[PATCH 08/10 V4] workqueue: explicit way to wait for idles workers to finish

[Lai Jiangshan]

busy_worker_rebind_fn() can't return until all idle workers are rebound.
This order is ensured by rebind_workers() currently.

We use synchronize_all_idles_rebound() to wait for all idle workers
to be rebound. this is an explicit way and it will ease the pain of
the rebind_workers().

The sleeping synchronize_all_idles_rebound() must be called before
the WORKER_REBIND has been cleared.

It adds a small overhead to the unlikely path.

Signed-off-by: Lai Jiangshan <laijs@xxxxxxxxxxxxxx>
---
 kernel/workqueue.c |   16 +++++++++++++++-
 1 files changed, 15 insertions(+), 1 deletions(-)

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index c875951..16bcd84 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1387,9 +1387,23 @@ static void busy_worker_rebind_fn(struct work_struct *work)
 {
 	struct worker *worker = container_of(work, struct worker, rebind_work);
 	struct global_cwq *gcwq = worker->pool->gcwq;
+	struct idle_rebind *idle_rebind;
+
+	if (worker_maybe_bind_and_lock(worker)) {
+		/* Is idle-rebinding still in progress? */
+		if ((idle_rebind = gcwq->idle_rebind) != NULL) {
+			/* get reference */
+			BUG_ON(idle_rebind->ref_cnt <= 0);
+			idle_rebind->ref_cnt++;
+			spin_unlock_irq(&gcwq->lock);
+
+			synchronize_all_idles_rebound(gcwq, idle_rebind);
+
+			spin_lock_irq(&gcwq->lock);
+		}
 
-	if (worker_maybe_bind_and_lock(worker))
 		worker_clr_flags(worker, WORKER_REBIND);
+	}
 
 	spin_unlock_irq(&gcwq->lock);
 }
-- 
1.7.4.4

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/