[PATCH v3 1/3] sched: introduce a new migration flag to task_struct

[<byungchul.park@lge.com>]

From: Byungchul Park <byungchul.park@lge.com>

This patch removes a weird coupling between se->avg.last_update_time and
the condition checking for migration, and introduce a new migration flag.
Now, scheduler can use the flag instead of se->avg.last_update_time to
check if migration already happened or not.

Signed-off-by: Byungchul Park <byungchul.park@lge.com>
---
 include/linux/sched.h |    3 +++
 kernel/sched/core.c   |    1 +
 kernel/sched/fair.c   |   22 ++++++++++++----------
 kernel/sched/sched.h  |    1 +
 4 files changed, 17 insertions(+), 10 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 699228b..a104c72 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1379,6 +1379,9 @@ struct task_struct {
 #endif
 	int on_rq;
 
+	/* For indicating if a migration has happened. */
+	int migrated;
+
 	int prio, static_prio, normal_prio;
 	unsigned int rt_priority;
 	const struct sched_class *sched_class;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index a91df61..57f4300 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2068,6 +2068,7 @@ void __dl_clear_params(struct task_struct *p)
 static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 {
 	p->on_rq			= 0;
+	p->migrated			= 0;
 
 	p->se.on_rq			= 0;
 	p->se.exec_start		= 0;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 077076f..0f76903 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2771,14 +2771,15 @@ static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s
 
 /* Add the load generated by se into cfs_rq's load average */
 static inline void
-enqueue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
+enqueue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 {
 	struct sched_avg *sa = &se->avg;
 	u64 now = cfs_rq_clock_task(cfs_rq);
-	int migrated, decayed;
+	int decayed;
+	int migrated = flags & ENQUEUE_MIGRATED;
+	int created = !sa->last_update_time;
 
-	migrated = !sa->last_update_time;
-	if (!migrated) {
+	if (!migrated && !created) {
 		__update_load_avg(now, cpu_of(rq_of(cfs_rq)), sa,
 			se->on_rq * scale_load_down(se->load.weight),
 			cfs_rq->curr == se, NULL);
@@ -2789,10 +2790,10 @@ enqueue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	cfs_rq->runnable_load_avg += sa->load_avg;
 	cfs_rq->runnable_load_sum += sa->load_sum;
 
-	if (migrated)
+	if (migrated || created)
 		attach_entity_load_avg(cfs_rq, se);
 
-	if (decayed || migrated)
+	if (decayed || migrated || created)
 		update_tg_load_avg(cfs_rq, 0);
 }
 
@@ -2868,7 +2869,7 @@ static int idle_balance(struct rq *this_rq);
 
 static inline void update_load_avg(struct sched_entity *se, int update_tg) {}
 static inline void
-enqueue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {}
+enqueue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) {}
 static inline void
 dequeue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {}
 static inline void remove_entity_load_avg(struct sched_entity *se) {}
@@ -3008,7 +3009,7 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	 * Update run-time statistics of the 'current'.
 	 */
 	update_curr(cfs_rq);
-	enqueue_entity_load_avg(cfs_rq, se);
+	enqueue_entity_load_avg(cfs_rq, se, flags);
 	account_entity_enqueue(cfs_rq, se);
 	update_cfs_shares(cfs_rq);
 
@@ -4136,6 +4137,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	struct cfs_rq *cfs_rq;
 	struct sched_entity *se = &p->se;
 
+	flags = flags | (xchg(&p->migrated, 0) ? ENQUEUE_MIGRATED : 0);
 	for_each_sched_entity(se) {
 		if (se->on_rq)
 			break;
@@ -5021,7 +5023,7 @@ static void migrate_task_rq_fair(struct task_struct *p, int next_cpu)
 	remove_entity_load_avg(&p->se);
 
 	/* Tell new CPU we are migrated */
-	p->se.avg.last_update_time = 0;
+	p->migrated = 1;
 
 	/* We have migrated, no longer consider this task hot */
 	p->se.exec_start = 0;
@@ -8082,7 +8084,7 @@ static void task_move_group_fair(struct task_struct *p)
 	set_task_rq(p, task_cpu(p));
 
 #ifdef CONFIG_SMP
-	/* Tell se's cfs_rq has been changed -- migrated */
+	/* Tell se's cfs_rq has been changed */
 	p->se.avg.last_update_time = 0;
 #endif
 	attach_task_cfs_rq(p);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index af6f252..66d0552 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1158,6 +1158,7 @@ static const u32 prio_to_wmult[40] = {
 #define ENQUEUE_WAKING		0
 #endif
 #define ENQUEUE_REPLENISH	8
+#define ENQUEUE_MIGRATED	16
 
 #define DEQUEUE_SLEEP		1
 
-- 
1.7.9.5