| Message ID | 20230824021249.271946-4-li.meng@amd.com |
|---|---|
| State | Superseded |
| Headers | show |
| Series | AMD Pstate Preferred Core | expand |
Hi Meng Li, On 24 Aug 10:12, Meng Li wrote: > AMD Pstate driver utilizes the functions and data structures > provided by the ITMT architecture to enable the scheduler to > favor scheduling on cores which can be get a higher frequency > with lower voltage. We call it AMD Pstate Preferrred Core. > > Here sched_set_itmt_core_prio() is called to set priorities and > sched_set_itmt_support() is called to enable ITMT feature. > AMD Pstate driver uses the highest performance value to indicate > the priority of CPU. The higher value has a higher priority. > > The initial core rankings are set up by AMD Pstate when the > system boots. > > Add device attribute for preferred core states. > > Add one new early parameter `enable` to allow user to > enable the preferred core if the processor and power > firmware can support preferred core feature. > > Signed-off-by: Perry Yuan <Perry.Yuan@amd.com> > Co-developed-by: Perry Yuan <Perry.Yuan@amd.com> > Signed-off-by: Meng Li <li.meng@amd.com> > Co-developed-by: Meng Li <li.meng@amd.com> > Reviewed-by: Mario Limonciello <mario.limonciello@amd.com> > --- > drivers/cpufreq/amd-pstate.c | 120 ++++++++++++++++++++++++++++++----- > 1 file changed, 104 insertions(+), 16 deletions(-) > > diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c > index 9a1e194d5cf8..d02305675f66 100644 > --- a/drivers/cpufreq/amd-pstate.c > +++ b/drivers/cpufreq/amd-pstate.c > @@ -37,6 +37,7 @@ > #include <linux/uaccess.h> > #include <linux/static_call.h> > #include <linux/amd-pstate.h> > +#include <linux/topology.h> > > #include <acpi/processor.h> > #include <acpi/cppc_acpi.h> > @@ -49,6 +50,8 @@ > > #define AMD_PSTATE_TRANSITION_LATENCY 20000 > #define AMD_PSTATE_TRANSITION_DELAY 1000 > +#define AMD_PSTATE_PREFCORE_THRESHOLD 166 > +#define AMD_PSTATE_MAX_CPPC_PERF 255 > > /* > * TODO: We need more time to fine tune processors with shared memory solution > @@ -65,6 +68,9 @@ static struct cpufreq_driver amd_pstate_epp_driver; > static int cppc_state = AMD_PSTATE_UNDEFINED; > static bool cppc_enabled; > > +/*Preferred Core featue is supported*/ > +static bool prefcore = true; > + > /* > * AMD Energy Preference Performance (EPP) > * The EPP is used in the CCLK DPM controller to drive > @@ -290,23 +296,21 @@ static inline int amd_pstate_enable(bool enable) > 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; > > - /* > - * TODO: Introduce AMD specific power feature. > - * > - * CPPC entry doesn't indicate the highest performance in some ASICs. > + /* 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. > */ > - highest_perf = amd_get_highest_perf(); > - if (highest_perf > AMD_CPPC_HIGHEST_PERF(cap1)) > - highest_perf = AMD_CPPC_HIGHEST_PERF(cap1); > - > - WRITE_ONCE(cpudata->highest_perf, highest_perf); > + if (prefcore) > + WRITE_ONCE(cpudata->highest_perf, AMD_PSTATE_PREFCORE_THRESHOLD); > + else > + WRITE_ONCE(cpudata->highest_perf, AMD_CPPC_HIGHEST_PERF(cap1)); Can we disable `preferred core` in HW? If not then when we disable `preferred core` in software (via the cmd line param you have created), HW still gives core