sctp: Implement quick failover draft from tsvwg

I've seen several attempts recently made to do quick failover of sctp transports
by reducing various retransmit timers and counters.  While its possible to
implement a faster failover on multihomed sctp associations, its not
particularly robust, in that it can lead to unneeded retransmits, as well as
false connection failures due to intermittent latency on a network.

Instead, lets implement the new ietf quick failover draft found here:
http://tools.ietf.org/html/draft-nishida-tsvwg-sctp-failover-05

This will let the sctp stack identify transports that have had a small number of
errors, and avoid using them quickly until their reliability can be
re-established.  I've tested this out on two virt guests connected via multiple
isolated virt networks and believe its in compliance with the above draft and
works well.

Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
CC: Vlad Yasevich <vyasevich@gmail.com>
CC: Sridhar Samudrala <sri@us.ibm.com>
CC: "David S. Miller" <davem@davemloft.net>
CC: linux-sctp@vger.kernel.org
CC: joe@perches.com
Acked-by: Vlad Yasevich <vyasevich@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 30 insertions, 7 deletions

diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 8cf348e62e7..ebaef3ed606 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -124,6 +124,8 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a
 	 * socket values.
 	 */
 	asoc->max_retrans = sp->assocparams.sasoc_asocmaxrxt;
+	asoc->pf_retrans  = sctp_pf_retrans;
+
 	asoc->rto_initial = msecs_to_jiffies(sp->rtoinfo.srto_initial);
 	asoc->rto_max = msecs_to_jiffies(sp->rtoinfo.srto_max);
 	asoc->rto_min = msecs_to_jiffies(sp->rtoinfo.srto_min);
@@ -686,6 +688,9 @@ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *asoc,
 	/* Set the path max_retrans.  */
 	peer->pathmaxrxt = asoc->pathmaxrxt;
 
+	/* And the partial failure retrnas threshold */
+	peer->pf_retrans = asoc->pf_retrans;
+
 	/* Initialize the peer's SACK delay timeout based on the
 	 * association configured value.
 	 */
@@ -841,6 +846,7 @@ void sctp_assoc_control_transport(struct sctp_association *asoc,
 	struct sctp_ulpevent *event;
 	struct sockaddr_storage addr;
 	int spc_state = 0;
+	bool ulp_notify = true;
 
 	/* Record the transition on the transport.  */
 	switch (command) {
@@ -854,6 +860,14 @@ void sctp_assoc_control_transport(struct sctp_association *asoc,
 			spc_state = SCTP_ADDR_CONFIRMED;
 		else
 			spc_state = SCTP_ADDR_AVAILABLE;
+		/* Don't inform ULP about transition from PF to
+		 * active state and set cwnd to 1, see SCTP
+		 * Quick failover draft section 5.1, point 5
+		 */
+		if (transport->state == SCTP_PF) {
+			ulp_notify = false;
+			transport->cwnd = 1;
+		}
 		transport->state = SCTP_ACTIVE;
 		break;
 
@@ -872,6 +886,11 @@ void sctp_assoc_control_transport(struct sctp_association *asoc,
 		spc_state = SCTP_ADDR_UNREACHABLE;
 		break;
 
+	case SCTP_TRANSPORT_PF:
+		transport->state = SCTP_PF;
+		ulp_notify = false;
+		break;
+
 	default:
 		return;
 	}
@@ -879,12 +898,15 @@ void sctp_assoc_control_transport(struct sctp_association *asoc,
 	/* Generate and send a SCTP_PEER_ADDR_CHANGE notification to the
 	 * user.
 	 */
-	memset(&addr, 0, sizeof(struct sockaddr_storage));
-	memcpy(&addr, &transport->ipaddr, transport->af_specific->sockaddr_len);
-	event = sctp_ulpevent_make_peer_addr_change(asoc, &addr,
-				0, spc_state, error, GFP_ATOMIC);
-	if (event)
-		sctp_ulpq_tail_event(&asoc->ulpq, event);
+	if (ulp_notify) {
+		memset(&addr, 0, sizeof(struct sockaddr_storage));
+		memcpy(&addr, &transport->ipaddr,
+		       transport->af_specific->sockaddr_len);
+		event = sctp_ulpevent_make_peer_addr_change(asoc, &addr,
+					0, spc_state, error, GFP_ATOMIC);
+		if (event)
+			sctp_ulpq_tail_event(&asoc->ulpq, event);
+	}
 
 	/* Select new active and retran paths. */
 
@@ -900,7 +922,8 @@ void sctp_assoc_control_transport(struct sctp_association *asoc,
 			transports) {
 
 		if ((t->state == SCTP_INACTIVE) ||
-		    (t->state == SCTP_UNCONFIRMED))
+		    (t->state == SCTP_UNCONFIRMED) ||
+		    (t->state == SCTP_PF))
 			continue;
 		if (!first || t->last_time_heard > first->last_time_heard) {
 			second = first;