linux-kernel - Re: [PATCH v8 14/25] x86/resctrl: Add data structures and definitions for ABMC assignment

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite for Android: free password hash cracker in your pocket

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <5aa05154-82ae-ed0b-18da-7582dd6ed2a4@amd.com>
Date: Thu, 17 Oct 2024 18:02:00 -0500
From: "Moger, Babu" <bmoger@....com>
To: Reinette Chatre <reinette.chatre@...el.com>, babu.moger@....com,
 corbet@....net, fenghua.yu@...el.com, tglx@...utronix.de, mingo@...hat.com,
 bp@...en8.de, dave.hansen@...ux.intel.com
Cc: x86@...nel.org, hpa@...or.com, paulmck@...nel.org, rdunlap@...radead.org,
 tj@...nel.org, peterz@...radead.org, yanjiewtw@...il.com,
 kim.phillips@....com, lukas.bulwahn@...il.com, seanjc@...gle.com,
 jmattson@...gle.com, leitao@...ian.org, jpoimboe@...nel.org,
 kirill.shutemov@...ux.intel.com, jithu.joseph@...el.com,
 kai.huang@...el.com, kan.liang@...ux.intel.com,
 daniel.sneddon@...ux.intel.com, pbonzini@...hat.com, sandipan.das@....com,
 ilpo.jarvinen@...ux.intel.com, peternewman@...gle.com,
 maciej.wieczor-retman@...el.com, linux-doc@...r.kernel.org,
 linux-kernel@...r.kernel.org, eranian@...gle.com, james.morse@....com
Subject: Re: [PATCH v8 14/25] x86/resctrl: Add data structures and definitions
 for ABMC assignment

Hi Reinette,

On 10/17/2024 4:13 PM, Reinette Chatre wrote:
> Hi Babu,
> 
> On 10/17/24 11:52 AM, Moger, Babu wrote:
>> On 10/15/24 22:21, Reinette Chatre wrote:
>>> On 10/9/24 10:39 AM, Babu Moger wrote:
> 
>>>> + *			  tracked by the @cntr_id.
>>>> + * @bw_src		: Bandwidth source (RMID or CLOSID).
>>>> + * @reserved1		: Reserved.
>>>> + * @is_clos		: @bw_src field is a CLOSID (not an RMID).
>>>> + * @cntr_id		: Counter identifier.
>>>> + * @reserved		: Reserved.
>>>> + * @cntr_en		: Counting enable bit.
>>>> + * @cfg_en		: Configuration enable bit.
>>>> + *
>>>> + * Configuration and counting:
>>>> + * cfg_en=0,            : No configuration changes applied.
>>>
>>> Can this be expanded? (sidenote: It is taking a long time to get clarity on how
>>> to interact with hardware. These incremental cryptic fragments make it difficult
>>> to know how to interact with the hardware.)
>>>
>>> For example, "No configuration changes applied. Counter can be configured across
>>> multiple writes to MSR while @cfg_en=0. Configuration applied when @cfg_en=1."
>>>
>>>> + * cfg_en=1, cntr_en=0  : Configure cntr_id and but no counting the events.
>>>
>>> hmmm ... still the same (""but no counting the events") strange language I
>>> highlighted in V7 ...
>>>
>>> I think it will make things easier to understand if similar language is used
>>> between the descriptions of the different fields.
>>>
>>> "Apply @cntr_id configuration but do not count events."
>>>   
>>>> + * cfg_en=1, cntr_en=1  : Configure cntr_id and start counting the events.
>>>
>>> "Apply @cntr_id configuration and start counting events."
>>>
>>> Can it be added here which of these settings (or combination of settings) result
>>> in counters being reset?
>>
>> Any change in the configuration will reset the counters.
>>
>> Little bit lost here. Let me summarize. How about this?
>>
>> Configuration and counting:
>> Counter can be configured across multiple writes to MSR. Configuration
>> is applied only when @cfg_en = 1. The event counters will reset when any
>> of the configuration is changed.
> 
> Is is not clear to me what is meant with "when any of the configuration is changed".
> Are event counters reset with every write to the MSR, whether @cfg_en is set or
> not? If counters are only reset when @cfg_en is set then I think it should read
> "Counter @cntr_id is reset when the configuration is applied." Note this is

Sure.

> also made specific to be related to *just* the counter being configured, not all
> event counters that "The event counters will reset ..." implies.
> 
>> cfg_en = 1, cntr_en = 0 : Apply @cntr_id configuration but do not count
>> events.
>> cfg_en = 1, cntr_en = 1 : Apply @cntr_id configuration and start counting
>> events.
>>
> 
> Please use the @ prefix when referring to union members.

Ok. Sure.

> 
> Thank you
> 
> Reinette
> 
> 

Thanks
- Babu Moger