| From | Sasha Levin <> | Subject | [PATCH AUTOSEL 5.7 57/60] io_uring: fix racy overflow count reporting | Date | Mon, 10 Aug 2020 15:10:25 -0400 |
| |
From: Pavel Begunkov <asml.silence@gmail.com>
[ Upstream commit b2bd1cf99f3e7c8fbf12ea07af2c6998e1209e25 ]
All ->cq_overflow modifications should be under completion_lock, otherwise it can report a wrong number to the userspace. Fix it in io_uring_cancel_files().
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com> Signed-off-by: Jens Axboe <axboe@kernel.dk> Signed-off-by: Sasha Levin <sashal@kernel.org> --- fs/io_uring.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/fs/io_uring.c b/fs/io_uring.c index 80a612d1e12bb..d04fede20acb8 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -7573,10 +7573,9 @@ static void io_uring_cancel_files(struct io_ring_ctx *ctx, clear_bit(0, &ctx->sq_check_overflow); clear_bit(0, &ctx->cq_check_overflow); } - spin_unlock_irq(&ctx->completion_lock); - WRITE_ONCE(ctx->rings->cq_overflow, atomic_inc_return(&ctx->cached_cq_overflow)); + spin_unlock_irq(&ctx->completion_lock); /* * Put inflight ref and overflow ref. If that's -- 2.25.1
|