qdisc));
+	struct pfifo_fast_priv *priv = qdisc_priv(qdisc);
+	int band = bitmap2band[priv->bitmap];
+
+	if (band >= 0) {
+		struct sk_buff_head *list = band2list(priv, band);
+
+		return skb_peek(list);
+	}
+
+	return NULL;
 }
 
-static void pfifo_fast_reset(struct Qdisc* qdisc)
+static void pfifo_fast_reset(struct Qdisc *qdisc)
 {
 	int prio;
-	struct sk_buff_head *list = qdisc_priv(qdisc);
+	struct pfifo_fast_priv *priv = qdisc_priv(qdisc);
 
 	for (prio = 0; prio < PFIFO_FAST_BANDS; prio++)
-		__qdisc_reset_queue(qdisc, list + prio);
+		__qdisc_reset_queue(qdisc, band2list(priv, prio));
 
+	priv->bitmap = 0;
 	qdisc->qstats.backlog = 0;
 	qdisc->q.qlen = 0;
 }
@@ -408,8 +503,9 @@ static int pfifo_fast_dump(struct Qdisc *qdisc, struct sk_buff *skb)
 {
 	struct tc_prio_qopt opt = { .bands = PFIFO_FAST_BANDS };
 
-	memcpy(&opt.priomap, prio2band, TC_PRIO_MAX+1);
-	NLA_PUT(skb, TCA_OPTIONS, sizeof(opt), &opt);
+	memcpy(&opt.priomap, prio2band, TC_PRIO_MAX + 1);
+	if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt))
+		goto nla_put_failure;
 	return skb->len;
 
 nla_put_failure:
@@ -419,66 +515,86 @@ nla_put_failure:
 static int pfifo_fast_init(struct Qdisc *qdisc, struct nlattr *opt)
 {
 	int prio;
-	struct sk_buff_head *list = qdisc_priv(qdisc);
+	struct pfifo_fast_priv *priv = qdisc_priv(qdisc);
 
 	for (prio = 0; prio < PFIFO_FAST_BANDS; prio++)
-		skb_queue_head_init(list + prio);
+		skb_queue_head_init(band2list(priv, prio));
 
+	/* Can by-pass the queue discipline */
+	qdisc->flags |= TCQ_F_CAN_BYPASS;
 	return 0;
 }
 
-static struct Qdisc_ops pfifo_fast_ops __read_mostly = {
+struct Qdisc_ops pfifo_fast_ops __read_mostly = {
 	.id		=	"pfifo_fast",
-	.priv_size	=	PFIFO_FAST_BANDS * sizeof(struct sk_buff_head),
+	.priv_size	=	sizeof(struct pfifo_fast_priv),
 	.enqueue	=	pfifo_fast_enqueue,
 	.dequeue	=	pfifo_fast_dequeue,
-	.requeue	=	pfifo_fast_requeue,
+	.peek		=	pfifo_fast_peek,
 	.init		=	pfifo_fast_init,
 	.reset		=	pfifo_fast_reset,
 	.dump		=	pfifo_fast_dump,
 	.owner		=	THIS_MODULE,
 };
 
-struct Qdisc *qdisc_alloc(struct net_device *dev, struct Qdisc_ops *ops)
+static struct lock_class_key qdisc_tx_busylock;
+
+struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
+			  const struct Qdisc_ops *ops)
 {
 	void *p;
 	struct Qdisc *sch;
-	unsigned int size;
+	unsigned int size = QDISC_ALIGN(sizeof(*sch)) + ops->priv_size;
 	int err = -ENOBUFS;
+	struct net_device *dev = dev_queue->dev;
 
-	/* ensure that the Qdisc and the private data are 32-byte aligned */
-	size = QDISC_ALIGN(sizeof(*sch));
-	size += ops->priv_size + (QDISC_ALIGNTO - 1);
+	p = kzalloc_node(size, GFP_KERNEL,
+			 netdev_queue_numa_node_read(dev_queue));
 
