X-Git-Url: http://pileus.org/git/?a=blobdiff_plain;f=net%2Fcore%2Fdev.c;h=09f3d6b9c0c800648591d03ff3a21ad90e558345;hb=8964be4a9a5ca8cab1219bb046db2f6d1936227c;hp=510ff205d5dbd8e318749f21bd8a31c671f59fcf;hpb=d9f5950f90292f7cc42834338dfd5f44dc4cc4ca;p=~andy%2Flinux

diff --git a/net/core/dev.c b/net/core/dev.c
index 510ff205d5d..09f3d6b9c0c 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>
@@ -175,7 +176,7 @@ static struct list_head ptype_all __read_mostly;	/* Taps */
  * The @dev_base_head list is protected by @dev_base_lock and the rtnl
  * semaphore.
  *
- * Pure readers hold dev_base_lock for reading.
+ * Pure readers hold dev_base_lock for reading, or rcu_read_lock()
  *
  * Writers must hold the rtnl semaphore while they loop through the
  * dev_base_head list, and hold dev_base_lock for writing when they do the
@@ -193,18 +194,15 @@ static struct list_head ptype_all __read_mostly;	/* Taps */
 DEFINE_RWLOCK(dev_base_lock);
 EXPORT_SYMBOL(dev_base_lock);
 
-#define NETDEV_HASHBITS	8
-#define NETDEV_HASHENTRIES (1 << NETDEV_HASHBITS)
-
 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 & ((1 << NETDEV_HASHBITS) - 1)];
+	return &net->dev_name_head[hash_32(hash, NETDEV_HASHBITS)];
 }
 
 static inline struct hlist_head *dev_index_hash(struct net *net, int ifindex)
 {
-	return &net->dev_index_head[ifindex & ((1 << NETDEV_HASHBITS) - 1)];
+	return &net->dev_index_head[ifindex & (NETDEV_HASHENTRIES - 1)];
 }
 
 /* Device list insertion */
@@ -215,23 +213,26 @@ static int list_netdevice(struct net_device *dev)
 	ASSERT_RTNL();
 
 	write_lock_bh(&dev_base_lock);
-	list_add_tail(&dev->dev_list, &net->dev_base_head);
-	hlist_add_head(&dev->name_hlist, dev_name_hash(net, dev->name));
-	hlist_add_head(&dev->index_hlist, dev_index_hash(net, dev->ifindex));
+	list_add_tail_rcu(&dev->dev_list, &net->dev_base_head);
+	hlist_add_head_rcu(&dev->name_hlist, dev_name_hash(net, dev->name));
+	hlist_add_head_rcu(&dev->index_hlist,
+			   dev_index_hash(net, dev->ifindex));
 	write_unlock_bh(&dev_base_lock);
 	return 0;
 }
 
-/* Device list removal */
+/* Device list removal
+ * caller must respect a RCU grace period before freeing/reusing dev
+ */
 static void unlist_netdevice(struct net_device *dev)
 {
 	ASSERT_RTNL();
 
 	/* Unlink dev from the device chain */
 	write_lock_bh(&dev_base_lock);
-	list_del(&dev->dev_list);
-	hlist_del(&dev->name_hlist);
-	hlist_del(&dev->index_hlist);
+	list_del_rcu(&dev->dev_list);
+	hlist_del_rcu(&dev->name_hlist);
+	hlist_del_rcu(&dev->index_hlist);
 	write_unlock_bh(&dev_base_lock);
 }
 
@@ -587,17 +588,43 @@ __setup("netdev=", netdev_boot_setup);
 struct net_device *__dev_get_by_name(struct net *net, const char *name)
 {
 	struct hlist_node *p;
+	struct net_device *dev;
+	struct hlist_head *head = dev_name_hash(net, name);
 
-	hlist_for_each(p, dev_name_hash(net, name)) {
-		struct net_device *dev
-			= hlist_entry(p, struct net_device, name_hlist);
+	hlist_for_each_entry(dev, p, head, name_hlist)
 		if (!strncmp(dev->name, name, IFNAMSIZ))
 			return dev;
-	}
+
 	return NULL;
 }
 EXPORT_SYMBOL(__dev_get_by_name);
 
