[PATCH 2/2] sched/fair: Skip detach and attach load avgs for new group task

[Yuyang Du]

Vincent reported that the first task to a new task group's cfs_rq will
be attached in attach_task_cfs_rq() and once more when it is enqueued
(see https://lkml.org/lkml/2016/5/25/388).

Actually, it is worse, attach_task_cfs_rq() is called for new task even
way before init_entity_runnable_average().

Solve this by avoiding attach as well as detach new task's sched avgs
in task_move_group_fair(). To do it, we need to know whether the task
is forked or not, so we pass this info all the way from sched_move_task()
to attach_task_cfs_rq().

Reported-by: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
Signed-off-by: Yuyang Du <yuyang.du@xxxxxxxxx>
---
 kernel/sched/auto_group.c |    2 +-
 kernel/sched/core.c       |    8 ++++----
 kernel/sched/fair.c       |   23 ++++++++++++-----------
 kernel/sched/sched.h      |    4 ++--
 4 files changed, 19 insertions(+), 18 deletions(-)

diff --git a/kernel/sched/auto_group.c b/kernel/sched/auto_group.c
index a5d966c..e5f0be2 100644
--- a/kernel/sched/auto_group.c
+++ b/kernel/sched/auto_group.c
@@ -143,7 +143,7 @@ autogroup_move_group(struct task_struct *p, struct autogroup *ag)
 		goto out;
 
 	for_each_thread(p, t)
-		sched_move_task(t);
+		sched_move_task(t, 0);
 out:
 	unlock_task_sighand(p, &flags);
 	autogroup_kref_put(prev);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 7f2cae4..8585032 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7724,7 +7724,7 @@ void sched_offline_group(struct task_group *tg)
  *	by now. This function just updates tsk->se.cfs_rq and tsk->se.parent to
  *	reflect its new group.
  */
-void sched_move_task(struct task_struct *tsk)
+void sched_move_task(struct task_struct *tsk, int fork)
 {
 	struct task_group *tg;
 	int queued, running;
@@ -7753,7 +7753,7 @@ void sched_move_task(struct task_struct *tsk)
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	if (tsk->sched_class->task_move_group)
-		tsk->sched_class->task_move_group(tsk);
+		tsk->sched_class->task_move_group(tsk, fork);
 	else
 #endif
 		set_task_rq(tsk, task_cpu(tsk));
@@ -8186,7 +8186,7 @@ static void cpu_cgroup_css_free(struct cgroup_subsys_state *css)
 
 static void cpu_cgroup_fork(struct task_struct *task)
 {
-	sched_move_task(task);
+	sched_move_task(task, 1);
 }
 
 static int cpu_cgroup_can_attach(struct cgroup_taskset *tset)
@@ -8213,7 +8213,7 @@ static void cpu_cgroup_attach(struct cgroup_taskset *tset)
 	struct cgroup_subsys_state *css;
 
 	cgroup_taskset_for_each(task, css, tset)
-		sched_move_task(task);
+		sched_move_task(task, 0);
 }
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index e89c39b..e5a61b1 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2970,6 +2970,7 @@ static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s
 	cfs_rq_util_change(cfs_rq);
 }
 
+/* Catch up with the cfs_rq and then remove our sched avgs from it */
 static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	__update_load_avg(cfs_rq->avg.last_update_time, cpu_of(rq_of(cfs_rq)),
@@ -8368,9 +8369,6 @@ static void detach_task_cfs_rq(struct task_struct *p)
 		place_entity(cfs_rq, se, 0);
 		se->vruntime -= cfs_rq->min_vruntime;
 	}
-
-	/* Catch up with the cfs_rq and remove our load when we leave */
-	detach_entity_load_avg(cfs_rq, se);
 }
 
 static void attach_task_cfs_rq(struct task_struct *p)
@@ -8386,9 +8384,6 @@ static void attach_task_cfs_rq(struct task_struct *p)
 	se->depth = se->parent ? se->parent->depth + 1 : 0;
 #endif
 
-	/* Synchronize task with its cfs_rq */
-	attach_entity_load_avg(cfs_rq, se);
-
 	if (!vruntime_normalized(p))
 		se->vruntime += cfs_rq->min_vruntime;
 }
@@ -8396,6 +8391,7 @@ static void attach_task_cfs_rq(struct task_struct *p)
 static void switched_from_fair(struct rq *rq, struct task_struct *p)
 {
 	detach_task_cfs_rq(p);
+	detach_entity_load_avg(cfs_rq_of(&p->se), &p->se);
 }
 
 static void switched_to_fair(struct rq *rq, struct task_struct *p)
@@ -8422,6 +8418,7 @@ static void switched_to_fair(struct rq *rq, struct task_struct *p)
 skip_aging:
 #endif
 	attach_task_cfs_rq(p);
+	attach_entity_load_avg(cfs_rq_of(se), se);
 
 	if (task_on_rq_queued(p)) {
 		/*
@@ -8468,16 +8465,20 @@ void init_cfs_rq(struct cfs_rq *cfs_rq)
 }
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
-static void task_move_group_fair(struct task_struct *p)
+static void task_move_group_fair(struct task_struct *p, int fork)
 {
 	detach_task_cfs_rq(p);
+	/*
+	 * New task does not need detach or attach load (see below)
+	 */
+	if (!fork)
+		detach_entity_load_avg(cfs_rq_of(&p->se), &p->se);
+
 	set_task_rq(p, task_cpu(p));
 
-#ifdef CONFIG_SMP
-	/* Tell se's cfs_rq has been changed -- migrated */
-	p->se.avg.last_update_time = 0;
-#endif
 	attach_task_cfs_rq(p);
+	if (!fork)
+		attach_entity_load_avg(cfs_rq_of(&p->se), &p->se);
 }
 
 void free_fair_sched_group(struct task_group *tg)
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 72f1f30..58b1259 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -343,7 +343,7 @@ extern void sched_online_group(struct task_group *tg,
 extern void sched_destroy_group(struct task_group *tg);
 extern void sched_offline_group(struct task_group *tg);
 
-extern void sched_move_task(struct task_struct *tsk);
+extern void sched_move_task(struct task_struct *tsk, int fork);
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 extern int sched_group_set_shares(struct task_group *tg, unsigned long shares);
@@ -1247,7 +1247,7 @@ struct sched_class {
 	void (*update_curr) (struct rq *rq);
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
-	void (*task_move_group) (struct task_struct *p);
+	void (*task_move_group) (struct task_struct *p, int fork);
 #endif
 };
 
-- 
1.7.9.5