linux-kernel - Re: [PATCH v2] x86/asm: Replace __force

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]

Date:   Wed, 2 Sep 2020 13:36:55 -0400
From:   Arvind Sankar <nivedita@...m.mit.edu>
To:     Segher Boessenkool <segher@...nel.crashing.org>
Cc:     Arvind Sankar <nivedita@...m.mit.edu>,
        Linus Torvalds <torvalds@...ux-foundation.org>,
        Miguel Ojeda <miguel.ojeda.sandonis@...il.com>,
        Sedat Dilek <sedat.dilek@...il.com>,
        Thomas Gleixner <tglx@...utronix.de>,
        Nick Desaulniers <ndesaulniers@...gle.com>,
        "Paul E. McKenney" <paulmck@...nel.org>,
        Ingo Molnar <mingo@...hat.com>, Arnd Bergmann <arnd@...db.de>,
        Borislav Petkov <bp@...en8.de>,
        "maintainer:X86 ARCHITECTURE (32-BIT AND 64-BIT)" <x86@...nel.org>,
        "H. Peter Anvin" <hpa@...or.com>,
        "Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>,
        Kees Cook <keescook@...omium.org>,
        Peter Zijlstra <peterz@...radead.org>,
        Juergen Gross <jgross@...e.com>,
        Andy Lutomirski <luto@...nel.org>,
        Andrew Cooper <andrew.cooper3@...rix.com>,
        LKML <linux-kernel@...r.kernel.org>,
        clang-built-linux <clang-built-linux@...glegroups.com>,
        Will Deacon <will@...nel.org>, nadav.amit@...il.com,
        Nathan Chancellor <natechancellor@...il.com>
Subject: Re: [PATCH v2] x86/asm: Replace __force_order with memory clobber

On Wed, Sep 02, 2020 at 12:16:24PM -0500, Segher Boessenkool wrote:
> On Wed, Sep 02, 2020 at 11:33:46AM -0400, Arvind Sankar wrote:
> > The CRn accessor functions use __force_order as a dummy operand to
> > prevent the compiler from reordering the inline asm.
> > 
> > The fact that the asm is volatile should be enough to prevent this
> > already, however older versions of GCC had a bug that could sometimes
> > result in reordering. This was fixed in 8.1, 7.3 and 6.5. Versions prior
> > to these, including 5.x and 4.9.x, may reorder volatile asm.
> 
> Reordering them amongst themselves.  Yes, that is bad.  Reordering them
> with "random" code is Just Fine.

Right, that's what I meant, but the text isn't clear. I will edit to clarify.

> 
> Volatile asm should be executed on the real machine exactly as often as
> on the C abstract machine, and in the same order.  That is all.
> 
> > + * The compiler should not reorder volatile asm,
> 
> So, this comment needs work.  And perhaps the rest of the patch as well?
> 
> 
> Segher

I think the patch itself is ok, we do only want to avoid reordering
volatile asm vs volatile asm. But the comment needs clarification.

Thanks.