[PATCH v2 14/17] sched/core: Compute steal values at regular intervals

[Shrikanth Hegde]

Kick off the work to compute the steal time at regular interval.
Gated with sched feature STEAL_MONITOR to avoid any overhead in systems
that are not interested in it.

The sampling period can configured at runtime using steal_mon_period.
By default is 1000 milliseconds. i.e. 1 second

This work is done by first online housekeeping CPU only. Hence it won't
need any complicated synchronization.

Signed-off-by: Shrikanth Hegde <sshegde@xxxxxxxxxxxxx>
---
 kernel/sched/core.c  | 27 +++++++++++++++++++++++++++
 kernel/sched/sched.h |  2 ++
 2 files changed, 29 insertions(+)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 8c80600ddd28..1c6fcf1ae4fe 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5694,6 +5694,10 @@ void sched_tick(void)
 		rq->idle_balance = idle_cpu(cpu);
 		sched_balance_trigger(rq);
 	}
+
+	/* This feature works currently on SMT system */
+	if (sched_feat(STEAL_MONITOR) && IS_ENABLED(CONFIG_SCHED_SMT))
+		sched_trigger_steal_computation(cpu);
 }
 
 #ifdef CONFIG_NO_HZ_FULL
@@ -11355,4 +11359,27 @@ void sched_steal_detection_work(struct work_struct *work)
 	now = ktime_get();
 	sm->prev_time = now;
 }
+
+void sched_trigger_steal_computation(int cpu)
+{
+	int first_hk_cpu = cpumask_first_and(housekeeping_cpumask(HK_TYPE_KERNEL_NOISE),
+					     cpu_online_mask);
+	ktime_t now;
+
+	/* Done by first online housekeeping CPU only */
+	if (likely(cpu != first_hk_cpu))
+		return;
+
+	/*
+	 * Since everything is updated by first housekeeping CPU,
+	 * There is no need for complex syncronization.
+	 */
+	now = ktime_get();
+
+	/* Default is once per second */
+	if (likely((now - steal_mon.prev_time) < steal_mon.sampling_period_ms * NSEC_PER_MSEC))
+		return;
+
+	schedule_work_on(first_hk_cpu, &steal_mon.work);
+}
 #endif
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index c0fbfb04eda3..337357e48a83 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -4157,6 +4157,7 @@ static inline bool task_can_run_on_preferred_cpu(struct task_struct *p)
 void sched_push_current_non_preferred_cpu(struct rq *rq);
 void sched_init_steal_monitor(void);
 void sched_steal_detection_work(struct work_struct *work);
+void sched_trigger_steal_computation(int cpu);
 #else
 static inline bool task_can_run_on_preferred_cpu(struct task_struct *p)
 {
@@ -4165,6 +4166,7 @@ static inline bool task_can_run_on_preferred_cpu(struct task_struct *p)
 
 static inline void sched_push_current_non_preferred_cpu(struct rq *rq) { }
 static inline void sched_init_steal_monitor(void) { }
+static inline void sched_trigger_steal_computation(int cpu) { }
 #endif
 
 #endif /* _KERNEL_SCHED_SCHED_H */
-- 
2.47.3