16 files changed, 826 insertions, 252 deletions

diff --git a/net/core/datagram.c b/net/core/datagram.c
index 8ab48cd8955..af814e76420 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -48,6 +48,7 @@
 #include <linux/highmem.h>
 #include <linux/spinlock.h>
 #include <linux/slab.h>
+#include <linux/pagemap.h>
 
 #include <net/protocol.h>
 #include <linux/skbuff.h>
@@ -573,6 +574,77 @@ fault:
 }
 EXPORT_SYMBOL(skb_copy_datagram_from_iovec);
 
+/**
+ *	zerocopy_sg_from_iovec - Build a zerocopy datagram from an iovec
+ *	@skb: buffer to copy
+ *	@from: io vector to copy to
+ *	@offset: offset in the io vector to start copying from
+ *	@count: amount of vectors to copy to buffer from
+ *
+ *	The function will first copy up to headlen, and then pin the userspace
+ *	pages and build frags through them.
+ *
+ *	Returns 0, -EFAULT or -EMSGSIZE.
+ *	Note: the iovec is not modified during the copy
+ */
+int zerocopy_sg_from_iovec(struct sk_buff *skb, const struct iovec *from,
+				  int offset, size_t count)
+{
+	int len = iov_length(from, count) - offset;
+	int copy = min_t(int, skb_headlen(skb), len);
+	int size;
+	int i = 0;
+
+	/* copy up to skb headlen */
+	if (skb_copy_datagram_from_iovec(skb, 0, from, offset, copy))
+		return -EFAULT;
+
+	if (len == copy)
+		return 0;
+
+	offset += copy;
+	while (count--) {
+		struct page *page[MAX_SKB_FRAGS];
+		int num_pages;
+		unsigned long base;
+		unsigned long truesize;
+
+		/* Skip over from offset and copied */
+		if (offset >= from->iov_len) {
+			offset -= from->iov_len;
+			++from;
+			continue;
+		}
+		len = from->iov_len - offset;
+		base = (unsigned long)from->iov_base + offset;
+		size = ((base & ~PAGE_MASK) + len + ~PAGE_MASK) >> PAGE_SHIFT;
+		if (i + size > MAX_SKB_FRAGS)
+			return -EMSGSIZE;
+		num_pages = get_user_pages_fast(base, size, 0, &page[i]);
+		if (num_pages != size) {
+			release_pages(&page[i], num_pages, 0);
+			return -EFAULT;
+		}
+		truesize = size * PAGE_SIZE;
+		skb->data_len += len;
+		skb->len += len;
+		skb->truesize += truesize;
+		atomic_add(truesize, &skb->sk->sk_wmem_alloc);
+		while (len) {
+			int off = base & ~PAGE_MASK;
+			int size = min_t(int, len, PAGE_SIZE - off);
+			skb_fill_page_desc(skb, i, page[i], off, size);
+			base += size;
+			len -= size;
+			i++;
+		}
+		offset = 0;
+		++from;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(zerocopy_sg_from_iovec);
+
 static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset,
 				      u8 __user *to, int len,
 				      __wsum *csump)
diff --git a/net/core/dev.c b/net/core/dev.c
index 26755dd40da..5c713f2239c 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -174,7 +174,7 @@ static DEFINE_SPINLOCK(napi_hash_lock);
 static unsigned int napi_gen_id;
 static DEFINE_HASHTABLE(napi_hash, 8);
 
-seqcount_t devnet_rename_seq;
+static seqcount_t devnet_rename_seq;
 
 static inline void dev_base_seq_inc(struct net *net)
 {
@@ -1691,13 +1691,13 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
 		kfree_skb(skb);
 		return NET_RX_DROP;
 	}
-	skb_scrub_packet(skb);
 	skb->protocol = eth_type_trans(skb, dev);
 
 	/* eth_type_trans() can set pkt_type.
-	 * clear pkt_type _after_ calling eth_type_trans()
+	 * call skb_scrub_packet() after it to clear pkt_type _after_ calling
+	 * eth_type_trans().
 	 */
-	skb->pkt_type = PACKET_HOST;
+	skb_scrub_packet(skb, true);
 
 	return netif_rx(skb);
 }
@@ -4367,57 +4367,48 @@ softnet_break:
 	goto out;
 }
 
-struct netdev_upper {
+struct netdev_adjacent {
 	struct net_device *dev;
+
+	/* upper master flag, there can only be one master device per list */
 	bool master;
+
+	/* indicates that this dev is our first-level lower/upper device */
+	bool neighbour;
+
+	/* counter for the number of times this device was added to us */
+	u16 ref_nr;
+
 	struct list_head list;
 	struct rcu_head rcu;
-	struct list_head search_list;
 };
 
