[PATCH 5/8] workqueue: Tag bound workers with KTHREAD_IS_PER_CPU

From: Peter Zijlstra <peterz@infradead.org>
To: mingo@kernel.org, tglx@linutronix.de
Cc: linux-kernel@vger.kernel.org, jiangshanlai@gmail.com,
	valentin.schneider@arm.com, cai@redhat.com,
	vincent.donnefort@arm.com, decui@microsoft.com,
	paulmck@kernel.org, vincent.guittot@linaro.org,
	rostedt@goodmis.org, tj@kernel.org, peterz@infradead.org
Subject: [PATCH 5/8] workqueue: Tag bound workers with KTHREAD_IS_PER_CPU
Date: Sat, 16 Jan 2021 12:30:38 +0100	[thread overview]
Message-ID: <20210116113919.933156564@infradead.org> (raw)
In-Reply-To: 20210116113033.608340773@infradead.org

Mark the per-cpu workqueue workers as KTHREAD_IS_PER_CPU.

Workqueues have unfortunate semantics in that per-cpu workers are not
default flushed and parked during hotplug, however a subset does
manual flush on hotplug and hard relies on them for correctness.

Therefore play silly games..

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 kernel/workqueue.c |   25 ++++++++++++++++++-------
 1 file changed, 18 insertions(+), 7 deletions(-)

--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1861,6 +1861,8 @@ static void worker_attach_to_pool(struct
 	 */
 	if (pool->flags & POOL_DISASSOCIATED)
 		worker->flags |= WORKER_UNBOUND;
+	else
+		kthread_set_per_cpu(worker->task, pool->cpu);
 
 	list_add_tail(&worker->node, &pool->workers);
 	worker->pool = pool;
@@ -1883,6 +1885,7 @@ static void worker_detach_from_pool(stru
 
 	mutex_lock(&wq_pool_attach_mutex);
 
+	kthread_set_per_cpu(worker->task, -1);
 	list_del(&worker->node);
 	worker->pool = NULL;
 
@@ -2368,6 +2371,7 @@ static int worker_thread(void *__worker)
 	/* tell the scheduler that this is a workqueue worker */
 	set_pf_worker(true);
 woke_up:
+	kthread_parkme();
 	raw_spin_lock_irq(&pool->lock);
 
 	/* am I supposed to die? */
@@ -2425,7 +2429,7 @@ static int worker_thread(void *__worker)
 			move_linked_works(work, &worker->scheduled, NULL);
 			process_scheduled_works(worker);
 		}
-	} while (keep_working(pool));
+	} while (keep_working(pool) && !kthread_should_park());
 
 	worker_set_flags(worker, WORKER_PREP);
 sleep:
@@ -2437,9 +2441,12 @@ static int worker_thread(void *__worker)
 	 * event.
 	 */
 	worker_enter_idle(worker);
-	__set_current_state(TASK_IDLE);
+	set_current_state(TASK_IDLE);
 	raw_spin_unlock_irq(&pool->lock);
-	schedule();
+
+	if (!kthread_should_park())
+		schedule();
+
 	goto woke_up;
 }
 
@@ -4919,8 +4926,10 @@ static void unbind_workers(int cpu)
 
 		raw_spin_unlock_irq(&pool->lock);
 
-		for_each_pool_worker(worker, pool)
+		for_each_pool_worker(worker, pool) {
+			kthread_set_per_cpu(worker->task, -1);
 			WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, cpu_possible_mask) < 0);
+		}
 
 		mutex_unlock(&wq_pool_attach_mutex);
 
@@ -4972,9 +4981,11 @@ static void rebind_workers(struct worker
 	 * of all workers first and then clear UNBOUND.  As we're called
 	 * from CPU_ONLINE, the following shouldn't fail.
 	 */
-	for_each_pool_worker(worker, pool)
-		WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task,
-						  pool->attrs->cpumask) < 0);
+	for_each_pool_worker(worker, pool) {
+		WARN_ON_ONCE(kthread_park(worker->task) < 0);
+		kthread_set_per_cpu(worker->task, pool->cpu);
+		kthread_unpark(worker->task);
+	}
 
 	raw_spin_lock_irq(&pool->lock);
 


