Merge branch 'nexthop_exceptions'

These patches implement the final mechanism necessary to really allow
us to go without the route cache in ipv4.

We need a place to have long-term storage of PMTU/redirect information
which is independent of the routes themselves, yet does not get us
back into a situation where we have to write to metrics or anything
like that.

For this we use an "next-hop exception" table in the FIB nexthops.

The one thing I desperately want to avoid is having to create clone
routes in the FIB trie for this purpose, because that is very
expensive.   However, I'm willing to entertain such an idea later
if this current scheme proves to have downsides that the FIB trie
variant would not have.

In order to accomodate this any such scheme, we need to be able to
produce a full flow key at PMTU/redirect time.  That required an
adjustment of the interface call-sites used to propagate these events.

For a PMTU/redirect with a fully specified socket, we pass that socket
and use it to produce the flow key.

Otherwise we use a passed in SKB to formulate the key.  There are two
cases that need to be distinguished, ICMP message processing (in which
case the IP header is at skb->data) and output packet processing
(mostly tunnels, and in all such cases the IP header is at ip_hdr(skb)).

We also have to make the code able to handle the case where the dst
itself passed into the dst_ops->{update_pmtu,redirect} method is
invalidated.  This matters for calls from sockets that have cached
that route.  We provide a inet{,6} helper function for this purpose,
and edit SCTP specially since it caches routes at the transport rather
than socket level.

Signed-off-by: David S. Miller <davem@davemloft.net>

30 files changed, 449 insertions, 183 deletions

diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
index 014504d8e43c..1ca732201f33 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
@@ -1397,7 +1397,7 @@ void ipoib_cm_skb_too_long(struct net_device *dev, struct sk_buff *skb,
 	int e = skb_queue_empty(&priv->cm.skb_queue);
 
 	if (skb_dst(skb))
-		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu);
+		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
 
 	skb_queue_tail(&priv->cm.skb_queue, skb);
 	if (e)
diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h
index 085931fa7ce0..d079fc61c123 100644
--- a/include/net/dst_ops.h
+++ b/include/net/dst_ops.h
@@ -24,8 +24,10 @@ struct dst_ops {
 					  struct net_device *dev, int how);
 	struct dst_entry *	(*negative_advice)(struct dst_entry *);
 	void			(*link_failure)(struct sk_buff *);
-	void			(*update_pmtu)(struct dst_entry *dst, u32 mtu);
-	void			(*redirect)(struct dst_entry *dst, struct sk_buff *skb);
+	void			(*update_pmtu)(struct dst_entry *dst, struct sock *sk,
+					       struct sk_buff *skb, u32 mtu);
+	void			(*redirect)(struct dst_entry *dst, struct sock *sk,
+					    struct sk_buff *skb);
 	int			(*local_out)(struct sk_buff *skb);
 	struct neighbour *	(*neigh_lookup)(const struct dst_entry *dst,
 						struct sk_buff *skb,
diff --git a/include/net/inet6_connection_sock.h b/include/net/inet6_connection_sock.h
index df2a857e853d..04642c920431 100644
--- a/include/net/inet6_connection_sock.h
+++ b/include/net/inet6_connection_sock.h
@@ -43,4 +43,6 @@ extern void inet6_csk_reqsk_queue_hash_add(struct sock *sk,
 extern void inet6_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr);
 
 extern int inet6_csk_xmit(struct sk_buff *skb, struct flowi *fl);
+
+extern struct dst_entry *inet6_csk_update_pmtu(struct sock *sk, u32 mtu);
 #endif /* _INET6_CONNECTION_SOCK_H */
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 291e7cee14e7..2cf44b4ed2e6 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -337,4 +337,6 @@ extern int inet_csk_compat_getsockopt(struct sock *sk, int level, int optname,
 				      char __user *optval, int __user *optlen);
 extern int inet_csk_compat_setsockopt(struct sock *sk, int level, int optname,
 				      char __user *optval, unsigned int optlen);
+
+extern struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu);
 #endif /* _INET_CONNECTION_SOCK_H */
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 5697acefeba3..e9ee1ca07087 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -18,6 +18,7 @@
 
 #include <net/flow.h>
 #include <linux/seq_file.h>
+#include <linux/rcupdate.h>
 #include <net/fib_rules.h>
 #include <net/inetpeer.h>
 
@@ -46,6 +47,22 @@ struct fib_config {
 
 struct fib_info;
 
+struct fib_nh_exception {
+	struct fib_nh_exception __rcu	*fnhe_next;
+	__be32				fnhe_daddr;
+	u32				fnhe_pmtu;
+	u32				fnhe_gw;
+	unsigned long			fnhe_expires;
+	unsigned long			fnhe_stamp;
+};
+
+struct fnhe_hash_bucket {
+	struct fib_nh_exception __rcu	*chain;
+};
+
+#define FNHE_HASH_SIZE		2048
+#define FNHE_RECLAIM_DEPTH	5
+
 struct fib_nh {
 	struct net_device	*nh_dev;
 	struct hlist_node	nh_hash;
@@ -63,6 +80,7 @@ struct fib_nh {
 	__be32			nh_gw;
 	__be32			nh_saddr;
 	int			nh_saddr_genid;
+	struct fnhe_hash_bucket	*nh_exceptions;
 };
 
 /*
diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index 1f2735dba753..ff499640528b 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -519,10 +519,10 @@ static inline int sctp_frag_point(const struct sctp_association *asoc, int pmtu)
 	return frag;
 }
 
-static inline void sctp_assoc_pending_pmtu(struct sctp_association *asoc)
+static inline void sctp_assoc_pending_pmtu(struct sock *sk, struct sctp_association *asoc)
 {
 
-	sctp_assoc_sync_pmtu(asoc);
+	sctp_assoc_sync_pmtu(sk, asoc);
 	asoc->pmtu_pending = 0;
 }
 
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index fecdf31816f2..536e439ddf1d 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -1091,7 +1091,7 @@ void sctp_transport_burst_limited(struct sctp_transport *);
 void sctp_transport_burst_reset(struct sctp_transport *);
 unsigned long sctp_transport_timeout(struct sctp_transport *);
 void sctp_transport_reset(struct sctp_transport *);
-void sctp_transport_update_pmtu(struct sctp_transport *, u32);
+void sctp_transport_update_pmtu(struct sock *, struct sctp_transport *, u32);
 void sctp_transport_immediate_rtx(struct sctp_transport *);
 