+/**
+ *	dev_get_by_name_rcu	- find a device by its name
+ *	@net: the applicable net namespace
+ *	@name: name to find
+ *
+ *	Find an interface by name.
+ *	If the name is found a pointer to the device is returned.
+ * 	If the name is not found then %NULL is returned.
+ *	The reference counters are not incremented so the caller must be
+ *	careful with locks. The caller must hold RCU lock.
+ */
+
+struct net_device *dev_get_by_name_rcu(struct net *net, const char *name)
+{
+	struct hlist_node *p;
+	struct net_device *dev;
+	struct hlist_head *head = dev_name_hash(net, name);
+
+	hlist_for_each_entry_rcu(dev, p, head, name_hlist)
+		if (!strncmp(dev->name, name, IFNAMSIZ))
+			return dev;
+
+	return NULL;
+}
+EXPORT_SYMBOL(dev_get_by_name_rcu);
+
 /**
  *	dev_get_by_name		- find a device by its name
  *	@net: the applicable net namespace
@@ -614,11 +641,11 @@ struct net_device *dev_get_by_name(struct net *net, const char *name)
 {
 	struct net_device *dev;
 
-	read_lock(&dev_base_lock);
-	dev = __dev_get_by_name(net, name);
+	rcu_read_lock();
+	dev = dev_get_by_name_rcu(net, name);
 	if (dev)
 		dev_hold(dev);
-	read_unlock(&dev_base_lock);
+	rcu_read_unlock();
 	return dev;
 }
 EXPORT_SYMBOL(dev_get_by_name);
@@ -638,17 +665,42 @@ EXPORT_SYMBOL(dev_get_by_name);
 struct net_device *__dev_get_by_index(struct net *net, int ifindex)
 {
 	struct hlist_node *p;
+	struct net_device *dev;
+	struct hlist_head *head = dev_index_hash(net, ifindex);
 
-	hlist_for_each(p, dev_index_hash(net, ifindex)) {
-		struct net_device *dev
-			= hlist_entry(p, struct net_device, index_hlist);
+	hlist_for_each_entry(dev, p, head, index_hlist)
 		if (dev->ifindex == ifindex)
 			return dev;
-	}
+
 	return NULL;
 }
 EXPORT_SYMBOL(__dev_get_by_index);
 
+/**
+ *	dev_get_by_index_rcu - find a device by its ifindex
+ *	@net: the applicable net namespace
+ *	@ifindex: index of device
+ *
+ *	Search for an interface by index. Returns %NULL if the device
+ *	is not found or a pointer to the device. The device has not
+ *	had its reference counter increased so the caller must be careful
+ *	about locking. The caller must hold RCU lock.
+ */
+
+struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex)
+{
+	struct hlist_node *p;
+	struct net_device *dev;
+	struct hlist_head *head = dev_index_hash(net, ifindex);
+
+	hlist_for_each_entry_rcu(dev, p, head, index_hlist)
+		if (dev->ifindex == ifindex)
+			return dev;
+
+	return NULL;
+}
+EXPORT_SYMBOL(dev_get_by_index_rcu);
+
 
 /**
  *	dev_get_by_index - find a device by its ifindex
@@ -665,11 +717,11 @@ struct net_device *dev_get_by_index(struct net *net, int ifindex)
 {
 	struct net_device *dev;
 
-	read_lock(&dev_base_lock);
-	dev = __dev_get_by_index(net, ifindex);
+	rcu_read_lock();
+	dev = dev_get_by_index_rcu(net, ifindex);
 	if (dev)
 		dev_hold(dev);
-	read_unlock(&dev_base_lock);
+	rcu_read_unlock();
 	return dev;
 }
 EXPORT_SYMBOL(dev_get_by_index);
@@ -748,15 +800,15 @@ struct net_device *dev_get_by_flags(struct net *net, unsigned short if_flags,
 	struct net_device *dev, *ret;
 
 	ret = NULL;
-	read_lock(&dev_base_lock);
-	for_each_netdev(net, dev) {
+	rcu_read_lock();
+	for_each_netdev_rcu(net, dev) {
 		if (((dev->flags ^ if_flags) & mask) == 0) {
 			dev_hold(dev);
 			ret = dev;
 			break;
 		}
 	}
-	read_unlock(&dev_base_lock);
+	rcu_read_unlock();
 	return ret;
 }
 EXPORT_SYMBOL(dev_get_by_flags);
@@ -841,7 +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;
 
