Re: [PATCH v2] cpufreq: CPPC: add autonomous mode boot parameter support

[Jie Zhan <zhanjie9@hisilicon.com>]

Hi Sumit,

In general, I would expect this parameter only toggles on auto_sel by
default.  IIUC, other CPPC configurations (min/max/desired perf, EPP,
enable) are optional and not closely related to this.

Why including those stuff here?


Please see other questions inline.

Thanks!
Jie

On 4/25/2026 4:18 AM, Sumit Gupta wrote:
> Add a kernel boot parameter 'cppc_cpufreq.auto_sel_mode' to enable
> CPPC autonomous performance selection on all CPUs at system startup.
> When autonomous mode is enabled, the hardware automatically adjusts
> CPU performance based on workload demands using Energy Performance
> Preference (EPP) hints.
> 
> When auto_sel_mode=1:
> - Configure all CPUs for autonomous operation on first init
> - Set EPP to performance preference (0x0)
> - Use HW min/max_perf when available; otherwise initialize from caps
> - Clamp desired_perf to bounds before enabling autonomous mode
> - Hardware controls frequency instead of the OS governor
> 
> The boot parameter is applied only during first policy initialization.
> Skip applying it on CPU hotplug to preserve runtime sysfs configuration.
> 
> This patch depends on patch [2] ("cpufreq: Set policy->min and max
> as real QoS constraints") so that the policy->min/max set in
> cppc_cpufreq_cpu_init() are not overridden by cpufreq_set_policy()
> during init.
> 
> Reviewed-by: Randy Dunlap <rdunlap@infradead.org> (Documentation)
> Signed-off-by: Sumit Gupta <sumitg@nvidia.com>
> ---
> v[1] -> v2:
> - Call cppc_set_enable() unconditionally so CPPC is enabled for both
>   OS-driven and autonomous modes.
Why adding this in v2?
This looks like a separate issue since setting CPPC Enable reg doesn't seem
to be related with autonomous control.
> - Init min/max from caps instead of cppc_cpufreq_update_perf_limits()
>   as policy->min/max aren't yet populated.
> 
> [1] https://lore.kernel.org/lkml/20260317151053.2361475-1-sumitg@nvidia.com/
> [2] https://lore.kernel.org/lkml/20260423084731.1090384-2-pierre.gondois@arm.com/
> ---
>  .../admin-guide/kernel-parameters.txt         | 13 +++
>  drivers/cpufreq/cppc_cpufreq.c                | 89 +++++++++++++++++--
>  2 files changed, 97 insertions(+), 5 deletions(-)
> 
> diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
> index 0a1abed1b93c..751817b0573a 100644
> --- a/Documentation/admin-guide/kernel-parameters.txt
> +++ b/Documentation/admin-guide/kernel-parameters.txt
> @@ -1067,6 +1067,19 @@ Kernel parameters
>  			policy to use. This governor must be registered in the
>  			kernel before the cpufreq driver probes.
>  
> +	cppc_cpufreq.auto_sel_mode=
> +			[CPU_FREQ] Enable ACPI CPPC autonomous performance
> +			selection. When enabled, hardware automatically adjusts
> +			CPU frequency on all CPUs based on workload demands.
> +			In Autonomous mode, Energy Performance Preference (EPP)
> +			hints guide hardware toward performance (0x0) or energy
> +			efficiency (0xff).
> +			Requires ACPI CPPC autonomous selection register support.
> +			Format: <bool>
> +			Default: 0 (disabled)
> +			0: use cpufreq governors
> +			1: enable if supported by hardware
> +
>  	cpu_init_udelay=N
>  			[X86,EARLY] Delay for N microsec between assert and de-assert
>  			of APIC INIT to start processors.  This delay occurs
> diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c
> index 02db03d03755..672fc3058190 100644
> --- a/drivers/cpufreq/cppc_cpufreq.c
> +++ b/drivers/cpufreq/cppc_cpufreq.c
> @@ -28,6 +28,9 @@
>  
>  static struct cpufreq_driver cppc_cpufreq_driver;
>  
> +/* Autonomous Selection boot parameter */
> +static bool auto_sel_mode;
> +
>  #ifdef CONFIG_ACPI_CPPC_CPUFREQ_FIE
>  static enum {
>  	FIE_UNSET = -1,
> @@ -656,6 +659,14 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy)
>  	caps = &cpu_data->perf_caps;
>  	policy->driver_data = cpu_data;
>  
> +	/*
> +	 * Enable CPPC for both OS-driven and autonomous modes.
> +	 * The Enable register is optional - some platforms may not support it
> +	 */
> +	ret = cppc_set_enable(cpu, true);
> +	if (ret && ret != -EOPNOTSUPP)
> +		pr_warn("Failed to enable CPPC for CPU%d (%d)\n", cpu, ret);
> +
>  	min = cppc_perf_to_khz(caps, caps->lowest_nonlinear_perf);
>  	max = cppc_perf_to_khz(caps, policy->boost_enabled ?
>  			caps->highest_perf : caps->nominal_perf);
> @@ -711,11 +722,71 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy)
>  	policy->cur = cppc_perf_to_khz(caps, caps->highest_perf);
>  	cpu_data->perf_ctrls.desired_perf =  caps->highest_perf;
>  
> -	ret = cppc_set_perf(cpu, &cpu_data->perf_ctrls);
> -	if (ret) {
> -		pr_debug("Err setting perf value:%d on CPU:%d. ret:%d\n",
> -			 caps->highest_perf, cpu, ret);
> -		goto out;
> +	/*
> +	 * Enable autonomous mode on first init if boot param is set.
> +	 * Check last_governor to detect first init and skip if auto_sel
> +	 * is already enabled.
> +	 */
> +	if (auto_sel_mode && policy->last_governor[0] == '\0' &&
> +	    !cpu_data->perf_ctrls.auto_sel) {
> +		/* Init min/max_perf from caps if not already set by HW. */
> +		if (!cpu_data->perf_ctrls.min_perf)
> +			cpu_data->perf_ctrls.min_perf = caps->lowest_nonlinear_perf;
> +		if (!cpu_data->perf_ctrls.max_perf)
> +			cpu_data->perf_ctrls.max_perf = policy->boost_enabled ?
> +				caps->highest_perf : caps->nominal_perf;
Is it automatically adjusted when switching boost on and off?
> +
> +		cpu_data->perf_ctrls.desired_perf =
> +			clamp_t(u32, cpu_data->perf_ctrls.desired_perf,
> +				cpu_data->perf_ctrls.min_perf,
> +				cpu_data->perf_ctrls.max_perf);
Why do we need to clamp desire_perf here?
> +
> +		policy->cur = cppc_perf_to_khz(caps,
> +					       cpu_data->perf_ctrls.desired_perf);
> +
> +		/* EPP is optional - some platforms may not support it */
> +		ret = cppc_set_epp(cpu, CPPC_EPP_PERFORMANCE_PREF);
Why setting this to PERFORMANCE by default?
A platform can have its own default EPP value.  This would override that.
> +		if (ret && ret != -EOPNOTSUPP)
> +			pr_warn("Failed to set EPP for CPU%d (%d)\n", cpu, ret);
> +		else if (!ret)
> +			cpu_data->perf_ctrls.energy_perf = CPPC_EPP_PERFORMANCE_PREF;
> +
> +		/* Program min/max/desired into CPPC regs before enabling auto_sel. */
> +		ret = cppc_set_perf(cpu, &cpu_data->perf_ctrls);
> +		if (ret) {
> +			pr_debug("Err setting perf for autonomous mode CPU:%d ret:%d\n",
> +				 cpu, ret);
> +			goto out;
Shouldn't this be pr_warn(), or even pr_err(), if it needs to bail out?

