Merge commit 'v2.6.27-rc6' into timers/hpet

1 files changed, 73 insertions, 53 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 8d13a9b9f1df..e719ed29310f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1339,19 +1339,23 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev)
 }
 
 
-void __netif_schedule(struct Qdisc *q)
+static inline void __netif_reschedule(struct Qdisc *q)
 {
-        if (!test_and_set_bit(__QDISC_STATE_SCHED, &q->state)) {
-                struct softnet_data *sd;
-                unsigned long flags;
+        struct softnet_data *sd;
+        unsigned long flags;
 
-                local_irq_save(flags);
-                sd = &__get_cpu_var(softnet_data);
-                q->next_sched = sd->output_queue;
-                sd->output_queue = q;
-                raise_softirq_irqoff(NET_TX_SOFTIRQ);
-                local_irq_restore(flags);
-        }
+        local_irq_save(flags);
+        sd = &__get_cpu_var(softnet_data);
+        q->next_sched = sd->output_queue;
+        sd->output_queue = q;
+        raise_softirq_irqoff(NET_TX_SOFTIRQ);
+        local_irq_restore(flags);
+}
+
+void __netif_schedule(struct Qdisc *q)
+{
+        if (!test_and_set_bit(__QDISC_STATE_SCHED, &q->state))
+                __netif_reschedule(q);
 }
 EXPORT_SYMBOL(__netif_schedule);
 
@@ -1796,16 +1800,19 @@ gso:
         skb->tc_verd = SET_TC_AT(skb->tc_verd,AT_EGRESS);
 #endif
         if (q->enqueue) {
-                spinlock_t *root_lock = qdisc_root_lock(q);
+                spinlock_t *root_lock = qdisc_lock(q);
 
                 spin_lock(root_lock);
 
-                rc = qdisc_enqueue_root(skb, q);
-                qdisc_run(q);
-
+                if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) {
+                        kfree_skb(skb);
+                        rc = NET_XMIT_DROP;
+                } else {
+                        rc = qdisc_enqueue_root(skb, q);
+                        qdisc_run(q);
+                }
                 spin_unlock(root_lock);
 
-                rc = rc == NET_XMIT_BYPASS ? NET_XMIT_SUCCESS : rc;
                 goto out;
         }
 
@@ -1909,7 +1916,6 @@ int netif_rx(struct sk_buff *skb)
         if (queue->input_pkt_queue.qlen <= netdev_max_backlog) {
                 if (queue->input_pkt_queue.qlen) {
 enqueue:
-                        dev_hold(skb->dev);
                         __skb_queue_tail(&queue->input_pkt_queue, skb);
                         local_irq_restore(flags);
                         return NET_RX_SUCCESS;
@@ -1941,22 +1947,6 @@ int netif_rx_ni(struct sk_buff *skb)
 
 EXPORT_SYMBOL(netif_rx_ni);
 
-static inline struct net_device *skb_bond(struct sk_buff *skb)
-{
-        struct net_device *dev = skb->dev;
-
-        if (dev->master) {
-                if (skb_bond_should_drop(skb)) {
-                        kfree_skb(skb);
-                        return NULL;
-                }
-                skb->dev = dev->master;
-        }
-
-        return dev;
-}
-
-
 static void net_tx_action(struct softirq_action *h)
 {
         struct softnet_data *sd = &__get_cpu_var(softnet_data);
@@ -1992,15 +1982,22 @@ static void net_tx_action(struct softirq_action *h)
 
                         head = head->next_sched;
 
-                        smp_mb__before_clear_bit();
-                        clear_bit(__QDISC_STATE_SCHED, &q->state);
-
-                        root_lock = qdisc_root_lock(q);
+                        root_lock = qdisc_lock(q);
                         if (spin_trylock(root_lock)) {
+                                smp_mb__before_clear_bit();
+                                clear_bit(__QDISC_STATE_SCHED,
+                                          &q->state);
                                 qdisc_run(q);
                                 spin_unlock(root_lock);
                         } else {
-                                __netif_schedule(q);
+                                if (!test_bit(__QDISC_STATE_DEACTIVATED,
+                                              &q->state)) {
+                                        __netif_reschedule(q);
+                                } else {
+                                        smp_mb__before_clear_bit();
+                                        clear_bit(__QDISC_STATE_SCHED,
+                                                  &q->state);
+                                }
                         }
                 }
         }
@@ -2100,9 +2097,10 @@ static int ing_filter(struct sk_buff *skb)
         rxq = &dev->rx_queue;
 
         q = rxq->qdisc;
-        if (q) {
+        if (q != &noop_qdisc) {
                 spin_lock(qdisc_lock(q));
-                result = qdisc_enqueue_root(skb, q);
+                if (likely(!test_bit(__QDISC_STATE_DEACTIVATED, &q->state)))
+                        result = qdisc_enqueue_root(skb, q);
                 spin_unlock(qdisc_lock(q));
         }
 
