sched: Add tunable capacity margin for fis_capacity

Currently, the margin of cpu frequency raising and cpu overutilized are
hard-coded as 25% (1280/1024). Make the margin tunable
to control the aggressive for placement and frequency control. Such as
for power tuning framework could adjust smaller margin to slow down
frequency raising speed and let task stay in smaller cpu.

For light loading scenarios, like beach buggy blitz and messaging apps,
the app threads are moved big core with 25% margin and causing
unnecessary power.
With 0% capacity margin (1024/1024), the app threads could be kept in
little core and deliver better power results without any fps drop.

capacity margin        0%          10%          20%          30%
                     current        current       current      current
                  Fps  (mA)    Fps    (mA)   Fps   (mA)    Fps  (mA)
Beach buggy blitz  60 198.164  60   203.211  60   209.984  60  213.374
Yahoo browser      60 232.301 59.97 237.52  59.95 248.213  60  262.809

Change-Id: Iba48c556ed1b73c9a2699e9e809bc7d9333dc004
Signed-off-by: YT Chang <yt.chang@mediatek.com>

include/linux/sched/cpufreq.h

@@ -23,6 +23,23 @@ void cpufreq_add_update_util_hook(int cpu, struct update_util_data *data,
 void cpufreq_remove_update_util_hook(int cpu);
 bool cpufreq_this_cpu_can_update(struct cpufreq_policy *policy);
 
+#ifdef CONFIG_SMP
+extern unsigned int sysctl_sched_capacity_margin;
+
+static inline unsigned long map_util_freq(unsigned long util,
+					  unsigned long freq, unsigned long cap)
+{
+	freq = freq * util / cap;
+	freq = freq * sysctl_sched_capacity_margin / SCHED_CAPACITY_SCALE;
+
+	return freq;
+}
+
+static inline unsigned long map_util_perf(unsigned long util)
+{
+	return util * sysctl_sched_capacity_margin / SCHED_CAPACITY_SCALE;
+}
+#else
 static inline unsigned long map_util_freq(unsigned long util,
 					unsigned long freq, unsigned long cap)
 {
@@ -33,6 +50,8 @@ static inline unsigned long map_util_perf(unsigned long util)
 {
 	return util + (util >> 2);
 }
+#endif
+
 #endif /* CONFIG_CPU_FREQ */
 
 #endif /* _LINUX_SCHED_CPUFREQ_H */

include/linux/sched/sysctl.h

@@ -10,6 +10,7 @@ struct ctl_table;
 
 #ifdef CONFIG_SMP
 extern unsigned int sysctl_hung_task_all_cpu_backtrace;
+extern unsigned int sysctl_sched_capacity_margin;
 #else
 #define sysctl_hung_task_all_cpu_backtrace 0
 #endif /* CONFIG_SMP */

include/linux/sysctl.h

@@ -41,6 +41,7 @@ struct ctl_dir;
 #define SYSCTL_ZERO	((void *)&sysctl_vals[0])
 #define SYSCTL_ONE	((void *)&sysctl_vals[1])
 #define SYSCTL_INT_MAX	((void *)&sysctl_vals[2])
+#define SCHED_CAPACITY_MARGIN_MIN   1024
 
 extern const int sysctl_vals[];
 

kernel/sched/fair.c

@@ -111,7 +111,9 @@ int __weak arch_asym_cpu_priority(int cpu)
  *
  * (default: ~20%)
  */
-#define fits_capacity(cap, max)	((cap) * 1280 < (max) * 1024)
+unsigned int sysctl_sched_capacity_margin = 1280;
+EXPORT_SYMBOL_GPL(sysctl_sched_capacity_margin);
+#define fits_capacity(cap, max)	((cap) * sysctl_sched_capacity_margin < (max) * 1024)
 
 /*
  * The margin used when comparing CPU capacities.

kernel/sysctl.c

@@ -127,6 +127,11 @@ static int ten_thousand = 10000;
 static int six_hundred_forty_kb = 640 * 1024;
 #endif
 
+/* this is needed for the proc of sysctl_sched_capacity_margin */
+#ifdef CONFIG_SMP
+static int min_sched_capacity_margin = 1024;
+#endif /* CONFIG_SMP */
+
 /* this is needed for the proc_doulongvec_minmax of vm_dirty_bytes */
 static unsigned long dirty_bytes_min = 2 * PAGE_SIZE;
 
@@ -1736,6 +1741,16 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
+#ifdef CONFIG_SMP
+	{
+		.procname	= "sched_capcity_margin",
+		.data		= &sysctl_sched_capacity_margin,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &min_sched_capacity_margin,
+	},
+#endif
 #ifdef CONFIG_SCHEDSTATS
 	{
 		.procname	= "sched_schedstats",