1 files changed, 163 insertions, 22 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 45fa2f11f84d..f6d8d7fe29ab 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -148,6 +148,9 @@ struct list_head ptype_all __read_mostly;	/* Taps */
 static struct list_head offload_base __read_mostly;
 
 static int netif_rx_internal(struct sk_buff *skb);
+static int call_netdevice_notifiers_info(unsigned long val,
+					 struct net_device *dev,
+					 struct netdev_notifier_info *info);
 
 /*
  * The @dev_base_head list is protected by @dev_base_lock and the rtnl
@@ -937,7 +940,7 @@ bool dev_valid_name(const char *name)
 		return false;
 
 	while (*name) {
-		if (*name == '/' || isspace(*name))
+		if (*name == '/' || *name == ':' || isspace(*name))
 			return false;
 		name++;
 	}
@@ -1207,7 +1210,11 @@ EXPORT_SYMBOL(netdev_features_change);
 void netdev_state_change(struct net_device *dev)
 {
 	if (dev->flags & IFF_UP) {
-		call_netdevice_notifiers(NETDEV_CHANGE, dev);
+		struct netdev_notifier_change_info change_info;
+
+		change_info.flags_changed = 0;
+		call_netdevice_notifiers_info(NETDEV_CHANGE, dev,
+					      &change_info.info);
 		rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL);
 	}
 }
@@ -1702,6 +1709,7 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
 
 	skb_scrub_packet(skb, true);
 	skb->protocol = eth_type_trans(skb, dev);
+	skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
 
 	return netif_rx_internal(skb);
 }
@@ -2289,7 +2297,7 @@ EXPORT_SYMBOL(skb_checksum_help);
 __be16 skb_network_protocol(struct sk_buff *skb, int *depth)
 {
 	__be16 type = skb->protocol;
-	int vlan_depth = ETH_HLEN;
+	int vlan_depth = skb->mac_len;
 
 	/* Tunnel gso handlers can set protocol to ethernet. */
 	if (type == htons(ETH_P_TEB)) {
@@ -2522,11 +2530,14 @@ netdev_features_t netif_skb_dev_features(struct sk_buff *skb,
 	if (skb_shinfo(skb)->gso_segs > dev->gso_max_segs)
 		features &= ~NETIF_F_GSO_MASK;
 
-	if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD)) {
-		struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data;
-		protocol = veh->h_vlan_encapsulated_proto;
-	} else if (!vlan_tx_tag_present(skb)) {
-		return harmonize_features(skb, dev, features);
+	if (!vlan_tx_tag_present(skb)) {
+		if (unlikely(protocol == htons(ETH_P_8021Q) ||
+			     protocol == htons(ETH_P_8021AD))) {
+			struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data;
+			protocol = veh->h_vlan_encapsulated_proto;
+		} else {
+			return harmonize_features(skb, dev, features);
+		}
 	}
 
 	features &= (dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX |
@@ -3547,7 +3558,7 @@ another_round:
 
 	if (skb->protocol == cpu_to_be16(ETH_P_8021Q) ||
 	    skb->protocol == cpu_to_be16(ETH_P_8021AD)) {
-		skb = vlan_untag(skb);
+		skb = skb_vlan_untag(skb);
 		if (unlikely(!skb))
 			goto unlock;
 	}
@@ -3944,6 +3955,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 	}
 	NAPI_GRO_CB(skb)->count = 1;
 	NAPI_GRO_CB(skb)->age = jiffies;
+	NAPI_GRO_CB(skb)->last = skb;
 	skb_shinfo(skb)->gso_size = skb_gro_len(skb);
 	skb->next = napi->gro_list;
 	napi->gro_list = skb;
@@ -4050,6 +4062,9 @@ static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb)
 	skb->vlan_tci = 0;
 	skb->dev = napi->dev;
 	skb->skb_iif = 0;
+	skb->encapsulation = 0;
+	skb_shinfo(skb)->gso_type = 0;
+	skb->truesize = SKB_TRUESIZE(skb_end_offset(skb));
 
 	napi->skb = skb;
 }
@@ -4605,6 +4620,32 @@ void *netdev_lower_get_next_private_rcu(struct net_device *dev,
 EXPORT_SYMBOL(netdev_lower_get_next_private_rcu);
 
 /**
+ * netdev_lower_get_next - Get the next device from the lower neighbour
+ *                         list
+ * @dev: device
+ * @iter: list_head ** of the current position
+ *
+ * Gets the next netdev_adjacent from the dev's lower neighbour
+ * list, starting from iter position. The caller must hold RTNL lock or
+ * its own locking that guarantees that the neighbour lower
+ * list will remain unchainged.
+ */
+void *netdev_lower_get_next(struct net_device *dev, struct list_head **iter)
+{
+	struct netdev_adjacent *lower;
+
+	lower = list_entry((*iter)->next, struct netdev_adjacent, list);
+
+	if (&lower->list == &dev->adj_list.lower)
+		return NULL;
+
+	*iter = &lower->list;
+
+	return lower->dev;
+}
+EXPORT_SYMBOL(netdev_lower_get_next);
+
+/**
  * netdev_lower_get_first_private_rcu - Get the first ->private from the
  *				       lower neighbour list, RCU
  *				       variant
@@ -4664,9 +4705,14 @@ static void netdev_adjacent_sysfs_del(struct net_device *dev,
 	sysfs_remove_link(&(dev->dev.kobj), linkname);
 }
 