-static void __append_search_uppers(struct list_head *search_list,
-				   struct net_device *dev)
+static struct netdev_adjacent *__netdev_find_adj(struct net_device *dev,
+						 struct net_device *adj_dev,
+						 bool upper)
 {
-	struct netdev_upper *upper;
+	struct netdev_adjacent *adj;
+	struct list_head *dev_list;
 
-	list_for_each_entry(upper, &dev->upper_dev_list, list) {
-		/* check if this upper is not already in search list */
-		if (list_empty(&upper->search_list))
-			list_add_tail(&upper->search_list, search_list);
+	dev_list = upper ? &dev->upper_dev_list : &dev->lower_dev_list;
+
+	list_for_each_entry(adj, dev_list, list) {
+		if (adj->dev == adj_dev)
+			return adj;
 	}
+	return NULL;
 }
 
-static bool __netdev_search_upper_dev(struct net_device *dev,
-				      struct net_device *upper_dev)
+static inline struct netdev_adjacent *__netdev_find_upper(struct net_device *dev,
+							  struct net_device *udev)
 {
-	LIST_HEAD(search_list);
-	struct netdev_upper *upper;
-	struct netdev_upper *tmp;
-	bool ret = false;
-
-	__append_search_uppers(&search_list, dev);
-	list_for_each_entry(upper, &search_list, search_list) {
-		if (upper->dev == upper_dev) {
-			ret = true;
-			break;
-		}
-		__append_search_uppers(&search_list, upper->dev);
-	}
-	list_for_each_entry_safe(upper, tmp, &search_list, search_list)
-		INIT_LIST_HEAD(&upper->search_list);
-	return ret;
+	return __netdev_find_adj(dev, udev, true);
 }
 
-static struct netdev_upper *__netdev_find_upper(struct net_device *dev,
-						struct net_device *upper_dev)
+static inline struct netdev_adjacent *__netdev_find_lower(struct net_device *dev,
+							  struct net_device *ldev)
 {
-	struct netdev_upper *upper;
-
-	list_for_each_entry(upper, &dev->upper_dev_list, list) {
-		if (upper->dev == upper_dev)
-			return upper;
-	}
-	return NULL;
+	return __netdev_find_adj(dev, ldev, false);
 }
 
 /**
@@ -4462,7 +4453,7 @@ EXPORT_SYMBOL(netdev_has_any_upper_dev);
  */
 struct net_device *netdev_master_upper_dev_get(struct net_device *dev)
 {
-	struct netdev_upper *upper;
+	struct netdev_adjacent *upper;
 
 	ASSERT_RTNL();
 
@@ -4470,13 +4461,38 @@ struct net_device *netdev_master_upper_dev_get(struct net_device *dev)
 		return NULL;
 
 	upper = list_first_entry(&dev->upper_dev_list,
-				 struct netdev_upper, list);
+				 struct netdev_adjacent, list);
 	if (likely(upper->master))
 		return upper->dev;
 	return NULL;
 }
 EXPORT_SYMBOL(netdev_master_upper_dev_get);
 
+/* netdev_upper_get_next_dev_rcu - Get the next dev from upper list
+ * @dev: device
+ * @iter: list_head ** of the current position
+ *
+ * Gets the next device from the dev's upper list, starting from iter
+ * position. The caller must hold RCU read lock.
+ */
+struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev,
+						 struct list_head **iter)
+{
+	struct netdev_adjacent *upper;
+
+	WARN_ON_ONCE(!rcu_read_lock_held());
+
+	upper = list_entry_rcu((*iter)->next, struct netdev_adjacent, list);
+
+	if (&upper->list == &dev->upper_dev_list)
+		return NULL;
+
+	*iter = &upper->list;
+
+	return upper->dev;
+}
+EXPORT_SYMBOL(netdev_upper_get_next_dev_rcu);
+
 /**
  * netdev_master_upper_dev_get_rcu - Get master upper device
  * @dev: device
@@ -4486,20 +4502,158 @@ EXPORT_SYMBOL(netdev_master_upper_dev_get);
  */
 struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev)
 {
-	struct netdev_upper *upper;
+	struct netdev_adjacent *upper;
 
 	upper = list_first_or_null_rcu(&dev->upper_dev_list,
-				       struct netdev_upper, list);
+				       struct netdev_adjacent, list);
 	if (upper && likely(upper->master))
 		return upper->dev;
 	return NULL;
 }
 EXPORT_SYMBOL(netdev_master_upper_dev_get_rcu);
 