-	p = kzalloc(size, GFP_KERNEL);
 	if (!p)
 		goto errout;
 	sch = (struct Qdisc *) QDISC_ALIGN((unsigned long) p);
-	sch->padded = (char *) sch - (char *) p;
-
+	/* if we got non aligned memory, ask more and do alignment ourself */
+	if (sch != p) {
+		kfree(p);
+		p = kzalloc_node(size + QDISC_ALIGNTO - 1, GFP_KERNEL,
+				 netdev_queue_numa_node_read(dev_queue));
+		if (!p)
+			goto errout;
+		sch = (struct Qdisc *) QDISC_ALIGN((unsigned long) p);
+		sch->padded = (char *) sch - (char *) p;
+	}
 	INIT_LIST_HEAD(&sch->list);
 	skb_queue_head_init(&sch->q);
+
+	spin_lock_init(&sch->busylock);
+	lockdep_set_class(&sch->busylock,
+			  dev->qdisc_tx_busylock ?: &qdisc_tx_busylock);
+
 	sch->ops = ops;
 	sch->enqueue = ops->enqueue;
 	sch->dequeue = ops->dequeue;
-	sch->dev = dev;
+	sch->dev_queue = dev_queue;
 	dev_hold(dev);
 	atomic_set(&sch->refcnt, 1);
 
 	return sch;
 errout:
-	return ERR_PTR(-err);
+	return ERR_PTR(err);
 }
 
-struct Qdisc * qdisc_create_dflt(struct net_device *dev, struct Qdisc_ops *ops,
-				 unsigned int parentid)
+struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue,
+				const struct Qdisc_ops *ops,
+				unsigned int parentid)
 {
 	struct Qdisc *sch;
 
-	sch = qdisc_alloc(dev, ops);
+	if (!try_module_get(ops->owner))
+		goto errout;
+
+	sch = qdisc_alloc(dev_queue, ops);
 	if (IS_ERR(sch))
 		goto errout;
-	sch->stats_lock = &dev->queue_lock;
 	sch->parent = parentid;
 
 	if (!ops->init || ops->init(sch, NULL) == 0)
@@ -490,7 +606,7 @@ errout:
 }
 EXPORT_SYMBOL(qdisc_create_dflt);
 
-/* Under dev->queue_lock and BH! */
+/* Under qdisc_lock(qdisc) and BH! */
 
 void qdisc_reset(struct Qdisc *qdisc)
 {
@@ -498,20 +614,22 @@ void qdisc_reset(struct Qdisc *qdisc)
 
 	if (ops->reset)
 		ops->reset(qdisc);
+
+	if (qdisc->gso_skb) {
+		kfree_skb(qdisc->gso_skb);
+		qdisc->gso_skb = NULL;
+		qdisc->q.qlen = 0;
+	}
 }
 EXPORT_SYMBOL(qdisc_reset);
 
-/* this is the rcu callback function to clean up a qdisc when there
- * are no further references to it */
-
-static void __qdisc_destroy(struct rcu_head *head)
+static void qdisc_rcu_free(struct rcu_head *head)
 {
-	struct Qdisc *qdisc = container_of(head, struct Qdisc, q_rcu);
+	struct Qdisc *qdisc = container_of(head, struct Qdisc, rcu_head);
+
 	kfree((char *) qdisc - qdisc->padded);
 }
 
-/* Under dev->queue_lock and BH! */
-
 void qdisc_destroy(struct Qdisc *qdisc)
 {
 	const struct Qdisc_ops  *ops = qdisc->ops;
@@ -520,7 +638,11 @@ void qdisc_destroy(struct Qdisc *qdisc)
 	    !atomic_dec_and_test(&qdisc->refcnt))
 		return;
 
-	list_del(&qdisc->list);
+#ifdef CONFIG_NET_SCHED
+	qdisc_list_del(qdisc);
+
+	qdisc_put_stab(rtnl_dereference(qdisc->stab));
+#endif
 	gen_kill_estimator(&qdisc->bstats, &qdisc->rate_est);
 	if (ops->reset)
 		ops->reset(qdisc);
@@ -528,121 +650,299 @@ void qdisc_destroy(struct Qdisc *qdisc)
 		ops->destroy(qdisc);
 
 	module_put(ops->owner);
-	dev_put(qdisc->dev);
-	call_rcu(&qdisc->q_rcu, __qdisc_destroy);
+	dev_put(qdisc_dev(qdisc));
+
+	kfree_skb(qdisc->gso_skb);
+	/*
+	 * gen_estimator est_timer() might access qdisc->q.lock,
+	 * wait a RCU grace period before freeing qdisc.
+	 */
+	call_rcu(&qdisc->rcu_head, qdisc_rcu_free);
 }
 EXPORT_SYMBOL(qdisc_destroy);
 
