1 files changed, 43 insertions, 30 deletions

diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 2ba53f4f6af2..fcb929ec5304 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -49,9 +49,9 @@ static inline int32_t mul_fp(int32_t x, int32_t y)
         return ((int64_t)x * (int64_t)y) >> FRAC_BITS;
 }
 
-static inline int32_t div_fp(int32_t x, int32_t y)
+static inline int32_t div_fp(s64 x, s64 y)
 {
-        return div_s64((int64_t)x << FRAC_BITS, y);
+        return div64_s64((int64_t)x << FRAC_BITS, y);
 }
 
 static inline int ceiling_fp(int32_t x)
@@ -69,6 +69,7 @@ struct sample {
         int32_t core_pct_busy;
         u64 aperf;
         u64 mperf;
+        u64 tsc;
         int freq;
         ktime_t time;
 };
@@ -110,6 +111,7 @@ struct cpudata {
         ktime_t last_sample_time;
         u64     prev_aperf;
         u64     prev_mperf;
+        u64     prev_tsc;
         struct sample sample;
 };
 
@@ -397,7 +399,7 @@ static ssize_t store_no_turbo(struct kobject *a, struct attribute *b,
 
         update_turbo_state();
         if (limits.turbo_disabled) {
-                pr_warn("Turbo disabled by BIOS or unavailable on processor\n");
+                pr_warn("intel_pstate: Turbo disabled by BIOS or unavailable on processor\n");
                 return -EPERM;
         }
 
@@ -485,7 +487,7 @@ static void __init intel_pstate_sysfs_expose_params(void)
 static void intel_pstate_hwp_enable(void)
 {
         hwp_active++;
-        pr_info("intel_pstate HWP enabled\n");
+        pr_info("intel_pstate: HWP enabled\n");
 
         wrmsrl( MSR_PM_ENABLE, 0x1);
 }
@@ -536,7 +538,7 @@ static void byt_set_pstate(struct cpudata *cpudata, int pstate)
 
         val |= vid;
 
-        wrmsrl(MSR_IA32_PERF_CTL, val);
+        wrmsrl_on_cpu(cpudata->cpu, MSR_IA32_PERF_CTL, val);
 }
 
 #define BYT_BCLK_FREQS 5
@@ -679,6 +681,7 @@ static struct cpu_defaults knl_params = {
                 .get_max = core_get_max_pstate,
                 .get_min = core_get_min_pstate,
                 .get_turbo = knl_get_turbo_pstate,
+                .get_scaling = core_get_scaling,
                 .set = core_set_pstate,
         },
 };
@@ -705,19 +708,20 @@ static void intel_pstate_get_min_max(struct cpudata *cpu, int *min, int *max)
         *min = clamp_t(int, min_perf, cpu->pstate.min_pstate, max_perf);
 }
 
-static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate)
+static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate, bool force)
 {
         int max_perf, min_perf;
 
-        update_turbo_state();
-
-        intel_pstate_get_min_max(cpu, &min_perf, &max_perf);
+        if (force) {
+                update_turbo_state();
 
-        pstate = clamp_t(int, pstate, min_perf, max_perf);
+                intel_pstate_get_min_max(cpu, &min_perf, &max_perf);
 
-        if (pstate == cpu->pstate.current_pstate)
-                return;
+                pstate = clamp_t(int, pstate, min_perf, max_perf);
 
+                if (pstate == cpu->pstate.current_pstate)
+                        return;
+        }
         trace_cpu_frequency(pstate * cpu->pstate.scaling, cpu->cpu);
 
         cpu->pstate.current_pstate = pstate;
@@ -734,7 +738,7 @@ static void intel_pstate_get_cpu_pstates(struct cpudata *cpu)
 
         if (pstate_funcs.get_vid)
                 pstate_funcs.get_vid(cpu);
-        intel_pstate_set_pstate(cpu, cpu->pstate.min_pstate);
+        intel_pstate_set_pstate(cpu, cpu->pstate.min_pstate, false);
 }
 
 static inline void intel_pstate_calc_busy(struct cpudata *cpu)
@@ -757,23 +761,28 @@ static inline void intel_pstate_sample(struct cpudata *cpu)
 {
         u64 aperf, mperf;
         unsigned long flags;
+        u64 tsc;
 
         local_irq_save(flags);
         rdmsrl(MSR_IA32_APERF, aperf);
         rdmsrl(MSR_IA32_MPERF, mperf);
+        tsc = native_read_tsc();
         local_irq_restore(flags);
 
