1 files changed, 115 insertions, 78 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index bf629ac08b87..9977288583b8 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -79,6 +79,7 @@
 #include <linux/cpu.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
+#include <linux/hash.h>
 #include <linux/sched.h>
 #include <linux/mutex.h>
 #include <linux/string.h>
@@ -196,7 +197,7 @@ EXPORT_SYMBOL(dev_base_lock);
 static inline struct hlist_head *dev_name_hash(struct net *net, const char *name)
 {
 	unsigned hash = full_name_hash(name, strnlen(name, IFNAMSIZ));
-	return &net->dev_name_head[hash & (NETDEV_HASHENTRIES - 1)];
+	return &net->dev_name_head[hash_32(hash, NETDEV_HASHBITS)];
 }
 
 static inline struct hlist_head *dev_index_hash(struct net *net, int ifindex)
@@ -892,7 +893,8 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf)
 		free_page((unsigned long) inuse);
 	}
 
-	snprintf(buf, IFNAMSIZ, name, i);
+	if (buf != name)
+		snprintf(buf, IFNAMSIZ, name, i);
 	if (!__dev_get_by_name(net, buf))
 		return i;
 
@@ -932,6 +934,21 @@ int dev_alloc_name(struct net_device *dev, const char *name)
 }
 EXPORT_SYMBOL(dev_alloc_name);
 
+static int dev_get_valid_name(struct net *net, const char *name, char *buf,
+			      bool fmt)
+{
+	if (!dev_valid_name(name))
+		return -EINVAL;
+
+	if (fmt && strchr(name, '%'))
+		return __dev_alloc_name(net, name, buf);
+	else if (__dev_get_by_name(net, name))
+		return -EEXIST;
+	else if (buf != name)
+		strlcpy(buf, name, IFNAMSIZ);
+
+	return 0;
+}
 
 /**
  *	dev_change_name - change name of a device
@@ -955,22 +972,14 @@ int dev_change_name(struct net_device *dev, const char *newname)
 	if (dev->flags & IFF_UP)
 		return -EBUSY;
 
-	if (!dev_valid_name(newname))
-		return -EINVAL;
-
 	if (strncmp(newname, dev->name, IFNAMSIZ) == 0)
 		return 0;
 
 	memcpy(oldname, dev->name, IFNAMSIZ);
 
-	if (strchr(newname, '%')) {
-		err = dev_alloc_name(dev, newname);
-		if (err < 0)
-			return err;
-	} else if (__dev_get_by_name(net, newname))
-		return -EEXIST;
-	else
-		strlcpy(dev->name, newname, IFNAMSIZ);
+	err = dev_get_valid_name(net, newname, dev->name, 1);
+	if (err < 0)
+		return err;
 
 rollback:
 	/* For now only devices in the initial network namespace
@@ -998,14 +1007,15 @@ rollback:
 	ret = notifier_to_errno(ret);
 
 	if (ret) {
-		if (err) {
-			printk(KERN_ERR
-			       "%s: name change rollback failed: %d.\n",
-			       dev->name, ret);
-		} else {
+		/* err >= 0 after dev_alloc_name() or stores the first errno */
+		if (err >= 0) {
 			err = ret;
 			memcpy(dev->name, oldname, IFNAMSIZ);
 			goto rollback;
+		} else {
+			printk(KERN_ERR
+			       "%s: name change rollback failed: %d.\n",
+			       dev->name, ret);
 		}
 	}
 
@@ -1342,6 +1352,7 @@ rollback:
 				nb->notifier_call(nb, NETDEV_DOWN, dev);
 			}
 			nb->notifier_call(nb, NETDEV_UNREGISTER, dev);
+			nb->notifier_call(nb, NETDEV_UNREGISTER_PERNET, dev);
 		}
 	}
 
@@ -1756,7 +1767,7 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
 			struct netdev_queue *txq)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
-	int rc;
+	int rc = NETDEV_TX_OK;
 
 	if (likely(!skb->next)) {
 		if (!list_empty(&ptype_all))
@@ -1804,6 +1815,8 @@ gso:
 		nskb->next = NULL;
 		rc = ops->ndo_start_xmit(nskb, dev);
 		if (unlikely(rc != NETDEV_TX_OK)) {
+			if (rc & ~NETDEV_TX_MASK)
+				goto out_kfree_gso_skb;
 			nskb->next = skb->next;
 			skb->next = nskb;
 			return rc;
@@ -1813,11 +1826,12 @@ gso:
 			return NETDEV_TX_BUSY;
 	} while (skb->next);
 
-	skb->destructor = DEV_GSO_CB(skb)->destructor;
-
+out_kfree_gso_skb:
+	if (likely(skb->next == NULL))
+		skb->destructor = DEV_GSO_CB(skb)->destructor;
 out_kfree_skb:
 	kfree_skb(skb);
-	return NETDEV_TX_OK;
+	return rc;
 }
 
 static u32 skb_tx_hashrnd;
@@ -1844,6 +1858,20 @@ u16 skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb)
 }
 EXPORT_SYMBOL(skb_tx_hash);
 
