[PATCH 4/6 v5] 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 group 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 greater 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  | 200 ++++++++++++++++++++++++++++++++++++++++++++++++++-
 kernel/sched/sched.h |   1 +
 2 files changed, 200 insertions(+), 1 deletion(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 52cbc92..91fc949 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3031,6 +3031,162 @@ static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq)
 }
 
 /*
+ * Signed add and clamp on underflow.
+ *
+ * Explicitly do a load-store to ensure the intermediate value never hits
+ * memory. This allows lockless observations without ever seeing the negative
+ * values.
+ */
+#define add_positive(_ptr, _val) do {				\
+	typeof(_ptr) ptr = (_ptr);				\
+	typeof(_val) res, val = (_val);				\
+	typeof(*ptr) var = READ_ONCE(*ptr);			\
+	res = var + val;					\
+	if (res < 0)						\
+		res = 0;					\
+	WRITE_ONCE(*ptr, res);					\
+} while (0)
+
+#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 utilization */
+	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 */
+	add_positive(&cfs_rq->avg.util_avg, delta);
+	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;
+
+		/*
+		 * We need to compute a correction term in the case that the
+		 * task group is consuming more cpu than a task of equal
+		 * weight. A task with a weight equals to tg->shares will have
+		 * a load less or equal to scale_load_down(tg->shares).
+		 * Similarly, the sched_entities that represent the task group
+		 * at parent level, can't have a load higher than
+		 * scale_load_down(tg->shares). And the Sum of sched_entities'
+		 * load must be <= scale_load_down(tg->shares).
+		 */
+		if (tg_load > scale_load_down(gcfs_rq->tg->shares)) {
+			/* scale gcfs_rq's load into tg's shares*/
+			load *= scale_load_down(gcfs_rq->tg->shares);
+			load /= tg_load;
+		}
+	}
+
+	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 */
+	add_positive(&cfs_rq->avg.load_avg, delta);
+	cfs_rq->avg.load_sum = cfs_rq->avg.load_avg * LOAD_AVG_MAX;
+
+	/*
+	 * If the sched_entity is already enqueued, we also have to update the
+	 * runnable load avg.
+	 */
+	if (se->on_rq) {
+		/* Update parent cfs_rq runnable_load_avg */
+		add_positive(&cfs_rq->runnable_load_avg, delta);
+		cfs_rq->runnable_load_sum = cfs_rq->runnable_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.
  *
  * Explicitly do a load-store to ensure the intermediate value never hits
@@ -3111,6 +3267,7 @@ static inline void update_load_avg(struct sched_entity *se, int flags)
 	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
@@ -3121,7 +3278,11 @@ static inline void update_load_avg(struct sched_entity *se, int flags)
 			  se->on_rq * scale_load_down(se->load.weight),
 			  cfs_rq->curr == se, NULL);
 
-	if (update_cfs_rq_load_avg(now, cfs_rq, true) && (flags & UPDATE_TG))
+	decayed = update_cfs_rq_load_avg(now, cfs_rq, true);
+
+	decayed |= propagate_entity_load_avg(se);
+
+	if (decayed && (flags & UPDATE_TG))
 		update_tg_load_avg(cfs_rq, 0);
 }
 
@@ -3140,6 +3301,7 @@ 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);
 }
@@ -3159,6 +3321,7 @@ 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);
 }
@@ -8704,6 +8867,22 @@ static void detach_task_cfs_rq(struct task_struct *p)
 	update_load_avg(se, 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, UPDATE_TG);
+	}
+#endif
 }
 
 static void attach_entity_cfs_rq(struct sched_entity *se)
@@ -8722,6 +8901,22 @@ static void attach_entity_cfs_rq(struct sched_entity *se)
 	update_load_avg(se, sched_feat(ATTACH_AGE_LOAD) ? 0 : SKIP_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, UPDATE_TG);
+	}
+#endif
 }
 
 static void attach_task_cfs_rq(struct task_struct *p)
@@ -8783,6 +8978,9 @@ 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 f1185c3..47385e2 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -404,6 +404,7 @@ 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
-- 
2.7.4