| Message ID | 20231030063403.3502816-4-li.meng@amd.com |
|---|---|
| State | Superseded |
| Headers | show |
| Series | amd-pstate preferred core | expand |
[AMD Official Use Only - General] Hi meng Li, > -----Original Message----- > From: Meng, Li (Jassmine) <Li.Meng@amd.com> > Sent: Monday, October 30, 2023 2:34 PM > To: Rafael J . Wysocki <rafael.j.wysocki@intel.com>; Huang, Ray > <Ray.Huang@amd.com> > Cc: 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>; Oleksandr Natalenko > <oleksandr@natalenko.name>; Meng, Li (Jassmine) <Li.Meng@amd.com>; > Karny, Wyes <Wyes.Karny@amd.com> > Subject: [PATCH V10 3/7] cpufreq: amd-pstate: Enable amd-pstate preferred > core supporting. > > 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 a variable hw_prefcore in cpudata structure. It will check if the processor > and power firmware support preferred core feature. > > Add one new early parameter `disable` to allow user to disable the preferred > core. > > Only when hardware supports preferred core and user set `enabled` in early > parameter, amd pstate driver supports preferred core featue. > > Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name> > Reviewed-by: Huang Rui <ray.huang@amd.com> > Reviewed-by: Wyes Karny <wyes.karny@amd.com> > Reviewed-by: Mario Limonciello <mario.limonciello@amd.com> > Co-developed-by: Perry Yuan <Perry.Yuan@amd.com> > Signed-off-by: Perry Yuan <Perry.Yuan@amd.com> > Signed-off-by: Meng Li <li.meng@amd.com> > --- > drivers/cpufreq/amd-pstate.c | 141 > +++++++++++++++++++++++++++++++---- > include/linux/amd-pstate.h | 4 + > 2 files changed, 129 insertions(+), 16 deletions(-) > > diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c > index 9a1e194d5cf8..2033e5e70017 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 +50,7 @@ > > #define AMD_PSTATE_TRANSITION_LATENCY 20000 > #define AMD_PSTATE_TRANSITION_DELAY 1000 > +#define AMD_PSTATE_PREFCORE_THRESHOLD 166 > > /* > * TODO: We need more time to fine tune processors with shared memory > solution @@ -64,6 +66,7 @@ static struct cpufreq_driver amd_pstate_driver; > static struct cpufreq_driver amd_pstate_epp_driver; static int cppc_state = > AMD_PSTATE_UNDEFINED; static bool cppc_enabled; > +static bool amd_pstate_prefcore = true; > > /* > * AMD Energy Preference Performance (EPP) @@ -290,23 +293,21 @@ > 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 (cpudata->hw_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 +319,15 @@ 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 (cpudata->hw_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 +675,80 @@ 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, u32 *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 { > + u64 cppc_highest_perf; > + > + ret = cppc_get_highest_perf(cpu, &cppc_highest_perf); > + if (ret) > + return ret; > + WRITE_ONCE(*highest_perf, cppc_highest_perf); > + } > + > + return (ret); > +} > + > +#define CPPC_MAX_PERF U8_MAX > + > +static void amd_pstate_init_prefcore(struct amd_cpudata *cpudata) { > + int ret, prio; > + u32 highest_perf; > + > + ret = amd_pstate_get_highest_perf(cpudata->cpu, &highest_perf); > + if (ret) > + return; > + > + cpudata->hw_prefcore = true; > + /* check if CPPC preferred core feature is enabled*/ > + if (highest_perf < CPPC_MAX_PERF) > + prio = (int)highest_perf; > + else { > + pr_debug("AMD CPPC preferred core is unsupported!