Messages in this thread | | | Date | Thu, 9 Sep 2021 17:59:33 +0800 | From | Huang Rui <> | Subject | Re: [PATCH 16/19] cpupower: enable boost state support for amd-pstate module |
| |
On Thu, Sep 09, 2021 at 01:32:37AM +0800, Fontenot, Nathan wrote: > On 9/8/2021 9:59 AM, Huang Rui wrote: > > The AMD P-state boost API is different from ACPI hardware P-states, so > > implement the support for amd-pstate kernel module. > > > > Signed-off-by: Huang Rui <ray.huang@amd.com> > > --- > > tools/power/cpupower/lib/cpufreq.c | 20 ++++++++++++++++++++ > > tools/power/cpupower/lib/cpufreq.h | 3 +++ > > tools/power/cpupower/utils/helpers/misc.c | 7 +++++++ > > 3 files changed, 30 insertions(+) > > > > diff --git a/tools/power/cpupower/lib/cpufreq.c b/tools/power/cpupower/lib/cpufreq.c > > index 3f92ddadaad2..37da87bdcfb1 100644 > > --- a/tools/power/cpupower/lib/cpufreq.c > > +++ b/tools/power/cpupower/lib/cpufreq.c > > @@ -790,3 +790,23 @@ unsigned long cpufreq_get_transitions(unsigned int cpu) > > { > > return sysfs_cpufreq_get_one_value(cpu, STATS_NUM_TRANSITIONS); > > } > > + > > +int amd_pstate_boost_support(unsigned int cpu) > > +{ > > + unsigned int highest_perf, nominal_perf; > > + > > + highest_perf = sysfs_cpufreq_get_one_value(cpu, AMD_PSTATE_HIGHEST_PERF); > > + nominal_perf = sysfs_cpufreq_get_one_value(cpu, AMD_PSTATE_NOMINAL_PERF); > > + > > + return highest_perf > nominal_perf ? 1 : 0; > > +} > > + > > +int amd_pstate_boost_enabled(unsigned int cpu) > > +{ > > + unsigned int cpuinfo_max, amd_pstate_max; > > + > > + cpuinfo_max = sysfs_cpufreq_get_one_value(cpu, CPUINFO_MAX_FREQ); > > + amd_pstate_max = sysfs_cpufreq_get_one_value(cpu, AMD_PSTATE_MAX_FREQ); > > + > > + return cpuinfo_max == amd_pstate_max ? 1 : 0; > > +} > > diff --git a/tools/power/cpupower/lib/cpufreq.h b/tools/power/cpupower/lib/cpufreq.h > > index 95f4fd9e2656..d54d02a7a4f4 100644 > > --- a/tools/power/cpupower/lib/cpufreq.h > > +++ b/tools/power/cpupower/lib/cpufreq.h > > @@ -203,6 +203,9 @@ int cpufreq_modify_policy_governor(unsigned int cpu, char *governor); > > int cpufreq_set_frequency(unsigned int cpu, > > unsigned long target_frequency); > > > > +int amd_pstate_boost_support(unsigned int cpu); > > +int amd_pstate_boost_enabled(unsigned int cpu); > > + > > #ifdef __cplusplus > > } > > #endif > > diff --git a/tools/power/cpupower/utils/helpers/misc.c b/tools/power/cpupower/utils/helpers/misc.c > > index 07d80775fb68..aba979320760 100644 > > --- a/tools/power/cpupower/utils/helpers/misc.c > > +++ b/tools/power/cpupower/utils/helpers/misc.c > > @@ -10,6 +10,7 @@ > > #if defined(__i386__) || defined(__x86_64__) > > > > #include "cpupower_intern.h" > > +#include "cpufreq.h" > > > > #define MSR_AMD_HWCR 0xc0010015 > > > > @@ -39,6 +40,12 @@ int cpufreq_has_boost_support(unsigned int cpu, int *support, int *active, > > if (ret) > > return ret; > > } > > + } if ((cpupower_cpu_info.caps & CPUPOWER_CAP_AMD_PSTATE) && > > Shouldn't this be > > } else if ((cpupower_cpu_info.caps & CPUPOWER_CAP_AMD_PSTATE) && >
Nice catch, it's my typo.
Thanks, Ray
| |