Re: [v3 04/12] x86/fsgsbase/64: Enable FSGSBASE instructions in the helper functions

[Andy Lutomirski]

On Thu, Oct 25, 2018 at 12:32 AM Bae, Chang Seok
<chang.seok.bae@xxxxxxxxx> wrote:
>
>
> > On Oct 24, 2018, at 12:16, Andy Lutomirski <luto@xxxxxxxxxx> wrote:
> >
> > On Tue, Oct 23, 2018 at 11:43 AM Chang S. Bae <chang.seok.bae@xxxxxxxxx> wrote:
> >> void x86_fsbase_write_cpu(unsigned long fsbase)
> >> {
> >> -       /*
> >> -        * Set the selector to 0 as a notion, that the segment base is
> >> -        * overwritten, which will be checked for skipping the segment load
> >> -        * during context switch.
> >> -        */
> >> -       loadseg(FS, 0);
> >> -       wrmsrl(MSR_FS_BASE, fsbase);
> >> +       if (static_cpu_has(X86_FEATURE_FSGSBASE)) {
> >> +               wrfsbase(fsbase);
> >> +       } else {
> >> +               /*
> >> +                * Set the selector to 0 as a notion, that the segment base is
> >> +                * overwritten, which will be checked for skipping the segment load
> >> +                * during context switch.
> >> +                */
> >> +               loadseg(FS, 0);
> >> +               wrmsrl(MSR_FS_BASE, fsbase);
> >> +       }
> >> }
> >>
> >> void x86_gsbase_write_cpu_inactive(unsigned long gsbase)
> >> {
> >> -       /* Set the selector to 0 for the same reason as %fs above. */
> >> -       loadseg(GS, 0);
> >> -       wrmsrl(MSR_KERNEL_GS_BASE, gsbase);
> >> +       if (static_cpu_has(X86_FEATURE_FSGSBASE)) {
> >> +               wr_inactive_gsbase(gsbase);
> >> +       } else {
> >> +               /* Set the selector to 0 for the same reason as %fs above. */
> >> +               loadseg(GS, 0);
> >> +               wrmsrl(MSR_KERNEL_GS_BASE, gsbase);
> >
> > I still don't get what this code is trying to do.  See other email.  I
> > think it will straight up crash the kernel on some CPUs, since writing
> > 0 to %%gs will zero out the *active* base on some CPUs.
> >
>
> On those CPUs, how the old do_arch_prctl_64() worked?
> loadseg(GS, 0) eventually hits the native_load_gs_index entry, where actual
> mov â, %gs is wrapped by two SWAPGSes. So, it wonât cause the side effect
> of overwriting the *active* base, I think.
>
> > I think that, if you really want some fancy optimization for the
> > non-FSGSBASE case, you need to pull that out into the callers of these
> > helpers.
>

I was thinking of loadsegment, not loadseg.  Sorry!