1 files changed, 111 insertions, 81 deletions

diff --git a/block/blk-mq.c b/block/blk-mq.c
index fc60ed7e940e..08a6248d8536 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Block multiqueue core code
  *
@@ -2062,7 +2063,7 @@ void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
 		list_del_init(&page->lru);
 		/*
 		 * Remove kmemleak object previously allocated in
-		 * blk_mq_init_rq_map().
+		 * blk_mq_alloc_rqs().
 		 */
 		kmemleak_free(page_address(page));
 		__free_pages(page, page->private);
@@ -2267,12 +2268,11 @@ static void blk_mq_exit_hctx(struct request_queue *q,
 	if (set->ops->exit_hctx)
 		set->ops->exit_hctx(hctx, hctx_idx);
 
-	if (hctx->flags & BLK_MQ_F_BLOCKING)
-		cleanup_srcu_struct(hctx->srcu);
-
 	blk_mq_remove_cpuhp(hctx);
-	blk_free_flush_queue(hctx->fq);
-	sbitmap_free(&hctx->ctx_map);
+
+	spin_lock(&q->unused_hctx_lock);
+	list_add(&hctx->hctx_list, &q->unused_hctx_list);
+	spin_unlock(&q->unused_hctx_lock);
 }
 
 static void blk_mq_exit_hw_queues(struct request_queue *q,
@@ -2289,15 +2289,65 @@ static void blk_mq_exit_hw_queues(struct request_queue *q,
 	}
 }
 
+static int blk_mq_hw_ctx_size(struct blk_mq_tag_set *tag_set)
+{
+	int hw_ctx_size = sizeof(struct blk_mq_hw_ctx);
+
+	BUILD_BUG_ON(ALIGN(offsetof(struct blk_mq_hw_ctx, srcu),
+			   __alignof__(struct blk_mq_hw_ctx)) !=
+		     sizeof(struct blk_mq_hw_ctx));
+
+	if (tag_set->flags & BLK_MQ_F_BLOCKING)
+		hw_ctx_size += sizeof(struct srcu_struct);
+
+	return hw_ctx_size;
+}
+
 static int blk_mq_init_hctx(struct request_queue *q,
 		struct blk_mq_tag_set *set,
 		struct blk_mq_hw_ctx *hctx, unsigned hctx_idx)
 {
-	int node;
+	hctx->queue_num = hctx_idx;
+
+	cpuhp_state_add_instance_nocalls(CPUHP_BLK_MQ_DEAD, &hctx->cpuhp_dead);
+
+	hctx->tags = set->tags[hctx_idx];
+
+	if (set->ops->init_hctx &&
+	    set->ops->init_hctx(hctx, set->driver_data, hctx_idx))
+		goto unregister_cpu_notifier;
+
+	if (blk_mq_init_request(set, hctx->fq->flush_rq, hctx_idx,
+				hctx->numa_node))
+		goto exit_hctx;
+	return 0;
+
+ exit_hctx:
+	if (set->ops->exit_hctx)
+		set->ops->exit_hctx(hctx, hctx_idx);
+ unregister_cpu_notifier:
+	blk_mq_remove_cpuhp(hctx);
+	return -1;
+}
+
+static struct blk_mq_hw_ctx *
+blk_mq_alloc_hctx(struct request_queue *q, struct blk_mq_tag_set *set,
+		int node)
+{
+	struct blk_mq_hw_ctx *hctx;
+	gfp_t gfp = GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY;
+
+	hctx = kzalloc_node(blk_mq_hw_ctx_size(set), gfp, node);
+	if (!hctx)
+		goto fail_alloc_hctx;
 
-	node = hctx->numa_node;
+	if (!zalloc_cpumask_var_node(&hctx->cpumask, gfp, node))
+		goto free_hctx;
+
+	atomic_set(&hctx->nr_active, 0);
 	if (node == NUMA_NO_NODE)
-		node = hctx->numa_node = set->numa_node;
+		node = set->numa_node;
+	hctx->numa_node = node;
 
