From f365882108a30dfb1e08c66a2e06a08317ae4305 Mon Sep 17 00:00:00 2001
From: Vincent Guittot <vincent.guittot@linaro.org>
Date: Wed, 6 Feb 2019 17:14:22 +0100
Subject: [PATCH] sched/fair: Fix O(nr_cgroups) in the load balancing path
References: bnc#1156462
Patch-mainline: v5.1
Git-commit: 039ae8bcf7a5f4476f4487e6bf816885fb3fb617
This re-applies the commit reverted here:
commit c40f7d74c741 ("sched/fair: Fix infinite loop in update_blocked_averages() by reverting a9e7f6544b9c")
I.e. now that cfs_rq can be safely removed/added in the list, we can re-apply:
commit a9e7f6544b9c ("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.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
kernel/sched/fair.c | 43 ++++++++++++++++++++++++++++++++++---------
1 file changed, 34 insertions(+), 9 deletions(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index c2c69f732977..b771a0534663 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -391,9 +391,10 @@ 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 *
@@ -491,8 +492,8 @@ 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)
{
@@ -7523,10 +7524,27 @@ static void attach_tasks(struct lb_env *env)
#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;
struct rq_flags rf;
rq_lock_irqsave(rq, &rf);
@@ -7536,7 +7554,7 @@ 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_task(cfs_rq), cfs_rq))
@@ -7546,6 +7564,13 @@ static void update_blocked_averages(int cpu)
se = cfs_rq->tg->se[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);
}
rq_unlock_irqrestore(rq, &rf);
}
@@ -10091,10 +10116,10 @@ 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();
}