block: free sched's request pool in blk_cleanup_queue

In theory, IO scheduler belongs to request queue, and the request pool
of sched tags belongs to the request queue too.

However, the current tags allocation interfaces are re-used for both
driver tags and sched tags, and driver tags is definitely host wide,
and doesn't belong to any request queue, same with its request pool.
So we need tagset instance for freeing request of sched tags.

Meantime, blk_mq_free_tag_set() often follows blk_cleanup_queue() in case
of non-BLK_MQ_F_TAG_SHARED, this way requires that request pool of sched
tags to be freed before calling blk_mq_free_tag_set().

Commit 47cdee29ef9d94e ("block: move blk_exit_queue into __blk_release_queue")
moves blk_exit_queue into __blk_release_queue for simplying the fast
path in generic_make_request(), then causes oops during freeing requests
of sched tags in __blk_release_queue().

Fix the above issue by move freeing request pool of sched tags into
blk_cleanup_queue(), this way is safe becasue queue has been frozen and no any
in-queue requests at that time. Freeing sched tags has to be kept in queue's
release handler becasue there might be un-completed dispatch activity
which might refer to sched tags.

Cc: Bart Van Assche <bvanassche@acm.org>
Cc: Christoph Hellwig <hch@lst.de>
Fixes: 47cdee29ef9d94e485eb08f962c74943023a5271 ("block: move blk_exit_queue into __blk_release_queue")
Tested-by: Yi Zhang <yi.zhang@redhat.com>
Reported-by: kernel test robot <rong.a.chen@intel.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 27 insertions, 3 deletions

diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index 74c6bb871f7e..500cb04901cc 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -475,14 +475,18 @@ static int blk_mq_sched_alloc_tags(struct request_queue *q,
 	return ret;
 }
 
+/* called in queue's release handler, tagset has gone away */
 static void blk_mq_sched_tags_teardown(struct request_queue *q)
 {
-	struct blk_mq_tag_set *set = q->tag_set;
 	struct blk_mq_hw_ctx *hctx;
 	int i;
 
-	queue_for_each_hw_ctx(q, hctx, i)
-		blk_mq_sched_free_tags(set, hctx, i);
+	queue_for_each_hw_ctx(q, hctx, i) {
+		if (hctx->sched_tags) {
+			blk_mq_free_rq_map(hctx->sched_tags);
+			hctx->sched_tags = NULL;
+		}
+	}
 }
 
 int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e)
@@ -523,6 +527,7 @@ int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e)
 			ret = e->ops.init_hctx(hctx, i);
 			if (ret) {
 				eq = q->elevator;
+				blk_mq_sched_free_requests(q);
 				blk_mq_exit_sched(q, eq);
 				kobject_put(&eq->kobj);
 				return ret;
@@ -534,11 +539,30 @@ int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e)
 	return 0;
 
 err:
+	blk_mq_sched_free_requests(q);
 	blk_mq_sched_tags_teardown(q);
 	q->elevator = NULL;
 	return ret;
 }
 
+/*
+ * called in either blk_queue_cleanup or elevator_switch, tagset
+ * is required for freeing requests
+ */
+void blk_mq_sched_free_requests(struct request_queue *q)
+{
+	struct blk_mq_hw_ctx *hctx;
+	int i;
+
+	lockdep_assert_held(&q->sysfs_lock);
+	WARN_ON(!q->elevator);
+
+	queue_for_each_hw_ctx(q, hctx, i) {
+		if (hctx->sched_tags)
+			blk_mq_free_rqs(q->tag_set, hctx->sched_tags, i);
+	}
+}
+
 void blk_mq_exit_sched(struct request_queue *q, struct elevator_queue *e)
 {
 	struct blk_mq_hw_ctx *hctx;