[PATCH 09/14] block: move blkcg initialization/destroy into disk allocation/release handler

[Christoph Hellwig <hch@lst.de>]

From: Ming Lei <ming.lei@redhat.com>

blkcg works on FS bio level, so it is reasonable to make both blkcg and
gendisk sharing same lifetime. Meantime there won't be any FS IO when
releasing disk, so safe to move blkcg initialization/destroy into disk
allocation/release handler

Long term, we can move blkcg into gendisk completely.

Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
---
 block/blk-core.c  | 5 -----
 block/blk-sysfs.c | 7 -------
 block/genhd.c     | 8 ++++++++
 3 files changed, 8 insertions(+), 12 deletions(-)

diff --git a/block/blk-core.c b/block/blk-core.c
index 4d858fc08f8ba..3fa2f08d3750b 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -496,17 +496,12 @@ struct request_queue *blk_alloc_queue(int node_id, bool alloc_srcu)
 				PERCPU_REF_INIT_ATOMIC, GFP_KERNEL))
 		goto fail_stats;
 
-	if (blkcg_init_queue(q))
-		goto fail_ref;
-
 	blk_queue_dma_alignment(q, 511);
 	blk_set_default_limits(&q->limits);
 	q->nr_requests = BLKDEV_DEFAULT_RQ;
 
 	return q;
 
-fail_ref:
-	percpu_ref_exit(&q->q_usage_counter);
 fail_stats:
 	blk_free_queue_stats(q->stats);
 fail_split:
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 241ded62f458f..220085109d7f0 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -751,13 +751,6 @@ static void blk_exit_queue(struct request_queue *q)
 		ioc_clear_queue(q);
 		elevator_exit(q);
 	}
-
-	/*
-	 * Remove all references to @q from the block cgroup controller before
-	 * restoring @q->queue_lock to avoid that restoring this pointer causes
-	 * e.g. blkcg_print_blkgs() to crash.
-	 */
-	blkcg_exit_queue(q);
 }
 
 /**
diff --git a/block/genhd.c b/block/genhd.c
index 54f60ded2ee6f..073e93f2fc40b 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -1120,9 +1120,12 @@ static void disk_release(struct device *dev)
 
 	blk_mq_cancel_work_sync(disk->queue);
 
+	blkcg_exit_queue(disk->queue);
+
 	disk_release_events(disk);
 	kfree(disk->random);
 	xa_destroy(&disk->part_tbl);
+
 	disk->queue->disk = NULL;
 	blk_put_queue(disk->queue);
 
@@ -1328,6 +1331,9 @@ struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id,
 	if (xa_insert(&disk->part_tbl, 0, disk->part0, GFP_KERNEL))
 		goto out_destroy_part_tbl;
 
+	if (blkcg_init_queue(q))
+		goto out_erase_part0;
+
 	rand_initialize_disk(disk);
 	disk_to_dev(disk)->class = &block_class;
 	disk_to_dev(disk)->type = &disk_type;
@@ -1340,6 +1346,8 @@ struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id,
 #endif
 	return disk;
 
+out_erase_part0:
+	xa_erase(&disk->part_tbl, 0);
 out_destroy_part_tbl:
 	xa_destroy(&disk->part_tbl);
 	disk->part0->bd_disk = NULL;
-- 
2.30.2