sched/fair: Propagate load for throttled cfs_rq

Before task based throttle model, propagating load will stop at a
throttled cfs_rq and that propagate will happen on unthrottle time by
update_load_avg().

Now that there is no update_load_avg() on unthrottle for throttled
cfs_rq and all load tracking is done by task related operations, let the
propagate happen immediately.

While at it, add a comment to explain why cfs_rqs that are not affected
by throttle have to be added to leaf cfs_rq list in
propagate_entity_cfs_rq() per my understanding of commit 0258bdfaff5b
("sched/fair: Fix unfairness caused by missing load decay").

Signed-off-by: Aaron Lu <ziqianlu@bytedance.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Chengming Zhou <chengming.zhou@linux.dev>

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index df8dc389af8e1491b891a31a8c349a197ffdfed2..f993de30e14669e127573b8509f8f42139fc3595 100644 (file)
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5729,6 +5729,11 @@ static inline int cfs_rq_throttled(struct cfs_rq *cfs_rq)
        return cfs_bandwidth_used() && cfs_rq->throttled;
 }
 
+static inline bool cfs_rq_pelt_clock_throttled(struct cfs_rq *cfs_rq)
+{
+       return cfs_bandwidth_used() && cfs_rq->pelt_clock_throttled;
+}
+
 /* check whether cfs_rq, or any parent, is throttled */
 static inline int throttled_hierarchy(struct cfs_rq *cfs_rq)
 {
@@ -6721,6 +6726,11 @@ static inline int cfs_rq_throttled(struct cfs_rq *cfs_rq)
        return 0;
 }
 
+static inline bool cfs_rq_pelt_clock_throttled(struct cfs_rq *cfs_rq)
+{
+       return false;
+}
+
 static inline int throttled_hierarchy(struct cfs_rq *cfs_rq)
 {
        return 0;
@@ -13151,10 +13161,13 @@ static void propagate_entity_cfs_rq(struct sched_entity *se)
 {
        struct cfs_rq *cfs_rq = cfs_rq_of(se);
 
-       if (cfs_rq_throttled(cfs_rq))
-               return;
-
-       if (!throttled_hierarchy(cfs_rq))
+       /*
+        * If a task gets attached to this cfs_rq and before being queued,
+        * it gets migrated to another CPU due to reasons like affinity
+        * change, make sure this cfs_rq stays on leaf cfs_rq list to have
+        * that removed load decayed or it can cause faireness problem.
+        */
+       if (!cfs_rq_pelt_clock_throttled(cfs_rq))
                list_add_leaf_cfs_rq(cfs_rq);
 
        /* Start to propagate at parent */
@@ -13165,10 +13178,7 @@ static void propagate_entity_cfs_rq(struct sched_entity *se)
 
                update_load_avg(cfs_rq, se, UPDATE_TG);
 
-               if (cfs_rq_throttled(cfs_rq))
-                       break;
-
-               if (!throttled_hierarchy(cfs_rq))
+               if (!cfs_rq_pelt_clock_throttled(cfs_rq))
                        list_add_leaf_cfs_rq(cfs_rq);
        }
 }