1 files changed, 29 insertions, 7 deletions

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 30d76a18ae1a..6f353de3f390 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2757,6 +2757,10 @@ static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
         cfs_rq->load_last_update_time_copy = sa->last_update_time;
 #endif
 
+        /* Trace CPU load, unless cfs_rq belongs to a non-root task_group */
+        if (cfs_rq == &rq_of(cfs_rq)->cfs)
+                trace_sched_load_avg_cpu(cpu_of(rq_of(cfs_rq)), cfs_rq);
+
         return decayed || removed;
 }
 
@@ -2780,7 +2784,6 @@ static inline void update_load_avg(struct sched_entity *se, int update_tg)
 
         if (entity_is_task(se))
                 trace_sched_load_avg_task(task_of(se), &se->avg);
-        trace_sched_load_avg_cpu(cpu, cfs_rq);
 }
 
 static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
@@ -3958,6 +3961,26 @@ static void check_enqueue_throttle(struct cfs_rq *cfs_rq)
         if (!cfs_bandwidth_used())
                 return;
 
+        /* Synchronize hierarchical throttle counter: */
+        if (unlikely(!cfs_rq->throttle_uptodate)) {
+                struct rq *rq = rq_of(cfs_rq);
+                struct cfs_rq *pcfs_rq;
+                struct task_group *tg;
+
+                cfs_rq->throttle_uptodate = 1;
+
+                /* Get closest up-to-date node, because leaves go first: */
+                for (tg = cfs_rq->tg->parent; tg; tg = tg->parent) {
+                        pcfs_rq = tg->cfs_rq[cpu_of(rq)];
+                        if (pcfs_rq->throttle_uptodate)
+                                break;
+                }
+                if (tg) {
+                        cfs_rq->throttle_count = pcfs_rq->throttle_count;
+                        cfs_rq->throttled_clock_task = rq_clock_task(rq);
+                }
+        }
+
         /* an active group must be handled by the update_curr()->put() path */
         if (!cfs_rq->runtime_enabled || cfs_rq->curr)
                 return;
@@ -4343,15 +4366,14 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 
                 /* Don't dequeue parent if it has other entities besides us */
                 if (cfs_rq->load.weight) {
+                        /* Avoid re-evaluating load for this entity: */
+                        se = parent_entity(se);
                         /*
                          * Bias pick_next to pick a task from this cfs_rq, as
                          * p is sleeping when it is within its sched_slice.
                          */
-                        if (task_sleep && parent_entity(se))
-                                set_next_buddy(parent_entity(se));
-
-                        /* avoid re-evaluating load for this entity */
-                        se = parent_entity(se);
+                        if (task_sleep && se && !throttled_hierarchy(cfs_rq))
+                                set_next_buddy(se);
                         break;
                 }
                 flags |= DEQUEUE_SLEEP;
@@ -4916,7 +4938,7 @@ long group_norm_util(struct energy_env *eenv, struct sched_group *sg)
 }
 
 static int find_new_capacity(struct energy_env *eenv,
-        const struct sched_group_energy const *sge)
+        const struct sched_group_energy * const sge)
 {
         int idx;
         unsigned long util = group_max_util(eenv);