Re: [PATCH v4 2/2] ACPI: CPPC: Add ospm_nominal_perf support

[Sumit Gupta <sumitg@nvidia.com>]

On 28/05/26 17:42, Pierre Gondois wrote:
> External email: Use caution opening links or attachments
>
>
> Hello Sumit,
>
> On 5/27/26 21:46, Sumit Gupta wrote:
>> Expose the OSPM Nominal Performance register (ACPI 6.6, Section
>> 8.4.6.1.2.6), which conveys the desired nominal performance level
>> at which the platform may run. Unlike the existing read-only
>> Nominal Performance register, it is writable and lets OSPM
>> request a lower nominal level than the platform-reported nominal.
>> The platform classifies performance above this level as boosted
>> and below as throttled for its power/thermal decisions.
>>
>> It is exposed as a per-policy cpufreq sysfs attribute in kHz, to
>> match the cpufreq sysfs unit convention:
>>
>>    /sys/devices/system/cpu/cpufreq/policyN/ospm_nominal_freq
>>
>> The attribute is documented in
>> Documentation/ABI/testing/sysfs-devices-system-cpu.
>>
>> Writes are converted to perf via cppc_khz_to_perf(), validated
>> against [Lowest Performance, Nominal Performance], and applied to
>> every CPU in policy->cpus.
>>
>> The register is write-only; the kernel caches the last written
>> value in struct cppc_cpudata for sysfs readback (returns 0 until
>> userspace writes a value).
>>
>> Signed-off-by: Sumit Gupta <sumitg@nvidia.com>
>> ---
>>   .../ABI/testing/sysfs-devices-system-cpu      | 17 ++++++
>>   drivers/acpi/cppc_acpi.c                      | 35 +++++++++++
>>   drivers/cpufreq/cppc_cpufreq.c                | 60 +++++++++++++++++++
>>   include/acpi/cppc_acpi.h                      | 12 ++++
>>   4 files changed, 124 insertions(+)
>>
>> diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu 
>> b/Documentation/ABI/testing/sysfs-devices-system-cpu
>> index 82d10d556cc8..ac1bf1b89ac4 100644
>> --- a/Documentation/ABI/testing/sysfs-devices-system-cpu
>> +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
>> @@ -346,6 +346,23 @@ Description:     Performance Limited
>>
>>               This file is only present if the cppc-cpufreq driver is 
>> in use.
>>
>> +What: /sys/devices/system/cpu/cpuX/cpufreq/ospm_nominal_freq
>> +Date:                May 2026
>> +Contact:     linux-pm@vger.kernel.org
>> +Description: OSPM Nominal Performance (kHz)
>> +
>> +             OSPM uses this attribute to request a nominal performance
>> +             level lower than the platform-reported nominal. The
>> +             platform treats performance above this level as boost
>> +             and below as throttle for power and thermal decisions.
>> +
>> +             Read returns the last written value in kHz, or 0 if no
>> +             value has been written. Write a kHz value in the range
>> +             [lowest_freq, nominal_freq].
>> +
>> +             This file is only present if the cppc-cpufreq driver is
>> +             in use.
>> +
>>   What: /sys/devices/system/cpu/cpu*/cache/index3/cache_disable_{0,1}
>>   Date:               August 2008
>>   KernelVersion:      2.6.27
>> diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c
>> index c76cfafa3589..ad6ece16c30d 100644
>> --- a/drivers/acpi/cppc_acpi.c
>> +++ b/drivers/acpi/cppc_acpi.c
>> @@ -1682,6 +1682,41 @@ int cppc_set_epp(int cpu, u64 epp_val)
>>   }
>>   EXPORT_SYMBOL_GPL(cppc_set_epp);
>>
>> +/**
>> + * cppc_set_ospm_nominal_perf() - Write OSPM Nominal Performance 
>> register.
>> + * @cpu: CPU on which to write register.
>> + * @ospm_nominal_perf: Value to write to the OSPM Nominal 
>> Performance register.
>> + *
>> + * OSPM Nominal Performance conveys the desired nominal performance 
>> level
>> + * at which the platform may run. Per ACPI 6.6, s8.4.6.1.2.6, the value
>> + * must lie within [Lowest Performance, Nominal Performance] and may be
>> + * set independently of Minimum, Maximum and Desired performance.
>> + *
>> + * Return: 0 on success or negative error code.
>> + */
>> +int cppc_set_ospm_nominal_perf(int cpu, u64 ospm_nominal_perf)
>> +{
>> +     struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpu);
>> +     struct cppc_perf_caps caps;
>> +     int ret;
>> +
>> +     if (!cpc_desc) {
>> +             pr_debug("No CPC descriptor for CPU:%d\n", cpu);
>> +             return -ENODEV;
>> +     }
>> +
>> +     ret = cppc_get_perf_caps(cpu, &caps);
>> +     if (ret)
>> +             return ret;
>> +
>> +     if (ospm_nominal_perf < caps.lowest_perf ||
>> +         ospm_nominal_perf > caps.nominal_perf)
>> +             return -EINVAL;
>> +
>> +     return cppc_set_reg_val(cpu, OSPM_NOMINAL_PERF, 
>> ospm_nominal_perf);
>> +}
>> +EXPORT_SYMBOL_GPL(cppc_set_ospm_nominal_perf);
>> +
>>   /**
>>    * cppc_get_auto_act_window() - Read autonomous activity window 
>> register.
>>    * @cpu: CPU from which to read register.
>> diff --git a/drivers/cpufreq/cppc_cpufreq.c 
>> b/drivers/cpufreq/cppc_cpufreq.c
>> index 15a728dea911..5c54af1655b5 100644
>> --- a/drivers/cpufreq/cppc_cpufreq.c
>> +++ b/drivers/cpufreq/cppc_cpufreq.c
>> @@ -1139,11 +1139,70 @@ static int cppc_get_perf_limited_filtered(int 
>> cpu, u64 *perf_limited)
>>   CPPC_CPUFREQ_ATTR_RW_U64(perf_limited, cppc_get_perf_limited_filtered,
>>                        cppc_set_perf_limited)
>>
>> +static ssize_t show_ospm_nominal_freq(struct cpufreq_policy *policy, 
>> char *buf)
>> +{
>> +     struct cppc_cpudata *cpu_data = policy->driver_data;
>> +     unsigned int freq_khz;
>> +
>> +     if (!cpu_data->ospm_nominal_perf_set)
>> +             return sysfs_emit(buf, "0\n");
>
> The questions on v3 might be more relevant,
> but for instance here, the ospm_nominal_perf value is not 0,
> the hardware register might contain any value.
>
> So reading the register might be more meaningful than
> returning 0.
>
>

Agreed.
In v5, reading the register instead of caching:

- Added cppc_get_ospm_nominal_perf().
- show_ospm_nominal_freq() now returns the current register value,
   or "<unsupported>" on -EOPNOTSUPP.
- Dropped the cpu_data->ospm_nominal_perf cache and the
   ospm_nominal_perf_set bool entirely.

This also follows your earlier point that being write-only doesn't mean
we can't read it (cppc_get_desired_perf() being the precedent).

Thank you,
Sumit Gupta