+/* Attach toplevel qdisc to device queue. */
+struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue,
+			      struct Qdisc *qdisc)
+{
+	struct Qdisc *oqdisc = dev_queue->qdisc_sleeping;
+	spinlock_t *root_lock;
+
+	root_lock = qdisc_lock(oqdisc);
+	spin_lock_bh(root_lock);
+
+	/* Prune old scheduler */
+	if (oqdisc && atomic_read(&oqdisc->refcnt) <= 1)
+		qdisc_reset(oqdisc);
+
+	/* ... and graft new one */
+	if (qdisc == NULL)
+		qdisc = &noop_qdisc;
+	dev_queue->qdisc_sleeping = qdisc;
+	rcu_assign_pointer(dev_queue->qdisc, &noop_qdisc);
+
+	spin_unlock_bh(root_lock);
+
+	return oqdisc;
+}
+EXPORT_SYMBOL(dev_graft_qdisc);
+
+static void attach_one_default_qdisc(struct net_device *dev,
+				     struct netdev_queue *dev_queue,
+				     void *_unused)
+{
+	struct Qdisc *qdisc = &noqueue_qdisc;
+
+	if (dev->tx_queue_len) {
+		qdisc = qdisc_create_dflt(dev_queue,
+					  default_qdisc_ops, TC_H_ROOT);
+		if (!qdisc) {
+			netdev_info(dev, "activation failed\n");
+			return;
+		}
+		if (!netif_is_multiqueue(dev))
+			qdisc->flags |= TCQ_F_ONETXQUEUE;
+	}
+	dev_queue->qdisc_sleeping = qdisc;
+}
+
+static void attach_default_qdiscs(struct net_device *dev)
+{
+	struct netdev_queue *txq;
+	struct Qdisc *qdisc;
+
+	txq = netdev_get_tx_queue(dev, 0);
+
+	if (!netif_is_multiqueue(dev) || dev->tx_queue_len == 0) {
+		netdev_for_each_tx_queue(dev, attach_one_default_qdisc, NULL);
+		dev->qdisc = txq->qdisc_sleeping;
+		atomic_inc(&dev->qdisc->refcnt);
+	} else {
+		qdisc = qdisc_create_dflt(txq, &mq_qdisc_ops, TC_H_ROOT);
+		if (qdisc) {
+			dev->qdisc = qdisc;
+			qdisc->ops->attach(qdisc);
+		}
+	}
+}
+
+static void transition_one_qdisc(struct net_device *dev,
+				 struct netdev_queue *dev_queue,
+				 void *_need_watchdog)
+{
+	struct Qdisc *new_qdisc = dev_queue->qdisc_sleeping;
+	int *need_watchdog_p = _need_watchdog;
+
+	if (!(new_qdisc->flags & TCQ_F_BUILTIN))
+		clear_bit(__QDISC_STATE_DEACTIVATED, &new_qdisc->state);
+
+	rcu_assign_pointer(dev_queue->qdisc, new_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)
 {
+	int need_watchdog;
+
 	/* No queueing discipline is attached to device;
-	   create default one i.e. pfifo_fast for devices,
-	   which need queueing and noqueue_qdisc for
-	   virtual interfaces
+	 * create default one for devices, which need queueing
+	 * and noqueue_qdisc for virtual interfaces
 	 */
 
