1 files changed, 100 insertions, 50 deletions

diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c
index c7f7e49609c..d49dc2ed30a 100644
--- a/net/sctp/ulpqueue.c
+++ b/net/sctp/ulpqueue.c
@@ -21,38 +21,32 @@
  * See the GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with GNU CC; see the file COPYING.  If not, write to
- * the Free Software Foundation, 59 Temple Place - Suite 330,
- * Boston, MA 02111-1307, USA.
+ * along with GNU CC; see the file COPYING.  If not, see
+ * <http://www.gnu.org/licenses/>.
  *
  * Please send any bug reports or fixes you make to the
  * email address(es):
- *    lksctp developers <lksctp-developers@lists.sourceforge.net>
- *
- * Or submit a bug report through the following website:
- *    http://www.sf.net/projects/lksctp
+ *    lksctp developers <linux-sctp@vger.kernel.org>
  *
  * Written or modified by:
  *    Jon Grimm             <jgrimm@us.ibm.com>
  *    La Monte H.P. Yarroll <piggy@acm.org>
  *    Sridhar Samudrala     <sri@us.ibm.com>
- *
- * Any bugs reported given to us we will try to fix... any fixes shared will
- * be incorporated into the next SCTP release.
  */
 
 #include <linux/slab.h>
 #include <linux/types.h>
 #include <linux/skbuff.h>
 #include <net/sock.h>
+#include <net/busy_poll.h>
 #include <net/sctp/structs.h>
 #include <net/sctp/sctp.h>
 #include <net/sctp/sm.h>
 
 /* Forward declarations for internal helpers.  */
-static struct sctp_ulpevent * sctp_ulpq_reasm(struct sctp_ulpq *ulpq,
+static struct sctp_ulpevent *sctp_ulpq_reasm(struct sctp_ulpq *ulpq,
 					      struct sctp_ulpevent *);
-static struct sctp_ulpevent * sctp_ulpq_order(struct sctp_ulpq *,
+static struct sctp_ulpevent *sctp_ulpq_order(struct sctp_ulpq *,
 					      struct sctp_ulpevent *);
 static void sctp_ulpq_reasm_drain(struct sctp_ulpq *ulpq);
 
@@ -68,7 +62,6 @@ struct sctp_ulpq *sctp_ulpq_init(struct sctp_ulpq *ulpq,
 	skb_queue_head_init(&ulpq->reasm);
 	skb_queue_head_init(&ulpq->lobby);
 	ulpq->pd_mode  = 0;
-	ulpq->malloced = 0;
 
 	return ulpq;
 }
@@ -96,8 +89,6 @@ void sctp_ulpq_flush(struct sctp_ulpq *ulpq)
 void sctp_ulpq_free(struct sctp_ulpq *ulpq)
 {
 	sctp_ulpq_flush(ulpq);
-	if (ulpq->malloced)
-		kfree(ulpq);
 }
 
 /* Process an incoming DATA chunk.  */
@@ -105,10 +96,8 @@ int sctp_ulpq_tail_data(struct sctp_ulpq *ulpq, struct sctp_chunk *chunk,
 			gfp_t gfp)
 {
 	struct sk_buff_head temp;
-	sctp_data_chunk_t *hdr;
 	struct sctp_ulpevent *event;
-
-	hdr = (sctp_data_chunk_t *) chunk->chunk_hdr;
+	int event_eor = 0;
 
 	/* Create an event from the incoming chunk. */
 	event = sctp_ulpevent_make_rcvmsg(chunk->asoc, chunk, gfp);
@@ -119,7 +108,7 @@ int sctp_ulpq_tail_data(struct sctp_ulpq *ulpq, struct sctp_chunk *chunk,
 	event = sctp_ulpq_reasm(ulpq, event);
 
 	/* Do ordering if needed.  */
-	if ((event) && (event->msg_flags & MSG_EOR)){
+	if ((event) && (event->msg_flags & MSG_EOR)) {
 		/* Create a temporary list to collect chunks on.  */
 		skb_queue_head_init(&temp);
 		__skb_queue_tail(&temp, sctp_event2skb(event));
@@ -130,10 +119,12 @@ 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.  */
@@ -214,6 +205,9 @@ int sctp_ulpq_tail_event(struct sctp_ulpq *ulpq, struct sctp_ulpevent *event)
 	if (sock_flag(sk, SOCK_DEAD) || (sk->sk_shutdown & RCV_SHUTDOWN))
 		goto out_free;
 
+	if (!sctp_ulpevent_is_notification(event))
+		sk_mark_napi_id(sk, skb);
+
 	/* Check if the user wishes to receive this event.  */
 	if (!sctp_ulpevent_is_enabled(event, &sctp_sk(sk)->subscribe))
 		goto out_free;
@@ -243,7 +237,7 @@ int sctp_ulpq_tail_event(struct sctp_ulpq *ulpq, struct sctp_ulpevent *event)
 		} else {
 			/*
 			 * If fragment interleave is enabled, we
-			 * can queue this to the recieve queue instead
+			 * can queue this to the receive queue instead
 			 * of the lobby.
 			 */
 			if (sctp_sk(sk)->frag_interleave)
@@ -269,7 +263,7 @@ int sctp_ulpq_tail_event(struct sctp_ulpq *ulpq, struct sctp_ulpevent *event)
 		sctp_ulpq_clear_pd(ulpq);
 
 	if (queue == &sk->sk_receive_queue)
-		sk->sk_data_ready(sk, 0);
+		sk->sk_data_ready(sk);
 	return 1;
 
 out_free:
@@ -329,7 +323,9 @@ static void sctp_ulpq_store_reasm(struct sctp_ulpq *ulpq,
  * payload was fragmented on the way and ip had to reassemble them.
  * We add the rest of skb's to the first skb's fraglist.
  */
-static struct sctp_ulpevent *sctp_make_reassembled_event(struct sk_buff_head *queue, struct sk_buff *f_frag, struct sk_buff *l_frag)
+static struct sctp_ulpevent *sctp_make_reassembled_event(struct net *net,
+	struct sk_buff_head *queue, struct sk_buff *f_frag,
+	struct sk_buff *l_frag)
 {
 	struct sk_buff *pos;
 	struct sk_buff *new = NULL;
@@ -344,7 +340,8 @@ static struct sctp_ulpevent *sctp_make_reassembled_event(struct sk_buff_head *qu
 		pos = f_frag->next;
 
