[PATCH 05/15] 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>
Suggested-by: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
---
 kernel/sched/fair.c | 35 ++++++++++++++++++++++++++++++++++-
 1 file changed, 34 insertions(+), 1 deletion(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index a48d0dbfc232..04b216234265 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -369,6 +369,39 @@ static inline void assert_list_leaf_cfs_rq(struct rq *rq)
 	SCHED_WARN_ON(rq->tmp_alone_branch != &rq->leaf_cfs_rq_list);
 }
 
+/*
+ * Because list_add_leaf_cfs_rq always places a child cfs_rq on the list
+ * immediately before a parent cfs_rq, and cfs_rqs are removed from the list
+ * bottom-up, we only have to test whether the cfs_rq before us on the list
+ * is our child.
+ */
+static inline bool child_cfs_rq_on_list(struct cfs_rq *cfs_rq)
+{
+	struct cfs_rq *prev_cfs_rq;
+	struct list_head *prev;
+
+	prev = cfs_rq->leaf_cfs_rq_list.prev;
+	prev_cfs_rq = container_of(prev, struct cfs_rq, leaf_cfs_rq_list);
+
+	return (prev_cfs_rq->tg->parent == cfs_rq->tg);
+}	
+
+/*
+ * Remove a cfs_rq from the list if it has no children on the list.
+ * The scheduler iterates over the list regularly; if conditions for
+ * removal are still true, we'll get to this cfs_rq in the future.
+ */
+static inline void list_del_leaf_cfs_rq_bottom(struct cfs_rq *cfs_rq)
+{
+	if (!cfs_rq->on_list)
+		return;
+
+	if (child_cfs_rq_on_list(cfs_rq))
+		return;
+
+	list_del_leaf_cfs_rq(cfs_rq);
+}
+
 /* Iterate thr' all leaf cfs_rq's on a runqueue */
 #define for_each_leaf_cfs_rq_safe(rq, cfs_rq, pos)			\
 	list_for_each_entry_safe(cfs_rq, pos, &rq->leaf_cfs_rq_list,	\
@@ -7723,7 +7756,7 @@ static void update_blocked_averages(int cpu)
 		 * decayed cfs_rqs linger on the list.
 		 */
 		if (cfs_rq_is_decayed(cfs_rq))
-			list_del_leaf_cfs_rq(cfs_rq);
+			list_del_leaf_cfs_rq_bottom(cfs_rq);
 
 		/* Don't need periodic decay once load/util_avg are null */
 		if (cfs_rq_has_blocked(cfs_rq))
-- 
2.20.1