linux-kernel - Re: [RFC PATCH v3 6/8] x86/pti: don't mark the user PGD with _PAGE

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]

Date:   Thu, 11 Jan 2018 07:27:43 +0100
From:   Willy Tarreau <w@....eu>
To:     Dave Hansen <dave.hansen@...ux.intel.com>
Cc:     linux-kernel@...r.kernel.org, x86@...nel.org,
        Andy Lutomirski <luto@...nel.org>,
        Borislav Petkov <bp@...en8.de>,
        Brian Gerst <brgerst@...il.com>,
        Ingo Molnar <mingo@...nel.org>,
        Linus Torvalds <torvalds@...ux-foundation.org>,
        Peter Zijlstra <peterz@...radead.org>,
        Thomas Gleixner <tglx@...utronix.de>,
        Josh Poimboeuf <jpoimboe@...hat.com>,
        "H. Peter Anvin" <hpa@...or.com>,
        David Woodhouse <dwmw@...zon.co.uk>,
        Kees Cook <keescook@...omium.org>
Subject: Re: [RFC PATCH v3 6/8] x86/pti: don't mark the user PGD with
 _PAGE_NX.

On Wed, Jan 10, 2018 at 12:20:05PM -0800, Dave Hansen wrote:
> Granted, you have an RFC on this, but please, for the love of everything
> that is good the world, please stop sending this patch set until you
> have a halfway reasonable method of dealing with NX that doesn't involve
> #ifdefs.  Please.

Dave, people have been disagreeing for a while on two critical points :
  - per-task vs per-mm setting
  - stop or pass execve()

The discussion resulted from the patchset publication with some good
and bad points detected in each case (including your comment about the
conditional jump in the entry code based on CR3).

The method of dealing with NX will result from design choices, so for
me it should be handled last (but I'm find with changing the commit
message to mark it "BROKEN" to avoid confusion).

Thanks,
Willy