Commit d0aac236 authored by Ming Lei's avatar Ming Lei Committed by Jens Axboe
Browse files

blk-cgroup: fix list corruption from reorder of WRITE ->lqueued 



__blkcg_rstat_flush() can be run anytime, especially when blk_cgroup_bio_start
is being executed.

If WRITE of `->lqueued` is re-ordered with READ of 'bisc->lnode.next' in
the loop of __blkcg_rstat_flush(), `next_bisc` can be assigned with one
stat instance being added in blk_cgroup_bio_start(), then the local
list in __blkcg_rstat_flush() could be corrupted.

Fix the issue by adding one barrier.

Cc: Tejun Heo <tj@kernel.org>
Cc: Waiman Long <longman@redhat.com>
Fixes: 3b8cc629 ("blk-cgroup: Optimize blkcg_rstat_flush()")
Signed-off-by: default avatarMing Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20240515013157.443672-3-ming.lei@redhat.com


Signed-off-by: default avatarJens Axboe <axboe@kernel.dk>
parent 6da66806

block/blk-cgroup.c

+10 −0
Original line number Diff line number Diff line
@@ -1035,6 +1035,16 @@ static void __blkcg_rstat_flush(struct blkcg *blkcg, int cpu) 
		struct blkg_iostat cur;

		unsigned int seq;



		/*

		 * Order assignment of `next_bisc` from `bisc->lnode.next` in

		 * llist_for_each_entry_safe and clearing `bisc->lqueued` for

		 * avoiding to assign `next_bisc` with new next pointer added

		 * in blk_cgroup_bio_start() in case of re-ordering.

		 *

		 * The pair barrier is implied in llist_add() in blk_cgroup_bio_start().

		 */

		smp_mb();



		WRITE_ONCE(bisc->lqueued, false);



		/* fetch the current per-cpu values */