sctp: be more restrictive in transport selection on bundled sacks

It was noticed recently that when we send data on a transport, its possible that
we might bundle a sack that arrived on a different transport.  While this isn't
a major problem, it does go against the SHOULD requirement in section 6.4 of RFC
2960:

 An endpoint SHOULD transmit reply chunks (e.g., SACK, HEARTBEAT ACK,
   etc.) to the same destination transport address from which it
   received the DATA or control chunk to which it is replying.  This
   rule should also be followed if the endpoint is bundling DATA chunks
   together with the reply chunk.

This patch seeks to correct that.  It restricts the bundling of sack operations
to only those transports which have moved the ctsn of the association forward
since the last sack.  By doing this we guarantee that we only bundle outbound
saks on a transport that has received a chunk since the last sack.  This brings
us into stricter compliance with the RFC.

Vlad had initially suggested that we strictly allow only sack bundling on the
transport that last moved the ctsn forward.  While this makes sense, I was
concerned that doing so prevented us from bundling in the case where we had
received chunks that moved the ctsn on multiple transports.  In those cases, the
RFC allows us to select any of the transports having received chunks to bundle
the sack on.  so I've modified the approach to allow for that, by adding a state
variable to each transport that tracks weather it has moved the ctsn since the
last sack.  This I think keeps our behavior (and performance), close enough to
our current profile that I think we can do this without a sysctl knob to
enable/disable it.

Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
CC: Vlad Yaseivch <vyasevich@gmail.com>
CC: David S. Miller <davem@davemloft.net>
CC: linux-sctp@vger.kernel.org
Reported-by: Michele Baldessari <michele@redhat.com>
Reported-by: sorin serban <sserban@redhat.com>
Acked-by: Vlad Yasevich <vyasevich@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/sctp/structs.h

@@ -912,6 +912,9 @@ struct sctp_transport {
 		/* Is this structure kfree()able? */
 		malloced:1;
 
+	/* Has this transport moved the ctsn since we last sacked */
+	__u32 sack_generation;
+
 	struct flowi fl;
 
 	/* This is the peer's IP address and port. */
@@ -1584,6 +1587,7 @@ struct sctp_association {
 		 */
 		__u8    sack_needed;     /* Do we need to sack the peer? */
 		__u32	sack_cnt;
+		__u32	sack_generation;
 
 		/* These are capabilities which our peer advertised.  */
 		__u8	ecn_capable:1,	    /* Can peer do ECN? */

include/net/sctp/tsnmap.h

@@ -117,7 +117,8 @@ void sctp_tsnmap_free(struct sctp_tsnmap *map);
 int sctp_tsnmap_check(const struct sctp_tsnmap *, __u32 tsn);
 
 /* Mark this TSN as seen.  */
-int sctp_tsnmap_mark(struct sctp_tsnmap *, __u32 tsn);
+int sctp_tsnmap_mark(struct sctp_tsnmap *, __u32 tsn,
+		     struct sctp_transport *trans);
 
 /* Mark this TSN and all lower as seen. */
 void sctp_tsnmap_skip(struct sctp_tsnmap *map, __u32 tsn);

net/sctp/associola.c

@@ -271,6 +271,7 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a
 	 */
 	asoc->peer.sack_needed = 1;
 	asoc->peer.sack_cnt = 0;
+	asoc->peer.sack_generation = 1;
 
 	/* Assume that the peer will tell us if he recognizes ASCONF
 	 * as part of INIT exchange.

net/sctp/output.c

@@ -248,6 +248,11 @@ static sctp_xmit_t sctp_packet_bundle_sack(struct sctp_packet *pkt,
 		/* If the SACK timer is running, we have a pending SACK */
 		if (timer_pending(timer)) {
 			struct sctp_chunk *sack;
+
+			if (pkt->transport->sack_generation !=
+			    pkt->transport->asoc->peer.sack_generation)
+				return retval;
+
 			asoc->a_rwnd = asoc->rwnd;
 			sack = sctp_make_sack(asoc);
 			if (sack) {

net/sctp/sm_make_chunk.c

@@ -734,8 +734,10 @@ struct sctp_chunk *sctp_make_sack(const struct sctp_association *asoc)
 	int len;
 	__u32 ctsn;
 	__u16 num_gabs, num_dup_tsns;
+	struct sctp_association *aptr = (struct sctp_association *)asoc;
 	struct sctp_tsnmap *map = (struct sctp_tsnmap *)&asoc->peer.tsn_map;
 	struct sctp_gap_ack_block gabs[SCTP_MAX_GABS];
+	struct sctp_transport *trans;
 
 	memset(gabs, 0, sizeof(gabs));
 	ctsn = sctp_tsnmap_get_ctsn(map);
@@ -805,6 +807,20 @@ struct sctp_chunk *sctp_make_sack(const struct sctp_association *asoc)
 		sctp_addto_chunk(retval, sizeof(__u32) * num_dup_tsns,
 				 sctp_tsnmap_get_dups(map));
 