\n"); > + cpudata->hw_prefcore = false; > + return; > + } > + > + if (!amd_pstate_prefcore) > + return; Move the feature state check to earlier before you call amd_pstate_get_highest_perf(). If the feature is not enabled, you have no need to read highest perf. > + > + /* > + * The priorities can be set regardless of whether or not > + * sched_set_itmt_support(true) has been called and it is valid to > + * update them at any time after it has been called. > + */ > + sched_set_itmt_core_prio(prio, cpudata->cpu); > + > + 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; > @@ -697,6 +770,8 @@ static int amd_pstate_cpu_init(struct cpufreq_policy > *policy) > > cpudata->cpu = policy->cpu; > > + amd_pstate_init_prefcore(cpudata); > + > ret = amd_pstate_init_perf(cpudata); > if (ret) > goto free_cpudata1; > @@ -845,6 +920,17 @@ static ssize_t show_amd_pstate_highest_perf(struct > cpufreq_policy *policy, > return sysfs_emit(buf, "%u\n", perf); > } > > +static ssize_t show_amd_pstate_hw_prefcore(struct cpufreq_policy *policy, > + char *buf) > +{ > + bool hw_prefcore; > + struct amd_cpudata *cpudata = policy->driver_data; > + > + hw_prefcore = READ_ONCE(cpudata->hw_prefcore); > + > + return sysfs_emit(buf, "%s\n", hw_prefcore ? "supported" : > +"unsupported"); } Replace the string with str_enabled_disabled() function that is defined as below. include/linux/string_helpers.h static inline const char *str_enabled_disabled(bool v) { return v ? "enabled" : "disabled"; } Perry. > + > static ssize_t show_energy_performance_available_preferences( > struct cpufreq_policy *policy, char *buf) > { @@ -1037,18 +1123,27 @@ 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", amd_pstate_prefcore ? "enabled" : > +"disabled"); } Replace the string with str_enabled_disabled() function that is defined as below. include/linux/string_helpers.h > + > cpufreq_freq_attr_ro(amd_pstate_max_freq); > cpufreq_freq_attr_ro(amd_pstate_lowest_nonlinear_freq); > > cpufreq_freq_attr_ro(amd_pstate_highest_perf); > +cpufreq_freq_attr_ro(amd_pstate_hw_prefcore); > 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, > &amd_pstate_lowest_nonlinear_freq, > &amd_pstate_highest_perf, > + &amd_pstate_hw_prefcore, > NULL, > }; > > @@ -1056,6 +1151,7 @@ static struct freq_attr *amd_pstate_epp_attr[] = { > &amd_pstate_max_freq, > &amd_pstate_lowest_nonlinear_freq, > &amd_pstate_highest_perf, > + &amd_pstate_hw_prefcore, > &energy_performance_preference, > &energy_performance_available_preferences, > NULL, > @@ -1063,6 +1159,7 @@ static struct freq_attr *amd_pstate_epp_attr[] = { > > static struct attribute *pstate_global_attributes[] = { > &dev_attr_status.attr, > + &dev_attr_prefcore.attr, > NULL > }; > > @@ -1114,6 +1211,8 @@ static int amd_pstate_epp_cpu_init(struct > cpufreq_policy *policy) > cpudata->cpu = policy->cpu; > cpudata->epp_policy = 0; > > + amd_pstate_init_prefcore(cpudata); > + > ret = amd_pstate_init_perf(cpudata); > if (ret) > goto free_cpudata1; > @@ -1527,7 +1626,17 @@ 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")) > + amd_pstate_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"); diff --git > a/include/linux/amd-pstate.h b/include/linux/amd-pstate.h index > 446394f84606..87e140e9e6db 100644 > --- a/include/linux/amd-pstate.h > +++ b/include/linux/amd-pstate.h > @@ -52,6 +52,9 @@ struct amd_aperf_mperf { > * @prev: Last Aperf/Mperf/tsc count value read from register > * @freq: current cpu frequency value > * @boost_supported: check whether the Processor or SBIOS supports boost > mode > + * @hw_prefcore: check whether HW supports preferred core featue. > + * Only when hw_prefcore and early prefcore param are true, > + * AMD P-State driver supports preferred core featue. > * @epp_policy: Last saved policy used to set energy-performance preference > * @epp_cached: Cached CPPC energy-performance preference value > * @policy: Cpufreq policy value > @@ -81,6 +84,7 @@ struct amd_cpudata { > > u64 freq; > bool boost_supported; > + bool hw_prefcore; > > /* EPP feature related attributes*/ > s16 epp_policy; > -- > 2.34.1
