linux-kernel - Re: [PATCH 00/12] x86/crypto: Fix RBP usage in several crypto .S files

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]

Date:   Thu, 14 Sep 2017 21:54:51 -0700
From:   Eric Biggers <ebiggers3@...il.com>
To:     Josh Poimboeuf <jpoimboe@...hat.com>
Cc:     Ingo Molnar <mingo@...nel.org>, x86@...nel.org,
        linux-kernel@...r.kernel.org,
        Tim Chen <tim.c.chen@...ux.intel.com>,
        Mathias Krause <minipli@...glemail.com>,
        Chandramouli Narayanan <mouli@...ux.intel.com>,
        Jussi Kivilinna <jussi.kivilinna@....fi>,
        Peter Zijlstra <peterz@...radead.org>,
        Herbert Xu <herbert@...dor.apana.org.au>,
        "David S. Miller" <davem@...emloft.net>,
        linux-crypto@...r.kernel.org, Eric Biggers <ebiggers@...gle.com>,
        Andy Lutomirski <luto@...nel.org>, Jiri Slaby <jslaby@...e.cz>
Subject: Re: [PATCH 00/12] x86/crypto: Fix RBP usage in several crypto .S
 files

Hi Josh,

On Wed, Sep 13, 2017 at 05:33:03PM -0500, Josh Poimboeuf wrote:
> And here's v2 of the sha512-avx2 patch.  It should hopefully gain back
> most of the performance lost by v1.
> 
> From: Josh Poimboeuf <jpoimboe@...hat.com>
> Subject: [PATCH] x86/crypto: Fix RBP usage in sha512-avx2-asm.S
> 
> Using RBP as a temporary register breaks frame pointer convention and
> breaks stack traces when unwinding from an interrupt in the crypto code.
> 
> Mix things up a little bit to get rid of the RBP usage, without
> destroying performance.  Use RDI instead of RBP for the TBL pointer.
> That will clobber CTX, so save CTX on the stack and use RDI as CTX
> before it gets clobbered, and R12 as CTX after it gets clobbered.
> 
> Also remove the unused y4 variable.
> 

I tested the v2 patches for both sha256-avx2 and sha512-avx2 on Skylake.  They
both pass the crypto self-tests, and there was no noticable performance
difference compared to the unpatched versions.  Thanks!

Eric