 
@@ -2003,7 +2003,7 @@ void sctp_assoc_update(struct sctp_association *old,
 
 __u32 sctp_association_get_next_tsn(struct sctp_association *);
 
-void sctp_assoc_sync_pmtu(struct sctp_association *);
+void sctp_assoc_sync_pmtu(struct sock *, struct sctp_association *);
 void sctp_assoc_rwnd_increase(struct sctp_association *, unsigned int);
 void sctp_assoc_rwnd_decrease(struct sctp_association *, unsigned int);
 void sctp_assoc_set_primary(struct sctp_association *,
diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c
index 81f76c402cf2..68e8f364bbf8 100644
--- a/net/bridge/br_netfilter.c
+++ b/net/bridge/br_netfilter.c
@@ -111,11 +111,13 @@ static inline __be16 pppoe_proto(const struct sk_buff *skb)
 	 pppoe_proto(skb) == htons(PPP_IPV6) && \
 	 brnf_filter_pppoe_tagged)
 
-static void fake_update_pmtu(struct dst_entry *dst, u32 mtu)
+static void fake_update_pmtu(struct dst_entry *dst, struct sock *sk,
+			     struct sk_buff *skb, u32 mtu)
 {
 }
 
-static void fake_redirect(struct dst_entry *dst, struct sk_buff *skb)
+static void fake_redirect(struct dst_entry *dst, struct sock *sk,
+			  struct sk_buff *skb)
 {
 }
 
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 129ed8f74138..ab4f44c9bb21 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -161,17 +161,10 @@ static inline void dccp_do_pmtu_discovery(struct sock *sk,
 	if (sk->sk_state == DCCP_LISTEN)
 		return;
 
-	/* We don't check in the destentry if pmtu discovery is forbidden
-	 * on this route. We just assume that no packet_to_big packets
-	 * are send back when pmtu discovery is not active.
-	 * There is a small race when the user changes this flag in the
-	 * route, but I think that's acceptable.
-	 */
-	if ((dst = __sk_dst_check(sk, 0)) == NULL)
+	dst = inet_csk_update_pmtu(sk, mtu);
+	if (!dst)
 		return;
 
-	dst->ops->update_pmtu(dst, mtu);
-
 	/* Something is about to be wrong... Remember soft error
 	 * for the case, if this connection will not able to recover.
 	 */
@@ -200,7 +193,7 @@ static void dccp_do_redirect(struct sk_buff *skb, struct sock *sk)
 	struct dst_entry *dst = __sk_dst_check(sk, 0);
 
 	if (dst)
-		dst->ops->redirect(dst, skb);
+		dst->ops->redirect(dst, sk, skb);
 }
 
 /*
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 090c0800ce03..56840b249f3b 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -134,7 +134,7 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
 
 		if (dst)
-			dst->ops->redirect(dst, skb);
+			dst->ops->redirect(dst, sk, skb);
 	}
 
 	if (type == ICMPV6_PKT_TOOBIG) {
@@ -145,39 +145,12 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		if ((1 << sk->sk_state) & (DCCPF_LISTEN | DCCPF_CLOSED))
 			goto out;
 
-		/* icmp should have updated the destination cache entry */
-		dst = __sk_dst_check(sk, np->dst_cookie);
-		if (dst == NULL) {
-			struct inet_sock *inet = inet_sk(sk);
-			struct flowi6 fl6;
-
-			/* BUGGG_FUTURE: Again, it is not clear how
-			   to handle rthdr case. Ignore this complexity
-			   for now.
-			 */
-			memset(&fl6, 0, sizeof(fl6));
-			fl6.flowi6_proto = IPPROTO_DCCP;
-			fl6.daddr = np->daddr;
-			fl6.saddr = np->saddr;
-			fl6.flowi6_oif = sk->sk_bound_dev_if;
-			fl6.fl6_dport = inet->inet_dport;
-			fl6.fl6_sport = inet->inet_sport;
-			security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
-
-			dst = ip6_dst_lookup_flow(sk, &fl6, NULL, false);
-			if (IS_ERR(dst)) {
-				sk->sk_err_soft = -PTR_ERR(dst);
-				goto out;
-			}
-		} else
-			dst_hold(dst);
-
-		dst->ops->update_pmtu(dst, ntohl(info));
+		dst = inet6_csk_update_pmtu(sk, ntohl(info));
+		if (!dst)
+			goto out;
 
-		if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) {
+		if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst))
 			dccp_sync_mss(sk, dst_mtu(dst));
-		} /* else let the usual retransmit timer handle it */
-		dst_release(dst);
 		goto out;
 	}
 
diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c
index e9c4e2e864c6..47de90d8fe94 100644
--- a/net/decnet/dn_route.c
+++ b/net/decnet/dn_route.c
@@ -117,8 +117,10 @@ static void dn_dst_destroy(struct dst_entry *);
 static void dn_dst_ifdown(struct dst_entry *, struct net_device *dev, int how);
 static struct dst_entry *dn_dst_negative_advice(struct dst_entry *);
 static void dn_dst_link_failure(struct sk_buff *);
-static void dn_dst_update_pmtu(struct dst_entry *dst, u32 mtu);
-static void dn_dst_redirect(struct dst_entry *dst, struct sk_buff *skb);
+static void dn_dst_update_pmtu(struct dst_entry *dst, struct sock *sk,
+			       struct sk_buff *skb , u32 mtu);
+static void dn_dst_redirect(struct dst_entry *dst, struct sock *sk,
+			    struct sk_buff *skb);
 static struct neighbour *dn_dst_neigh_lookup(const struct dst_entry *dst,
 					     struct sk_buff *skb,
 					     const void *daddr);
@@ -266,7 +268,8 @@ static int dn_dst_gc(struct dst_ops *ops)
  * We update both the mtu and the advertised mss (i.e. the segment size we
  * advertise to the other end).
  */
-static void dn_dst_update_pmtu(struct dst_entry *dst, u32 mtu)
+static void dn_dst_update_pmtu(struct dst_entry *dst, struct sock *sk,
+			       struct sk_buff *skb, u32 mtu)
 {
 	struct dn_route *rt = (struct dn_route *) dst;
 	struct neighbour *n = rt->n;
@@ -294,7 +297,8 @@ static void dn_dst_update_pmtu(struct dst_entry *dst, u32 mtu)
 	}
 }
 
-static void dn_dst_redirect(struct dst_entry *dst, struct sk_buff *skb)
+static void dn_dst_redirect(struct dst_entry *dst, struct sock *sk,
+			    struct sk_buff *skb)
 {
 }
 
