[RFC v3 PATCH 4/7] sched: Unthrottle the throttled tasks

[Bharata B Rao <bharata@linux.vnet.ibm.com>]

sched: Unthrottle the throttled tasks.

From: Bharata B Rao <bharata@linux.vnet.ibm.com>

Refresh runtimes when group's period expires. Unthrottle any
throttled groups at that time. Refreshing runtimes is driven through
a periodic timer.

Signed-off-by: Bharata B Rao <bharata@linux.vnet.ibm.com>
---
 kernel/sched.c      |    3 +++
 kernel/sched_fair.c |   45 ++++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 47 insertions(+), 1 deletions(-)

diff --git a/kernel/sched.c b/kernel/sched.c
index 5d2e5e5..8cccda2 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -1889,6 +1889,8 @@ static inline u64 global_cfs_runtime(void)
 	return RUNTIME_INF;
 }
 
+void do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b);
+
 static inline void cfs_rq_runtime_lock(struct cfs_rq *cfs_rq)
 {
 	spin_lock(&cfs_rq->cfs_runtime_lock);
@@ -1908,6 +1910,7 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
 	struct cfs_bandwidth *cfs_b =
 		container_of(timer, struct cfs_bandwidth, cfs_period_timer);
 
+	do_sched_cfs_period_timer(cfs_b);
 	hrtimer_add_expires_ns(timer, ktime_to_ns(cfs_b->cfs_period));
 	return HRTIMER_RESTART;
 }
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index b83ff7d..557d30d 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -221,6 +221,50 @@ static void sched_cfs_runtime_exceeded(struct sched_entity *se,
 	}
 }
 
+static void enqueue_entity_locked(struct cfs_rq *cfs_rq,
+		struct sched_entity *se, int wakeup);
+
+static void enqueue_throttled_entity(struct rq *rq, struct sched_entity *se)
+{
+	for_each_sched_entity(se) {
+		if (se->on_rq)
+			break;
+		if (cfs_rq_throttled(group_cfs_rq(se)))
+			break;
+		enqueue_entity_locked(cfs_rq_of(se), se, 0);
+	}
+}
+
+/*
+ * Refresh runtimes of all cfs_rqs in this group, i,e.,
+ * refresh runtimes of the representative cfs_rq of this
+ * tg on all cpus. Enqueue any throttled entity back.
+ */
+void do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b)
+{
+	int i;
+	const struct cpumask *span = sched_bw_period_mask();
+	struct task_group *tg = container_of(cfs_b, struct task_group,
+					cfs_bandwidth);
+	unsigned long flags;
+
+	for_each_cpu(i, span) {
+		struct rq *rq = cpu_rq(i);
+		struct cfs_rq *cfs_rq = tg->cfs_rq[i];
+		struct sched_entity *se = tg->se[i];
+
+		spin_lock_irqsave(&rq->lock, flags);
+		cfs_rq_runtime_lock(cfs_rq);
+		cfs_rq->cfs_time = 0;
+		if (cfs_rq_throttled(cfs_rq)) {
+			cfs_rq->cfs_throttled = 0;
+			enqueue_throttled_entity(rq, se);
+		}
+		cfs_rq_runtime_unlock(cfs_rq);
+		spin_unlock_irqrestore(&rq->lock, flags);
+	}
+}
+
 #else
 
 static inline int cfs_rq_throttled(struct cfs_rq *cfs_rq)
@@ -304,7 +348,6 @@ static void sched_cfs_runtime_exceeded(struct sched_entity *se,
 
 #endif	/* CONFIG_FAIR_GROUP_SCHED */
 
-
 /**************************************************************
  * Scheduling class tree data structure manipulation methods:
  */