Re: [PATCH v3 01/12] x86/resctrl: Support Privilege-Level Zero Association (PLZA)

[Babu Moger <babu.moger@amd.com>]

Hi Reinette,


On 6/16/26 19:00, Reinette Chatre wrote:
> Hi Babu,
> 
> On 6/12/26 9:56 AM, Moger, Babu wrote:
>> Hi Reinette,
>>
>> On 6/11/2026 6:23 PM, Reinette Chatre wrote:
>>> Hi Babu,
>>>
>>> On 4/30/26 4:24 PM, Babu Moger wrote:
>>>> Customers have identified an issue while using the QoS resource Control
>>>
>>> "Control" -> "control"?
>>>
>>
>> ack
>>
>>>> feature. If a memory bandwidth associated with a CLOSID is aggressively
>>>
>>> "a memory bandwidth" -> "memory bandwidth"?
>>
>> ack.
>>
>>>
>>>> throttled, and it moves into Kernel mode, the Kernel operations are also
>>>
>>> What does "it" refer to here? From text it seems to be the "CLOSID" but that
>>> does not sound right? Should "it" instead be something like "a task with that
>>> CLOSID"?
>>
>> sure.
>>
>>>
>>> "Kernel" -> "kernel"?
>>
>> ack.
>>>
>>>> aggressively throttled. This can stall forward progress and eventually
>>>> degrade overall system performance. AMD hardware supports a feature
>>>> Privilege-Level Zero Association (PLZA) to change the association of the
>>>> thread as soon as it begins executing.
>>>
>>> "change the association of the thread as soon as it begins executing." I am
>>> not able to parse this.
>>
>> How about ?
>>
>> Customers have identified an issue while using the QoS resource Control
>> feature. If memory bandwidth associated with a CLOSID is aggressively
>> throttled, and a task with that CLOSID moves into kernel mode, the kernel operations are also aggressively throttled. This can stall forward progress and eventually degrade overall system performance.
>> AMD hardware supports a feature Privilege-Level Zero Association (PLZA)
>> to change the CPU association at the user-to-kernel transition, so the kernel execution can use a different association than user mode.
> 
> "change the CPU association at the user-to-kernel transition" -> What is this
> trying to describe? CPU association of what?
> 
> "a different association"? What does this mean?
> 

Will change it to:

AMD hardware supports a feature Privilege-Level Zero Association (PLZA),
which allows the CPU’s CLOSID association to be changed during the 
transition from user mode to kernel mode. This enables the kernel to 
operate with a different CLOSID than the user mode.


>>
>> Privilege-Level Zero Association (PLZA) allows the user to specify a> CLOSID and/or RMID associated with execution in Privilege-Level
>> Zero. When enabled on a CPU, as the CPU enters Privilege-Level Zero,
>> allocation and monitoring for that CPU will be associated with the
>> PLZA CLOSID and/or RMID. Otherwise, the CPU will be associated with
>> the CLOSID and RMID given by PQR_ASSOC.
> 
> 
> Sounds like this is vague because MSR_IA32_PQR_PLZA_ASSOC has not been
> introduced yet. Could it help to introduce MSR_IA32_PQR_PLZA_ASSOC as
> part of this patch and then the changelog can be specific about PLZA
> feature introducing this new MSR and how it complements MSR_IA32_PQR_ASSOC?

Its probably better to remove the second paragraph. This text can go 
with the patch which introduces MSR_IA32_PQR_PLZA_ASSOC.

With splitting the patch, this will only have cpufeatures changes.

> 
> ...
> 
>>>>    Documentation/admin-guide/kernel-parameters.txt | 2 +-
>>>>    arch/x86/include/asm/cpufeatures.h              | 1 +
>>>>    arch/x86/kernel/cpu/resctrl/core.c              | 2 ++
>>>>    arch/x86/kernel/cpu/scattered.c                 | 1 +
>>>
>>> Please split changes to other subsystems and make these changes
>>> obvious with their own subject prefix to avoid sneaking changes into
>>> other subsystems via resctrl.
>>>
>>
>> Ok. Will be two patches.
>> 1. For Documentation/admin-guide/kernel-parameters.txt
>> 2.  arch/x86/include/asm/cpufeatures.h
>>      arch/x86/kernel/cpu/resctrl/core.c
>>      arch/x86/kernel/cpu/scattered.c
> 
> The resctrl changes found in (2) would be documented in (1)? That does not
> look right. Why not just split the resctrl changes from the cpufeatures changes?
> This would be similar to how you did ABMC enabling.
> 

Sounds good.

Thanks
Babu