Merge: sched: Fix stop_one_cpu_nowait() vs hotplug [rhel-9]

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-9/-/merge_requests/6623

JIRA: https://issues.redhat.com/browse/RHEL-84526

Sporadic failures on a sched_setaffinity() vs CPU hotplug stress-test
have been reported and fixed upstream – Notably affine_move_task()
remains stuck in wait_for_completion(), leading to a hung-task detector
warning.

Both C10S and RHEL-10 already carry the fix from this upstream commit:

    f0498d2 sched: Fix stop_one_cpu_nowait() vs hotplug

Signed-off-by: Luis Claudio R. Goncalves <lgoncalv@redhat.com>

Approved-by: Gabriele Monaco <gmonaco@redhat.com>
Approved-by: Wander Lairson Costa <wander@redhat.com>
Approved-by: Phil Auld <pauld@redhat.com>
Approved-by: CKI KWF Bot <cki-ci-bot+kwf-gitlab-com@redhat.com>

Merged-by: Augusto Caringi <acaringi@redhat.com>

Author: caringi

kernel/sched/core.c

@@ -2531,9 +2531,11 @@ static int migration_cpu_stop(void *data)
 		 * it.
 		 */
 		WARN_ON_ONCE(!pending->stop_pending);
+		preempt_disable();
 		task_rq_unlock(rq, p, &rf);
 		stop_one_cpu_nowait(task_cpu(p), migration_cpu_stop,
 				    &pending->arg, &pending->stop_work);
+		preempt_enable();
 		return 0;
 	}
 out:
@@ -2841,12 +2843,13 @@ static int affine_move_task(struct rq *rq, struct task_struct *p, struct rq_flag
 			complete = true;
 		}
 
+		preempt_disable();
 		task_rq_unlock(rq, p, rf);
-
 		if (push_task) {
 			stop_one_cpu_nowait(rq->cpu, push_cpu_stop,
 					    p, &rq->push_work);
 		}
+		preempt_enable();
 
 		if (complete)
 			complete_all(&pending->done);
@@ -2912,12 +2915,13 @@ static int affine_move_task(struct rq *rq, struct task_struct *p, struct rq_flag
 		if (flags & SCA_MIGRATE_ENABLE)
 			p->migration_flags &= ~MDF_PUSH;
 
+		preempt_disable();
 		task_rq_unlock(rq, p, rf);
-
 		if (!stop_pending) {
 			stop_one_cpu_nowait(cpu_of(rq), migration_cpu_stop,
 					    &pending->arg, &pending->stop_work);
 		}
+		preempt_enable();
 
 		if (flags & SCA_MIGRATE_ENABLE)
 			return 0;
@@ -7797,9 +7801,11 @@ static void balance_push(struct rq *rq)
 	 * Temporarily drop rq->lock such that we can wake-up the stop task.
 	 * Both preemption and IRQs are still disabled.
 	 */
+	preempt_disable();
 	raw_spin_rq_unlock(rq);
 	stop_one_cpu_nowait(rq->cpu, __balance_push_cpu_stop, push_task,
 			    this_cpu_ptr(&push_work));
+	preempt_enable();
 	/*
 	 * At this point need_resched() is true and we'll take the loop in
 	 * schedule(). The next pick is obviously going to be the stop task

kernel/sched/deadline.c

@@ -2543,9 +2543,11 @@ static void pull_dl_task(struct rq *this_rq)
 		double_unlock_balance(this_rq, src_rq);
 
 		if (push_task) {
+			preempt_disable();
 			raw_spin_rq_unlock(this_rq);
 			stop_one_cpu_nowait(src_rq->cpu, push_cpu_stop,
 					    push_task, &src_rq->push_work);
+			preempt_enable();
 			raw_spin_rq_lock(this_rq);
 		}
 	}

kernel/sched/fair.c

@@ -11452,13 +11452,15 @@ static int sched_balance_rq(int this_cpu, struct rq *this_rq,
 				busiest->push_cpu = this_cpu;
 				active_balance = 1;
 			}
-			raw_spin_rq_unlock_irqrestore(busiest, flags);
 
+			preempt_disable();
+			raw_spin_rq_unlock_irqrestore(busiest, flags);
 			if (active_balance) {
 				stop_one_cpu_nowait(cpu_of(busiest),
 					active_load_balance_cpu_stop, busiest,
 					&busiest->active_balance_work);
 			}
+			preempt_enable();
 		}
 	} else {
 		sd->nr_balance_failed = 0;

kernel/sched/rt.c

@@ -2045,9 +2045,11 @@ static int push_rt_task(struct rq *rq, bool pull)
 		 */
 		push_task = get_push_task(rq);
 		if (push_task) {
+			preempt_disable();
 			raw_spin_rq_unlock(rq);
 			stop_one_cpu_nowait(rq->cpu, push_cpu_stop,
 					    push_task, &rq->push_work);
+			preempt_enable();
 			raw_spin_rq_lock(rq);
 		}
 
@@ -2383,9 +2385,11 @@ static void pull_rt_task(struct rq *this_rq)
 		double_unlock_balance(this_rq, src_rq);
 
 		if (push_task) {
+			preempt_disable();
 			raw_spin_rq_unlock(this_rq);
 			stop_one_cpu_nowait(src_rq->cpu, push_cpu_stop,
 					    push_task, &src_rq->push_work);
+			preempt_enable();
 			raw_spin_rq_lock(this_rq);
 		}
 	}