[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20230531134020.3383253-36-sashal@kernel.org>
Date: Wed, 31 May 2023 09:40:18 -0400
From: Sasha Levin <sashal@...nel.org>
To: linux-kernel@...r.kernel.org, stable@...r.kernel.org
Cc: Wenwen Chen <wenwen.chen@...sung.com>,
Kanchan Joshi <joshi.k@...sung.com>,
Jens Axboe <axboe@...nel.dk>, Sasha Levin <sashal@...nel.org>,
io-uring@...r.kernel.org
Subject: [PATCH AUTOSEL 6.3 36/37] io_uring: unlock sqd->lock before sq thread release CPU
From: Wenwen Chen <wenwen.chen@...sung.com>
[ Upstream commit 533ab73f5b5c95dcb4152b52d5482abcc824c690 ]
The sq thread actively releases CPU resources by calling the
cond_resched() and schedule() interfaces when it is idle. Therefore,
more resources are available for other threads to run.
There exists a problem in sq thread: it does not unlock sqd->lock before
releasing CPU resources every time. This makes other threads pending on
sqd->lock for a long time. For example, the following interfaces all
require sqd->lock: io_sq_offload_create(), io_register_iowq_max_workers()
and io_ring_exit_work().
Before the sq thread releases CPU resources, unlocking sqd->lock will
provide the user a better experience because it can respond quickly to
user requests.
Signed-off-by: Kanchan Joshi<joshi.k@...sung.com>
Signed-off-by: Wenwen Chen<wenwen.chen@...sung.com>
Link: https://lore.kernel.org/r/20230525082626.577862-1-wenwen.chen@samsung.com
Signed-off-by: Jens Axboe <axboe@...nel.dk>
Signed-off-by: Sasha Levin <sashal@...nel.org>
---
io_uring/sqpoll.c | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/io_uring/sqpoll.c b/io_uring/sqpoll.c
index 9db4bc1f521a3..5e329e3cd4706 100644
--- a/io_uring/sqpoll.c
+++ b/io_uring/sqpoll.c
@@ -255,9 +255,13 @@ static int io_sq_thread(void *data)
sqt_spin = true;
if (sqt_spin || !time_after(jiffies, timeout)) {
- cond_resched();
if (sqt_spin)
timeout = jiffies + sqd->sq_thread_idle;
+ if (unlikely(need_resched())) {
+ mutex_unlock(&sqd->lock);
+ cond_resched();
+ mutex_lock(&sqd->lock);
+ }
continue;
}
--
2.39.2
Powered by blists - more mailing lists