Re: [PATCH v38 21/24] x86/vdso: Implement a vDSO for Intel SGX enclave call

[Borislav Petkov]

On Fri, Sep 25, 2020 at 04:00:40AM +0300, Jarkko Sakkinen wrote:
> I renamed it as vsgx.S (for the sake of convention).

Right.

> I have not authored this patch but what I would propose is to use just
> raw value in the place of these constants. It is practially just a
> boolean value.
> 
> I can also add sgx_vdso.h to uapi directory. I just don't see the point.

Just be very cautious what you add to the uapi/ directory because it
becomes API and there's no changing it. That's why I point you guys to
it, to think hard what you expose there and that it becomes contract
with luserspace.

> > I can see why you would write "TCS" though - there's a thread control
> > structure thing too in that patch.
> 
> Renamed.

See Sean's reply.

> /**
>  * typedef sgx_enclave_exit_handler_t - Exit handler function accepted by
>  *					__vdso_sgx_enter_enclave()
>  * @rdi:	RDI snapshot
>  * @rsi:	RSI snapshot
>  * @rdx:	RDX snapshot
>  * @rsp:	RSP snapshot (untrusted stack)
>  * @r8:		R8 snapshot
>  * @r9:		R9 snapshot

I'd say here:

"The registers' content is the snapshot made at enclave exit."

> Also, I renamed 'r' as 'run' in some places.
> 
> End result:
> 
> https://git.kernel.org/pub/scm/linux/kernel/git/jarkko/linux-sgx.git/tree/arch/x86/include/uapi/asm/sgx.h
> 
> I'm wondering this sentence:
> 
> "The calling convention is custom and does not follow System V x86-64 ABI."

Yeah, I was wondering what that meant too.

-- 
Regards/Gruss,
    Boris.

https://people.kernel.org/tglx/notes-about-netiquette