@@ -2113,7 +2111,7 @@ static inline struct sk_buff *handle_ing(struct sk_buff *skb,
                                          struct packet_type **pt_prev,
                                          int *ret, struct net_device *orig_dev)
 {
-        if (!skb->dev->rx_queue.qdisc)
+        if (skb->dev->rx_queue.qdisc == &noop_qdisc)
                 goto out;
 
         if (*pt_prev) {
@@ -2183,6 +2181,7 @@ int netif_receive_skb(struct sk_buff *skb)
 {
         struct packet_type *ptype, *pt_prev;
         struct net_device *orig_dev;
+        struct net_device *null_or_orig;
         int ret = NET_RX_DROP;
         __be16 type;
 
@@ -2196,10 +2195,14 @@ int netif_receive_skb(struct sk_buff *skb)
         if (!skb->iif)
                 skb->iif = skb->dev->ifindex;
 
-        orig_dev = skb_bond(skb);
-
-        if (!orig_dev)
-                return NET_RX_DROP;
+        null_or_orig = NULL;
+        orig_dev = skb->dev;
+        if (orig_dev->master) {
+                if (skb_bond_should_drop(skb))
+                        null_or_orig = orig_dev; /* deliver only exact match */
+                else
+                        skb->dev = orig_dev->master;
+        }
 
         __get_cpu_var(netdev_rx_stat).total++;
 
@@ -2223,7 +2226,8 @@ int netif_receive_skb(struct sk_buff *skb)
 #endif
 
         list_for_each_entry_rcu(ptype, &ptype_all, list) {
-                if (!ptype->dev || ptype->dev == skb->dev) {
+                if (ptype->dev == null_or_orig || ptype->dev == skb->dev ||
+                    ptype->dev == orig_dev) {
                         if (pt_prev)
                                 ret = deliver_skb(skb, pt_prev, orig_dev);
                         pt_prev = ptype;
@@ -2248,7 +2252,8 @@ ncls:
         list_for_each_entry_rcu(ptype,
                         &ptype_base[ntohs(type) & PTYPE_HASH_MASK], list) {
                 if (ptype->type == type &&
-                    (!ptype->dev || ptype->dev == skb->dev)) {
+                    (ptype->dev == null_or_orig || ptype->dev == skb->dev ||
+                     ptype->dev == orig_dev)) {
                         if (pt_prev)
                                 ret = deliver_skb(skb, pt_prev, orig_dev);
                         pt_prev = ptype;
@@ -2270,6 +2275,20 @@ out:
         return ret;
 }
 
+/* Network device is going away, flush any packets still pending  */
+static void flush_backlog(void *arg)
+{
+        struct net_device *dev = arg;
+        struct softnet_data *queue = &__get_cpu_var(softnet_data);
+        struct sk_buff *skb, *tmp;
+
+        skb_queue_walk_safe(&queue->input_pkt_queue, skb, tmp)
+                if (skb->dev == dev) {
+                        __skb_unlink(skb, &queue->input_pkt_queue);
+                        kfree_skb(skb);
+                }
+}
+
 static int process_backlog(struct napi_struct *napi, int quota)
 {
         int work = 0;
@@ -2279,7 +2298,6 @@ static int process_backlog(struct napi_struct *napi, int quota)
         napi->weight = weight_p;
         do {
                 struct sk_buff *skb;
-                struct net_device *dev;
 
                 local_irq_disable();
                 skb = __skb_dequeue(&queue->input_pkt_queue);
@@ -2288,14 +2306,9 @@ static int process_backlog(struct napi_struct *napi, int quota)
                         local_irq_enable();
                         break;
                 }
-
                 local_irq_enable();
 
-                dev = skb->dev;
-
                 netif_receive_skb(skb);
-
-                dev_put(dev);
         } while (++work < quota && jiffies == start_time);
 
         return work;
@@ -3988,6 +4001,10 @@ int register_netdevice(struct net_device *dev)
                 }
         }
 
+        /* Enable software GSO if SG is supported. */
+        if (dev->features & NETIF_F_SG)
+                dev->features |= NETIF_F_GSO;
+
         netdev_initialize_kobject(dev);
         ret = netdev_register_kobject(dev);
         if (ret)
@@ -4165,6 +4182,8 @@ void netdev_run_todo(void)
 
                 dev->reg_state = NETREG_UNREGISTERED;
 
+                on_each_cpu(flush_backlog, dev, 1);
+
                 netdev_wait_allrefs(dev);
 
                 /* paranoia */
@@ -4200,6 +4219,7 @@ static void netdev_init_queues(struct net_device *dev)
 {
         netdev_init_one_queue(dev, &dev->rx_queue, NULL);
         netdev_for_each_tx_queue(dev, netdev_init_one_queue, NULL);
+        spin_lock_init(&dev->tx_global_lock);
 }
 
 /**