[PATCH v23 9/9] sched: Migrate whole chain in proxy_migrate_task()

[John Stultz <jstultz@google.com>]

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.

Signed-off-by: John Stultz <jstultz@google.com>
---
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
v18:
* Add init_task initialization of migration_node as suggested
  by Suleiman
v22:
* Move migration_node under CONFIG_SCHED_PROXY_EXEC as suggested
  by K Prateek
Cc: Joel Fernandes <joelagnelf@nvidia.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: Suleiman Souhlal <suleiman@google.com>
Cc: kuyo chang <kuyo.chang@mediatek.com>
Cc: hupu <hupu.gm@gmail.com>
Cc: kernel-team@android.com
---
 include/linux/sched.h |  3 +++
 init/init_task.c      |  3 +++
 kernel/fork.c         |  3 +++
 kernel/sched/core.c   | 25 +++++++++++++++++--------
 4 files changed, 26 insertions(+), 8 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index bac1b956027e2..cd2453c2085c1 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1243,6 +1243,9 @@ struct task_struct {
 	struct mutex			*blocked_on;	/* lock we're blocked on */
 	struct task_struct		*blocked_donor;	/* task that is boosting this task */
 	raw_spinlock_t			blocked_lock;
+#ifdef CONFIG_SCHED_PROXY_EXEC
+	struct list_head		migration_node;
+#endif
 
 #ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
 	/*
diff --git a/init/init_task.c b/init/init_task.c
index 34853a511b4d8..78fb7cb83fa5d 100644
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -178,6 +178,9 @@ struct task_struct init_task __aligned(L1_CACHE_BYTES) = {
 						 &init_task.alloc_lock),
 #endif
 	.blocked_donor = NULL,
+#ifdef CONFIG_SCHED_PROXY_EXEC
+	.migration_node = LIST_HEAD_INIT(init_task.migration_node),
+#endif
 #ifdef CONFIG_RT_MUTEXES
 	.pi_waiters	= RB_ROOT_CACHED,
 	.pi_top_task	= NULL,
diff --git a/kernel/fork.c b/kernel/fork.c
index 0a9a17e25b85d..a7561480e879e 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2137,6 +2137,9 @@ __latent_entropy struct task_struct *copy_process(
 
 	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;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index eabde9706981a..c202ae19b4ac8 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6718,6 +6718,7 @@ static void proxy_migrate_task(struct rq *rq, struct rq_flags *rf,
 			       struct task_struct *p, int target_cpu)
 {
 	struct rq *target_rq = cpu_rq(target_cpu);
+	LIST_HEAD(migrate_list);
 
 	lockdep_assert_rq_held(rq);
 
@@ -6734,11 +6735,16 @@ static void proxy_migrate_task(struct rq *rq, struct rq_flags *rf,
 	 */
 	proxy_resched_idle(rq);
 
-	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);
+	}
 	/*
 	 * We have to zap callbacks before unlocking the rq
 	 * as another CPU may jump in and call sched_balance_rq
@@ -6749,10 +6755,13 @@ static void proxy_migrate_task(struct rq *rq, struct rq_flags *rf,
 	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);
-- 
2.51.1.930.gacf6e81ea2-goog