linux-kernel - Re: [PATCH v3 0/1] arm64: Add workaround for Fujitsu A64FX erratum 010001

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] [day] [month] [year] [list]

Message-ID: <20190213131906.GB5875@brain-police>
Date:   Wed, 13 Feb 2019 13:19:06 +0000
From:   Will Deacon <will.deacon@....com>
To:     "Zhang, Lei" <zhang.lei@...fujitsu.com>
Cc:     'Mark Rutland' <mark.rutland@....com>,
        'Catalin Marinas' <catalin.marinas@....com>,
        'James Morse' <james.morse@....com>,
        "'linux-kernel@...r.kernel.org'" <linux-kernel@...r.kernel.org>,
        "'linux-arm-kernel@...ts.infradead.org'" 
        <linux-arm-kernel@...ts.infradead.org>
Subject: Re: [PATCH v3 0/1] arm64: Add workaround for Fujitsu A64FX erratum
 010001

On Tue, Feb 05, 2019 at 01:32:07PM +0000, Zhang, Lei wrote:
> > -----Original Message-----
> > From: linux-arm-kernel
> > [mailto:linux-arm-kernel-bounces@...ts.infradead.org] On Behalf Of
> > Will Deacon
> > Sent: Friday, February 01, 2019 7:52 PM
> > To: Zhang, Lei 
> > Cc: 'Mark Rutland'; 'Catalin Marinas'; 'James Morse';
> > 'linux-kernel@...r.kernel.org';
> > 'linux-arm-kernel@...ts.infradead.org'
> > Subject: Re: [PATCH v3 0/1] arm64: Add workaround for Fujitsu A64FX
> > erratum 010001
> 
> > So I guess we should boot with NFD1 clear, and then set it only when we
> > realise we're not on an A64FX?
> 
> In my patch, I do similar things at __cpu_setup which we 
> set NFD1=1 on all processors except A64FX.
> 
> Do you mean we would better to change the place where we 
> set/clear NFD1?

Yes, I think we should keep the code as simple as we can:

  - Don't set NFDx=1 in proc.S for any CPU
  - Later, in C code, we can set the bit for any CPU that is not an affected
    A64FX (this can be a simple MIDR check).

Does that work?

Will