diff options
Diffstat (limited to 'drivers/cpufreq/intel_pstate.c')
-rw-r--r-- | drivers/cpufreq/intel_pstate.c | 127 |
1 files changed, 66 insertions, 61 deletions
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 099967302bf..86631cb6f7d 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -32,17 +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) { @@ -58,8 +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 { @@ -70,8 +69,9 @@ struct pstate_data { }; struct vid_data { - int32_t min; - int32_t max; + int min; + int max; + int turbo; int32_t ratio; }; @@ -88,17 +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; }; @@ -130,6 +128,7 @@ static struct pstate_funcs pstate_funcs; struct perf_limits { int no_turbo; + int turbo_disabled; int max_perf_pct; int min_perf_pct; int32_t max_perf; @@ -198,7 +197,7 @@ 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; - + result = result + (1 << (FRAC_BITS-1)); return (signed int)fp_toint(result); } @@ -289,7 +288,10 @@ static ssize_t store_no_turbo(struct kobject *a, struct attribute *b, if (ret != 1) return -EINVAL; limits.no_turbo = clamp_t(int, input, 0 , 1); - + if (limits.turbo_disabled) { + pr_warn("Turbo disabled by BIOS or unavailable on processor\n"); + limits.no_turbo = limits.turbo_disabled; + } return count; } @@ -359,21 +361,21 @@ static int byt_get_min_pstate(void) { u64 value; rdmsrl(BYT_RATIOS, value); - return (value >> 8) & 0xFF; + return (value >> 8) & 0x7F; } static int byt_get_max_pstate(void) { u64 value; rdmsrl(BYT_RATIOS, value); - return (value >> 16) & 0xFF; + return (value >> 16) & 0x7F; } static int byt_get_turbo_pstate(void) { u64 value; rdmsrl(BYT_TURBO_RATIOS, value); - return value & 0x3F; + return value & 0x7F; } static void byt_set_pstate(struct cpudata *cpudata, int pstate) @@ -383,7 +385,7 @@ static void byt_set_pstate(struct cpudata *cpudata, int pstate) u32 vid; val = pstate << 8; - if (limits.no_turbo) + if (limits.no_turbo && !limits.turbo_disabled) val |= (u64)1 << 32; vid_fp = cpudata->vid.min + mul_fp( @@ -393,6 +395,9 @@ static void byt_set_pstate(struct cpudata *cpudata, int pstate) vid_fp = clamp_t(int32_t, vid_fp, cpudata->vid.min, cpudata->vid.max); vid = fp_toint(vid_fp); + if (pstate > cpudata->pstate.max_pstate) + vid = cpudata->vid.turbo; + val |= vid; wrmsrl(MSR_IA32_PERF_CTL, val); @@ -402,6 +407,7 @@ static void byt_get_vid(struct cpudata *cpudata) { u64 value; + rdmsrl(BYT_VIDS, value); cpudata->vid.min = int_tofp((value >> 8) & 0x7f); cpudata->vid.max = int_tofp((value >> 16) & 0x7f); @@ -409,6 +415,9 @@ static void byt_get_vid(struct cpudata *cpudata) cpudata->vid.max - cpudata->vid.min, int_tofp(cpudata->pstate.max_pstate - cpudata->pstate.min_pstate)); + + rdmsrl(BYT_TURBO_VIDS, value); + cpudata->vid.turbo = value & 0x7f; } @@ -443,7 +452,7 @@ static void core_set_pstate(struct cpudata *cpudata, int pstate) u64 val; val = pstate << 8; - if (limits.no_turbo) + if (limits.no_turbo && !limits.turbo_disabled) val |= (u64)1 << 32; wrmsrl_on_cpu(cpudata->cpu, MSR_IA32_PERF_CTL, val); @@ -537,66 +546,54 @@ 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(); if (pstate_funcs.get_vid) pstate_funcs.get_vid(cpu); - - /* - * goto max pstate so we don't slow up boot if we are built-in if we are - * a module we will take care of it during normal operation - */ - intel_pstate_set_pstate(cpu, cpu->pstate.max_pstate); + 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) @@ -610,13 +607,25 @@ 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) @@ -670,38 +679,29 @@ 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); static int intel_pstate_init_cpu(unsigned int cpunum) { - - const struct x86_cpu_id *id; struct cpudata *cpu; - id = x86_match_cpu(intel_pstate_cpu_ids); - if (!id) - return -ENODEV; - all_cpu_data[cpunum] = kzalloc(sizeof(struct cpudata), GFP_KERNEL); if (!all_cpu_data[cpunum]) return -ENOMEM; cpu = all_cpu_data[cpunum]; - intel_pstate_get_cpu_pstates(cpu); - if (!cpu->pstate.current_pstate) { - all_cpu_data[cpunum] = NULL; - kfree(cpu); - return -ENODATA; - } - cpu->cpu = cpunum; + intel_pstate_get_cpu_pstates(cpu); init_timer_deferrable(&cpu->timer); cpu->timer.function = intel_pstate_timer_func; @@ -710,7 +710,6 @@ static int intel_pstate_init_cpu(unsigned int cpunum) cpu->timer.expires = jiffies + HZ/100; intel_pstate_busy_pid_reset(cpu); intel_pstate_sample(cpu); - intel_pstate_set_pstate(cpu, cpu->pstate.max_pstate); add_timer_on(&cpu->timer, cpunum); @@ -745,7 +744,7 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy) limits.min_perf = int_tofp(1); limits.max_perf_pct = 100; limits.max_perf = int_tofp(1); - limits.no_turbo = 0; + limits.no_turbo = limits.turbo_disabled; return 0; } limits.min_perf_pct = (policy->min * 100) / policy->cpuinfo.max_freq; @@ -788,6 +787,7 @@ static int intel_pstate_cpu_init(struct cpufreq_policy *policy) { struct cpudata *cpu; int rc; + u64 misc_en; rc = intel_pstate_init_cpu(policy->cpu); if (rc) @@ -795,8 +795,13 @@ static int intel_pstate_cpu_init(struct cpufreq_policy *policy) cpu = all_cpu_data[policy->cpu]; - if (!limits.no_turbo && - limits.min_perf_pct == 100 && limits.max_perf_pct == 100) + rdmsrl(MSR_IA32_MISC_ENABLE, misc_en); + if (misc_en & MSR_IA32_MISC_ENABLE_TURBO_DISABLE || + cpu->pstate.max_pstate == cpu->pstate.turbo_pstate) { + limits.turbo_disabled = 1; + limits.no_turbo = 1; + } + if (limits.min_perf_pct == 100 && limits.max_perf_pct == 100) policy->policy = CPUFREQ_POLICY_PERFORMANCE; else policy->policy = CPUFREQ_POLICY_POWERSAVE; |