[PATCH RT 2/8] sched: Simplify migration_cpu_stop()

[Steven Rostedt]

5.10.47-rt46-rc1 stable review patch.
If anyone has any objections, please let me know.

------------------

From: Peter Zijlstra <peterz@xxxxxxxxxxxxx>

commit c20cf065d4a619d394d23290093b1002e27dff86 upstream.

When affine_move_task() issues a migration_cpu_stop(), the purpose of
that function is to complete that @pending, not any random other
p->migration_pending that might have gotten installed since.

This realization much simplifies migration_cpu_stop() and allows
further necessary steps to fix all this as it provides the guarantee
that @pending's stopper will complete @pending (and not some random
other @pending).

Fixes: 6d337eab041d ("sched: Fix migrate_disable() vs set_cpus_allowed_ptr()")
Cc: stable@xxxxxxxxxx
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
Reviewed-by: Valentin Schneider <valentin.schneider@xxxxxxx>
Link: https://lkml.kernel.org/r/20210224131355.430014682@xxxxxxxxxxxxx
Signed-off-by: Paul Gortmaker <paul.gortmaker@xxxxxxxxxxxxx>
Signed-off-by: Steven Rostedt (VMware) <rostedt@xxxxxxxxxxx>
---
 kernel/sched/core.c | 56 +++++++--------------------------------------
 1 file changed, 8 insertions(+), 48 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index a3dea38f410a..d497b13efb53 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1934,8 +1934,8 @@ static struct rq *__migrate_task(struct rq *rq, struct rq_flags *rf,
  */
 static int migration_cpu_stop(void *data)
 {
-	struct set_affinity_pending *pending;
 	struct migration_arg *arg = data;
+	struct set_affinity_pending *pending = arg->pending;
 	struct task_struct *p = arg->task;
 	int dest_cpu = arg->dest_cpu;
 	struct rq *rq = this_rq();
@@ -1957,25 +1957,6 @@ static int migration_cpu_stop(void *data)
 	raw_spin_lock(&p->pi_lock);
 	rq_lock(rq, &rf);
 
-	pending = p->migration_pending;
-	if (pending && !arg->pending) {
-		/*
-		 * This happens from sched_exec() and migrate_task_to(),
-		 * neither of them care about pending and just want a task to
-		 * maybe move about.
-		 *
-		 * Even if there is a pending, we can ignore it, since
-		 * affine_move_task() will have it's own stop_work's in flight
-		 * which will manage the completion.
-		 *
-		 * Notably, pending doesn't need to match arg->pending. This can
-		 * happen when tripple concurrent affine_move_task() first sets
-		 * pending, then clears pending and eventually sets another
-		 * pending.
-		 */
-		pending = NULL;
-	}
-
 	/*
 	 * If task_rq(p) != rq, it cannot be migrated here, because we're
 	 * holding rq->lock, if p->on_rq == 0 it cannot get enqueued because
@@ -1986,31 +1967,20 @@ static int migration_cpu_stop(void *data)
 			goto out;
 
 		if (pending) {
-			p->migration_pending = NULL;
+			if (p->migration_pending == pending)
+				p->migration_pending = NULL;
 			complete = true;
 		}
 
-		/* migrate_enable() --  we must not race against SCA */
-		if (dest_cpu < 0) {
-			/*
-			 * When this was migrate_enable() but we no longer
-			 * have a @pending, a concurrent SCA 'fixed' things
-			 * and we should be valid again. Nothing to do.
-			 */
-			if (!pending) {
-				WARN_ON_ONCE(!cpumask_test_cpu(task_cpu(p), &p->cpus_mask));
-				goto out;
-			}
-
+		if (dest_cpu < 0)
 			dest_cpu = cpumask_any_distribute(&p->cpus_mask);
-		}
 
 		if (task_on_rq_queued(p))
 			rq = __migrate_task(rq, &rf, p, dest_cpu);
 		else
 			p->wake_cpu = dest_cpu;
 
-	} else if (dest_cpu < 0 || pending) {
+	} else if (pending) {
 		/*
 		 * This happens when we get migrated between migrate_enable()'s
 		 * preempt_enable() and scheduling the stopper task. At that
@@ -2025,22 +1995,13 @@ static int migration_cpu_stop(void *data)
 		 * ->pi_lock, so the allowed mask is stable - if it got
 		 * somewhere allowed, we're done.
 		 */
-		if (pending && cpumask_test_cpu(task_cpu(p), p->cpus_ptr)) {
-			p->migration_pending = NULL;
+		if (cpumask_test_cpu(task_cpu(p), p->cpus_ptr)) {
+			if (p->migration_pending == pending)
+				p->migration_pending = NULL;
 			complete = true;
 			goto out;
 		}
 
-		/*
-		 * When this was migrate_enable() but we no longer have an
-		 * @pending, a concurrent SCA 'fixed' things and we should be
-		 * valid again. Nothing to do.
-		 */
-		if (!pending) {
-			WARN_ON_ONCE(!cpumask_test_cpu(task_cpu(p), &p->cpus_mask));
-			goto out;
-		}
-
 		/*
 		 * When migrate_enable() hits a rq mis-match we can't reliably
 		 * determine is_migration_disabled() and so have to chase after
@@ -2058,7 +2019,6 @@ static int migration_cpu_stop(void *data)
 		complete_all(&pending->done);
 
 	/* For pending->{arg,stop_work} */
-	pending = arg->pending;
 	if (pending && refcount_dec_and_test(&pending->refs))
 		wake_up_var(&pending->refs);
 
-- 
2.30.2