+static int __netdev_adjacent_dev_insert(struct net_device *dev,
+					struct net_device *adj_dev,
+					bool neighbour, bool master,
+					bool upper)
+{
+	struct netdev_adjacent *adj;
+
+	adj = __netdev_find_adj(dev, adj_dev, upper);
+
+	if (adj) {
+		BUG_ON(neighbour);
+		adj->ref_nr++;
+		return 0;
+	}
+
+	adj = kmalloc(sizeof(*adj), GFP_KERNEL);
+	if (!adj)
+		return -ENOMEM;
+
+	adj->dev = adj_dev;
+	adj->master = master;
+	adj->neighbour = neighbour;
+	adj->ref_nr = 1;
+
+	dev_hold(adj_dev);
+	pr_debug("dev_hold for %s, because of %s link added from %s to %s\n",
+		 adj_dev->name, upper ? "upper" : "lower", dev->name,
+		 adj_dev->name);
+
+	if (!upper) {
+		list_add_tail_rcu(&adj->list, &dev->lower_dev_list);
+		return 0;
+	}
+
+	/* Ensure that master upper link is always the first item in list. */
+	if (master)
+		list_add_rcu(&adj->list, &dev->upper_dev_list);
+	else
+		list_add_tail_rcu(&adj->list, &dev->upper_dev_list);
+
+	return 0;
+}
+
+static inline int __netdev_upper_dev_insert(struct net_device *dev,
+					    struct net_device *udev,
+					    bool master, bool neighbour)
+{
+	return __netdev_adjacent_dev_insert(dev, udev, neighbour, master,
+					    true);
+}
+
+static inline int __netdev_lower_dev_insert(struct net_device *dev,
+					    struct net_device *ldev,
+					    bool neighbour)
+{
+	return __netdev_adjacent_dev_insert(dev, ldev, neighbour, false,
+					    false);
+}
+
+void __netdev_adjacent_dev_remove(struct net_device *dev,
+				  struct net_device *adj_dev, bool upper)
+{
+	struct netdev_adjacent *adj;
+
+	if (upper)
+		adj = __netdev_find_upper(dev, adj_dev);
+	else
+		adj = __netdev_find_lower(dev, adj_dev);
+
+	if (!adj)
+		BUG();
+
+	if (adj->ref_nr > 1) {
+		adj->ref_nr--;
+		return;
+	}
+
+	list_del_rcu(&adj->list);
+	pr_debug("dev_put for %s, because of %s link removed from %s to %s\n",
+		 adj_dev->name, upper ? "upper" : "lower", dev->name,
+		 adj_dev->name);
+	dev_put(adj_dev);
+	kfree_rcu(adj, rcu);
+}
+
+static inline void __netdev_upper_dev_remove(struct net_device *dev,
+					     struct net_device *udev)
+{
+	return __netdev_adjacent_dev_remove(dev, udev, true);
+}
+
+static inline void __netdev_lower_dev_remove(struct net_device *dev,
+					     struct net_device *ldev)
+{
+	return __netdev_adjacent_dev_remove(dev, ldev, false);
+}
+
+int __netdev_adjacent_dev_insert_link(struct net_device *dev,
+				      struct net_device *upper_dev,
+				      bool master, bool neighbour)
+{
+	int ret;
+
+	ret = __netdev_upper_dev_insert(dev, upper_dev, master, neighbour);
+	if (ret)
+		return ret;
+
+	ret = __netdev_lower_dev_insert(upper_dev, dev, neighbour);
+	if (ret) {
+		__netdev_upper_dev_remove(dev, upper_dev);
+		return ret;
+	}
+
+	return 0;
+}
+
+static inline int __netdev_adjacent_dev_link(struct net_device *dev,
+					     struct net_device *udev)
+{
+	return __netdev_adjacent_dev_insert_link(dev, udev, false, false);
+}
+
+static inline int __netdev_adjacent_dev_link_neighbour(struct net_device *dev,
+						       struct net_device *udev,
+						       bool master)
+{
+	return __netdev_adjacent_dev_insert_link(dev, udev, master, true);
+}
+
+void __netdev_adjacent_dev_unlink(struct net_device *dev,
+				  struct net_device *upper_dev)
+{
+	__netdev_upper_dev_remove(dev, upper_dev);
+	__netdev_lower_dev_remove(upper_dev, dev);
+}
+
+
 static int __netdev_upper_dev_link(struct net_device *dev,
 				   struct net_device *upper_dev, bool master)
 {
-	struct netdev_upper *upper;
+	struct netdev_adjacent *i, *j, *to_i, *to_j;
+	int ret = 0;
 
 	ASSERT_RTNL();
 
@@ -4507,7 +4661,7 @@ static int __netdev_upper_dev_link(struct net_device *dev,
 		return -EBUSY;
 
