[PATCH 02/18] sched/eevdf: Reset lag when waking up on idle cpu

[Vincent Guittot]

When several tasks wake up simultaneously on an idle CPU, their final vlag
will depend of the ordering as the first one will lose its lag but not
the next ones.
Reset the lag when the enqueue happens while no fair task has already been
picked et set as the running task.

As a typical example:
CPU0 is idle
TA with vlag 0ms and TB with vlag 5ms wake up on CPU0 simultaneously.
Depending which grab the lock 1st the behavior will be different:
If TA is enqueued 1st, TB will be enqueued with a positive lag and will
be picked 1st.
But if TB is enqueued 1st, it will loose its positive vlag and both TA and
TB will have 0 vlag when fair will pick a task.

Signed-off-by: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
---
 include/linux/sched.h |  1 +
 kernel/sched/fair.c   | 17 +++++++++++++++++
 kernel/sched/sched.h  |  1 +
 3 files changed, 19 insertions(+)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index d7cc77181ef9..32d7077ef148 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -592,6 +592,7 @@ struct sched_entity {
 	u64				vruntime;
 	/* Approximated virtual lag: */
 	s64				vlag;
+	u32				vlag_seq;
 	/* 'Protected' deadline, to give out minimum quantums: */
 	u64				vprot;
 	u64				slice;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 8cda1d39b037..4c8f12fc8869 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -893,6 +893,7 @@ bool update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se)
 			vlag = min(vlag, 0);
 	}
 	se->vlag = vlag;
+	se->vlag_seq = cfs_rq->idle_seq;
 
 	return avruntime - vlag != se->vruntime;
 }
@@ -914,9 +915,22 @@ void decay_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 
 	rq = rq_of(cfs_rq);
 
+	/* You can't claim any lag when waking on idle CPU */
+	if (rq->curr == rq->idle) {
+		se->vlag = 0;
+		return;
+	}
+
+	/* Accessing remote rq task clock is a cost */
 	if (flags & ENQUEUE_MIGRATED)
 		return;
 
+	/* CPU has been idle in between so the lag has been removed */
+	if (se->vlag_seq != cfs_rq->idle_seq) {
+		se->vlag = 0;
+		return;
+	}
+
 	/* Compute sleep time */
 	delta_exec = rq_clock_task(rq) - se->exec_start;
 	if (unlikely(delta_exec <= 0))
@@ -8190,6 +8204,9 @@ static bool __dequeue_task(struct rq *rq, struct task_struct *p, int flags)
 
 	dequeue_hierarchy(p, flags);
 
+	if (!cfs_rq->h_nr_queued)
+		cfs_rq->idle_seq++;
+
 	if (sched_feat(PLACE_REL_DEADLINE) && !task_sleep) {
 		se->deadline -= se->vruntime;
 		se->rel_deadline = 1;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index b98084e1f5b0..69a2a749e188 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -689,6 +689,7 @@ struct cfs_rq {
 	u64			sum_weight;
 	u64			zero_vruntime;
 	unsigned int		sum_shift;
+	u32			idle_seq;
 
 #ifdef CONFIG_SCHED_CORE
 	unsigned int		forceidle_seq;
-- 
2.53.0