From: Pavel Begunkov <asml.silence@gmail.com>
Date: Sun, 11 Apr 2021 00:46:38 +0000 (+0100)
Subject: io_uring: improve sqo stop
X-Git-Url: http://git.maquefel.me/?a=commitdiff_plain;h=88885f66e8c66311923c16caf1ccb6415ebfef72;p=linux.git

io_uring: improve sqo stop

Set IO_SQ_THREAD_SHOULD_STOP before taking sqd lock, so the sqpoll task
sees earlier. Not a problem, it will stop eventually. Also check
invariant that it's stopped only once.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/653b24ee93843a50ff65a45847d9138f5adb76d7.1618101759.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 880c7743ab090..7f2590c5d1943 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -7229,9 +7229,10 @@ static void io_sq_thread_park(struct io_sq_data *sqd)
 static void io_sq_thread_stop(struct io_sq_data *sqd)
 {
 	WARN_ON_ONCE(sqd->thread == current);
+	WARN_ON_ONCE(test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state));
 
-	mutex_lock(&sqd->lock);
 	set_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state);
+	mutex_lock(&sqd->lock);
 	if (sqd->thread)
 		wake_up_process(sqd->thread);
 	mutex_unlock(&sqd->lock);