[RFC][PATCH v20 6/6] sched: Migrate whole chain in proxy_migrate_task()

[John Stultz]

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@xxxxxxxxxx>
---
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

Cc: Joel Fernandes <joelagnelf@xxxxxxxxxx>
Cc: Qais Yousef <qyousef@xxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Juri Lelli <juri.lelli@xxxxxxxxxx>
Cc: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
Cc: Dietmar Eggemann <dietmar.eggemann@xxxxxxx>
Cc: Valentin Schneider <vschneid@xxxxxxxxxx>
Cc: Steven Rostedt <rostedt@xxxxxxxxxxx>
Cc: Ben Segall <bsegall@xxxxxxxxxx>
Cc: Zimuzo Ezeozue <zezeozue@xxxxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxx>
Cc: Will Deacon <will@xxxxxxxxxx>
Cc: Waiman Long <longman@xxxxxxxxxx>
Cc: Boqun Feng <boqun.feng@xxxxxxxxx>
Cc: "Paul E. McKenney" <paulmck@xxxxxxxxxx>
Cc: Metin Kaya <Metin.Kaya@xxxxxxx>
Cc: Xuewen Yan <xuewen.yan94@xxxxxxxxx>
Cc: K Prateek Nayak <kprateek.nayak@xxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Daniel Lezcano <daniel.lezcano@xxxxxxxxxx>
Cc: Suleiman Souhlal <suleiman@xxxxxxxxxx>
Cc: kuyo chang <kuyo.chang@xxxxxxxxxxxx>
Cc: hupu <hupu.gm@xxxxxxxxx>
Cc: kernel-team@xxxxxxxxxxx
---
 include/linux/sched.h |  1 +
 init/init_task.c      |  1 +
 kernel/fork.c         |  1 +
 kernel/sched/core.c   | 25 +++++++++++++++++--------
 4 files changed, 20 insertions(+), 8 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 675e2f89ec0f8..e9242dfa5f271 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1240,6 +1240,7 @@ 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 */
+	struct list_head		migration_node;
 	raw_spinlock_t			blocked_lock;
 
 #ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
diff --git a/init/init_task.c b/init/init_task.c
index 627bbd8953e88..65e0f90285966 100644
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -176,6 +176,7 @@ struct task_struct init_task __aligned(L1_CACHE_BYTES) = {
 #endif
 	.blocked_on_state = BO_RUNNABLE,
 	.blocked_donor = NULL,
+	.migration_node = LIST_HEAD_INIT(init_task.migration_node),
 #ifdef CONFIG_RT_MUTEXES
 	.pi_waiters	= RB_ROOT_CACHED,
 	.pi_top_task	= NULL,
diff --git a/kernel/fork.c b/kernel/fork.c
index 61a2ac850faf0..892940ea52958 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2127,6 +2127,7 @@ __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 */
+	INIT_LIST_HEAD(&p->migration_node);
 
 #ifdef CONFIG_BCACHE
 	p->sequential_io	= 0;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 2c3a4b9518927..c1d813a9cde96 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6741,6 +6741,7 @@ 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);
 
@@ -6768,19 +6769,27 @@ static void proxy_migrate_task(struct rq *rq, struct rq_flags *rf,
 	rq_set_donor(rq, rq->idle);
 	set_next_task(rq, rq->idle);
 
-	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);
-- 
2.50.0.727.gbf7dc18ff4-goog