From be49e3465f222b4b796be8a21d14afbfd8f5d20f Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Wed, 2 Oct 2013 14:13:19 +0530 Subject: cpufreq: add new routine cpufreq_verify_within_cpu_limits() Most of the users of cpufreq_verify_within_limits() calls it for limiting with min/max from policy->cpuinfo. We can make that code simple by introducing another routine which will do this for them automatically. This patch adds another routine cpufreq_verify_within_cpu_limits() and updates others to use it. Signed-off-by: Viresh Kumar Acked-by: Dirk Brandewie Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/intel_pstate.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'drivers/cpufreq/intel_pstate.c') diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 9733f29ed148..a02bd77cbfe8 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -611,9 +611,7 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy) static int intel_pstate_verify_policy(struct cpufreq_policy *policy) { - cpufreq_verify_within_limits(policy, - policy->cpuinfo.min_freq, - policy->cpuinfo.max_freq); + cpufreq_verify_within_cpu_limits(policy); if ((policy->policy != CPUFREQ_POLICY_POWERSAVE) && (policy->policy != CPUFREQ_POLICY_PERFORMANCE)) -- cgit v1.2.3 From 52e0a509e5d6f902ec26bc2a8bb02b137dc453be Mon Sep 17 00:00:00 2001 From: Dirk Brandewie Date: Tue, 15 Oct 2013 11:06:14 -0700 Subject: cpufreq / intel_pstate: Fix max_perf_pct on resume If the system is suspended while max_perf_pct is less than 100 percent or no_turbo set policy->{min,max} will be set incorrectly with scaled values which turn the scaled values into hard limits. References: https://bugzilla.kernel.org/show_bug.cgi?id=61241 Reported-by: Patrick Bartels Signed-off-by: Dirk Brandewie Cc: 3.9+ # 3.9+ Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/intel_pstate.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'drivers/cpufreq/intel_pstate.c') diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 32b3479a2405..28fefe3dd731 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -637,8 +637,8 @@ static int intel_pstate_cpu_exit(struct cpufreq_policy *policy) static int intel_pstate_cpu_init(struct cpufreq_policy *policy) { - int rc, min_pstate, max_pstate; struct cpudata *cpu; + int rc; rc = intel_pstate_init_cpu(policy->cpu); if (rc) @@ -652,9 +652,8 @@ static int intel_pstate_cpu_init(struct cpufreq_policy *policy) else policy->policy = CPUFREQ_POLICY_POWERSAVE; - intel_pstate_get_min_max(cpu, &min_pstate, &max_pstate); - policy->min = min_pstate * 100000; - policy->max = max_pstate * 100000; + policy->min = cpu->pstate.min_pstate * 100000; + policy->max = cpu->pstate.turbo_pstate * 100000; /* cpuinfo and default policy values */ policy->cpuinfo.min_freq = cpu->pstate.min_pstate * 100000; -- cgit v1.2.3 From 09c87e2f79eb336bd313090be8113ae29345b8f5 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 16 Oct 2013 22:59:33 +0200 Subject: intel_pstate: Fix type mismatch warning The expression in line 398 of intel_pstate.c causes the following warning to be emitted: drivers/cpufreq/intel_pstate.c:398:3: warning: left shift count >= width of type which happens because unsigned long is 32-bit on some architectures. Fix that by using a helper u64 variable and simplify the code slightly. Tested-by: Srinivas Pandruvada Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/intel_pstate.