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index d71bfbdc0bf4..1e09852df512 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -140,6 +140,27 @@ const struct fib_prop fib_props[RTN_MAX + 1] = {
 	},
 };
 
+static void free_nh_exceptions(struct fib_nh *nh)
+{
+	struct fnhe_hash_bucket *hash = nh->nh_exceptions;
+	int i;
+
+	for (i = 0; i < FNHE_HASH_SIZE; i++) {
+		struct fib_nh_exception *fnhe;
+
+		fnhe = rcu_dereference(hash[i].chain);
+		while (fnhe) {
+			struct fib_nh_exception *next;
+			
+			next = rcu_dereference(fnhe->fnhe_next);
+			kfree(fnhe);
+
+			fnhe = next;
+		}
+	}
+	kfree(hash);
+}
+
 /* Release a nexthop info record */
 static void free_fib_info_rcu(struct rcu_head *head)
 {
@@ -148,6 +169,8 @@ static void free_fib_info_rcu(struct rcu_head *head)
 	change_nexthops(fi) {
 		if (nexthop_nh->nh_dev)
 			dev_put(nexthop_nh->nh_dev);
+		if (nexthop_nh->nh_exceptions)
+			free_nh_exceptions(nexthop_nh);
 	} endfor_nexthops(fi);
 
 	release_net(fi->fib_net);
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 76825be3b643..3ea465286a39 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -803,3 +803,49 @@ int inet_csk_compat_setsockopt(struct sock *sk, int level, int optname,
 }
 EXPORT_SYMBOL_GPL(inet_csk_compat_setsockopt);
 #endif
+
+static struct dst_entry *inet_csk_rebuild_route(struct sock *sk, struct flowi *fl)
+{
+	struct inet_sock *inet = inet_sk(sk);
+	struct ip_options_rcu *inet_opt;
+	__be32 daddr = inet->inet_daddr;
+	struct flowi4 *fl4;
+	struct rtable *rt;
+
+	rcu_read_lock();
+	inet_opt = rcu_dereference(inet->inet_opt);
+	if (inet_opt && inet_opt->opt.srr)
+		daddr = inet_opt->opt.faddr;
+	fl4 = &fl->u.ip4;
+	rt = ip_route_output_ports(sock_net(sk), fl4, sk, daddr,
+				   inet->inet_saddr, inet->inet_dport,
+				   inet->inet_sport, sk->sk_protocol,
+				   RT_CONN_FLAGS(sk), sk->sk_bound_dev_if);
+	if (IS_ERR(rt))
+		rt = NULL;
+	if (rt)
+		sk_setup_caps(sk, &rt->dst);
+	rcu_read_unlock();
+
+	return &rt->dst;
+}
+
+struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu)
+{
+	struct dst_entry *dst = __sk_dst_check(sk, 0);
+	struct inet_sock *inet = inet_sk(sk);
+
+	if (!dst) {
+		dst = inet_csk_rebuild_route(sk, &inet->cork.fl);
+		if (!dst)
+			goto out;
+	}
+	dst->ops->update_pmtu(dst, sk, NULL, mtu);
+
+	dst = __sk_dst_check(sk, 0);
+	if (!dst)
+		dst = inet_csk_rebuild_route(sk, &inet->cork.fl);
+out:
+	return dst;
+}
+EXPORT_SYMBOL_GPL(inet_csk_update_pmtu);
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 0c3123566d76..42c44b1403c9 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -833,7 +833,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
 		mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu;
 
 	if (skb_dst(skb))
-		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu);
+		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
 
 	if (skb->protocol == htons(ETH_P_IP)) {
 		df |= (old_iph->frag_off&htons(IP_DF));
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index c2d0e6d8baaf..2c2c35bace76 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -519,7 +519,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 		}
 
 		if (skb_dst(skb))
-			skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu);
+			skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
 
 		if ((old_iph->frag_off & htons(IP_DF)) &&
 		    mtu < ntohs(old_iph->tot_len)) {
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index aad21819316d..a5bd0b4acc61 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -148,8 +148,10 @@ static unsigned int	 ipv4_mtu(const struct dst_entry *dst);
 static void		 ipv4_dst_destroy(struct dst_entry *dst);
 static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst);
 static void		 ipv4_link_failure(struct sk_buff *skb);
-static void		 ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu);
-static void		 ip_do_redirect(struct dst_entry *dst, struct sk_buff *skb);
+static void		 ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
+					   struct sk_buff *skb, u32 mtu);
+static void		 ip_do_redirect(struct dst_entry *dst, struct sock *sk,
+					struct sk_buff *skb);
 static int rt_garbage_collect(struct dst_ops *ops);
 
 static void ipv4_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
@@ -1273,14 +1275,130 @@ static void rt_del(unsigned int hash, struct rtable *rt)
 	spin_unlock_bh(rt_hash_lock_addr(hash));
 }
 
