1 files changed, 60 insertions, 20 deletions

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index d126365ac046..25661f968f3f 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -109,7 +109,6 @@ static struct dst_ops ip6_dst_ops_template = {
 	.link_failure		=	ip6_link_failure,
 	.update_pmtu		=	ip6_rt_update_pmtu,
 	.local_out		=	__ip6_local_out,
-	.entries		=	ATOMIC_INIT(0),
 };
 
 static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu)
@@ -122,7 +121,6 @@ static struct dst_ops ip6_dst_blackhole_ops = {
 	.destroy		=	ip6_dst_destroy,
 	.check			=	ip6_dst_check,
 	.update_pmtu		=	ip6_rt_blackhole_update_pmtu,
-	.entries		=	ATOMIC_INIT(0),
 };
 
 static struct rt6_info ip6_null_entry_template = {
@@ -217,14 +215,14 @@ static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
 
 static __inline__ int rt6_check_expired(const struct rt6_info *rt)
 {
-	return (rt->rt6i_flags & RTF_EXPIRES &&
-		time_after(jiffies, rt->rt6i_expires));
+	return (rt->rt6i_flags & RTF_EXPIRES) &&
+		time_after(jiffies, rt->rt6i_expires);
 }
 
 static inline int rt6_need_strict(struct in6_addr *daddr)
 {
-	return (ipv6_addr_type(daddr) &
-		(IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK));
+	return ipv6_addr_type(daddr) &
+		(IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK);
 }
 
 /*
@@ -440,7 +438,7 @@ static struct rt6_info *rt6_select(struct fib6_node *fn, int oif, int strict)
 		  __func__, match);
 
 	net = dev_net(rt0->rt6i_dev);
-	return (match ? match : net->ipv6.ip6_null_entry);
+	return match ? match : net->ipv6.ip6_null_entry;
 }
 
 #ifdef CONFIG_IPV6_ROUTE_INFO
@@ -670,7 +668,7 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, struct in6_addr *dad
 
 			if (net_ratelimit())
 				printk(KERN_WARNING
-				       "Neighbour table overflow.\n");
+				       "ipv6: Neighbour table overflow.\n");
 			dst_free(&rt->dst);
 			return NULL;
 		}
@@ -859,7 +857,7 @@ int ip6_dst_blackhole(struct sock *sk, struct dst_entry **dstp, struct flowi *fl
 
 	dst_release(*dstp);
 	*dstp = new;
-	return (new ? 0 : -ENOMEM);
+	return new ? 0 : -ENOMEM;
 }
 EXPORT_SYMBOL_GPL(ip6_dst_blackhole);
 
@@ -1058,19 +1056,22 @@ static int ip6_dst_gc(struct dst_ops *ops)
 	int rt_elasticity = net->ipv6.sysctl.ip6_rt_gc_elasticity;
 	int rt_gc_timeout = net->ipv6.sysctl.ip6_rt_gc_timeout;
 	unsigned long rt_last_gc = net->ipv6.ip6_rt_last_gc;
+	int entries;
 
+	entries = dst_entries_get_fast(ops);
 	if (time_after(rt_last_gc + rt_min_interval, now) &&
-	    atomic_read(&ops->entries) <= rt_max_size)
+	    entries <= rt_max_size)
 		goto out;
 
 	net->ipv6.ip6_rt_gc_expire++;
 	fib6_run_gc(net->ipv6.ip6_rt_gc_expire, net);
 	net->ipv6.ip6_rt_last_gc = now;
-	if (atomic_read(&ops->entries) < ops->gc_thresh)
+	entries = dst_entries_get_slow(ops);
+	if (entries < ops->gc_thresh)
 		net->ipv6.ip6_rt_gc_expire = rt_gc_timeout>>1;
 out:
 	net->ipv6.ip6_rt_gc_expire -= net->ipv6.ip6_rt_gc_expire>>rt_elasticity;
-	return (atomic_read(&ops->entries) > rt_max_size);
+	return entries > rt_max_size;
 }
 
 /* Clean host part of a prefix. Not necessary in radix tree,
@@ -1169,6 +1170,8 @@ int ip6_route_add(struct fib6_config *cfg)
 
 	if (addr_type & IPV6_ADDR_MULTICAST)
 		rt->dst.input = ip6_mc_input;
+	else if (cfg->fc_flags & RTF_LOCAL)
+		rt->dst.input = ip6_input;
 	else
 		rt->dst.input = ip6_forward;
 
@@ -1190,7 +1193,8 @@ int ip6_route_add(struct fib6_config *cfg)
 	   they would result in kernel looping; promote them to reject routes
 	 */
 	if ((cfg->fc_flags & RTF_REJECT) ||
-	    (dev && (dev->flags&IFF_LOOPBACK) && !(addr_type&IPV6_ADDR_LOOPBACK))) {
+	    (dev && (dev->flags&IFF_LOOPBACK) && !(addr_type&IPV6_ADDR_LOOPBACK)
+					      && !(cfg->fc_flags&RTF_LOCAL))) {
 		/* hold loopback dev/idev if we haven't done so. */
 		if (dev != net->loopback_dev) {
 			if (dev) {
@@ -1556,14 +1560,13 @@ out:
  *	i.e. Path MTU discovery
  */
 
