[PATCH 2/3] sched/fair: Correctly insert cfs_rq's to list on unthrottle

[Odin Ugedal]

This fixes an issue where fairness is decreased since cfs_rq's can
end up not being decayed properly. For two sibling control groups with
the same priority, this can often lead to a load ratio of 99/1 (!!).

This happen because when a cfs_rq is throttled, all the descendant cfs_rq's
will be removed from the leaf list. When they initial cfs_rq is
unthrottled, it will currently only re add descendant cfs_rq's if they
have one or more entities enqueued. This is not a perfect heuristic.

This fix change this behavior to save what cfs_rq's was removed from the
list, and readds them properly on unthrottle.

Can often lead to sutiations like this for equally weighted control
groups:

$ ps u -C stress
USER         PID %CPU %MEM    VSZ   RSS TTY      STAT START   TIME COMMAND
root       10009 88.8  0.0   3676   100 pts/1    R+   11:04   0:13 stress --cpu 1
root       10023  3.0  0.0   3676   104 pts/1    R+   11:04   0:00 stress --cpu 1

Fixes: 31bc6aeaab1d ("sched/fair: Optimize update_blocked_averages()")
Signed-off-by: Odin Ugedal <odin@xxxxxxx>
---
 kernel/sched/fair.c  | 11 ++++++-----
 kernel/sched/sched.h |  1 +
 2 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index ceda53c2a87a..e7423d658389 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -376,7 +376,8 @@ static inline bool list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq)
 	return false;
 }
 
-static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq)
+/* Returns 1 if cfs_rq was present in the list and removed */
+static inline bool list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq)
 {
 	if (cfs_rq->on_list) {
 		struct rq *rq = rq_of(cfs_rq);
@@ -393,7 +394,9 @@ static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq)
 
 		list_del_rcu(&cfs_rq->leaf_cfs_rq_list);
 		cfs_rq->on_list = 0;
+		return 1;
 	}
+	return 0;
 }
 
 static inline void assert_list_leaf_cfs_rq(struct rq *rq)
@@ -4742,9 +4745,7 @@ static int tg_unthrottle_up(struct task_group *tg, void *data)
 	if (!cfs_rq->throttle_count) {
 		cfs_rq->throttled_clock_task_time += rq_clock_task(rq) -
 					     cfs_rq->throttled_clock_task;
-
-		/* Add cfs_rq with already running entity in the list */
-		if (cfs_rq->nr_running >= 1)
+		if (cfs_rq->insert_on_unthrottle)
 			list_add_leaf_cfs_rq(cfs_rq);
 	}
 
@@ -4759,7 +4760,7 @@ static int tg_throttle_down(struct task_group *tg, void *data)
 	/* group is entering throttled state, stop time */
 	if (!cfs_rq->throttle_count) {
 		cfs_rq->throttled_clock_task = rq_clock_task(rq);
-		list_del_leaf_cfs_rq(cfs_rq);
+		cfs_rq->insert_on_unthrottle = list_del_leaf_cfs_rq(cfs_rq);
 	}
 	cfs_rq->throttle_count++;
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index a189bec13729..12a707d99ee6 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -602,6 +602,7 @@ struct cfs_rq {
 	u64			throttled_clock_task_time;
 	int			throttled;
 	int			throttle_count;
+	int			insert_on_unthrottle;
 	struct list_head	throttled_list;
 #endif /* CONFIG_CFS_BANDWIDTH */
 #endif /* CONFIG_FAIR_GROUP_SCHED */
-- 
2.31.1