aboutsummaryrefslogtreecommitdiff
path: root/drivers/cpufreq/intel_pstate.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/cpufreq/intel_pstate.c')
-rw-r--r--drivers/cpufreq/intel_pstate.c238
1 files changed, 167 insertions, 71 deletions
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 5f1cbae3696..86631cb6f7d 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -32,14 +32,17 @@
#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 BYT_RATIOS 0x66a
#define FRAC_BITS 8
#define int_tofp(X) ((int64_t)(X) << FRAC_BITS)
#define fp_toint(X) ((X) >> FRAC_BITS)
+
static inline int32_t mul_fp(int32_t x, int32_t y)
{
return ((int64_t)x * (int64_t)y) >> FRAC_BITS;
@@ -55,6 +58,7 @@ struct sample {
u64 aperf;
u64 mperf;
int freq;
+ ktime_t time;
};
struct pstate_data {
@@ -64,6 +68,13 @@ struct pstate_data {
int turbo_pstate;
};
+struct vid_data {
+ int min;
+ int max;
+ int turbo;
+ int32_t ratio;
+};
+
struct _pid {
int setpoint;
int32_t integral;
@@ -77,19 +88,16 @@ struct _pid {
struct cpudata {
int cpu;
- char name[64];
-
struct timer_list timer;
struct pstate_data pstate;
+ struct vid_data vid;
struct _pid pid;
- int min_pstate_count;
-
+ ktime_t last_sample_time;
u64 prev_aperf;
u64 prev_mperf;
- int sample_ptr;
- struct sample samples[SAMPLE_COUNT];
+ struct sample sample;
};
static struct cpudata **all_cpu_data;
@@ -106,7 +114,8 @@ struct pstate_funcs {
int (*get_max)(void);
int (*get_min)(void);
int (*get_turbo)(void);
- void (*set)(int pstate);
+ void (*set)(struct cpudata*, int pstate);
+ void (*get_vid)(struct cpudata *);
};
struct cpu_defaults {
@@ -119,6 +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;
@@ -142,7 +152,7 @@ static inline void pid_reset(struct _pid *pid, int setpoint, int busy,
pid->setpoint = setpoint;
pid->deadband = deadband;
pid->integral = int_tofp(integral);
- pid->last_err = setpoint - busy;
+ pid->last_err = int_tofp(setpoint) - int_tofp(busy);
}
static inline void pid_p_gain_set(struct _pid *pid, int percent)
@@ -187,7 +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);
}
@@ -278,7 +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;
}
@@ -348,16 +361,66 @@ static int byt_get_min_pstate(void)
{
u64 value;
rdmsrl(BYT_RATIOS, value);
- return value & 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 & 0x7F;
+}
+
+static void byt_set_pstate(struct cpudata *cpudata, int pstate)
+{
+ u64 val;
+ int32_t vid_fp;
+ u32 vid;
+
+ val = pstate << 8;
+ if (limits.no_turbo && !limits.turbo_disabled)
+ val |= (u64)1 << 32;
+
+ vid_fp = cpudata->vid.min + mul_fp(
+ int_tofp(pstate - cpudata->pstate.min_pstate),
+ cpudata->vid.ratio);
+
+ 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);
+}
+
+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);
+ cpudata->vid.ratio = div_fp(
+ 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;
}
+
static int core_get_min_pstate(void)
{
u64 value;
@@ -384,15 +447,15 @@ static int core_get_turbo_pstate(void)
return ret;
}
-static void core_set_pstate(int pstate)
+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(MSR_IA32_PERF_CTL, val);
+ wrmsrl_on_cpu(cpudata->cpu, MSR_IA32_PERF_CTL, val);
}
static struct cpu_defaults core_params = {
@@ -424,8 +487,9 @@ static struct cpu_defaults byt_params = {
.funcs = {
.get_max = byt_get_max_pstate,
.get_min = byt_get_min_pstate,
- .get_turbo = byt_get_max_pstate,
- .set = core_set_pstate,
+ .get_turbo = byt_get_turbo_pstate,
+ .set = byt_set_pstate,
+ .get_vid = byt_get_vid,
},
};
@@ -462,7 +526,7 @@ static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate)
cpu->pstate.current_pstate = pstate;
- pstate_funcs.set(pstate);
+ pstate_funcs.set(cpu, pstate);
}
static inline void intel_pstate_pstate_increase(struct cpudata *cpu, int steps)
@@ -482,28 +546,31 @@ 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();
- /*
- * 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);
+ if (pstate_funcs.get_vid)
+ pstate_funcs.get_vid(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)
{
- u64 core_pct;
- core_pct = div64_u64(int_tofp(sample->aperf * 100),
- sample->mperf);
- sample->freq = fp_toint(cpu->pstate.max_pstate * core_pct * 1000);
+ struct sample *sample = &cpu->sample;
+ int64_t core_pct;
+ int32_t rem;
+
+ core_pct = int_tofp(sample->aperf) * int_tofp(100);
+ core_pct = div_u64_rem(core_pct, int_tofp(sample->mperf), &rem);
- sample->core_pct_busy = core_pct;