-void rt6_pmtu_discovery(struct in6_addr *daddr, struct in6_addr *saddr,
-			struct net_device *dev, u32 pmtu)
+static void rt6_do_pmtu_disc(struct in6_addr *daddr, struct in6_addr *saddr,
+			     struct net *net, u32 pmtu, int ifindex)
 {
 	struct rt6_info *rt, *nrt;
-	struct net *net = dev_net(dev);
 	int allfrag = 0;
 
-	rt = rt6_lookup(net, daddr, saddr, dev->ifindex, 0);
+	rt = rt6_lookup(net, daddr, saddr, ifindex, 0);
 	if (rt == NULL)
 		return;
 
@@ -1631,6 +1634,27 @@ out:
 	dst_release(&rt->dst);
 }
 
+void rt6_pmtu_discovery(struct in6_addr *daddr, 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
  */
@@ -2082,6 +2106,9 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (rtm->rtm_type == RTN_UNREACHABLE)
 		cfg->fc_flags |= RTF_REJECT;
 
+	if (rtm->rtm_type == RTN_LOCAL)
+		cfg->fc_flags |= RTF_LOCAL;
+
 	cfg->fc_nlinfo.pid = NETLINK_CB(skb).pid;
 	cfg->fc_nlinfo.nlh = nlh;
 	cfg->fc_nlinfo.nl_net = sock_net(skb->sk);
@@ -2202,6 +2229,8 @@ static int rt6_fill_node(struct net *net,
 	NLA_PUT_U32(skb, RTA_TABLE, table);
 	if (rt->rt6i_flags&RTF_REJECT)
 		rtm->rtm_type = RTN_UNREACHABLE;
+	else if (rt->rt6i_flags&RTF_LOCAL)
+		rtm->rtm_type = RTN_LOCAL;
 	else if (rt->rt6i_dev && (rt->rt6i_dev->flags&IFF_LOOPBACK))
 		rtm->rtm_type = RTN_LOCAL;
 	else
@@ -2496,7 +2525,7 @@ static int rt6_stats_seq_show(struct seq_file *seq, void *v)
 		   net->ipv6.rt6_stats->fib_rt_alloc,
 		   net->ipv6.rt6_stats->fib_rt_entries,
 		   net->ipv6.rt6_stats->fib_rt_cache,
-		   atomic_read(&net->ipv6.ip6_dst_ops.entries),
+		   dst_entries_get_slow(&net->ipv6.ip6_dst_ops),
 		   net->ipv6.rt6_stats->fib_discarded_routes);
 
 	return 0;
@@ -2638,11 +2667,14 @@ static int __net_init ip6_route_net_init(struct net *net)
 	memcpy(&net->ipv6.ip6_dst_ops, &ip6_dst_ops_template,
 	       sizeof(net->ipv6.ip6_dst_ops));
 
+	if (dst_entries_init(&net->ipv6.ip6_dst_ops) < 0)
+		goto out_ip6_dst_ops;
+
 	net->ipv6.ip6_null_entry = kmemdup(&ip6_null_entry_template,
 					   sizeof(*net->ipv6.ip6_null_entry),
 					   GFP_KERNEL);
 	if (!net->ipv6.ip6_null_entry)
-		goto out_ip6_dst_ops;
+		goto out_ip6_dst_entries;
 	net->ipv6.ip6_null_entry->dst.path =
 		(struct dst_entry *)net->ipv6.ip6_null_entry;
 	net->ipv6.ip6_null_entry->dst.ops = &net->ipv6.ip6_dst_ops;
@@ -2692,6 +2724,8 @@ out_ip6_prohibit_entry:
 out_ip6_null_entry:
 	kfree(net->ipv6.ip6_null_entry);
 #endif
+out_ip6_dst_entries:
+	dst_entries_destroy(&net->ipv6.ip6_dst_ops);
 out_ip6_dst_ops:
 	goto out;
 }
@@ -2730,10 +2764,14 @@ int __init ip6_route_init(void)
 	if (!ip6_dst_ops_template.kmem_cachep)
 		goto out;
 
-	ret = register_pernet_subsys(&ip6_route_net_ops);
+	ret = dst_entries_init(&ip6_dst_blackhole_ops);
 	if (ret)
 		goto out_kmem_cache;
 
+	ret = register_pernet_subsys(&ip6_route_net_ops);
+	if (ret)
+		goto out_dst_entries;
+
 	ip6_dst_blackhole_ops.kmem_cachep = ip6_dst_ops_template.kmem_cachep;
 
 	/* Registering of the loopback is done before this portion of code,
@@ -2780,6 +2818,8 @@ out_fib6_init:
 	fib6_gc_cleanup();
 out_register_subsys:
 	unregister_pernet_subsys(&ip6_route_net_ops);
+out_dst_entries:
+	dst_entries_destroy(&ip6_dst_blackhole_ops);
 out_kmem_cache:
 	kmem_cache_destroy(ip6_dst_ops_template.kmem_cachep);
 	goto out;