 	/* Get the last skb in the f_frag's frag_list if present. */
-	for (last = list; list; last = list, list = list->next);
+	for (last = list; list; last = list, list = list->next)
+		;
 
 	/* Add the list of remaining fragments to the first fragments
 	 * frag_list.
@@ -397,7 +394,7 @@ static struct sctp_ulpevent *sctp_make_reassembled_event(struct sk_buff_head *qu
 	}
 
 	event = sctp_skb2event(f_frag);
-	SCTP_INC_STATS(SCTP_MIB_REASMUSRMSGS);
+	SCTP_INC_STATS(net, SCTP_MIB_REASMUSRMSGS);
 
 	return event;
 }
@@ -496,7 +493,8 @@ static struct sctp_ulpevent *sctp_ulpq_retrieve_reassembled(struct sctp_ulpq *ul
 		cevent = sctp_skb2event(pd_first);
 		pd_point = sctp_sk(asoc->base.sk)->pd_point;
 		if (pd_point && pd_point <= pd_len) {
-			retval = sctp_make_reassembled_event(&ulpq->reasm,
+			retval = sctp_make_reassembled_event(sock_net(asoc->base.sk),
+							     &ulpq->reasm,
 							     pd_first,
 							     pd_last);
 			if (retval)
@@ -506,7 +504,8 @@ static struct sctp_ulpevent *sctp_ulpq_retrieve_reassembled(struct sctp_ulpq *ul
 done:
 	return retval;
 found:
-	retval = sctp_make_reassembled_event(&ulpq->reasm, first_frag, pos);
+	retval = sctp_make_reassembled_event(sock_net(ulpq->asoc->base.sk),
+					     &ulpq->reasm, first_frag, pos);
 	if (retval)
 		retval->msg_flags |= MSG_EOR;
 	goto done;
@@ -539,14 +538,19 @@ 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:
@@ -566,7 +570,8 @@ static struct sctp_ulpevent *sctp_ulpq_retrieve_partial(struct sctp_ulpq *ulpq)
 	 * further.
 	 */
 done:
-	retval = sctp_make_reassembled_event(&ulpq->reasm, first_frag, last_frag);
+	retval = sctp_make_reassembled_event(sock_net(ulpq->asoc->base.sk),
+					&ulpq->reasm, first_frag, last_frag);
 	if (retval && is_last)
 		retval->msg_flags |= MSG_EOR;
 
@@ -649,6 +654,14 @@ 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;
 		}
@@ -658,7 +671,8 @@ static struct sctp_ulpevent *sctp_ulpq_retrieve_first(struct sctp_ulpq *ulpq)
 	 * further.
 	 */
 done:
-	retval = sctp_make_reassembled_event(&ulpq->reasm, first_frag, last_frag);
+	retval = sctp_make_reassembled_event(sock_net(ulpq->asoc->base.sk),
+					&ulpq->reasm, first_frag, last_frag);
 	return retval;
 }
 
@@ -717,7 +731,7 @@ static void sctp_ulpq_reasm_drain(struct sctp_ulpq *ulpq)
 
 	while ((event = sctp_ulpq_retrieve_reassembled(ulpq)) != NULL) {
 		/* Do ordering if needed.  */
-		if ((event) && (event->msg_flags & MSG_EOR)){
+		if ((event) && (event->msg_flags & MSG_EOR)) {
 			skb_queue_head_init(&temp);
 			__skb_queue_tail(&temp, sctp_event2skb(event));
 
@@ -743,11 +757,9 @@ static void sctp_ulpq_retrieve_ordered(struct sctp_ulpq *ulpq,
 	struct sk_buff *pos, *tmp;
 	struct sctp_ulpevent *cevent;
 	struct sctp_stream *in;
-	__u16 sid, csid;
-	__u16 ssn, cssn;
+	__u16 sid, csid, cssn;
 
 	sid = event->stream;
-	ssn = event->ssn;
 	in  = &ulpq->asoc->ssnmap->in;
 
 	event_list = (struct sk_buff_head *) sctp_event2skb(event)->prev;
@@ -961,20 +973,43 @@ 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;
 	}
@@ -996,22 +1031,33 @@ static __u16 sctp_ulpq_renege_frags(struct sctp_ulpq *ulpq, __u16 needed)
 
 /* Partial deliver the first message as there is pressure on rwnd. */
 void sctp_ulpq_partial_delivery(struct sctp_ulpq *ulpq,
-				struct sctp_chunk *chunk,
 				gfp_t gfp)
 {
 	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 +1100,16 @@ 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);
-		sctp_ulpq_tail_data(ulpq, chunk, gfp);
-
-		sctp_ulpq_partial_delivery(ulpq, chunk, 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);
@@ -1089,5 +1139,5 @@ void sctp_ulpq_abort_pd(struct sctp_ulpq *ulpq, gfp_t gfp)
 
 	/* If there is data waiting, send it up the socket now. */
 	if (sctp_ulpq_clear_pd(ulpq) || ev)
-		sk->sk_data_ready(sk, 0);
+		sk->sk_data_ready(sk);
 }