 	INIT_DELAYED_WORK(&hctx->run_work, blk_mq_run_work_fn);
 	spin_lock_init(&hctx->lock);
@@ -2305,58 +2355,47 @@ static int blk_mq_init_hctx(struct request_queue *q,
 	hctx->queue = q;
 	hctx->flags = set->flags & ~BLK_MQ_F_TAG_SHARED;
 
-	cpuhp_state_add_instance_nocalls(CPUHP_BLK_MQ_DEAD, &hctx->cpuhp_dead);
-
-	hctx->tags = set->tags[hctx_idx];
+	INIT_LIST_HEAD(&hctx->hctx_list);
 
 	/*
 	 * Allocate space for all possible cpus to avoid allocation at
 	 * runtime
 	 */
 	hctx->ctxs = kmalloc_array_node(nr_cpu_ids, sizeof(void *),
-			GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY, node);
+			gfp, node);
 	if (!hctx->ctxs)
-		goto unregister_cpu_notifier;
+		goto free_cpumask;
 
 	if (sbitmap_init_node(&hctx->ctx_map, nr_cpu_ids, ilog2(8),
-				GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY, node))
+				gfp, node))
 		goto free_ctxs;
-
 	hctx->nr_ctx = 0;
 
 	spin_lock_init(&hctx->dispatch_wait_lock);
 	init_waitqueue_func_entry(&hctx->dispatch_wait, blk_mq_dispatch_wake);
 	INIT_LIST_HEAD(&hctx->dispatch_wait.entry);
 
-	if (set->ops->init_hctx &&
-	    set->ops->init_hctx(hctx, set->driver_data, hctx_idx))
-		goto free_bitmap;
-
 	hctx->fq = blk_alloc_flush_queue(q, hctx->numa_node, set->cmd_size,
-			GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY);
+			gfp);
 	if (!hctx->fq)
-		goto exit_hctx;
-
-	if (blk_mq_init_request(set, hctx->fq->flush_rq, hctx_idx, node))
-		goto free_fq;
+		goto free_bitmap;
 
 	if (hctx->flags & BLK_MQ_F_BLOCKING)
 		init_srcu_struct(hctx->srcu);
+	blk_mq_hctx_kobj_init(hctx);
 
-	return 0;
+	return hctx;
 
- free_fq:
-	blk_free_flush_queue(hctx->fq);
- exit_hctx:
-	if (set->ops->exit_hctx)
-		set->ops->exit_hctx(hctx, hctx_idx);
  free_bitmap:
 	sbitmap_free(&hctx->ctx_map);
  free_ctxs:
 	kfree(hctx->ctxs);
- unregister_cpu_notifier:
-	blk_mq_remove_cpuhp(hctx);
-	return -1;
+ free_cpumask:
+	free_cpumask_var(hctx->cpumask);
+ free_hctx:
+	kfree(hctx);
+ fail_alloc_hctx:
+	return NULL;
 }
 
 static void blk_mq_init_cpu_queues(struct request_queue *q,
@@ -2631,13 +2670,17 @@ static int blk_mq_alloc_ctxs(struct request_queue *q)
  */
 void blk_mq_release(struct request_queue *q)
 {
-	struct blk_mq_hw_ctx *hctx;
-	unsigned int i;
+	struct blk_mq_hw_ctx *hctx, *next;
+	int i;
 
-	/* hctx kobj stays in hctx */
-	queue_for_each_hw_ctx(q, hctx, i) {
-		if (!hctx)
-			continue;
+	cancel_delayed_work_sync(&q->requeue_work);
+
+	queue_for_each_hw_ctx(q, hctx, i)
+		WARN_ON_ONCE(hctx && list_empty(&hctx->hctx_list));
+
+	/* all hctx are in .unused_hctx_list now */
+	list_for_each_entry_safe(hctx, next, &q->unused_hctx_list, hctx_list) {
+		list_del_init(&hctx->hctx_list);
 		kobject_put(&hctx->kobj);
 	}
 
@@ -2700,51 +2743,38 @@ struct request_queue *blk_mq_init_sq_queue(struct blk_mq_tag_set *set,
 }
 EXPORT_SYMBOL(blk_mq_init_sq_queue);
 
