sched/fair: Correctly insert cfs_rq's to list on unthrottle

Fix 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 happens 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.

Instead, we insert all cfs_rq's that contain one or more enqueued
entities, or it its load is not completely decayed.

Can often lead to situations 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: 31bc6aeaab ("sched/fair: Optimize update_blocked_averages()")
[vingo: !SMP build fix]
Signed-off-by: Odin Ugedal <odin@uged.al>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lore.kernel.org/r/20210612112815.61678-1-odin@uged.al

kernel/sched/fair.c

@@ -3298,6 +3298,24 @@ static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq, int flags)
 
 #ifdef CONFIG_SMP
 #ifdef CONFIG_FAIR_GROUP_SCHED
+
+static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq)
+{
+	if (cfs_rq->load.weight)
+		return false;
+
+	if (cfs_rq->avg.load_sum)
+		return false;
+
+	if (cfs_rq->avg.util_sum)
+		return false;
+
+	if (cfs_rq->avg.runnable_sum)
+		return false;
+
+	return true;
+}
+
 /**
  * update_tg_load_avg - update the tg's load avg
  * @cfs_rq: the cfs_rq whose avg changed
@@ -4091,6 +4109,11 @@ static inline void update_misfit_status(struct task_struct *p, struct rq *rq)
 
 #else /* CONFIG_SMP */
 
+static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq)
+{
+	return true;
+}
+
 #define UPDATE_TG	0x0
 #define SKIP_AGE_LOAD	0x0
 #define DO_ATTACH	0x0
@@ -4749,8 +4772,8 @@ static int tg_unthrottle_up(struct task_group *tg, void *data)
 		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 */
+		/* Add cfs_rq with load or one or more already running entities to the list */
-		if (cfs_rq->nr_running >= 1)
+		if (!cfs_rq_is_decayed(cfs_rq) || cfs_rq->nr_running)
 			list_add_leaf_cfs_rq(cfs_rq);
 	}
 
@@ -7996,23 +8019,6 @@ static bool __update_blocked_others(struct rq *rq, bool *done)
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 
-static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq)
-{
-	if (cfs_rq->load.weight)
-		return false;
-
-	if (cfs_rq->avg.load_sum)
-		return false;
-
-	if (cfs_rq->avg.util_sum)
-		return false;
-
-	if (cfs_rq->avg.runnable_sum)
-		return false;
-
-	return true;
-}
-
 static bool __update_blocked_fair(struct rq *rq, bool *done)
 {
 	struct cfs_rq *cfs_rq, *pos;