Re: [PATCH v2 1/5] cpufreq/amd-pstate: Add dynamic energy performance preference

["Gautham R. Shenoy" <gautham.shenoy@amd.com>]

Hello Mario,

On Tue, Mar 04, 2025 at 09:23:23AM -0600, Mario Limonciello wrote:
> From: Mario Limonciello <mario.limonciello@amd.com>
> 
> Dynamic energy performance preference will change the EPP profile
> based on whether the machine is running on AC or DC power.
> 
> A notification chain from the power supply core is used to adjust
> EPP values on plug in or plug out events.
> 
> For non-server systems:
>     * the default EPP for AC mode is `performance`.
>     * the default EPP for DC mode is `balance_performance`.
> 
> Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
> ---
> v1->v2:
>  * Change defaults to performance (AC) and balance_performance (DC)
>  * Default Kconfig to disabled for now
>  * Rebase on latest branch
> ---
>  Documentation/admin-guide/pm/amd-pstate.rst |  18 ++-
>  drivers/cpufreq/Kconfig.x86                 |  12 ++
>  drivers/cpufreq/amd-pstate.c                | 129 ++++++++++++++++++--
>  drivers/cpufreq/amd-pstate.h                |   5 +-
>  4 files changed, 155 insertions(+), 9 deletions(-)
> 
> diff --git a/Documentation/admin-guide/pm/amd-pstate.rst b/Documentation/admin-guide/pm/amd-pstate.rst
> index 412423c54f258..2e076650dc77c 100644
> --- a/Documentation/admin-guide/pm/amd-pstate.rst
> +++ b/Documentation/admin-guide/pm/amd-pstate.rst

[...snip..]

> @@ -311,6 +311,22 @@ boost or `1` to enable it, for the respective CPU using the sysfs path
>  Other performance and frequency values can be read back from
>  ``/sys/devices/system/cpu/cpuX/acpi_cppc/``, see :ref:`cppc_sysfs`.
>  
> +Dynamic energy performance profile
> +==================================
> +The amd-pstate driver supports dynamically selecting the energy performance
> +profile based on whether the machine is running on AC or DC power.
> +
> +Whether this behavior is enabled by default with the kernel config option
> +`CONFIG_X86_AMD_PSTATE_DYNAMIC_EPP`. This behavior can also be overridden
> +at runtime by the sysfs file ``/sys/devices/system/cpu/cpufreq/policyX/dynamic_epp``.
> +
> +When set to enabled, the driver will select a different energy performance
> +profile when the machine is running on battery or AC power.
> +When set to disabled, the driver will not change the energy performance profile
> +based on the power source and will not react to user desired power state.
> +
> +Attempting to manually write to the ``energy_performance_preference`` sysfs
> +file will fail when ``dynamic_epp`` is enabled.
>  
>  ``amd-pstate`` vs ``acpi-cpufreq``
>  ======================================
> diff --git a/drivers/cpufreq/Kconfig.x86 b/drivers/cpufreq/Kconfig.x86
> index 97c2d4f15d76e..c5ef92634ddf4 100644
> --- a/drivers/cpufreq/Kconfig.x86
> +++ b/drivers/cpufreq/Kconfig.x86
> @@ -68,6 +68,18 @@ config X86_AMD_PSTATE_DEFAULT_MODE
>  	  For details, take a look at:
>  	  <file:Documentation/admin-guide/pm/amd-pstate.rst>.
>  
> +config X86_AMD_PSTATE_DYNAMIC_EPP
> +	bool "AMD Processor P-State dynamic EPP support"
> +	depends on X86_AMD_PSTATE
> +	default n
> +	help
> +	  Allow the kenrel to dynamically change the energy performance
                    ^^^^^^
		    kernel
		    

> +	  value from events like ACPI platform profile and AC adapter plug
> +	  events.
> +
> +	  This feature can also be changed at runtime, this configuration
> +	  option only sets the kernel default value behavior.
> +
>  config X86_AMD_PSTATE_UT
>  	tristate "selftest for AMD Processor P-State driver"
>  	depends on X86 && ACPI_PROCESSOR
> diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
> index e98ef41083ba1..f00fb4ba9f26e 100644
> --- a/drivers/cpufreq/amd-pstate.c
> +++ b/drivers/cpufreq/amd-pstate.c
> @@ -36,6 +36,7 @@
>  #include <linux/io.h>
>  #include <linux/delay.h>
>  #include <linux/uaccess.h>
> +#include <linux/power_supply.h>
>  #include <linux/static_call.h>
>  #include <linux/topology.h>
>  
> @@ -86,6 +87,7 @@ static struct cpufreq_driver amd_pstate_driver;
>  static struct cpufreq_driver amd_pstate_epp_driver;
>  static int cppc_state = AMD_PSTATE_UNDEFINED;
>  static bool amd_pstate_prefcore = true;
> +static bool dynamic_epp = CONFIG_X86_AMD_PSTATE_DYNAMIC_EPP;
>  static struct quirk_entry *quirks;
>  
>  /*
> @@ -1050,6 +1052,73 @@ static void amd_pstate_cpu_exit(struct cpufreq_policy *policy)
>  	kfree(cpudata);
>  }
>  
> +static int amd_pstate_get_balanced_epp(struct cpufreq_policy *policy)

Can we rename this function as amd_pstate_get_dynamic_epp() ?