 	/* To prevent loops, check if dev is not upper device to upper_dev. */
-	if (__netdev_search_upper_dev(upper_dev, dev))
+	if (__netdev_find_upper(upper_dev, dev))
 		return -EBUSY;
 
 	if (__netdev_find_upper(dev, upper_dev))
@@ -4516,22 +4670,76 @@ static int __netdev_upper_dev_link(struct net_device *dev,
 	if (master && netdev_master_upper_dev_get(dev))
 		return -EBUSY;
 
-	upper = kmalloc(sizeof(*upper), GFP_KERNEL);
-	if (!upper)
-		return -ENOMEM;
+	ret = __netdev_adjacent_dev_link_neighbour(dev, upper_dev, master);
+	if (ret)
+		return ret;
 
-	upper->dev = upper_dev;
-	upper->master = master;
-	INIT_LIST_HEAD(&upper->search_list);
+	/* Now that we linked these devs, make all the upper_dev's
+	 * upper_dev_list visible to every dev's lower_dev_list and vice
+	 * versa, and don't forget the devices itself. All of these
+	 * links are non-neighbours.
+	 */
+	list_for_each_entry(i, &dev->lower_dev_list, list) {
+		list_for_each_entry(j, &upper_dev->upper_dev_list, list) {
+			ret = __netdev_adjacent_dev_link(i->dev, j->dev);
+			if (ret)
+				goto rollback_mesh;
+		}
+	}
+
+	/* add dev to every upper_dev's upper device */
+	list_for_each_entry(i, &upper_dev->upper_dev_list, list) {
+		ret = __netdev_adjacent_dev_link(dev, i->dev);
+		if (ret)
+			goto rollback_upper_mesh;
+	}
+
+	/* add upper_dev to every dev's lower device */
+	list_for_each_entry(i, &dev->lower_dev_list, list) {
+		ret = __netdev_adjacent_dev_link(i->dev, upper_dev);
+		if (ret)
+			goto rollback_lower_mesh;
+	}
 
-	/* Ensure that master upper link is always the first item in list. */
-	if (master)
-		list_add_rcu(&upper->list, &dev->upper_dev_list);
-	else
-		list_add_tail_rcu(&upper->list, &dev->upper_dev_list);
-	dev_hold(upper_dev);
 	call_netdevice_notifiers(NETDEV_CHANGEUPPER, dev);
 	return 0;
+
+rollback_lower_mesh:
+	to_i = i;
+	list_for_each_entry(i, &dev->lower_dev_list, list) {
+		if (i == to_i)
+			break;
+		__netdev_adjacent_dev_unlink(i->dev, upper_dev);
+	}
+
+	i = NULL;
+
+rollback_upper_mesh:
+	to_i = i;
+	list_for_each_entry(i, &upper_dev->upper_dev_list, list) {
+		if (i == to_i)
+			break;
+		__netdev_adjacent_dev_unlink(dev, i->dev);
+	}
+
+	i = j = NULL;
+
+rollback_mesh:
+	to_i = i;
+	to_j = j;
+	list_for_each_entry(i, &dev->lower_dev_list, list) {
+		list_for_each_entry(j, &upper_dev->upper_dev_list, list) {
+			if (i == to_i && j == to_j)
+				break;
+			__netdev_adjacent_dev_unlink(i->dev, j->dev);
+		}
+		if (i == to_i)
+			break;
+	}
+
+	__netdev_adjacent_dev_unlink(dev, upper_dev);
+
+	return ret;
 }
 
 /**
@@ -4580,16 +4788,28 @@ EXPORT_SYMBOL(netdev_master_upper_dev_link);
 void netdev_upper_dev_unlink(struct net_device *dev,
 			     struct net_device *upper_dev)
 {
-	struct netdev_upper *upper;
-
+	struct netdev_adjacent *i, *j;
 	ASSERT_RTNL();
 
-	upper = __netdev_find_upper(dev, upper_dev);
-	if (!upper)
-		return;
-	list_del_rcu(&upper->list);
-	dev_put(upper_dev);
-	kfree_rcu(upper, rcu);
+	__netdev_adjacent_dev_unlink(dev, upper_dev);
+
+	/* Here is the tricky part. We must remove all dev's lower
+	 * devices from all upper_dev's upper devices and vice
+	 * versa, to maintain the graph relationship.
+	 */
+	list_for_each_entry(i, &dev->lower_dev_list, list)
+		list_for_each_entry(j, &upper_dev->upper_dev_list, list)
+			__netdev_adjacent_dev_unlink(i->dev, j->dev);
+
+	/* remove also the devices itself from lower/upper device
+	 * list
+	 */
+	list_for_each_entry(i, &dev->lower_dev_list, list)
+		__netdev_adjacent_dev_unlink(i->dev, upper_dev);
+
+	list_for_each_entry(i, &upper_dev->upper_dev_list, list)
+		__netdev_adjacent_dev_unlink(dev, i->dev);
+
 	call_netdevice_notifiers(NETDEV_CHANGEUPPER, dev);
 }
 EXPORT_SYMBOL(netdev_upper_dev_unlink);
@@ -4989,6 +5209,24 @@ int dev_change_carrier(struct net_device *dev, bool new_carrier)
 EXPORT_SYMBOL(dev_change_carrier);
 
