6 files changed, 143 insertions, 72 deletions

diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 7b79d1e781a8..d5cc731b6798 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -1206,6 +1206,9 @@ void sctp_assoc_update_retran_path(struct sctp_association *asoc)
         struct list_head *head = &asoc->peer.transport_addr_list;
         struct list_head *pos;
 
+        if (asoc->peer.transport_count == 1)
+                return;
+
         /* Find the next transport in a round-robin fashion. */
         t = asoc->peer.retran_path;
         pos = &t->transports;
@@ -1220,6 +1223,15 @@ void sctp_assoc_update_retran_path(struct sctp_association *asoc)
 
                 t = list_entry(pos, struct sctp_transport, transports);
 
+                /* We have exhausted the list, but didn't find any
+                 * other active transports.  If so, use the next
+                 * transport.
+                 */
+                if (t == asoc->peer.retran_path) {
+                        t = next;
+                        break;
+                }
+
                 /* Try to find an active transport. */
 
                 if ((t->state == SCTP_ACTIVE) ||
@@ -1232,15 +1244,6 @@ void sctp_assoc_update_retran_path(struct sctp_association *asoc)
                         if (!next)
                                 next = t;
                 }
-
-                /* We have exhausted the list, but didn't find any
-                 * other active transports.  If so, use the next
-                 * transport.
-                 */
-                if (t == asoc->peer.retran_path) {
-                        t = next;
-                        break;
-                }
         }
 
         asoc->peer.retran_path = t;
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index e45e44c60635..a2f4d4d51593 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -299,7 +299,8 @@ static inline int sctp_v6_addr_match_len(union sctp_addr *s1,
 /* Fills in the source address(saddr) based on the destination address(daddr)
  * and asoc's bind address list.
  */
-static void sctp_v6_get_saddr(struct sctp_association *asoc,
+static void sctp_v6_get_saddr(struct sctp_sock *sk,
+                              struct sctp_association *asoc,
                               struct dst_entry *dst,
                               union sctp_addr *daddr,
                               union sctp_addr *saddr)
@@ -318,7 +319,7 @@ static void sctp_v6_get_saddr(struct sctp_association *asoc,
         if (!asoc) {
                 ipv6_dev_get_saddr(dst ? ip6_dst_idev(dst)->dev : NULL,
                                    &daddr->v6.sin6_addr,
-                                   inet6_sk(asoc->base.sk)->srcprefs,
+                                   inet6_sk(&sk->inet.sk)->srcprefs,
                                    &saddr->v6.sin6_addr);
                 SCTP_DEBUG_PRINTK("saddr from ipv6_get_saddr: " NIP6_FMT "\n",
                                   NIP6(saddr->v6.sin6_addr));
@@ -726,6 +727,11 @@ static void sctp_v6_seq_dump_addr(struct seq_file *seq, union sctp_addr *addr)
         seq_printf(seq, NIP6_FMT " ", NIP6(addr->v6.sin6_addr));
 }
 
+static void sctp_v6_ecn_capable(struct sock *sk)
+{
+        inet6_sk(sk)->tclass |= INET_ECN_ECT_0;
+}
+
 /* Initialize a PF_INET6 socket msg_name. */
 static void sctp_inet6_msgname(char *msgname, int *addr_len)
 {
@@ -996,6 +1002,7 @@ static struct sctp_af sctp_af_inet6 = {
         .skb_iif           = sctp_v6_skb_iif,
         .is_ce             = sctp_v6_is_ce,
         .seq_dump_addr     = sctp_v6_seq_dump_addr,
+        .ecn_capable       = sctp_v6_ecn_capable,
         .net_header_len    = sizeof(struct ipv6hdr),
         .sockaddr_len      = sizeof(struct sockaddr_in6),
 #ifdef CONFIG_COMPAT
diff --git a/net/sctp/output.c b/net/sctp/output.c
index cf4f9fb6819d..6d45bae93b46 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -548,7 +548,7 @@ int sctp_packet_transmit(struct sctp_packet *packet)
          * Note: The works for IPv6 layer checks this bit too later
          * in transmission.  See IP6_ECN_flow_xmit().
          */
-        INET_ECN_xmit(nskb->sk);
+        (*tp->af_specific->ecn_capable)(nskb->sk);
 
