1 files changed, 88 insertions, 50 deletions

diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 2aeb3a4386a1..b4c680900d7a 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -60,8 +60,7 @@ static inline struct sk_buff *dequeue_skb(struct Qdisc *q)
 
                 /* check the reason of requeuing without tx lock first */
                 txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb));
-                if (!netif_tx_queue_stopped(txq) &&
-                    !netif_tx_queue_frozen(txq)) {
+                if (!netif_tx_queue_frozen_or_stopped(txq)) {
                         q->gso_skb = NULL;
                         q->q.qlen--;
                 } else
@@ -88,8 +87,8 @@ static inline int handle_dev_cpu_collision(struct sk_buff *skb,
                  */
                 kfree_skb(skb);
                 if (net_ratelimit())
-                        printk(KERN_WARNING "Dead loop on netdevice %s, "
-                               "fix it urgently!\n", dev_queue->dev->name);
+                        pr_warning("Dead loop on netdevice %s, fix it urgently!\n",
+                                   dev_queue->dev->name);
                 ret = qdisc_qlen(q);
         } else {
                 /*
@@ -122,7 +121,7 @@ int sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q,
         spin_unlock(root_lock);
 
         HARD_TX_LOCK(dev, txq, smp_processor_id());
-        if (!netif_tx_queue_stopped(txq) && !netif_tx_queue_frozen(txq))
+        if (!netif_tx_queue_frozen_or_stopped(txq))
                 ret = dev_hard_start_xmit(skb, dev, txq);
 
         HARD_TX_UNLOCK(dev, txq);
@@ -138,14 +137,13 @@ int sch_direct_xmit(struct sk_buff *skb, struct Qdisc *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);
+                        pr_warning("BUG %s code %d qlen %d\n",
+                                   dev->name, ret, q->q.qlen);
 
                 ret = dev_requeue_skb(skb, q);
         }
 
-        if (ret && (netif_tx_queue_stopped(txq) ||
-                    netif_tx_queue_frozen(txq)))
+        if (ret && netif_tx_queue_frozen_or_stopped(txq))
                 ret = 0;
 
         return ret;
@@ -253,9 +251,8 @@ static void dev_watchdog(unsigned long arg)
                         }
 
                         if (some_queue_timedout) {
-                                char 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->name, netdev_drivername(dev), i);
                                 dev->netdev_ops->ndo_tx_timeout(dev);
                         }
                         if (!mod_timer(&dev->watchdog_timer,
@@ -383,6 +380,7 @@ struct Qdisc noop_qdisc = {
         .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);
 
@@ -409,11 +407,13 @@ static struct Qdisc noqueue_qdisc = {
         .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.
@@ -445,7 +445,7 @@ static inline struct sk_buff_head *band2list(struct pfifo_fast_priv *priv,
         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)
 {
         if (skb_queue_len(&qdisc->q) < qdisc_dev(qdisc)->tx_queue_len) {
                 int band = prio2band[skb->priority & TC_PRIO_MAX];
@@ -460,7 +460,7 @@ 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)
 {
         struct pfifo_fast_priv *priv = qdisc_priv(qdisc);
         int band = bitmap2band[priv->bitmap];
@@ -479,7 +479,7 @@ static struct sk_buff *pfifo_fast_dequeue(struct Qdisc* qdisc)
         return NULL;
 }
 
-static struct sk_buff *pfifo_fast_peek(struct Qdisc* qdisc)
+static struct sk_buff *pfifo_fast_peek(struct Qdisc *qdisc)
 {
         struct pfifo_fast_priv *priv = qdisc_priv(qdisc);
         int band = bitmap2band[priv->bitmap];
@@ -493,7 +493,7 @@ static struct sk_buff *pfifo_fast_peek(struct Qdisc* qdisc)
         return NULL;
 }
 
-static void pfifo_fast_reset(struct Qdisc* qdisc)
+static void pfifo_fast_reset(struct Qdisc *qdisc)
 {
         int prio;
         struct pfifo_fast_priv *priv = qdisc_priv(qdisc);
@@ -510,7 +510,7 @@ 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);
+        memcpy(&opt.priomap, prio2band, TC_PRIO_MAX + 1);
         NLA_PUT(skb, TCA_OPTIONS, sizeof(opt), &opt);
         return skb->len;
 
@@ -526,6 +526,8 @@ static int pfifo_fast_init(struct Qdisc *qdisc, struct nlattr *opt)
         for (prio = 0; prio < PFIFO_FAST_BANDS; prio++)
                 skb_queue_head_init(band2list(priv, prio));
 
+        /* Can by-pass the queue discipline */
+        qdisc->flags |= TCQ_F_CAN_BYPASS;
         return 0;
 }
 