         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->prev_aperf = aperf;
         cpu->prev_mperf = mperf;
+        cpu->prev_tsc = tsc;
 }
 
 static inline void intel_hwp_set_sample_time(struct cpudata *cpu)
@@ -795,7 +804,7 @@ 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, sample_ratio;
-        u32 duration_us;
+        s64 duration_us;
         u32 sample_time;
 
         /*
@@ -822,8 +831,8 @@ static inline int32_t intel_pstate_get_scaled_busy(struct cpudata *cpu)
          * to adjust our busyness.
          */
         sample_time = pid_params.sample_rate_ms  * USEC_PER_MSEC;
-        duration_us = (u32) ktime_us_delta(cpu->sample.time,
-                                           cpu->last_sample_time);
+        duration_us = 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));
@@ -838,6 +847,10 @@ static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu)
         int32_t busy_scaled;
         struct _pid *pid;
         signed int ctl;
+        int from;
+        struct sample *sample;
+
+        from = cpu->pstate.current_pstate;
 
         pid = &cpu->pid;
         busy_scaled = intel_pstate_get_scaled_busy(cpu);
@@ -845,7 +858,17 @@ static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu)
         ctl = pid_calc(pid, busy_scaled);
 
         /* Negative values of ctl increase the pstate and vice versa */
-        intel_pstate_set_pstate(cpu, cpu->pstate.current_pstate - ctl);
+        intel_pstate_set_pstate(cpu, cpu->pstate.current_pstate - ctl, true);
+
+        sample = &cpu->sample;
+        trace_pstate_sample(fp_toint(sample->core_pct_busy),
+                fp_toint(busy_scaled),
+                from,
+                cpu->pstate.current_pstate,
+                sample->mperf,
+                sample->aperf,
+                sample->tsc,
+                sample->freq);
 }
 
 static void intel_hwp_timer_func(unsigned long __data)
@@ -859,21 +882,11 @@ static void intel_hwp_timer_func(unsigned long __data)
 static void intel_pstate_timer_func(unsigned long __data)
 {
         struct cpudata *cpu = (struct cpudata *) __data;
-        struct sample *sample;
 
         intel_pstate_sample(cpu);
 
-        sample = &cpu->sample;
-
         intel_pstate_adjust_busy_pstate(cpu);
 
-        trace_pstate_sample(fp_toint(sample->core_pct_busy),
-                        fp_toint(intel_pstate_get_scaled_busy(cpu)),
-                        cpu->pstate.current_pstate,
-                        sample->mperf,
-                        sample->aperf,
-                        sample->freq);
-
         intel_pstate_set_sample_time(cpu);
 }
 
@@ -936,7 +949,7 @@ static int intel_pstate_init_cpu(unsigned int cpunum)
 
         add_timer_on(&cpu->timer, cpunum);
 
-        pr_debug("Intel pstate controlling: cpu %d\n", cpunum);
+        pr_debug("intel_pstate: controlling: cpu %d\n", cpunum);
 
         return 0;
 }
@@ -1002,13 +1015,13 @@ static void intel_pstate_stop_cpu(struct cpufreq_policy *policy)
         int cpu_num = policy->cpu;
         struct cpudata *cpu = all_cpu_data[cpu_num];
 
-        pr_info("intel_pstate CPU %d exiting\n", cpu_num);
+        pr_debug("intel_pstate: CPU %d exiting\n", cpu_num);
 
         del_timer_sync(&all_cpu_data[cpu_num]->timer);
         if (hwp_active)
                 return;
 
-        intel_pstate_set_pstate(cpu, cpu->pstate.min_pstate);
+        intel_pstate_set_pstate(cpu, cpu->pstate.min_pstate, false);
 }
 
 static int intel_pstate_cpu_init(struct cpufreq_policy *policy)