-static int blk_mq_hw_ctx_size(struct blk_mq_tag_set *tag_set)
-{
-	int hw_ctx_size = sizeof(struct blk_mq_hw_ctx);
-
-	BUILD_BUG_ON(ALIGN(offsetof(struct blk_mq_hw_ctx, srcu),
-			   __alignof__(struct blk_mq_hw_ctx)) !=
-		     sizeof(struct blk_mq_hw_ctx));
-
-	if (tag_set->flags & BLK_MQ_F_BLOCKING)
-		hw_ctx_size += sizeof(struct srcu_struct);
-
-	return hw_ctx_size;
-}
-
 static struct blk_mq_hw_ctx *blk_mq_alloc_and_init_hctx(
 		struct blk_mq_tag_set *set, struct request_queue *q,
 		int hctx_idx, int node)
 {
-	struct blk_mq_hw_ctx *hctx;
-
-	hctx = kzalloc_node(blk_mq_hw_ctx_size(set),
-			GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY,
-			node);
-	if (!hctx)
-		return NULL;
+	struct blk_mq_hw_ctx *hctx = NULL, *tmp;
 
-	if (!zalloc_cpumask_var_node(&hctx->cpumask,
-				GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY,
-				node)) {
-		kfree(hctx);
-		return NULL;
+	/* reuse dead hctx first */
+	spin_lock(&q->unused_hctx_lock);
+	list_for_each_entry(tmp, &q->unused_hctx_list, hctx_list) {
+		if (tmp->numa_node == node) {
+			hctx = tmp;
+			break;
+		}
 	}
+	if (hctx)
+		list_del_init(&hctx->hctx_list);
+	spin_unlock(&q->unused_hctx_lock);
 
-	atomic_set(&hctx->nr_active, 0);
-	hctx->numa_node = node;
-	hctx->queue_num = hctx_idx;
+	if (!hctx)
+		hctx = blk_mq_alloc_hctx(q, set, node);
+	if (!hctx)
+		goto fail;
 
-	if (blk_mq_init_hctx(q, set, hctx, hctx_idx)) {
-		free_cpumask_var(hctx->cpumask);
-		kfree(hctx);
-		return NULL;
-	}
-	blk_mq_hctx_kobj_init(hctx);
+	if (blk_mq_init_hctx(q, set, hctx, hctx_idx))
+		goto free_hctx;
 
 	return hctx;
+
+ free_hctx:
+	kobject_put(&hctx->kobj);
+ fail:
+	return NULL;
 }
 
 static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
@@ -2770,10 +2800,8 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
 
 		hctx = blk_mq_alloc_and_init_hctx(set, q, i, node);
 		if (hctx) {
-			if (hctxs[i]) {
+			if (hctxs[i])
 				blk_mq_exit_hctx(q, set, hctxs[i], i);
-				kobject_put(&hctxs[i]->kobj);
-			}
 			hctxs[i] = hctx;
 		} else {
 			if (hctxs[i])
@@ -2804,9 +2832,7 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
 			if (hctx->tags)
 				blk_mq_free_map_and_requests(set, j);
 			blk_mq_exit_hctx(q, set, hctx, j);
-			kobject_put(&hctx->kobj);
 			hctxs[j] = NULL;
-
 		}
 	}
 	mutex_unlock(&q->sysfs_lock);
@@ -2849,6 +2875,9 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 	if (!q->queue_hw_ctx)
 		goto err_sys_init;
 
+	INIT_LIST_HEAD(&q->unused_hctx_list);
+	spin_lock_init(&q->unused_hctx_lock);
+
 	blk_mq_realloc_hw_ctxs(set, q);
 	if (!q->nr_hw_queues)
 		goto err_hctxs;
@@ -2905,7 +2934,8 @@ err_exit:
 }
 EXPORT_SYMBOL(blk_mq_init_allocated_queue);
 
-void blk_mq_free_queue(struct request_queue *q)
+/* tags can _not_ be used after returning from blk_mq_exit_queue */
+void blk_mq_exit_queue(struct request_queue *q)
 {
 	struct blk_mq_tag_set	*set = q->tag_set;