[Patch v6 1/7] sched/pelt.c: Add support to track thermal pressure

[Thara Gopinath]

Extrapolating on the existing framework to track rt/dl utilization using
pelt signals, add a similar mechanism to track thermal pressure. The
difference here from rt/dl utilization tracking is that, instead of
tracking time spent by a cpu running a rt/dl task through util_avg, the
average thermal pressure is tracked through load_avg. This is because
thermal pressure signal is weighted "delta" capacity and is not
binary(util_avg is binary). "delta capacity" here means delta between the
actual capacity of a cpu and the decreased capacity a cpu due to a thermal
event.

In order to track average thermal pressure, a new sched_avg variable
avg_thermal is introduced. Function update_thermal_load_avg can be called
to do the periodic bookkeeping (accumulate, decay and average) of the
thermal pressure.

Signed-off-by: Thara Gopinath <thara.gopinath@xxxxxxxxxx>
Reviewed-by: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
---

v5->v6:
	- added trace support for thermal pressure pelt signal.

 include/trace/events/sched.h |  4 ++++
 kernel/sched/pelt.c          | 22 ++++++++++++++++++++++
 kernel/sched/pelt.h          |  7 +++++++
 kernel/sched/sched.h         |  1 +
 4 files changed, 34 insertions(+)

diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 420e80e..a8fb667 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -613,6 +613,10 @@ DECLARE_TRACE(pelt_dl_tp,
 	TP_PROTO(struct rq *rq),
 	TP_ARGS(rq));
 
+DECLARE_TRACE(pelt_thermal_tp,
+	TP_PROTO(struct rq *rq),
+	TP_ARGS(rq));
+
 DECLARE_TRACE(pelt_irq_tp,
 	TP_PROTO(struct rq *rq),
 	TP_ARGS(rq));
diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c
index a96db50..9aac3b7 100644
--- a/kernel/sched/pelt.c
+++ b/kernel/sched/pelt.c
@@ -353,6 +353,28 @@ int update_dl_rq_load_avg(u64 now, struct rq *rq, int running)
 	return 0;
 }
 
+/*
+ * thermal:
+ *
+ *   load_sum = \Sum se->avg.load_sum
+ *
+ *   util_avg and runnable_load_avg are not supported and meaningless.
+ *
+ */
+int update_thermal_load_avg(u64 now, struct rq *rq, u64 capacity)
+{
+	if (___update_load_sum(now, &rq->avg_thermal,
+			       capacity,
+			       capacity,
+			       capacity)) {
+		___update_load_avg(&rq->avg_thermal, 1, 1);
+		trace_pelt_thermal_tp(rq);
+		return 1;
+	}
+
+	return 0;
+}
+
 #ifdef CONFIG_HAVE_SCHED_AVG_IRQ
 /*
  * irq:
diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h
index afff644..c74226d 100644
--- a/kernel/sched/pelt.h
+++ b/kernel/sched/pelt.h
@@ -6,6 +6,7 @@ int __update_load_avg_se(u64 now, struct cfs_rq *cfs_rq, struct sched_entity *se
 int __update_load_avg_cfs_rq(u64 now, struct cfs_rq *cfs_rq);
 int update_rt_rq_load_avg(u64 now, struct rq *rq, int running);
 int update_dl_rq_load_avg(u64 now, struct rq *rq, int running);
+int update_thermal_load_avg(u64 now, struct rq *rq, u64 capacity);
 
 #ifdef CONFIG_HAVE_SCHED_AVG_IRQ
 int update_irq_load_avg(struct rq *rq, u64 running);
@@ -159,6 +160,12 @@ update_dl_rq_load_avg(u64 now, struct rq *rq, int running)
 }
 
 static inline int
+update_thermal_load_avg(u64 now, struct rq *rq, u64 capacity)
+{
+	return 0;
+}
+
+static inline int
 update_irq_load_avg(struct rq *rq, u64 running)
 {
 	return 0;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 280a3c7..37bd7ef 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -944,6 +944,7 @@ struct rq {
 #ifdef CONFIG_HAVE_SCHED_AVG_IRQ
 	struct sched_avg	avg_irq;
 #endif
+	struct sched_avg	avg_thermal;
 	u64			idle_stamp;
 	u64			avg_idle;
 
-- 
2.1.4