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: <20160321082129.GP6344@twins.programming.kicks-ass.net>
Date:	Mon, 21 Mar 2016 09:21:29 +0100
From:	Peter Zijlstra <peterz@...radead.org>
To:	Huang Rui <ray.huang@....com>
Cc:	Borislav Petkov <bp@...en8.de>,
	Sherry Hurwitz <sherry.hurwitz@....com>, 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

On Mon, Mar 21, 2016 at 11:07:46AM +0800, Huang Rui wrote:
> > > The issue is that Linux assumes:
> > > 
> > > 	nr_logical_cpus = nr_cores * nr_siblings
> > > 
> > > But AMD reports its CU unit as 2 cores, but then sets num_smp_siblings
> > > to 2 as well.

> But I am confused with c->x86_max_cores /= smp_num_siblings, what is
> the real meaning of c->x86_max_cores here for AMD, the whole compute
> unit numbers per socket?

Yes, with the whole Compute Unit being the Core, each logical CPU
becomes a Thread. This is the direct consequence of using the SMT
topology to model the CU thing.