1 files changed, 142 insertions, 156 deletions

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index becb048d18d4..ceff71d24f8e 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -99,10 +99,7 @@ static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old)
 	if (!(rt->dst.flags & DST_HOST))
 		return NULL;
 
-	if (!rt->rt6i_peer)
-		rt6_bind_peer(rt, 1);
-
-	peer = rt->rt6i_peer;
+	peer = rt6_get_peer_create(rt);
 	if (peer) {
 		u32 *old_p = __DST_METRICS_PTR(old);
 		unsigned long prev, new;
@@ -123,21 +120,27 @@ static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old)
 	return p;
 }
 
-static inline const void *choose_neigh_daddr(struct rt6_info *rt, const void *daddr)
+static inline const void *choose_neigh_daddr(struct rt6_info *rt,
+					     struct sk_buff *skb,
+					     const void *daddr)
 {
 	struct in6_addr *p = &rt->rt6i_gateway;
 
 	if (!ipv6_addr_any(p))
 		return (const void *) p;
+	else if (skb)
+		return &ipv6_hdr(skb)->daddr;
 	return daddr;
 }
 
-static struct neighbour *ip6_neigh_lookup(const struct dst_entry *dst, const void *daddr)
+static struct neighbour *ip6_neigh_lookup(const struct dst_entry *dst,
+					  struct sk_buff *skb,
+					  const void *daddr)
 {
 	struct rt6_info *rt = (struct rt6_info *) dst;
 	struct neighbour *n;
 
-	daddr = choose_neigh_daddr(rt, daddr);
+	daddr = choose_neigh_daddr(rt, skb, daddr);
 	n = __ipv6_neigh_lookup(&nd_tbl, dst->dev, daddr);
 	if (n)
 		return n;
@@ -152,7 +155,7 @@ static int rt6_bind_neighbour(struct rt6_info *rt, struct net_device *dev)
 		if (IS_ERR(n))
 			return PTR_ERR(n);
 	}
-	dst_set_neighbour(&rt->dst, n);
+	rt->n = n;
 
 	return 0;
 }
@@ -261,16 +264,19 @@ static struct rt6_info ip6_blk_hole_entry_template = {
 #endif
 
 /* allocate dst with ip6_dst_ops */
-static inline struct rt6_info *ip6_dst_alloc(struct dst_ops *ops,
+static inline struct rt6_info *ip6_dst_alloc(struct net *net,
 					     struct net_device *dev,
-					     int flags)
+					     int flags,
+					     struct fib6_table *table)
 {
-	struct rt6_info *rt = dst_alloc(ops, dev, 0, 0, flags);
+	struct rt6_info *rt = dst_alloc(&net->ipv6.ip6_dst_ops, dev,
+					0, 0, flags);
 
-	if (rt)
+	if (rt) {
 		memset(&rt->rt6i_table, 0,
 		       sizeof(*rt) - sizeof(struct dst_entry));
-
+		rt6_init_peer(rt, table ? &table->tb6_peers : net->ipv6.peers);
+	}
 	return rt;
 }
 
@@ -278,7 +284,9 @@ static void ip6_dst_destroy(struct dst_entry *dst)
 {
 	struct rt6_info *rt = (struct rt6_info *)dst;
 	struct inet6_dev *idev = rt->rt6i_idev;
-	struct inet_peer *peer = rt->rt6i_peer;
+
+	if (rt->n)
+		neigh_release(rt->n);
 
 	if (!(rt->dst.flags & DST_HOST))
 		dst_destroy_metrics_generic(dst);
@@ -291,8 +299,8 @@ static void ip6_dst_destroy(struct dst_entry *dst)
 	if (!(rt->rt6i_flags & RTF_EXPIRES) && dst->from)
 		dst_release(dst->from);
 
-	if (peer) {
-		rt->rt6i_peer = NULL;
+	if (rt6_has_peer(rt)) {
+		struct inet_peer *peer = rt6_peer_ptr(rt);
 		inet_putpeer(peer);
 	}
 }
@@ -306,13 +314,20 @@ static u32 rt6_peer_genid(void)
 
 void rt6_bind_peer(struct rt6_info *rt, int create)
 {
+	struct inet_peer_base *base;
 	struct inet_peer *peer;
 
