[PATCH io_uring backport to 5.13.y] io_uring: Fix race condition when sqp thread goes to sleep

From: Olivier Langlois <olivier@trillion01.com>
To: Jens Axboe <axboe@kernel.dk>,
	Pavel Begunkov <asml.silence@gmail.com>,
	io-uring@vger.kernel.org, linux-kernel@vger.kernel.org,
	stable@vger.kernel.org, gregkh@linuxfoundation.org
Subject: [PATCH io_uring backport to 5.13.y] io_uring: Fix race condition when sqp thread goes to sleep
Date: Sat, 24 Jul 2021 22:07:59 -0700	[thread overview]
Message-ID: <82a82077d8b02166482df754b1abb7c3fbc3c560.1627189961.git.olivier@trillion01.com> (raw)

[ Upstream commit 997135017716 ("io_uring: Fix race condition when sqp thread goes to sleep") ]

If an asynchronous completion happens before the task is preparing
itself to wait and set its state to TASK_INTERRUPTIBLE, the completion
will not wake up the sqp thread.

Signed-off-by: Olivier Langlois <olivier@trillion01.com>
---
 fs/io_uring.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index eeea6b8c8bee..a7f1cbd7be9a 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -6876,7 +6876,8 @@ static int io_sq_thread(void *data)
 		}
 
 		prepare_to_wait(&sqd->wait, &wait, TASK_INTERRUPTIBLE);
-		if (!test_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state)) {
+		if (!test_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state) &&
+		    !io_run_task_work()) {
 			list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
 				io_ring_set_wakeup_flag(ctx);
 
-- 
2.32.0