-#define netdev_adjacent_is_neigh_list(dev, dev_list) \
-		(dev_list == &dev->adj_list.upper || \
-		 dev_list == &dev->adj_list.lower)
+static inline bool netdev_adjacent_is_neigh_list(struct net_device *dev,
+						 struct net_device *adj_dev,
+						 struct list_head *dev_list)
+{
+	return (dev_list == &dev->adj_list.upper ||
+		dev_list == &dev->adj_list.lower) &&
+		net_eq(dev_net(dev), dev_net(adj_dev));
+}
 
 static int __netdev_adjacent_dev_insert(struct net_device *dev,
 					struct net_device *adj_dev,
@@ -4696,7 +4742,7 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev,
 	pr_debug("dev_hold for %s, because of link added from %s to %s\n",
 		 adj_dev->name, dev->name, adj_dev->name);
 
-	if (netdev_adjacent_is_neigh_list(dev, dev_list)) {
+	if (netdev_adjacent_is_neigh_list(dev, adj_dev, dev_list)) {
 		ret = netdev_adjacent_sysfs_add(dev, adj_dev, dev_list);
 		if (ret)
 			goto free_adj;
@@ -4717,7 +4763,7 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev,
 	return 0;
 
 remove_symlinks:
-	if (netdev_adjacent_is_neigh_list(dev, dev_list))
+	if (netdev_adjacent_is_neigh_list(dev, adj_dev, dev_list))
 		netdev_adjacent_sysfs_del(dev, adj_dev->name, dev_list);
 free_adj:
 	kfree(adj);
@@ -4750,7 +4796,7 @@ static void __netdev_adjacent_dev_remove(struct net_device *dev,
 	if (adj->master)
 		sysfs_remove_link(&(dev->dev.kobj), "master");
 
-	if (netdev_adjacent_is_neigh_list(dev, dev_list))
+	if (netdev_adjacent_is_neigh_list(dev, adj_dev, dev_list))
 		netdev_adjacent_sysfs_del(dev, adj_dev->name, dev_list);
 
 	list_del_rcu(&adj->list);
@@ -5020,11 +5066,65 @@ void netdev_upper_dev_unlink(struct net_device *dev,
 }
 EXPORT_SYMBOL(netdev_upper_dev_unlink);
 
+void netdev_adjacent_add_links(struct net_device *dev)
+{
+	struct netdev_adjacent *iter;
+
+	struct net *net = dev_net(dev);
+
+	list_for_each_entry(iter, &dev->adj_list.upper, list) {
+		if (!net_eq(net,dev_net(iter->dev)))
+			continue;
+		netdev_adjacent_sysfs_add(iter->dev, dev,
+					  &iter->dev->adj_list.lower);
+		netdev_adjacent_sysfs_add(dev, iter->dev,
+					  &dev->adj_list.upper);
+	}
+
+	list_for_each_entry(iter, &dev->adj_list.lower, list) {
+		if (!net_eq(net,dev_net(iter->dev)))
+			continue;
+		netdev_adjacent_sysfs_add(iter->dev, dev,
+					  &iter->dev->adj_list.upper);
+		netdev_adjacent_sysfs_add(dev, iter->dev,
+					  &dev->adj_list.lower);
+	}
+}
+
+void netdev_adjacent_del_links(struct net_device *dev)
+{
+	struct netdev_adjacent *iter;
+
+	struct net *net = dev_net(dev);
+
+	list_for_each_entry(iter, &dev->adj_list.upper, list) {
+		if (!net_eq(net,dev_net(iter->dev)))
+			continue;
+		netdev_adjacent_sysfs_del(iter->dev, dev->name,
+					  &iter->dev->adj_list.lower);
+		netdev_adjacent_sysfs_del(dev, iter->dev->name,
+					  &dev->adj_list.upper);
+	}
+
+	list_for_each_entry(iter, &dev->adj_list.lower, list) {
+		if (!net_eq(net,dev_net(iter->dev)))
+			continue;
+		netdev_adjacent_sysfs_del(iter->dev, dev->name,
+					  &iter->dev->adj_list.upper);
+		netdev_adjacent_sysfs_del(dev, iter->dev->name,
+					  &dev->adj_list.lower);
+	}
+}
+
 void netdev_adjacent_rename_links(struct net_device *dev, char *oldname)
 {
 	struct netdev_adjacent *iter;
 
