1 files changed, 37 insertions, 30 deletions

diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index eab8ccfe6beb..aebd4572eb6d 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -32,18 +32,16 @@
 #include <asm/msr.h>
 #include <asm/cpu_device_id.h>
 
-#define SAMPLE_COUNT            3
-
 #define BYT_RATIOS              0x66a
 #define BYT_VIDS                0x66b
 #define BYT_TURBO_RATIOS        0x66c
 #define BYT_TURBO_VIDS          0x66d
 
 
-#define FRAC_BITS 6
+#define FRAC_BITS 8
 #define int_tofp(X) ((int64_t)(X) << FRAC_BITS)
 #define fp_toint(X) ((X) >> FRAC_BITS)
-#define FP_ROUNDUP(X) ((X) += 1 << FRAC_BITS)
+
 
 static inline int32_t mul_fp(int32_t x, int32_t y)
 {
@@ -59,8 +57,8 @@ struct sample {
         int32_t core_pct_busy;
         u64 aperf;
         u64 mperf;
-        unsigned long long tsc;
         int freq;
+        ktime_t time;
 };
 
 struct pstate_data {
@@ -90,17 +88,15 @@ struct _pid {
 struct cpudata {
         int cpu;
 
-        char name[64];
-
         struct timer_list timer;
 
         struct pstate_data pstate;
         struct vid_data vid;
         struct _pid pid;
 
+        ktime_t last_sample_time;
         u64     prev_aperf;
         u64     prev_mperf;
-        unsigned long long prev_tsc;
         struct sample sample;
 };
 
@@ -200,7 +196,10 @@ static signed int pid_calc(struct _pid *pid, int32_t busy)
         pid->last_err = fp_error;
 
         result = pterm + mul_fp(pid->integral, pid->i_gain) + dterm;
-
+        if (result >= 0)
+                result = result + (1 << (FRAC_BITS-1));
+        else
+                result = result - (1 << (FRAC_BITS-1));
         return (signed int)fp_toint(result);
 }
 
@@ -546,8 +545,6 @@ static inline void intel_pstate_pstate_decrease(struct cpudata *cpu, int steps)
 
 static void intel_pstate_get_cpu_pstates(struct cpudata *cpu)
 {
-        sprintf(cpu->name, "Intel 2nd generation core");
-
         cpu->pstate.min_pstate = pstate_funcs.get_min();
         cpu->pstate.max_pstate = pstate_funcs.get_max();
         cpu->pstate.turbo_pstate = pstate_funcs.get_turbo();
@@ -557,50 +554,45 @@ static void intel_pstate_get_cpu_pstates(struct cpudata *cpu)
         intel_pstate_set_pstate(cpu, cpu->pstate.min_pstate);
 }
 
-static inline void intel_pstate_calc_busy(struct cpudata *cpu,
-                                        struct sample *sample)
+static inline void intel_pstate_calc_busy(struct cpudata *cpu)
 {
-        int32_t core_pct;
-        int32_t c0_pct;
+        struct sample *sample = &cpu->sample;
+        int64_t core_pct;
+        int32_t rem;
 
-        core_pct = div_fp(int_tofp((sample->aperf)),
-                        int_tofp((sample->mperf)));
-        core_pct = mul_fp(core_pct, int_tofp(100));
-        FP_ROUNDUP(core_pct);
+        core_pct = int_tofp(sample->aperf) * int_tofp(100);
+        core_pct = div_u64_rem(core_pct, int_tofp(sample->mperf), &rem);
 
-        c0_pct = div_fp(int_tofp(sample->mperf), int_tofp(sample->tsc));
+        if ((rem << 1) >= int_tofp(sample->mperf))
+                core_pct += 1;
 
         sample->freq = fp_toint(
                 mul_fp(int_tofp(cpu->pstate.max_pstate * 1000), core_pct));
 
-        sample->core_pct_busy = mul_fp(core_pct, c0_pct);
+        sample->core_pct_busy = (int32_t)core_pct;
 }
 
 static inline void intel_pstate_sample(struct cpudata *cpu)
 {
         u64 aperf, mperf;
-        unsigned long long tsc;
 
         rdmsrl(MSR_IA32_APERF, aperf);
         rdmsrl(MSR_IA32_MPERF, mperf);
-        tsc = native_read_tsc();
 
         aperf = aperf >> FRAC_BITS;
         mperf = mperf >> FRAC_BITS;
-        tsc = tsc >> FRAC_BITS;
 
+        cpu->last_sample_time = cpu->sample.time;
+        cpu->sample.time = ktime_get();
         cpu->sample.aperf = aperf;
         cpu->sample.mperf = mperf;
-        cpu->sample.tsc = tsc;
         cpu->sample.aperf -= cpu->prev_aperf;
         cpu->sample.mperf -= cpu->prev_mperf;
-        cpu->sample.tsc -= cpu->prev_tsc;
 
-        intel_pstate_calc_busy(cpu, &cpu->sample);
+        intel_pstate_calc_busy(cpu);
 
         cpu->prev_aperf = aperf;
         cpu->prev_mperf = mperf;
-        cpu->prev_tsc = tsc;
 }
 
 static inline void intel_pstate_set_sample_time(struct cpudata *cpu)
@@ -614,13 +606,25 @@ static inline void intel_pstate_set_sample_time(struct cpudata *cpu)
 
 static inline int32_t intel_pstate_get_scaled_busy(struct cpudata *cpu)
 {
-        int32_t core_busy, max_pstate, current_pstate;
+        int32_t core_busy, max_pstate, current_pstate, sample_ratio;
+        u32 duration_us;
+        u32 sample_time;
 
         core_busy = cpu->sample.core_pct_busy;
         max_pstate = int_tofp(cpu->pstate.max_pstate);
         current_pstate = int_tofp(cpu->pstate.current_pstate);
         core_busy = mul_fp(core_busy, div_fp(max_pstate, current_pstate));
-        return FP_ROUNDUP(core_busy);
+
+        sample_time = (pid_params.sample_rate_ms  * USEC_PER_MSEC);
+        duration_us = (u32) ktime_us_delta(cpu->sample.time,
+                                        cpu->last_sample_time);
+        if (duration_us > sample_time * 3) {
+                sample_ratio = div_fp(int_tofp(sample_time),
+                                int_tofp(duration_us));
+                core_busy = mul_fp(core_busy, sample_ratio);
+        }
+
+        return core_busy;
 }
 
 static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu)
@@ -674,10 +678,13 @@ static const struct x86_cpu_id intel_pstate_cpu_ids[] = {
         ICPU(0x37, byt_params),
         ICPU(0x3a, core_params),
         ICPU(0x3c, core_params),
+        ICPU(0x3d, core_params),
         ICPU(0x3e, core_params),
         ICPU(0x3f, core_params),
         ICPU(0x45, core_params),
         ICPU(0x46, core_params),
+        ICPU(0x4f, core_params),
+        ICPU(0x56, core_params),
         {}
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_pstate_cpu_ids);