cpufreq: schedutil: Use policy-dependent transition delays

Make the schedutil governor take the initial (default) value of the
rate_limit_us sysfs attribute from the (new) transition_delay_us
policy parameter (to be set by the scaling driver).

That will allow scaling drivers to make schedutil use smaller default
values of rate_limit_us and reduce the default average time interval
between consecutive frequency changes.

Make intel_pstate set transition_delay_us to 500.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>

3 files changed, 19 insertions, 5 deletions

diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index c31b72b16c2b..b7de5bd76a31 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -41,6 +41,7 @@
 #define INTEL_PSTATE_HWP_SAMPLING_INTERVAL      (50 * NSEC_PER_MSEC)
 
 #define INTEL_CPUFREQ_TRANSITION_LATENCY        20000
+#define INTEL_CPUFREQ_TRANSITION_DELAY          500
 
 #ifdef CONFIG_ACPI
 #include <acpi/processor.h>
@@ -2237,6 +2238,7 @@ static int intel_cpufreq_cpu_init(struct cpufreq_policy *policy)
                 return ret;
 
         policy->cpuinfo.transition_latency = INTEL_CPUFREQ_TRANSITION_LATENCY;
+        policy->transition_delay_us = INTEL_CPUFREQ_TRANSITION_DELAY;
         /* This reflects the intel_pstate_get_cpu_pstates() setting. */
         policy->cur = policy->cpuinfo.min_freq;
 
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 87165f06a307..a5ce0bbeadb5 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -120,6 +120,13 @@ struct cpufreq_policy {
         bool                    fast_switch_possible;
         bool                    fast_switch_enabled;
 
+        /*
+         * Preferred average time interval between consecutive invocations of
+         * the driver to set the frequency for this policy.  To be set by the
+         * scaling driver (0, which is the default, means no preference).
+         */
+        unsigned int            transition_delay_us;
+
          /* Cached frequency lookup from cpufreq_driver_resolve_freq. */
         unsigned int cached_target_freq;
         int cached_resolved_idx;
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index b1fedf9932d6..76877a62b5fa 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -494,7 +494,6 @@ static int sugov_init(struct cpufreq_policy *policy)
 {
         struct sugov_policy *sg_policy;
         struct sugov_tunables *tunables;
-        unsigned int lat;
         int ret = 0;
 
         /* State should be equivalent to EXIT */
@@ -533,10 +532,16 @@ static int sugov_init(struct cpufreq_policy *policy)
                 goto stop_kthread;
         }
 
-        tunables->rate_limit_us = LATENCY_MULTIPLIER;
-        lat = policy->cpuinfo.transition_latency / NSEC_PER_USEC;
-        if (lat)
-                tunables->rate_limit_us *= lat;
+        if (policy->transition_delay_us) {
+                tunables->rate_limit_us = policy->transition_delay_us;
+        } else {
+                unsigned int lat;
+
+                tunables->rate_limit_us = LATENCY_MULTIPLIER;
+                lat = policy->cpuinfo.transition_latency / NSEC_PER_USEC;
+                if (lat)
+                        tunables->rate_limit_us *= lat;
+        }
 
         policy->governor_data = sg_policy;
         sg_policy->tunables = tunables;