linux-kernel - Re: [PATCH 2/3] x86/topology: Fix AMD core count

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: <20160322112218.GD3688@pd.tnic>
Date:	Tue, 22 Mar 2016 12:22:18 +0100
From:	Borislav Petkov <bp@...en8.de>
To:	Sherry Hurwitz <sherry.hurwitz@....com>
Cc:	Huang Rui <ray.huang@....com>,
	Peter Zijlstra <peterz@...radead.org>, tglx@...utronix.de,
	linux-kernel@...r.kernel.org, mingo@...nel.org, aherrmann@...e.com,
	jencce.kernel@...il.com, Gang Long <gang.long@....com>
Subject: Re: [PATCH 2/3] x86/topology: Fix AMD core count

Hi Sherry,

On Tue, Mar 22, 2016 at 03:10:15AM -0500, Sherry Hurwitz wrote:
> Boris, this documentation will help tremendously.

Yeah, I'm collecting more stuff for it. If you feel like something else
should be explained there, holler.

> In just this line of
> code:
> 
> nr_local_cpus = nr_cores * nr_siblings
> 
> we have an Intel HT = AMD core = logical_cpu
> and core = AMD compute unit.
> 
> Anybody surprised there was a bug?
> 
> The surprising thing is that running lscpu on a 32 core 2 socket 6300
> Opteron system without
> the patches I get the same output as with the patches and it matches Ray's.
> I don't see an impact.

Yeah, so the logic is closer to an Intel core which can have 1 or more
threads and we did set x86_max_cores to the number of Bulldozer cores
(each of them in a pair forming a Compute Unit). And that's fine but
then we did set smp_num_siblings to 2.

In any case, I'm not seeing any issues here too but we wanted for you
guys to run those changes too before we apply them.

In any case, they will be in 4.6 and you could test tip/master from time
to time and scream if there's an issue.

Thanks!

-- 
Regards/Gruss,
    Boris.

ECO tip #101: Trim your mails when you reply.