[PATCH 1/2] io_uring : correct timeout req sequence when waiting timeout

From: "zhangyi (F)" <yi.zhang@huawei.com>
To: <axboe@kernel.dk>, <linux-block@vger.kernel.org>
Cc: <yi.zhang@huawei.com>, <yangerkun@huawei.com>
Subject: [PATCH 1/2] io_uring : correct timeout req sequence when waiting timeout
Date: Wed, 23 Oct 2019 15:10:08 +0800	[thread overview]
Message-ID: <20191023071009.13891-1-yi.zhang@huawei.com> (raw)

The sequence number of reqs on the timeout_list before the timeout req
should be adjusted in io_timeout_fn(), because the current timeout req
will consumes a slot in the cq_ring and cq_tail pointer will be
increased, otherwise other timeout reqs may return in advance without
waiting for enough wait_nr.

Signed-off-by: zhangyi (F) <yi.zhang@huawei.com>
---
 fs/io_uring.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 67dbe0201e0d..e7a856392a23 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1877,7 +1877,7 @@ static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 static enum hrtimer_restart io_timeout_fn(struct hrtimer *timer)
 {
 	struct io_ring_ctx *ctx;
-	struct io_kiocb *req;
+	struct io_kiocb *req, *prev;
 	unsigned long flags;
 
 	req = container_of(timer, struct io_kiocb, timeout.timer);
@@ -1885,6 +1885,15 @@ static enum hrtimer_restart io_timeout_fn(struct hrtimer *timer)
 	atomic_inc(&ctx->cq_timeouts);
 
 	spin_lock_irqsave(&ctx->completion_lock, flags);
+	/*
+	 * Adjust the reqs sequence before the current one because it
+	 * will consume a slot in the cq_ring and the the cq_tail pointer
+	 * will be increased, otherwise other timeout reqs may return in
+	 * advance without waiting for enough wait_nr.
+	 */
+	prev = req;
+	list_for_each_entry_continue_reverse(prev, &ctx->timeout_list, list)
+		prev->sequence++;
 	list_del(&req->list);
 
 	io_cqring_fill_event(ctx, req->user_data, -ETIME);
-- 
2.17.2