-static void ip_do_redirect(struct dst_entry *dst, struct sk_buff *skb)
+static void __build_flow_key(struct flowi4 *fl4, struct sock *sk,
+			     const struct iphdr *iph,
+			     int oif, u8 tos,
+			     u8 prot, u32 mark, int flow_flags)
+{
+	if (sk) {
+		const struct inet_sock *inet = inet_sk(sk);
+
+		oif = sk->sk_bound_dev_if;
+		mark = sk->sk_mark;
+		tos = RT_CONN_FLAGS(sk);
+		prot = inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol;
+	}
+	flowi4_init_output(fl4, oif, mark, tos,
+			   RT_SCOPE_UNIVERSE, prot,
+			   flow_flags,
+			   iph->daddr, iph->saddr, 0, 0);
+}
+
+static void build_skb_flow_key(struct flowi4 *fl4, struct sk_buff *skb, struct sock *sk)
+{
+	const struct iphdr *iph = ip_hdr(skb);
+	int oif = skb->dev->ifindex;
+	u8 tos = RT_TOS(iph->tos);
+	u8 prot = iph->protocol;
+	u32 mark = skb->mark;
+
+	__build_flow_key(fl4, sk, iph, oif, tos, prot, mark, 0);
+}
+
+static void build_sk_flow_key(struct flowi4 *fl4, struct sock *sk)
+{
+	const struct inet_sock *inet = inet_sk(sk);
+	struct ip_options_rcu *inet_opt;
+	__be32 daddr = inet->inet_daddr;
+
+	rcu_read_lock();
+	inet_opt = rcu_dereference(inet->inet_opt);
+	if (inet_opt && inet_opt->opt.srr)
+		daddr = inet_opt->opt.faddr;
+	flowi4_init_output(fl4, sk->sk_bound_dev_if, sk->sk_mark,
+			   RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
+			   inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol,
+			   inet_sk_flowi_flags(sk),
+			   daddr, inet->inet_saddr, 0, 0);
+	rcu_read_unlock();
+}
+
+static void ip_rt_build_flow_key(struct flowi4 *fl4, struct sock *sk,
+				 struct sk_buff *skb)
+{
+	if (skb)
+		build_skb_flow_key(fl4, skb, sk);
+	else
+		build_sk_flow_key(fl4, sk);
+}
+
+static DEFINE_SPINLOCK(fnhe_lock);
+
+static struct fib_nh_exception *fnhe_oldest(struct fnhe_hash_bucket *hash, __be32 daddr)
+{
+	struct fib_nh_exception *fnhe, *oldest;
+
+	oldest = rcu_dereference(hash->chain);
+	for (fnhe = rcu_dereference(oldest->fnhe_next); fnhe;
+	     fnhe = rcu_dereference(fnhe->fnhe_next)) {
+		if (time_before(fnhe->fnhe_stamp, oldest->fnhe_stamp))
+			oldest = fnhe;
+	}
+	return oldest;
+}
+
+static struct fib_nh_exception *find_or_create_fnhe(struct fib_nh *nh, __be32 daddr)
+{
+	struct fnhe_hash_bucket *hash = nh->nh_exceptions;
+	struct fib_nh_exception *fnhe;
+	int depth;
+	u32 hval;
+
+	if (!hash) {
+		hash = nh->nh_exceptions = kzalloc(FNHE_HASH_SIZE * sizeof(*hash),
+						   GFP_ATOMIC);
+		if (!hash)
+			return NULL;
+	}
+
+	hval = (__force u32) daddr;
+	hval ^= (hval >> 11) ^ (hval >> 22);
+	hash += hval;
+
+	depth = 0;
+	for (fnhe = rcu_dereference(hash->chain); fnhe;
+	     fnhe = rcu_dereference(fnhe->fnhe_next)) {
+		if (fnhe->fnhe_daddr == daddr)
+			goto out;
+		depth++;
+	}
+
+	if (depth > FNHE_RECLAIM_DEPTH) {
+		fnhe = fnhe_oldest(hash + hval, daddr);
+		goto out_daddr;
+	}
+	fnhe = kzalloc(sizeof(*fnhe), GFP_ATOMIC);
+	if (!fnhe)
+		return NULL;
+
+	fnhe->fnhe_next = hash->chain;
+	rcu_assign_pointer(hash->chain, fnhe);
+
+out_daddr:
+	fnhe->fnhe_daddr = daddr;
+out:
+	fnhe->fnhe_stamp = jiffies;
+	return fnhe;
+}
+
+static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flowi4 *fl4)
 {
 	__be32 new_gw = icmp_hdr(skb)->un.gateway;
 	__be32 old_gw = ip_hdr(skb)->saddr;
 	struct net_device *dev = skb->dev;
 	struct in_device *in_dev;
+	struct fib_result res;
 	struct neighbour *n;
-	struct rtable *rt;
 	struct net *net;
 
 	switch (icmp_hdr(skb)->code & 7) {
@@ -1294,7 +1412,6 @@ static void ip_do_redirect(struct dst_entry *dst, struct sk_buff *skb)
 		return;
 	}
 
-	rt = (struct rtable *) dst;
 	if (rt->rt_gateway != old_gw)
 		return;
 
@@ -1318,11 +1435,21 @@ static void ip_do_redirect(struct dst_entry *dst, struct sk_buff *skb)
 			goto reject_redirect;
 	}
 
-	n = ipv4_neigh_lookup(dst, NULL, &new_gw);
+	n = ipv4_neigh_lookup(&rt->dst, NULL, &new_gw);
 	if (n) {
 		if (!(n->nud_state & NUD_VALID)) {
 			neigh_event_send(n, NULL);
 		} else {
+			if (fib_lookup(net, fl4, &res) == 0) {
+				struct fib_nh *nh = &FIB_RES_NH(res);
+				struct fib_nh_exception *fnhe;
+
+				spin_lock_bh(&fnhe_lock);
+				fnhe = find_or_create_fnhe(nh, fl4->daddr);
+				if (fnhe)
+					fnhe->fnhe_gw = new_gw;
+				spin_unlock_bh(&fnhe_lock);
+			}
 			rt->rt_gateway = new_gw;
 			rt->rt_flags |= RTCF_REDIRECTED;
 			call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, n);
@@ -1347,6 +1474,17 @@ reject_redirect:
 	;
 }
 
+static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb)
+{
+	struct rtable *rt;
+	struct flowi4 fl4;
+
+	rt = (struct rtable *) dst;
+
+	ip_rt_build_flow_key(&fl4, sk, skb);
+	__ip_do_redirect(rt, skb, &fl4);
+}
+
 static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst)
 {
 	struct rtable *rt = (struct rtable *)dst;
@@ -1506,32 +1644,51 @@ out:	kfree_skb(skb);
 	return 0;
 }
 
-static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu)
+static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
 {
-	struct rtable *rt = (struct rtable *) dst;
-
-	dst_confirm(dst);
+	struct fib_result res;
 
 	if (mtu < ip_rt_min_pmtu)
 		mtu = ip_rt_min_pmtu;
 
+	if (fib_lookup(dev_net(rt->dst.dev), fl4, &res) == 0) {
+		struct fib_nh *nh = &FIB_RES_NH(res);
+		struct fib_nh_exception *fnhe;
+
+		spin_lock_bh(&fnhe_lock);
+		fnhe = find_or_create_fnhe(nh, fl4->daddr);
+		if (fnhe) {
+			fnhe->fnhe_pmtu = mtu;
+			fnhe->fnhe_expires = jiffies + ip_rt_mtu_expires;
+		}
+		spin_unlock_bh(&fnhe_lock);
+	}
 	rt->rt_pmtu = mtu;
 	dst_set_expires(&rt->dst, ip_rt_mtu_expires);
 }
 