+	/* Once we have a sack generated, check to see what our sack
+	 * generation is, if its 0, reset the transports to 0, and reset
+	 * the association generation to 1
+	 *
+	 * The idea is that zero is never used as a valid generation for the
+	 * association so no transport will match after a wrap event like this,
+	 * Until the next sack
+	 */
+	if (++aptr->peer.sack_generation == 0) {
+		list_for_each_entry(trans, &asoc->peer.transport_addr_list,
+				    transports)
+			trans->sack_generation = 0;
+		aptr->peer.sack_generation = 1;
+	}
 nodata:
 	return retval;
 }

net/sctp/sm_sideeffect.c

@@ -1268,7 +1268,7 @@ static int sctp_cmd_interpreter(sctp_event_t event_type,
 		case SCTP_CMD_REPORT_TSN:
 			/* Record the arrival of a TSN.  */
 			error = sctp_tsnmap_mark(&asoc->peer.tsn_map,
-						 cmd->obj.u32);
+						 cmd->obj.u32, NULL);
 			break;
 
 		case SCTP_CMD_REPORT_FWDTSN:

net/sctp/transport.c

@@ -68,6 +68,8 @@ static struct sctp_transport *sctp_transport_init(struct sctp_transport *peer,
 	peer->af_specific = sctp_get_af_specific(addr->sa.sa_family);
 	memset(&peer->saddr, 0, sizeof(union sctp_addr));
 
+	peer->sack_generation = 0;
+
 	/* From 6.3.1 RTO Calculation:
 	 *
 	 * C1) Until an RTT measurement has been made for a packet sent to the

net/sctp/tsnmap.c

@@ -114,7 +114,8 @@ int sctp_tsnmap_check(const struct sctp_tsnmap *map, __u32 tsn)
 
 
 /* Mark this TSN as seen.  */
-int sctp_tsnmap_mark(struct sctp_tsnmap *map, __u32 tsn)
+int sctp_tsnmap_mark(struct sctp_tsnmap *map, __u32 tsn,
+		     struct sctp_transport *trans)
 {
 	u16 gap;
 
@@ -133,6 +134,9 @@ int sctp_tsnmap_mark(struct sctp_tsnmap *map, __u32 tsn)
 		 */
 		map->max_tsn_seen++;
 		map->cumulative_tsn_ack_point++;
+		if (trans)
+			trans->sack_generation =
+				trans->asoc->peer.sack_generation;
 		map->base_tsn++;
 	} else {
 		/* Either we already have a gap, or about to record a gap, so

net/sctp/ulpevent.c

@@ -715,7 +715,8 @@ struct sctp_ulpevent *sctp_ulpevent_make_rcvmsg(struct sctp_association *asoc,
 	 * can mark it as received so the tsn_map is updated correctly.
 	 */
 	if (sctp_tsnmap_mark(&asoc->peer.tsn_map,
-			     ntohl(chunk->subh.data_hdr->tsn)))
+			     ntohl(chunk->subh.data_hdr->tsn),
+			     chunk->transport))
 		goto fail_mark;
 
 	/* First calculate the padding, so we don't inadvertently

net/sctp/ulpqueue.c

@@ -1051,7 +1051,7 @@ void sctp_ulpq_renege(struct sctp_ulpq *ulpq, struct sctp_chunk *chunk,
 	if (chunk && (freed >= needed)) {
 		__u32 tsn;
 		tsn = ntohl(chunk->subh.data_hdr->tsn);
-		sctp_tsnmap_mark(&asoc->peer.tsn_map, tsn);
+		sctp_tsnmap_mark(&asoc->peer.tsn_map, tsn, chunk->transport);
 		sctp_ulpq_tail_data(ulpq, chunk, gfp);
 
 		sctp_ulpq_partial_delivery(ulpq, chunk, gfp);