Re: [PATCH 4/4] x86/cpu: Use SERIALIZE in sync_core() when available

[peterz]

On Mon, Jul 27, 2020 at 09:41:14PM -0700, Ricardo Neri wrote:
> I think I got a little lost here.

Hehe, sorry. I got carried away, it's just that recently people
expressed interest in 'fixing' some of the text_poke_sync() issues
again.

> If I understand correctly, there are
> two alternatives to implement support for serialize better:
> 
>   a) alternative(IRET_TO_SELF, SERIALIZE, X86_FEATURE_SERIALIZE); or
>   b) asm volatile("1:.byte 0xf, 0x1, 0xe8;2:" _ASM_EXTABLE(1b:2b)
> 
> a) would be the traditional and simpler solution. b) would rely on
> causing an #UD and getting an IRET on existing hardware b) would need some
> more optimization work when handling the exception and a few reworks on
> the poke patching code.
> 
> Which option should I focus on? Which option would be more desirable/better?

I'd say go with (a) for now. We can always go overboard later ;-)