         /* Set up the IP options.  */
         /* BUG: not implemented
diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c
index 59edfd25a19c..ace6770e9048 100644
--- a/net/sctp/outqueue.c
+++ b/net/sctp/outqueue.c
@@ -208,6 +208,7 @@ void sctp_outq_init(struct sctp_association *asoc, struct sctp_outq *q)
         INIT_LIST_HEAD(&q->sacked);
         INIT_LIST_HEAD(&q->abandoned);
 
+        q->fast_rtx = 0;
         q->outstanding_bytes = 0;
         q->empty = 1;
         q->cork  = 0;
@@ -500,6 +501,7 @@ void sctp_retransmit(struct sctp_outq *q, struct sctp_transport *transport,
         case SCTP_RTXR_FAST_RTX:
                 SCTP_INC_STATS(SCTP_MIB_FAST_RETRANSMITS);
                 sctp_transport_lower_cwnd(transport, SCTP_LOWER_CWND_FAST_RTX);
+                q->fast_rtx = 1;
                 break;
         case SCTP_RTXR_PMTUD:
                 SCTP_INC_STATS(SCTP_MIB_PMTUD_RETRANSMITS);
@@ -518,9 +520,15 @@ void sctp_retransmit(struct sctp_outq *q, struct sctp_transport *transport,
          * the sender SHOULD try to advance the "Advanced.Peer.Ack.Point" by
          * following the procedures outlined in C1 - C5.
          */
-        sctp_generate_fwdtsn(q, q->asoc->ctsn_ack_point);
+        if (reason == SCTP_RTXR_T3_RTX)
+                sctp_generate_fwdtsn(q, q->asoc->ctsn_ack_point);
 
-        error = sctp_outq_flush(q, /* rtx_timeout */ 1);
+        /* Flush the queues only on timeout, since fast_rtx is only
+         * triggered during sack processing and the queue
+         * will be flushed at the end.
+         */
+        if (reason != SCTP_RTXR_FAST_RTX)
+                error = sctp_outq_flush(q, /* rtx_timeout */ 1);
 
         if (error)
                 q->asoc->base.sk->sk_err = -error;
@@ -538,17 +546,23 @@ static int sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt,
                                int rtx_timeout, int *start_timer)
 {
         struct list_head *lqueue;
-        struct list_head *lchunk;
         struct sctp_transport *transport = pkt->transport;
         sctp_xmit_t status;
         struct sctp_chunk *chunk, *chunk1;
         struct sctp_association *asoc;
+        int fast_rtx;
         int error = 0;
+        int timer = 0;
+        int done = 0;
 
         asoc = q->asoc;
         lqueue = &q->retransmit;
+        fast_rtx = q->fast_rtx;
 
-        /* RFC 2960 6.3.3 Handle T3-rtx Expiration
+        /* This loop handles time-out retransmissions, fast retransmissions,
+         * and retransmissions due to opening of whindow.
+         *
+         * RFC 2960 6.3.3 Handle T3-rtx Expiration
          *
          * E3) Determine how many of the earliest (i.e., lowest TSN)
          * outstanding DATA chunks for the address for which the
@@ -563,12 +577,12 @@ static int sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt,
          * [Just to be painfully clear, if we are retransmitting
          * because a timeout just happened, we should send only ONE
          * packet of retransmitted data.]
+         *
+         * For fast retransmissions we also send only ONE packet.  However,
+         * if we are just flushing the queue due to open window, we'll
+         * try to send as much as possible.
          */
-        lchunk = sctp_list_dequeue(lqueue);
-
-        while (lchunk) {
-                chunk = list_entry(lchunk, struct sctp_chunk,
-                                   transmitted_list);
+        list_for_each_entry_safe(chunk, chunk1, lqueue, transmitted_list) {
 
                 /* Make sure that Gap Acked TSNs are not retransmitted.  A
                  * simple approach is just to move such TSNs out of the
@@ -576,58 +590,60 @@ static int sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt,
                  * next chunk.
                  */
                 if (chunk->tsn_gap_acked) {
-                        list_add_tail(lchunk, &transport->transmitted);
-                        lchunk = sctp_list_dequeue(lqueue);
+                        list_del(&chunk->transmitted_list);
+                        list_add_tail(&chunk->transmitted_list,
+                                        &transport->transmitted);
                         continue;
                 }
 
