[RFC/RFT][PATCH 3/4] cpufreq: intel_pstate: Use average P-state in get_target_pstate_default()

[Rafael J. Wysocki]

From: Rafael J. Wysocki 

Adjust the next P-state formula in get_target_pstate_default()
(in the filtered case) to use the average P-state as given by
the APERF and MPERF feedback registers instead of the exact
P-state requested previously, as that request might not be
granted.

Suggested-by: Doug Smythies 
Signed-off-by: Rafael J. Wysocki 
---
 drivers/cpufreq/intel_pstate.c |   18 +-
 1 file changed, 9 insertions(+), 9 deletions(-)

Index: linux-pm/drivers/cpufreq/intel_pstate.c
===
--- linux-pm.orig/drivers/cpufreq/intel_pstate.c
+++ linux-pm/drivers/cpufreq/intel_pstate.c
@@ -98,7 +98,6 @@ static inline u64 div_ext_fp(u64 x, u64
  * @tsc:   Difference of time stamp counter between last and
  * current sample
  * @time:  Current time from scheduler
- * @target:Target P-state
  *
  * This structure is used in the cpudata structure to store performance sample
  * data for choosing next P State.
@@ -110,7 +109,6 @@ struct sample {
u64 mperf;
u64 tsc;
u64 time;
-   int target;
 };
 
 /**
@@ -1149,7 +1147,6 @@ static void intel_pstate_set_min_pstate(
 
trace_cpu_frequency(pstate * cpu->pstate.scaling, cpu->cpu);
cpu->pstate.current_pstate = pstate;
-   cpu->sample.target = pstate;
/*
 * Generally, there is no guarantee that this code will always run on
 * the CPU being updated, so force the register update to run on the
@@ -1305,8 +1302,8 @@ static inline int32_t get_target_pstate_
 {
struct sample *sample = >sample;
int32_t busy_frac, boost;
-   int pstate, max_perf, min_perf;
int64_t target;
+   int pstate;
 
pstate = limits->no_turbo || limits->turbo_disabled ?
cpu->pstate.max_pstate : cpu->pstate.turbo_pstate;
@@ -1341,17 +1338,20 @@ static inline int32_t get_target_pstate_
 * Take the raw gain as 1/8 and compute the effective gain as
 *
 *  iir_gain = 1/8 * delta_t / sampling_interval
+*
+* Moreover, since the output is a request that may or may not
+* be granted (depending on what the other CPUs are doing, for
+* example), instead of using the output value obtained
+* previously in the computation, use the effective average
+* P-state since the last pass as given by APERF and MPERF.
 */
iir_gain = div_fp(sample->time - cpu->last_sample_time,
  pid_params.sample_rate_ns << 3);
if (iir_gain < int_tofp(1))
-   target = sample->target * (int_tofp(1) - iir_gain) +
+   target = get_avg_pstate(cpu) * (int_tofp(1) - iir_gain) 
+
mul_fp(target, iir_gain);
}
-   intel_pstate_get_min_max(cpu, _perf, _perf);
-   target = clamp_val(target, int_tofp(min_perf), int_tofp(max_perf));
-   sample->target = fp_toint(target + (1 << (FRAC_BITS-1)));
-   return sample->target;
+   return fp_toint(target + (1 << (FRAC_BITS-1)));
 }
 
 static inline void intel_pstate_update_pstate(struct cpudata *cpu, int pstate)

[RFC/RFT][PATCH 3/4] cpufreq: intel_pstate: Use average P-state in get_target_pstate_default()

[Rafael J. Wysocki]

From: Rafael J. Wysocki 

Adjust the next P-state formula in get_target_pstate_default()
(in the filtered case) to use the average P-state as given by
the APERF and MPERF feedback registers instead of the exact
P-state requested previously, as that request might not be
granted.

Suggested-by: Doug Smythies 
Signed-off-by: Rafael J. Wysocki 
---
 drivers/cpufreq/intel_pstate.c |   18 +-
 1 file changed, 9 insertions(+), 9 deletions(-)

Index: linux-pm/drivers/cpufreq/intel_pstate.c
===
--- linux-pm.orig/drivers/cpufreq/intel_pstate.c
+++ linux-pm/drivers/cpufreq/intel_pstate.c
@@ -98,7 +98,6 @@ static inline u64 div_ext_fp(u64 x, u64
  * @tsc:   Difference of time stamp counter between last and
  * current sample
  * @time:  Current time from scheduler
- * @target:Target P-state
  *
  * This structure is used in the cpudata structure to store performance sample
  * data for choosing next P State.
@@ -110,7 +109,6 @@ struct sample {
u64 mperf;
u64 tsc;
u64 time;
-   int target;
 };
 
 /**
@@ -1149,7 +1147,6 @@ static void intel_pstate_set_min_pstate(
 
trace_cpu_frequency(pstate * cpu->pstate.scaling, cpu->cpu);
cpu->pstate.current_pstate = pstate;
-   cpu->sample.target = pstate;
/*
 * Generally, there is no guarantee that this code will always run on
 * the CPU being updated, so force the register update to run on the
@@ -1305,8 +1302,8 @@ static inline int32_t get_target_pstate_
 {
struct sample *sample = >sample;
int32_t busy_frac, boost;
-   int pstate, max_perf, min_perf;
int64_t target;
+   int pstate;
 
pstate = limits->no_turbo || limits->turbo_disabled ?
cpu->pstate.max_pstate : cpu->pstate.turbo_pstate;
@@ -1341,17 +1338,20 @@ static inline int32_t get_target_pstate_
 * Take the raw gain as 1/8 and compute the effective gain as
 *
 *  iir_gain = 1/8 * delta_t / sampling_interval
+*
+* Moreover, since the output is a request that may or may not
+* be granted (depending on what the other CPUs are doing, for
+* example), instead of using the output value obtained
+* previously in the computation, use the effective average
+* P-state since the last pass as given by APERF and MPERF.
 */
iir_gain = div_fp(sample->time - cpu->last_sample_time,
  pid_params.sample_rate_ns << 3);
if (iir_gain < int_tofp(1))
-   target = sample->target * (int_tofp(1) - iir_gain) +
+   target = get_avg_pstate(cpu) * (int_tofp(1) - iir_gain) 
+
mul_fp(target, iir_gain);
}
-   intel_pstate_get_min_max(cpu, _perf, _perf);
-   target = clamp_val(target, int_tofp(min_perf), int_tofp(max_perf));
-   sample->target = fp_toint(target + (1 << (FRAC_BITS-1)));
-   return sample->target;
+   return fp_toint(target + (1 << (FRAC_BITS-1)));
 }
 
 static inline void intel_pstate_update_pstate(struct cpudata *cpu, int pstate)