Merge branch 'sctp'

Lee A. Roberts says:

====================
This series of patches resolves several SCTP association hangs observed during
SCTP stress testing.  Observable symptoms include communications hangs with
data being held in the association reassembly and/or lobby (ordering) queues.
Close examination of reassembly/ordering queues may show either duplicated
or missing packets.

In version #2, corrected build failure in initial version of patch series
due to wrong calling sequence for sctp_ulpq_partial_delivery() being inserted
in sctp_ulpq_renege().

In version #3, adjusted patch documentation to be less repetitive.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

net/sctp/tsnmap.c

@@ -51,7 +51,7 @@
 static void sctp_tsnmap_update(struct sctp_tsnmap *map);
 static void sctp_tsnmap_find_gap_ack(unsigned long *map, __u16 off,
 				     __u16 len, __u16 *start, __u16 *end);
-static int sctp_tsnmap_grow(struct sctp_tsnmap *map, u16 gap);
+static int sctp_tsnmap_grow(struct sctp_tsnmap *map, u16 size);
 
 /* Initialize a block of memory as a tsnmap.  */
 struct sctp_tsnmap *sctp_tsnmap_init(struct sctp_tsnmap *map, __u16 len,
@@ -124,7 +124,7 @@ int sctp_tsnmap_mark(struct sctp_tsnmap *map, __u32 tsn,
 
 	gap = tsn - map->base_tsn;
 
-	if (gap >= map->len && !sctp_tsnmap_grow(map, gap))
+	if (gap >= map->len && !sctp_tsnmap_grow(map, gap + 1))
 		return -ENOMEM;
 
 	if (!sctp_tsnmap_has_gap(map) && gap == 0) {
@@ -360,23 +360,24 @@ __u16 sctp_tsnmap_num_gabs(struct sctp_tsnmap *map,
 	return ngaps;
 }
 
-static int sctp_tsnmap_grow(struct sctp_tsnmap *map, u16 gap)
+static int sctp_tsnmap_grow(struct sctp_tsnmap *map, u16 size)
 {
 	unsigned long *new;
 	unsigned long inc;
 	u16  len;
 
-	if (gap >= SCTP_TSN_MAP_SIZE)
+	if (size > SCTP_TSN_MAP_SIZE)
 		return 0;
 
-	inc = ALIGN((gap - map->len),BITS_PER_LONG) + SCTP_TSN_MAP_INCREMENT;
+	inc = ALIGN((size - map->len), BITS_PER_LONG) + SCTP_TSN_MAP_INCREMENT;
 	len = min_t(u16, map->len + inc, SCTP_TSN_MAP_SIZE);
 
 	new = kzalloc(len>>3, GFP_ATOMIC);
 	if (!new)
 		return 0;
 
-	bitmap_copy(new, map->tsn_map, map->max_tsn_seen - map->base_tsn);
+	bitmap_copy(new, map->tsn_map,
+		map->max_tsn_seen - map->cumulative_tsn_ack_point);
 	kfree(map->tsn_map);
 	map->tsn_map = new;
 	map->len = len;

net/sctp/ulpqueue.c

@@ -106,6 +106,7 @@ int sctp_ulpq_tail_data(struct sctp_ulpq *ulpq, struct sctp_chunk *chunk,
 {
 	struct sk_buff_head temp;
 	struct sctp_ulpevent *event;
+	int event_eor = 0;
 
 	/* Create an event from the incoming chunk. */
 	event = sctp_ulpevent_make_rcvmsg(chunk->asoc, chunk, gfp);
@@ -127,10 +128,12 @@ int sctp_ulpq_tail_data(struct sctp_ulpq *ulpq, struct sctp_chunk *chunk,
 	/* Send event to the ULP.  'event' is the sctp_ulpevent for
 	 * very first SKB on the 'temp' list.
 	 */
-	if (event)
+	if (event) {
+		event_eor = (event->msg_flags & MSG_EOR) ? 1 : 0;
 		sctp_ulpq_tail_event(ulpq, event);
+	}
 
-	return 0;
+	return event_eor;
 }
 
 /* Add a new event for propagation to the ULP.  */
@@ -540,14 +543,19 @@ static struct sctp_ulpevent *sctp_ulpq_retrieve_partial(struct sctp_ulpq *ulpq)
 		ctsn = cevent->tsn;
 
