sched/fair: Use task_groups instead of leaf_cfs_rq_list to walk all cfs_rqs

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>

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index eede181b4530cb74cca4c66b566e27d205673940..c8fa777de76c9630b162a189ce73818c911f7e45 100644 (file)
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4642,24 +4642,43 @@ 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;
 
-       for_each_leaf_cfs_rq(rq, cfs_rq) {
-               struct cfs_bandwidth *cfs_b = &cfs_rq->tg->cfs_bandwidth;
+       lockdep_assert_held(&rq->lock);
+
+       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;
 
@@ -4677,6 +4696,7 @@ 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 */