Merge tag 'v3.9-rc5' into wq/for-3.10

Writeback conversion to workqueue will be based on top of wq/for-3.10
branch to take advantage of custom attrs and NUMA support for unbound
workqueues.  Mainline currently contains two commits which result in
non-trivial merge conflicts with wq/for-3.10 and because
block/for-3.10/core is based on v3.9-rc3 which contains one of the
conflicting commits, we need a pre-merge-window merge anyway.  Let's
pull v3.9-rc5 into wq/for-3.10 so that the block tree doesn't suffer
from workqueue merge conflicts.

The two conflicts and their resolutions:

* e68035fb65 ("workqueue: convert to idr_alloc()") in mainline changes
  worker_pool_assign_id() to use idr_alloc() instead of the old idr
  interface.  worker_pool_assign_id() goes through multiple locking
  changes in wq/for-3.10 causing the following conflict.

  static int worker_pool_assign_id(struct worker_pool *pool)
  {
	  int ret;

  <<<<<<< HEAD
	  lockdep_assert_held(&wq_pool_mutex);

	  do {
		  if (!idr_pre_get(&worker_pool_idr, GFP_KERNEL))
			  return -ENOMEM;
		  ret = idr_get_new(&worker_pool_idr, pool, &pool->id);
	  } while (ret == -EAGAIN);
  =======
	  mutex_lock(&worker_pool_idr_mutex);
	  ret = idr_alloc(&worker_pool_idr, pool, 0, 0, GFP_KERNEL);
	  if (ret >= 0)
		  pool->id = ret;
	  mutex_unlock(&worker_pool_idr_mutex);
  >>>>>>> c67bf5361e7e66a0ff1f4caf95f89347d55dfb89

	  return ret < 0 ? ret : 0;
  }

  We want locking from the former and idr_alloc() usage from the
  latter, which can be combined to the following.

  static int worker_pool_assign_id(struct worker_pool *pool)
  {
	  int ret;

	  lockdep_assert_held(&wq_pool_mutex);

	  ret = idr_alloc(&worker_pool_idr, pool, 0, 0, GFP_KERNEL);
	  if (ret >= 0) {
		  pool->id = ret;
		  return 0;
	  }
	  return ret;
   }

* eb2834285c ("workqueue: fix possible pool stall bug in
  wq_unbind_fn()") updated wq_unbind_fn() such that it has single
  larger for_each_std_worker_pool() loop instead of two separate loops
  with a schedule() call inbetween.  wq/for-3.10 renamed
  pool->assoc_mutex to pool->manager_mutex causing the following
  conflict (earlier function body and comments omitted for brevity).

  static void wq_unbind_fn(struct work_struct *work)
  {
  ...
		  spin_unlock_irq(&pool->lock);
  <<<<<<< HEAD
		  mutex_unlock(&pool->manager_mutex);
	  }
  =======
		  mutex_unlock(&pool->assoc_mutex);
  >>>>>>> c67bf5361e7e66a0ff1f4caf95f89347d55dfb89

		  schedule();

  <<<<<<< HEAD
	  for_each_cpu_worker_pool(pool, cpu)
  =======
  >>>>>>> c67bf5361e7e66a0ff1f4caf95f89347d55dfb89
		  atomic_set(&pool->nr_running, 0);

		  spin_lock_irq(&pool->lock);
		  wake_up_worker(pool);
		  spin_unlock_irq(&pool->lock);
	  }
  }

  The resolution is mostly trivial.  We want the control flow of the
  latter with the rename of the former.

  static void wq_unbind_fn(struct work_struct *work)
  {
  ...
		  spin_unlock_irq(&pool->lock);
		  mutex_unlock(&pool->manager_mutex);

		  schedule();

		  atomic_set(&pool->nr_running, 0);

		  spin_lock_irq(&pool->lock);
		  wake_up_worker(pool);
		  spin_unlock_irq(&pool->lock);
	  }
  }

Signed-off-by: Tejun Heo <tj@kernel.org>

1 files changed, 71 insertions, 16 deletions

diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c
index ada17464b65..0fd5b3d2df0 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);