backport "io_uring: fix race between timeout flush and removal"

[pve-kernel.git] / patches / kernel / 0014-io_uring-fix-race-between-timeout-flush-and-removal.patch

From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Fri, 8 Apr 2022 11:08:58 -0600
Subject: [PATCH] io_uring: fix race between timeout flush and removal

commit e677edbcabee849bfdd43f1602bccbecf736a646 upstream.

io_flush_timeouts() assumes the timeout isn't in progress of triggering
or being removed/canceled, so it unconditionally removes it from the
timeout list and attempts to cancel it.

Leave it on the list and let the normal timeout cancelation take care
of it.

Cc: stable@vger.kernel.org # 5.5+
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
---
 fs/io_uring.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 156c54ebb62b..367b7ba2fcb0 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1546,12 +1546,11 @@ static void io_flush_timeouts(struct io_ring_ctx *ctx)
 	__must_hold(&ctx->completion_lock)
 {
 	u32 seq = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts);
+	struct io_kiocb *req, *tmp;
 
 	spin_lock_irq(&ctx->timeout_lock);
-	while (!list_empty(&ctx->timeout_list)) {
+	list_for_each_entry_safe(req, tmp, &ctx->timeout_list, timeout.list) {
 		u32 events_needed, events_got;
-		struct io_kiocb *req = list_first_entry(&ctx->timeout_list,
-						struct io_kiocb, timeout.list);
 
 		if (io_is_timeout_noseq(req))
 			break;
@@ -1568,7 +1567,6 @@ static void io_flush_timeouts(struct io_ring_ctx *ctx)
 		if (events_got < events_needed)
 			break;
 
-		list_del_init(&req->timeout.list);
 		io_kill_timeout(req, 0);
 	}
 	ctx->cq_last_tm_flush = seq;
@@ -6209,6 +6207,7 @@ static int io_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 	if (get_timespec64(&data->ts, u64_to_user_ptr(sqe->addr)))
 		return -EFAULT;
 
+	INIT_LIST_HEAD(&req->timeout.list);
 	data->mode = io_translate_timeout_mode(flags);
 	hrtimer_init(&data->timer, io_timeout_get_clock(data), data->mode);