-	peer = inet_getpeer_v6(&rt->rt6i_dst.addr, create);
-	if (peer && cmpxchg(&rt->rt6i_peer, NULL, peer) != NULL)
-		inet_putpeer(peer);
-	else
-		rt->rt6i_peer_genid = rt6_peer_genid();
+	base = inetpeer_base_ptr(rt->_rt6i_peer);
+	if (!base)
+		return;
+
+	peer = inet_getpeer_v6(base, &rt->rt6i_dst.addr, create);
+	if (peer) {
+		if (!rt6_set_peer(rt, peer))
+			inet_putpeer(peer);
+		else
+			rt->rt6i_peer_genid = rt6_peer_genid();
+	}
 }
 
 static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
@@ -323,12 +338,19 @@ static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
 	struct net_device *loopback_dev =
 		dev_net(dev)->loopback_dev;
 
-	if (dev != loopback_dev && idev && idev->dev == dev) {
-		struct inet6_dev *loopback_idev =
-			in6_dev_get(loopback_dev);
-		if (loopback_idev) {
-			rt->rt6i_idev = loopback_idev;
-			in6_dev_put(idev);
+	if (dev != loopback_dev) {
+		if (idev && idev->dev == dev) {
+			struct inet6_dev *loopback_idev =
+				in6_dev_get(loopback_dev);
+			if (loopback_idev) {
+				rt->rt6i_idev = loopback_idev;
+				in6_dev_put(idev);
+			}
+		}
+		if (rt->n && rt->n->dev == dev) {
+			rt->n->dev = loopback_dev;
+			dev_hold(loopback_dev);
+			dev_put(dev);
 		}
 	}
 }
@@ -418,7 +440,7 @@ static void rt6_probe(struct rt6_info *rt)
 	 * to no more than one per minute.
 	 */
 	rcu_read_lock();
-	neigh = rt ? dst_get_neighbour_noref(&rt->dst) : NULL;
+	neigh = rt ? rt->n : NULL;
 	if (!neigh || (neigh->nud_state & NUD_VALID))
 		goto out;
 	read_lock_bh(&neigh->lock);
@@ -465,7 +487,7 @@ static inline int rt6_check_neigh(struct rt6_info *rt)
 	int m;
 
 	rcu_read_lock();
-	neigh = dst_get_neighbour_noref(&rt->dst);
+	neigh = rt->n;
 	if (rt->rt6i_flags & RTF_NONEXTHOP ||
 	    !(rt->rt6i_flags & RTF_GATEWAY))
 		m = 1;
@@ -812,7 +834,7 @@ static struct rt6_info *rt6_alloc_clone(struct rt6_info *ort,
 
 	if (rt) {
 		rt->rt6i_flags |= RTF_CACHE;
-		dst_set_neighbour(&rt->dst, neigh_clone(dst_get_neighbour_noref_raw(&ort->dst)));
+		rt->n = neigh_clone(ort->n);
 	}
 	return rt;
 }
@@ -846,7 +868,7 @@ restart:
 	dst_hold(&rt->dst);
 	read_unlock_bh(&table->tb6_lock);
 
-	if (!dst_get_neighbour_noref_raw(&rt->dst) && !(rt->rt6i_flags & RTF_NONEXTHOP))
+	if (!rt->n && !(rt->rt6i_flags & RTF_NONEXTHOP))
 		nrt = rt6_alloc_cow(rt, &fl6->daddr, &fl6->saddr);
 	else if (!(rt->dst.flags & DST_HOST))
 		nrt = rt6_alloc_clone(rt, &fl6->daddr);
@@ -931,6 +953,8 @@ struct dst_entry * ip6_route_output(struct net *net, const struct sock *sk,
 {
 	int flags = 0;
 
