workqueue: Tag bound workers with KTHREAD_IS_PER_CPU

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>
Reviewed-by: Valentin Schneider <valentin.schneider@arm.com>
Tested-by: Valentin Schneider <valentin.schneider@arm.com>
Link: https://lkml.kernel.org/r/20210121103506.693465814@infradead.org

Author: Peter Zijlstra

kernel/workqueue.c

@@ -1861,6 +1861,8 @@ static void worker_attach_to_pool(struct worker *worker,
 	 */
 	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(struct worker *worker)
 
 	mutex_lock(&wq_pool_attach_mutex);
 
+	kthread_set_per_cpu(worker->task, -1);
 	list_del(&worker->node);
 	worker->pool = NULL;
 
@@ -4919,8 +4922,10 @@ 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 +4977,11 @@ static void rebind_workers(struct worker_pool *pool)
 	 * 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)
+	for_each_pool_worker(worker, pool) {
+		kthread_set_per_cpu(worker->task, pool->cpu);
 		WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task,
 						  pool->attrs->cpumask) < 0);
+	}
 
 	raw_spin_lock_irq(&pool->lock);