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'drivers/cpufreq/intel_pstate.c') diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 28fefe3dd731..badf6206b2b2 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -383,6 +383,7 @@ static void intel_pstate_get_min_max(struct cpudata *cpu, int *min, int *max) static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate) { int max_perf, min_perf; + u64 val; intel_pstate_get_min_max(cpu, &min_perf, &max_perf); @@ -394,11 +395,11 @@ static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate) trace_cpu_frequency(pstate * 100000, cpu->cpu); cpu->pstate.current_pstate = pstate; + val = pstate << 8; if (limits.no_turbo) - wrmsrl(MSR_IA32_PERF_CTL, BIT(32) | (pstate << 8)); - else - wrmsrl(MSR_IA32_PERF_CTL, pstate << 8); + val |= (u64)1 << 32; + wrmsrl(MSR_IA32_PERF_CTL, val); } static inline void intel_pstate_pstate_increase(struct cpudata *cpu, int steps) -- cgit v1.2.3 From d253d2a52676cfa3d89b8f0737a08ce7db665207 Mon Sep 17 00:00:00 2001 From: Brennan Shacklett Date: Mon, 21 Oct 2013 09:20:32 -0700 Subject: intel_pstate: Improve accuracy by not truncating until final result This patch addresses Bug 60727 (https://bugzilla.kernel.org/show_bug.cgi?id=60727) which was due to the truncation of intermediate values in the calculations, which causes the code to consistently underestimate the current cpu frequency, specifically 100% cpu utilization was truncated down to the setpoint of 97%. This patch fixes the problem by keeping the results of all intermediate calculations as fixed point numbers rather scaling them back and forth between integers and fixed point. References: https://bugzilla.kernel.org/show_bug.cgi?id=60727 Signed-off-by: Brennan Shacklett Acked-by: Dirk Brandewie Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/intel_pstate.c | 33 +++++++++++++++------------------ 1 file changed, 15 insertions(+), 18 deletions(-) (limited to 'drivers/cpufreq/intel_pstate.c') diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index badf6206b2b2..8b8677f92700 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -48,7 +48,7 @@ static inline int32_t div_fp(int32_t x, int32_t y) } struct sample { - int core_pct_busy; + int32_t core_pct_busy; u64 aperf; u64 mperf; int freq; @@ -68,7 +68,7 @@ struct _pid { int32_t i_gain; int32_t d_gain; int deadband; - int last_err; + int32_t last_err; }; struct cpudata { @@ -153,16 +153,15 @@ static inline void pid_d_gain_set(struct _pid *pid, int percent) pid->d_gain = div_fp(int_tofp(percent), int_tofp(100)); } -static signed int pid_calc(struct _pid *pid, int busy) +static signed int pid_calc(struct _pid *pid, int32_t busy) { - signed int err, result; + signed int result; int32_t pterm, dterm, fp_error; int32_t integral_limit; - err = pid->setpoint - busy; - fp_error = int_tofp(err); + fp_error = int_tofp(pid->setpoint) - busy; - if (abs(err) <= pid->deadband) + if (abs(fp_error) <= int_tofp(pid->deadband)) return 0; pterm = mul_fp(pid->p_gain, fp_error); @@ -176,8 +175,8 @@ static signed int pid_calc(struct _pid *pid, int busy) if (pid->integral < -integral_limit) pid->integral = -integral_limit; - dterm = mul_fp(pid->d_gain, (err - pid->last_err)); - pid->last_err = err; + dterm = mul_fp(pid->d_gain, fp_error - pid->last_err); + pid->last_err = fp_error; result = pterm + mul_fp(pid->integral, pid->i_gain) + dterm; @@ -436,8 +435,9 @@ static inline void intel_pstate_calc_busy(struct cpudata *cpu, struct sample *sample) { u64 core_pct; - core_pct = div64_u64(sample->aperf * 100, sample->mperf); - sample->freq = cpu->pstate.max_pstate * core_pct * 1000; + core_pct = div64_u64(int_tofp(sample->aperf * 