Message ID | 20240903203701.2695040-9-superm1@kernel.org (mailing list archive) |
---|---|
State | Handled Elsewhere, archived |
Headers | show |
Series | Adjustments for preferred core detection | expand |
On Tue, Sep 03, 2024 at 03:36:58PM -0500, Mario Limonciello wrote: > From: Mario Limonciello <mario.limonciello@amd.com> > > The special case in amd_pstate_highest_perf_set() is the value used > for calculating the boost numerator. Merge this into > amd_get_boost_ratio_numerator() and then use that to calculate boost > ratio. > > This allows dropping more special casing of the highest perf value. > > Signed-off-by: Mario Limonciello <mario.limonciello@amd.com> > --- > v1->v2: > * Document that preferred cores will have different values for highest > perf. > * Fix an uninitialized variable caused by merge > --- > Documentation/admin-guide/pm/amd-pstate.rst | 3 +- > arch/x86/kernel/acpi/cppc.c | 16 +++++++ > drivers/cpufreq/amd-pstate.c | 52 ++++----------------- > 3 files changed, 28 insertions(+), 43 deletions(-) > > diff --git a/Documentation/admin-guide/pm/amd-pstate.rst b/Documentation/admin-guide/pm/amd-pstate.rst > index d0324d44f5482..e13915c540648 100644 > --- a/Documentation/admin-guide/pm/amd-pstate.rst > +++ b/Documentation/admin-guide/pm/amd-pstate.rst > @@ -251,7 +251,8 @@ performance supported in `AMD CPPC Performance Capability <perf_cap_>`_). > In some ASICs, the highest CPPC performance is not the one in the ``_CPC`` > table, so we need to expose it to sysfs. If boost is not active, but > still supported, this maximum frequency will be larger than the one in > -``cpuinfo``. > +``cpuinfo``. On systems that support preferred core, the driver will have > +different values for some cores than others. Thanks for documenting this. The patch looks good to me. Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com> -- Thanks and Regards gautham. > This attribute is read-only. > > ``amd_pstate_lowest_nonlinear_freq`` > diff --git a/arch/x86/kernel/acpi/cppc.c b/arch/x86/kernel/acpi/cppc.c > index df367bc359308..956984054bf30 100644 > --- a/arch/x86/kernel/acpi/cppc.c > +++ b/arch/x86/kernel/acpi/cppc.c > @@ -9,6 +9,7 @@ > #include <asm/processor.h> > #include <asm/topology.h> > > +#define CPPC_HIGHEST_PERF_PERFORMANCE 196 > #define CPPC_HIGHEST_PERF_PREFCORE 166 > > enum amd_pref_core { > @@ -245,6 +246,21 @@ int amd_get_boost_ratio_numerator(unsigned int cpu, u64 *numerator) > *numerator = boost_numerator; > return 0; > } > + > + /* > + * For AMD CPUs with Family ID 19H and Model ID range 0x70 to 0x7f, > + * the highest performance level is set to 196. > + * https://bugzilla.kernel.org/show_bug.cgi?id=218759 > + */ > + if (cpu_feature_enabled(X86_FEATURE_ZEN4)) { > + switch (boot_cpu_data.x86_model) { > + case 0x70 ... 