[PATCH v2 1/2] sched/fair: Decrease cfs bandwidth usage in task_group destruction

[Chuyi Zhou]

The static key __cfs_bandwidth_used is used to indicate whether bandwidth
control is enabled in the system. Currently, it is only decreased when a
task group disables bandwidth control. This is incorrect because if there
was a task group in the past that enabled bandwidth control, the
__cfs_bandwidth_used will never go to zero, even if there are no task_group
using bandwidth control now.

This patch tries to fix this issue by decrsasing bandwidth usage in
destroy_cfs_bandwidth(). cfs_bandwidth_usage_dec() calls
static_key_slow_dec_cpuslocked which needs to hold hotplug lock, but cfs
bandwidth destroy maybe run in a rcu callback. Move the call to
destroy_cfs_bandwidth() from unregister_fair_sched_group() to
cpu_cgroup_css_free() which runs in process context.

Signed-off-by: Chuyi Zhou <zhouchuyi@xxxxxxxxxxxxx>
---
 kernel/sched/core.c  |  2 ++
 kernel/sched/fair.c  | 13 +++++++------
 kernel/sched/sched.h |  2 ++
 3 files changed, 11 insertions(+), 6 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 6d35c48239be..7720d34bd71b 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -8816,6 +8816,8 @@ static void cpu_cgroup_css_free(struct cgroup_subsys_state *css)
 {
 	struct task_group *tg = css_tg(css);
 
+	destroy_cfs_bandwidth(tg_cfs_bandwidth(tg));
+
 	/*
 	 * Relies on the RCU grace period between css_released() and this.
 	 */
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index da3cdd86ab2e..c56b6d5b8ed7 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5615,7 +5615,7 @@ void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b)
 	cfs_b->runtime_snap = cfs_b->runtime;
 }
 
-static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg)
+struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg)
 {
 	return &tg->cfs_bandwidth;
 }
@@ -6438,7 +6438,7 @@ void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
 	hrtimer_start_expires(&cfs_b->period_timer, HRTIMER_MODE_ABS_PINNED);
 }
 
-static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
+void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
 {
 	int __maybe_unused i;
 
@@ -6472,6 +6472,9 @@ static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
 		local_irq_restore(flags);
 	}
 #endif
+	guard(cpus_read_lock)();
+	if (cfs_b->quota != RUNTIME_INF)
+		cfs_bandwidth_usage_dec();
 }
 
 /*
@@ -6614,11 +6617,11 @@ void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b, struct cfs_bandwidth *paren
 static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq) {}
 #endif
 
-static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg)
+struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg)
 {
 	return NULL;
 }
-static inline void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b) {}
+void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b) {}
 static inline void update_runtime_enabled(struct rq *rq) {}
 static inline void unthrottle_offline_cfs_rqs(struct rq *rq) {}
 #ifdef CONFIG_CGROUP_SCHED
@@ -12992,8 +12995,6 @@ void unregister_fair_sched_group(struct task_group *tg)
 	struct rq *rq;
 	int cpu;
 
-	destroy_cfs_bandwidth(tg_cfs_bandwidth(tg));
-
 	for_each_possible_cpu(cpu) {
 		if (tg->se[cpu])
 			remove_entity_load_avg(tg->se[cpu]);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 8a071022bdec..d251842867ce 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2938,6 +2938,8 @@ extern void init_dl_rq(struct dl_rq *dl_rq);
 extern void cfs_bandwidth_usage_inc(void);
 extern void cfs_bandwidth_usage_dec(void);
 
+extern struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg);
+extern void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b);
 #ifdef CONFIG_NO_HZ_COMMON
 
 #define NOHZ_BALANCE_KICK_BIT	0
-- 
2.20.1