Re: [PATCH v4 8/8] cpufreq: CPPC: add autonomous mode boot parameter support

[Pierre Gondois <pierre.gondois@arm.com>]

On 11/5/25 12:38, Sumit Gupta wrote:
> Add kernel boot parameter 'cppc_cpufreq.auto_sel_mode' to enable CPPC
> autonomous performance selection at system startup. When autonomous mode
> is enabled, the hardware automatically adjusts CPU performance based on
> workload demands using Energy Performance Preference (EPP) hints.
>
> This parameter allows to configure the autonomous mode on all CPUs
> without requiring runtime sysfs manipulation if the 'auto_sel' register
> is present.
>
> When auto_sel_mode=1:
> - All CPUs are configured for autonomous operation during module init
> - EPP is set to performance preference (0x0) by default
> - Min/max performance bounds use defaults
> - CPU frequency scaling is handled by hardware instead of OS governor
>
> For Documentation/:
> Reviewed-by: Randy Dunlap<rdunlap@infradead.org>
> Signed-off-by: Sumit Gupta<sumitg@nvidia.com>
> ---
>   .../admin-guide/kernel-parameters.txt         |  12 ++
>   drivers/cpufreq/cppc_cpufreq.c                | 197 +++++++++++++++---
>   2 files changed, 182 insertions(+), 27 deletions(-)
>
> diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
> index b8f8f5d74093..048f84008a7e 100644
> --- a/Documentation/admin-guide/kernel-parameters.txt
> +++ b/Documentation/admin-guide/kernel-parameters.txt
> @@ -929,6 +929,18 @@
>   			Format:
>   			<first_slot>,<last_slot>,<port>,<enum_bit>[,<debug>]
>   
> +	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 supoorted by hardware
> +
>   	cpuidle.off=1	[CPU_IDLE]
>   			disable the cpuidle sub-system
>   
> diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c
> index d1b44beaddda..0a55ab011317 100644
> --- a/drivers/cpufreq/cppc_cpufreq.c
> +++ b/drivers/cpufreq/cppc_cpufreq.c
> @@ -28,8 +28,12 @@
>   #include <acpi/cppc_acpi.h>
>   
>   static struct cpufreq_driver cppc_cpufreq_driver;
> +
>   static DEFINE_MUTEX(cppc_cpufreq_update_autosel_config_lock);
>   
> +/* Autonomous Selection */
> +static bool auto_sel_mode;
> +
>   #ifdef CONFIG_ACPI_CPPC_CPUFREQ_FIE
>   static enum {
>   	FIE_UNSET = -1,
> @@ -272,8 +276,13 @@ static int cppc_cpufreq_set_target(struct cpufreq_policy *policy,
>   	freqs.old = policy->cur;
>   	freqs.new = target_freq;
>   
> +	/*
> +	 * In autonomous selection mode, hardware handles frequency scaling directly
> +	 * based on workload and EPP hints. So, skip the OS frequency set requests.
> +	 */
>   	cpufreq_freq_transition_begin(policy, &freqs);
> -	ret = cppc_set_perf(cpu, &cpu_data->perf_ctrls);
> +	if (!cpu_data->perf_caps.auto_sel)
> +		ret = cppc_set_perf(cpu, &cpu_data->perf_ctrls);
>   	cpufreq_freq_transition_end(policy, &freqs, ret != 0);
>   
>   	if (ret)
> @@ -565,6 +574,12 @@ static struct cppc_cpudata *cppc_cpufreq_get_cpu_data(unsigned int cpu)
>   		goto free_mask;
>   	}
>   
> +	ret = cppc_get_perf(cpu, &cpu_data->perf_ctrls);
> +	if (ret) {
> +		pr_debug("Err reading CPU%d perf ctrls:ret:%d\n", cpu, ret);
> +		goto free_mask;
> +	}
> +
>   	return cpu_data;
>   
>   free_mask:
> @@ -666,11 +681,81 @@ static int cppc_cpufreq_update_autosel_val(struct cpufreq_policy *policy, bool a
>   	return 0;
>   }
>   
> +static int cppc_cpufreq_update_epp_val(struct cpufreq_policy *policy, u32 epp)
> +{
> +	struct cppc_cpudata *cpu_data = policy->driver_data;
> +	unsigned int cpu = policy->cpu;
> +	int ret;
> +
> +	pr_debug("cpu%d, eppcurr:%u,new:%u\n", cpu, cpu_data->perf_ctrls.energy_perf, epp);
> +
> +	guard(mutex)(&cppc_cpufreq_update_autosel_config_lock);
Do we need to take the mutex ? Or is it reserved to auto_sel ?