0x7f: > + *numerator = CPPC_HIGHEST_PERF_PERFORMANCE; > + return 0; > + default: > + break; > + } > + } > *numerator = CPPC_HIGHEST_PERF_PREFCORE; > > return 0; > diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c > index c29cdf2d3882c..3ae41af6f041e 100644 > --- a/drivers/cpufreq/amd-pstate.c > +++ b/drivers/cpufreq/amd-pstate.c > @@ -52,8 +52,6 @@ > #define AMD_PSTATE_TRANSITION_LATENCY 20000 > #define AMD_PSTATE_TRANSITION_DELAY 1000 > #define AMD_PSTATE_FAST_CPPC_TRANSITION_DELAY 600 > -#define CPPC_HIGHEST_PERF_PERFORMANCE 196 > -#define CPPC_HIGHEST_PERF_DEFAULT 166 > > #define AMD_CPPC_EPP_PERFORMANCE 0x00 > #define AMD_CPPC_EPP_BALANCE_PERFORMANCE 0x80 > @@ -372,43 +370,17 @@ static inline int amd_pstate_enable(bool enable) > return static_call(amd_pstate_enable)(enable); > } > > -static u32 amd_pstate_highest_perf_set(struct amd_cpudata *cpudata) > -{ > - struct cpuinfo_x86 *c = &cpu_data(0); > - > - /* > - * For AMD CPUs with Family ID 19H and Model ID range 0x70 to 0x7f, > - * the highest performance level is set to 196. > - * https://bugzilla.kernel.org/show_bug.cgi?id=218759 > - */ > - if (c->x86 == 0x19 && (c->x86_model >= 0x70 && c->x86_model <= 0x7f)) > - return CPPC_HIGHEST_PERF_PERFORMANCE; > - > - return CPPC_HIGHEST_PERF_DEFAULT; > -} > - > static int pstate_init_perf(struct amd_cpudata *cpudata) > { > u64 cap1; > - u32 highest_perf; > > int ret = rdmsrl_safe_on_cpu(cpudata->cpu, MSR_AMD_CPPC_CAP1, > &cap1); > if (ret) > return ret; > > - /* For platforms that do not support the preferred core feature, the > - * highest_pef may be configured with 166 or 255, to avoid max frequency > - * calculated wrongly. we take the AMD_CPPC_HIGHEST_PERF(cap1) value as > - * the default max perf. > - */ > - if (cpudata->hw_prefcore) > - highest_perf = amd_pstate_highest_perf_set(cpudata); > - else > - highest_perf = AMD_CPPC_HIGHEST_PERF(cap1); > - > - WRITE_ONCE(cpudata->highest_perf, highest_perf); > - WRITE_ONCE(cpudata->max_limit_perf, highest_perf); > + WRITE_ONCE(cpudata->highest_perf, AMD_CPPC_HIGHEST_PERF(cap1)); > + WRITE_ONCE(cpudata->max_limit_perf, AMD_CPPC_HIGHEST_PERF(cap1)); > WRITE_ONCE(cpudata->nominal_perf, AMD_CPPC_NOMINAL_PERF(cap1)); > WRITE_ONCE(cpudata->lowest_nonlinear_perf, AMD_CPPC_LOWNONLIN_PERF(cap1)); > WRITE_ONCE(cpudata->lowest_perf, AMD_CPPC_LOWEST_PERF(cap1)); > @@ -420,19 +392,13 @@ static int pstate_init_perf(struct amd_cpudata *cpudata) > static int cppc_init_perf(struct amd_cpudata *cpudata) > { > struct cppc_perf_caps cppc_perf; > - u32 highest_perf; > > int ret = cppc_get_perf_caps(cpudata->cpu, &cppc_perf); > if (ret) > return ret; > > - if (cpudata->hw_prefcore) > - highest_perf = amd_pstate_highest_perf_set(cpudata); > - else > - highest_perf = cppc_perf.highest_perf; > - > - WRITE_ONCE(cpudata->highest_perf, highest_perf); > - WRITE_ONCE(cpudata->max_limit_perf, highest_perf); > + WRITE_ONCE(cpudata->highest_perf, cppc_perf.highest_perf); > + WRITE_ONCE(cpudata->max_limit_perf, cppc_perf.highest_perf); > WRITE_ONCE(cpudata->nominal_perf, cppc_perf.nominal_perf); > WRITE_ONCE(cpudata->lowest_nonlinear_perf, > cppc_perf.lowest_nonlinear_perf); > @@ -905,8 +871,8 @@ static u32 amd_pstate_get_transition_latency(unsigned int cpu) > static int amd_pstate_init_freq(struct amd_cpudata *cpudata) > { > int ret; > - u32 min_freq; > - u32 highest_perf, max_freq; > + u32 