Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Pull networking fixes from David Miller:
 "A moderately sized pile of fixes, some specifically for merge window
  introduced regressions although others are for longer standing items
  and have been queued up for -stable.

  I'm kind of tired of all the RDS protocol bugs over the years, to be
  honest, it's way out of proportion to the number of people who
  actually use it.

   1) Fix missing range initialization in netfilter IPSET, from Jozsef
      Kadlecsik.

   2) ieee80211_local->tim_lock needs to use BH disabling, from Johannes
      Berg.

   3) Fix DMA syncing in SFC driver, from Ben Hutchings.

   4) Fix regression in BOND device MAC address setting, from Jiri
      Pirko.

   5) Missing usb_free_urb in ISDN Hisax driver, from Marina Makienko.

   6) Fix UDP checksumming in bnx2x driver for 57710 and 57711 chips,
      fix from Dmitry Kravkov.

   7) Missing cfgspace_lock initialization in BCMA driver.

   8) Validate parameter size for SCTP assoc stats getsockopt(), from
      Guenter Roeck.

   9) Fix SCTP association hangs, from Lee A Roberts.

  10) Fix jumbo frame handling in r8169, from Francois Romieu.

  11) Fix phy_device memory leak, from Petr Malat.

  12) Omit trailing FCS from frames received in BGMAC driver, from Hauke
      Mehrtens.

  13) Missing socket refcount release in L2TP, from Guillaume Nault.

  14) sctp_endpoint_init should respect passed in gfp_t, rather than use
      GFP_KERNEL unconditionally.  From Dan Carpenter.

  15) Add AISX AX88179 USB driver, from Freddy Xin.

  16) Remove MAINTAINERS entries for drivers deleted during the merge
      window, from Cesar Eduardo Barros.

  17) RDS protocol can try to allocate huge amounts of memory, check
      that the user's request length makes sense, from Cong Wang.

  18) SCTP should use the provided KMALLOC_MAX_SIZE instead of it's own,
      bogus, definition.  From Cong Wang.

  19) Fix deadlocks in FEC driver by moving TX reclaim into NAPI poll,
      from Frank Li.  Also, fix a build error introduced in the merge
      window.

  20) Fix bogus purging of default routes in ipv6, from Lorenzo Colitti.

  21) Don't double count RTT measurements when we leave the TCP receive
      fast path, from Neal Cardwell."

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (61 commits)
  tcp: fix double-counted receiver RTT when leaving receiver fast path
  CAIF: fix sparse warning for caif_usb
  rds: simplify a warning message
  net: fec: fix build error in no MXC platform
  net: ipv6: Don't purge default router if accept_ra=2
  net: fec: put tx to napi poll function to fix dead lock
  sctp: use KMALLOC_MAX_SIZE instead of its own MAX_KMALLOC_SIZE
  rds: limit the size allocated by rds_message_alloc()
  MAINTAINERS: remove eexpress
  MAINTAINERS: remove drivers/net/wan/cycx*
  MAINTAINERS: remove 3c505
  caif_dev: fix sparse warnings for caif_flow_cb
  ax88179_178a: ASIX AX88179_178A USB 3.0/2.0 to gigabit ethernet adapter driver
  sctp: use the passed in gfp flags instead GFP_KERNEL
  ipv[4|6]: correct dropwatch false positive in local_deliver_finish
  l2tp: Restore socket refcount when sendmsg succeeds
  net/phy: micrel: Disable asymmetric pause for KSZ9021
  bgmac: omit the fcs
  phy: Fix phy_device_free memory leak
  bnx2x: Fix KR2 work-around condition
  ...

1 files changed, 71 insertions, 16 deletions

diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c
index ada17464b65b..0fd5b3d2df03 100644
--- a/net/sctp/ulpqueue.c
+++ b/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);