[PATCH 05/10] sched,fair: remove cfs rqs from leaf_cfs_rq_list bottom up

[Rik van Riel]

Reducing the overhead of the CPU controller is achieved by not walking
all the sched_entities every time a task is enqueued or dequeued.

One of the things being checked every single time is whether the cfs_rq
is on the rq->leaf_cfs_rq_list.

By only removing a cfs_rq from the list once it no longer has children
on the list, we can avoid walking the sched_entity hierarchy if the bottom
cfs_rq is on the list, once the runqueues have been flattened.

Signed-off-by: Rik van Riel <riel@xxxxxxxxxxx>
---
 kernel/sched/fair.c  | 17 +++++++++++++++++
 kernel/sched/sched.h |  1 +
 2 files changed, 18 insertions(+)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 63cb40253b26..e41feacc45d9 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -286,6 +286,13 @@ static inline bool list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq)
 
 	cfs_rq->on_list = 1;
 
+	/*
+	 * If the tmp_alone_branch cursor was moved, it means a child cfs_rq
+	 * is already on the list ahead of us.
+	 */
+	if (rq->tmp_alone_branch != &rq->leaf_cfs_rq_list)
+		cfs_rq->children_on_list++;
+
 	/*
 	 * Ensure we either appear before our parent (if already
 	 * enqueued) or force our parent to appear after us when it is
@@ -311,6 +318,7 @@ static inline bool list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq)
 		 * list.
 		 */
 		rq->tmp_alone_branch = &rq->leaf_cfs_rq_list;
+		cfs_rq->tg->parent->cfs_rq[cpu]->children_on_list++;
 		return true;
 	}
 
@@ -359,6 +367,11 @@ static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq)
 		if (rq->tmp_alone_branch == &cfs_rq->leaf_cfs_rq_list)
 			rq->tmp_alone_branch = cfs_rq->leaf_cfs_rq_list.prev;
 
+		if (cfs_rq->tg->parent) {
+			int cpu = cpu_of(rq);
+			cfs_rq->tg->parent->cfs_rq[cpu]->children_on_list--;
+		}
+
 		list_del_rcu(&cfs_rq->leaf_cfs_rq_list);
 		cfs_rq->on_list = 0;
 	}
@@ -7687,6 +7700,10 @@ static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq)
 	if (cfs_rq->avg.util_sum)
 		return false;
 
+	/* Remove decayed parents once their decayed children are gone. */
+	if (cfs_rq->children_on_list)
+		return false;
+
 	return true;
 }
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 32978a8de8ce..4f8acbab0fb2 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -557,6 +557,7 @@ struct cfs_rq {
 	 * This list is used during load balance.
 	 */
 	int			on_list;
+	int			children_on_list;
 	struct list_head	leaf_cfs_rq_list;
 	struct task_group	*tg;	/* group that "owns" this runqueue */
 
-- 
2.20.1