> +
> +	ret = cppc_set_epp(cpu, epp);
> +	if (ret) {
> +		pr_warn("failed to set energy_perf forcpu:%d (%d)\n", cpu, ret);
> +		return ret;
> +	}
> +	cpu_data->perf_ctrls.energy_perf = epp;
> +
> +	return 0;
> +}
> +
> +/**
> + * cppc_cpufreq_update_autosel_config - Update Autonomous selection configuration
> + * @policy: cpufreq policy for the CPU
> + * @min_perf: minimum performance value to set
> + * @max_perf: maximum performance value to set
> + * @auto_sel: autonomous selection mode enable/disable (also controls min/max perf reg updates)
> + * @epp_val: energy performance preference value
> + * @update_epp: whether to update EPP register
> + * @update_policy: whether to update policy constraints
> + *
> + * Return: 0 on success, negative error code on failure
> + */
> +static int cppc_cpufreq_update_autosel_config(struct cpufreq_policy *policy,
> +					      u64 min_perf, u64 max_perf, bool auto_sel,
> +					      u32 epp_val, bool update_epp, bool update_policy)
> +{
> +	const unsigned int cpu = policy->cpu;
> +	int ret;
> +
> +	/*
> +	 * Set min/max performance registers and update policy constraints.
> +	 *   When enabling: update both registers and policy.
> +	 *   When disabling: update policy only.
> +	 * Continue even if min/max are not supported, as EPP and autosel
> +	 * might still be supported.
> +	 */
> +	ret = cppc_cpufreq_set_min_perf(policy, min_perf, auto_sel, update_policy);
> +	if (ret && ret != -EOPNOTSUPP)
> +		return ret;
> +
> +	ret = cppc_cpufreq_set_max_perf(policy, max_perf, auto_sel, update_policy);
> +	if (ret && ret != -EOPNOTSUPP)
> +		return ret;
> +
> +	if (update_epp) {
> +		ret = cppc_cpufreq_update_epp_val(policy, epp_val);
> +		if (ret)
> +			return ret;
> +	}
> +
> +	ret = cppc_cpufreq_update_autosel_val(policy, auto_sel);
> +	if (ret)
> +		return ret;
> +
> +	pr_debug("Updated autonomous config [%llu-%llu] for CPU%d\n", min_perf, max_perf, cpu);
> +
> +	return 0;
> +}
> +
>   static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy)
>   {
>   	unsigned int cpu = policy->cpu;
>   	struct cppc_cpudata *cpu_data;
>   	struct cppc_perf_caps *caps;
> +	u64 min_perf, max_perf;
>   	int ret;
>   
>   	cpu_data = cppc_cpufreq_get_cpu_data(cpu);
> @@ -734,11 +819,31 @@ 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;
> +	if (cpu_data->perf_caps.auto_sel) {
> +		ret = cppc_set_enable(cpu, true);
The CPPC enable register is optional.
However this doesn't mean CPPC is not working.
> +		if (ret) {
> +			pr_err("Failed to enable CPPC on cpu%d (%d)\n", cpu, ret);
> +			goto out;
> +		}
> +
> +		min_perf = cpu_data->perf_ctrls.min_perf ?
> +			   cpu_data->perf_ctrls.min_perf : caps->lowest_nonlinear_perf;
> +		max_perf = cpu_data->perf_ctrls.max_perf ?
> +			   cpu_data->perf_ctrls.max_perf : caps->nominal_perf;
> +
> +		ret = cppc_cpufreq_update_autosel_config(policy, min_perf, max_perf, true,
> +							 CPPC_EPP_PERFORMANCE_PREF, true, false);
> +		if (ret) {
> +			cppc_set_enable(cpu, false);
> +			goto out;
> +		}
> +	} else {
> +		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);
> @@ -910,7 +1015,6 @@ static int cppc_cpufreq_update_auto_select(struct cpufreq_policy *policy, bool e
>   	struct cppc_perf_caps *caps = &cpu_data->perf_caps;
>   	u64 min_perf = caps->lowest_nonlinear_perf;
>   	u64 max_perf = caps->nominal_perf;
> -	int ret;
>   
>   	if (enable) {
>   		if (cpu_data->perf_ctrls.min_perf)
> @@ -919,26 +1023,8 @@ static int cppc_cpufreq_update_auto_select(struct cpufreq_policy *policy, bool e
>   			max_perf = cpu_data->perf_ctrls.max_perf;
>   	}
>   
> -	/*
> -	 * Set min/max performance registers and update policy constraints.