@@ -881,6 +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
@@ -904,22 +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
@@ -935,21 +995,27 @@ rollback:
 
 	write_lock_bh(&dev_base_lock);
 	hlist_del(&dev->name_hlist);
-	hlist_add_head(&dev->name_hlist, dev_name_hash(net, dev->name));
+	write_unlock_bh(&dev_base_lock);
+
+	synchronize_rcu();
+
+	write_lock_bh(&dev_base_lock);
+	hlist_add_head_rcu(&dev->name_hlist, dev_name_hash(net, dev->name));
 	write_unlock_bh(&dev_base_lock);
 
 	ret = call_netdevice_notifiers(NETDEV_CHANGENAME, dev);
 	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);
 		}
 	}
 
@@ -1037,9 +1103,9 @@ void dev_load(struct net *net, const char *name)
 {
 	struct net_device *dev;
 
-	read_lock(&dev_base_lock);
-	dev = __dev_get_by_name(net, name);
-	read_unlock(&dev_base_lock);
+	rcu_read_lock();
+	dev = dev_get_by_name_rcu(net, name);
+	rcu_read_unlock();
 
 	if (!dev && capable(CAP_NET_ADMIN))
 		request_module("%s", name);
@@ -1286,6 +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);
 		}
 	}
 
@@ -1700,7 +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))
@@ -1748,6 +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;
@@ -1757,11 +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;
@@ -1788,16 +1858,43 @@ 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)
 {
-	const struct net_device_ops *ops = dev->netdev_ops;
-	u16 queue_index = 0;
+	u16 queue_index;
+	struct sock *sk = skb->sk;
 
-	if (ops->ndo_select_queue)
-		queue_index = ops->ndo_select_queue(dev, skb);
-	else if (dev->real_num_tx_queues > 1)
-		queue_index = skb_tx_hash(dev, skb);
+	if (sk_tx_queue_recorded(sk)) {
+		queue_index = sk_tx_queue_get(sk);
+	} else {
+		const struct net_device_ops *ops = dev->netdev_ops;
+
+		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)
+				queue_index = skb_tx_hash(dev, skb);
+
+			if (sk && sk->sk_dst_cache)
+				sk_tx_queue_set(sk, queue_index);
+		}
+	}
 
 	skb_set_queue_mapping(skb, queue_index);
 	return netdev_get_tx_queue(dev, queue_index);
@@ -1934,8 +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;
 				}
@@ -2190,7 +2287,7 @@ static int ing_filter(struct sk_buff *skb)
 	if (MAX_RED_LOOP < ttl++) {
 		printk(KERN_WARNING
 		       "Redir loop detected Dropping packet (%d->%d)\n",
-		       skb->iif, dev->ifindex);
+		       skb->skb_iif, dev->ifindex);
 		return TC_ACT_SHOT;
 	}
 
@@ -2291,15 +2388,15 @@ int netif_receive_skb(struct sk_buff *skb)
 	if (!skb->tstamp.tv64)
 		net_timestamp(skb);
 
-	if (skb->vlan_tci && vlan_hwaccel_do_receive(skb))
+	if (vlan_tx_tag_present(skb) && vlan_hwaccel_do_receive(skb))
 		return NET_RX_SUCCESS;
 
 	/* if we've gotten here through NAPI, check netpoll */
 	if (netpoll_receive_skb(skb))
 		return NET_RX_DROP;
 
-	if (!skb->iif)
-		skb->iif = skb->dev->ifindex;
+	if (!skb->skb_iif)
+		skb->skb_iif = skb->dev->ifindex;
 
 	null_or_orig = NULL;
 	orig_dev = skb->dev;
@@ -2439,7 +2536,7 @@ void napi_gro_flush(struct napi_struct *napi)
 }
 EXPORT_SYMBOL(napi_gro_flush);
 
-int dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
+enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 {
 	struct sk_buff **pp = NULL;
 	struct packet_type *ptype;
@@ -2447,7 +2544,7 @@ int dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 	struct list_head *head = &ptype_base[ntohs(type) & PTYPE_HASH_MASK];
 	int same_flow;
 	int mac_len;
-	int ret;
+	enum gro_result ret;
 
 	if (!(skb->dev->features & NETIF_F_GRO))
 		goto normal;
@@ -2531,7 +2628,8 @@ normal:
 }
 EXPORT_SYMBOL(dev_gro_receive);
 
-static int __napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
+static gro_result_t
+__napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 {
 	struct sk_buff *p;
 