+	fl6->flowi6_iif = net->loopback_dev->ifindex;
+
 	if ((sk && sk->sk_bound_dev_if) || rt6_need_strict(&fl6->daddr))
 		flags |= RT6_LOOKUP_F_IFACE;
 
@@ -952,6 +976,7 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori
 	rt = dst_alloc(&ip6_dst_blackhole_ops, ort->dst.dev, 1, 0, 0);
 	if (rt) {
 		memset(&rt->rt6i_table, 0, sizeof(*rt) - sizeof(struct dst_entry));
+		rt6_init_peer(rt, net->ipv6.peers);
 
 		new = &rt->dst;
 
@@ -996,7 +1021,7 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie)
 
 	if (rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie)) {
 		if (rt->rt6i_peer_genid != rt6_peer_genid()) {
-			if (!rt->rt6i_peer)
+			if (!rt6_has_peer(rt))
 				rt6_bind_peer(rt, 0);
 			rt->rt6i_peer_genid = rt6_peer_genid();
 		}
@@ -1042,7 +1067,10 @@ static void ip6_rt_update_pmtu(struct dst_entry *dst, u32 mtu)
 {
 	struct rt6_info *rt6 = (struct rt6_info*)dst;
 
+	dst_confirm(dst);
 	if (mtu < dst_mtu(dst) && rt6->rt6i_dst.plen == 128) {
+		struct net *net = dev_net(dst->dev);
+
 		rt6->rt6i_flags |= RTF_MODIFIED;
 		if (mtu < IPV6_MIN_MTU) {
 			u32 features = dst_metric(dst, RTAX_FEATURES);
@@ -1051,9 +1079,39 @@ static void ip6_rt_update_pmtu(struct dst_entry *dst, u32 mtu)
 			dst_metric_set(dst, RTAX_FEATURES, features);
 		}
 		dst_metric_set(dst, RTAX_MTU, mtu);
+		rt6_update_expires(rt6, net->ipv6.sysctl.ip6_rt_mtu_expires);
 	}
 }
 
+void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,
+		     int oif, u32 mark)
+{
+	const struct ipv6hdr *iph = (struct ipv6hdr *) skb->data;
+	struct dst_entry *dst;
+	struct flowi6 fl6;
+
+	memset(&fl6, 0, sizeof(fl6));
+	fl6.flowi6_oif = oif;
+	fl6.flowi6_mark = mark;
+	fl6.flowi6_flags = FLOWI_FLAG_PRECOW_METRICS;
+	fl6.daddr = iph->daddr;
+	fl6.saddr = iph->saddr;
+	fl6.flowlabel = (*(__be32 *) iph) & IPV6_FLOWINFO_MASK;
+
+	dst = ip6_route_output(net, NULL, &fl6);
+	if (!dst->error)
+		ip6_rt_update_pmtu(dst, ntohl(mtu));
+	dst_release(dst);
+}
+EXPORT_SYMBOL_GPL(ip6_update_pmtu);
+
+void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu)
+{
+	ip6_update_pmtu(skb, sock_net(sk), mtu,
+			sk->sk_bound_dev_if, sk->sk_mark);
+}
+EXPORT_SYMBOL_GPL(ip6_sk_update_pmtu);
+
 static unsigned int ip6_default_advmss(const struct dst_entry *dst)
 {
 	struct net_device *dev = dst->dev;
@@ -1110,7 +1168,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev,
 	if (unlikely(!idev))
 		return ERR_PTR(-ENODEV);
 
-	rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, dev, 0);
+	rt = ip6_dst_alloc(net, dev, 0, NULL);
 	if (unlikely(!rt)) {
 		in6_dev_put(idev);
 		dst = ERR_PTR(-ENOMEM);
@@ -1120,7 +1178,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev,
 	if (neigh)
 		neigh_hold(neigh);
 	else {
-		neigh = ip6_neigh_lookup(&rt->dst, &fl6->daddr);
+		neigh = ip6_neigh_lookup(&rt->dst, NULL, &fl6->daddr);
 		if (IS_ERR(neigh)) {
 			in6_dev_put(idev);
 			dst_free(&rt->dst);
@@ -1130,7 +1188,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev,
 
 	rt->dst.flags |= DST_HOST;
 	rt->dst.output  = ip6_output;
-	dst_set_neighbour(&rt->dst, neigh);
+	rt->n = neigh;
 	atomic_set(&rt->dst.__refcnt, 1);
 	rt->rt6i_dst.addr = fl6->daddr;
 	rt->rt6i_dst.plen = 128;
@@ -1292,7 +1350,7 @@ int ip6_route_add(struct fib6_config *cfg)
 	if (!table)
 		goto out;
 
