diff options
| author | Michal Koutný <mkoutny@suse.com> | 2026-02-05 23:54:23 +0800 |
|---|---|---|
| committer | Jens Axboe <axboe@kernel.dk> | 2026-06-22 15:58:41 -0600 |
| commit | 0ab5ee5a1badb58cbb2242617cb01a4972b1f2a2 (patch) | |
| tree | 1533af7cafafd1e0df5840802c6ba57d2f71a065 /block | |
| parent | 17b2d950a3c0328ed749476e6118ca869b3ca8b5 (diff) | |
| download | linux-2.6-0ab5ee5a1badb58cbb2242617cb01a4972b1f2a2.tar.gz linux-2.6-0ab5ee5a1badb58cbb2242617cb01a4972b1f2a2.zip | |
blk-cgroup: fix UAF in __blkcg_rstat_flush()
When multiple blkgs in the same blkcg are released concurrently,
a use-after-free can occur. The race happens when one blkg's
__blkcg_rstat_flush() removes another blkg's iostat entries via
llist_del_all(). The second blkg sees an empty list and proceeds
to free itself while the first is still iterating over its entries.
Move the flush from __blkg_release() (RCU callback) to blkg_release()
(before call_rcu). This ensures the RCU grace period waits for any
concurrent flush's rcu_read_lock() section to complete before freeing.
Cc: stable@vger.kernel.org
Cc: Jay Shin <jaeshin@redhat.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Waiman Long <longman@redhat.com>
Fixes: 20cb1c2fb756 ("blk-cgroup: Flush stats before releasing blkcg_gq")
Reported-by: coregee2000@gmail.com
Closes: https://lore.kernel.org/linux-block/CAHPqNmwT9oRpem3J3erS_W0uSQND47LGGSBsNxP8E6uSUish1w@mail.gmail.com/
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Tested-by: Jose Fernandez (Anthropic) <jose.fernandez@linux.dev>
Link: https://patch.msgid.link/20260205155425.342084-1-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Diffstat (limited to 'block')
| -rw-r--r-- | block/blk-cgroup.c | 21 |
1 files changed, 11 insertions, 10 deletions
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 3093c1c03902..342816cbbd1b 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -164,20 +164,10 @@ static void blkg_free(struct blkcg_gq *blkg) static void __blkg_release(struct rcu_head *rcu) { struct blkcg_gq *blkg = container_of(rcu, struct blkcg_gq, rcu_head); - struct blkcg *blkcg = blkg->blkcg; - int cpu; #ifdef CONFIG_BLK_CGROUP_PUNT_BIO WARN_ON(!bio_list_empty(&blkg->async_bios)); #endif - /* - * Flush all the non-empty percpu lockless lists before releasing - * us, given these stat belongs to us. - * - * blkg_stat_lock is for serializing blkg stat update - */ - for_each_possible_cpu(cpu) - __blkcg_rstat_flush(blkcg, cpu); /* release the blkcg and parent blkg refs this blkg has been holding */ css_put(&blkg->blkcg->css); @@ -195,6 +185,17 @@ static void __blkg_release(struct rcu_head *rcu) static void blkg_release(struct percpu_ref *ref) { struct blkcg_gq *blkg = container_of(ref, struct blkcg_gq, refcnt); + struct blkcg *blkcg = blkg->blkcg; + int cpu; + + /* + * Flush all the non-empty percpu lockless lists before releasing + * us, given these stat belongs to us. + * + * blkg_stat_lock is for serializing blkg stat update + */ + for_each_possible_cpu(cpu) + __blkcg_rstat_flush(blkcg, cpu); call_rcu(&blkg->rcu_head, __blkg_release); } |