drivers/block/loop.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
From: Zhaoyang Huang <zhaoyang.huang@unisoc.com>
queue_work could spin on wq->cpu_pwq->pool->lock which could lead to
concurrent loop_process_work failed on lo_work_lock contention and
increase the request latency. Remove this combination by moving the
lock release ahead of queue_work.
Signed-off-by: Zhaoyang Huang <zhaoyang.huang@unisoc.com>
---
drivers/block/loop.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 8f6761c27c68..33e31cd95953 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -890,8 +890,8 @@ static void loop_queue_work(struct loop_device *lo, struct loop_cmd *cmd)
cmd_list = &lo->rootcg_cmd_list;
}
list_add_tail(&cmd->list_entry, cmd_list);
- queue_work(lo->workqueue, work);
spin_unlock_irq(&lo->lo_work_lock);
+ queue_work(lo->workqueue, work);
}
static void loop_set_timer(struct loop_device *lo)
--
2.25.1
On Fri, Feb 7, 2025 at 5:20 PM zhaoyang.huang <zhaoyang.huang@unisoc.com> wrote: > > From: Zhaoyang Huang <zhaoyang.huang@unisoc.com> > > queue_work could spin on wq->cpu_pwq->pool->lock which could lead to > concurrent loop_process_work failed on lo_work_lock contention and > increase the request latency. Remove this combination by moving the > lock release ahead of queue_work. > > Signed-off-by: Zhaoyang Huang <zhaoyang.huang@unisoc.com> > --- > drivers/block/loop.c | 2 +- > 1 file changed, 1 insertion(+), 1 deletion(-) > > diff --git a/drivers/block/loop.c b/drivers/block/loop.c > index 8f6761c27c68..33e31cd95953 100644 > --- a/drivers/block/loop.c > +++ b/drivers/block/loop.c > @@ -890,8 +890,8 @@ static void loop_queue_work(struct loop_device *lo, struct loop_cmd *cmd) > cmd_list = &lo->rootcg_cmd_list; > } > list_add_tail(&cmd->list_entry, cmd_list); > - queue_work(lo->workqueue, work); > spin_unlock_irq(&lo->lo_work_lock); > + queue_work(lo->workqueue, work); > } Reviewed-by: Ming Lei <ming.lei@redhat.com>
On Fri, 07 Feb 2025 17:19:42 +0800, zhaoyang.huang wrote:
> queue_work could spin on wq->cpu_pwq->pool->lock which could lead to
> concurrent loop_process_work failed on lo_work_lock contention and
> increase the request latency. Remove this combination by moving the
> lock release ahead of queue_work.
>
>
Applied, thanks!
[1/1] driver: block: release the lo_work_lock before queue_work
commit: 3bee991f2b68175c828dc3f9c26367fe1827319a
Best regards,
--
Jens Axboe
© 2016 - 2026 Red Hat, Inc.