sched/fair: add tunable to set initial task load

The choice of initial task load upon fork has a large influence
on CPU and OPP selection when scheduler-driven DVFS is in use.
Make this tuneable by adding a new sysctl "sched_initial_task_util".

If the sched governor is not used, the default remains at SCHED_LOAD_SCALE
Otherwise, the value from the sysctl is used. This defaults to 0.

Signed-off-by: "Todd Kjos <tkjos@google.com>"

include/linux/sched/sysctl.h

@@ -41,6 +41,7 @@ extern unsigned int sysctl_sched_wakeup_granularity;
 extern unsigned int sysctl_sched_child_runs_first;
 extern unsigned int sysctl_sched_is_big_little;
 extern unsigned int sysctl_sched_sync_hint_enable;
+extern unsigned int sysctl_sched_initial_task_util;
 extern unsigned int sysctl_sched_cstate_aware;
 
 enum sched_tunable_scaling {

kernel/sched/fair.c

@@ -53,6 +53,7 @@ unsigned int normalized_sysctl_sched_latency = 6000000ULL;
 
 unsigned int sysctl_sched_is_big_little = 0;
 unsigned int sysctl_sched_sync_hint_enable = 1;
+unsigned int sysctl_sched_initial_task_util = 0;
 unsigned int sysctl_sched_cstate_aware = 1;
 
 /*
@@ -687,7 +688,9 @@ void init_entity_runnable_average(struct sched_entity *se)
 	sa->period_contrib = 1023;
 	sa->load_avg = scale_load_down(se->load.weight);
 	sa->load_sum = sa->load_avg * LOAD_AVG_MAX;
-	sa->util_avg = scale_load_down(SCHED_LOAD_SCALE);
+	sa->util_avg =  sched_freq() ?
+		sysctl_sched_initial_task_util :
+		scale_load_down(SCHED_LOAD_SCALE);
 	sa->util_sum = sa->util_avg * LOAD_AVG_MAX;
 	/* when this task enqueue'ed, it will contribute to its cfs_rq's load_avg */
 }

kernel/sysctl.c

@@ -317,6 +317,13 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
+	{
+		.procname	= "sched_initial_task_util",
+		.data		= &sysctl_sched_initial_task_util,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
 	{
 		.procname	= "sched_cstate_aware",
 		.data		= &sysctl_sched_cstate_aware,