Re: [PATCH V2 7/7] perf/x86/intel/uncore: Implement global init callback for GNR uncore

[Chen, Zide]

On 5/29/2026 5:55 AM, Peter Zijlstra wrote:
> On Fri, May 29, 2026 at 04:47:39PM +0800, Mi, Dapeng wrote:
>>
>> On 5/29/2026 2:14 AM, Chen, Zide wrote:
>>>
>>> On 5/28/2026 1:46 AM, Mi, Dapeng wrote:
>>>> On 5/27/2026 11:11 PM, Zide Chen wrote:
>>>>> On Sierra Forest and Clearwater Forest, the FRZ_ALL bit in the global
>>>>> control register defaults to 0 at boot, but UBOX PMON units do not
>>>>> work until the global control register is explicitly written with 0
>>>>> to trigger hardware initialization properly.
>>>>>
>>>>> Implement the generic uncore_msr_global_init() callback and add it to
>>>>> gnr_uncore_init[], which is shared by GNR, GRR, SRF, and CWF.
>>>> Need a "Fixes" tag?
>>> No Fixes tag needed. This is a hardware initialization workaround rather
>>> than a fix for a software bug. The register defaults to 0, but the
>>> hardware requires an explicit write to trigger PMON functionality.
>>
>> Zide, per my understanding, some uncore PMUs can't work for SRF and CWF
>> without this change. Is it right? If so, we need to add a "Fixes" tag to
>> ensure this patch is merged to the corresponding stable branches. Thanks.
> 
> If you all agree on Fixes tags, then those patches that end up getting
> one should be at the front of the series.
> 
> I was about to pick this up, but if you guys want to send a new series,
> let me know and I'll hold off.

Yes, please hold off and I can send out a new series to add a Fixes tag,
fix the missing '---' in patch 5/7, etc.