@@ -2548,24 +2646,25 @@ static int __napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 	return dev_gro_receive(napi, skb);
 }
 
-int napi_skb_finish(int ret, struct sk_buff *skb)
+gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb)
 {
-	int err = NET_RX_SUCCESS;
-
 	switch (ret) {
 	case GRO_NORMAL:
-		return netif_receive_skb(skb);
+		if (netif_receive_skb(skb))
+			ret = GRO_DROP;
+		break;
 
 	case GRO_DROP:
-		err = NET_RX_DROP;
-		/* fall through */
-
 	case GRO_MERGED_FREE:
 		kfree_skb(skb);
 		break;
+
+	case GRO_HELD:
+	case GRO_MERGED:
+		break;
 	}
 
-	return err;
+	return ret;
 }
 EXPORT_SYMBOL(napi_skb_finish);
 
@@ -2585,7 +2684,7 @@ void skb_gro_reset_offset(struct sk_buff *skb)
 }
 EXPORT_SYMBOL(skb_gro_reset_offset);
 
-int napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
+gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 {
 	skb_gro_reset_offset(skb);
 
@@ -2604,49 +2703,41 @@ EXPORT_SYMBOL(napi_reuse_skb);
 
 struct sk_buff *napi_get_frags(struct napi_struct *napi)
 {
-	struct net_device *dev = napi->dev;
 	struct sk_buff *skb = napi->skb;
 
 	if (!skb) {
-		skb = netdev_alloc_skb(dev, GRO_MAX_HEAD + NET_IP_ALIGN);
-		if (!skb)
-			goto out;
-
-		skb_reserve(skb, NET_IP_ALIGN);
-
-		napi->skb = skb;
+		skb = netdev_alloc_skb_ip_align(napi->dev, GRO_MAX_HEAD);
+		if (skb)
+			napi->skb = skb;
 	}
-
-out:
 	return skb;
 }
 EXPORT_SYMBOL(napi_get_frags);
 
-int napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb, int ret)
+gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb,
+			       gro_result_t ret)
 {
-	int err = NET_RX_SUCCESS;
-
 	switch (ret) {
 	case GRO_NORMAL:
 	case GRO_HELD:
 		skb->protocol = eth_type_trans(skb, napi->dev);
 
-		if (ret == GRO_NORMAL)
-			return netif_receive_skb(skb);
-
-		skb_gro_pull(skb, -ETH_HLEN);
+		if (ret == GRO_HELD)
+			skb_gro_pull(skb, -ETH_HLEN);
+		else if (netif_receive_skb(skb))
+			ret = GRO_DROP;
 		break;
 
 	case GRO_DROP:
-		err = NET_RX_DROP;
-		/* fall through */
-
 	case GRO_MERGED_FREE:
 		napi_reuse_skb(napi, skb);
 		break;
+
+	case GRO_MERGED:
+		break;
 	}
 
-	return err;
+	return ret;
 }
 EXPORT_SYMBOL(napi_frags_finish);
 
@@ -2687,12 +2778,12 @@ out:
 }
 EXPORT_SYMBOL(napi_frags_skb);
 
-int napi_gro_frags(struct napi_struct *napi)
+gro_result_t napi_gro_frags(struct napi_struct *napi)
 {
 	struct sk_buff *skb = napi_frags_skb(napi);
 
 	if (!skb)
-		return NET_RX_DROP;
+		return GRO_DROP;
 
 	return napi_frags_finish(napi, skb, __napi_gro_receive(napi, skb));
 }
@@ -2937,15 +3028,15 @@ static int dev_ifname(struct net *net, struct ifreq __user *arg)
 	if (copy_from_user(&ifr, arg, sizeof(struct ifreq)))
 		return -EFAULT;
 
-	read_lock(&dev_base_lock);
-	dev = __dev_get_by_index(net, ifr.ifr_ifindex);
+	rcu_read_lock();
+	dev = dev_get_by_index_rcu(net, ifr.ifr_ifindex);
 	if (!dev) {
-		read_unlock(&dev_base_lock);
+		rcu_read_unlock();
 		return -ENODEV;
 	}
 
 	strcpy(ifr.ifr_name, dev->name);
-	read_unlock(&dev_base_lock);
+	rcu_read_unlock();
 
 	if (copy_to_user(arg, &ifr, sizeof(struct ifreq)))
 		return -EFAULT;
@@ -3015,18 +3106,18 @@ static int dev_ifconf(struct net *net, char __user *arg)
  *	in detail.
  */
 void *dev_seq_start(struct seq_file *seq, loff_t *pos)
-	__acquires(dev_base_lock)
+	__acquires(RCU)
 {
 	struct net *net = seq_file_net(seq);
 	loff_t off;
 	struct net_device *dev;
 