+	struct net *net = dev_net(dev);
+
 	list_for_each_entry(iter, &dev->adj_list.upper, list) {
+		if (!net_eq(net,dev_net(iter->dev)))
+			continue;
 		netdev_adjacent_sysfs_del(iter->dev, oldname,
 					  &iter->dev->adj_list.lower);
 		netdev_adjacent_sysfs_add(iter->dev, dev,
@@ -5032,6 +5132,8 @@ void netdev_adjacent_rename_links(struct net_device *dev, char *oldname)
 	}
 
 	list_for_each_entry(iter, &dev->adj_list.lower, list) {
+		if (!net_eq(net,dev_net(iter->dev)))
+			continue;
 		netdev_adjacent_sysfs_del(iter->dev, oldname,
 					  &iter->dev->adj_list.upper);
 		netdev_adjacent_sysfs_add(iter->dev, dev,
@@ -5054,6 +5156,30 @@ void *netdev_lower_dev_get_private(struct net_device *dev,
 }
 EXPORT_SYMBOL(netdev_lower_dev_get_private);
 
+
+int dev_get_nest_level(struct net_device *dev,
+		       bool (*type_check)(struct net_device *dev))
+{
+	struct net_device *lower = NULL;
+	struct list_head *iter;
+	int max_nest = -1;
+	int nest;
+
+	ASSERT_RTNL();
+
+	netdev_for_each_lower_dev(dev, lower, iter) {
+		nest = dev_get_nest_level(lower, type_check);
+		if (max_nest < nest)
+			max_nest = nest;
+	}
+
+	if (type_check(dev))
+		max_nest++;
+
+	return max_nest;
+}
+EXPORT_SYMBOL(dev_get_nest_level);
+
 static void dev_change_rx_flags(struct net_device *dev, int flags)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
@@ -5523,7 +5649,7 @@ static int dev_new_index(struct net *net)
 
 /* Delayed registration/unregisteration */
 static LIST_HEAD(net_todo_list);
-static DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq);
+DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq);
 
 static void net_set_todo(struct net_device *dev)
 {
@@ -6496,6 +6622,9 @@ EXPORT_SYMBOL(unregister_netdevice_queue);
 /**
  *	unregister_netdevice_many - unregister many devices
  *	@head: list of devices
+ *
+ *  Note: As most callers use a stack allocated list_head,
+ *  we force a list_del() to make sure stack wont be corrupted later.
  */
 void unregister_netdevice_many(struct list_head *head)
 {
@@ -6505,6 +6634,7 @@ void unregister_netdevice_many(struct list_head *head)
 		rollback_registered_many(head);
 		list_for_each_entry(dev, head, unreg_list)
 			net_set_todo(dev);
+		list_del(head);
 	}
 }
 EXPORT_SYMBOL(unregister_netdevice_many);
@@ -6610,6 +6740,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char
 
 	/* Send a netdev-removed uevent to the old namespace */
 	kobject_uevent(&dev->dev.kobj, KOBJ_REMOVE);
+	netdev_adjacent_del_links(dev);
 
 	/* Actually switch the network namespace */
 	dev_net_set(dev, net);
@@ -6624,6 +6755,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char
 
 	/* Send a netdev-add uevent to the new namespace */
 	kobject_uevent(&dev->dev.kobj, KOBJ_ADD);
+	netdev_adjacent_add_links(dev);
 
 	/* Fixup kobjects */
 	err = device_rename(&dev->dev, dev->name);
@@ -6680,10 +6812,20 @@ static int dev_cpu_callback(struct notifier_block *nfb,
 		oldsd->output_queue = NULL;
 		oldsd->output_queue_tailp = &oldsd->output_queue;
 	}
-	/* Append NAPI poll list from offline CPU. */
-	if (!list_empty(&oldsd->poll_list)) {
-		list_splice_init(&oldsd->poll_list, &sd->poll_list);
-		raise_softirq_irqoff(NET_RX_SOFTIRQ);
+	/* Append NAPI poll list from offline CPU, with one exception :
+	 * process_backlog() must be called by cpu owning percpu backlog.
+	 * We properly handle process_queue & input_pkt_queue later.
+	 */
+	while (!list_empty(&oldsd->poll_list)) {
+		struct napi_struct *napi = list_first_entry(&oldsd->poll_list,
+							    struct napi_struct,
+							    poll_list);
+
+		list_del_init(&napi->poll_list);
+		if (napi->poll == process_backlog)
+			napi->state = 0;
+		else
+			____napi_schedule(sd, napi);
 	}
 
 	raise_softirq_irqoff(NET_TX_SOFTIRQ);
@@ -6694,7 +6836,7 @@ static int dev_cpu_callback(struct notifier_block *nfb,
 		netif_rx_internal(skb);
 		input_queue_head_incr(oldsd);
 	}
-	while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) {
+	while ((skb = skb_dequeue(&oldsd->input_pkt_queue))) {
 		netif_rx_internal(skb);
 		input_queue_head_incr(oldsd);
 	}
@@ -6960,7 +7102,6 @@ static void __net_exit default_device_exit_batch(struct list_head *net_list)
 		}
 	}
 	unregister_netdevice_many(&dev_kill_list);
-	list_del(&dev_kill_list);
 	rtnl_unlock();
 }