Re: [PATCH v9 6/8] ACPI: CPPC: Add ospm_nominal_perf support

[Sumit Gupta <sumitg@nvidia.com>]

On 09/11/26 22:34, Rafael J. Wysocki (Intel) wrote:
> External email: Use caution opening links or attachments
> 
> 
> On Mon, Nov 9, 2026 at 6:01 PM Rafael J. Wysocki (Intel)
> <rafael@kernel.org> wrote:
>>
>> On Fri, Nov 6, 2026 at 8:35 PM Sumit Gupta <sumitg@nvidia.com> wrote:
>>>
>>> Expose the OSPM Nominal Performance register (ACPI 6.6, Section
>>> 8.4.6.1.2.6), which conveys the nominal performance level at which the
>>> platform may run. Unlike the read-only Nominal Performance register, it
>>> is writable, so OSPM can ask for a nominal level below the
>>> platform-reported one, which then becomes the boundary between boosted
>>> and throttled operation.
>>>
>>> Add cppc_set_ospm_nominal_perf() to write the register. Per the spec,
>>> the value must lie in [Lowest Performance, Nominal Performance], which
>>> the caller is responsible for validating.
>>>
>>> Add cppc_ospm_nominal_perf_supported() to report whether the platform
>>> implements the register as writable, since a write-only register cannot
>>> be probed by reading it. It uses the same cpc_is_writable() test as the
>>> setter, so support is never reported for a register that a write would
>>> reject, and takes cpc_desc_lock while looking the descriptor up.
>>>
>>> The register also joins the writable set that the SystemMemory overlap
>>> validation uses, as the driver now writes it and can compete with
>>> another control sharing an access unit.
>>>
>>> Reviewed-by: Christian Loehle <christian.loehle@arm.com>
>>> Signed-off-by: Sumit Gupta <sumitg@nvidia.com>
>>> ---
>>>   drivers/acpi/cppc_acpi.c | 44 ++++++++++++++++++++++++++++++++++++++++
>>>   include/acpi/cppc_acpi.h | 10 +++++++++
>>>   2 files changed, 54 insertions(+)
>>>
>>> diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c
>>> index 5a1f84fddb7f..3a0ecdd1ab11 100644
>>> --- a/drivers/acpi/cppc_acpi.c
>>> +++ b/drivers/acpi/cppc_acpi.c
>>> @@ -463,6 +463,7 @@ static bool cpc_reg_is_writable(unsigned int reg_idx)
>>>          case AUTO_SEL_ENABLE:
>>>          case AUTO_ACT_WINDOW:
>>>          case ENERGY_PERF:
>>> +       case OSPM_NOMINAL_PERF:
>>
>> Sashiko is unhappy about this change:
>>
>> https://sashiko.dev/#/patchset/20261106193304.3347374-1-sumitg%40nvidia.com
> 
> So I've queued up patches [1-5/8] for 7.5 and I'll wait for a
> clarification here.

Hi Rafael,

Thanks for queuing 1-5.

Sorry, I missed this Sashiko error.

In v9, if OSPM_NOMINAL_PERF shares an access unit with Performance
Limited, its range is no longer checked for overlaps.
It is write-only, so another field's read-modify-write over it would
write undefined bits into it.
v10 keeps its range reserved, so such a layout is still rejected.

Sent v10 of patches 6-8 on top of the queued 1-5 [1].

[1] https://lore.kernel.org/lkml/20261109195400.3600561-1-sumitg@nvidia.com/

Thanks,
Sumit