From 5a978dcfc0f054e4f6983a0a26355a65e34708cb Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Sat, 27 Mar 2021 09:59:30 +0000 Subject: [PATCH] io_uring: always go for cancellation spin on exec Always try to do cancellation in __io_uring_task_cancel() at least once, so it actually goes and cleans its sqpoll tasks (i.e. via io_sqpoll_cancel_sync()), otherwise sqpoll task may submit new requests after cancellation and it's racy for many reasons. Fixes: 521d6a737a31c ("io_uring: cancel sqpoll via task_work") Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/0a21bd6d794bb1629bc906dd57a57b2c2985a8ac.1616839147.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- fs/io_uring.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/io_uring.c b/fs/io_uring.c index 1949b80..a4a944d 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -9002,6 +9002,8 @@ void __io_uring_task_cancel(void) /* make sure overflow events are dropped */ atomic_inc(&tctx->in_idle); + __io_uring_files_cancel(NULL); + do { /* read completions before cancelations */ inflight = tctx_inflight(tctx); -- 2.7.4