sched/fair: Fix O(nr_cgroups) in the load balancing path

This re-applies the commit reverted here:

  commit c40f7d74 ("sched/fair: Fix infinite loop in update_blocked_averages() by reverting a9e7f654")

I.e. now that cfs_rq can be safely removed/added in the list, we can re-apply:

 commit a9e7f654 ("sched/fair: Fix O(nr_cgroups) in load balance path")
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: sargun@sargun.me
Cc: tj@kernel.org
Cc: xiexiuqi@huawei.com
Cc: xiezhipeng1@huawei.com
Link: https://lkml.kernel.org/r/1549469662-13614-3-git-send-email-vincent.guittot@linaro.orgSigned-off-by: Ingo Molnar <mingo@kernel.org>

kernel/sched/fair.c

@@ -368,9 +368,10 @@ static inline void assert_list_leaf_cfs_rq(struct rq *rq)
 	SCHED_WARN_ON(rq->tmp_alone_branch != &rq->leaf_cfs_rq_list);
 }
 
-/* Iterate through all cfs_rq's on a runqueue in bottom-up order */
-#define for_each_leaf_cfs_rq(rq, cfs_rq) \
-	list_for_each_entry_rcu(cfs_rq, &rq->leaf_cfs_rq_list, leaf_cfs_rq_list)
+/* Iterate thr' all leaf cfs_rq's on a runqueue */
+#define for_each_leaf_cfs_rq_safe(rq, cfs_rq, pos)			\
+	list_for_each_entry_safe(cfs_rq, pos, &rq->leaf_cfs_rq_list,	\
+				 leaf_cfs_rq_list)
 
 /* Do the two (enqueued) entities belong to the same group ? */
 static inline struct cfs_rq *
@@ -461,8 +462,8 @@ static inline void assert_list_leaf_cfs_rq(struct rq *rq)
 {
 }
 
-#define for_each_leaf_cfs_rq(rq, cfs_rq)	\
-		for (cfs_rq = &rq->cfs; cfs_rq; cfs_rq = NULL)
+#define for_each_leaf_cfs_rq_safe(rq, cfs_rq, pos)	\
+		for (cfs_rq = &rq->cfs, pos = NULL; cfs_rq; cfs_rq = pos)
 
 static inline struct sched_entity *parent_entity(struct sched_entity *se)
 {
@@ -7702,10 +7703,27 @@ static inline bool others_have_blocked(struct rq *rq)
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 
+static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq)
+{
+	if (cfs_rq->load.weight)
+		return false;
+
+	if (cfs_rq->avg.load_sum)
+		return false;
+
+	if (cfs_rq->avg.util_sum)
+		return false;
+
+	if (cfs_rq->avg.runnable_load_sum)
+		return false;
+
+	return true;
+}
+
 static void update_blocked_averages(int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
-	struct cfs_rq *cfs_rq;
+	struct cfs_rq *cfs_rq, *pos;
 	const struct sched_class *curr_class;
 	struct rq_flags rf;
 	bool done = true;
@@ -7717,7 +7735,7 @@ static void update_blocked_averages(int cpu)
 	 * Iterates the task_group tree in a bottom up fashion, see
 	 * list_add_leaf_cfs_rq() for details.
 	 */
-	for_each_leaf_cfs_rq(rq, cfs_rq) {
+	for_each_leaf_cfs_rq_safe(rq, cfs_rq, pos) {
 		struct sched_entity *se;
 
 		if (update_cfs_rq_load_avg(cfs_rq_clock_pelt(cfs_rq), cfs_rq))
@@ -7728,6 +7746,13 @@ static void update_blocked_averages(int cpu)
 		if (se && !skip_blocked_update(se))
 			update_load_avg(cfs_rq_of(se), se, 0);
 
+		/*
+		 * There can be a lot of idle CPU cgroups.  Don't let fully
+		 * decayed cfs_rqs linger on the list.
+		 */
+		if (cfs_rq_is_decayed(cfs_rq))
+			list_del_leaf_cfs_rq(cfs_rq);
+
 		/* Don't need periodic decay once load/util_avg are null */
 		if (cfs_rq_has_blocked(cfs_rq))
 			done = false;
@@ -10609,10 +10634,10 @@ const struct sched_class fair_sched_class = {
 #ifdef CONFIG_SCHED_DEBUG
 void print_cfs_stats(struct seq_file *m, int cpu)
 {
-	struct cfs_rq *cfs_rq;
+	struct cfs_rq *cfs_rq, *pos;
 
 	rcu_read_lock();
-	for_each_leaf_cfs_rq(cpu_rq(cpu), cfs_rq)
+	for_each_leaf_cfs_rq_safe(cpu_rq(cpu), cfs_rq, pos)
 		print_cfs_rq(m, cpu, cfs_rq);
 	rcu_read_unlock();
 }