-	if (dev->qdisc_sleeping == &noop_qdisc) {
-		struct Qdisc *qdisc;
-		if (dev->tx_queue_len) {
-			qdisc = qdisc_create_dflt(dev, &pfifo_fast_ops,
-						  TC_H_ROOT);
-			if (qdisc == NULL) {
-				printk(KERN_INFO "%s: activation failed\n", dev->name);
-				return;
-			}
-			list_add_tail(&qdisc->list, &dev->qdisc_list);
-		} else {
-			qdisc =  &noqueue_qdisc;
-		}
-		dev->qdisc_sleeping = qdisc;
-	}
+	if (dev->qdisc == &noop_qdisc)
+		attach_default_qdiscs(dev);
 
 	if (!netif_carrier_ok(dev))
 		/* Delay activation until next carrier-on event */
 		return;
 
-	spin_lock_bh(&dev->queue_lock);
-	rcu_assign_pointer(dev->qdisc, dev->qdisc_sleeping);
-	if (dev->qdisc != &noqueue_qdisc) {
+	need_watchdog = 0;
+	netdev_for_each_tx_queue(dev, transition_one_qdisc, &need_watchdog);
+	if (dev_ingress_queue(dev))
+		transition_one_qdisc(dev, dev_ingress_queue(dev), NULL);
+
+	if (need_watchdog) {
 		dev->trans_start = jiffies;
 		dev_watchdog_up(dev);
 	}
-	spin_unlock_bh(&dev->queue_lock);
 }
+EXPORT_SYMBOL(dev_activate);
 
-void dev_deactivate(struct net_device *dev)
+static void dev_deactivate_queue(struct net_device *dev,
+				 struct netdev_queue *dev_queue,
+				 void *_qdisc_default)
 {
+	struct Qdisc *qdisc_default = _qdisc_default;
 	struct Qdisc *qdisc;
-	struct sk_buff *skb;
-	int running;
 
-	spin_lock_bh(&dev->queue_lock);
-	qdisc = dev->qdisc;
-	dev->qdisc = &noop_qdisc;
+	qdisc = dev_queue->qdisc;
+	if (qdisc) {
+		spin_lock_bh(qdisc_lock(qdisc));
 
-	qdisc_reset(qdisc);
+		if (!(qdisc->flags & TCQ_F_BUILTIN))
+			set_bit(__QDISC_STATE_DEACTIVATED, &qdisc->state);
 
-	skb = dev->gso_skb;
-	dev->gso_skb = NULL;
-	spin_unlock_bh(&dev->queue_lock);
+		rcu_assign_pointer(dev_queue->qdisc, qdisc_default);
+		qdisc_reset(qdisc);
 
-	kfree_skb(skb);
+		spin_unlock_bh(qdisc_lock(qdisc));
+	}
+}
+
+static bool some_qdisc_is_busy(struct net_device *dev)
+{
+	unsigned int i;
+
+	for (i = 0; i < dev->num_tx_queues; i++) {
+		struct netdev_queue *dev_queue;
+		spinlock_t *root_lock;
+		struct Qdisc *q;
+		int val;
 
-	dev_watchdog_down(dev);
+		dev_queue = netdev_get_tx_queue(dev, i);
+		q = dev_queue->qdisc_sleeping;
+		root_lock = qdisc_lock(q);
 
-	/* Wait for outstanding qdisc-less dev_queue_xmit calls. */
-	synchronize_rcu();
+		spin_lock_bh(root_lock);
+
+		val = (qdisc_is_running(q) ||
+		       test_bit(__QDISC_STATE_SCHED, &q->state));
+
+		spin_unlock_bh(root_lock);
+
+		if (val)
+			return true;
+	}
+	return false;
+}
+
+/**
+ * 	dev_deactivate_many - deactivate transmissions on several devices
+ * 	@head: list of devices to deactivate
+ *
+ *	This function returns only when all outstanding transmissions
+ *	have completed, unless all devices are in dismantle phase.
+ */
+void dev_deactivate_many(struct list_head *head)
+{
+	struct net_device *dev;
+	bool sync_needed = false;
+
+	list_for_each_entry(dev, head, close_list) {
+		netdev_for_each_tx_queue(dev, dev_deactivate_queue,
+					 &noop_qdisc);
+		if (dev_ingress_queue(dev))
+			dev_deactivate_queue(dev, dev_ingress_queue(dev),
+					     &noop_qdisc);
+
+		dev_watchdog_down(dev);
+		sync_needed |= !dev->dismantle;
+	}
+
+	/* Wait for outstanding qdisc-less dev_queue_xmit calls.
+	 * This is avoided if all devices are in dismantle phase :
+	 * Caller will call synchronize_net() for us
+	 */
+	if (sync_needed)
+		synchronize_net();
 
