linux-kernel - Re: [patch 28/30] x86/microcode: Handle "offline" CPUs correctly

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: <87cyzuictv.ffs@tglx>
Date:   Fri, 11 Aug 2023 03:31:56 +0200
From:   Thomas Gleixner <tglx@...utronix.de>
To:     Ashok Raj <ashok.raj@...el.com>,
        Peter Zijlstra <peterz@...radead.org>
Cc:     LKML <linux-kernel@...r.kernel.org>, x86@...nel.org,
        Borislav Petkov <bp@...en8.de>,
        Arjan van de Ven <arjan@...ux.intel.com>,
        Ashok Raj <ashok.raj@...el.com>
Subject: Re: [patch 28/30] x86/microcode: Handle "offline" CPUs correctly

On Fri, Aug 11 2023 at 03:19, Thomas Gleixner wrote:

> On Thu, Aug 10 2023 at 16:02, Ashok Raj wrote:
>> On Fri, Aug 11, 2023 at 12:29:57AM +0200, Peter Zijlstra wrote:
>>> 
>>> Yeah, not placing constraints on who is online at all. Also, if both
>>> siblings are offline, then onlining will re-load ucode anyway, no?
>>
>> We need one thread in a core online,  because a MCE can happen and we don't
>> want those running something stale.
>
> Nonsense. This is a constraint at boot time. But afterwards it does not
> matter at all. That's what Peter is talking about.

And worse. It does not matter whether one thread of a core is online or
not in the case of a broadcast MCE during a microcode update simply
because that's game over.

Thanks,

        tglx