Re: [PATCH RFC v1 02/11] x86/fpu/xstate: Introduce xstate order table and accessor macro

[Ingo Molnar]

* Andrew Cooper <andrew.cooper3@xxxxxxxxxx> wrote:

> On 2/27/25 19:03, Dave Hansen wrote:
> 
> > On 2/27/25 10:44, Chang S. Bae wrote:
> >> The kernel has largely assumed that higher xstate component numbers
> >> correspond to later offsets in the buffer. However, this assumption
> >> does not hold for the non-compacted format, where a newer state
> >> component may have a lower offset.
> > Maybe "no longer holds" instead of "does not hold".
> >
> > This never happened before APX, right?
> 
> I'm afraid that AMD beat you there by a decade with LWP, index 63 but 
> also overlaps the MPX state.

https://giphy.com/gifs/moodman-TJawtKM6OCKkvwCIqX

> Except LWP support never became mainstream, and it also got 
> sacrificed to make room for IBPB in microcode, so you can safely 
> ignore it[1].

yay! CPU makers always chose the right solution, once they have 
exhaused all the alternatives.

Thanks,

	Ingo