sched: Fix stop_one_cpu_nowait() vs hotplug

Kuyo reported sporadic failures on a sched_setaffinity() vs CPU
hotplug stress-test -- notably affine_move_task() remains stuck in
wait_for_completion(), leading to a hung-task detector warning.

Specifically, it was reported that stop_one_cpu_nowait(.fn =
migration_cpu_stop) returns false -- this stopper is responsible for
the matching complete().

The race scenario is:

	CPU0					CPU1

					// doing _cpu_down()

  __set_cpus_allowed_ptr()
    task_rq_lock();
					takedown_cpu()
					  stop_machine_cpuslocked(take_cpu_down..)

					<PREEMPT: cpu_stopper_thread()
					  MULTI_STOP_PREPARE
					  ...
    __set_cpus_allowed_ptr_locked()
      affine_move_task()
        task_rq_unlock();

  <PREEMPT: cpu_stopper_thread()\>
    ack_state()
					  MULTI_STOP_RUN
					    take_cpu_down()
					      __cpu_disable();
					      stop_machine_park();
						stopper->enabled = false;
					 />
   />
	stop_one_cpu_nowait(.fn = migration_cpu_stop);
          if (stopper->enabled) // false!!!

That is, by doing stop_one_cpu_nowait() after dropping rq-lock, the
stopper thread gets a chance to preempt and allows the cpu-down for
the target CPU to complete.

OTOH, since stop_one_cpu_nowait() / cpu_stop_queue_work() needs to
issue a wakeup, it must not be ran under the scheduler locks.

Solve this apparent contradiction by keeping preemption disabled over
the unlock + queue_stopper combination:

	preempt_disable();
	task_rq_unlock(...);
	if (!stop_pending)
	  stop_one_cpu_nowait(...)
	preempt_enable();

This respects the lock ordering contraints while still avoiding the
above race. That is, if we find the CPU is online under rq-lock, the
targeted stop_one_cpu_nowait() must succeed.

Apply this pattern to all similar stop_one_cpu_nowait() invocations.

Fixes: 6d337eab041d ("sched: Fix migrate_disable() vs set_cpus_allowed_ptr()")
Reported-by: "Kuyo Chang (張建文)" <Kuyo.Chang@mediatek.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: "Kuyo Chang (張建文)" <Kuyo.Chang@mediatek.com>
Link: https://lkml.kernel.org/r/20231010200442.GA16515@noisy.programming.kicks-ass.net

1 files changed, 8 insertions, 2 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index a3f9cd52eec5..264c2eb380d7 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2645,9 +2645,11 @@ 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:
@@ -2967,12 +2969,13 @@ 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);
@@ -3038,12 +3041,13 @@ 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;
@@ -9421,9 +9425,11 @@ 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