ranking through highest perf register/MSR. So, we have to filter the core ranking info form the highest perf register/MSR and set cpudata->highest_perf accordingly. IMO we should have two variables, one which indicated HW support and other one which indicates SW overwrite. In this function we should be checking only HW support. > > WRITE_ONCE(cpudata->nominal_perf, AMD_CPPC_NOMINAL_PERF(cap1)); > WRITE_ONCE(cpudata->lowest_nonlinear_perf, AMD_CPPC_LOWNONLIN_PERF(cap1)); > @@ -318,17 +322,15 @@ 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; > > - highest_perf = amd_get_highest_perf(); > - if (highest_perf > cppc_perf.highest_perf) > - highest_perf = cppc_perf.highest_perf; > - > - WRITE_ONCE(cpudata->highest_perf, highest_perf); > + if (prefcore) > + WRITE_ONCE(cpudata->highest_perf, AMD_PSTATE_PREFCORE_THRESHOLD); > + else > + WRITE_ONCE(cpudata->highest_perf, cppc_perf.highest_perf); Here also we should be checking only HW support. > > WRITE_ONCE(cpudata->nominal_perf, cppc_perf.nominal_perf); > WRITE_ONCE(cpudata->lowest_nonlinear_perf, > @@ -676,6 +678,72 @@ static void amd_perf_ctl_reset(unsigned int cpu) > wrmsrl_on_cpu(cpu, MSR_AMD_PERF_CTL, 0); > } > > +/* > + * Set AMD Pstate Preferred Core enable can't be done directly from cpufreq callbacks > + * due to locking, so queue the work for later. > + */ > +static void amd_pstste_sched_prefcore_workfn(struct work_struct *work) > +{ > + sched_set_itmt_support(); > +} > +static DECLARE_WORK(sched_prefcore_work, amd_pstste_sched_prefcore_workfn); > + > +/** > + * Get the highest performance register value. > + * @cpu: CPU from which to get highest performance. > + * @highest_perf: Return address. > + * > + * Return: 0 for success, -EIO otherwise. > + */ > +static int amd_pstate_get_highest_perf(int cpu, u64 *highest_perf) > +{ > + int ret; > + > + if (boot_cpu_has(X86_FEATURE_CPPC)) { > + u64 cap1; > + > + ret = rdmsrl_safe_on_cpu(cpu, MSR_AMD_CPPC_CAP1, &cap1); > + if (ret) > + return ret; > + WRITE_ONCE(*highest_perf, AMD_CPPC_HIGHEST_PERF(cap1)); > + } else { > + ret = cppc_get_highest_perf(cpu, highest_perf); > + } > + > + return (ret); > +} > + > +static void amd_pstate_init_prefcore(void) > +{ > + int cpu, ret; > + u64 highest_perf; > + > + if (!prefcore) > + return; > + > + for_each_online_cpu(cpu) { > + ret = amd_pstate_get_highest_perf(cpu, &highest_perf); > + if (ret) > + break; > + > + sched_set_itmt_core_prio(highest_perf, cpu); > + > + /* check if CPPC preferred core feature is enabled*/ > + if (highest_perf == AMD_PSTATE_MAX_CPPC_PERF) { > + prefcore = false; > + return; 255 is a valid core ranking right? Thanks & Regards, Wyes > + } > + } > + > + /* > + * This code can be run during CPU online under the > + * CPU hotplug locks, so sched_set_amd_prefcore_support() > + * cannot be called from here. Queue up a work item > + * to invoke it. > + */ > + schedule_work(&sched_prefcore_work); > +} > + > static int amd_pstate_cpu_init(struct cpufreq_policy *policy) > { > int min_freq, max_freq, nominal_freq, lowest_nonlinear_freq, ret; > @@ -1037,6 +1105,12 @@ static ssize_t status_store(struct device *a, struct device_attribute *b, > return ret < 0 ? ret : count; > } > > +static ssize_t prefcore_show(struct device *dev, > + struct device_attribute *attr, char *buf) > +{ > + return sysfs_emit(buf, "%s\n", prefcore ? "enabled" : "disabled"); > +} > + > cpufreq_freq_attr_ro(amd_pstate_max_freq); > cpufreq_freq_attr_ro(amd_pstate_lowest_nonlinear_freq); > > @@ -1044,6 +1118,7 @@ cpufreq_freq_attr_ro(amd_pstate_highest_perf); > cpufreq_freq_attr_rw(energy_performance_preference); > cpufreq_freq_attr_ro(energy_performance_available_preferences); > static DEVICE_ATTR_RW(status); > +static DEVICE_ATTR_RO(prefcore); > > static struct freq_attr *amd_pstate_attr[] = { > &amd_pstate_max_freq, > @@ -1063,6 +1138,7 @@ static struct freq_attr *amd_pstate_epp_attr[] = { > > static struct attribute *pstate_global_attributes[] = { > &dev_attr_status.attr, > + &dev_attr_prefcore.attr, > NULL > }; > > @@ -1506,6 +1582,8 @@ static int __init amd_pstate_init(void) > } > } > > + amd_pstate_init_prefcore(); > + > return ret; > > global_attr_free: > @@ -1527,7 +1605,17 @@ static int __init amd_pstate_param(char *str) > > return amd_pstate_set_driver(mode_idx); > } > + > +static int __init amd_prefcore_param(char *str) > +{ > + if (!strcmp(str, "disable")) > + prefcore = false; > + > + return 0; > +} > + > early_param("amd_pstate", amd_pstate_param); > +early_param("amd_prefcore", amd_prefcore_param); > > MODULE_AUTHOR("Huang Rui <ray.huang@amd.com>"); > MODULE_DESCRIPTION("AMD Processor P-state Frequency Driver"); > -- > 2.34.1 >
[AMD Official Use Only - General] Hello Wyes: > -----Original Message----- > From: Karny, Wyes <Wyes.Karny@amd.com> > Sent: Thursday, August 24, 2023 2:48 PM > To: Meng, Li (Jassmine) <Li.Meng@amd.com> > Cc: Karny, Wyes <Wyes.Karny@amd.com>; Rafael J . Wysocki > <rafael.j.wysocki@intel.com>; Huang, Ray <Ray.Huang@amd.com>; linux- > pm@vger.kernel.org; linux-kernel@vger.kernel.org; x86@kernel.org; linux- > acpi@vger.kernel.org; Shuah Khan <skhan@linuxfoundation.org>; linux- > kselftest@vger.kernel.org; Fontenot, Nathan > <Nathan.Fontenot@amd.com>; Sharma, Deepak > <Deepak.Sharma@amd.com>; Deucher, Alexander > <Alexander.Deucher@amd.com>; Limonciello, Mario > <Mario.Limonciello@amd.com>; Huang, Shimmer > <Shimmer.Huang@amd.com>; Yuan, Perry <Perry.Yuan@amd.com>; Du, > Xiaojian <Xiaojian.Du@amd.com>; Viresh Kumar <viresh.kumar@linaro.org>; > Borislav Petkov <bp@alien8.de> > Subject: Re: [PATCH V3 3/7] cpufreq: amd-pstate: Enable AMD Pstate > Preferred Core Supporting. > > Hi Meng Li, > > On 24 Aug 10:12, Meng Li wrote: > > AMD Pstate driver utilizes the functions and data structures provided > > by the ITMT architecture to enable the scheduler to favor scheduling > > on cores which can be get a higher frequency with lower voltage. We > > call it AMD Pstate Preferrred Core. > > > > Here sched_set_itmt_core_prio() is called to set priorities and > > sched_set_itmt_support() is called to enable ITMT feature. > > AMD Pstate driver uses the highest performance value to indicate the > > priority of CPU. The higher value has a higher priority. > > > > The initial core rankings are set up by AMD Pstate when the system > > boots. > > > > Add device attribute for preferred core states. > > > > Add one new early parameter `enable` to allow user to enable the > > preferred core if the processor and power firmware can