 /**
+ *	dev_get_phys_port_id - Get device physical port ID
+ *	@dev: device
+ *	@ppid: port ID
+ *
+ *	Get device physical port ID
+ */
+int dev_get_phys_port_id(struct net_device *dev,
+			 struct netdev_phys_port_id *ppid)
+{
+	const struct net_device_ops *ops = dev->netdev_ops;
+
+	if (!ops->ndo_get_phys_port_id)
+		return -EOPNOTSUPP;
+	return ops->ndo_get_phys_port_id(dev, ppid);
+}
+EXPORT_SYMBOL(dev_get_phys_port_id);
+
+/**
  *	dev_new_index	-	allocate an ifindex
  *	@net: the applicable net namespace
  *
@@ -5832,6 +6070,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 	INIT_LIST_HEAD(&dev->unreg_list);
 	INIT_LIST_HEAD(&dev->link_watch_list);
 	INIT_LIST_HEAD(&dev->upper_dev_list);
+	INIT_LIST_HEAD(&dev->lower_dev_list);
 	dev->priv_flags = IFF_XMIT_DST_RELEASE;
 	setup(dev);
 
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 21735440c44..2e654138433 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -33,6 +33,9 @@ int fib_default_rule_add(struct fib_rules_ops *ops,
 	r->flags = flags;
 	r->fr_net = hold_net(ops->fro_net);
 
+	r->suppress_prefixlen = -1;
+	r->suppress_ifgroup = -1;
+
 	/* The lock is not required here, the list in unreacheable
 	 * at the moment this function is called */
 	list_add_tail(&r->list, &ops->rules_list);
@@ -226,6 +229,9 @@ jumped:
 		else
 			err = ops->action(rule, fl, flags, arg);
 
+		if (!err && ops->suppress && ops->suppress(rule, arg))
+			continue;
+
 		if (err != -EAGAIN) {
 			if ((arg->flags & FIB_LOOKUP_NOREF) ||
 			    likely(atomic_inc_not_zero(&rule->refcnt))) {
@@ -337,6 +343,15 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh)
 	rule->action = frh->action;
 	rule->flags = frh->flags;
 	rule->table = frh_get_table(frh, tb);
+	if (tb[FRA_SUPPRESS_PREFIXLEN])
+		rule->suppress_prefixlen = nla_get_u32(tb[FRA_SUPPRESS_PREFIXLEN]);
+	else
+		rule->suppress_prefixlen = -1;
+
+	if (tb[FRA_SUPPRESS_IFGROUP])
+		rule->suppress_ifgroup = nla_get_u32(tb[FRA_SUPPRESS_IFGROUP]);
+	else
+		rule->suppress_ifgroup = -1;
 
 	if (!tb[FRA_PRIORITY] && ops->default_pref)
 		rule->pref = ops->default_pref(ops);
@@ -523,6 +538,8 @@ static inline size_t fib_rule_nlmsg_size(struct fib_rules_ops *ops,
 			 + nla_total_size(IFNAMSIZ) /* FRA_OIFNAME */
 			 + nla_total_size(4) /* FRA_PRIORITY */
 			 + nla_total_size(4) /* FRA_TABLE */
+			 + nla_total_size(4) /* FRA_SUPPRESS_PREFIXLEN */
+			 + nla_total_size(4) /* FRA_SUPPRESS_IFGROUP */
 			 + nla_total_size(4) /* FRA_FWMARK */
 			 + nla_total_size(4); /* FRA_FWMASK */
 
@@ -548,6 +565,8 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule,
 	frh->table = rule->table;
 	if (nla_put_u32(skb, FRA_TABLE, rule->table))
 		goto nla_put_failure;
+	if (nla_put_u32(skb, FRA_SUPPRESS_PREFIXLEN, rule->suppress_prefixlen))
+		goto nla_put_failure;
 	frh->res1 = 0;
 	frh->res2 = 0;
 	frh->action = rule->action;
@@ -580,6 +599,12 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule,
 	    (rule->target &&
 	     nla_put_u32(skb, FRA_GOTO, rule->target)))
 		goto nla_put_failure;
+
+	if (rule->suppress_ifgroup != -1) {
+		if (nla_put_u32(skb, FRA_SUPPRESS_IFGROUP, rule->suppress_ifgroup))
+			goto nla_put_failure;
+	}
+
 	if (ops->fill(rule, skb, frh) < 0)
 		goto nla_put_failure;
 