+static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
+			      struct sk_buff *skb, u32 mtu)
+{
+	struct rtable *rt = (struct rtable *) dst;
+	struct flowi4 fl4;
+
+	ip_rt_build_flow_key(&fl4, sk, skb);
+	__ip_rt_update_pmtu(rt, &fl4, mtu);
+}
+
 void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu,
 		      int oif, u32 mark, u8 protocol, int flow_flags)
 {
-	const struct iphdr *iph = (const struct iphdr *)skb->data;
+	const struct iphdr *iph = (const struct iphdr *) skb->data;
 	struct flowi4 fl4;
 	struct rtable *rt;
 
-	flowi4_init_output(&fl4, oif, mark, RT_TOS(iph->tos), RT_SCOPE_UNIVERSE,
-			   protocol, flow_flags,
-			   iph->daddr, iph->saddr, 0, 0);
+	__build_flow_key(&fl4, NULL, iph, oif,
+			 RT_TOS(iph->tos), protocol, mark, flow_flags);
 	rt = __ip_route_output_key(net, &fl4);
 	if (!IS_ERR(rt)) {
-		ip_rt_update_pmtu(&rt->dst, mtu);
+		__ip_rt_update_pmtu(rt, &fl4, mtu);
 		ip_rt_put(rt);
 	}
 }
@@ -1539,27 +1696,31 @@ EXPORT_SYMBOL_GPL(ipv4_update_pmtu);
 
 void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
 {
-	const struct inet_sock *inet = inet_sk(sk);
+	const struct iphdr *iph = (const struct iphdr *) skb->data;
+	struct flowi4 fl4;
+	struct rtable *rt;
 
-	return ipv4_update_pmtu(skb, sock_net(sk), mtu,
-				sk->sk_bound_dev_if, sk->sk_mark,
-				inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol,
-				inet_sk_flowi_flags(sk));
+	__build_flow_key(&fl4, sk, iph, 0, 0, 0, 0, 0);
+	rt = __ip_route_output_key(sock_net(sk), &fl4);
+	if (!IS_ERR(rt)) {
+		__ip_rt_update_pmtu(rt, &fl4, mtu);
+		ip_rt_put(rt);
+	}
 }
 EXPORT_SYMBOL_GPL(ipv4_sk_update_pmtu);
 
 void ipv4_redirect(struct sk_buff *skb, struct net *net,
 		   int oif, u32 mark, u8 protocol, int flow_flags)
 {
-	const struct iphdr *iph = (const struct iphdr *)skb->data;
+	const struct iphdr *iph = (const struct iphdr *) skb->data;
 	struct flowi4 fl4;
 	struct rtable *rt;
 
-	flowi4_init_output(&fl4, oif, mark, RT_TOS(iph->tos), RT_SCOPE_UNIVERSE,
-			   protocol, flow_flags, iph->daddr, iph->saddr, 0, 0);
+	__build_flow_key(&fl4, NULL, iph, oif,
+			 RT_TOS(iph->tos), protocol, mark, flow_flags);
 	rt = __ip_route_output_key(net, &fl4);
 	if (!IS_ERR(rt)) {
-		ip_do_redirect(&rt->dst, skb);
+		__ip_do_redirect(rt, skb, &fl4);
 		ip_rt_put(rt);
 	}
 }
@@ -1567,12 +1728,16 @@ EXPORT_SYMBOL_GPL(ipv4_redirect);
 
 void ipv4_sk_redirect(struct sk_buff *skb, struct sock *sk)
 {
-	const struct inet_sock *inet = inet_sk(sk);
+	const struct iphdr *iph = (const struct iphdr *) skb->data;
+	struct flowi4 fl4;
+	struct rtable *rt;
 
-	return ipv4_redirect(skb, sock_net(sk), sk->sk_bound_dev_if,
-			     sk->sk_mark,
-			     inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol,
-			     inet_sk_flowi_flags(sk));
+	__build_flow_key(&fl4, sk, iph, 0, 0, 0, 0, 0);
+	rt = __ip_route_output_key(sock_net(sk), &fl4);
+	if (!IS_ERR(rt)) {
+		__ip_do_redirect(rt, skb, &fl4);
+		ip_rt_put(rt);
+	}
 }
 EXPORT_SYMBOL_GPL(ipv4_sk_redirect);
 
@@ -1719,14 +1884,46 @@ static void rt_init_metrics(struct rtable *rt, const struct flowi4 *fl4,
 	dst_init_metrics(&rt->dst, fi->fib_metrics, true);
 }
 
+static void rt_bind_exception(struct rtable *rt, struct fib_nh *nh, __be32 daddr)
+{
+	struct fnhe_hash_bucket *hash = nh->nh_exceptions;
+	struct fib_nh_exception *fnhe;
+	u32 hval;
+
+	hval = (__force u32) daddr;
+	hval ^= (hval >> 11) ^ (hval >> 22);
+
+	for (fnhe = rcu_dereference(hash[hval].chain); fnhe;
+	     fnhe = rcu_dereference(fnhe->fnhe_next)) {
+		if (fnhe->fnhe_daddr == daddr) {
+			if (fnhe->fnhe_pmtu) {
+				unsigned long expires = fnhe->fnhe_expires;
+				unsigned long diff = jiffies - expires;
+
+				if (time_before(jiffies, expires)) {
+					rt->rt_pmtu = fnhe->fnhe_pmtu;
+					dst_set_expires(&rt->dst, diff);
+				}
+			}
+			if (fnhe->fnhe_gw)
+				rt->rt_gateway = fnhe->fnhe_gw;
+			fnhe->fnhe_stamp = jiffies;
+			break;
+		}
+	}
+}
+
 static void rt_set_nexthop(struct rtable *rt, const struct flowi4 *fl4,
 			   const struct fib_result *res,
 			   struct fib_info *fi, u16 type, u32 itag)
 {
 	if (fi) {
-		if (FIB_RES_GW(*res) &&
-		    FIB_RES_NH(*res).nh_scope == RT_SCOPE_LINK)
-			rt->rt_gateway = FIB_RES_GW(*res);
+		struct fib_nh *nh = &FIB_RES_NH(*res);
+
+		if (nh->nh_gw && nh->nh_scope == RT_SCOPE_LINK)
+			rt->rt_gateway = nh->nh_gw;
+		if (unlikely(nh->nh_exceptions))
+			rt_bind_exception(rt, nh, fl4->daddr);
 		rt_init_metrics(rt, fl4, fi);
 #ifdef CONFIG_IP_ROUTE_CLASSID
 		rt->dst.tclassid = FIB_RES_NH(*res).nh_tclassid;
@@ -2587,11 +2784,13 @@ static unsigned int ipv4_blackhole_mtu(const struct dst_entry *dst)
 	return mtu ? : dst->dev->mtu;
 }
 
