Merge tag 'sched_urgent_for_v5.11_rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler fixes from Borislav Petkov:

 - Correct the marking of kthreads which are supposed to run on a
   specific, single CPU vs such which are affine to only one CPU, mark
   per-cpu workqueue threads as such and make sure that marking
   "survives" CPU hotplug. Fix CPU hotplug issues with such kthreads.

 - A fix to not push away tasks on CPUs coming online.

 - Have workqueue CPU hotplug code use cpu_possible_mask when breaking
   affinity on CPU offlining so that pending workers can finish on newly
   arrived onlined CPUs too.

 - Dump tasks which haven't vacated a CPU which is currently being
   unplugged.

 - Register a special scale invariance callback which gets called on
   resume from RAM to read out APERF/MPERF after resume and thus make
   the schedutil scaling governor more precise.

* tag 'sched_urgent_for_v5.11_rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched: Relax the set_cpus_allowed_ptr() semantics
  sched: Fix CPU hotplug / tighten is_per_cpu_kthread()
  sched: Prepare to use balance_push in ttwu()
  workqueue: Restrict affinity change to rescuer
  workqueue: Tag bound workers with KTHREAD_IS_PER_CPU
  kthread: Extract KTHREAD_IS_PER_CPU
  sched: Don't run cpu-online with balance_push() enabled
  workqueue: Use cpu_possible_mask instead of cpu_active_mask to break affinity
  sched/core: Print out straggler tasks in sched_cpu_dying()
  x86: PM: Register syscore_ops for scale invariance

1 files changed, 13 insertions, 9 deletions

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 9880b6c0e272..894bb885b40b 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1849,18 +1849,17 @@ static void worker_attach_to_pool(struct worker *worker,
 	mutex_lock(&wq_pool_attach_mutex);
 
 	/*
-	 * set_cpus_allowed_ptr() will fail if the cpumask doesn't have any
-	 * online CPUs.  It'll be re-applied when any of the CPUs come up.
-	 */
-	set_cpus_allowed_ptr(worker->task, pool->attrs->cpumask);
-
-	/*
 	 * The wq_pool_attach_mutex ensures %POOL_DISASSOCIATED remains
 	 * stable across this function.  See the comments above the flag
 	 * definition for details.
 	 */
 	if (pool->flags & POOL_DISASSOCIATED)
 		worker->flags |= WORKER_UNBOUND;
+	else
+		kthread_set_per_cpu(worker->task, pool->cpu);
+
+	if (worker->rescue_wq)
+		set_cpus_allowed_ptr(worker->task, pool->attrs->cpumask);
 
 	list_add_tail(&worker->node, &pool->workers);
 	worker->pool = pool;
@@ -1883,6 +1882,7 @@ 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 +4919,10 @@ static void unbind_workers(int cpu)
 
 		raw_spin_unlock_irq(&pool->lock);
 
-		for_each_pool_worker(worker, pool)
-			WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, cpu_active_mask) < 0);
+		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 +4974,11 @@ 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);