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 00ee068efc1..0ff42f029ac 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -65,6 +65,7 @@ ipv6:
 		nhoff += sizeof(struct ipv6hdr);
 		break;
 	}
+	case __constant_htons(ETH_P_8021AD):
 	case __constant_htons(ETH_P_8021Q): {
 		const struct vlan_hdr *vlan;
 		struct vlan_hdr _vlan;
@@ -139,7 +140,11 @@ ipv6:
 		break;
 	}
 	case IPPROTO_IPIP:
-		goto again;
+		proto = htons(ETH_P_IP);
+		goto ip;
+	case IPPROTO_IPV6:
+		proto = htons(ETH_P_IPV6);
+		goto ipv6;
 	default:
 		break;
 	}
@@ -345,14 +350,9 @@ u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb)
 		if (new_index < 0)
 			new_index = skb_tx_hash(dev, skb);
 
-		if (queue_index != new_index && sk) {
-			struct dst_entry *dst =
-				    rcu_dereference_check(sk->sk_dst_cache, 1);
-
-			if (dst && skb_dst(skb) == dst)
-				sk_tx_queue_set(sk, queue_index);
-
-		}
+		if (queue_index != new_index && sk &&
+		    rcu_access_pointer(sk->sk_dst_cache))
+			sk_tx_queue_set(sk, queue_index);
 
 		queue_index = new_index;
 	}
diff --git a/net/core/iovec.c b/net/core/iovec.c
index de178e46268..b77eeecc001 100644
--- a/net/core/iovec.c
+++ b/net/core/iovec.c
@@ -212,3 +212,27 @@ out_fault:
 	goto out;
 }
 EXPORT_SYMBOL(csum_partial_copy_fromiovecend);
+
+unsigned long iov_pages(const struct iovec *iov, int offset,
+			unsigned long nr_segs)
+{
+	unsigned long seg, base;
+	int pages = 0, len, size;
+
+	while (nr_segs && (offset >= iov->iov_len)) {
+		offset -= iov->iov_len;
+		++iov;
+		--nr_segs;
+	}
+
+	for (seg = 0; seg < nr_segs; seg++) {
+		base = (unsigned long)iov[seg].iov_base + offset;
+		len = iov[seg].iov_len - offset;
+		size = ((base & ~PAGE_MASK) + len + ~PAGE_MASK) >> PAGE_SHIFT;
+		pages += size;
+		offset = 0;
+	}
+
+	return pages;
+}
+EXPORT_SYMBOL(iov_pages);
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 9232c68941a..6072610a867 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1441,16 +1441,18 @@ struct neigh_parms *neigh_parms_alloc(struct net_device *dev,
 		atomic_set(&p->refcnt, 1);
 		p->reachable_time =
 				neigh_rand_reach_time(p->base_reachable_time);
+		dev_hold(dev);
+		p->dev = dev;
+		write_pnet(&p->net, hold_net(net));
+		p->sysctl_table = NULL;
 
 		if (ops->ndo_neigh_setup && ops->ndo_neigh_setup(dev, p)) {
+			release_net(net);
+			dev_put(dev);
 			kfree(p);
 			return NULL;
 		}
 
-		dev_hold(dev);
-		p->dev = dev;
-		write_pnet(&p->net, hold_net(net));
-		p->sysctl_table = NULL;
 		write_lock_bh(&tbl->lock);
 		p->next		= tbl->parms.next;
 		tbl->parms.next = p;
@@ -2757,13 +2759,11 @@ errout:
 		rtnl_set_sk_err(net, RTNLGRP_NEIGH, err);
 }
 
-#ifdef CONFIG_ARPD
 void neigh_app_ns(struct neighbour *n)
 {
 	__neigh_notify(n, RTM_GETNEIGH, NLM_F_REQUEST);
 }
 EXPORT_SYMBOL(neigh_app_ns);
-#endif /* CONFIG_ARPD */
 
 #ifdef CONFIG_SYSCTL
 static int zero;
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 981fed397d1..d954b56b4e4 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -60,12 +60,19 @@ static ssize_t format_##field(const struct net_device *net, char *buf)	\
 {									\
 	return sprintf(buf, format_string, net->field);			\
 }									\
-static ssize_t show_##field(struct device *dev,				\
+static ssize_t field##_show(struct device *dev,				\
 			    struct device_attribute *attr, char *buf)	\
 {									\
 	return netdev_show(dev, attr, buf, format_##field);		\
-}
+}									\
+
+#define NETDEVICE_SHOW_RO(field, format_string)				\
+NETDEVICE_SHOW(field, format_string);					\
+static DEVICE_ATTR_RO(field)
 