-static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu)
+static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk,
+					  struct sk_buff *skb, u32 mtu)
 {
 }
 
-static void ipv4_rt_blackhole_redirect(struct dst_entry *dst, struct sk_buff *skb)
+static void ipv4_rt_blackhole_redirect(struct dst_entry *dst, struct sock *sk,
+				       struct sk_buff *skb)
 {
 }
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 7a0062cb4ed0..d9caf5c07aae 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -289,17 +289,10 @@ static void do_pmtu_discovery(struct sock *sk, const struct iphdr *iph, u32 mtu)
 	if (sk->sk_state == TCP_LISTEN)
 		return;
 
-	/* We don't check in the destentry if pmtu discovery is forbidden
-	 * on this route. We just assume that no packet_to_big packets
-	 * are send back when pmtu discovery is not active.
-	 * There is a small race when the user changes this flag in the
-	 * route, but I think that's acceptable.
-	 */
-	if ((dst = __sk_dst_check(sk, 0)) == NULL)
+	dst = inet_csk_update_pmtu(sk, mtu);
+	if (!dst)
 		return;
 
-	dst->ops->update_pmtu(dst, mtu);
-
 	/* Something is about to be wrong... Remember soft error
 	 * for the case, if this connection will not able to recover.
 	 */
@@ -326,7 +319,7 @@ static void do_redirect(struct sk_buff *skb, struct sock *sk)
 	struct dst_entry *dst = __sk_dst_check(sk, 0);
 
 	if (dst)
-		dst->ops->redirect(dst, skb);
+		dst->ops->redirect(dst, sk, skb);
 }
 
 /*
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 737131cef375..fcf7678bc009 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -194,20 +194,22 @@ static inline int xfrm4_garbage_collect(struct dst_ops *ops)
 	return (dst_entries_get_slow(ops) > ops->gc_thresh * 2);
 }
 
-static void xfrm4_update_pmtu(struct dst_entry *dst, u32 mtu)
+static void xfrm4_update_pmtu(struct dst_entry *dst, struct sock *sk,
+			      struct sk_buff *skb, u32 mtu)
 {
 	struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
 	struct dst_entry *path = xdst->route;
 
-	path->ops->update_pmtu(path, mtu);
+	path->ops->update_pmtu(path, sk, skb, mtu);
 }
 
-static void xfrm4_redirect(struct dst_entry *dst, struct sk_buff *skb)
+static void xfrm4_redirect(struct dst_entry *dst, struct sock *sk,
+			   struct sk_buff *skb)
 {
 	struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
 	struct dst_entry *path = xdst->route;
 
-	path->ops->redirect(path, skb);
+	path->ops->redirect(path, sk, skb);
 }
 
 static void xfrm4_dst_destroy(struct dst_entry *dst)
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index bceb14450a1d..4a0c4d2d8b05 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -203,15 +203,13 @@ struct dst_entry *__inet6_csk_dst_check(struct sock *sk, u32 cookie)
 	return dst;
 }
 
-int inet6_csk_xmit(struct sk_buff *skb, struct flowi *fl_unused)
+static struct dst_entry *inet6_csk_route_socket(struct sock *sk)
 {
-	struct sock *sk = skb->sk;
 	struct inet_sock *inet = inet_sk(sk);
 	struct ipv6_pinfo *np = inet6_sk(sk);
-	struct flowi6 fl6;
-	struct dst_entry *dst;
 	struct in6_addr *final_p, final;
-	int res;
+	struct dst_entry *dst;
+	struct flowi6 fl6;
 
 	memset(&fl6, 0, sizeof(fl6));
 	fl6.flowi6_proto = sk->sk_protocol;
@@ -228,18 +226,29 @@ int inet6_csk_xmit(struct sk_buff *skb, struct flowi *fl_unused)
 	final_p = fl6_update_dst(&fl6, np->opt, &final);
 
 	dst = __inet6_csk_dst_check(sk, np->dst_cookie);
-
-	if (dst == NULL) {
+	if (!dst) {
 		dst = ip6_dst_lookup_flow(sk, &fl6, final_p, false);
 
-		if (IS_ERR(dst)) {
-			sk->sk_err_soft = -PTR_ERR(dst);
-			sk->sk_route_caps = 0;
-			kfree_skb(skb);
-			return PTR_ERR(dst);
-		}
+		if (!IS_ERR(dst))
+			__inet6_csk_dst_store(sk, dst, NULL, NULL);
+	}
+	return dst;
+}
 
-		__inet6_csk_dst_store(sk, dst, NULL, NULL);
+int inet6_csk_xmit(struct sk_buff *skb, struct flowi *fl_unused)
+{
+	struct sock *sk = skb->sk;
+	struct ipv6_pinfo *np = inet6_sk(sk);
+	struct flowi6 fl6;
+	struct dst_entry *dst;
+	int res;
+
+	dst = inet6_csk_route_socket(sk);
+	if (IS_ERR(dst)) {
+		sk->sk_err_soft = -PTR_ERR(dst);
+		sk->sk_route_caps = 0;
+		kfree_skb(skb);
+		return PTR_ERR(dst);
 	}
 
 	rcu_read_lock();
@@ -253,3 +262,15 @@ int inet6_csk_xmit(struct sk_buff *skb, struct flowi *fl_unused)
 	return res;
 }
 EXPORT_SYMBOL_GPL(inet6_csk_xmit);
+
+struct dst_entry *inet6_csk_update_pmtu(struct sock *sk, u32 mtu)
+{
+	struct dst_entry *dst = inet6_csk_route_socket(sk);
+
+	if (IS_ERR(dst))
+		return NULL;
+	dst->ops->update_pmtu(dst, sk, NULL, mtu);
+
+	return inet6_csk_route_socket(sk);
+}
+EXPORT_SYMBOL_GPL(inet6_csk_update_pmtu);
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 61d106597296..db3284667968 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -609,10 +609,10 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		if (rel_info > dst_mtu(skb_dst(skb2)))
 			goto out;
 