@@ -540,25 +542,32 @@ struct Qdisc_ops pfifo_fast_ops __read_mostly = {
         .dump           =       pfifo_fast_dump,
         .owner          =       THIS_MODULE,
 };
+EXPORT_SYMBOL(pfifo_fast_ops);
 
 struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
                           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;
 
-        /* ensure that the Qdisc and the private data are 64-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);
@@ -574,10 +583,8 @@ errout:
         return ERR_PTR(err);
 }
 
-struct Qdisc * qdisc_create_dflt(struct net_device *dev,
-                                 struct netdev_queue *dev_queue,
-                                 struct Qdisc_ops *ops,
-                                 unsigned int parentid)
+struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue,
+                                struct Qdisc_ops *ops, unsigned int parentid)
 {
         struct Qdisc *sch;
 
@@ -630,7 +637,7 @@ void qdisc_destroy(struct Qdisc *qdisc)
 #ifdef CONFIG_NET_SCHED
         qdisc_list_del(qdisc);
 
-        qdisc_put_stab(qdisc->stab);
+        qdisc_put_stab(rtnl_dereference(qdisc->stab));
 #endif
         gen_kill_estimator(&qdisc->bstats, &qdisc->rate_est);
         if (ops->reset)
@@ -674,25 +681,21 @@ struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue,
 
         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;
+        struct Qdisc *qdisc = &noqueue_qdisc;
 
         if (dev->tx_queue_len) {
-                qdisc = qdisc_create_dflt(dev, dev_queue,
+                qdisc = qdisc_create_dflt(dev_queue,
                                           &pfifo_fast_ops, TC_H_ROOT);
                 if (!qdisc) {
-                        printk(KERN_INFO "%s: activation failed\n", dev->name);
+                        netdev_info(dev, "activation failed\n");
                         return;
                 }
-
-                /* Can by-pass the queue discipline for default qdisc */
-                qdisc->flags |= TCQ_F_CAN_BYPASS;
-        } else {
-                qdisc =  &noqueue_qdisc;
         }
         dev_queue->qdisc_sleeping = qdisc;
 }
@@ -709,7 +712,7 @@ static void attach_default_qdiscs(struct net_device *dev)
                 dev->qdisc = txq->qdisc_sleeping;
                 atomic_inc(&dev->qdisc->refcnt);
         } else {
-                qdisc = qdisc_create_dflt(dev, txq, &mq_qdisc_ops, TC_H_ROOT);
+                qdisc = qdisc_create_dflt(txq, &mq_qdisc_ops, TC_H_ROOT);
                 if (qdisc) {
                         qdisc->ops->attach(qdisc);
                         dev->qdisc = qdisc;
@@ -753,13 +756,15 @@ void dev_activate(struct net_device *dev)
 
         need_watchdog = 0;
         netdev_for_each_tx_queue(dev, transition_one_qdisc, &need_watchdog);
-        transition_one_qdisc(dev, &dev->rx_queue, NULL);
+        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);
         }
 }
+EXPORT_SYMBOL(dev_activate);
 
 static void dev_deactivate_queue(struct net_device *dev,
                                  struct netdev_queue *dev_queue,
@@ -809,20 +814,51 @@ static bool some_qdisc_is_busy(struct net_device *dev)
         return false;
 }
 
-void dev_deactivate(struct net_device *dev)
+/**
+ *      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)
 {
-        netdev_for_each_tx_queue(dev, dev_deactivate_queue, &noop_qdisc);
-        dev_deactivate_queue(dev, &dev->rx_queue, &noop_qdisc);
+        struct net_device *dev;
+        bool sync_needed = false;
 
-        dev_watchdog_down(dev);
+        list_for_each_entry(dev, head, unreg_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);
 
-        /* Wait for outstanding qdisc-less dev_queue_xmit calls. */
-        synchronize_rcu();
+                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. */
-        while (some_qdisc_is_busy(dev))
-                yield();
+        list_for_each_entry(dev, head, unreg_list)
+                while (some_qdisc_is_busy(dev))
+                        yield();
+}
+
+void dev_deactivate(struct net_device *dev)
+{
+        LIST_HEAD(single);
+
+        list_add(&dev->unreg_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,
@@ -838,7 +874,8 @@ void dev_init_scheduler(struct net_device *dev)
 {
         dev->qdisc = &noop_qdisc;
         netdev_for_each_tx_queue(dev, dev_init_scheduler_queue, &noop_qdisc);
-        dev_init_scheduler_queue(dev, &dev->rx_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);
 }
@@ -861,7 +898,8 @@ static void shutdown_scheduler_queue(struct net_device *dev,
 void dev_shutdown(struct net_device *dev)
 {
         netdev_for_each_tx_queue(dev, shutdown_scheduler_queue, &noop_qdisc);
-        shutdown_scheduler_queue(dev, &dev->rx_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;