+#define NETDEVICE_SHOW_RW(field, format_string)				\
+NETDEVICE_SHOW(field, format_string);					\
+static DEVICE_ATTR_RW(field)
 
 /* use same locking and permission rules as SIF* ioctl's */
 static ssize_t netdev_store(struct device *dev, struct device_attribute *attr,
@@ -96,16 +103,16 @@ static ssize_t netdev_store(struct device *dev, struct device_attribute *attr,
 	return ret;
 }
 
-NETDEVICE_SHOW(dev_id, fmt_hex);
-NETDEVICE_SHOW(addr_assign_type, fmt_dec);
-NETDEVICE_SHOW(addr_len, fmt_dec);
-NETDEVICE_SHOW(iflink, fmt_dec);
-NETDEVICE_SHOW(ifindex, fmt_dec);
-NETDEVICE_SHOW(type, fmt_dec);
-NETDEVICE_SHOW(link_mode, fmt_dec);
+NETDEVICE_SHOW_RO(dev_id, fmt_hex);
+NETDEVICE_SHOW_RO(addr_assign_type, fmt_dec);
+NETDEVICE_SHOW_RO(addr_len, fmt_dec);
+NETDEVICE_SHOW_RO(iflink, fmt_dec);
+NETDEVICE_SHOW_RO(ifindex, fmt_dec);
+NETDEVICE_SHOW_RO(type, fmt_dec);
+NETDEVICE_SHOW_RO(link_mode, fmt_dec);
 
 /* use same locking rules as GIFHWADDR ioctl's */
-static ssize_t show_address(struct device *dev, struct device_attribute *attr,
+static ssize_t address_show(struct device *dev, struct device_attribute *attr,
 			    char *buf)
 {
 	struct net_device *net = to_net_dev(dev);
@@ -117,15 +124,17 @@ static ssize_t show_address(struct device *dev, struct device_attribute *attr,
 	read_unlock(&dev_base_lock);
 	return ret;
 }
+static DEVICE_ATTR_RO(address);
 
-static ssize_t show_broadcast(struct device *dev,
-			    struct device_attribute *attr, char *buf)
+static ssize_t broadcast_show(struct device *dev,
+			      struct device_attribute *attr, char *buf)
 {
 	struct net_device *net = to_net_dev(dev);
 	if (dev_isalive(net))
 		return sysfs_format_mac(buf, net->broadcast, net->addr_len);
 	return -EINVAL;
 }
+static DEVICE_ATTR_RO(broadcast);
 
 static int change_carrier(struct net_device *net, unsigned long new_carrier)
 {
@@ -134,13 +143,13 @@ static int change_carrier(struct net_device *net, unsigned long new_carrier)
 	return dev_change_carrier(net, (bool) new_carrier);
 }
 
-static ssize_t store_carrier(struct device *dev, struct device_attribute *attr,
-			 const char *buf, size_t len)
+static ssize_t carrier_store(struct device *dev, struct device_attribute *attr,
+			     const char *buf, size_t len)
 {
 	return netdev_store(dev, attr, buf, len, change_carrier);
 }
 
-static ssize_t show_carrier(struct device *dev,
+static ssize_t carrier_show(struct device *dev,
 			    struct device_attribute *attr, char *buf)
 {
 	struct net_device *netdev = to_net_dev(dev);
@@ -149,8 +158,9 @@ static ssize_t show_carrier(struct device *dev,
 	}
 	return -EINVAL;
 }
+static DEVICE_ATTR_RW(carrier);
 
-static ssize_t show_speed(struct device *dev,
+static ssize_t speed_show(struct device *dev,
 			  struct device_attribute *attr, char *buf)
 {
 	struct net_device *netdev = to_net_dev(dev);
@@ -167,8 +177,9 @@ static ssize_t show_speed(struct device *dev,
 	rtnl_unlock();
 	return ret;
 }
+static DEVICE_ATTR_RO(speed);
 
-static ssize_t show_duplex(struct device *dev,
+static ssize_t duplex_show(struct device *dev,
 			   struct device_attribute *attr, char *buf)
 {
 	struct net_device *netdev = to_net_dev(dev);
@@ -198,8 +209,9 @@ static ssize_t show_duplex(struct device *dev,
 	rtnl_unlock();
 	return ret;
 }
+static DEVICE_ATTR_RO(duplex);
 
-static ssize_t show_dormant(struct device *dev,
+static ssize_t dormant_show(struct device *dev,
 			    struct device_attribute *attr, char *buf)
 {
 	struct net_device *netdev = to_net_dev(dev);
@@ -209,6 +221,7 @@ static ssize_t show_dormant(struct device *dev,
 
 	return -EINVAL;
 }
+static DEVICE_ATTR_RO(dormant);
 
 static const char *const operstates[] = {
 	"unknown",
@@ -220,7 +233,7 @@ static const char *const operstates[] = {
 	"up"
 };
 
