diff mbox series

[V3,3/7] cpufreq: amd-pstate: Enable AMD Pstate Preferred Core Supporting.

Message ID 20230824021249.271946-4-li.meng@amd.com
State Superseded
Headers show
Series AMD Pstate Preferred Core | expand

Commit Message

Meng, Li (Jassmine) Aug. 24, 2023, 2:12 a.m. UTC
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(-)

Comments

Wyes Karny Aug. 24, 2023, 6:48 a.m. UTC | #1
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
>
Meng, Li (Jassmine) Aug. 25, 2023, 1:58 a.m. UTC | #2
[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 mbox series

Patch

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");