+static inline u16 dev_cap_txqueue(struct net_device *dev, u16 queue_index)
+{
+	if (unlikely(queue_index >= dev->real_num_tx_queues)) {
+		if (net_ratelimit()) {
+			WARN(1, "%s selects TX queue %d, but "
+			     "real number of TX queues is %d\n",
+			     dev->name, queue_index,
+			     dev->real_num_tx_queues);
+		}
+		return 0;
+	}
+	return queue_index;
+}
+
 static struct netdev_queue *dev_pick_tx(struct net_device *dev,
 					struct sk_buff *skb)
 {
@@ -1857,6 +1885,7 @@ static struct netdev_queue *dev_pick_tx(struct net_device *dev,
 
 		if (ops->ndo_select_queue) {
 			queue_index = ops->ndo_select_queue(dev, skb);
+			queue_index = dev_cap_txqueue(dev, queue_index);
 		} else {
 			queue_index = 0;
 			if (dev->real_num_tx_queues > 1)
@@ -2002,8 +2031,8 @@ gso:
 			HARD_TX_LOCK(dev, txq, cpu);
 
 			if (!netif_tx_queue_stopped(txq)) {
-				rc = NET_XMIT_SUCCESS;
-				if (!dev_hard_start_xmit(skb, dev, txq)) {
+				rc = dev_hard_start_xmit(skb, dev, txq);
+				if (dev_xmit_complete(rc)) {
 					HARD_TX_UNLOCK(dev, txq);
 					goto out;
 				}
@@ -4701,7 +4730,8 @@ static void net_set_todo(struct net_device *dev)
 
 static void rollback_registered_many(struct list_head *head)
 {
-	struct net_device *dev;
+	struct net_device *dev, *aux, *fdev;
+	LIST_HEAD(pernet_list);
 
 	BUG_ON(dev_boot_phase);
 	ASSERT_RTNL();
@@ -4759,8 +4789,24 @@ static void rollback_registered_many(struct list_head *head)
 
 	synchronize_net();
 
-	list_for_each_entry(dev, head, unreg_list)
+	list_for_each_entry_safe(dev, aux, head, unreg_list) {
+		int new_net = 1;
+		list_for_each_entry(fdev, &pernet_list, unreg_list) {
+			if (dev_net(dev) == dev_net(fdev)) {
+				new_net = 0;
+				dev_put(dev);
+				break;
+			}
+		}
+		if (new_net)
+			list_move(&dev->unreg_list, &pernet_list);
+	}
+
+	list_for_each_entry_safe(dev, aux, &pernet_list, unreg_list) {
+		call_netdevice_notifiers(NETDEV_UNREGISTER_PERNET, dev);
+		list_move(&dev->unreg_list, head);
 		dev_put(dev);
+	}
 }
 
 static void rollback_registered(struct net_device *dev)
@@ -4845,8 +4891,6 @@ EXPORT_SYMBOL(netdev_fix_features);
 
 int register_netdevice(struct net_device *dev)
 {
-	struct hlist_head *head;
-	struct hlist_node *p;
 	int ret;
 	struct net *net = dev_net(dev);
 
@@ -4875,26 +4919,14 @@ int register_netdevice(struct net_device *dev)
 		}
 	}
 
-	if (!dev_valid_name(dev->name)) {
-		ret = -EINVAL;
+	ret = dev_get_valid_name(net, dev->name, dev->name, 0);
+	if (ret)
 		goto err_uninit;
-	}
 
 	dev->ifindex = dev_new_index(net);
 	if (dev->iflink == -1)
 		dev->iflink = dev->ifindex;
 
-	/* Check for existence of name */
-	head = dev_name_hash(net, dev->name);
-	hlist_for_each(p, head) {
-		struct net_device *d
-			= hlist_entry(p, struct net_device, name_hlist);
-		if (!strncmp(d->name, dev->name, IFNAMSIZ)) {
-			ret = -EEXIST;
-			goto err_uninit;
-		}
-	}
-
 	/* Fix illegal checksum combinations */
 	if ((dev->features & NETIF_F_HW_CSUM) &&
 	    (dev->features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) {
@@ -5047,6 +5079,8 @@ static void netdev_wait_allrefs(struct net_device *dev)
 {
 	unsigned long rebroadcast_time, warning_time;
 
+	linkwatch_forget_dev(dev);
+
 	rebroadcast_time = warning_time = jiffies;
 	while (atomic_read(&dev->refcnt) != 0) {
 		if (time_after(jiffies, rebroadcast_time + 1 * HZ)) {
@@ -5054,6 +5088,8 @@ static void netdev_wait_allrefs(struct net_device *dev)
 
 			/* Rebroadcast unregister notification */
 			call_netdevice_notifiers(NETDEV_UNREGISTER, dev);
+			/* don't resend NETDEV_UNREGISTER_PERNET, _PERNET users
+			 * should have already handle it the first time */
 
 			if (test_bit(__LINK_STATE_LINKWATCH_PENDING,
 				     &dev->state)) {
@@ -5149,6 +5185,32 @@ void netdev_run_todo(void)
 }
 