-	rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, NULL, DST_NOCOUNT);
+	rt = ip6_dst_alloc(net, NULL, DST_NOCOUNT, table);
 
 	if (!rt) {
 		err = -ENOMEM;
@@ -1639,6 +1697,7 @@ void rt6_redirect(const struct in6_addr *dest, const struct in6_addr *src,
 	struct rt6_info *rt, *nrt = NULL;
 	struct netevent_redirect netevent;
 	struct net *net = dev_net(neigh->dev);
+	struct neighbour *old_neigh;
 
 	rt = ip6_route_redirect(dest, src, saddr, neigh->dev);
 
@@ -1666,7 +1725,8 @@ void rt6_redirect(const struct in6_addr *dest, const struct in6_addr *src,
 	dst_confirm(&rt->dst);
 
 	/* Duplicate redirect: silently ignore. */
-	if (neigh == dst_get_neighbour_noref_raw(&rt->dst))
+	old_neigh = rt->n;
+	if (neigh == old_neigh)
 		goto out;
 
 	nrt = ip6_rt_copy(rt, dest);
@@ -1678,13 +1738,16 @@ void rt6_redirect(const struct in6_addr *dest, const struct in6_addr *src,
 		nrt->rt6i_flags &= ~RTF_GATEWAY;
 
 	nrt->rt6i_gateway = *(struct in6_addr *)neigh->primary_key;
-	dst_set_neighbour(&nrt->dst, neigh_clone(neigh));
+	nrt->n = neigh_clone(neigh);
 
 	if (ip6_ins_rt(nrt))
 		goto out;
 
 	netevent.old = &rt->dst;
+	netevent.old_neigh = old_neigh;
 	netevent.new = &nrt->dst;
+	netevent.new_neigh = neigh;
+	netevent.daddr = dest;
 	call_netevent_notifiers(NETEVENT_REDIRECT, &netevent);
 