-static ssize_t show_operstate(struct device *dev,
+static ssize_t operstate_show(struct device *dev,
 			      struct device_attribute *attr, char *buf)
 {
 	const struct net_device *netdev = to_net_dev(dev);
@@ -237,35 +250,33 @@ static ssize_t show_operstate(struct device *dev,
 
 	return sprintf(buf, "%s\n", operstates[operstate]);
 }
+static DEVICE_ATTR_RO(operstate);
 
 /* read-write attributes */
-NETDEVICE_SHOW(mtu, fmt_dec);
 
 static int change_mtu(struct net_device *net, unsigned long new_mtu)
 {
 	return dev_set_mtu(net, (int) new_mtu);
 }
 
-static ssize_t store_mtu(struct device *dev, struct device_attribute *attr,
+static ssize_t mtu_store(struct device *dev, struct device_attribute *attr,
 			 const char *buf, size_t len)
 {
 	return netdev_store(dev, attr, buf, len, change_mtu);
 }
-
-NETDEVICE_SHOW(flags, fmt_hex);
+NETDEVICE_SHOW_RW(mtu, fmt_dec);
 
 static int change_flags(struct net_device *net, unsigned long new_flags)
 {
 	return dev_change_flags(net, (unsigned int) new_flags);
 }
 
-static ssize_t store_flags(struct device *dev, struct device_attribute *attr,
+static ssize_t flags_store(struct device *dev, struct device_attribute *attr,
 			   const char *buf, size_t len)
 {
 	return netdev_store(dev, attr, buf, len, change_flags);
 }
-
-NETDEVICE_SHOW(tx_queue_len, fmt_ulong);
+NETDEVICE_SHOW_RW(flags, fmt_hex);
 
 static int change_tx_queue_len(struct net_device *net, unsigned long new_len)
 {
@@ -273,7 +284,7 @@ static int change_tx_queue_len(struct net_device *net, unsigned long new_len)
 	return 0;
 }
 
-static ssize_t store_tx_queue_len(struct device *dev,
+static ssize_t tx_queue_len_store(struct device *dev,
 				  struct device_attribute *attr,
 				  const char *buf, size_t len)
 {
@@ -282,8 +293,9 @@ static ssize_t store_tx_queue_len(struct device *dev,
 
 	return netdev_store(dev, attr, buf, len, change_tx_queue_len);
 }
+NETDEVICE_SHOW_RW(tx_queue_len, fmt_ulong);
 
-static ssize_t store_ifalias(struct device *dev, struct device_attribute *attr,
+static ssize_t ifalias_store(struct device *dev, struct device_attribute *attr,
 			     const char *buf, size_t len)
 {
 	struct net_device *netdev = to_net_dev(dev);
@@ -306,7 +318,7 @@ static ssize_t store_ifalias(struct device *dev, struct device_attribute *attr,
 	return ret < 0 ? ret : len;
 }
 
-static ssize_t show_ifalias(struct device *dev,
+static ssize_t ifalias_show(struct device *dev,
 			    struct device_attribute *attr, char *buf)
 {
 	const struct net_device *netdev = to_net_dev(dev);
@@ -319,8 +331,7 @@ static ssize_t show_ifalias(struct device *dev,
 	rtnl_unlock();
 	return ret;
 }
-
-NETDEVICE_SHOW(group, fmt_dec);
+static DEVICE_ATTR_RW(ifalias);
 
 static int change_group(struct net_device *net, unsigned long new_group)
 {
@@ -328,35 +339,60 @@ static int change_group(struct net_device *net, unsigned long new_group)
 	return 0;
 }
 
-static ssize_t store_group(struct device *dev, struct device_attribute *attr,
-			 const char *buf, size_t len)
+static ssize_t group_store(struct device *dev, struct device_attribute *attr,
+			   const char *buf, size_t len)
 {
 	return netdev_store(dev, attr, buf, len, change_group);
 }
+NETDEVICE_SHOW(group, fmt_dec);
+static DEVICE_ATTR(netdev_group, S_IRUGO | S_IWUSR, group_show, group_store);
+
+static ssize_t phys_port_id_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	struct net_device *netdev = to_net_dev(dev);
+	ssize_t ret = -EINVAL;
 
-static struct device_attribute net_class_attributes[] = {
-	__ATTR(addr_assign_type, S_IRUGO, show_addr_assign_type, NULL),
-	__ATTR(addr_len, S_IRUGO, show_addr_len, NULL),
-	__ATTR(dev_id, S