blk-mq: Move flush queue allocation into blk_mq_init_hctx()

Move flush queue allocation into blk_mq_init_hctx() and its release into
blk_mq_exit_hctx(), and prepare for replacing tags->lock with SRCU to
draining inflight request walking. blk_mq_exit_hctx() is the last chance
for us to get valid `tag_set` reference, and we need to add one SRCU to
`tag_set` for freeing flush request via call_srcu().

It is safe to move flush queue & request release into blk_mq_exit_hctx(),
because blk_mq_clear_flush_rq_mapping() clears the flush request
reference int driver tags inflight request table, meantime inflight
request walking is drained.

Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Yu Kuai <yukuai3@huawei.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Author: Ming Lei

block/blk-mq-sysfs.c

@@ -34,7 +34,6 @@ static void blk_mq_hw_sysfs_release(struct kobject *kobj)
 	struct blk_mq_hw_ctx *hctx = container_of(kobj, struct blk_mq_hw_ctx,
 						  kobj);
 
-	blk_free_flush_queue(hctx->fq);
 	sbitmap_free(&hctx->ctx_map);
 	free_cpumask_var(hctx->cpumask);
 	kfree(hctx->ctxs);

block/blk-mq.c

@@ -3939,6 +3939,9 @@ static void blk_mq_exit_hctx(struct request_queue *q,
 	if (set->ops->exit_hctx)
 		set->ops->exit_hctx(hctx, hctx_idx);
 
+	blk_free_flush_queue(hctx->fq);
+	hctx->fq = NULL;
+
 	xa_erase(&q->hctx_table, hctx_idx);
 
 	spin_lock(&q->unused_hctx_lock);
@@ -3964,13 +3967,19 @@ 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)
 {
+	gfp_t gfp = GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY;
+
+	hctx->fq = blk_alloc_flush_queue(hctx->numa_node, set->cmd_size, gfp);
+	if (!hctx->fq)
+		goto fail;
+
 	hctx->queue_num = hctx_idx;
 
 	hctx->tags = set->tags[hctx_idx];
 
 	if (set->ops->init_hctx &&
 	    set->ops->init_hctx(hctx, set->driver_data, hctx_idx))
-		goto fail;
+		goto fail_free_fq;
 
 	if (blk_mq_init_request(set, hctx->fq->flush_rq, hctx_idx,
 				hctx->numa_node))
@@ -3987,6 +3996,9 @@ static int blk_mq_init_hctx(struct request_queue *q,
  exit_hctx:
 	if (set->ops->exit_hctx)
 		set->ops->exit_hctx(hctx, hctx_idx);
+ fail_free_fq:
+	blk_free_flush_queue(hctx->fq);
+	hctx->fq = NULL;
  fail:
 	return -1;
 }
@@ -4038,16 +4050,10 @@ blk_mq_alloc_hctx(struct request_queue *q, struct blk_mq_tag_set *set,
 	init_waitqueue_func_entry(&hctx->dispatch_wait, blk_mq_dispatch_wake);
 	INIT_LIST_HEAD(&hctx->dispatch_wait.entry);
 
-	hctx->fq = blk_alloc_flush_queue(hctx->numa_node, set->cmd_size, gfp);
-	if (!hctx->fq)
-		goto free_bitmap;
-
 	blk_mq_hctx_kobj_init(hctx);
 
 	return hctx;
 
- free_bitmap:
-	sbitmap_free(&hctx->ctx_map);
  free_ctxs:
 	kfree(hctx->ctxs);
  free_cpumask: