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: <79296353-1fa3-458a-b055-88bc6a772180@kernel.dk>
Date: Fri, 18 Oct 2024 07:30:15 -0600
From: Jens Axboe <axboe@...nel.dk>
To: Borislav Petkov <bp@...en8.de>
Cc: Thomas Gleixner <tglx@...utronix.de>,
 the arch/x86 maintainers <x86@...nel.org>,
 LKML <linux-kernel@...r.kernel.org>,
 "regressions@...ts.linux.dev" <regressions@...ts.linux.dev>
Subject: Re: AMD zen microcode updates breaks boot

On 10/18/24 6:49 AM, Borislav Petkov wrote:
> On Fri, Oct 18, 2024 at 01:58:57PM +0200, Borislav Petkov wrote:
>> The next thing that is catching my eye is your simulated NUMA config:
>>
>> [    1.668943] smp: Brought up 32 nodes, 512 CPUs
>>
>> Lemme see if I can repro that here.
> 
> I can do only 4 nodes here:
> 
> [   23.137188] smp: Brought up 4 nodes, 255 CPUs
> 
> But that thing boots fine too.
> 
> I guess the next thing to try is a two-socket box like yours.

At least on mine, the BIOS has an option that says something like "L3
cache as numa domain", which is on and why there's 32 nodes on that box.
It's pretty handy for testing since there's a crap ton of CPUs, as it
makes affinity handling easier.

-- 
Jens Axboe

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