100), + sample->mperf); + sample->freq = fp_toint(cpu->pstate.max_pstate * core_pct * 1000); sample->core_pct_busy = core_pct; } @@ -469,22 +469,19 @@ static inline void intel_pstate_set_sample_time(struct cpudata *cpu) mod_timer_pinned(&cpu->timer, jiffies + delay); } -static inline int intel_pstate_get_scaled_busy(struct cpudata *cpu) +static inline int32_t intel_pstate_get_scaled_busy(struct cpudata *cpu) { - int32_t busy_scaled; int32_t core_busy, max_pstate, current_pstate; - core_busy = int_tofp(cpu->samples[cpu->sample_ptr].core_pct_busy); + core_busy = cpu->samples[cpu->sample_ptr].core_pct_busy; max_pstate = int_tofp(cpu->pstate.max_pstate); current_pstate = int_tofp(cpu->pstate.current_pstate); - busy_scaled = mul_fp(core_busy, div_fp(max_pstate, current_pstate)); - - return fp_toint(busy_scaled); + return mul_fp(core_busy, div_fp(max_pstate, current_pstate)); } static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu) { - int busy_scaled; + int32_t busy_scaled; struct _pid *pid; signed int ctl = 0; int steps; -- cgit v1.2.3 From 7244cb62d96e735847dc9d08f870550df896898c Mon Sep 17 00:00:00 2001 From: Dirk Brandewie Date: Mon, 21 Oct 2013 09:20:33 -0700 Subject: intel_pstate: Correct calculation of min pstate value The minimum pstate is supposed to be a percentage of the maximum P state available. Calculate min using max pstate and not the current max which may have been limited by the user Signed-off-by: Dirk Brandewie Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/intel_pstate.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'drivers/cpufreq/intel_pstate.c') diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 8b8677f92700..eb3fdc755000 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -366,12 +366,13 @@ static int intel_pstate_turbo_pstate(void) static void intel_pstate_get_min_max(struct cpudata *cpu, int *min, int *max) { int max_perf = cpu->pstate.turbo_pstate; + int max_perf_adj; int min_perf; if (limits.no_turbo) max_perf = cpu->pstate.max_pstate; - max_perf = fp_toint(mul_fp(int_tofp(max_perf), limits.max_perf)); - *max = clamp_t(int, max_perf, + max_perf_adj = fp_toint(mul_fp(int_tofp(max_perf), limits.max_perf)); + *max = clamp_t(int, max_perf_adj, cpu->pstate.min_pstate, cpu->pstate.turbo_pstate); min_perf = fp_toint(mul_fp(int_tofp(max_perf), limits.min_perf)); -- cgit v1.2.3 From 016c815084d5b89f7c1a24b1a3a0b796512a91bc Mon Sep 17 00:00:00 2001 From: Dirk Brandewie Date: Mon, 21 Oct 2013 09:20:34 -0700 Subject: intel_pstate: Refactor driver to support CPUs with different MSR layouts Non-core processors have a different MSR layout to commumicate P state information. Refactor the driver to use CPU dependent accessors to P state information. Signed-off-by: Dirk Brandewie Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/intel_pstate.c | 144 ++++++++++++++++++++++++++++------------- 1 file changed, 98 insertions(+), 46 deletions(-) (limited to 'drivers/cpufreq/intel_pstate.c') diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index d57648989c0b..6b37c9ff1d64 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -78,7 +78,6 @@ struct cpudata { struct timer_list timer; - struct pstate_adjust_policy *pstate_policy; struct pstate_data pstate; struct _pid pid; @@ -100,15 +99,21 @@ struct pstate_adjust_policy { int i_gain_pct; }; -static struct pstate_adjust_policy default_policy = { - .sample_rate_ms = 10, - .deadband = 0, - .setpoint = 97, - .p_gain_pct = 20, - .d_gain_pct = 0, - .i_gain_pct = 0, +struct pstate_funcs { + int (*get_max)(void); + int (*get_min)(void); + int (*get_turbo)(void); + void (*set)(int pstate); }; +struct cpu_defaults { + struct pstate_adjust_policy pid_policy; + struct pstate_funcs funcs; +}; + +static struct pstate_adjust_policy pid_params; +static struct pstate_funcs pstate_funcs; + struct perf_limits { int no_turbo; int max_perf_pct; @@ -186,14 +191,14 @@ static signed int pid_calc(struct _pid *pid, int busy) static inline void intel_pstate_busy_pid_reset(struct cpudata *cpu) { - pid_p_gain_set(&cpu->pid, cpu->pstate_policy->p_gain_pct); - pid_d_gain_set(&cpu->pid, cpu->pstate_policy->d_gain_pct); - pid_i_gain_set(&cpu->pid, cpu->pstate_policy->i_gain_pct); + pid_p_gain_set(&cpu->pid, pid_params.p_gain_pct); + pid_d_gain_set(&cpu->pid, pid_params.d_gain_pct); + pid_i_gain_set(&cpu->pid, pid_params.i_gain_pct); pid_reset(&cpu->pid, - cpu->pstate_policy->setpoint, + pid_params.setpoint, 100, - cpu->pstate_policy->deadband, + pid_params.deadband, 0); } @@ -227,12 +232,12 @@ struct pid_param { }; static struct pid_param pid_files[] = { - {"sample_rate_ms", &default_policy.sample_rate_ms}, - {"d_gain_pct", &default_policy.d_gain_pct}, - {"i_gain_pct", &default_policy.i_gain_pct}, - {"deadband", &default_policy.deadband}, - {"setpoint", &default_policy.setpoint}, - {"p_gain_pct", &default_policy.p_gain_pct}, + {"sample_rate_ms", &pid_params.sample_rate_ms}, + {"d_gain_pct", &pid_params.d_gain_pct}, + {"i_gain_pct", &pid_params.i_gain_pct}, + {"deadband", &pid_params.deadband}, + {"setpoint", &pid_params.setpoint}, + {"p_gain_pct", &pid_params.p_gain_pct}, {NULL, NULL} }; @@ -337,33 +342,60 @@ static void intel_pstate_sysfs_expose_params(void) } /************************** sysfs end ************************/ - -static int intel_pstate_min_pstate(void) +static int core_get_min_pstate(void) { u64 value; rdmsrl(MSR_PLATFORM_INFO, value); return (value >> 40) & 0xFF; } -static int intel_pstate_max_pstate(void) +static int core_get_max_pstate(void) { u64 value; rdmsrl(MSR_PLATFORM_INFO, value); return (value >> 8) & 0xFF; } -static int intel_pstate_turbo_pstate(void) +static int core_get_turbo_pstate(void) { u64 value; int nont, ret; rdmsrl(MSR_NHM_TURBO_RATIO_LIMIT, value); - nont = intel_pstate_max_pstate(); + nont = core_get_max_pstate(); ret = ((value) & 255); if (ret <= nont) ret = nont; return ret; } +static void core_set_pstate(int pstate) +{ + u64 val; + + val = pstate << 8; + if (limits.no_turbo) + val |= (u64)1 << 32; + + wrmsrl(MSR_IA32_PERF_CTL, val); +} + +static struct cpu_defaults core_params = { + .pid_policy = { + .sample_rate_ms = 10, + .deadband = 0, + .setpoint = 97, + .p_gain_pct = 20, + .d_gain_pct = 0, + .i_gain_pct = 0, + }, + .funcs = { + .get_max = core_get_max_pstate, + .get_min = core_get_min_pstate, + .get_turbo = core_get_turbo_pstate, + .set = core_set_pstate, + }, +}; + static void intel_pstate_get_min_max(struct cpudata *cpu, int *min, int *max) { int max_perf = cpu->pstate.turbo_pstate; @@ -383,7 +415,6 @@ static void intel_pstate_get_min_max(struct cpudata *cpu, int *min, int *max) static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate) { int max_perf, min_perf; - u64 val; intel_pstate_get_min_max(cpu, &min_perf, &max_perf); @@ -395,11 +426,8 @@ static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate) trace_cpu_frequency(pstate * 100000, cpu->cpu); cpu->pstate.current_pstate = pstate; - val = pstate << 8; - if (limits.no_turbo) - val |= (u64)1 << 32; - wrmsrl(MSR_IA32_PERF_CTL, val); + pstate_funcs.set(pstate); } static inline void