-	read_lock(&dev_base_lock);
+	rcu_read_lock();
 	if (!*pos)
 		return SEQ_START_TOKEN;
 
 	off = 1;
-	for_each_netdev(net, dev)
+	for_each_netdev_rcu(net, dev)
 		if (off++ == *pos)
 			return dev;
 
@@ -3035,16 +3126,18 @@ void *dev_seq_start(struct seq_file *seq, loff_t *pos)
 
 void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
-	struct net *net = seq_file_net(seq);
+	struct net_device *dev = (v == SEQ_START_TOKEN) ?
+				  first_net_device(seq_file_net(seq)) :
+				  next_net_device((struct net_device *)v);
+
 	++*pos;
-	return v == SEQ_START_TOKEN ?
-		first_net_device(net) : next_net_device((struct net_device *)v);
+	return rcu_dereference(dev);
 }
 
 void dev_seq_stop(struct seq_file *seq, void *v)
-	__releases(dev_base_lock)
+	__releases(RCU)
 {
-	read_unlock(&dev_base_lock);
+	rcu_read_unlock();
 }
 
 static void dev_seq_printf_stats(struct seq_file *seq, struct net_device *dev)
@@ -4253,12 +4346,12 @@ int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa)
 EXPORT_SYMBOL(dev_set_mac_address);
 
 /*
- *	Perform the SIOCxIFxxx calls, inside read_lock(dev_base_lock)
+ *	Perform the SIOCxIFxxx calls, inside rcu_read_lock()
  */
 static int dev_ifsioc_locked(struct net *net, struct ifreq *ifr, unsigned int cmd)
 {
 	int err;
-	struct net_device *dev = __dev_get_by_name(net, ifr->ifr_name);
+	struct net_device *dev = dev_get_by_name_rcu(net, ifr->ifr_name);
 
 	if (!dev)
 		return -ENODEV;
@@ -4490,9 +4583,9 @@ int dev_ioctl(struct net *net, unsigned int cmd, void __user *arg)
 	case SIOCGIFINDEX:
 	case SIOCGIFTXQLEN:
 		dev_load(net, ifr.ifr_name);
-		read_lock(&dev_base_lock);
+		rcu_read_lock();
 		ret = dev_ifsioc_locked(net, &ifr, cmd);
-		read_unlock(&dev_base_lock);
+		rcu_read_unlock();
 		if (!ret) {
 			if (colon)
 				*colon = ':';
@@ -4635,59 +4728,93 @@ static void net_set_todo(struct net_device *dev)
 	list_add_tail(&dev->todo_list, &net_todo_list);
 }
 
-static void rollback_registered(struct net_device *dev)
+static void rollback_registered_many(struct list_head *head)
 {
+	struct net_device *dev, *aux, *fdev;
+	LIST_HEAD(pernet_list);
+
 	BUG_ON(dev_boot_phase);
 	ASSERT_RTNL();
 
-	/* Some devices call without registering for initialization unwind. */
-	if (dev->reg_state == NETREG_UNINITIALIZED) {
-		printk(KERN_DEBUG "unregister_netdevice: device %s/%p never "
-				  "was registered\n", dev->name, dev);
+	list_for_each_entry(dev, head, unreg_list) {
+		/* Some devices call without registering
+		 * for initialization unwind.
+		 */
+		if (dev->reg_state == NETREG_UNINITIALIZED) {
+			pr_debug("unregister_netdevice: device %s/%p never "
+				 "was registered\n", dev->name, dev);
 
-		WARN_ON(1);
-		return;
-	}
+			WARN_ON(1);
+			return;
+		}
 
-	BUG_ON(dev->reg_state != NETREG_REGISTERED);
+		BUG_ON(dev->reg_state != NETREG_REGISTERED);
 
-	/* If device is running, close it first. */
-	dev_close(dev);
+		/* If device is running, close it first. */
+		dev_close(dev);
 
-	/* And unlink it from device chain. */
-	unlist_netdevice(dev);
+		/* And unlink it from device chain. */
+		unlist_netdevice(dev);
 
