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>

5 files changed, 20 insertions, 12 deletions

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