intel_pstate_pstate_increase(struct cpudata *cpu, int steps) @@ -421,9 +449,9 @@ static void intel_pstate_get_cpu_pstates(struct cpudata *cpu) { sprintf(cpu->name, "Intel 2nd generation core"); - cpu->pstate.min_pstate = intel_pstate_min_pstate(); - cpu->pstate.max_pstate = intel_pstate_max_pstate(); - cpu->pstate.turbo_pstate = intel_pstate_turbo_pstate(); + 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 @@ -464,7 +492,7 @@ static inline void intel_pstate_set_sample_time(struct cpudata *cpu) { int sample_time, delay; - sample_time = cpu->pstate_policy->sample_rate_ms; + sample_time = pid_params.sample_rate_ms; delay = msecs_to_jiffies(sample_time); mod_timer_pinned(&cpu->timer, jiffies + delay); } @@ -523,14 +551,14 @@ static void intel_pstate_timer_func(unsigned long __data) { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)&policy } static const struct x86_cpu_id intel_pstate_cpu_ids[] = { - ICPU(0x2a, default_policy), - ICPU(0x2d, default_policy), - ICPU(0x3a, default_policy), - ICPU(0x3c, default_policy), - ICPU(0x3e, default_policy), - ICPU(0x3f, default_policy), - ICPU(0x45, default_policy), - ICPU(0x46, default_policy), + ICPU(0x2a, core_params), + ICPU(0x2d, core_params), + ICPU(0x3a, core_params), + ICPU(0x3c, core_params), + ICPU(0x3e, core_params), + ICPU(0x3f, core_params), + ICPU(0x45, core_params), + ICPU(0x46, core_params), {} }; MODULE_DEVICE_TABLE(x86cpu, intel_pstate_cpu_ids); @@ -554,8 +582,7 @@ static int intel_pstate_init_cpu(unsigned int cpunum) intel_pstate_get_cpu_pstates(cpu); cpu->cpu = cpunum; - cpu->pstate_policy = - (struct pstate_adjust_policy *)id->driver_data; + init_timer_deferrable(&cpu->timer); cpu->timer.function = intel_pstate_timer_func; cpu->timer.data = @@ -683,9 +710,9 @@ static int intel_pstate_msrs_not_valid(void) rdmsrl(MSR_IA32_APERF, aperf); rdmsrl(MSR_IA32_MPERF, mperf); - if (!intel_pstate_min_pstate() || - !intel_pstate_max_pstate() || - !intel_pstate_turbo_pstate()) + if (!pstate_funcs.get_max() || + !pstate_funcs.get_min() || + !pstate_funcs.get_turbo()) return -ENODEV; rdmsrl(MSR_IA32_APERF, tmp); @@ -698,10 +725,30 @@ static int intel_pstate_msrs_not_valid(void) return 0; } + +void copy_pid_params(struct pstate_adjust_policy *policy) +{ + pid_params.sample_rate_ms = policy->sample_rate_ms; + pid_params.p_gain_pct = policy->p_gain_pct; + pid_params.i_gain_pct = policy->i_gain_pct; + pid_params.d_gain_pct = policy->d_gain_pct; + pid_params.deadband = policy->deadband; + pid_params.setpoint = policy->setpoint; +} + +void copy_cpu_funcs(struct pstate_funcs *funcs) +{ + pstate_funcs.get_max = funcs->get_max; + pstate_funcs.get_min = funcs->get_min; + pstate_funcs.get_turbo = funcs->get_turbo; + pstate_funcs.set = funcs->set; +} + static int __init intel_pstate_init(void) { int cpu, rc = 0; const struct x86_cpu_id *id; + struct cpu_defaults *cpu_info; if (no_load) return -ENODEV; @@ -710,6 +757,11 @@ static int __init intel_pstate_init(void) if (!id) return -ENODEV; + cpu_info = (struct cpu_defaults *)id->driver_data; + + copy_pid_params(&cpu_info->pid_policy); + copy_cpu_funcs(&cpu_info->funcs); + if (intel_pstate_msrs_not_valid()) return -ENODEV; -- cgit v1.2.3 From 19e77c28dbf1972305da0dfeb92a62f83df3a91d Mon Sep 17 00:00:00 2001 From: Dirk Brandewie Date: Mon, 21 Oct 2013 09:20:35 -0700 Subject: intel_pstate: Add Baytrail support Add support for the Baytrail processor. Signed-off-by: Dirk Brandewie Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/intel_pstate.c | 35 +++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) (limited to 'drivers/cpufreq/intel_pstate.c') diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 6b37c9ff1d64..27c2753909fe 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -33,6 +33,8 @@ #define SAMPLE_COUNT 3 +#define BYT_RATIOS 0x66a + #define FRAC_BITS 8 #define int_tofp(X) ((int64_t)(X) << FRAC_BITS) #define fp_toint(X) ((X) >> FRAC_BITS) @@ -342,6 +344,20 @@ static void intel_pstate_sysfs_expose_params(void) } /************************** sysfs end ************************/ +static int byt_get_min_pstate(void) +{ + u64 value; + rdmsrl(BYT_RATIOS, value); + return value & 0xFF; +} + +static int byt_get_max_pstate(void) +{ + u64 value; + rdmsrl(BYT_RATIOS, value); + return (value >> 16) & 0xFF; +} + static int core_get_min_pstate(void) { u64 value; @@ -396,6 +412,24 @@ static struct cpu_defaults core_params = { }, }; +static struct cpu_defaults byt_params = { + .pid_policy = { + .sample_rate_ms = 10, + .deadband = 0, + .setpoint = 97, + .p_gain_pct = 14, + .d_gain_pct = 0, + .i_gain_pct = 4, + }, + .funcs = { + .get_max = byt_get_max_pstate, + .get_min = byt_get_min_pstate, + .get_turbo = byt_get_max_pstate, + .set = core_set_pstate, + }, +}; + + static void intel_pstate_get_min_max(struct cpudata *cpu, int *min, int *max) { int max_perf = cpu->pstate.turbo_pstate; @@ -553,6 +587,7 @@ static void intel_pstate_timer_func(unsigned long __data) static const struct x86_cpu_id intel_pstate_cpu_ids[] = { ICPU(0x2a, core_params), ICPU(0x2d, core_params), + ICPU(0x37, byt_params), ICPU(0x3a, core_params), ICPU(0x3c, core_params), ICPU(0x3e, core_params), -- cgit v1.2.3 From e0a261a207fb5bcbc6cc5db3b51a96d9cbe9b97e Mon Sep 17 00:00:00 2001 From: Dirk Brandewie Date: Wed, 30 Oct 2013 08:38:32 -0700 Subject: cpufreq/intel_pstate: Add static declarations to internal functions Fixes warnings reported by kbuild test robot sparse warnings: (new ones prefixed by >>) drivers/cpufreq/intel_pstate.c:729:6: sparse: symbol 'copy_pid_params' was not declared. Should it be static? drivers/cpufreq/intel_pstate.c:739:6: sparse: symbol 'copy_cpu_funcs' was not declared. Should it be static? Signed-off-by: Dirk Brandewie Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/intel_pstate.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers/cpufreq/intel_pstate.c') diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 27c2753909fe..81e0062a6d2a 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -761,7 +761,7 @@ static int intel_pstate_msrs_not_valid(void) return 0; } -void copy_pid_params(struct pstate_adjust_policy *policy) +static void copy_pid_params(struct pstate_adjust_policy *policy) { pid_params.sample_rate_ms = policy->sample_rate_ms; pid_params.p_gain_pct = policy->p_gain_pct; @@ -771,7 +771,7 @@ void copy_pid_params(struct pstate_adjust_policy *policy) pid_params.setpoint = policy->setpoint; } -void copy_cpu_funcs(struct pstate_funcs *funcs) +static void copy_cpu_funcs(struct pstate_funcs *funcs) { pstate_funcs.get_max = funcs->get_max; pstate_funcs.get_min = funcs->get_min; -- cgit v1.2.3 From fbbcdc0744dace5fcc8147d11c5fb0791126848a Mon Sep 17 00:00:00 2001 From: Adrian Huang Date: Thu, 31 Oct 2013 23:24:05 +0800 Subject: intel_pstate: skip the driver if ACPI has power mgmt option Do not load the Intel pstate driver if the platform firmware (ACPI BIOS) supports the power management alternatives. The ACPI BIOS indicates that the OS control mode can be used if the _PSS (Performance Supported States) is defined in ACPI table. For the OS