+ 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 = (int32_t)core_pct;
}
static inline void intel_pstate_sample(struct cpudata *cpu)
@@ -512,13 +579,18 @@ static inline void intel_pstate_sample(struct cpudata *cpu)
rdmsrl(MSR_IA32_APERF, aperf);
rdmsrl(MSR_IA32_MPERF, mperf);
- cpu->sample_ptr = (cpu->sample_ptr + 1) % SAMPLE_COUNT;
- cpu->samples[cpu->sample_ptr].aperf = aperf;
- cpu->samples[cpu->sample_ptr].mperf = mperf;
- cpu->samples[cpu->sample_ptr].aperf -= cpu->prev_aperf;
- cpu->samples[cpu->sample_ptr].mperf -= cpu->prev_mperf;
- intel_pstate_calc_busy(cpu, &cpu->samples[cpu->sample_ptr]);
+ aperf = aperf >> FRAC_BITS;
+ mperf = mperf >> FRAC_BITS;
+
+ cpu->last_sample_time = cpu->sample.time;
+ cpu->sample.time = ktime_get();
+ cpu->sample.aperf = aperf;
+ cpu->sample.mperf = mperf;
+ cpu->sample.aperf -= cpu->prev_aperf;
+ cpu->sample.mperf -= cpu->prev_mperf;
+
+ intel_pstate_calc_busy(cpu);
cpu->prev_aperf = aperf;
cpu->prev_mperf = mperf;
@@ -535,12 +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->samples[cpu->sample_ptr].core_pct_busy;
+ core_busy = cpu->sample.core_pct_busy;
max_pstate = int_tofp(cpu->pstate.max_pstate);
current_pstate = int_tofp(cpu->pstate.current_pstate);
- return mul_fp(core_busy, div_fp(max_pstate, current_pstate));
+ core_busy = mul_fp(core_busy, div_fp(max_pstate, current_pstate));
+
+ 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)
@@ -556,6 +641,7 @@ static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu)
ctl = pid_calc(pid, busy_scaled);
steps = abs(ctl);
+
if (ctl < 0)
intel_pstate_pstate_increase(cpu, steps);
else
@@ -565,23 +651,27 @@ static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu)
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);
- if (cpu->pstate.current_pstate == cpu->pstate.min_pstate) {
- cpu->min_pstate_count++;
- if (!(cpu->min_pstate_count % 5)) {
- intel_pstate_set_pstate(cpu, cpu->pstate.max_pstate);
- }
- } else
- cpu->min_pstate_count = 0;
+ 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);
}
#define ICPU(model, policy) \
- { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)&policy }
+ { X86_VENDOR_INTEL, 6, model, X86_FEATURE_APERFMPERF,\
+ (unsigned long)&policy }
static const struct x86_cpu_id intel_pstate_cpu_ids[] = {
ICPU(0x2a, core_params),
@@ -589,33 +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);
-
cpu->cpu = cpunum;
+ intel_pstate_get_cpu_pstates(cpu);
init_timer_deferrable(&cpu->timer);
cpu->timer.function = intel_pstate_timer_func;
@@ -624,7 +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);
@@ -641,7 +726,7 @@ static unsigned int intel_pstate_get(unsigned int cpu_num)
cpu = all_cpu_data[cpu_num];
if (!cpu)
return 0;
- sample = &cpu->samples[cpu->sample_ptr];
+ sample = &cpu->sample;
return sample->freq;
}
@@ -659,7 +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;
@@ -685,20 +770,24 @@ static int intel_pstate_verify_policy(struct cpufreq_policy *policy)
return 0;
}
-static int intel_pstate_cpu_exit(struct cpufreq_policy *policy)
+static void intel_pstate_stop_cpu(struct cpufreq_policy *policy)
{
- int cpu = policy->cpu;
+ int cpu_num = policy->cpu;
+ struct cpudata *cpu = all_cpu_data[cpu_num];
- del_timer(&all_cpu_data[cpu]->timer);
- kfree(all_cpu_data[cpu]);
- all_cpu_data[cpu] = NULL;
- return 0;
+ pr_info("intel_pstate CPU %d exiting\n", cpu_num);
+
+ del_timer_sync(&all_cpu_data[cpu_num]->timer);
+ intel_pstate_set_pstate(cpu, cpu->pstate.min_pstate);
+ kfree(all_cpu_data[cpu_num]);
+ all_cpu_data[cpu_num] = NULL;
}
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)
@@ -706,8 +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;
@@ -730,7 +824,7 @@ static struct cpufreq_driver intel_pstate_driver = {
.setpolicy = intel_pstate_set_policy,
.get = intel_pstate_get,
.init = intel_pstate_cpu_init,
- .exit = intel_pstate_cpu_exit,
+ .stop_cpu = intel_pstate_stop_cpu,
.name = "intel_pstate",
};
@@ -776,6 +870,7 @@ static void copy_cpu_funcs(struct pstate_funcs *funcs)
pstate_funcs.get_min = funcs->get_min;
pstate_funcs.get_turbo = funcs->get_turbo;
pstate_funcs.set = funcs->set;
+ pstate_funcs.get_vid = funcs->get_vid;
}
#if IS_ENABLED(CONFIG_ACPI)
@@ -884,6 +979,7 @@ static int __init intel_pstate_init(void)
intel_pstate_debug_expose_params();
intel_pstate_sysfs_expose_params();
+
return rc;
out:
get_online_cpus();