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

5 files changed, 93 insertions, 46 deletions

diff --git a/block/blk-core.c b/block/blk-core.c
index 794c3e7f01cf..fd154b94447a 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -557,6 +557,18 @@ void blk_cleanup_queue(struct request_queue *q)
 }
 EXPORT_SYMBOL(blk_cleanup_queue);
 
+/* Allocate memory local to the request queue */
+static void *alloc_request_struct(gfp_t gfp_mask, void *data)
+{
+	int nid = (int)(long)data;
+	return kmem_cache_alloc_node(request_cachep, gfp_mask, nid);
+}
+
+static void free_request_struct(void *element, void *unused)
+{
+	kmem_cache_free(request_cachep, element);
+}
+
 int blk_init_rl(struct request_list *rl, struct request_queue *q,
 		gfp_t gfp_mask)
 {
@@ -569,9 +581,10 @@ int blk_init_rl(struct request_list *rl, struct request_queue *q,
 	init_waitqueue_head(&rl->wait[BLK_RW_SYNC]);
 	init_waitqueue_head(&rl->wait[BLK_RW_ASYNC]);
 
-	rl->rq_pool = mempool_create_node(BLKDEV_MIN_RQ, mempool_alloc_slab,
-					  mempool_free_slab, request_cachep,
-					  gfp_mask, q->node);
+	rl->rq_pool = mempool_create_node(BLKDEV_MIN_RQ, alloc_request_struct,
+					  free_request_struct,
+					  (void *)(long)q->node, gfp_mask,
+					  q->node);
 	if (!rl->rq_pool)
 		return -ENOMEM;
 
diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c
index 1630a20d5dcf..b79685e06b70 100644
--- a/block/blk-mq-sysfs.c
+++ b/block/blk-mq-sysfs.c
@@ -436,6 +436,7 @@ int blk_mq_register_disk(struct gendisk *disk)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(blk_mq_register_disk);
 
 void blk_mq_sysfs_unregister(struct request_queue *q)
 {
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 33c428530193..c82de08f3721 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -33,7 +33,6 @@ static DEFINE_MUTEX(all_q_mutex);
 static LIST_HEAD(all_q_list);
 
 static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx);
-static void blk_mq_run_queues(struct request_queue *q);
 
 /*
  * Check if any of the ctx's have pending work in this hardware queue
@@ -78,7 +77,7 @@ static void blk_mq_hctx_clear_pending(struct blk_mq_hw_ctx *hctx,
 	clear_bit(CTX_TO_BIT(hctx, ctx), &bm->word);
 }
 
-static int blk_mq_queue_enter(struct request_queue *q)
+static int blk_mq_queue_enter(struct request_queue *q, gfp_t gfp)
 {
 	while (true) {
 		int ret;
@@ -86,6 +85,9 @@ static int blk_mq_queue_enter(struct request_queue *q)
 		if (percpu_ref_tryget_live(&q->mq_usage_counter))
 			return 0;
 
+		if (!(gfp & __GFP_WAIT))
+			return -EBUSY;
+
 		ret = wait_event_interruptible(q->mq_freeze_wq,
 				!q->mq_freeze_depth || blk_queue_dying(q));
 		if (blk_queue_dying(q))
@@ -118,7 +120,7 @@ void blk_mq_freeze_queue_start(struct request_queue *q)
 
 	if (freeze) {
 		percpu_ref_kill(&q->mq_usage_counter);
-		blk_mq_run_queues(q);
+		blk_mq_run_hw_queues(q, false);
 	}
 }
 EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_start);
@@ -257,7 +259,7 @@ struct request *blk_mq_alloc_request(struct request_queue *q, int rw, gfp_t gfp,
 	struct blk_mq_alloc_data alloc_data;
 	int ret;
 
-	ret = blk_mq_queue_enter(q);
+	ret = blk_mq_queue_enter(q, gfp);
 	if (ret)
 		return ERR_PTR(ret);
 
@@ -904,7 +906,7 @@ void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
 			&hctx->run_work, 0);
 }
 
