[PATCH] Sched/fair: Block nohz tick_stop when cfs bandwidth in use

[Phil Auld <pauld@redhat.com>]

CFS bandwidth limits and NOHZ full don't play well together.  Tasks
can easily run well past their quotas before a remote tick does
accounting.  This leads to long, multi-period stalls before such
tasks can run again. Currentlyi, when presented with these conflicting
requirements the scheduler is favoring nohz_full and letting the tick
be stopped. However, nohz tick stopping is already best-effort, there
are a number of conditions that can prevent it, whereas cfs runtime
bandwidth is expected to be enforced.

Make the scheduler favor bandwidth over stopping the tick by setting
TICK_DEP_BIT_SCHED when the only running task is a cfs task with
runtime limit enabled.

Add sched_feat HZ_BW (off by default) to control this behavior.

Signed-off-by: Phil Auld <pauld@redhat.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Valentin Schneider <vschneid@redhat.com>
Cc: Ben Segall <bsegall@google.com>
---
 kernel/sched/fair.c     | 33 ++++++++++++++++++++++++++++++++-
 kernel/sched/features.h |  2 ++
 2 files changed, 34 insertions(+), 1 deletion(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 373ff5f55884..880eadfac330 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6139,6 +6139,33 @@ static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq)
 	rcu_read_unlock();
 }
 
+#ifdef CONFIG_NO_HZ_FULL
+/* called from pick_next_task_fair() */
+static void sched_fair_update_stop_tick(struct rq *rq, struct task_struct *p)
+{
+	struct cfs_rq *cfs_rq = task_cfs_rq(p);
+	int cpu = cpu_of(rq);
+
+	if (!sched_feat(HZ_BW) || !cfs_bandwidth_used())
+		return;
+
+	if (!tick_nohz_full_cpu(cpu))
+		return;
+
+	if (rq->nr_running != 1 || !sched_can_stop_tick(rq))
+		return;
+
+	/*
+	 *  We know there is only one task runnable and we've just picked it. The
+	 *  normal enqueue path will have cleared TICK_DEP_BIT_SCHED if we will
+	 *  be otherwise able to stop the tick. Just need to check if we are using
+	 *  bandwidth control.
+	 */
+	if (cfs_rq->runtime_enabled)
+		tick_nohz_dep_set_cpu(cpu, TICK_DEP_BIT_SCHED);
+}
+#endif
+
 #else /* CONFIG_CFS_BANDWIDTH */
 
 static inline bool cfs_bandwidth_used(void)
@@ -6181,9 +6208,12 @@ static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg)
 static inline 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) {}
-
 #endif /* CONFIG_CFS_BANDWIDTH */
 
+#if !defined(CONFIG_CFS_BANDWIDTH) || !defined(CONFIG_NO_HZ_FULL)
+static inline void sched_fair_update_stop_tick(struct rq *rq, struct task_struct *p) {}
+#endif
+
 /**************************************************
  * CFS operations on tasks:
  */
@@ -8097,6 +8127,7 @@ done: __maybe_unused;
 		hrtick_start_fair(rq, p);
 
 	update_misfit_status(p, rq);
+	sched_fair_update_stop_tick(rq, p);
 
 	return p;
 
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index ee7f23c76bd3..6fdf1fdf6b17 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -101,3 +101,5 @@ SCHED_FEAT(LATENCY_WARN, false)
 
 SCHED_FEAT(ALT_PERIOD, true)
 SCHED_FEAT(BASE_SLICE, true)
+
+SCHED_FEAT(HZ_BW, false)
-- 
2.31.1