[AMD Official Use Only - General] Hi perry： > -----Original Message----- > From: Yuan, Perry <Perry.Yuan@amd.com> > Sent: Thursday, November 2, 2023 5:06 PM > To: Meng, Li (Jassmine) <Li.Meng@amd.com>; Rafael J . Wysocki > <rafael.j.wysocki@intel.com>; Huang, Ray <Ray.Huang@amd.com> > Cc: 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>; Du, Xiaojian <Xiaojian.Du@amd.com>; Viresh > Kumar <viresh.kumar@linaro.org>; Borislav Petkov <bp@alien8.de>; > Oleksandr Natalenko <oleksandr@natalenko.name>; Karny, Wyes > <Wyes.Karny@amd.com> > Subject: RE: [PATCH V10 3/7] cpufreq: amd-pstate: Enable amd-pstate > preferred core supporting. > > [AMD Official Use Only - General] > > Hi meng Li, > > > > -----Original Message----- > > From: Meng, Li (Jassmine) <Li.Meng@amd.com> > > Sent: Monday, October 30, 2023 2:34 PM > > To: Rafael J . Wysocki <rafael.j.wysocki@intel.com>; Huang, Ray > > <Ray.Huang@amd.com> > > Cc: 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>; Oleksandr Natalenko <oleksandr@natalenko.name>; > Meng, > > Li (Jassmine) <Li.Meng@amd.com>; Karny, Wyes <Wyes.Karny@amd.com> > > Subject: [PATCH V10 3/7] cpufreq: amd-pstate: Enable amd-pstate > > preferred core supporting. > > > > 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 a variable hw_prefcore in cpudata structure. It will check if the > > processor and power firmware support preferred core feature. > > > > Add one new early parameter `disable` to allow user to disable the > > preferred core. > > > > Only when hardware supports preferred core and user set `enabled` in > > early parameter, amd pstate driver supports preferred core featue. > > > > Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name> > > Reviewed-by: Huang Rui <ray.huang@amd.com> > > Reviewed-by: Wyes Karny <wyes.karny@amd.com> > > Reviewed-by: Mario Limonciello <mario.limonciello@amd.com> > > Co-developed-by: Perry Yuan <Perry.Yuan@amd.com> > > Signed-off-by: Perry Yuan <Perry.Yuan@amd.com> > > Signed-off-by: Meng Li <li.meng@amd.com> > > --- > > drivers/cpufreq/amd-pstate.c | 141 > > +++++++++++++++++++++++++++++++---- > > include/linux/amd-pstate.h | 4 + > > 2 files changed, 129 insertions(+), 16 deletions(-) > > > > diff --git a/drivers/cpufreq/amd-pstate.c > > b/drivers/cpufreq/amd-pstate.c index 9a1e194d5cf8..2033e5e70017 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 +50,7 @@ > > > > #define AMD_PSTATE_TRANSITION_LATENCY 20000 > > #define AMD_PSTATE_TRANSITION_DELAY 1000 > > +#define AMD_PSTATE_PREFCORE_THRESHOLD 166 > > > > /* > > * TODO: We need more time to fine tune processors with shared memory > > solution @@ -64,6 +66,7 @@ static struct cpufreq_driver > > amd_pstate_driver; static struct cpufreq_driver amd_pstate_epp_driver; > > static int cppc_state = AMD_PSTATE_UNDEFINED; static bool > > cppc_enabled; > > +static bool amd_pstate_prefcore = true; > > > > /* > > * AMD Energy Preference Performance (EPP) @@ -290,23 +293,21 @@ > > 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 (cpudata->hw_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 +319,15 @@ 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 (cpudata->hw_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 +675,80 @@ 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, u32 *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 { > > + u64 cppc_highest_perf; > > + > > + ret = cppc_get_highest_perf(cpu, &cppc_highest_perf); > > + if (ret) > > + return ret; > > + WRITE_ONCE(*highest_perf, cppc_highest_perf); > > + } > > + > > + return (ret); > > +} > > + > > +#define CPPC_MAX_PERF U8_MAX > > + > > +static void amd_pstate_init_prefcore(struct amd_cpudata *cpudata) { > > + int ret, prio; > > + u32 highest_perf; > > + > > + ret = amd_pstate_get_highest_perf(cpudata->cpu, &highest_perf); > > + if (ret) > > + return; > > + > > + cpudata->hw_prefcore = true; > > + /* check if CPPC preferred core feature is enabled*/ > > + if (highest_perf < CPPC_MAX_PERF) > > + prio = (int)highest_perf; > > + else { > > + pr_debug("AMD CPPC preferred core is unsupported!\n"); > > + cpudata->hw_prefcore = false; > > + return; > > + } > > + > > + if (!amd_pstate_prefcore) > > + return; > > Move the feature state check to earlier before you call > amd_pstate_get_highest_perf(). > If the feature is not enabled, you have no need to read highest perf. > [Meng, Li (Jassmine)] I need to set hw_prefcore by highest_perf. Therefore, the judgment condition “amd_pstate_prefcore” cannot be moved forward. > > > + > > + /* > > + * The priorities can be set regardless of whether or not > > + * sched_set_itmt_support(true) has been called and it is valid to > > + * update them at any time after it has been called. > > + */ > > + sched_set_itmt_core_prio(prio, cpudata->cpu); > > + > > + 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; @@ -697,6 +770,8 @@ static int amd_pstate_cpu_init(struct > > cpufreq_policy > > *policy) > > > > cpudata->cpu = policy->cpu; > > > > + amd_pstate_init_prefcore(cpudata); > > + > > ret = amd_pstate_init_perf(cpudata); > > if (ret) > > goto free_cpudata1; > > @@ -845,6 +920,17 @@ static ssize_t > > show_amd_pstate_highest_perf(struct > > cpufreq_policy *policy, > > return sysfs_emit(buf, "%u\n", perf); } > > > > +static ssize_t show_amd_pstate_hw_prefcore(struct cpufreq_policy > *policy, > > + char *buf) { > > + bool hw_prefcore; > > + struct amd_cpudata *cpudata = policy->driver_data; > > + > > + hw_prefcore = READ_ONCE(cpudata->hw_prefcore); > > + > > + return sysfs_emit(buf, "%s\n", hw_prefcore ? "supported" : > > +"unsupported"); } > > Replace the string with str_enabled_disabled() function that is defined as > below. > > include/linux/string_helpers.h > > static inline const char *str_enabled_disabled(bool v) { > return v ? "enabled" : "disabled"; } > > Perry. > > > + > > static ssize_t show_energy_performance_available_preferences( > > struct cpufreq_policy *policy, char > > *buf) { @@ -1037,18 +1123,27 @@ 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", amd_pstate_prefcore ? "enabled" : > > +"disabled"); } > > Replace the string with str_enabled_disabled() function that is defined as > below. > > include/linux/string_helpers.h > > > > + > > cpufreq_freq_attr_ro(amd_pstate_max_freq); > > cpufreq_freq_attr_ro(amd_pstate_lowest_nonlinear_freq); > > > > cpufreq_freq_attr_ro(amd_pstate_highest_perf); > > +cpufreq_freq_attr_ro(amd_pstate_hw_prefcore); > > 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, > > &amd_pstate_lowest_nonlinear_freq, > > &amd_pstate_highest_perf, > > + &amd_pstate_hw_prefcore, > > NULL, > > }; > > > > @@ -1056,6 +1151,7 @@ static struct freq_attr *amd_pstate_epp_attr[] = > { > > &amd_pstate_max_freq, > > &amd_pstate_lowest_nonlinear_freq, > > &amd_pstate_highest_perf, > > + &amd_pstate_hw_prefcore, > > &energy_performance_preference, > > &energy_performance_available_preferences, > > NULL, > > @@ -1063,6 +1159,7 @@ static struct freq_attr *amd_pstate_epp_attr[] = > > { > > > > static struct attribute *pstate_global_attributes[] = { > > &dev_attr_status.attr, > > + &dev_attr_prefcore.attr, > > NULL > > }; > > > > @@ -1114,6 +1211,8 @@ static int amd_pstate_epp_cpu_init(struct > > cpufreq_policy *policy) > > cpudata->cpu = policy->cpu; > > cpudata->epp_policy = 0; > > > > + amd_pstate_init_prefcore(cpudata); > > + > > ret = amd_pstate_init_perf(cpudata); > > if (ret) > > goto free_cpudata1; > > @@ -1527,7 +1626,17 @@ 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")) > > + amd_pstate_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"); diff > > --git a/include/linux/amd-pstate.h b/include/linux/amd-pstate.h index > > 446394f84606..87e140e9e6db 100644 > > --- a/include/linux/amd-pstate.h > > +++ b/include/linux/amd-pstate.h > > @@ -52,6 +52,9 @@ struct amd_aperf_mperf { > > * @prev: Last Aperf/Mperf/tsc count value read from register > > * @freq: current cpu frequency value > > * @boost_supported: check whether the Processor or SBIOS supports > > boost mode > > + * @hw_prefcore: check whether HW supports preferred core featue. > > + * Only when hw_prefcore and early prefcore param are true, > > + * AMD P-State driver supports preferred core featue. > > * @epp_policy: Last saved policy used to set energy-performance > preference > > * @epp_cached: Cached CPPC energy-performance preference value > > * @policy: Cpufreq policy value > > @@ -81,6 +84,7 @@ struct amd_cpudata { > > > > u64 freq; > > bool boost_supported; > > + bool hw_prefcore; > > > > /* EPP feature related attributes*/ > > s16 epp_policy; > > -- > > 2.34.1 >
diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index 9a1e194d5cf8..2033e5e70017 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 +50,7 @@ #define AMD_PSTATE_TRANSITION_LATENCY 20000 #define AMD_PSTATE_TRANSITION_DELAY 1000 +#define AMD_PSTATE_PREFCORE_THRESHOLD 166 /* * TODO: We need more time to fine tune processors with shared memory solution @@ -64,6 +66,7 @@ static struct cpufreq_driver amd_pstate_driver; static struct cpufreq_driver amd_pstate_epp_driver; static int cppc_state = AMD_PSTATE_UNDEFINED; static bool cppc_enabled; +static bool amd_pstate_prefcore = true; /* * AMD Energy Preference Performance (EPP) @@ -290,23 +293,21 @@ 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 (cpudata->hw_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 +319,15 @@ 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 (cpudata->hw_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 +675,80 @@ 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, u32 *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 { + u64 cppc_highest_perf; + + ret = cppc_get_highest_perf(cpu, &cppc_highest_perf); + if (ret) + return ret; + WRITE_ONCE(*highest_perf, cppc_highest_perf); + } + + return (ret); +} + +#define CPPC_MAX_PERF U8_MAX + +static void amd_pstate_init_prefcore(struct amd_cpudata *cpudata) +{ + int ret, prio; + u32 highest_perf; + + ret = amd_pstate_get_highest_perf(cpudata->cpu, &highest_perf); + if (ret) + return; + + cpudata->hw_prefcore = true; + /* check if CPPC preferred core feature is enabled*/ + if (highest_perf < CPPC_MAX_PERF) + prio = (int)highest_perf; + else { + pr_debug("AMD CPPC preferred core is unsupported!