Because the values being returned may not be
balance_performance/balance_power.

> +{
> +	struct amd_cpudata *cpudata = policy->driver_data;
> +
> +	if (power_supply_is_system_supplied())
> +		return cpudata->epp_default_ac;
> +	else
> +		return cpudata->epp_default_dc;
> +}
> +
> +static int amd_pstate_power_supply_notifier(struct notifier_block *nb,
> +					    unsigned long event, void *data)
> +{
> +	struct amd_cpudata *cpudata = container_of(nb, struct amd_cpudata, power_nb);
> +	struct cpufreq_policy *policy __free(put_cpufreq_policy) = cpufreq_cpu_get(cpudata->cpu);
> +	u8 epp;
> +	int ret;
> +
> +	if (event != PSY_EVENT_PROP_CHANGED)
> +		return NOTIFY_OK;
> +
> +	epp = amd_pstate_get_balanced_epp(policy);
> +
> +	ret = amd_pstate_set_epp(policy, epp);
> +	if (ret)
> +		pr_warn("Failed to set CPU %d EPP %u: %d\n", cpudata->cpu, epp, ret);
> +
> +	return NOTIFY_OK;
> +}
> +static void amd_pstate_clear_dynamic_epp(struct cpufreq_policy *policy)
> +{
> +	struct amd_cpudata *cpudata = policy->driver_data;
> +
> +	if (cpudata->power_nb.notifier_call)
> +		power_supply_unreg_notifier(&cpudata->power_nb);
> +	cpudata->dynamic_epp = false;
> +}
> +
> +static int amd_pstate_set_dynamic_epp(struct cpufreq_policy *policy)
> +{
> +	struct amd_cpudata *cpudata = policy->driver_data;
> +	int ret;
> +	u8 epp;
> +
> +	epp = amd_pstate_get_balanced_epp(policy);
> +	ret = amd_pstate_set_epp(policy, epp);
> +	if (ret)
> +		return ret;
> +
> +	/* only enable notifier if things will actually change */
> +	if (cpudata->epp_default_ac != cpudata->epp_default_dc) {
> +		ret = power_supply_reg_notifier(&cpudata->power_nb);
> +		if (ret)
> +			goto cleanup;
> +		cpudata->power_nb.notifier_call = amd_pstate_power_supply_notifier;
> +	}
> +
> +	cpudata->dynamic_epp = true;
> +
> +	return 0;
> +
> +cleanup:
> +	amd_pstate_clear_dynamic_epp(policy);
> +
> +	return ret;
> +}
> +
>  /* Sysfs attributes */
>  
>  /*
> @@ -1146,6 +1215,11 @@ static ssize_t store_energy_performance_preference(
>  	ssize_t ret;
>  	u8 epp;
>  
> +	if (cpudata->dynamic_epp) {
> +		pr_debug("EPP cannot be set when dynamic EPP is enabled\n");
> +		return -EBUSY;
> +	}
> +
>  	ret = sscanf(buf, "%20s", str_preference);
>  	if (ret != 1)
>  		return -EINVAL;
> @@ -1154,10 +1228,10 @@ static ssize_t store_energy_performance_preference(
>  	if (ret < 0)
>  		return -EINVAL;
>  
> -	if (!ret)
> -		epp = cpudata->epp_default;
> -	else
> +	if (ret)
>  		epp = epp_values[ret];
> +	else
> +		epp = amd_pstate_get_balanced_epp(policy);
>  
>  	if (epp > 0 && policy->policy == CPUFREQ_POLICY_PERFORMANCE) {
>  		pr_debug("EPP cannot be set under performance policy\n");
> @@ -1165,6 +1239,8 @@ static ssize_t store_energy_performance_preference(
>  	}
>  
>  	ret = amd_pstate_set_epp(policy, epp);
> +	if (ret)
> +		return ret;

Isn't this unecessary given that the next line is doing exactly this ?

>  
>  	return ret ? ret : count;
>  }

Rest of the patch looks good to me.

-- 
Thanks and Regards
gautham.