workqueue: defer the worker wakeup outside pool->lock in __queue_work()

__queue_work() is the enqueue hot path: it inserts the work item and
calls kick_pool() while holding pool->lock. kick_pool() ends in a
wakeup, which takes the target task's rq->lock, so rq->lock nests under
pool->lock on every enqueue that wakes a worker on a contended unbound
pool.

Use kick_pool_pick() to select and claim the worker under pool->lock and
issue the wakeup with wake_up_process() right after dropping the lock.

Signed-off-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Tejun Heo <tj@kernel.org>

1 files changed, 4 insertions, 1 deletions

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 49770093e785..2d41000c918f 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -2302,6 +2302,7 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
 {
 	struct pool_workqueue *pwq;
 	struct worker_pool *last_pool, *pool;
+	struct task_struct *wake_task = NULL;
 	unsigned int work_flags;
 	unsigned int req_cpu = cpu;
 
@@ -2424,7 +2425,7 @@ retry:
 
 		trace_workqueue_activate_work(work);
 		insert_work(pwq, work, &pool->worklist, work_flags);
-		kick_pool(pool);
+		kick_pool_pick(pool, &wake_task);
 	} else {
 		work_flags |= WORK_STRUCT_INACTIVE;
 		insert_work(pwq, work, &pwq->inactive_works, work_flags);
@@ -2432,6 +2433,8 @@ retry:
 
 out:
 	raw_spin_unlock(&pool->lock);
+	if (wake_task)
+		wake_up_process(wake_task);
 	rcu_read_unlock();
 }