[PATCH v2 3/4] workqueue: defer the worker wakeup outside pool->lock in __queue_work()

[Breno Leitao]

__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,
queue it on an on-stack wake_q, and issue the wakeup with wake_up_q()
right after dropping the lock via raw_spin_unlock_wake().  Worker
selection, wake_cpu setup and claiming the worker off pool->idle_list
still happen under the lock; only the rq->lock acquisition moves out.

Signed-off-by: Breno Leitao <leitao@xxxxxxxxxx>
---
 kernel/workqueue.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 2811ada6dec6..b4246a801dd8 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -2317,6 +2317,7 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
 {
 	struct pool_workqueue *pwq;
 	struct worker_pool *last_pool, *pool;
+	DEFINE_WAKE_Q(wakeq);
 	unsigned int work_flags;
 	unsigned int req_cpu = cpu;
 
@@ -2431,14 +2432,15 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
 
 		trace_workqueue_activate_work(work);
 		insert_work(pwq, work, &pool->worklist, work_flags);
-		kick_pool(pool);
+		kick_pool_pick(pool, &wakeq);
 	} else {
 		work_flags |= WORK_STRUCT_INACTIVE;
 		insert_work(pwq, work, &pwq->inactive_works, work_flags);
 	}
 
 out:
-	raw_spin_unlock(&pool->lock);
+	/* deferred kick_pool_pick() wakeup, issued outside pool->lock */
+	raw_spin_unlock_wake(&pool->lock, &wakeq);
 	rcu_read_unlock();
 }
 

-- 
2.54.0