+                /* If we are doing fast retransmit, ignore non-fast_rtransmit
+                 * chunks
+                 */
+                if (fast_rtx && !chunk->fast_retransmit)
+                        continue;
+
                 /* Attempt to append this chunk to the packet. */
                 status = sctp_packet_append_chunk(pkt, chunk);
 
                 switch (status) {
                 case SCTP_XMIT_PMTU_FULL:
                         /* Send this packet.  */
-                        if ((error = sctp_packet_transmit(pkt)) == 0)
-                                *start_timer = 1;
+                        error = sctp_packet_transmit(pkt);
 
                         /* If we are retransmitting, we should only
                          * send a single packet.
                          */
-                        if (rtx_timeout) {
-                                list_add(lchunk, lqueue);
-                                lchunk = NULL;
-                        }
+                        if (rtx_timeout || fast_rtx)
+                                done = 1;
 
-                        /* Bundle lchunk in the next round.  */
+                        /* Bundle next chunk in the next round.  */
                         break;
 
                 case SCTP_XMIT_RWND_FULL:
                         /* Send this packet. */
-                        if ((error = sctp_packet_transmit(pkt)) == 0)
-                                *start_timer = 1;
+                        error = sctp_packet_transmit(pkt);
 
                         /* Stop sending DATA as there is no more room
                          * at the receiver.
                          */
-                        list_add(lchunk, lqueue);
-                        lchunk = NULL;
+                        done = 1;
                         break;
 
                 case SCTP_XMIT_NAGLE_DELAY:
                         /* Send this packet. */
-                        if ((error = sctp_packet_transmit(pkt)) == 0)
-                                *start_timer = 1;
+                        error = sctp_packet_transmit(pkt);
 
                         /* Stop sending DATA because of nagle delay. */
-                        list_add(lchunk, lqueue);
-                        lchunk = NULL;
+                        done = 1;
                         break;
 
                 default:
                         /* The append was successful, so add this chunk to
                          * the transmitted list.
                          */
-                        list_add_tail(lchunk, &transport->transmitted);
+                        list_del(&chunk->transmitted_list);
+                        list_add_tail(&chunk->transmitted_list,
+                                        &transport->transmitted);
 
                         /* Mark the chunk as ineligible for fast retransmit
                          * after it is retransmitted.
@@ -635,27 +651,44 @@ static int sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt,
                         if (chunk->fast_retransmit > 0)
                                 chunk->fast_retransmit = -1;
 
-                        *start_timer = 1;
-                        q->empty = 0;
+                        /* Force start T3-rtx timer when fast retransmitting
+                         * the earliest outstanding TSN
+                         */
+                        if (!timer && fast_rtx &&
+                            ntohl(chunk->subh.data_hdr->tsn) ==
+                                             asoc->ctsn_ack_point + 1)
+                                timer = 2;
 
-                        /* Retrieve a new chunk to bundle. */
-                        lchunk = sctp_list_dequeue(lqueue);
+                        q->empty = 0;
                         break;
                 }
 
-                /* If we are here due to a retransmit timeout or a fast
-                 * retransmit and if there are any chunks left in the retransmit
-                 * queue that could not fit in the PMTU sized packet, they need
-                 * to be marked as ineligible for a subsequent fast retransmit.
-                 */
-                if (rtx_timeout && !lchunk) {
-                        list_for_each_entry(chunk1, lqueue, transmitted_list) {
-                                if (chunk1->fast_retransmit > 0)
-                                        chunk1->fast_retransmit = -1;
-                        }
+                /* Set the timer if there were no errors */
+                if (!error && !timer)
+                        timer = 1;
+
+                if (done)
+                        break;
+        }
+
+        /* If we are here due to a retransmit timeout or a fast
+         * retransmit and if there are any chunks left in the retransmit
+         * queue that could not fit in the PMTU sized packet, they need
+         * to be marked as ineligible for a subsequent fast retransmit.
+         */
+        if (rtx_timeout || fast_rtx) {
+                list_for_each_entry(chunk1, lqueue, transmitted_list) {
+                        if (chunk1->fast_retransmit > 0)
+                                chunk1->fast_retransmit = -1;
                 }
         }
 
