[PATCH 4/7 v3] sched: propagate load during synchronous attach/detach

[Vincent Guittot]

When a task moves from/to a cfs_rq, we set a flag which is then used to
propagate the change at parent level (sched_entity and cfs_rq) during
next update. If the cfs_rq is throttled, the flag will stay pending until
the cfs_rw is unthrottled.

For propagating the utilization, we copy the utilization of child cfs_rq to
the sched_entity.

For propagating the load, we have to take into account the load of the
whole task group in order to evaluate the load of the sched_entity.
Similarly to what was done before the rewrite of PELT, we add a correction
factor in case the task group's load is less than its share so it will
contribute the same load of a task of equal weight.

Signed-off-by: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
---
 kernel/sched/fair.c  | 170 ++++++++++++++++++++++++++++++++++++++++++++++++++-
 kernel/sched/sched.h |   1 +
 2 files changed, 170 insertions(+), 1 deletion(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 0aa1d7d..e4015f6 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3017,6 +3017,132 @@ static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq)
 	}
 }
 
+#ifdef CONFIG_FAIR_GROUP_SCHED
+/* Take into account change of utilization of a child task group */
+static inline void
+update_tg_cfs_util(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+	struct cfs_rq *gcfs_rq =  group_cfs_rq(se);
+	long delta = gcfs_rq->avg.util_avg - se->avg.util_avg;
+
+	/* Nothing to update */
+	if (!delta)
+		return;
+
+	/* Set new sched_entity's utilizaton */
+	se->avg.util_avg = gcfs_rq->avg.util_avg;
+	se->avg.util_sum = se->avg.util_avg * LOAD_AVG_MAX;
+
+	/* Update parent cfs_rq utilization */
+	cfs_rq->avg.util_avg =  max_t(long, cfs_rq->avg.util_avg + delta, 0);
+	cfs_rq->avg.util_sum = cfs_rq->avg.util_avg * LOAD_AVG_MAX;
+}
+
+/* Take into account change of load of a child task group */
+static inline void
+update_tg_cfs_load(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+	struct cfs_rq *gcfs_rq = group_cfs_rq(se);
+	long delta, load = gcfs_rq->avg.load_avg;
+
+	/* If the load of group cfs_rq is null, the load of the
+	 * sched_entity will also be null so we can skip the formula
+	 */
+	if (load) {
+		long tg_load;
+
+		/* Get tg's load and ensure tg_load > 0 */
+		tg_load = atomic_long_read(&gcfs_rq->tg->load_avg) + 1;
+
+		/* Ensure tg_load >= load and updated with current load*/
+		tg_load -= gcfs_rq->tg_load_avg_contrib;
+		tg_load += load;
+
+		/* scale gcfs_rq's load into tg's shares*/
+		load *= scale_load_down(gcfs_rq->tg->shares);
+		load /= tg_load;
+
+		/*
+		 * we need to compute a correction term in the case that the
+		 * task group is consuming <1 cpu so that we would contribute
+		 * the same load as a task of equal weight.
+		*/
+		if (tg_load < scale_load_down(gcfs_rq->tg->shares)) {
+			load *= tg_load;
+			load /= scale_load_down(gcfs_rq->tg->shares);
+		}
+	}
+
+	delta = load - se->avg.load_avg;
+
+	/* Nothing to update */
+	if (!delta)
+		return;
+
+	/* Set new sched_entity's load */
+	se->avg.load_avg = load;
+	se->avg.load_sum = se->avg.load_avg * LOAD_AVG_MAX;
+
+	/* Update parent cfs_rq load */
+	cfs_rq->avg.load_avg = max_t(long, cfs_rq->avg.load_avg + delta, 0);
+	cfs_rq->avg.load_sum = cfs_rq->avg.load_avg * LOAD_AVG_MAX;
+}
+
+static inline void set_tg_cfs_propagate(struct cfs_rq *cfs_rq)
+{
+	/* set cfs_rq's flag */
+	cfs_rq->propagate_avg = 1;
+}
+
+static inline int test_and_clear_tg_cfs_propagate(struct sched_entity *se)
+{
+	/* Get my cfs_rq */
+	struct cfs_rq *cfs_rq = group_cfs_rq(se);
+
+	/* Nothing to propagate */
+	if (!cfs_rq->propagate_avg)
+		return 0;
+
+	/* Clear my cfs_rq's flag */
+	cfs_rq->propagate_avg = 0;
+
+	return 1;
+}
+
+/* Update task and its cfs_rq load average */
+static inline int propagate_entity_load_avg(struct sched_entity *se)
+{
+	struct cfs_rq *cfs_rq;
+
+	if (entity_is_task(se))
+		return 0;
+
+	if (!test_and_clear_tg_cfs_propagate(se))
+		return 0;
+
+	/* Get parent cfs_rq */
+	cfs_rq = cfs_rq_of(se);
+
+	/* Propagate to parent */
+	set_tg_cfs_propagate(cfs_rq);
+
+	/* Update utilization */
+	update_tg_cfs_util(cfs_rq, se);
+
+	/* Update load */
+	update_tg_cfs_load(cfs_rq, se);
+
+	return 1;
+}
+#else
+static inline int propagate_entity_load_avg(struct sched_entity *se)
+{
+	return 0;
+}
+
+static inline void set_tg_cfs_propagate(struct cfs_rq *cfs_rq) {}
+#endif
+
 /*
  * Unsigned subtract and clamp on underflow.
  *
@@ -3093,6 +3219,7 @@ static inline void update_load_avg(struct sched_entity *se, int update_tg,
 	u64 now = cfs_rq_clock_task(cfs_rq);
 	struct rq *rq = rq_of(cfs_rq);
 	int cpu = cpu_of(rq);
+	int decayed;
 