 	if (rt->rt6i_flags & RTF_CACHE) {
@@ -1697,116 +1760,6 @@ out:
 }
 
 /*
- *	Handle ICMP "packet too big" messages
- *	i.e. Path MTU discovery
- */
-
-static void rt6_do_pmtu_disc(const struct in6_addr *daddr, const struct in6_addr *saddr,
-			     struct net *net, u32 pmtu, int ifindex)
-{
-	struct rt6_info *rt, *nrt;
-	int allfrag = 0;
-again:
-	rt = rt6_lookup(net, daddr, saddr, ifindex, 0);
-	if (!rt)
-		return;
-
-	if (rt6_check_expired(rt)) {
-		ip6_del_rt(rt);
-		goto again;
-	}
-
-	if (pmtu >= dst_mtu(&rt->dst))
-		goto out;
-
-	if (pmtu < IPV6_MIN_MTU) {
-		/*
-		 * According to RFC2460, PMTU is set to the IPv6 Minimum Link
-		 * MTU (1280) and a fragment header should always be included
-		 * after a node receiving Too Big message reporting PMTU is
-		 * less than the IPv6 Minimum Link MTU.
-		 */
-		pmtu = IPV6_MIN_MTU;
-		allfrag = 1;
-	}
-
-	/* New mtu received -> path was valid.
-	   They are sent only in response to data packets,
-	   so that this nexthop apparently is reachable. --ANK
-	 */
-	dst_confirm(&rt->dst);
-
-	/* Host route. If it is static, it would be better
-	   not to override it, but add new one, so that
-	   when cache entry will expire old pmtu
-	   would return automatically.
-	 */
-	if (rt->rt6i_flags & RTF_CACHE) {
-		dst_metric_set(&rt->dst, RTAX_MTU, pmtu);
-		if (allfrag) {
-			u32 features = dst_metric(&rt->dst, RTAX_FEATURES);
-			features |= RTAX_FEATURE_ALLFRAG;
-			dst_metric_set(&rt->dst, RTAX_FEATURES, features);
-		}
-		rt6_update_expires(rt, net->ipv6.sysctl.ip6_rt_mtu_expires);
-		rt->rt6i_flags |= RTF_MODIFIED;
-		goto out;
-	}
-
-	/* Network route.
-	   Two cases are possible:
-	   1. It is connected route. Action: COW
-	   2. It is gatewayed route or NONEXTHOP route. Action: clone it.
-	 */
-	if (!dst_get_neighbour_noref_raw(&rt->dst) && !(rt->rt6i_flags & RTF_NONEXTHOP))
-		nrt = rt6_alloc_cow(rt, daddr, saddr);
-	else
-		nrt = rt6_alloc_clone(rt, daddr);
-
-	if (nrt) {
-		dst_metric_set(&nrt->dst, RTAX_MTU, pmtu);
-		if (allfrag) {
-			u32 features = dst_metric(&nrt->dst, RTAX_FEATURES);
-			features |= RTAX_FEATURE_ALLFRAG;
-			dst_metric_set(&nrt->dst, RTAX_FEATURES, features);
-		}
-
-		/* According to RFC 1981, detecting PMTU increase shouldn't be
-		 * happened within 5 mins, the recommended timer is 10 mins.
-		 * Here this route expiration time is set to ip6_rt_mtu_expires
-		 * which is 10 mins. After 10 mins the decreased pmtu is expired
-		 * and detecting PMTU increase will be automatically happened.
-		 */
-		rt6_update_expires(nrt, net->ipv6.sysctl.ip6_rt_mtu_expires);
-		nrt->rt6i_flags |= RTF_DYNAMIC;
-		ip6_ins_rt(nrt);
-	}
-out:
-	dst_release(&rt->dst);
-}
-
-void rt6_pmtu_discovery(const struct in6_addr *daddr, const struct in6_addr *saddr,
-			struct net_device *dev, u32 pmtu)
-{
-	struct net *net = dev_net(dev);
-
-	/*
-	 * RFC 1981 states that a node "MUST reduce the size of the packets it
-	 * is sending along the path" that caused the Packet Too Big message.
-	 * Since it's not possible in the general case to determine which
-	 * interface was used to send the original packet, we update the MTU
-	 * on the interface that will be used to send future packets. We also
-	 * update the MTU on the interface that received the Packet Too Big in
-	 * case the original packet was forced out that interface with
-	 * SO_BINDTODEVICE or similar. This is the next best thing to the
-	 * correct behaviour, which would be to update the MTU on all
-	 * interfaces.
-	 */
-	rt6_do_pmtu_disc(daddr, saddr, net, pmtu, 0);
-	rt6_do_pmtu_disc(daddr, saddr, net, pmtu, dev->ifindex);
-}
-
-/*
  *	Misc support functions
  */
 
@@ -1814,8 +1767,8 @@ static struct rt6_info *ip6_rt_copy(struct rt6_info *ort,
 				    const struct in6_addr *dest)
 {
 	struct net *net = dev_net(ort->dst.dev);
-	struct rt6_info *rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops,
-					    ort->dst.dev, 0);
+	struct rt6_info *rt = ip6_dst_alloc(net, ort->dst.dev, 0,
+					    ort->rt6i_table);
 
 	if (rt) {
 		rt->dst.input = ort->dst.input;
@@ -2099,8 +2052,7 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
 				    bool anycast)
 {
 	struct net *net = dev_net(idev->dev);
-	struct rt6_info *rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops,
-					    net->loopback_dev, 0);
+	struct rt6_info *rt = ip6_dst_alloc(net, net->loopback_dev, 0, NULL);
 	int err;
 