-		skb_dst(skb2)->ops->update_pmtu(skb_dst(skb2), rel_info);
+		skb_dst(skb2)->ops->update_pmtu(skb_dst(skb2), NULL, skb2, rel_info);
 	}
 	if (rel_type == ICMP_REDIRECT)
-		skb_dst(skb2)->ops->redirect(skb_dst(skb2), skb2);
+		skb_dst(skb2)->ops->redirect(skb_dst(skb2), NULL, skb2);
 
 	icmp_send(skb2, rel_type, rel_code, htonl(rel_info));
 
@@ -952,7 +952,7 @@ static int ip6_tnl_xmit2(struct sk_buff *skb,
 	if (mtu < IPV6_MIN_MTU)
 		mtu = IPV6_MIN_MTU;
 	if (skb_dst(skb))
-		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu);
+		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
 	if (skb->len > mtu) {
 		*pmtu = mtu;
 		err = -EMSGSIZE;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 412fad809a3b..84f6564dd372 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -78,8 +78,10 @@ static int		 ip6_dst_gc(struct dst_ops *ops);
 static int		ip6_pkt_discard(struct sk_buff *skb);
 static int		ip6_pkt_discard_out(struct sk_buff *skb);
 static void		ip6_link_failure(struct sk_buff *skb);
-static void		ip6_rt_update_pmtu(struct dst_entry *dst, u32 mtu);
-static void		rt6_do_redirect(struct dst_entry *dst, struct sk_buff *skb);
+static void		ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
+					   struct sk_buff *skb, u32 mtu);
+static void		rt6_do_redirect(struct dst_entry *dst, struct sock *sk,
+					struct sk_buff *skb);
 
 #ifdef CONFIG_IPV6_ROUTE_INFO
 static struct rt6_info *rt6_add_route_info(struct net *net,
@@ -187,11 +189,13 @@ static unsigned int ip6_blackhole_mtu(const struct dst_entry *dst)
 	return mtu ? : dst->dev->mtu;
 }
 
-static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu)
+static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk,
+					 struct sk_buff *skb, u32 mtu)
 {
 }
 
-static void ip6_rt_blackhole_redirect(struct dst_entry *dst, struct sk_buff *skb)
+static void ip6_rt_blackhole_redirect(struct dst_entry *dst, struct sock *sk,
+				      struct sk_buff *skb)
 {
 }
 
@@ -1071,7 +1075,8 @@ static void ip6_link_failure(struct sk_buff *skb)
 	}
 }
 
-static void ip6_rt_update_pmtu(struct dst_entry *dst, u32 mtu)
+static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
+			       struct sk_buff *skb, u32 mtu)
 {
 	struct rt6_info *rt6 = (struct rt6_info*)dst;
 
@@ -1108,7 +1113,7 @@ void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,
 
 	dst = ip6_route_output(net, NULL, &fl6);
 	if (!dst->error)
-		ip6_rt_update_pmtu(dst, ntohl(mtu));
+		ip6_rt_update_pmtu(dst, NULL, skb, ntohl(mtu));
 	dst_release(dst);
 }
 EXPORT_SYMBOL_GPL(ip6_update_pmtu);
@@ -1136,7 +1141,7 @@ void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark)
 
 	dst = ip6_route_output(net, NULL, &fl6);
 	if (!dst->error)
-		rt6_do_redirect(dst, skb);
+		rt6_do_redirect(dst, NULL, skb);
 	dst_release(dst);
 }
 EXPORT_SYMBOL_GPL(ip6_redirect);
@@ -1639,7 +1644,7 @@ static int ip6_route_del(struct fib6_config *cfg)
 	return err;
 }
 
-static void rt6_do_redirect(struct dst_entry *dst, struct sk_buff *skb)
+static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb)
 {
 	struct net *net = dev_net(skb->dev);
 	struct netevent_redirect netevent;
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index fbf1622fdeef..3bd1bfc01f85 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -807,7 +807,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 		}
 
 		if (tunnel->parms.iph.daddr && skb_dst(skb))
-			skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu);
+			skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
 
 		if (skb->len > mtu) {
 			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 3071f377145c..c9dabdd832d7 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -367,7 +367,7 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
 
 		if (dst)
-			dst->ops->redirect(dst,skb);
+			dst->ops->redirect(dst, sk, skb);
 	}
 
 	if (type == ICMPV6_PKT_TOOBIG) {
@@ -378,43 +378,14 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))
 			goto out;
 
-		/* icmp should have updated the destination cache entry */
-		dst = __sk_dst_check(sk, np->dst_cookie);
-
-		if (dst == NULL) {
-			struct inet_sock *inet = inet_sk(sk);
-			struct flowi6 fl6;
-
-			/* BUGGG_FUTURE: Again, it is not clear how
-			   to handle rthdr case. Ignore this complexity
-			   for now.
-			 */
-			memset(&fl6, 0, sizeof(fl6));
-			fl6.flowi6_proto = IPPROTO_TCP;
-			fl6.daddr = np->daddr;
-			fl6.saddr = np->saddr;
-			fl6.flowi6_oif = sk->sk_bound_dev_if;
-			fl6.flowi6_mark = sk->sk_mark;
-			fl6.fl6_dport = inet->inet_dport;
-			fl6.fl6_sport = inet->inet_sport;
-			security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
-
-			dst = ip6_dst_lookup_flow(sk, &fl6, NULL, false);
-			if (IS_ERR(dst)) {
-				sk->sk_err_soft = -PTR_ERR(dst);
-				goto out;
-			}
-
-		} else
-			dst_hold(dst);
-
-		dst->ops->update_pmtu(dst, ntohl(info));
+		dst = inet6_csk_update_pmtu(sk, ntohl(info));
+		if (!dst)
+			goto out;
 
 		if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) {
 			tcp_sync_mss(sk, dst_mtu(dst));
 			tcp_simple_retransmit(sk);
-		} /* else let the usual retransmit timer handle it */
-		dst_release(dst);
+		}
 		goto out;
 	}
 
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index f5a9cb8257b9..ef39812107b1 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -207,20 +207,22 @@ static inline int xfrm6_garbage_collect(struct dst_ops *ops)
 	return dst_entries_get_fast(ops) > ops->gc_thresh * 2;
 }
 
-static void xfrm6_update_pmtu(struct dst_entry *dst, u32 mtu)
+static void xfrm6_update_pmtu(struct dst_entry *dst, struct sock *sk,
+			      struct sk_buff *skb, u32 mtu)
 {
 	struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
 	struct dst_entry *path = xdst->route;
 
-	path->ops->update_pmtu(path, mtu);
+	path->ops->update_pmtu(path, sk, skb, mtu);
 }
 
