Merge branch 'for-4.1/core' of git://git.kernel.dk/linux-block

Pull block layer core bits from Jens Axboe:
 "This is the core pull request for 4.1.  Not a lot of stuff in here for
  this round, mostly little fixes or optimizations.  This pull request
  contains:

   - An optimization that speeds up queue runs on blk-mq, especially for
     the case where there's a large difference between nr_cpu_ids and
     the actual mapped software queues on a hardware queue.  From Chong
     Yuan.

   - Honor node local allocations for requests on legacy devices.  From
     David Rientjes.

   - Cleanup of blk_mq_rq_to_pdu() from me.

   - exit_aio() fixup from me, greatly speeding up exiting multiple IO
     contexts off exit_group().  For my particular test case, fio exit
     took ~6 seconds.  A typical case of both exposing RCU grace periods
     to user space, and serializing exit of them.

   - Make blk_mq_queue_enter() honor the gfp mask passed in, so we only
     wait if __GFP_WAIT is set.  From Keith Busch.

   - blk-mq exports and two added helpers from Mike Snitzer, which will
     be used by the dm-mq code.

   - Cleanups of blk-mq queue init from Wei Fang and Xiaoguang Wang"

* 'for-4.1/core' of git://git.kernel.dk/linux-block:
  blk-mq: reduce unnecessary software queue looping
  aio: fix serial draining in exit_aio()
  blk-mq: cleanup blk_mq_rq_to_pdu()
  blk-mq: put blk_queue_rq_timeout together in blk_mq_init_queue()
  block: remove redundant check about 'set->nr_hw_queues' in blk_mq_alloc_tag_set()
  block: allocate request memory local to request queue
  blk-mq: don't wait in blk_mq_queue_enter() if __GFP_WAIT isn't set
  blk-mq: export blk_mq_run_hw_queues
  blk-mq: add blk_mq_init_allocated_queue and export blk_mq_register_disk

1 files changed, 30 insertions, 15 deletions

diff --git a/fs/aio.c b/fs/aio.c
index 5785c4b58fea..fa8b16f47f1a 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -77,6 +77,11 @@ struct kioctx_cpu {
 	unsigned		reqs_available;
 };
 
+struct ctx_rq_wait {
+	struct completion comp;
+	atomic_t count;
+};
+
 struct kioctx {
 	struct percpu_ref	users;
 	atomic_t		dead;
@@ -115,7 +120,7 @@ struct kioctx {
 	/*
 	 * signals when all in-flight requests are done
 	 */
-	struct completion *requests_done;
+	struct ctx_rq_wait	*rq_wait;
 
 	struct {
 		/*
@@ -572,8 +577,8 @@ static void free_ioctx_reqs(struct percpu_ref *ref)
 	struct kioctx *ctx = container_of(ref, struct kioctx, reqs);
 
 	/* At this point we know that there are no any in-flight requests */
-	if (ctx->requests_done)
-		complete(ctx->requests_done);
+	if (ctx->rq_wait && atomic_dec_and_test(&ctx->rq_wait->count))
+		complete(&ctx->rq_wait->comp);
 
 	INIT_WORK(&ctx->free_work, free_ioctx);
 	schedule_work(&ctx->free_work);
@@ -783,7 +788,7 @@ err:
  *	the rapid destruction of the kioctx.
  */
 static int kill_ioctx(struct mm_struct *mm, struct kioctx *ctx,
-		struct completion *requests_done)
+		      struct ctx_rq_wait *wait)
 {
 	struct kioctx_table *table;
 
@@ -813,7 +818,7 @@ static int kill_ioctx(struct mm_struct *mm, struct kioctx *ctx,
 	if (ctx->mmap_size)
 		vm_munmap(ctx->mmap_base, ctx->mmap_size);
 
-	ctx->requests_done = requests_done;
+	ctx->rq_wait = wait;
 	percpu_ref_kill(&ctx->users);
 	return 0;
 }
@@ -829,18 +834,24 @@ static int kill_ioctx(struct mm_struct *mm, struct kioctx *ctx,
 void exit_aio(struct mm_struct *mm)
 {
 	struct kioctx_table *table = rcu_dereference_raw(mm->ioctx_table);
-	int i;
+	struct ctx_rq_wait wait;
+	int i, skipped;
 
 	if (!table)
 		return;
 
+	atomic_set(&wait.count, table->nr);
+	init_completion(&wait.comp);
+
+	skipped = 0;
 	for (i = 0; i < table->nr; ++i) {
 		struct kioctx *ctx = table->table[i];
-		struct completion requests_done =
-			COMPLETION_INITIALIZER_ONSTACK(requests_done);
 
-		if (!ctx)
+		if (!ctx) {
+			skipped++;
 			continue;
+		}
+
 		/*
 		 * We don't need to bother with munmap() here - exit_mmap(mm)
 		 * is coming and it'll unmap everything. And we simply can't,
@@ -849,10 +860,12 @@ void exit_aio(struct mm_struct *mm)
 		 * that it needs to unmap the area, just set it to 0.
 		 */
 		ctx->mmap_size = 0;
-		kill_ioctx(mm, ctx, &requests_done);
+		kill_ioctx(mm, ctx, &wait);
+	}
 
+	if (!atomic_sub_and_test(skipped, &wait.count)) {
 		/* Wait until all IO for the context are done. */
-		wait_for_completion(&requests_done);
+		wait_for_completion(&wait.comp);
 	}
 
 	RCU_INIT_POINTER(mm->ioctx_table, NULL);
@@ -1331,15 +1344,17 @@ SYSCALL_DEFINE1(io_destroy, aio_context_t, ctx)
 {
 	struct kioctx *ioctx = lookup_ioctx(ctx);
 	if (likely(NULL != ioctx)) {
-		struct completion requests_done =
-			COMPLETION_INITIALIZER_ONSTACK(requests_done);
+		struct ctx_rq_wait wait;
 		int ret;
 
+		init_completion(&wait.comp);
+		atomic_set(&wait.count, 1);
+
 		/* Pass requests_done to kill_ioctx() where it can be set
 		 * in a thread-safe way. If we try to set it here then we have
 		 * a race condition if two io_destroy() called simultaneously.
 		 */
-		ret = kill_ioctx(current->mm, ioctx, &requests_done);
+		ret = kill_ioctx(current->mm, ioctx, &wait);
 		percpu_ref_put(&ioctx->users);
 
 		/* Wait until all IO for the context are done. Otherwise kernel
@@ -1347,7 +1362,7 @@ SYSCALL_DEFINE1(io_destroy, aio_context_t, ctx)
 		 * is destroyed.
 		 */
 		if (!ret)
-			wait_for_completion(&requests_done);
+			wait_for_completion(&wait.comp);
 
 		return ret;
 	}