[PATCH 01/18 v2] sched/eevdf: Decay positive lag of sleeping entities

[Vincent Guittot]

Similarly to delayed dequeue that enables an entity to decay its negative
lag while sleeping, a task should not keep a positive lag forever.

The sleep duration and the weight of the entity is used to decay the
positive lag at wakeup.

Signed-off-by: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
---
 kernel/sched/fair.c | 51 +++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 49 insertions(+), 2 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 03206e15e6fe..8cda1d39b037 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -897,6 +897,51 @@ bool update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	return avruntime - vlag != se->vruntime;
 }
 
+static inline unsigned long cfs_rq_load_avg(struct cfs_rq *cfs_rq);
+
+static __always_inline
+void decay_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
+{
+	s64 delta_exec, vlag = se->vlag;
+	unsigned long cfs_load;
+	struct rq *rq;
+
+	WARN_ON_ONCE(se->on_rq);
+
+	/* Negative lag implies delayed dequeue */
+	if (vlag <= 0)
+		return;
+
+	rq = rq_of(cfs_rq);
+
+	if (flags & ENQUEUE_MIGRATED)
+		return;
+
+	/* Compute sleep time */
+	delta_exec = rq_clock_task(rq) - se->exec_start;
+	if (unlikely(delta_exec <= 0))
+		return;
+
+	/* For anything above ~4 seconds, save computation and clear the lag */
+	if (unlikely(delta_exec >> 32)) {
+		se->vlag = 0;
+		return;
+	}
+
+	cfs_load = cfs_rq_load_avg(cfs_rq);
+	if (cfs_load) {
+		unsigned long weight = scale_load_down(se->h_load.weight);
+
+		delta_exec *= weight;
+		delta_exec = div64_long(delta_exec, cfs_load + weight);
+	}
+
+	vlag -= calc_delta_fair(delta_exec, se);
+
+	/* vlag can't become neg while sleeping */
+	se->vlag = max(0, vlag);
+}
+
 /*
  * Entity is eligible once it received less service than it ought to have,
  * eg. lag >= 0.
@@ -7987,7 +8032,7 @@ static void
 enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 {
 	int rq_h_nr_queued = rq->cfs.h_nr_queued;
-	int task_new = !(flags & ENQUEUE_WAKEUP);
+	int task_wake = flags & ENQUEUE_WAKEUP;
 	struct sched_entity *se = &p->se;
 	struct cfs_rq *cfs_rq = &rq->cfs;
 	unsigned long weight;
@@ -8019,6 +8064,8 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	if (p->in_iowait)
 		cpufreq_update_util(rq, SCHED_CPUFREQ_IOWAIT);
 
+	if (task_wake)
+		decay_entity_lag(cfs_rq, se, flags);
 
 	if (se->on_rq && se->sched_delayed)
 		requeue_delayed_entity(cfs_rq, se);
@@ -8048,7 +8095,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	 * into account, but that is not straightforward to implement,
 	 * and the following generally works well enough in practice.
 	 */
-	if (!task_new)
+	if (task_wake)
 		check_update_overutilized_status(rq);
 
 	assert_list_leaf_cfs_rq(rq);
-- 
2.53.0