sctp: use the pmtu from the icmp packet to update transport pathmtu

Other than asoc pmtu sync from all transports, sctp_assoc_sync_pmtu
is also processing transport pmtu_pending by icmp packets. But it's
meaningless to use sctp_dst_mtu(t->dst) as new pmtu for a transport.

The right pmtu value should come from the icmp packet, and it would
be saved into transport->mtu_info in this patch and used later when
the pmtu sync happens in sctp_sendmsg_to_asoc or sctp_packet_config.

Besides, without this patch, as pmtu can only be updated correctly
when receiving a icmp packet and no place is holding sock lock, it
will take long time if the sock is busy with sending packets.

Note that it doesn't process transport->mtu_info in .release_cb(),
as there is no enough information for pmtu update, like for which
asoc or transport. It is not worth traversing all asocs to check
pmtu_pending. So unlike tcp, sctp does this in tx path, for which
mtu_info needs to be atomic_t.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 11 insertions, 1 deletions

diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 28a7c8e44636..a11f93790476 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -876,6 +876,8 @@ struct sctp_transport {
         unsigned long sackdelay;
         __u32 sackfreq;
 
+        atomic_t mtu_info;
+
         /* When was the last time that we heard from this transport? We use
          * this to pick new active and retran paths.
          */
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 297d9cf960b9..a827a1f562bf 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -1450,7 +1450,8 @@ void sctp_assoc_sync_pmtu(struct sctp_association *asoc)
         /* Get the lowest pmtu of all the transports. */
         list_for_each_entry(t, &asoc->peer.transport_addr_list, transports) {
                 if (t->pmtu_pending && t->dst) {
-                        sctp_transport_update_pmtu(t, sctp_dst_mtu(t->dst));
+                        sctp_transport_update_pmtu(t,
+                                                   atomic_read(&t->mtu_info));
                         t->pmtu_pending = 0;
                 }
                 if (!pmtu || (t->pathmtu < pmtu))
diff --git a/net/sctp/input.c b/net/sctp/input.c
index 9bbc5f92c941..5c36a99882ed 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -395,6 +395,7 @@ void sctp_icmp_frag_needed(struct sock *sk, struct sctp_association *asoc,
                 return;
 
         if (sock_owned_by_user(sk)) {
+                atomic_set(&t->mtu_info, pmtu);
                 asoc->pmtu_pending = 1;
                 t->pmtu_pending = 1;
                 return;
diff --git a/net/sctp/output.c b/net/sctp/output.c
index 7f849b01ec8e..67939ad99c01 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -120,6 +120,12 @@ void sctp_packet_config(struct sctp_packet *packet, __u32 vtag,
                         sctp_assoc_sync_pmtu(asoc);
         }
 
+        if (asoc->pmtu_pending) {
+                if (asoc->param_flags & SPP_PMTUD_ENABLE)
+                        sctp_assoc_sync_pmtu(asoc);
+                asoc->pmtu_pending = 0;
+        }
+
         /* If there a is a prepend chunk stick it on the list before
          * any other chunks get appended.
          */