control mode, the Intel pstate driver will be loaded. HP BIOS has several power management modes (firmware, OS-control and so on). For the OS control mode in HP BIOS, the Intel p-state driver will be loaded. When the customer chooses the firmware power management in HP BIOS, the Intel p-state driver will be ignored. I put hw_vendor_info vendor_info in case other vendors (Dell, Lenovo...) have their firmware power management. Vendors should make sure their firmware power management works properly, and they can go for adding their vendor info to the variable. I have verified the patch on HP ProLiant servers. The patch worked correctly. Signed-off-by: Adrian Huang [rjw: Fixed up !CONFIG_ACPI build] [Linda Knippers: As Adrian has recently left HP, I retested the updated patch on an HP ProLiant server and verified that it is behaving correctly. When the BIOS is configured for OS control for power management, the intel_pstate driver loads as expected. When the BIOS is configured to provide the power management, the intel_pstate driver does not load and we get the pcc_cpufreq driver instead.] Signed-off-by: Linda Knippers Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/intel_pstate.c | 74 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 74 insertions(+) (limited to 'drivers/cpufreq/intel_pstate.c') diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 81e0062a6d2a..3b5c5359a44b 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include @@ -779,6 +780,72 @@ static void copy_cpu_funcs(struct pstate_funcs *funcs) pstate_funcs.set = funcs->set; } +#if IS_ENABLED(CONFIG_ACPI) +#include + +static bool intel_pstate_no_acpi_pss(void) +{ + int i; + + for_each_possible_cpu(i) { + acpi_status status; + union acpi_object *pss; + struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; + struct acpi_processor *pr = per_cpu(processors, i); + + if (!pr) + continue; + + status = acpi_evaluate_object(pr->handle, "_PSS", NULL, &buffer); + if (ACPI_FAILURE(status)) + continue; + + pss = buffer.pointer; + if (pss && pss->type == ACPI_TYPE_PACKAGE) { + kfree(pss); + return false; + } + + kfree(pss); + } + + return true; +} + +struct hw_vendor_info { + u16 valid; + char oem_id[ACPI_OEM_ID_SIZE]; + char oem_table_id[ACPI_OEM_TABLE_ID_SIZE]; +}; + +/* Hardware vendor-specific info that has its own power management modes */ +static struct hw_vendor_info vendor_info[] = { + {1, "HP ", "ProLiant"}, + {0, "", ""}, +}; + +static bool intel_pstate_platform_pwr_mgmt_exists(void) +{ + struct acpi_table_header hdr; + struct hw_vendor_info *v_info; + + if (acpi_disabled + || ACPI_FAILURE(acpi_get_table_header(ACPI_SIG_FADT, 0, &hdr))) + return false; + + for (v_info = vendor_info; v_info->valid; v_info++) { + if (!strncmp(hdr.oem_id, v_info->oem_id, ACPI_OEM_ID_SIZE) + && !strncmp(hdr.oem_table_id, v_info->oem_table_id, ACPI_OEM_TABLE_ID_SIZE) + && intel_pstate_no_acpi_pss()) + return true; + } + + return false; +} +#else /* CONFIG_ACPI not enabled */ +static inline bool intel_pstate_platform_pwr_mgmt_exists(void) { return false; } +#endif /* CONFIG_ACPI */ + static int __init intel_pstate_init(void) { int cpu, rc = 0; @@ -792,6 +859,13 @@ static int __init intel_pstate_init(void) if (!id) return -ENODEV; + /* + * The Intel pstate driver will be ignored if the platform + * firmware has its own power management modes. + */ + if (intel_pstate_platform_pwr_mgmt_exists()) + return -ENODEV; + cpu_info = (struct cpu_defaults *)id->driver_data; copy_pid_params(&cpu_info->pid_policy); -- cgit v1.2.3