1 files changed, 44 insertions, 31 deletions

diff --git a/block/blk-mq.c b/block/blk-mq.c
index b7b8933ec241..ade8a2d1b0aa 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
@@ -42,7 +41,7 @@ static bool blk_mq_hctx_has_pending(struct blk_mq_hw_ctx *hctx)
 {
 	unsigned int i;
 
-	for (i = 0; i < hctx->ctx_map.map_size; i++)
+	for (i = 0; i < hctx->ctx_map.size; i++)
 		if (hctx->ctx_map.map[i].word)
 			return true;
 
@@ -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);
 
@@ -728,7 +730,7 @@ static void flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list)
 	struct blk_mq_ctx *ctx;
 	int i;
 
-	for (i = 0; i < hctx->ctx_map.map_size; i++) {
+	for (i = 0; i < hctx->ctx_map.size; i++) {
 		struct blk_align_bitmap *bm = &hctx->ctx_map.map[i];
 		unsigned int off, bit;
 
@@ -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;
 	}
@@ -1457,7 +1460,7 @@ static struct blk_mq_tags *blk_mq_init_rq_map(struct blk_mq_tag_set *set,
 
 		do {
 			page = alloc_pages_node(set->numa_node,
-				GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY,
+				GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY | __GFP_ZERO,
 				this_order);
 			if (page)
 				break;
@@ -1479,8 +1482,6 @@ static struct blk_mq_tags *blk_mq_init_rq_map(struct blk_mq_tag_set *set,
 		left -= to_do * rq_size;
 		for (j = 0; j < to_do; j++) {
 			tags->rqs[i] = p;
-			tags->rqs[i]->atomic_flags = 0;
-			tags->rqs[i]->cmd_flags = 0;
 			if (set->ops->init_request) {
 				if (set->ops->init_request(set->driver_data,
 						tags->rqs[i], hctx_idx, i,
@@ -1519,8 +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);
@@ -1761,8 +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
@@ -1799,6 +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.
@@ -1815,6 +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->size = DIV_ROUND_UP(hctx->nr_ctx, map->bits_per_word);
+
+		/*
 		 * Initialize batch roundrobin counts
 		 */
 		hctx->next_cpu = cpumask_first(hctx->cpumask);
@@ -1891,9 +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;
 
@@ -1928,20 +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;
@@ -1967,9 +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...
 	 */
@@ -1981,7 +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);
@@ -1993,8 +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++) {
@@ -2009,7 +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)
 {
@@ -2161,7 +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) {