> -	 *   When enabling: update both registers and policy.
> -	 *   When disabling: update policy only.
> -	 * Continue even if min/max are not supported, as EPP and autosel
> -	 * might still be supported.
> -	 */
> -	ret = cppc_cpufreq_set_min_perf(policy, min_perf, enable, true);
> -	if (ret && ret != -EOPNOTSUPP)
> -		return ret;
> -
> -	ret = cppc_cpufreq_set_max_perf(policy, max_perf, enable, true);
> -	if (ret && ret != -EOPNOTSUPP)
> -		return ret;
> -
> -	ret = cppc_cpufreq_update_autosel_val(policy, enable);
> -	if (ret)
> -		return ret;
> -
> -	return 0;
> +	return cppc_cpufreq_update_autosel_config(policy, min_perf, max_perf, enable,
> +						  0, false, true);
>   }
>   
>   static ssize_t store_auto_select(struct cpufreq_policy *policy, const char *buf, size_t count)
> @@ -1146,13 +1232,61 @@ static struct cpufreq_driver cppc_cpufreq_driver = {
>   	.name = "cppc_cpufreq",
>   };
>   
> +static int cppc_cpufreq_set_epp_autosel_allcpus(bool auto_sel, u64 epp)
> +{
> +	int cpu, ret;
> +
> +	for_each_present_cpu(cpu) {
> +		ret = cppc_set_epp(cpu, epp);
Isn't the EPP optional ?
If autonomous selection is available but not EPP, we will bail out.
> +		if (ret) {
> +			pr_warn("Failed to set EPP on CPU%d (%d)\n", cpu, ret);
> +			goto disable_all;
> +		}
> +
> +		ret = cppc_set_auto_sel(cpu, auto_sel);

Also, it is possible that a platform only supports autonomous selection.
In this case, writing to auto_sel will fail, but auto_sel is still relevant.

> +		if (ret) {
> +			pr_warn("Failed to set auto_sel on CPU%d (%d)\n", cpu, ret);
> +			goto disable_all;
> +		}
> +	}
> +
> +	return 0;
> +
> +disable_all:
> +	pr_warn("Disabling auto_sel for all CPUs\n");
> +	for_each_present_cpu(cpu)
> +		cppc_set_auto_sel(cpu, false);
> +
> +	return -EIO;
> +}
> +
>   static int __init cppc_cpufreq_init(void)
>   {
> +	bool auto_sel;
>   	int ret;
>   
>   	if (!acpi_cpc_valid())
>   		return -ENODEV;
>   
> +	if (auto_sel_mode) {
> +		/*
> +		 * Check if autonomous selection is supported by testing CPU 0.
> +		 * If supported, enable autonomous mode on all CPUs.
> +		 */
> +		ret = cppc_get_auto_sel(0, &auto_sel);
> +		if (!ret) {
> +			pr_info("Enabling auto_sel_mode (autonomous selection mode)\n");
> +			ret = cppc_cpufreq_set_epp_autosel_allcpus(true, CPPC_EPP_PERFORMANCE_PREF);
> +			if (ret) {
> +				pr_warn("Disabling auto_sel_mode, fallback to standard\n");
> +				auto_sel_mode = false;
> +			}
> +		} else {
> +			pr_warn("Disabling auto_sel_mode as not supported by hardware\n");
> +			auto_sel_mode = false;
> +		}
> +	}
> +
>   	cppc_freq_invariance_init();
>   	populate_efficiency_class();
>   
> @@ -1165,10 +1299,19 @@ static int __init cppc_cpufreq_init(void)
>   
>   static void __exit cppc_cpufreq_exit(void)
>   {
> +	int cpu;
> +
> +	for_each_present_cpu(cpu)
> +		cppc_set_auto_sel(cpu, false);
> +	auto_sel_mode = false;
> +
>   	cpufreq_unregister_driver(&cppc_cpufreq_driver);
>   	cppc_freq_invariance_exit();
>   }
>   
> +module_param(auto_sel_mode, bool, 0000);
> +MODULE_PARM_DESC(auto_sel_mode, "Enable Autonomous Performance Level Selection");
> +
>   module_exit(cppc_cpufreq_exit);
>   MODULE_AUTHOR("Ashwin Chaugule");
>   MODULE_DESCRIPTION("CPUFreq driver based on the ACPI CPPC v5.0+ spec");