+        *start_timer = timer;
+
+        /* Clear fast retransmit hint */
+        if (fast_rtx)
+                q->fast_rtx = 0;
+
         return error;
 }
 
@@ -862,7 +895,8 @@ int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout)
                                                     rtx_timeout, &start_timer);
 
                         if (start_timer)
-                                sctp_transport_reset_timers(transport);
+                                sctp_transport_reset_timers(transport,
+                                                            start_timer-1);
 
                         /* This can happen on COOKIE-ECHO resend.  Only
                          * one chunk can get bundled with a COOKIE-ECHO.
@@ -977,7 +1011,7 @@ int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout)
                         list_add_tail(&chunk->transmitted_list,
                                       &transport->transmitted);
 
-                        sctp_transport_reset_timers(transport);
+                        sctp_transport_reset_timers(transport, start_timer-1);
 
                         q->empty = 0;
 
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index b8bd9e014498..d6af466091d2 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -473,11 +473,11 @@ static struct dst_entry *sctp_v4_get_dst(struct sctp_association *asoc,
                 /* Walk through the bind address list and look for a bind
                  * address that matches the source address of the returned dst.
                  */
+                sctp_v4_dst_saddr(&dst_saddr, dst, htons(bp->port));
                 rcu_read_lock();
                 list_for_each_entry_rcu(laddr, &bp->address_list, list) {
                         if (!laddr->valid || (laddr->state != SCTP_ADDR_SRC))
                                 continue;
-                        sctp_v4_dst_saddr(&dst_saddr, dst, htons(bp->port));
                         if (sctp_v4_cmp_addr(&dst_saddr, &laddr->a))
                                 goto out_unlock;
                 }
@@ -522,7 +522,8 @@ out:
 /* For v4, the source address is cached in the route entry(dst). So no need
  * to cache it separately and hence this is an empty routine.
  */
-static void sctp_v4_get_saddr(struct sctp_association *asoc,
+static void sctp_v4_get_saddr(struct sctp_sock *sk,
+                              struct sctp_association *asoc,
                               struct dst_entry *dst,
                               union sctp_addr *daddr,
                               union sctp_addr *saddr)
@@ -619,6 +620,11 @@ static void sctp_v4_seq_dump_addr(struct seq_file *seq, union sctp_addr *addr)
         seq_printf(seq, "%d.%d.%d.%d ", NIPQUAD(addr->v4.sin_addr));
 }
 
+static void sctp_v4_ecn_capable(struct sock *sk)
+{
+        INET_ECN_xmit(sk);
+}
+
 /* Event handler for inet address addition/deletion events.
  * The sctp_local_addr_list needs to be protocted by a spin lock since
  * multiple notifiers (say IPv4 and IPv6) may be running at the same
@@ -937,6 +943,7 @@ static struct sctp_af sctp_af_inet = {
         .skb_iif           = sctp_v4_skb_iif,
         .is_ce             = sctp_v4_is_ce,
         .seq_dump_addr     = sctp_v4_seq_dump_addr,
+        .ecn_capable       = sctp_v4_ecn_capable,
         .net_header_len    = sizeof(struct iphdr),
         .sockaddr_len      = sizeof(struct sockaddr_in),
 #ifdef CONFIG_COMPAT
diff --git a/net/sctp/transport.c b/net/sctp/transport.c
index f4938f6c5abe..3f34f61221ec 100644
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -79,6 +79,7 @@ static struct sctp_transport *sctp_transport_init(struct sctp_transport *peer,
         peer->rttvar = 0;
         peer->srtt = 0;
         peer->rto_pending = 0;
+        peer->fast_recovery = 0;
 
         peer->last_time_heard = jiffies;
         peer->last_time_used = jiffies;
@@ -190,7 +191,7 @@ 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 +201,7 @@ 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 +292,7 @@ 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 +404,16 @@ 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 +422,23 @@ 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 +514,13 @@ 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 +605,7 @@ void sctp_transport_reset(struct sctp_transport *t)
         t->flight_size = 0;
         t->error_count = 0;
         t->rto_pending = 0;
+        t->fast_recovery = 0;
 
         /* Initialize the state information for SFR-CACC */
         t->cacc.changeover_active = 0;