From 7e603b207928fa403d4e271695bbeb1509bc3fd8 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Fri, 2 Dec 2022 14:27:11 +0000 Subject: [PATCH] UPSTREAM: io_uring: update res mask in io_poll_check_events [ upstream commit b98186aee22fa593bc8c6b2c5d839c2ee518bc8c ] When io_poll_check_events() collides with someone attempting to queue a task work, it'll spin for one more time. However, it'll continue to use the mask from the first iteration instead of updating it. For example, if the first wake up was a EPOLLIN and the second EPOLLOUT, the userspace will not get EPOLLOUT in time. Clear the mask for all subsequent iterations to force vfs_poll(). Cc: stable@vger.kernel.org Fixes: aa43477b04025 ("io_uring: poll rework") Change-Id: I3e846a7e14626c9d19a8b1cd4f0997d002b83fb0 Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/2dac97e8f691231049cb259c4ae57e79e40b537c.1668710222.git.asml.silence@gmail.com Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 62321dc7b08103259b19a82089fc49f66f1e4ce6) Bug: 268174392 Signed-off-by: Greg Kroah-Hartman --- fs/io_uring.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/io_uring.c b/fs/io_uring.c index b8ae64df90e3..2ba42e6e0881 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -5464,6 +5464,9 @@ static int io_poll_check_events(struct io_kiocb *req) return 0; } + /* force the next iteration to vfs_poll() */ + req->result = 0; + /* * Release all references, retry if someone tried to restart * task_work while we were executing it.