linux-kernel - Re: AVX register corruption from signal delivery

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: <e4d6406b-0d47-5cc5-f3a8-6d14bd90760b@google.com>
Date:   Tue, 26 Nov 2019 16:23:40 -0500
From:   Barret Rhoden <brho@...gle.com>
To:     Sebastian Andrzej Siewior <bigeasy@...utronix.de>
Cc:     "Rik van Riel\"" <riel@...riel.com>, x86@...nel.org,
        linux-kernel@...r.kernel.org, Thomas Gleixner <tglx@...utronix.de>,
        Ingo Molnar <mingo@...hat.com>, Borislav Petkov <bp@...en8.de>
Subject: Re: AVX register corruption from signal delivery

On 11/26/19 3:20 PM, Sebastian Andrzej Siewior wrote:
> On 2019-11-26 14:49:55 [-0500], Barret Rhoden wrote:
>> Hi -
> Hi,
> 
>> The bug requires the kernel to be built with GCC 9 to trigger.  In
>> particular, arch/x86/kernel/fpu/signal.c needs to be built with GCC 9.
> 
> I've been pinged already, I will look into this. Please send me a
> .config just to be sure. From browsing over the bug CONFIG_PREEMPTION
> was required.

Thanks; config attached.  I've been able to recreate it in QEMU with at 
least 2 cores.

Barret




Download attachment "avx-bug.config.gz" of type "application/gzip" (28236 bytes)