linux-kernel - Re: [tip:x86/pti] x86/retpoline: Fill return stack buffer on vmexit

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, 25 Jan 2018 12:32:28 -0600
From:   Josh Poimboeuf <jpoimboe@...hat.com>
To:     David Woodhouse <dwmw2@...radead.org>
Cc:     Borislav Petkov <bp@...en8.de>, tim.c.chen@...ux.intel.com,
        pjt@...gle.com, jikos@...nel.org, gregkh@...ux-foundation.org,
        dave.hansen@...el.com, mingo@...nel.org, riel@...hat.com,
        luto@...capital.net, torvalds@...ux-foundation.org,
        ak@...ux.intel.com, keescook@...gle.com, peterz@...radead.org,
        tglx@...utronix.de, hpa@...or.com, linux-kernel@...r.kernel.org,
        linux-tip-commits@...r.kernel.org
Subject: Re: [tip:x86/pti] x86/retpoline: Fill return stack buffer on vmexit

On Thu, Jan 25, 2018 at 06:04:23PM +0000, David Woodhouse wrote:
> On Thu, 2018-01-25 at 18:53 +0100, Borislav Petkov wrote:
> > 
> > So forget the KABI angle and think: simpler, cleaner, more readable
> > macros.
> > 
> > Oh, and David, if while doing so I manage to add the alignment, then
> > *that* is even better.
> > 
> > Win-win-effing-win situation!
> 
> Yep, I'll buy that. But first we need Josh to work out what he's having
> for lunch.

This is what I've been eating every day:

  https://www.urbandictionary.com/define.php?term=Shit%20Sandwich

:-)

> Although just another marker to tell objtool "ignore this whole
> function" might be sufficient to allow us to have an out-of-line RSB-
> stuffing function.

If the function is only in arch/x86/lib/retpoline.S, we can just tell
objtool to ignore the entire file for now, as the file has no useful
information anyway (until I get around to adding ORC hints to it).  Just
add

  OBJECT_FILES_NON_STANDARD_retpoline.o :=y
  
to the Makefile.

-- 
Josh