-	dev->reg_state = NETREG_UNREGISTERING;
+		dev->reg_state = NETREG_UNREGISTERING;
+	}
 
 	synchronize_net();
 
-	/* Shutdown queueing discipline. */
-	dev_shutdown(dev);
+	list_for_each_entry(dev, head, unreg_list) {
+		/* Shutdown queueing discipline. */
+		dev_shutdown(dev);
 
 
-	/* Notify protocols, that we are about to destroy
-	   this device. They should clean all the things.
-	*/
-	call_netdevice_notifiers(NETDEV_UNREGISTER, dev);
+		/* Notify protocols, that we are about to destroy
+		   this device. They should clean all the things.
+		*/
+		call_netdevice_notifiers(NETDEV_UNREGISTER, dev);
 
-	/*
-	 *	Flush the unicast and multicast chains
-	 */
-	dev_unicast_flush(dev);
-	dev_addr_discard(dev);
+		/*
+		 *	Flush the unicast and multicast chains
+		 */
+		dev_unicast_flush(dev);
+		dev_addr_discard(dev);
 
-	if (dev->netdev_ops->ndo_uninit)
-		dev->netdev_ops->ndo_uninit(dev);
+		if (dev->netdev_ops->ndo_uninit)
+			dev->netdev_ops->ndo_uninit(dev);
 
-	/* Notifier chain MUST detach us from master device. */
-	WARN_ON(dev->master);
+		/* Notifier chain MUST detach us from master device. */
+		WARN_ON(dev->master);
 
-	/* Remove entries from kobject tree */
-	netdev_unregister_kobject(dev);
+		/* Remove entries from kobject tree */
+		netdev_unregister_kobject(dev);
+	}
 
 	synchronize_net();
 
-	dev_put(dev);
+	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)
+{
+	LIST_HEAD(single);
+
+	list_add(&dev->unreg_list, &single);
+	rollback_registered_many(&single);
 }
 
 static void __netdev_init_queue_locks_one(struct net_device *dev,
@@ -4764,8 +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);
 
@@ -4794,26 +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))) {
@@ -4966,6 +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)) {
@@ -4973,6 +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)) {
@@ -5067,6 +5184,32 @@ 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
@@ -5081,25 +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);
 
@@ -5179,6 +5306,8 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name,
 	netdev_init_queues(dev);
 
 	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);
@@ -5243,25 +5372,52 @@ void synchronize_net(void)
 EXPORT_SYMBOL(synchronize_net);
 
 /**
- *	unregister_netdevice - remove device from the kernel
+ *	unregister_netdevice_queue - remove device from the kernel
  *	@dev: device
- *
+ *	@head: list
+
  *	This function shuts down a device interface and removes it
  *	from the kernel tables.
+ *	If head not NULL, device is queued to be unregistered later.
  *
  *	Callers must hold the rtnl semaphore.  You may want
  *	unregister_netdev() instead of this.
  */
 
-void unregister_netdevice(struct net_device *dev)
+void unregister_netdevice_queue(struct net_device *dev, struct list_head *head)
 {
 	ASSERT_RTNL();
 
-	rollback_registered(dev);
-	/* Finish processing unregister after unlock */
-	net_set_todo(dev);
+	if (head) {
+		list_move_tail(&dev->unreg_list, head);
+	} else {
+		rollback_registered(dev);
+		/* Finish processing unregister after unlock */
+		net_set_todo(dev);
+	}
+}
+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)
+{
+	struct net_device *dev;
+
+	if (!list_empty(head)) {
+		rollback_registered_many(head);
+		list_for_each_entry(dev, head, unreg_list)
+			net_set_todo(dev);
+	}
 }
-EXPORT_SYMBOL(unregister_netdevice);
+EXPORT_SYMBOL(unregister_netdevice_many);
 
 /**
  *	unregister_netdev - remove device from the kernel
@@ -5298,8 +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();
@@ -5332,20 +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;
 	}
 
@@ -5369,6 +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
@@ -5381,10 +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);
@@ -5588,7 +5730,7 @@ restart:
 
 		/* Delete virtual devices */
 		if (dev->rtnl_link_ops && dev->rtnl_link_ops->dellink) {
-			dev->rtnl_link_ops->dellink(dev);
+			dev->rtnl_link_ops->dellink(dev, NULL);
 			goto restart;
 		}