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>

6 files changed, 63 insertions, 64 deletions

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)