[Patch v9 1/8] sched/pelt: 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>
---

v6->v7:
	- Added CONFIG_HAVE_SCHED_THERMAL_PRESSURE to stub out
	  update_thermal_load_avg in unsupported architectures as per
	  review comments from Peter, Dietmar and Quentin.
	- Updated comment for update_thermal_load_avg as per review
	  comments from Peter and Dietmar.
v7->v8:
	- Fixed typo in defining update_thermal_load_avg which was
	  causing build errors (reported by kbuild test report)
v8->v9:
	- Defined thermal_load_avg to read rq->avg_thermal.load_avg and
	  avoid cacheline miss in unsupported cases as per Peter's
          suggestion.

 include/trace/events/sched.h |  4 ++++
 init/Kconfig                 |  4 ++++
 kernel/sched/pelt.c          | 31 +++++++++++++++++++++++++++++++
 kernel/sched/pelt.h          | 31 +++++++++++++++++++++++++++++++
 kernel/sched/sched.h         |  3 +++
 5 files changed, 73 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/init/Kconfig b/init/Kconfig
index bd9f1fd..055c3bf 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -463,6 +463,10 @@ config HAVE_SCHED_AVG_IRQ
 	depends on IRQ_TIME_ACCOUNTING || PARAVIRT_TIME_ACCOUNTING
 	depends on SMP
 
+config HAVE_SCHED_THERMAL_PRESSURE
+	bool "Enable periodic averaging of thermal pressure"
+	depends on SMP
+
 config BSD_PROCESS_ACCT
 	bool "BSD Process Accounting"
 	depends on MULTIUSER
diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c
index bd006b7..5d1fbf0 100644
--- a/kernel/sched/pelt.c
+++ b/kernel/sched/pelt.c
@@ -367,6 +367,37 @@ int update_dl_rq_load_avg(u64 now, struct rq *rq, int running)
 	return 0;
 }
 
+#ifdef CONFIG_HAVE_SCHED_THERMAL_PRESSURE
+/*
+ * thermal:
+ *
+ *   load_sum = \Sum se->avg.load_sum but se->avg.load_sum is not tracked
+ *
+ *   util_avg and runnable_load_avg are not supported and meaningless.
+ *
+ * Unlike rt/dl utilization tracking that track 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.
+ */
+
+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;
+}
+#endif
+
 #ifdef CONFIG_HAVE_SCHED_AVG_IRQ
 /*
  * irq:
diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h
index afff644..916979a 100644
--- a/kernel/sched/pelt.h
+++ b/kernel/sched/pelt.h
@@ -7,6 +7,26 @@ 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);
 
+#ifdef CONFIG_HAVE_SCHED_THERMAL_PRESSURE
+int update_thermal_load_avg(u64 now, struct rq *rq, u64 capacity);
+
+static inline u64 thermal_load_avg(struct rq *rq)
+{
+	return READ_ONCE(rq->avg_thermal.load_avg);
+}
+#else
+static inline int
+update_thermal_load_avg(u64 now, struct rq *rq, u64 capacity)
+{
+	return 0;
+}
+
+static inline u64 thermal_load_avg(struct rq *rq)
+{
+	return 0;
+}
+#endif
+
 #ifdef CONFIG_HAVE_SCHED_AVG_IRQ
 int update_irq_load_avg(struct rq *rq, u64 running);
 #else
@@ -159,6 +179,17 @@ 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 u64 thermal_load_avg(struct rq *rq)
+{
+	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 1a88dc8..1f256cb 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -944,6 +944,9 @@ struct rq {
 #ifdef CONFIG_HAVE_SCHED_AVG_IRQ
 	struct sched_avg	avg_irq;
 #endif
+#ifdef CONFIG_HAVE_SCHED_THERMAL_PRESSURE
+	struct sched_avg	avg_thermal;
+#endif
 	u64			idle_stamp;
 	u64			avg_idle;
 
-- 
2.1.4