linux-kernel - Re: [PATCH RESEND] x86/speculation: Fix user-mode spectre-v2 protection with KERNEL

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]

Message-ID: <CACYkzJ6K77T8aFNC0oxcq8-huGZSX8spLpvNDiJQbyYsx5HwNg@mail.gmail.com>
Date:   Mon, 20 Feb 2023 15:01:47 -0800
From:   KP Singh <kpsingh@...nel.org>
To:     Borislav Petkov <bp@...en8.de>
Cc:     Andrew Cooper <andrew.cooper3@...rix.com>,
        Dave Hansen <dave.hansen@...el.com>,
        Josh Poimboeuf <jpoimboe@...nel.org>,
        linux-kernel@...r.kernel.org, pjt@...gle.com, evn@...gle.com,
        tglx@...utronix.de, mingo@...hat.com, dave.hansen@...ux.intel.com,
        x86@...nel.org, hpa@...or.com, peterz@...radead.org,
        pawan.kumar.gupta@...ux.intel.com, kim.phillips@....com,
        alexandre.chartre@...cle.com, daniel.sneddon@...ux.intel.com,
        José Oliveira <joseloliveira11@...il.com>,
        Rodrigo Branco <rodrigo@...nelhacking.com>,
        Alexandra Sandulescu <aesa@...gle.com>,
        Jim Mattson <jmattson@...gle.com>
Subject: Re: [PATCH RESEND] x86/speculation: Fix user-mode spectre-v2
 protection with KERNEL_IBRS

On Mon, Feb 20, 2023 at 1:10 PM Borislav Petkov <bp@...en8.de> wrote:
>
> On Mon, Feb 20, 2023 at 07:57:25PM +0000, Andrew Cooper wrote:
> > "When IBRS or enhanced IBRS is enabled, STIBP is not needed."
> >
> > This is misleading, if not strictly wrong.  The IBRS bit being set
> > implies STIBP, which reads differently to "not needed".
> >
> >
> > Now - eIBRS is "set once at start of day" which ends up becoming a
> > global implicit STIBP.
>
> Right.
>
> > I think we're discussing the legacy IBRS case here.  i.e. what was
> > retrofitted in microcode for existing parts?
>
> Any IBRS actually. The one which is *not* the automatic, fire'n'forget
> thing.
>
> > The reason why it is "write 1 on each privilege increase, 0 on privilege
> > decrease" is because on some CPUs its an inhibit control, and on some
> > CPUs is a flush (i.e. its actually IBPB).
> >
> > But these same CPUs don't actually have an ability to thread-tag the
> > indirect predictor nicely so STIBP is also horribly expensive under the
> > hood - so much so that we were firmly recommended to clear STIBP/IBRS
> > when going idle so as to reduce the impact on the sibling.
>
> Yap, we do that. And we do the write to 0 for IBRS on exit to
> luserspace, probably for very similar reasons.
>
> > IMO the proper way to do this is to set STIBP uniformly depending on
> > whether you want it in userspace or not, and treat it logically
> > separately to IBRS.  It doesn't hurt (any more) to have both bits set.
>
> So we have this thing:
>
>         /*
>          * If no STIBP, IBRS or enhanced IBRS is enabled, or SMT impossible,
>          * STIBP is not required.
>          */
>         if (!boot_cpu_has(X86_FEATURE_STIBP) ||
>             !smt_possible ||
>             spectre_v2_in_ibrs_mode(spectre_v2_enabled))
>                 return;
>
> What you propose sounds cleaner but would definitely need more massaging
> of this madness code. So I guess we could do only the
> enable-STIBP-when-IBRS-enabled thing first and do more cleanups later.
>

I do like the idea of decoupling, but yeah this is a bit tangled and
abstracted away from the user. The user currently just selects one of
(note the absence of STIBP in the choices here).

SPECTRE_V2_USER_CMD_NONE,
SPECTRE_V2_USER_CMD_AUTO,
SPECTRE_V2_USER_CMD_FORCE,
SPECTRE_V2_USER_CMD_PRCTL,
SPECTRE_V2_USER_CMD_PRCTL_IBPB,
SPECTRE_V2_USER_CMD_SECCOMP,
SPECTRE_V2_USER_CMD_SECCOMP_IBPB,

and the STIBP mode is selected implicitly based on the kernel's choice
of spectre v2 mitigations. I will fix the default case and we can
eventually decouple STIBP from the v2 kernel mitigation choice.

> Thx.
>
> --
> Regards/Gruss,
>     Boris.
>
> https://people.kernel.org/tglx/notes-about-netiquette