ANDROID: sched: Migrate whole chain in proxy_migrate_task()

Instead of migrating one task each time through find_proxy_task(),
we can walk up the blocked_donor ptrs and migrate the entire
current chain in one go.

This was broken out of earlier patches and held back while the
series was being stabilized, but I wanted to re-introduce it.

Cc: Joel Fernandes <joelaf@google.com>
Cc: Qais Yousef <qyousef@layalina.io>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Valentin Schneider <vschneid@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ben Segall <bsegall@google.com>
Cc: Zimuzo Ezeozue <zezeozue@google.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Will Deacon <will@kernel.org>
Cc: Waiman Long <longman@redhat.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: "Paul E. McKenney" <paulmck@kernel.org>
Cc: Metin Kaya <Metin.Kaya@arm.com>
Cc: Xuewen Yan <xuewen.yan94@gmail.com>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Daniel Lezcano <daniel.lezcano@linaro.org>
Cc: kernel-team@android.com
Change-Id: Ia920b2d4161b47b10b5d0774fb1e3283e92bbf0f
Signed-off-by: John Stultz <jstultz@google.com>
Bug: 306081722
---
v12:
* Earlier this was re-using blocked_node, but I hit
  a race with activating blocked entities, and to
  avoid it introduced a new migration_node listhead

include/linux/sched.h

@@ -1213,6 +1213,9 @@ struct task_struct {
 	enum blocked_on_state		blocked_on_state;
 	struct mutex			*blocked_on;	/* lock we're blocked on */
 	struct task_struct		*blocked_donor;	/* task that is boosting this task */
+#ifdef CONFIG_SCHED_PROXY_EXEC
+	struct list_head		migration_node;
+#endif
 	raw_spinlock_t			blocked_lock;
 
 #ifdef CONFIG_DEBUG_ATOMIC_SLEEP

kernel/fork.c

@@ -2366,6 +2366,9 @@ __latent_entropy struct task_struct *copy_process(
 	p->blocked_on_state = BO_RUNNABLE;
 	p->blocked_on = NULL; /* not blocked yet */
 	p->blocked_donor = NULL; /* nobody is boosting p yet */
+#ifdef CONFIG_SCHED_PROXY_EXEC
+	INIT_LIST_HEAD(&p->migration_node);
+#endif
 #ifdef CONFIG_BCACHE
 	p->sequential_io	= 0;
 	p->sequential_io_avg	= 0;

kernel/sched/core.c

@@ -6851,6 +6851,7 @@ static bool proxy_deactivate(struct rq *rq, struct task_struct *donor)
 static void proxy_migrate_task(struct rq *rq, struct rq_flags *rf,
 			       struct task_struct *p, int target_cpu)
 {
+	LIST_HEAD(migrate_list);
 	struct rq *target_rq;
 
 	lockdep_assert_rq_held(rq);
@@ -6880,19 +6881,27 @@ static void proxy_migrate_task(struct rq *rq, struct rq_flags *rf,
 	rq_set_donor(rq, rq->curr);
 	set_next_task(rq, rq->curr);
 
-	WARN_ON(p == rq->curr);
-
-	deactivate_task(rq, p, 0);
-	proxy_set_task_cpu(p, target_cpu);
-
+	for (; p; p = p->blocked_donor) {
+		WARN_ON(p == rq->curr);
+		deactivate_task(rq, p, 0);
+		proxy_set_task_cpu(p, target_cpu);
+		/*
+		 * We can abuse blocked_node to migrate the thing,
+		 * because @p was still on the rq.
+		 */
+		list_add(&p->migration_node, &migrate_list);
+	}
 	zap_balance_callbacks(rq);
 	rq_unpin_lock(rq, rf);
 	raw_spin_rq_unlock(rq);
 	raw_spin_rq_lock(target_rq);
+	while (!list_empty(&migrate_list)) {
+		p = list_first_entry(&migrate_list, struct task_struct, migration_node);
+		list_del_init(&p->migration_node);
 
-	activate_task(target_rq, p, 0);
-	wakeup_preempt(target_rq, p, 0);
-
+		activate_task(target_rq, p, 0);
+		wakeup_preempt(target_rq, p, 0);
+	}
 	raw_spin_rq_unlock(target_rq);
 	raw_spin_rq_lock(rq);
 	rq_repin_lock(rq, rf);