However, IIUC setting min/max/desired perf is optional for auto_sel, so
better to pr_info() and continue setting auto_sel?
> +		}
> +
> +		ret = cppc_set_auto_sel(cpu, true);
> +		if (ret && ret != -EOPNOTSUPP) {
> +			pr_warn("Failed autonomous config for CPU%d (%d)\n",
> +				cpu, ret);
> +			goto out;
Bailing out here would end up without DVFS support.
Can we fall back to the normal OS directed mode?
> +		}
> +		if (!ret)
> +			cpu_data->perf_ctrls.auto_sel = true;
> +	}
> +
> +	if (cpu_data->perf_ctrls.auto_sel) {
> +		/* Sync policy limits from HW when autonomous mode is active */
> +		policy->min = cppc_perf_to_khz(caps,
> +					       cpu_data->perf_ctrls.min_perf ?:
> +					       caps->lowest_nonlinear_perf);
> +		policy->max = cppc_perf_to_khz(caps,
> +					       cpu_data->perf_ctrls.max_perf ?:
> +					       (policy->boost_enabled ?
> +						caps->highest_perf :
> +						caps->nominal_perf));
> +	} else {
> +		/* Normal mode: governors control frequency */
> +		ret = cppc_set_perf(cpu, &cpu_data->perf_ctrls);
> +		if (ret) {
> +			pr_debug("Err setting perf value:%d on CPU:%d. ret:%d\n",
> +				 caps->highest_perf, cpu, ret);
> +			goto out;
> +		}
>  	}
>  
>  	cppc_cpufreq_cpu_fie_init(policy);
> @@ -1035,10 +1106,18 @@ static int __init cppc_cpufreq_init(void)
>  
>  static void __exit cppc_cpufreq_exit(void)
>  {
> +	unsigned int cpu;
> +
> +	for_each_present_cpu(cpu)
> +		cppc_set_auto_sel(cpu, false);
> +
>  	cpufreq_unregister_driver(&cppc_cpufreq_driver);
>  	cppc_freq_invariance_exit();
>  }
>  
> +module_param(auto_sel_mode, bool, 0444);
> +MODULE_PARM_DESC(auto_sel_mode, "Enable CPPC autonomous performance selection at boot");
> +
>  module_exit(cppc_cpufreq_exit);
>  MODULE_AUTHOR("Ashwin Chaugule");
>  MODULE_DESCRIPTION("CPUFreq driver based on the ACPI CPPC v5.0+ spec");