 /**
+ *	dev_txq_stats_fold - fold tx_queues stats
+ *	@dev: device to get statistics from
+ *	@stats: struct net_device_stats to hold results
+ */
+void dev_txq_stats_fold(const struct net_device *dev,
+			struct net_device_stats *stats)
+{
+	unsigned long tx_bytes = 0, tx_packets = 0, tx_dropped = 0;
+	unsigned int i;
+	struct netdev_queue *txq;
+
+	for (i = 0; i < dev->num_tx_queues; i++) {
+		txq = netdev_get_tx_queue(dev, i);
+		tx_bytes   += txq->tx_bytes;
+		tx_packets += txq->tx_packets;
+		tx_dropped += txq->tx_dropped;
+	}
+	if (tx_bytes || tx_packets || tx_dropped) {
+		stats->tx_bytes   = tx_bytes;
+		stats->tx_packets = tx_packets;
+		stats->tx_dropped = tx_dropped;
+	}
+}
+EXPORT_SYMBOL(dev_txq_stats_fold);
+
+/**
  *	dev_get_stats	- get network device statistics
  *	@dev: device to get statistics from
  *
@@ -5162,25 +5224,9 @@ const struct net_device_stats *dev_get_stats(struct net_device *dev)
 
 	if (ops->ndo_get_stats)
 		return ops->ndo_get_stats(dev);
-	else {
-		unsigned long tx_bytes = 0, tx_packets = 0, tx_dropped = 0;
-		struct net_device_stats *stats = &dev->stats;
-		unsigned int i;
-		struct netdev_queue *txq;
-
-		for (i = 0; i < dev->num_tx_queues; i++) {
-			txq = netdev_get_tx_queue(dev, i);
-			tx_bytes   += txq->tx_bytes;
-			tx_packets += txq->tx_packets;
-			tx_dropped += txq->tx_dropped;
-		}
-		if (tx_bytes || tx_packets || tx_dropped) {
-			stats->tx_bytes   = tx_bytes;
-			stats->tx_packets = tx_packets;
-			stats->tx_dropped = tx_dropped;
-		}
-		return stats;
-	}
+
+	dev_txq_stats_fold(dev, &dev->stats);
+	return &dev->stats;
 }
 EXPORT_SYMBOL(dev_get_stats);
 
@@ -5261,6 +5307,7 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name,
 
 	INIT_LIST_HEAD(&dev->napi_list);
 	INIT_LIST_HEAD(&dev->unreg_list);
+	INIT_LIST_HEAD(&dev->link_watch_list);
 	dev->priv_flags = IFF_XMIT_DST_RELEASE;
 	setup(dev);
 	strcpy(dev->name, name);
@@ -5355,6 +5402,10 @@ EXPORT_SYMBOL(unregister_netdevice_queue);
  *	unregister_netdevice_many - unregister many devices
  *	@head: list of devices
  *
+ *	WARNING: Calling this modifies the given list
+ *	(in rollback_registered_many). It may change the order of the elements
+ *	in the list. However, you can assume it does not add or delete elements
+ *	to/from the list.
  */
 void unregister_netdevice_many(struct list_head *head)
 {
@@ -5403,8 +5454,6 @@ EXPORT_SYMBOL(unregister_netdev);
 
 int dev_change_net_namespace(struct net_device *dev, struct net *net, const char *pat)
 {
-	char buf[IFNAMSIZ];
-	const char *destname;
 	int err;
 
 	ASSERT_RTNL();
@@ -5437,20 +5486,11 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char
 	 * we can use it in the destination network namespace.
 	 */
 	err = -EEXIST;
-	destname = dev->name;
-	if (__dev_get_by_name(net, destname)) {
+	if (__dev_get_by_name(net, dev->name)) {
 		/* We get here if we can't use the current device name */
 		if (!pat)
 			goto out;
-		if (!dev_valid_name(pat))
-			goto out;
-		if (strchr(pat, '%')) {
-			if (__dev_alloc_name(net, pat, buf) < 0)
-				goto out;
-			destname = buf;
-		} else
-			destname = pat;
-		if (__dev_get_by_name(net, destname))
+		if (dev_get_valid_name(net, pat, dev->name, 1))
 			goto out;
 	}
 
@@ -5474,6 +5514,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char
 	   this device. They should clean all the things.
 	*/
 	call_netdevice_notifiers(NETDEV_UNREGISTER, dev);
+	call_netdevice_notifiers(NETDEV_UNREGISTER_PERNET, dev);
 
 	/*
 	 *	Flush the unicast and multicast chains
@@ -5486,10 +5527,6 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char
 	/* Actually switch the network namespace */
 	dev_net_set(dev, net);
 
-	/* Assign the new device name */
-	if (destname != dev->name)
-		strcpy(dev->name, destname);
-
 	/* If there is an ifindex conflict assign a new one */
 	if (__dev_get_by_index(net, dev->ifindex)) {
 		int iflink = (dev->iflink == dev->ifindex);