sctp: Fix the RTO-doubling on idle-link heartbeats

[safe/jmp/linux-2.6] / net / sctp / transport.c

diff --git a/net/sctp/transport.c b/net/sctp/transport.c
index f4938f6..5c29b14 100644 (file)
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -79,6 +79,8 @@ static struct sctp_transport *sctp_transport_init(struct sctp_transport *peer,
        peer->rttvar = 0;
        peer->srtt = 0;
        peer->rto_pending = 0;
+       peer->hb_sent = 0;
+       peer->fast_recovery = 0;
 
        peer->last_time_heard = jiffies;
        peer->last_time_used = jiffies;
@@ -99,6 +101,9 @@ static struct sctp_transport *sctp_transport_init(struct sctp_transport *peer,
        INIT_LIST_HEAD(&peer->send_ready);
        INIT_LIST_HEAD(&peer->transports);
 
+       peer->T3_rtx_timer.expires = 0;
+       peer->hb_timer.expires = 0;
+
        setup_timer(&peer->T3_rtx_timer, sctp_generate_t3_rtx_event,
                        (unsigned long)peer);
        setup_timer(&peer->hb_timer, sctp_generate_heartbeat_event,
@@ -190,7 +195,7 @@ static void sctp_transport_destroy(struct sctp_transport *transport)
 /* Start T3_rtx timer if it is not already running and update the heartbeat
  * timer.  This routine is called every time a DATA chunk is sent.
  */
-void sctp_transport_reset_timers(struct sctp_transport *transport)
+void sctp_transport_reset_timers(struct sctp_transport *transport, int force)
 {
        /* RFC 2960 6.3.2 Retransmission Timer Rules
         *
@@ -200,7 +205,7 @@ void sctp_transport_reset_timers(struct sctp_transport *transport)
         * address.
         */
 
-       if (!timer_pending(&transport->T3_rtx_timer))
+       if (force || !timer_pending(&transport->T3_rtx_timer))
                if (!mod_timer(&transport->T3_rtx_timer,
                               jiffies + transport->rto))
                        sctp_transport_hold(transport);
@@ -291,7 +296,7 @@ void sctp_transport_route(struct sctp_transport *transport,
        if (saddr)
                memcpy(&transport->saddr, saddr, sizeof(union sctp_addr));
        else
-               af->get_saddr(asoc, dst, daddr, &transport->saddr);
+               af->get_saddr(opt, asoc, dst, daddr, &transport->saddr);
 
        transport->dst = dst;
        if ((transport->param_flags & SPP_PMTUD_DISABLE) && transport->pathmtu) {
@@ -403,11 +408,16 @@ void sctp_transport_raise_cwnd(struct sctp_transport *transport,
        cwnd = transport->cwnd;
        flight_size = transport->flight_size;
 
+       /* See if we need to exit Fast Recovery first */
+       if (transport->fast_recovery &&
+           TSN_lte(transport->fast_recovery_exit, sack_ctsn))
+               transport->fast_recovery = 0;
+
        /* The appropriate cwnd increase algorithm is performed if, and only
-        * if the cumulative TSN has advanced and the congestion window is
+        * if the cumulative TSN whould advanced and the congestion window is
         * being fully utilized.
         */
-       if ((transport->asoc->ctsn_ack_point >= sack_ctsn) ||
+       if (TSN_lte(sack_ctsn, transport->asoc->ctsn_ack_point) ||
            (flight_size < cwnd))
                return;
 
@@ -416,17 +426,23 @@ void sctp_transport_raise_cwnd(struct sctp_transport *transport,
        pmtu = transport->asoc->pathmtu;
 
        if (cwnd <= ssthresh) {
-               /* RFC 2960 7.2.1, sctpimpguide-05 2.14.2 When cwnd is less
-                * than or equal to ssthresh an SCTP endpoint MUST use the
-                * slow start algorithm to increase cwnd only if the current
-                * congestion window is being fully utilized and an incoming
-                * SACK advances the Cumulative TSN Ack Point. Only when these
-                * two conditions are met can the cwnd be increased otherwise
-                * the cwnd MUST not be increased. If these conditions are met
-                * then cwnd MUST be increased by at most the lesser of
-                * 1) the total size of the previously outstanding DATA
-                * chunk(s) acknowledged, and 2) the destination's path MTU.
+               /* RFC 4960 7.2.1
+                * o  When cwnd is less than or equal to ssthresh, an SCTP
+                *    endpoint MUST use the slow-start algorithm to increase
+                *    cwnd only if the current congestion window is being fully
+                *    utilized, an incoming SACK advances the Cumulative TSN
+                *    Ack Point, and the data sender is not in Fast Recovery.
+                *    Only when these three conditions are met can the cwnd be
+                *    increased; otherwise, the cwnd MUST not be increased.
+                *    If these conditions are met, then cwnd MUST be increased
+                *    by, at most, the lesser of 1) the total size of the
+                *    previously outstanding DATA chunk(s) acknowledged, and
+                *    2) the destination's path MTU.  This upper bound protects
+                *    against the ACK-Splitting attack outlined in [SAVAGE99].
                 */
+               if (transport->fast_recovery)
+                       return;
+
                if (bytes_acked > pmtu)
                        cwnd += pmtu;
                else
@@ -502,6 +518,13 @@ void sctp_transport_lower_cwnd(struct sctp_transport *transport,
                 *      cwnd = ssthresh
                 *      partial_bytes_acked = 0
                 */
+               if (transport->fast_recovery)
+                       return;
+
+               /* Mark Fast recovery */
+               transport->fast_recovery = 1;
+               transport->fast_recovery_exit = transport->asoc->next_tsn - 1;
+
                transport->ssthresh = max(transport->cwnd/2,
                                          4*transport->asoc->pathmtu);
                transport->cwnd = transport->ssthresh;
@@ -586,6 +609,8 @@ void sctp_transport_reset(struct sctp_transport *t)
        t->flight_size = 0;
        t->error_count = 0;
        t->rto_pending = 0;
+       t->hb_sent = 0;
+       t->fast_recovery = 0;
 
        /* Initialize the state information for SFR-CACC */
        t->cacc.changeover_active = 0;