-static void xfrm6_redirect(struct dst_entry *dst, struct sk_buff *skb)
+static void xfrm6_redirect(struct dst_entry *dst, struct sock *sk,
+			   struct sk_buff *skb)
 {
 	struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
 	struct dst_entry *path = xdst->route;
 
-	path->ops->redirect(path, skb);
+	path->ops->redirect(path, sk, skb);
 }
 
 static void xfrm6_dst_destroy(struct dst_entry *dst)
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index 71d6ecb65926..65b616ae1716 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -797,7 +797,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 		goto tx_error_put;
 	}
 	if (skb_dst(skb))
-		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu);
+		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
 
 	df |= (old_iph->frag_off & htons(IP_DF));
 
@@ -913,7 +913,7 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 		goto tx_error_put;
 	}
 	if (skb_dst(skb))
-		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu);
+		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
 
 	if (mtu < ntohs(old_iph->payload_len) + sizeof(struct ipv6hdr) &&
 	    !skb_is_gso(skb)) {
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index b16517ee1aaf..8cf348e62e74 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -1360,7 +1360,7 @@ struct sctp_transport *sctp_assoc_choose_alter_transport(
 /* Update the association's pmtu and frag_point by going through all the
  * transports. This routine is called when a transport's PMTU has changed.
  */
-void sctp_assoc_sync_pmtu(struct sctp_association *asoc)
+void sctp_assoc_sync_pmtu(struct sock *sk, struct sctp_association *asoc)
 {
 	struct sctp_transport *t;
 	__u32 pmtu = 0;
@@ -1372,7 +1372,7 @@ void sctp_assoc_sync_pmtu(struct sctp_association *asoc)
 	list_for_each_entry(t, &asoc->peer.transport_addr_list,
 				transports) {
 		if (t->pmtu_pending && t->dst) {
-			sctp_transport_update_pmtu(t, dst_mtu(t->dst));
+			sctp_transport_update_pmtu(sk, t, dst_mtu(t->dst));
 			t->pmtu_pending = 0;
 		}
 		if (!pmtu || (t->pathmtu < pmtu))
diff --git a/net/sctp/input.c b/net/sctp/input.c
index f050d45faa98..c201b26879a1 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -408,10 +408,10 @@ void sctp_icmp_frag_needed(struct sock *sk, struct sctp_association *asoc,
 
 	if (t->param_flags & SPP_PMTUD_ENABLE) {
 		/* Update transports view of the MTU */
-		sctp_transport_update_pmtu(t, pmtu);
+		sctp_transport_update_pmtu(sk, t, pmtu);
 
 		/* Update association pmtu. */
-		sctp_assoc_sync_pmtu(asoc);
+		sctp_assoc_sync_pmtu(sk, asoc);
 	}
 
 	/* Retransmit with the new pmtu setting.
@@ -432,7 +432,7 @@ void sctp_icmp_redirect(struct sock *sk, struct sctp_transport *t,
 		return;
 	dst = sctp_transport_dst_check(t);
 	if (dst)
-		dst->ops->redirect(dst, skb);
+		dst->ops->redirect(dst, sk, skb);
 }
 
 /*
diff --git a/net/sctp/output.c b/net/sctp/output.c
index 539f35d07f4e..838e18b4d7ea 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -410,7 +410,7 @@ int sctp_packet_transmit(struct sctp_packet *packet)
 	if (!sctp_transport_dst_check(tp)) {
 		sctp_transport_route(tp, NULL, sctp_sk(sk));
 		if (asoc && (asoc->param_flags & SPP_PMTUD_ENABLE)) {
-			sctp_assoc_sync_pmtu(asoc);
+			sctp_assoc_sync_pmtu(sk, asoc);
 		}
 	}
 	dst = dst_clone(tp->dst);
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index b3b8a8d813eb..74bd3c47350a 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -1853,7 +1853,7 @@ SCTP_STATIC int sctp_sendmsg(struct kiocb *iocb, struct sock *sk,
 	}
 
 	if (asoc->pmtu_pending)
-		sctp_assoc_pending_pmtu(asoc);
+		sctp_assoc_pending_pmtu(sk, asoc);
 
 	/* If fragmentation is disabled and the message length exceeds the
 	 * association fragmentation point, return EMSGSIZE.  The I-D
@@ -2365,7 +2365,7 @@ static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params,
 	if ((params->spp_flags & SPP_PMTUD_DISABLE) && params->spp_pathmtu) {
 		if (trans) {
 			trans->pathmtu = params->spp_pathmtu;
-			sctp_assoc_sync_pmtu(asoc);
+			sctp_assoc_sync_pmtu(sctp_opt2sk(sp), asoc);
 		} else if (asoc) {
 			asoc->pathmtu = params->spp_pathmtu;
 			sctp_frag_point(asoc, params->spp_pathmtu);
@@ -2382,7 +2382,7 @@ static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params,
 				(trans->param_flags & ~SPP_PMTUD) | pmtud_change;
 			if (update) {
 				sctp_transport_pmtu(trans, sctp_opt2sk(sp));
-				sctp_assoc_sync_pmtu(asoc);
+				sctp_assoc_sync_pmtu(sctp_opt2sk(sp), asoc);
 			}
 		} else if (asoc) {
 			asoc->param_flags =
diff --git a/net/sctp/transport.c b/net/sctp/transport.c
index 1dcceb6e0ce6..a6b7ee9ce28a 100644
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -228,7 +228,7 @@ void sctp_transport_pmtu(struct sctp_transport *transport, struct sock *sk)
 		transport->pathmtu = SCTP_DEFAULT_MAXSEGMENT;
 }
 
-void sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu)
+void sctp_transport_update_pmtu(struct sock *sk, struct sctp_transport *t, u32 pmtu)
 {
 	struct dst_entry *dst;
 
@@ -245,8 +245,16 @@ void sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu)
 	}
 
 	dst = sctp_transport_dst_check(t);
-	if (dst)
-		dst->ops->update_pmtu(dst, pmtu);
+	if (!dst)
+		t->af_specific->get_dst(t, &t->saddr, &t->fl, sk);
+
+	if (dst) {
+		dst->ops->update_pmtu(dst, sk, NULL, pmtu);
+
+		dst = sctp_transport_dst_check(t);
+		if (!dst)
+			t->af_specific->get_dst(t, &t->saddr, &t->fl, sk);
+	}
 }
 
 /* Caches the dst entry and source address for a transport's destination