[PATCH v2 for-4.12-fixes 1/2] sched/fair: Use task_groups instead of leaf_cfs_rq_list to walk all cfs_rqs

[Tejun Heo]

Currently, rq->leaf_cfs_rq_list is a traversal ordered list of all
live cfs_rqs which have ever been active on the CPU; unfortunately,
this makes update_blocked_averages() O(total number of CPU cgroups)
which isn't scalable at all.

The next patch will make rq->leaf_cfs_rq_list only contain the cfs_rqs
which are currently active.  In preparation, this patch converts users
which need to traverse all cfs_rqs to use task_groups list instead.

task_groups list is protected by its own lock and allows RCU protected
traversal and the order of operations guarantees that all online
cfs_rqs will be visited, but holding rq->lock won't protect against
iterating an already unregistered cfs_rq.  However, the operations of
the two users that get converted - update_runtime_enabled() and
unthrottle_offline_cfs_rqs() - should be safe to perform on already
dead cfs_rqs, so adding rcu read protection around them should be
enough.

Note that print_cfs_stats() is not converted.  The next patch will
change its behavior to print out only active cfs_rqs, which is
intended as there's not much point in printing out idle cfs_rqs.

v2: Dropped strong synchronization around removal and left
    print_cfs_stats() unchanged as suggested by Peterz.

Signed-off-by: Tejun Heo <tj@xxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Mike Galbraith <efault@xxxxxx>
Cc: Paul Turner <pjt@xxxxxxxxxx>
Cc: Chris Mason <clm@xxxxxx>
Cc: stable@xxxxxxxxxxxxxxx
---
Peter,

Updated the patch - pasted in your version and updated the description
accordingly.  Please feel free to use this one or whichever you like.

Based on mainline and stable is cc'd.

Thanks.

 kernel/sched/fair.c |   21 ++++++++++++++++-----
 1 file changed, 16 insertions(+), 5 deletions(-)

--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4644,22 +4644,32 @@ static void destroy_cfs_bandwidth(struct
 
 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();
 }
 
 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 +4687,7 @@ static void __maybe_unused unthrottle_of
 		if (cfs_rq_throttled(cfs_rq))
 			unthrottle_cfs_rq(cfs_rq);
 	}
+	rcu_read_unlock();
 }
 
 #else /* CONFIG_CFS_BANDWIDTH */