-static void blk_mq_run_queues(struct request_queue *q)
+void blk_mq_run_hw_queues(struct request_queue *q, bool async)
 {
 	struct blk_mq_hw_ctx *hctx;
 	int i;
@@ -915,9 +917,10 @@ static void blk_mq_run_queues(struct request_queue *q)
 		    test_bit(BLK_MQ_S_STOPPED, &hctx->state))
 			continue;
 
-		blk_mq_run_hw_queue(hctx, false);
+		blk_mq_run_hw_queue(hctx, async);
 	}
 }
+EXPORT_SYMBOL(blk_mq_run_hw_queues);
 
 void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx)
 {
@@ -1186,7 +1189,7 @@ static struct request *blk_mq_map_request(struct request_queue *q,
 	int rw = bio_data_dir(bio);
 	struct blk_mq_alloc_data alloc_data;
 
-	if (unlikely(blk_mq_queue_enter(q))) {
+	if (unlikely(blk_mq_queue_enter(q, GFP_KERNEL))) {
 		bio_endio(bio, -EIO);
 		return NULL;
 	}
@@ -1517,8 +1520,6 @@ static int blk_mq_alloc_bitmap(struct blk_mq_ctxmap *bitmap, int node)
 	if (!bitmap->map)
 		return -ENOMEM;
 
-	bitmap->map_size = num_maps;
-
 	total = nr_cpu_ids;
 	for (i = 0; i < num_maps; i++) {
 		bitmap->map[i].depth = min(total, bitmap->bits_per_word);
@@ -1759,8 +1760,6 @@ static void blk_mq_init_cpu_queues(struct request_queue *q,
 			continue;
 
 		hctx = q->mq_ops->map_queue(q, i);
-		cpumask_set_cpu(i, hctx->cpumask);
-		hctx->nr_ctx++;
 
 		/*
 		 * Set local node, IFF we have more than one hw queue. If
@@ -1797,6 +1796,8 @@ static void blk_mq_map_swqueue(struct request_queue *q)
 	}
 
 	queue_for_each_hw_ctx(q, hctx, i) {
+		struct blk_mq_ctxmap *map = &hctx->ctx_map;
+
 		/*
 		 * If no software queues are mapped to this hardware queue,
 		 * disable it and free the request entries.
@@ -1813,6 +1814,13 @@ static void blk_mq_map_swqueue(struct request_queue *q)
 		}
 
 		/*
+		 * Set the map size to the number of mapped software queues.
+		 * This is more accurate and more efficient than looping
+		 * over all possibly mapped software queues.
+		 */
+		map->map_size = hctx->nr_ctx / map->bits_per_word;
+
+		/*
 		 * Initialize batch roundrobin counts
 		 */
 		hctx->next_cpu = cpumask_first(hctx->cpumask);
@@ -1889,9 +1897,25 @@ void blk_mq_release(struct request_queue *q)
 
 struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set)
 {
+	struct request_queue *uninit_q, *q;
+
+	uninit_q = blk_alloc_queue_node(GFP_KERNEL, set->numa_node);
+	if (!uninit_q)
+		return ERR_PTR(-ENOMEM);
+
+	q = blk_mq_init_allocated_queue(set, uninit_q);
+	if (IS_ERR(q))
+		blk_cleanup_queue(uninit_q);
+
+	return q;
+}
+EXPORT_SYMBOL(blk_mq_init_queue);
+
+struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
+						  struct request_queue *q)
+{
 	struct blk_mq_hw_ctx **hctxs;
 	struct blk_mq_ctx __percpu *ctx;
-	struct request_queue *q;
 	unsigned int *map;
 	int i;
 
@@ -1926,20 +1950,16 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set)
 		hctxs[i]->queue_num = i;
 	}
 
