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, 29 insertions, 4 deletions

diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index 8716da1a859..fe99628e125 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -76,6 +76,8 @@ static int sctp_side_effects(sctp_event_t event_type, sctp_subtype_t subtype,
 			     sctp_cmd_seq_t *commands,
 			     gfp_t gfp);
 
+static void sctp_cmd_hb_timer_update(sctp_cmd_seq_t *cmds,
+				     struct sctp_transport *t);
 /********************************************************************
  * Helper functions
  ********************************************************************/
@@ -470,7 +472,8 @@ sctp_timer_event_t *sctp_timer_events[SCTP_NUM_TIMEOUT_TYPES] = {
  * notification SHOULD be sent to the upper layer.
  *
  */
-static void sctp_do_8_2_transport_strike(struct sctp_association *asoc,
+static void sctp_do_8_2_transport_strike(sctp_cmd_seq_t *commands,
+					 struct sctp_association *asoc,
 					 struct sctp_transport *transport,
 					 int is_hb)
 {
@@ -495,6 +498,23 @@ static void sctp_do_8_2_transport_strike(struct sctp_association *asoc,
 			transport->error_count++;
 	}
 
+	/* If the transport error count is greater than the pf_retrans
+	 * threshold, and less than pathmaxrtx, then mark this transport
+	 * as Partially Failed, ee SCTP Quick Failover Draft, secon 5.1,
+	 * point 1
+	 */
+	if ((transport->state != SCTP_PF) &&
+	   (asoc->pf_retrans < transport->pathmaxrxt) &&
+	   (transport->error_count > asoc->pf_retrans)) {
+
+		sctp_assoc_control_transport(asoc, transport,
+					     SCTP_TRANSPORT_PF,
+					     0);
+
+		/* Update the hb timer to resend a heartbeat every rto */
+		sctp_cmd_hb_timer_update(commands, transport);
+	}
+
 	if (transport->state != SCTP_INACTIVE &&
 	    (transport->error_count > transport->pathmaxrxt)) {
 		SCTP_DEBUG_PRINTK_IPADDR("transport_strike:association %p",
@@ -699,6 +719,10 @@ static void sctp_cmd_transport_on(sctp_cmd_seq_t *cmds,
 					     SCTP_HEARTBEAT_SUCCESS);
 	}
 
+	if (t->state == SCTP_PF)
+		sctp_assoc_control_transport(asoc, t, SCTP_TRANSPORT_UP,
+					     SCTP_HEARTBEAT_SUCCESS);
+
 	/* The receiver of the HEARTBEAT ACK should also perform an
 	 * RTT measurement for that destination transport address
 	 * using the time value carried in the HEARTBEAT ACK chunk.
@@ -1565,8 +1589,8 @@ static int sctp_cmd_interpreter(sctp_event_t event_type,
 
 		case SCTP_CMD_STRIKE:
 			/* Mark one strike against a transport.  */
-			sctp_do_8_2_transport_strike(asoc, cmd->obj.transport,
-						    0);
+			sctp_do_8_2_transport_strike(commands, asoc,
+						    cmd->obj.transport, 0);
 			break;
 
 		case SCTP_CMD_TRANSPORT_IDLE:
@@ -1576,7 +1600,8 @@ static int sctp_cmd_interpreter(sctp_event_t event_type,
 
 		case SCTP_CMD_TRANSPORT_HB_SENT:
 			t = cmd->obj.transport;
-			sctp_do_8_2_transport_strike(asoc, t, 1);
+			sctp_do_8_2_transport_strike(commands, asoc,
+						     t, 1);
 			t->hb_sent = 1;
 			break;