This is a note to let you know that I've just added the patch titled
io_uring: fix io_queue_proc modifying req->flags
to the 6.8-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
io_uring-fix-io_queue_proc-modifying-req-flags.patch
and it can be found in the queue-6.8 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
commit 78b414c246782d766fadacdf435fcc53d8a6019b
Author: Pavel Begunkov <asml.silence@xxxxxxxxx>
Date: Thu Mar 7 18:06:32 2024 +0000
io_uring: fix io_queue_proc modifying req->flags
[ Upstream commit 1a8ec63b2b6c91caec87d4e132b1f71b5df342be ]
With multiple poll entries __io_queue_proc() might be running in
parallel with poll handlers and possibly task_work, we should not be
carelessly modifying req->flags there. io_poll_double_prepare() handles
a similar case with locking but it's much easier to move it into
__io_arm_poll_handler().
Cc: stable@xxxxxxxxxxxxxxx
Fixes: 595e52284d24a ("io_uring/poll: don't enable lazy wake for POLLEXCLUSIVE")
Signed-off-by: Pavel Begunkov <asml.silence@xxxxxxxxx>
Link: https://lore.kernel.org/r/455cc49e38cf32026fa1b49670be8c162c2cb583.1709834755.git.asml.silence@xxxxxxxxx
Signed-off-by: Jens Axboe <axboe@xxxxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
diff --git a/io_uring/poll.c b/io_uring/poll.c
index 58b7556f621eb..c6f4789623cb2 100644
--- a/io_uring/poll.c
+++ b/io_uring/poll.c
@@ -539,14 +539,6 @@ static void __io_queue_proc(struct io_poll *poll, struct io_poll_table *pt,
poll->wait.private = (void *) wqe_private;
if (poll->events & EPOLLEXCLUSIVE) {
- /*
- * Exclusive waits may only wake a limited amount of entries
- * rather than all of them, this may interfere with lazy
- * wake if someone does wait(events > 1). Ensure we don't do
- * lazy wake for those, as we need to process each one as they
- * come in.
- */
- req->flags |= REQ_F_POLL_NO_LAZY;
add_wait_queue_exclusive(head, &poll->wait);
} else {
add_wait_queue(head, &poll->wait);
@@ -618,6 +610,17 @@ static int __io_arm_poll_handler(struct io_kiocb *req,
if (issue_flags & IO_URING_F_UNLOCKED)
req->flags &= ~REQ_F_HASH_LOCKED;
+
+ /*
+ * Exclusive waits may only wake a limited amount of entries
+ * rather than all of them, this may interfere with lazy
+ * wake if someone does wait(events > 1). Ensure we don't do
+ * lazy wake for those, as we need to process each one as they
+ * come in.
+ */
+ if (poll->events & EPOLLEXCLUSIVE)
+ req->flags |= REQ_F_POLL_NO_LAZY;
+
mask = vfs_poll(req->file, &ipt->pt) & poll->events;
if (unlikely(ipt->error || !ipt->nr_entries)) {
