stop_machine: Fix stop_cpus_in_progress ordering

Make sure the entire for loop has stop_cpus_in_progress set.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Aaron Lu <aaron.lwe@gmail.com>
Cc: Valentin Schneider <valentin.schneider@arm.com>
Cc: mingo@kernel.org
Cc: Phil Auld <pauld@redhat.com>
Cc: Julien Desfossez <jdesfossez@digitalocean.com>
Cc: Nishanth Aravamudan <naravamudan@digitalocean.com>
Link: https://lkml.kernel.org/r/0fd8fd4b99b9b9aa88d8b2dff897f7fd0d88f72c.1559129225.git.vpillai@digitalocean.com

kernel/stop_machine.c

@@ -383,6 +383,7 @@ static bool queue_stop_cpus_work(const struct cpumask *cpumask,
 	 */
 	preempt_disable();
 	stop_cpus_in_progress = true;
+	barrier();
 	for_each_cpu(cpu, cpumask) {
 		work = &per_cpu(cpu_stopper.stop_work, cpu);
 		work->fn = fn;
@@ -391,6 +392,7 @@ static bool queue_stop_cpus_work(const struct cpumask *cpumask,
 		if (cpu_stop_queue_work(cpu, work))
 			queued = true;
 	}
+	barrier();
 	stop_cpus_in_progress = false;
 	preempt_enable();