support > > preferred core feature. > > > > Signed-off-by: Perry Yuan <Perry.Yuan@amd.com> > > Co-developed-by: Perry Yuan <Perry.Yuan@amd.com> > > Signed-off-by: Meng Li <li.meng@amd.com> > > Co-developed-by: Meng Li <li.meng@amd.com> > > Reviewed-by: Mario Limonciello <mario.limonciello@amd.com> > > --- > > drivers/cpufreq/amd-pstate.c | 120 > > ++++++++++++++++++++++++++++++----- > > 1 file changed, 104 insertions(+), 16 deletions(-) > > > > diff --git a/drivers/cpufreq/amd-pstate.c > > b/drivers/cpufreq/amd-pstate.c index 9a1e194d5cf8..d02305675f66 100644 > > --- a/drivers/cpufreq/amd-pstate.c > > +++ b/drivers/cpufreq/amd-pstate.c > > @@ -37,6 +37,7 @@ > > #include <linux/uaccess.h> > > #include <linux/static_call.h> > > #include <linux/amd-pstate.h> > > +#include <linux/topology.h> > > > > #include <acpi/processor.h> > > #include <acpi/cppc_acpi.h> > > @@ -49,6 +50,8 @@ > > > > #define AMD_PSTATE_TRANSITION_LATENCY 20000 > > #define AMD_PSTATE_TRANSITION_DELAY 1000 > > +#define AMD_PSTATE_PREFCORE_THRESHOLD 166 > > +#define AMD_PSTATE_MAX_CPPC_PERF 255 > > > > /* > > * TODO: We need more time to fine tune processors with shared memory > > solution @@ -65,6 +68,9 @@ static struct cpufreq_driver > > amd_pstate_epp_driver; static int cppc_state = > AMD_PSTATE_UNDEFINED; > > static bool cppc_enabled; > > > > +/*Preferred Core featue is supported*/ static bool prefcore = true; > > + > > /* > > * AMD Energy Preference Performance (EPP) > > * The EPP is used in the CCLK DPM controller to drive @@ -290,23 > > +296,21 @@ static inline int amd_pstate_enable(bool enable) 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; > > > > - /* > > - * TODO: Introduce AMD specific power feature. > > - * > > - * CPPC entry doesn't indicate the highest performance in some > ASICs. > > + /* 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. > > */ > > - highest_perf = amd_get_highest_perf(); > > - if (highest_perf > AMD_CPPC_HIGHEST_PERF(cap1)) > > - highest_perf = AMD_CPPC_HIGHEST_PERF(cap1); > > - > > - WRITE_ONCE(cpudata->highest_perf, highest_perf); > > + if (prefcore) > > + WRITE_ONCE(cpudata->highest_perf, > AMD_PSTATE_PREFCORE_THRESHOLD); > > + else > > + WRITE_ONCE(cpudata->highest_perf, > AMD_CPPC_HIGHEST_PERF(cap1)); > > Can we disable `preferred core` in HW? If not then when we disable > `preferred core` in software (via the cmd line param you have created), HW > still gives core ranking through highest perf register/MSR. So, we have to > filter the core ranking info form the highest perf register/MSR and set > cpudata->highest_perf accordingly. IMO we should have two variables, one > which indicated HW support and other one which indicates SW overwrite. In > this function we should be checking only HW support. > [Meng, Li (Jassmine)] We use one variable 'prefcore' to check whether the `preferred core` is supported. When either HW or SW does not support `preferred core`, it will be set to false. When 'highest_perf' is 255, it indicates that HW does not support `preferred core`. > > > > WRITE_ONCE(cpudata->nominal_perf, > AMD_CPPC_NOMINAL_PERF(cap1)); > > WRITE_ONCE(cpudata->lowest_nonlinear_perf, > > AMD_CPPC_LOWNONLIN_PERF(cap1)); @@ -318,17 +322,15 @@ 