From f36d8a8f857d6590a83755673b338e48104aa13a Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Thu, 4 May 2017 15:31:22 +0200
Subject: [PATCH] sched/fair: Use task_groups instead of leaf_cfs_rq_list to
 walk all cfs_rqs

References: bnc#1066110 Scheduler utilisation tracking
Patch-mainline: v4.13-rc1
Git-commit: 502ce005ab95d5d9481768649dbab808845b24d7

In order to allow leaf_cfs_rq_list to remove entries switch the
bandwidth hotplug code over to the task_groups list.

Suggested-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Chris Mason <clm@fb.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Turner <pjt@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20170504133122.a6qjlj3hlblbjxux@hirez.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 kernel/sched/fair.c | 30 +++++++++++++++++++++++++-----
 1 file changed, 25 insertions(+), 5 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index e9a677fe9675..ae4c48583797 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4716,24 +4716,43 @@ static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
 	hrtimer_cancel(&cfs_b->slack_timer);
 }
 
+/*
+ * Both these cpu hotplug callbacks race against unregister_fair_sched_group()
+ *
+ * The race is harmless, since modifying bandwidth settings of unhooked group
+ * bits doesn't do much.
+ */
+
+/* cpu online calback */
 static void __maybe_unused update_runtime_enabled(struct rq *rq)
 {
-	struct cfs_rq *cfs_rq;
+	struct task_group *tg;
+
+	lockdep_assert_held(&rq->lock);
 
-	for_each_leaf_cfs_rq(rq, cfs_rq) {
-		struct cfs_bandwidth *cfs_b = &cfs_rq->tg->cfs_bandwidth;
+	rcu_read_lock();
+	list_for_each_entry_rcu(tg, &task_groups, list) {
+		struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth;
+		struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)];
 
 		raw_spin_lock(&cfs_b->lock);
 		cfs_rq->runtime_enabled = cfs_b->quota != RUNTIME_INF;
 		raw_spin_unlock(&cfs_b->lock);
 	}
+	rcu_read_unlock();
 }
 
+/* cpu offline callback */
 static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq)
 {
-	struct cfs_rq *cfs_rq;
+	struct task_group *tg;
+
+	lockdep_assert_held(&rq->lock);
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(tg, &task_groups, list) {
+		struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)];
 
-	for_each_leaf_cfs_rq(rq, cfs_rq) {
 		if (!cfs_rq->runtime_enabled)
 			continue;
 
@@ -4751,6 +4770,7 @@ static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq)
 		if (cfs_rq_throttled(cfs_rq))
 			unthrottle_cfs_rq(cfs_rq);
 	}
+	rcu_read_unlock();
 }
 
 #else /* CONFIG_CFS_BANDWIDTH */