-	q = blk_alloc_queue_node(GFP_KERNEL, set->numa_node);
-	if (!q)
-		goto err_hctxs;
-
 	/*
 	 * Init percpu_ref in atomic mode so that it's faster to shutdown.
 	 * See blk_register_queue() for details.
 	 */
 	if (percpu_ref_init(&q->mq_usage_counter, blk_mq_usage_counter_release,
 			    PERCPU_REF_INIT_ATOMIC, GFP_KERNEL))
-		goto err_mq_usage;
+		goto err_hctxs;
 
 	setup_timer(&q->timeout, blk_mq_rq_timer, (unsigned long) q);
-	blk_queue_rq_timeout(q, 30000);
+	blk_queue_rq_timeout(q, set->timeout ? set->timeout : 30000);
 
 	q->nr_queues = nr_cpu_ids;
 	q->nr_hw_queues = set->nr_hw_queues;
@@ -1965,9 +1985,6 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set)
 	else
 		blk_queue_make_request(q, blk_sq_make_request);
 
-	if (set->timeout)
-		blk_queue_rq_timeout(q, set->timeout);
-
 	/*
 	 * Do this after blk_queue_make_request() overrides it...
 	 */
@@ -1979,7 +1996,7 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set)
 	blk_mq_init_cpu_queues(q, set->nr_hw_queues);
 
 	if (blk_mq_init_hw_queues(q, set))
-		goto err_mq_usage;
+		goto err_hctxs;
 
 	mutex_lock(&all_q_mutex);
 	list_add_tail(&q->all_q_node, &all_q_list);
@@ -1991,8 +2008,6 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set)
 
 	return q;
 
-err_mq_usage:
-	blk_cleanup_queue(q);
 err_hctxs:
 	kfree(map);
 	for (i = 0; i < set->nr_hw_queues; i++) {
@@ -2007,7 +2022,7 @@ err_percpu:
 	free_percpu(ctx);
 	return ERR_PTR(-ENOMEM);
 }
-EXPORT_SYMBOL(blk_mq_init_queue);
+EXPORT_SYMBOL(blk_mq_init_allocated_queue);
 
 void blk_mq_free_queue(struct request_queue *q)
 {
@@ -2159,7 +2174,7 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
 	if (set->queue_depth < set->reserved_tags + BLK_MQ_TAG_MIN)
 		return -EINVAL;
 
-	if (!set->nr_hw_queues || !set->ops->queue_rq || !set->ops->map_queue)
+	if (!set->ops->queue_rq || !set->ops->map_queue)
 		return -EINVAL;
 
 	if (set->queue_depth > BLK_MQ_MAX_DEPTH) {
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;
 	}
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 7aec86127335..8210e8797c12 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -164,6 +164,8 @@ enum {
 		<< BLK_MQ_F_ALLOC_POLICY_START_BIT)
 
 struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *);
+struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
+						  struct request_queue *q);
 void blk_mq_finish_init(struct request_queue *q);
 int blk_mq_register_disk(struct gendisk *);
 void blk_mq_unregister_disk(struct gendisk *);
@@ -218,6 +220,7 @@ void blk_mq_start_hw_queue(struct blk_mq_hw_ctx *hctx);
 void blk_mq_stop_hw_queues(struct request_queue *q);
 void blk_mq_start_hw_queues(struct request_queue *q);
 void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async);
+void blk_mq_run_hw_queues(struct request_queue *q, bool async);
 void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs);
 void blk_mq_tag_busy_iter(struct blk_mq_hw_ctx *hctx, busy_iter_fn *fn,
 		void *priv);
@@ -227,7 +230,7 @@ void blk_mq_freeze_queue_start(struct request_queue *q);
 
 /*
  * Driver command data is immediately after the request. So subtract request
- * size to get back to the original request.
+ * size to get back to the original request, add request size to get the PDU.
  */
 static inline struct request *blk_mq_rq_from_pdu(void *pdu)
 {
@@ -235,7 +238,7 @@ static inline struct request *blk_mq_rq_from_pdu(void *pdu)
 }
 static inline void *blk_mq_rq_to_pdu(struct request *rq)
 {
-	return (void *) rq + sizeof(*rq);
+	return rq + 1;
 }
 
 #define queue_for_each_hw_ctx(q, hctx, i)				\