[PATCH] block: fix q->blkg_list corruption during disk rebind

[Ming Lei <ming.lei@xxxxxxxxxx>]

Multiple gendisk instances can allocated/added for single request queue
in case of disk rebind. blkg may still stay in q->blkg_list when calling
blkcg_init_disk() for rebind, then q->blkg_list becomes corrupted.

Fix the list corruption issue by:

- add blkg_init_queue() to initialize q->blkg_list & q->blkcg_mutex only
- move calling blkg_init_queue() into blk_alloc_queue()

The list corruption should be started since commit f1c006f1c685 ("blk-cgroup:
synchronize pd_free_fn() from blkg_free_workfn() and blkcg_deactivate_policy()")
which delays removing blkg from q->blkg_list into blkg_free_workfn().

Fixes: f1c006f1c685 ("blk-cgroup: synchronize pd_free_fn() from blkg_free_workfn() and blkcg_deactivate_policy()")
Fixes: 1059699f87eb ("block: move blkcg initialization/destroy into disk allocation/release handler")
Cc: Yu Kuai <yukuai3@xxxxxxxxxx>
Cc: Tejun Heo <tj@xxxxxxxxxx>
Signed-off-by: Ming Lei <ming.lei@xxxxxxxxxx>
---
blktests:
	https://lore.kernel.org/linux-block/20240407125717.4052964-1-ming.lei@xxxxxxxxxx/

 block/blk-cgroup.c | 9 ++++++---
 block/blk-cgroup.h | 2 ++
 block/blk-core.c   | 2 ++
 3 files changed, 10 insertions(+), 3 deletions(-)

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index bdbb557feb5a..059467086b13 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -1409,6 +1409,12 @@ static int blkcg_css_online(struct cgroup_subsys_state *css)
 	return 0;
 }
 
+void blkg_init_queue(struct request_queue *q)
+{
+	INIT_LIST_HEAD(&q->blkg_list);
+	mutex_init(&q->blkcg_mutex);
+}
+
 int blkcg_init_disk(struct gendisk *disk)
 {
 	struct request_queue *q = disk->queue;
@@ -1416,9 +1422,6 @@ int blkcg_init_disk(struct gendisk *disk)
 	bool preloaded;
 	int ret;
 
-	INIT_LIST_HEAD(&q->blkg_list);
-	mutex_init(&q->blkcg_mutex);
-
 	new_blkg = blkg_alloc(&blkcg_root, disk, GFP_KERNEL);
 	if (!new_blkg)
 		return -ENOMEM;
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index 78b74106bf10..90b3959d88cf 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -189,6 +189,7 @@ struct blkcg_policy {
 extern struct blkcg blkcg_root;
 extern bool blkcg_debug_stats;
 
+void blkg_init_queue(struct request_queue *q);
 int blkcg_init_disk(struct gendisk *disk);
 void blkcg_exit_disk(struct gendisk *disk);
 
@@ -482,6 +483,7 @@ struct blkcg {
 };
 
 static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, void *key) { return NULL; }
+static inline void blkg_init_queue(struct request_queue *q) { }
 static inline int blkcg_init_disk(struct gendisk *disk) { return 0; }
 static inline void blkcg_exit_disk(struct gendisk *disk) { }
 static inline int blkcg_policy_register(struct blkcg_policy *pol) { return 0; }
diff --git a/block/blk-core.c b/block/blk-core.c
index a16b5abdbbf5..3a6f5603fb44 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -442,6 +442,8 @@ struct request_queue *blk_alloc_queue(struct queue_limits *lim, int node_id)
 	init_waitqueue_head(&q->mq_freeze_wq);
 	mutex_init(&q->mq_freeze_lock);
 
+	blkg_init_queue(q);
+
 	/*
 	 * Init percpu_ref in atomic mode so that it's faster to shutdown.
 	 * See blk_register_queue() for details.
-- 
2.41.0