On Thu, Sep 24, 2020 at 05:38:10PM -0700, Sean Christopherson wrote:
> > Why not simply
> >
> > arch/x86/entry/vdso/sgx.S
> >
> > ?
>
> I really like typing?
I'll say.
> Yes, to call out that there's a field there, but a field that the vDSO should
> never touch.
You wanna enforce that in the vdso code?
Because if it is there, luserspace will touch it.
> > > +#define SGX_ENCLAVE_RUN_EXCEPTION 4*8
> > > +
> > > +#define SGX_SYNCHRONOUS_EXIT 0
> > > +#define SGX_EXCEPTION_EXIT 1
> >
> > Those are in ...uapi/asm/sgx.h too. Unify?
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
What about this here?
> > Are the CFI annotations for userspace?
>
> Yes, though that's a 90% confident "yes".
Looks like we wanna support it:
f24f91088427 ("x86/vdso: Define BUILD_VDSO while building and emit .eh_frame in asm")
> Argh, it's actually supposed to be TCS, SGX_ENCLAVE_RUN_TSC is the one that's
> wrong.
Whoopsie :-)
Thx.
--
Regards/Gruss,
Boris.
https://people.kernel.org/tglx/notes-about-netiquette