 	/* Wait for outstanding qdisc_run calls. */
-	do {
-		while (test_bit(__LINK_STATE_QDISC_RUNNING, &dev->state))
+	list_for_each_entry(dev, head, close_list)
+		while (some_qdisc_is_busy(dev))
 			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);
+void dev_deactivate(struct net_device *dev)
+{
+	LIST_HEAD(single);
 
-		/*
-		 * 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));
+	list_add(&dev->close_list, &single);
+	dev_deactivate_many(&single);
+	list_del(&single);
+}
+EXPORT_SYMBOL(dev_deactivate);
+
+static void dev_init_scheduler_queue(struct net_device *dev,
+				     struct netdev_queue *dev_queue,
+				     void *_qdisc)
+{
+	struct Qdisc *qdisc = _qdisc;
+
+	dev_queue->qdisc = qdisc;
+	dev_queue->qdisc_sleeping = qdisc;
 }
 
 void dev_init_scheduler(struct net_device *dev)
 {
-	qdisc_lock_tree(dev);
 	dev->qdisc = &noop_qdisc;
-	dev->qdisc_sleeping = &noop_qdisc;
-	INIT_LIST_HEAD(&dev->qdisc_list);
-	qdisc_unlock_tree(dev);
+	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);
 
 	setup_timer(&dev->watchdog_timer, dev_watchdog, (unsigned long)dev);
 }
 
-void dev_shutdown(struct net_device *dev)
+static void shutdown_scheduler_queue(struct net_device *dev,
+				     struct netdev_queue *dev_queue,
+				     void *_qdisc_default)
 {
-	struct Qdisc *qdisc;
+	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_lock_tree(dev);
-	qdisc = dev->qdisc_sleeping;
-	dev->qdisc = &noop_qdisc;
-	dev->qdisc_sleeping = &noop_qdisc;
-	qdisc_destroy(qdisc);
-#if defined(CONFIG_NET_SCH_INGRESS) || defined(CONFIG_NET_SCH_INGRESS_MODULE)
-	if ((qdisc = dev->qdisc_ingress) != NULL) {
-		dev->qdisc_ingress = NULL;
 		qdisc_destroy(qdisc);
 	}
-#endif
-	BUG_TRAP(!timer_pending(&dev->watchdog_timer));
-	qdisc_unlock_tree(dev);
 }
+
+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_destroy(dev->qdisc);
+	dev->qdisc = &noop_qdisc;
+
+	WARN_ON(timer_pending(&dev->watchdog_timer));
+}
+
+void psched_ratecfg_precompute(struct psched_ratecfg *r,
+			       const struct tc_ratespec *conf,
+			       u64 rate64)
+{
+	memset(r, 0, sizeof(*r));
+	r->overhead = conf->overhead;
+	r->rate_bytes_ps = max_t(u64, conf->rate, rate64);
+	r->linklayer = (conf->linklayer & TC_LINKLAYER_MASK);
+	r->mult = 1;
+	/*
+	 * The deal here is to replace a divide by a reciprocal one
+	 * in fast path (a reciprocal divide is a multiply and a shift)
+	 *
+	 * Normal formula would be :
+	 *  time_in_ns = (NSEC_PER_SEC * len) / rate_bps
+	 *
+	 * We compute mult/shift to use instead :
+	 *  time_in_ns = (len * mult) >> shift;
+	 *
+	 * We try to get the highest possible mult value for accuracy,
+	 * but have to make sure no overflows will ever happen.
+	 */
+	if (r->rate_bytes_ps > 0) {
+		u64 factor = NSEC_PER_SEC;
+
+		for (;;) {
+			r->mult = div64_u64(factor, r->rate_bytes_ps);
+			if (r->mult & (1U << 31) || factor & (1ULL << 63))
+				break;
+			factor <<= 1;
+			r->shift++;
+		}
+	}
+}
+EXPORT_SYMBOL(psched_ratecfg_precompute);