[PATCH 12/15] sched,fair: propagate sum_exec_runtime up the hierarchy

[Rik van Riel]

Now that enqueue_task_fair and dequeue_task_fair no longer iterate up
the hierarchy all the time, a method to lazily propagate sum_exec_runtime
up the hierarchy is necessary.

Once a tick, propagate the newly accumulated exec_runtime up the hierarchy,
and feed it into CFS bandwidth control.

Remove the pointless call to account_cfs_rq_runtime from update_curr,
which is always called with a root cfs_rq.

Signed-off-by: Rik van Riel <riel@xxxxxxxxxxx>
---
 include/linux/sched.h |  1 +
 kernel/sched/core.c   |  1 +
 kernel/sched/fair.c   | 22 ++++++++++++++++++++--
 3 files changed, 22 insertions(+), 2 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 901c710363e7..bdca15b3afe7 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -454,6 +454,7 @@ struct sched_entity {
 	int				depth;
 	unsigned long			enqueued_h_load;
 	unsigned long			enqueued_h_weight;
+	u64				propagated_exec_runtime;
 	struct load_weight		h_load;
 	struct sched_entity		*parent;
 	/* rq on which this entity is (to be) queued: */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index fbd96900f715..9915d20e84a9 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2137,6 +2137,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 	INIT_LIST_HEAD(&p->se.group_node);
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
+	p->se.propagated_exec_runtime	= 0;
 	p->se.cfs_rq			= NULL;
 #endif
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 5dc6d70e0df1..84481c9ca51d 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -916,8 +916,6 @@ static void update_curr(struct cfs_rq *cfs_rq)
 	trace_sched_stat_runtime(curtask, delta_exec, curr->vruntime);
 	cgroup_account_cputime(curtask, delta_exec);
 	account_group_exec_runtime(curtask, delta_exec);
-
-	account_cfs_rq_runtime(cfs_rq, delta_exec);
 }
 
 static void update_curr_fair(struct rq *rq)
@@ -3430,6 +3428,20 @@ static inline bool skip_blocked_update(struct sched_entity *se)
 	return true;
 }
 
+static void propagate_exec_runtime(struct cfs_rq *cfs_rq,
+				struct sched_entity *se)
+{
+	struct sched_entity *parent = se->parent;
+	u64 diff = se->sum_exec_runtime - se->propagated_exec_runtime;
+
+	if (parent) {
+		parent->sum_exec_runtime += diff;
+		account_cfs_rq_runtime(cfs_rq, diff);
+	}
+
+	se->propagated_exec_runtime = se->sum_exec_runtime;
+}
+
 #else /* CONFIG_FAIR_GROUP_SCHED */
 
 static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force) {}
@@ -3441,6 +3453,11 @@ static inline int propagate_entity_load_avg(struct sched_entity *se)
 
 static inline void add_tg_cfs_propagate(struct cfs_rq *cfs_rq, long runnable_sum) {}
 
+static void propagate_exec_runtime(struct cfs_rq *cfs_rq,
+				struct sched_entity *se);
+{
+}
+
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 
 /**
@@ -10175,6 +10192,7 @@ static void propagate_entity_cfs_rq(struct sched_entity *se, int flags)
 			if (!(flags & DO_ATTACH))
 				break;
 
+		propagate_exec_runtime(cfs_rq, se);
 		update_cfs_group(se);
 	}
 }
-- 
2.20.1