 	if (!rt) {
@@ -2500,7 +2452,7 @@ static int rt6_fill_node(struct net *net,
 		goto nla_put_failure;
 
 	rcu_read_lock();
-	n = dst_get_neighbour_noref(&rt->dst);
+	n = rt->n;
 	if (n) {
 		if (nla_put(skb, RTA_GATEWAY, 16, &n->primary_key) < 0) {
 			rcu_read_unlock();
@@ -2521,7 +2473,9 @@ static int rt6_fill_node(struct net *net,
 	else
 		expires = INT_MAX;
 
-	peer = rt->rt6i_peer;
+	peer = NULL;
+	if (rt6_has_peer(rt))
+		peer = rt6_peer_ptr(rt);
 	ts = tsage = 0;
 	if (peer && peer->tcp_ts_stamp) {
 		ts = peer->tcp_ts;
@@ -2722,7 +2676,7 @@ static int rt6_info_route(struct rt6_info *rt, void *p_arg)
 	seq_puts(m, "00000000000000000000000000000000 00 ");
 #endif
 	rcu_read_lock();
-	n = dst_get_neighbour_noref(&rt->dst);
+	n = rt->n;
 	if (n) {
 		seq_printf(m, "%pi6", n->primary_key);
 	} else {
@@ -3007,6 +2961,31 @@ static struct pernet_operations ip6_route_net_ops = {
 	.exit = ip6_route_net_exit,
 };
 
+static int __net_init ipv6_inetpeer_init(struct net *net)
+{
+	struct inet_peer_base *bp = kmalloc(sizeof(*bp), GFP_KERNEL);
+
+	if (!bp)
+		return -ENOMEM;
+	inet_peer_base_init(bp);
+	net->ipv6.peers = bp;
+	return 0;
+}
+
+static void __net_exit ipv6_inetpeer_exit(struct net *net)
+{
+	struct inet_peer_base *bp = net->ipv6.peers;
+
+	net->ipv6.peers = NULL;
+	inetpeer_invalidate_tree(bp);
+	kfree(bp);
+}
+
+static struct pernet_operations ipv6_inetpeer_ops = {
+	.init	=	ipv6_inetpeer_init,
+	.exit	=	ipv6_inetpeer_exit,
+};
+
 static struct pernet_operations ip6_route_net_late_ops = {
 	.init = ip6_route_net_init_late,
 	.exit = ip6_route_net_exit_late,
@@ -3032,10 +3011,14 @@ int __init ip6_route_init(void)
 	if (ret)
 		goto out_kmem_cache;
 
-	ret = register_pernet_subsys(&ip6_route_net_ops);
+	ret = register_pernet_subsys(&ipv6_inetpeer_ops);
 	if (ret)
 		goto out_dst_entries;
 
+	ret = register_pernet_subsys(&ip6_route_net_ops);
+	if (ret)
+		goto out_register_inetpeer;
+
 	ip6_dst_blackhole_ops.kmem_cachep = ip6_dst_ops_template.kmem_cachep;
 
 	/* Registering of the loopback is done before this portion of code,
@@ -3088,6 +3071,8 @@ out_fib6_init:
 	fib6_gc_cleanup();
 out_register_subsys:
 	unregister_pernet_subsys(&ip6_route_net_ops);
+out_register_inetpeer:
+	unregister_pernet_subsys(&ipv6_inetpeer_ops);
 out_dst_entries:
 	dst_entries_destroy(&ip6_dst_blackhole_ops);
 out_kmem_cache:
@@ -3102,6 +3087,7 @@ void ip6_route_cleanup(void)
 	fib6_rules_cleanup();
 	xfrm6_fini();
 	fib6_gc_cleanup();
+	unregister_pernet_subsys(&ipv6_inetpeer_ops);
 	unregister_pernet_subsys(&ip6_route_net_ops);
 	dst_entries_destroy(&ip6_dst_blackhole_ops);
 	kmem_cache_destroy(ip6_dst_ops_template.kmem_cachep);