 		switch (cevent->msg_flags & SCTP_DATA_FRAG_MASK) {
+		case SCTP_DATA_FIRST_FRAG:
+			if (!first_frag)
+				return NULL;
+			goto done;
 		case SCTP_DATA_MIDDLE_FRAG:
 			if (!first_frag) {
 				first_frag = pos;
 				next_tsn = ctsn + 1;
 				last_frag = pos;
-			} else if (next_tsn == ctsn)
+			} else if (next_tsn == ctsn) {
 				next_tsn++;
-			else
+				last_frag = pos;
+			} else
 				goto done;
 			break;
 		case SCTP_DATA_LAST_FRAG:
@@ -651,6 +659,14 @@ static struct sctp_ulpevent *sctp_ulpq_retrieve_first(struct sctp_ulpq *ulpq)
 			} else
 				goto done;
 			break;
+
+		case SCTP_DATA_LAST_FRAG:
+			if (!first_frag)
+				return NULL;
+			else
+				goto done;
+			break;
+
 		default:
 			return NULL;
 		}
@@ -962,20 +978,43 @@ static __u16 sctp_ulpq_renege_list(struct sctp_ulpq *ulpq,
 		struct sk_buff_head *list, __u16 needed)
 {
 	__u16 freed = 0;
-	__u32 tsn;
-	struct sk_buff *skb;
+	__u32 tsn, last_tsn;
+	struct sk_buff *skb, *flist, *last;
 	struct sctp_ulpevent *event;
 	struct sctp_tsnmap *tsnmap;
 
 	tsnmap = &ulpq->asoc->peer.tsn_map;
 
-	while ((skb = __skb_dequeue_tail(list)) != NULL) {
-		freed += skb_headlen(skb);
+	while ((skb = skb_peek_tail(list)) != NULL) {
 		event = sctp_skb2event(skb);
 		tsn = event->tsn;
 
+		/* Don't renege below the Cumulative TSN ACK Point. */
+		if (TSN_lte(tsn, sctp_tsnmap_get_ctsn(tsnmap)))
+			break;
+
+		/* Events in ordering queue may have multiple fragments
+		 * corresponding to additional TSNs.  Sum the total
+		 * freed space; find the last TSN.
+		 */
+		freed += skb_headlen(skb);
+		flist = skb_shinfo(skb)->frag_list;
+		for (last = flist; flist; flist = flist->next) {
+			last = flist;
+			freed += skb_headlen(last);
+		}
+		if (last)
+			last_tsn = sctp_skb2event(last)->tsn;
+		else
+			last_tsn = tsn;
+
+		/* Unlink the event, then renege all applicable TSNs. */
+		__skb_unlink(skb, list);
 		sctp_ulpevent_free(event);
-		sctp_tsnmap_renege(tsnmap, tsn);
+		while (TSN_lte(tsn, last_tsn)) {
+			sctp_tsnmap_renege(tsnmap, tsn);
+			tsn++;
+		}
 		if (freed >= needed)
 			return freed;
 	}
@@ -1002,16 +1041,28 @@ void sctp_ulpq_partial_delivery(struct sctp_ulpq *ulpq,
 	struct sctp_ulpevent *event;
 	struct sctp_association *asoc;
 	struct sctp_sock *sp;
+	__u32 ctsn;
+	struct sk_buff *skb;
 
 	asoc = ulpq->asoc;
 	sp = sctp_sk(asoc->base.sk);
 
 	/* If the association is already in Partial Delivery mode
-	 * we have noting to do.
+	 * we have nothing to do.
 	 */
 	if (ulpq->pd_mode)
 		return;
 
+	/* Data must be at or below the Cumulative TSN ACK Point to
+	 * start partial delivery.
+	 */
+	skb = skb_peek(&asoc->ulpq.reasm);
+	if (skb != NULL) {
+		ctsn = sctp_skb2event(skb)->tsn;
+		if (!TSN_lte(ctsn, sctp_tsnmap_get_ctsn(&asoc->peer.tsn_map)))
+			return;
+	}
+
 	/* If the user enabled fragment interleave socket option,
 	 * multiple associations can enter partial delivery.
 	 * Otherwise, we can only enter partial delivery if the
@@ -1054,12 +1105,16 @@ void sctp_ulpq_renege(struct sctp_ulpq *ulpq, struct sctp_chunk *chunk,
 	}
 	/* If able to free enough room, accept this chunk. */
 	if (chunk && (freed >= needed)) {
-		__u32 tsn;
-		tsn = ntohl(chunk->subh.data_hdr->tsn);
-		sctp_tsnmap_mark(&asoc->peer.tsn_map, tsn, chunk->transport);
-		sctp_ulpq_tail_data(ulpq, chunk, gfp);
-
-		sctp_ulpq_partial_delivery(ulpq, gfp);
+		int retval;
+		retval = sctp_ulpq_tail_data(ulpq, chunk, gfp);
+		/*
+		 * Enter partial delivery if chunk has not been
+		 * delivered; otherwise, drain the reassembly queue.
+		 */
+		if (retval <= 0)
+			sctp_ulpq_partial_delivery(ulpq, gfp);
+		else if (retval == 1)
+			sctp_ulpq_reasm_drain(ulpq);
 	}
 
 	sk_mem_reclaim(asoc->base.sk);