Re: [PATCH v5 0/3] cpufreq: cppc: Handle Highest Performance changes at runtime

[Christian Loehle <christian.loehle@arm.com>]

On 9/7/26 09:49, Jie Zhan wrote:
> 
> 
> On 8/7/2026 2:08 PM, Xueqin Luo wrote:
>> Hi Rafael, Pierre,
>>
>> This series adds support for handling ACPI CPPC Highest Performance
>> register changes at runtime, triggered by Notify(0x85) on a processor
>> device.
>>
>> When the platform changes the Highest Performance value (e.g. due to
>> thermal or power budget adjustments), the OSPM must re-evaluate the
>> cached capability and propagate the change to the cpufreq policy,
>> the scheduler's CPU capacity model, and the frequency invariance
>> engine.
> Any real use case of this on platforms that run cppc_cpufreq drivers?
> Some addtional motivation may help.
> 
> For example, a processor can age over time and its core frequency degrades.
> It's good if platforms can make OSPM and userspace aware of this.

+1
If this is still current then I'd love to see a resend with a fix to affect
the entire policy at once, not just policy->cpu and I'd propose for now
also limiting highest_perf at first probe and ignoring any
highest_perf_new > highest_perf, until we have a compelling case / platform
that uses it, because IMO it does make everything more complicated.
(+CC Ionela)

> [snip]