 	/*
 	 * Track task load average for carrying it to new CPU after migrated, and
@@ -3103,7 +3230,11 @@ static inline void update_load_avg(struct sched_entity *se, int update_tg,
 			  se->on_rq * scale_load_down(se->load.weight),
 			  cfs_rq->curr == se, NULL);
 
-	if (update_cfs_rq_load_avg(now, cfs_rq, true) && update_tg)
+	decayed = update_cfs_rq_load_avg(now, cfs_rq, true);
+
+	decayed |= propagate_entity_load_avg(se);
+
+	if (decayed && update_tg)
 		update_tg_load_avg(cfs_rq, 0);
 }
 
@@ -3122,6 +3253,7 @@ static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s
 	cfs_rq->avg.load_sum += se->avg.load_sum;
 	cfs_rq->avg.util_avg += se->avg.util_avg;
 	cfs_rq->avg.util_sum += se->avg.util_sum;
+	set_tg_cfs_propagate(cfs_rq);
 
 	cfs_rq_util_change(cfs_rq);
 }
@@ -3141,6 +3273,7 @@ static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s
 	sub_positive(&cfs_rq->avg.load_sum, se->avg.load_sum);
 	sub_positive(&cfs_rq->avg.util_avg, se->avg.util_avg);
 	sub_positive(&cfs_rq->avg.util_sum, se->avg.util_sum);
+	set_tg_cfs_propagate(cfs_rq);
 
 	cfs_rq_util_change(cfs_rq);
 }
@@ -8499,6 +8632,22 @@ static void detach_task_cfs_rq(struct task_struct *p)
 	update_load_avg(se, 0, 0);
 	detach_entity_load_avg(cfs_rq, se);
 	update_tg_load_avg(cfs_rq, false);
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+	/*
+	 * Propagate the detach across the tg tree to make it visible to the
+	 * root
+	 */
+	se = se->parent;
+	for_each_sched_entity(se) {
+		cfs_rq = cfs_rq_of(se);
+
+		if (cfs_rq_throttled(cfs_rq))
+			break;
+
+		update_load_avg(se, 1, 0);
+	}
+#endif
 }
 
 static void attach_entity_cfs_rq(struct sched_entity *se)
@@ -8517,6 +8666,22 @@ static void attach_entity_cfs_rq(struct sched_entity *se)
 	update_load_avg(se, 0, !sched_feat(ATTACH_AGE_LOAD));
 	attach_entity_load_avg(cfs_rq, se);
 	update_tg_load_avg(cfs_rq, false);
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+	/*
+	 * Propagate the attach across the tg tree to make it visible to the
+	 * root
+	 */
+	se = se->parent;
+	for_each_sched_entity(se) {
+		cfs_rq = cfs_rq_of(se);
+
+		if (cfs_rq_throttled(cfs_rq))
+			break;
+
+		update_load_avg(se, 1, 0);
+	}
+#endif
 }
 
 static void attach_task_cfs_rq(struct task_struct *p)
@@ -8578,6 +8743,9 @@ void init_cfs_rq(struct cfs_rq *cfs_rq)
 	cfs_rq->min_vruntime_copy = cfs_rq->min_vruntime;
 #endif
 #ifdef CONFIG_SMP
+#ifdef CONFIG_FAIR_GROUP_SCHED
+	cfs_rq->propagate_avg = 0;
+#endif
 	atomic_long_set(&cfs_rq->removed_load_avg, 0);
 	atomic_long_set(&cfs_rq->removed_util_avg, 0);
 #endif
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 483616a..0517a9e 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -397,6 +397,7 @@ struct cfs_rq {
 	unsigned long runnable_load_avg;
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	unsigned long tg_load_avg_contrib;
+	unsigned long propagate_avg;
 #endif
 	atomic_long_t removed_load_avg, removed_util_avg;
 #ifndef CONFIG_64BIT
-- 
1.9.1