linux-kernel - RE: [PATCH v2 7/7] x86/resctrl: Determine if Sub-NUMA Cluster is enabled and initialize.

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: Windows password security audit tool. GUI, reports in PDF.

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

Message-ID: <SJ1PR11MB608334F6555F9CEF3F740DE8FC26A@SJ1PR11MB6083.namprd11.prod.outlook.com>
Date:   Mon, 26 Jun 2023 15:52:03 +0000
From:   "Luck, Tony" <tony.luck@...el.com>
To:     Peter Newman <peternewman@...gle.com>
CC:     "Yu, Fenghua" <fenghua.yu@...el.com>,
        "Chatre, Reinette" <reinette.chatre@...el.com>,
        Jonathan Corbet <corbet@....net>,
        "x86@...nel.org" <x86@...nel.org>,
        Shaopeng Tan <tan.shaopeng@...itsu.com>,
        James Morse <james.morse@....com>,
        Jamie Iles <quic_jiles@...cinc.com>,
        "Babu Moger" <babu.moger@....com>,
        "linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
        "linux-doc@...r.kernel.org" <linux-doc@...r.kernel.org>,
        "patches@...ts.linux.dev" <patches@...ts.linux.dev>
Subject: RE: [PATCH v2 7/7] x86/resctrl: Determine if Sub-NUMA Cluster is
 enabled and initialize.

>> +++ b/arch/x86/include/asm/resctrl.h
>> @@ -35,6 +35,8 @@ DECLARE_STATIC_KEY_FALSE(rdt_enable_key);
>>  DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key);
>>  DECLARE_STATIC_KEY_FALSE(rdt_mon_enable_key);
>>
>> +DECLARE_PER_CPU(int, rmid_offset);
>> +
>
> I assumed that declarations in this file were those needed by
> __resctrl_sched_in(). Now that rmid_offset is used when setting
> PQR_ASSOC, would this go somewhere else?

PQR_ASSOC no longer needs rmid_offset. But QM_EVTSEL still does.

I'll take a look to see if all the SNC detection code can move into
monitor.c. Then rmid_offset could be static in that file. But if that gets
complicated I may leave it alone (with rmid_offset set in core.c and used
in monitor.c).

> Other than this and fixing the MSR update, the series looks fine to me.
>
> Reviewed-By: Peter Newman <peternewman@...gle.com>

Peter,

Thanks for testing and review. Did you also test on one of your systems
with a memory-only node? I recall that was an issue with my very first
patch series.

-Tony