\n"); + cpudata->hw_prefcore = false; + return; + } + + if (!amd_pstate_prefcore) + return; + + /* + * The priorities can be set regardless of whether or not + * sched_set_itmt_support(true) has been called and it is valid to + * update them at any time after it has been called. + */ + sched_set_itmt_core_prio(prio, cpudata->cpu); + + 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; @@ -697,6 +770,8 @@ static int amd_pstate_cpu_init(struct cpufreq_policy *policy) cpudata->cpu = policy->cpu; + amd_pstate_init_prefcore(cpudata); + ret = amd_pstate_init_perf(cpudata); if (ret) goto free_cpudata1; @@ -845,6 +920,17 @@ static ssize_t show_amd_pstate_highest_perf(struct cpufreq_policy *policy, return sysfs_emit(buf, "%u\n", perf); } +static ssize_t show_amd_pstate_hw_prefcore(struct cpufreq_policy *policy, + char *buf) +{ + bool hw_prefcore; + struct amd_cpudata *cpudata = policy->driver_data; + + hw_prefcore = READ_ONCE(cpudata->hw_prefcore); + + return sysfs_emit(buf, "%s\n", hw_prefcore ? "supported" : "unsupported"); +} + static ssize_t show_energy_performance_available_preferences( struct cpufreq_policy *policy, char *buf) { @@ -1037,18 +1123,27 @@ 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", amd_pstate_prefcore ? "enabled" : "disabled"); +} + cpufreq_freq_attr_ro(amd_pstate_max_freq); cpufreq_freq_attr_ro(amd_pstate_lowest_nonlinear_freq); cpufreq_freq_attr_ro(amd_pstate_highest_perf); +cpufreq_freq_attr_ro(amd_pstate_hw_prefcore); 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, &amd_pstate_lowest_nonlinear_freq, &amd_pstate_highest_perf, + &amd_pstate_hw_prefcore, NULL, }; @@ -1056,6 +1151,7 @@ static struct freq_attr *amd_pstate_epp_attr[] = { &amd_pstate_max_freq, &amd_pstate_lowest_nonlinear_freq, &amd_pstate_highest_perf, + &amd_pstate_hw_prefcore, &energy_performance_preference, &energy_performance_available_preferences, NULL, @@ -1063,6 +1159,7 @@ static struct freq_attr *amd_pstate_epp_attr[] = { static struct attribute *pstate_global_attributes[] = { &dev_attr_status.attr, + &dev_attr_prefcore.attr, NULL }; @@ -1114,6 +1211,8 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy) cpudata->cpu = policy->cpu; cpudata->epp_policy = 0; + amd_pstate_init_prefcore(cpudata); + ret = amd_pstate_init_perf(cpudata); if (ret) goto free_cpudata1; @@ -1527,7 +1626,17 @@ 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")) + amd_pstate_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"); diff --git a/include/linux/amd-pstate.h b/include/linux/amd-pstate.h index 446394f84606..87e140e9e6db 100644 --- a/include/linux/amd-pstate.h +++ b/include/linux/amd-pstate.h @@ -52,6 +52,9 @@ struct amd_aperf_mperf { * @prev: Last Aperf/Mperf/tsc count value read from register * @freq: current cpu frequency value * @boost_supported: check whether the Processor or SBIOS supports boost mode + * @hw_prefcore: check whether HW supports preferred core featue. + * Only when hw_prefcore and early prefcore param are true, + * AMD P-State driver supports preferred core featue. * @epp_policy: Last saved policy used to set energy-performance preference * @epp_cached: Cached CPPC energy-performance preference value * @policy: Cpufreq policy value @@ -81,6 +84,7 @@ struct amd_cpudata { u64 freq; bool boost_supported; + bool hw_prefcore; /* EPP feature related attributes*/ s16 epp_policy;