WIP: sched/tune: add sysctl interface to define a boost value

The energy-aware scheduler extension has been designed to exploit an
energy model to support an energy efficient allocation of tasks on available
CPUs. The main goal of the current implementation is to schedule
tasks in such a way to minimise the expected system energy while still
meeting the requirements of tasks in terms of computational demand.
Thus, the current implementation does not allow "to boost" tasks performances,
for example by running them at an higher OPP (or a more capable CPU), even
if that could require a "reasonable" increase in energy consumption.

To support tasks performance boosting, while still operating in energy-aware
mode, the scheduler should to provide a "knob" which allows to tune how
much the system is going to be optimised for energy efficiency vs performances.

This patch is the first of a series which provides a simple sysctl based
interface to define an EAS tuning knob.
For the time being, just one system-wide "boost" tunable is exposed via:
  /proc/sys/kernel/sched_cfs_boost
which can be configured in the range [0..100], to define a percentage
where:
  - 0%   boost requires to operate in "standard" EAS mode by scheduling
         tasks at the minimum capacities required by the workload demand
  - 100% boost requires to push at maximum the task performances,
         "regardless" of the incurred energy consumption

A boost value in between these two boundaries is used to bias the
power/performance trade-off, the higher the boost value the more the
EAS scheduler is biased toward performance boosting instead of energy
efficiency.

Change-Id: I1fb22390aee04e8f1a55a9f30db505d9040ec693
Signed-off-by: Patrick Bellasi <patrick.bellasi@arm.com>

5 files changed, 71 insertions, 0 deletions

diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index c9e4731cf10b..0362ae508e6a 100644
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -77,6 +77,22 @@ extern int sysctl_sched_rt_runtime;
 extern unsigned int sysctl_sched_cfs_bandwidth_slice;
 #endif
 
+#ifdef CONFIG_SCHED_TUNE
+extern unsigned int sysctl_sched_cfs_boost;
+int sysctl_sched_cfs_boost_handler(struct ctl_table *table, int write,
+		void __user *buffer, size_t *length,
+		loff_t *ppos);
+static inline unsigned int get_sysctl_sched_cfs_boost(void)
+{
+	return sysctl_sched_cfs_boost;
+}
+#else
+static inline unsigned int get_sysctl_sched_cfs_boost(void)
+{
+	return 0;
+}
+#endif
+
 #ifdef CONFIG_SCHED_AUTOGROUP
 extern unsigned int sysctl_sched_autogroup_enabled;
 #endif
diff --git a/init/Kconfig b/init/Kconfig
index af09b4fb43d2..1c3b8eb1a2a4 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1220,6 +1220,33 @@ config SCHED_AUTOGROUP
 	  desktop applications.  Task group autogeneration is currently based
 	  upon task session.
 
+config SCHED_TUNE
+	bool "Tasks boosting for energy-aware scheduler (EXPERIMENTAL)"
+	help
+	  This option enable the system-wide support for task boosting.
+	  When this support is enabled a new sysctl interface is exposed to
+	  userspace via:
+	     /proc/sys/kernel/sched_cfs_boost
+	  which allows to set a system-wide boost value in range [0..100].
+
+	  The currently boosting strategy is implemented in such a way that:
+	  - a 0% boost value requires to operate in "standard" EAS mode by
+	    scheduling all tasks at the minimum capacities required by their
+	    workload demand
+	  - a 100% boost value requires to push at maximum the task
+	    performances, "regardless" of the incurred energy consumption
+
+	  A boost value in between these two boundaries is used to bias the
+	  power/performance trade-off, the higher the boost value the more the
+	  EAS scheduler is biased toward performance boosting instead of energy
+	  efficiency.
+
+	  Since this support exposes a single system-wide knob, the specified
+	  boost value is applied to all (CFS) tasks in the system.
+
+	  Only if you are testing a kernel with energy-aware scheduler support,
+	  you might want to say Y here.
+
 config SYSFS_DEPRECATED
 	bool "Enable deprecated sysfs features to support old userspace tools"
 	depends on SYSFS
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index 0eabc9db4c3d..c6a85f813dfd 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -18,5 +18,6 @@ obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o
 obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o
 obj-$(CONFIG_SCHEDSTATS) += stats.o
 obj-$(CONFIG_SCHED_DEBUG) += debug.o
+obj-$(CONFIG_SCHED_TUNE) += tune.o
 obj-$(CONFIG_CGROUP_CPUACCT) += cpuacct.o
 obj-$(CONFIG_CPU_FREQ_GOV_SCHED) += cpufreq_sched.o
diff --git a/kernel/sched/tune.c b/kernel/sched/tune.c
new file mode 100644
index 000000000000..25377e0dd8cf
--- /dev/null
+++ b/kernel/sched/tune.c
@@ -0,0 +1,16 @@
+#include "sched.h"
+
+unsigned int sysctl_sched_cfs_boost __read_mostly = 0;
+
+int
+sysctl_sched_cfs_boost_handler(struct ctl_table *table, int write,
+		void __user *buffer, size_t *lenp,
+		loff_t *ppos)
+{
+	int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+	if (ret || !write)
+		return ret;
+
+	return 0;
+}
+
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 19b62b522158..2b4673ea0749 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -433,6 +433,17 @@ static struct ctl_table kern_table[] = {
 		.extra1		= &one,
 	},
 #endif
+#ifdef CONFIG_SCHED_TUNE
+	{
+		.procname	= "sched_cfs_boost",
+		.data		= &sysctl_sched_cfs_boost,
+		.maxlen		= sizeof(sysctl_sched_cfs_boost),
+		.mode		= 0644,
+		.proc_handler	= &sysctl_sched_cfs_boost_handler,
+		.extra1		= &zero,
+		.extra2		= &one_hundred,
+	},
+#endif
 #ifdef CONFIG_PROVE_LOCKING
 	{
 		.procname	= "prove_locking",