[PATCH 1/2] sched: migrate_enable: Use per-cpu cpu_stop_work

[PATCH 1/2] sched: migrate_enable: Use per-cpu cpu_stop_work

[Scott Wood]

Commit e6c287b1512d ("sched: migrate_enable: Use stop_one_cpu_nowait()")
adds a busy wait to deal with an edge case where the migrated thread
can resume running on another CPU before the stopper has consumed
cpu_stop_work.  However, this is done with preemption disabled and can
potentially lead to deadlock.

While it is not guaranteed that the cpu_stop_work will be consumed before
the migrating thread resumes and exits the stack frame, it is guaranteed
that nothing other than the stopper can run on the old cpu between the
migrating thread scheduling out and the cpu_stop_work being consumed.
Thus, we can store cpu_stop_work in per-cpu data without it being
reused too early.

Fixes: e6c287b1512d ("sched: migrate_enable: Use stop_one_cpu_nowait()")
Suggested-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Scott Wood <swood@redhat.com>
---
 kernel/sched/core.c | 22 ++++++++++++++--------
 1 file changed, 14 insertions(+), 8 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 754f6afb438d..7713e9c34ad1 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -8189,6 +8189,9 @@ static void migrate_disabled_sched(struct task_struct *p)
 	p->migrate_disable_scheduled = 1;
 }
 
+static DEFINE_PER_CPU(struct cpu_stop_work, migrate_work);
+static DEFINE_PER_CPU(struct migration_arg, migrate_arg);
+
 void migrate_enable(void)
 {
 	struct task_struct *p = current;
@@ -8227,22 +8230,25 @@ void migrate_enable(void)
 
 	WARN_ON(smp_processor_id() != cpu);
 	if (!is_cpu_allowed(p, cpu)) {
-		struct migration_arg arg = { .task = p };
-		struct cpu_stop_work work;
+		struct migration_arg __percpu *arg;
+		struct cpu_stop_work __percpu *work;
 		struct rq_flags rf;
 
+		work = this_cpu_ptr(&migrate_work);
+		arg = this_cpu_ptr(&migrate_arg);
+		WARN_ON_ONCE(!arg->done && !work->disabled && work->arg);
+
+		arg->task = p;
+		arg->done = false;
+
 		rq = task_rq_lock(p, &rf);
 		update_rq_clock(rq);
-		arg.dest_cpu = select_fallback_rq(cpu, p);
+		arg->dest_cpu = select_fallback_rq(cpu, p);
 		task_rq_unlock(rq, p, &rf);
 
 		stop_one_cpu_nowait(task_cpu(p), migration_cpu_stop,
-				    &arg, &work);
+				    arg, work);
 		__schedule(true);
-		if (!work.disabled) {
-			while (!arg.done)
-				cpu_relax();
-		}
 	}
 
 out:
-- 
1.8.3.1