cpufreq: intel_pstate: Account for non C0 time

The current function to calculate cpu utilization uses the average P-state
ratio (APerf/Mperf) scaled by the ratio of the current P-state to the
max available non-turbo one. This leads to an overestimation of
utilization which causes higher-performance P-states to be selected more
often and that leads to increased energy consumption.

This is a problem for low-power systems, so it is better to use a
different utilization calculation algorithm for them.

Namely, the Percent Busy value (or load) can be estimated as the ratio of the
MPERF counter that runs at a constant rate only during active periods (C0) to
the time stamp counter (TSC) that also runs (at the same rate) during idle.
That is:

Percent Busy = 100 * (delta_mperf / delta_tsc)

Use this algorithm for platforms with SoCs based on the Airmont and Silvermont
Atom cores.

Signed-off-by: Philippe Longepe <philippe.longepe@intel.com>
Signed-off-by: Stephane Gasparini <stephane.gasparini@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index ff58029a56e20f4a26a7ce733e3e7ad49487cfd2..8bfebaeda2dd12b1b741afd4a12471fc1d2b3d58 100644 (file)
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -143,6 +143,7 @@ struct cpu_defaults {
 };
 
 static inline int32_t get_target_pstate_use_performance(struct cpudata *cpu);
+static inline int32_t get_target_pstate_use_cpu_load(struct cpudata *cpu);
 
 static struct pstate_adjust_policy pid_params;
 static struct pstate_funcs pstate_funcs;
@@ -763,7 +764,7 @@ static struct cpu_defaults silvermont_params = {
                .set = atom_set_pstate,
                .get_scaling = silvermont_get_scaling,
                .get_vid = atom_get_vid,
-               .get_target_pstate = get_target_pstate_use_performance,
+               .get_target_pstate = get_target_pstate_use_cpu_load,
        },
 };
 
@@ -784,7 +785,7 @@ static struct cpu_defaults airmont_params = {
                .set = atom_set_pstate,
                .get_scaling = airmont_get_scaling,
                .get_vid = atom_get_vid,
-               .get_target_pstate = get_target_pstate_use_performance,
+               .get_target_pstate = get_target_pstate_use_cpu_load,
        },
 };
 
@@ -890,12 +891,11 @@ static inline void intel_pstate_sample(struct cpudata *cpu)
        local_irq_save(flags);
        rdmsrl(MSR_IA32_APERF, aperf);
        rdmsrl(MSR_IA32_MPERF, mperf);
-       if (cpu->prev_mperf == mperf) {
+       tsc = rdtsc();
+       if ((cpu->prev_mperf == mperf) || (cpu->prev_tsc == tsc)) {
                local_irq_restore(flags);
                return;
        }
-
-       tsc = rdtsc();
        local_irq_restore(flags);
 
        cpu->last_sample_time = cpu->sample.time;
@@ -930,6 +930,25 @@ static inline void intel_pstate_set_sample_time(struct cpudata *cpu)
        mod_timer_pinned(&cpu->timer, jiffies + delay);
 }
 
+static inline int32_t get_target_pstate_use_cpu_load(struct cpudata *cpu)
+{
+       struct sample *sample = &cpu->sample;
+       int32_t cpu_load;
+
+       /*
+        * The load can be estimated as the ratio of the mperf counter
+        * running at a constant frequency during active periods
+        * (C0) and the time stamp counter running at the same frequency
+        * also during C-states.
+        */
+       cpu_load = div64_u64(int_tofp(100) * sample->mperf, sample->tsc);
+
+       cpu->sample.busy_scaled = cpu_load;
+
+       return cpu->pstate.current_pstate - pid_calc(&cpu->pid, cpu_load);
+}
+
+
 static inline int32_t get_target_pstate_use_performance(struct cpudata *cpu)
 {
        int32_t core_busy, max_pstate, current_pstate, sample_ratio;