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; > > > > - highest_perf = amd_get_highest_perf(); > > - if (highest_perf > cppc_perf.highest_perf) > > - highest_perf = cppc_perf.highest_perf; > > - > > - WRITE_ONCE(cpudata->highest_perf, highest_perf); > > + if (prefcore) > > + WRITE_ONCE(cpudata->highest_perf, > AMD_PSTATE_PREFCORE_THRESHOLD); > > + else > > + WRITE_ONCE(cpudata->highest_perf, > cppc_perf.highest_perf); > > Here also we should be checking only HW support. > > > > > WRITE_ONCE(cpudata->nominal_perf, cppc_perf.nominal_perf); > > WRITE_ONCE(cpudata->lowest_nonlinear_perf, > > @@ -676,6 +678,72 @@ static void amd_perf_ctl_reset(unsigned int cpu) > > wrmsrl_on_cpu(cpu, MSR_AMD_PERF_CTL, 0); } > > > > +/* > > + * Set AMD Pstate Preferred Core enable can't be done directly from > > +cpufreq callbacks > > + * due to locking, so queue the work for later. > > + */ > > +static void amd_pstste_sched_prefcore_workfn(struct work_struct > > +*work) { > > + sched_set_itmt_support(); > > +} > > +static DECLARE_WORK(sched_prefcore_work, > > +amd_pstste_sched_prefcore_workfn); > > + > > +/** > > + * Get the highest performance register value. > > + * @cpu: CPU from which to get highest performance. > > + * @highest_perf: Return address. > > + * > > + * Return: 0 for success, -EIO otherwise. > > + */ > > +static int amd_pstate_get_highest_perf(int cpu, u64 *highest_perf) { > > + int ret; > > + > > + if (boot_cpu_has(X86_FEATURE_CPPC)) { > > + u64 cap1; > > + > > + ret = rdmsrl_safe_on_cpu(cpu, MSR_AMD_CPPC_CAP1, &cap1); > > + if (ret) > > + return ret; > > + WRITE_ONCE(*highest_perf, AMD_CPPC_HIGHEST_PERF(cap1)); > > + } else { > > + ret = cppc_get_highest_perf(cpu, highest_perf); > > + } > > + > > + return (ret); > > +} > > + > > +static void amd_pstate_init_prefcore(void) { > > + int cpu, ret; > > + u64 highest_perf; > > + > > + if (!prefcore) > > + return; > > + > > + for_each_online_cpu(cpu) { > > + ret = amd_pstate_get_highest_perf(cpu, &highest_perf); > > + if (ret) > > + break; > > + > > + sched_set_itmt_core_prio(highest_perf, cpu); > > + > > + /* check if CPPC preferred core feature is enabled*/ > > + if (highest_perf == AMD_PSTATE_MAX_CPPC_PERF) { > > + prefcore = false; > > + return; > > 255 is a valid core ranking right? > > Thanks & Regards, > Wyes > > > + } > > + } > > + > > + /* > > + * This code can be run during CPU online under the > > + * CPU hotplug locks, so sched_set_amd_prefcore_support() > > + * cannot be called from here. Queue up a work item > > + * to invoke it. > > + */ > > + schedule_work(&sched_prefcore_work); > > +} > > + > > static int amd_pstate_cpu_init(struct cpufreq_policy *policy) { > > int min_freq, max_freq, nominal_freq, lowest_nonlinear_freq, ret; > @@ > > -1037,6 +1105,12 @@ static ssize_t status_store(struct device *a, struct > device_attribute *b, > > return ret < 0 ? ret : count; > > } > > > > +static ssize_t prefcore_show(struct device *dev, > > + struct device_attribute *attr, char *buf) { > > + return sysfs_emit(buf, "%s\n", prefcore ? "enabled" : "disabled"); } > > + > > cpufreq_freq_attr_ro(amd_pstate_max_freq); > > cpufreq_freq_attr_ro(amd_pstate_lowest_nonlinear_freq); > > > > @@ -1044,6 +1118,7 @@ cpufreq_freq_attr_ro(amd_pstate_highest_perf); > > cpufreq_freq_attr_rw(energy_performance_preference); > > cpufreq_freq_attr_ro(energy_performance_available_preferences); > > static DEVICE_ATTR_RW(status); > > +static DEVICE_ATTR_RO(prefcore); > > > > static struct freq_attr *amd_pstate_attr[] = { > > &amd_pstate_max_freq, > > @@ -1063,6 +1138,7 @@ static struct freq_attr *amd_pstate_epp_attr[] = > > { > > > > static struct attribute *pstate_global_attributes[] = { > > &dev_attr_status.attr, > > + &dev_attr_prefcore.attr, > > NULL > > }; > > > > @@ -1506,6 +1582,8 @@ static int __init amd_pstate_init(void) > > } > > } > > > > + amd_pstate_init_prefcore(); > > + > > return ret; > > > > global_attr_free: > > @@ -1527,7 +1605,17 @@ static int __init amd_pstate_param(char *str) > > > > return amd_pstate_set_driver(mode_idx); } > > + > > +static int __init amd_prefcore_param(char *str) { > > + if (!strcmp(str, "disable")) > > + prefcore = false; > > + > > + return 0; > > +} > > + > > early_param("amd_pstate", amd_pstate_param); > > +early_param("amd_prefcore", amd_prefcore_param); > > > > MODULE_AUTHOR("Huang Rui <ray.huang@amd.com>"); > > MODULE_DESCRIPTION("AMD Processor P-state Frequency Driver"); > > -- > > 2.34.1 > >
diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index 9a1e194d5cf8..d02305675f66 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -37,6 +37,7 @@ #include <linux/uaccess.h> #include <linux/static_call.h> #include <linux/amd-pstate.h> +#include <linux/topology.h> #include <acpi/processor.h> #include <acpi/cppc_acpi.h> @@ -49,6 +50,8 @@ #define AMD_PSTATE_TRANSITION_LATENCY 20000 #define AMD_PSTATE_TRANSITION_DELAY 1000 +#define AMD_PSTATE_PREFCORE_THRESHOLD 166 +#define AMD_PSTATE_MAX_CPPC_PERF 255 /* * TODO: We need more time to fine tune processors with shared memory solution @@ -65,6 +68,9 @@ static struct cpufreq_driver amd_pstate_epp_driver; static int cppc_state = AMD_PSTATE_UNDEFINED; static bool cppc_enabled; +/*Preferred Core featue is supported*/ +static bool prefcore = true; + /* * AMD Energy Preference Performance (EPP) * The EPP is used in the CCLK DPM controller to drive @@ -290,23 +296,21 @@ static inline int amd_pstate_enable(bool enable) 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; - /* - * TODO: Introduce AMD specific power feature. - * - * CPPC entry doesn't indicate the highest performance in some ASICs. + /* 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. */ - highest_perf = amd_get_highest_perf(); - if (highest_perf > AMD_CPPC_HIGHEST_PERF(cap1)) - highest_perf = AMD_CPPC_HIGHEST_PERF(cap1); - - WRITE_ONCE(cpudata->highest_perf, highest_perf); + if (prefcore) + WRITE_ONCE(cpudata->highest_perf, AMD_PSTATE_PREFCORE_THRESHOLD); + else + WRITE_ONCE(cpudata->highest_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)); @@ -318,17 +322,15 @@ 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; - highest_perf = amd_get_highest_perf(); - if (highest_perf > cppc_perf.highest_perf) - highest_perf = cppc_perf.highest_perf; - - WRITE_ONCE(cpudata->highest_perf, highest_perf); + if (prefcore) + WRITE_ONCE(cpudata->highest_perf, AMD_PSTATE_PREFCORE_THRESHOLD); + else + WRITE_ONCE(cpudata->highest_perf, cppc_perf.highest_perf); WRITE_ONCE(cpudata->nominal_perf, cppc_perf.nominal_perf); WRITE_ONCE(cpudata->lowest_nonlinear_perf, @@ -676,6 +678,72 @@ static void amd_perf_ctl_reset(unsigned int cpu) wrmsrl_on_cpu(cpu, MSR_AMD_PERF_CTL, 0); } +/* + * Set AMD Pstate Preferred Core enable can't be done directly from cpufreq callbacks + * due to locking, so queue the work for later. + */ +static void amd_pstste_sched_prefcore_workfn(struct work_struct *work) +{ + sched_set_itmt_support(); +} +static DECLARE_WORK(sched_prefcore_work, amd_pstste_sched_prefcore_workfn); + +/** + * Get the highest performance register value. + * @cpu: CPU from which to get highest performance. + * @highest_perf: Return address. + * + * Return: 0 for success, -EIO otherwise. + */ +static int amd_pstate_get_highest_perf(int cpu, u64 *highest_perf) +{ + int ret; + + if (boot_cpu_has(X86_FEATURE_CPPC)) { + u64 cap1; + + ret = rdmsrl_safe_on_cpu(cpu, MSR_AMD_CPPC_CAP1, &cap1); + if (ret) + return ret; + WRITE_ONCE(*highest_perf, AMD_CPPC_HIGHEST_PERF(cap1)); + } else { + ret = cppc_get_highest_perf(cpu, highest_perf); + } + + return (ret); +} + +static void amd_pstate_init_prefcore(void) +{ + int cpu, ret; + u64 highest_perf; + + if (!prefcore) + return; + + for_each_online_cpu(cpu) { + ret = amd_pstate_get_highest_perf(cpu, &highest_perf); + if (ret) + break; + + sched_set_itmt_core_prio(highest_perf, cpu); + + /* check if CPPC preferred core feature is enabled*/ + if (highest_perf == AMD_PSTATE_MAX_CPPC_PERF) { + prefcore = false; + return; + } + } + + /* + * This code can be run during CPU online under the + * CPU hotplug locks, so sched_set_amd_prefcore_support() + * cannot be called from here. Queue up a work item + * to invoke it. + */ + schedule_work(&sched_prefcore_work); +} + static int amd_pstate_cpu_init(struct cpufreq_policy *policy) { int min_freq, max_freq, nominal_freq, lowest_nonlinear_freq, ret; @@ -1037,6 +1105,12 @@ static ssize_t status_store(struct device *a, struct device_attribute *b, return ret < 0 ? ret : count; } +static ssize_t prefcore_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "%s\n", prefcore ? "enabled" : "disabled"); +} + cpufreq_freq_attr_ro(amd_pstate_max_freq); cpufreq_freq_attr_ro(amd_pstate_lowest_nonlinear_freq); @@ -1044,6 +1118,7 @@ cpufreq_freq_attr_ro(amd_pstate_highest_perf); cpufreq_freq_attr_rw(energy_performance_preference); cpufreq_freq_attr_ro(energy_performance_available_preferences); static DEVICE_ATTR_RW(status); +static DEVICE_ATTR_RO(prefcore); static struct freq_attr *amd_pstate_attr[] = { &amd_pstate_max_freq, @@ -1063,6 +1138,7 @@ static struct freq_attr *amd_pstate_epp_attr[] = { static struct attribute *pstate_global_attributes[] = { &dev_attr_status.attr, + &dev_attr_prefcore.attr, NULL }; @@ -1506,6 +1582,8 @@ static int __init amd_pstate_init(void) } } + amd_pstate_init_prefcore(); + return ret; global_attr_free: @@ -1527,7 +1605,17 @@ static int __init amd_pstate_param(char *str) return amd_pstate_set_driver(mode_idx); } + +static int __init amd_prefcore_param(char *str) +{ + if (!strcmp(str, "disable")) + prefcore = false; + + return 0; +} + early_param("amd_pstate", amd_pstate_param); +early_param("amd_prefcore", amd_prefcore_param); MODULE_AUTHOR("Huang Rui <ray.huang@amd.com>"); MODULE_DESCRIPTION("AMD Processor P-state Frequency Driver");