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

[KP Singh]

On Mon, Feb 20, 2023 at 1:10 PM Borislav Petkov <bp@xxxxxxxxx> 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