Merge back earlier cpufreq material for v4.5.

[deliverable/linux.git] / drivers / cpufreq / intel_pstate.c

diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index ff58029a56e20f4a26a7ce733e3e7ad49487cfd2..cd83d477e32d412394da574e8e02adb6dd7be832 100644 (file)
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -113,6 +113,7 @@ struct cpudata {
        u64     prev_aperf;
        u64     prev_mperf;
        u64     prev_tsc;
+       u64     prev_cummulative_iowait;
        struct sample sample;
 };
 
@@ -143,6 +144,7 @@ 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 +765,7 @@ 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 +786,7 @@ 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 +892,11 @@ 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 +931,42 @@ 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;
+       u64 cummulative_iowait, delta_iowait_us;
+       u64 delta_iowait_mperf;
+       u64 mperf, now;
+       int32_t cpu_load;
+
+       cummulative_iowait = get_cpu_iowait_time_us(cpu->cpu, &now);
+
+       /*
+        * Convert iowait time into number of IO cycles spent at max_freq.
+        * IO is considered as busy only for the cpu_load algorithm. For
+        * performance this is not needed since we always try to reach the
+        * maximum P-State, so we are already boosting the IOs.
+        */
+       delta_iowait_us = cummulative_iowait - cpu->prev_cummulative_iowait;
+       delta_iowait_mperf = div64_u64(delta_iowait_us * cpu->pstate.scaling *
+               cpu->pstate.max_pstate, MSEC_PER_SEC);
+
+       mperf = cpu->sample.mperf + delta_iowait_mperf;
+       cpu->prev_cummulative_iowait = cummulative_iowait;
+
+
+       /*
+        * 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) * 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;
@@ -1125,7 +1162,7 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
                                   limits->max_sysfs_pct);
        limits->max_perf_pct = max(limits->min_policy_pct,
                                   limits->max_perf_pct);
-       limits->max_perf = round_up(limits->max_perf, 8);
+       limits->max_perf = round_up(limits->max_perf, FRAC_BITS);
 
        /* Make sure min_perf_pct <= max_perf_pct */
        limits->min_perf_pct = min(limits->max_perf_pct, limits->min_perf_pct);