min_freq, max_freq; > + u64 numerator; > u32 nominal_perf, nominal_freq; > u32 lowest_nonlinear_perf, lowest_nonlinear_freq; > u32 boost_ratio, lowest_nonlinear_ratio; > @@ -928,8 +894,10 @@ static int amd_pstate_init_freq(struct amd_cpudata *cpudata) > > nominal_perf = READ_ONCE(cpudata->nominal_perf); > > - highest_perf = READ_ONCE(cpudata->highest_perf); > - boost_ratio = div_u64(highest_perf << SCHED_CAPACITY_SHIFT, nominal_perf); > + ret = amd_get_boost_ratio_numerator(cpudata->cpu, &numerator); > + if (ret) > + return ret; > + boost_ratio = div_u64(numerator << SCHED_CAPACITY_SHIFT, nominal_perf); > max_freq = (nominal_freq * boost_ratio >> SCHED_CAPACITY_SHIFT) * 1000; > > lowest_nonlinear_perf = READ_ONCE(cpudata->lowest_nonlinear_perf); > -- > 2.43.0 >
diff --git a/Documentation/admin-guide/pm/amd-pstate.rst b/Documentation/admin-guide/pm/amd-pstate.rst index d0324d44f5482..e13915c540648 100644 --- a/Documentation/admin-guide/pm/amd-pstate.rst +++ b/Documentation/admin-guide/pm/amd-pstate.rst @@ -251,7 +251,8 @@ performance supported in `AMD CPPC Performance Capability <perf_cap_>`_). In some ASICs, the highest CPPC performance is not the one in the ``_CPC`` table, so we need to expose it to sysfs. If boost is not active, but still supported, this maximum frequency will be larger than the one in -``cpuinfo``. +``cpuinfo``. On systems that support preferred core, the driver will have +different values for some cores than others. This attribute is read-only. ``amd_pstate_lowest_nonlinear_freq`` diff --git a/arch/x86/kernel/acpi/cppc.c b/arch/x86/kernel/acpi/cppc.c index df367bc359308..956984054bf30 100644 --- a/arch/x86/kernel/acpi/cppc.c +++ b/arch/x86/kernel/acpi/cppc.c @@ -9,6 +9,7 @@ #include <asm/processor.h> #include <asm/topology.h> +#define CPPC_HIGHEST_PERF_PERFORMANCE 196 #define CPPC_HIGHEST_PERF_PREFCORE 166 enum amd_pref_core { @@ -245,6 +246,21 @@ int amd_get_boost_ratio_numerator(unsigned int cpu, u64 *numerator) *numerator = boost_numerator; return 0; } + + /* + * For AMD CPUs with Family ID 19H and Model ID range 0x70 to 0x7f, + * the highest performance level is set to 196. + * https://bugzilla.kernel.org/show_bug.cgi?id=218759 + */ + if (cpu_feature_enabled(X86_FEATURE_ZEN4)) { + switch (boot_cpu_data.x86_model) { + case 0x70 ... 0x7f: + *numerator = CPPC_HIGHEST_PERF_PERFORMANCE; + return 0; + default: + break; + } + } *numerator = CPPC_HIGHEST_PERF_PREFCORE; return 0; diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index c29cdf2d3882c..3ae41af6f041e 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -52,8 +52,6 @@ #define AMD_PSTATE_TRANSITION_LATENCY 20000 #define AMD_PSTATE_TRANSITION_DELAY 1000 #define AMD_PSTATE_FAST_CPPC_TRANSITION_DELAY 600 -#define CPPC_HIGHEST_PERF_PERFORMANCE 196 -#define CPPC_HIGHEST_PERF_DEFAULT 166 #define AMD_CPPC_EPP_PERFORMANCE 0x00 #define AMD_CPPC_EPP_BALANCE_PERFORMANCE 0x80 @@ -372,43 +370,17 @@ static inline int amd_pstate_enable(bool enable) return static_call(amd_pstate_enable)(enable); } -static u32 amd_pstate_highest_perf_set(struct amd_cpudata *cpudata) -{ - struct cpuinfo_x86 *c = &cpu_data(0); - - /* - * For AMD CPUs with Family ID 19H and Model ID range 0x70 to 0x7f, - * the highest performance level is set to 196. - * https://bugzilla.kernel.org/show_bug.cgi?id=218759 - */ - if (c->x86 == 0x19 && (c->x86_model >= 0x70 && c->x86_model <= 0x7f)) - return CPPC_HIGHEST_PERF_PERFORMANCE; - - return CPPC_HIGHEST_PERF_DEFAULT; -} - static int pstate_init_perf(struct amd_cpudata *cpudata) { u64 cap1; - u32 highest_perf; int ret = rdmsrl_safe_on_cpu(cpudata->cpu, MSR_AMD_CPPC_CAP1, &cap1); if (ret) return ret; - /* For platforms that do not support the preferred core feature, the - * highest_pef may be configured with 166 or 255, to avoid max frequency - * calculated wrongly. we take the AMD_CPPC_HIGHEST_PERF(cap1) value as - * the default max perf. - */ - if (cpudata->hw_prefcore) - highest_perf = amd_pstate_highest_perf_set(cpudata); - else - highest_perf = AMD_CPPC_HIGHEST_PERF(cap1); - - WRITE_ONCE(cpudata->highest_perf, highest_perf); - WRITE_ONCE(cpudata->max_limit_perf, highest_perf); + WRITE_ONCE(cpudata->highest_perf, AMD_CPPC_HIGHEST_PERF(cap1)); + WRITE_ONCE(cpudata->max_limit_perf, AMD_CPPC_HIGHEST_PERF(cap1)); WRITE_ONCE(cpudata->nominal_perf, AMD_CPPC_NOMINAL_PERF(cap1)); WRITE_ONCE(cpudata->lowest_nonlinear_perf, AMD_CPPC_LOWNONLIN_PERF(cap1)); WRITE_ONCE(cpudata->lowest_perf, AMD_CPPC_LOWEST_PERF(cap1)); @@ -420,19 +392,13 @@ static int pstate_init_perf(struct amd_cpudata *cpudata) static int cppc_init_perf(struct amd_cpudata *cpudata) { struct cppc_perf_caps cppc_perf; - u32 highest_perf; int ret = cppc_get_perf_caps(cpudata->cpu, &cppc_perf); if (ret) return ret; - if (cpudata->hw_prefcore) - highest_perf = amd_pstate_highest_perf_set(cpudata); - else - highest_perf = cppc_perf.highest_perf; - - WRITE_ONCE(cpudata->highest_perf, highest_perf); - WRITE_ONCE(cpudata->max_limit_perf, highest_perf); + WRITE_ONCE(cpudata->highest_perf, cppc_perf.highest_perf); + WRITE_ONCE(cpudata->max_limit_perf, cppc_perf.highest_perf); WRITE_ONCE(cpudata->nominal_perf, cppc_perf.nominal_perf); WRITE_ONCE(cpudata->lowest_nonlinear_perf, cppc_perf.lowest_nonlinear_perf); @@ -905,8 +871,8 @@ static u32 amd_pstate_get_transition_latency(unsigned int cpu) static int amd_pstate_init_freq(struct amd_cpudata *cpudata) { int ret; - u32 min_freq; - u32 highest_perf, max_freq; + u32 min_freq, max_freq; + u64 numerator; u32 nominal_perf, nominal_freq; u32 lowest_nonlinear_perf, lowest_nonlinear_freq; u32 boost_ratio, lowest_nonlinear_ratio; @@ -928,8 +894,10 @@ static int amd_pstate_init_freq(struct amd_cpudata *cpudata) nominal_perf = READ_ONCE(cpudata->nominal_perf); - highest_perf = READ_ONCE(cpudata->highest_perf); - boost_ratio = div_u64(highest_perf << SCHED_CAPACITY_SHIFT, nominal_perf); + ret = amd_get_boost_ratio_numerator(cpudata->cpu, &numerator); + if (ret) + return ret; + boost_ratio = div_u64(numerator << SCHED_CAPACITY_SHIFT, nominal_perf); max_freq = (nominal_freq * boost_ratio >> SCHED_CAPACITY_SHIFT) * 1000; lowest_nonlinear_perf = READ_ONCE(cpudata->lowest_nonlinear_perf);