Re: [PATCH v2 0/1] KVM: arm64: Map GPU memory with no struct pages

[Donald Dutile]

On 12/10/24 9:18 AM, Jason Gunthorpe wrote:
> On Tue, Dec 10, 2024 at 02:07:40PM +0000, Will Deacon wrote:
> > On Mon, Nov 18, 2024 at 01:19:57PM +0000, ankita@xxxxxxxxxx wrote:
> > > The changes are heavily influenced by the insightful discussions between
> > > Catalin Marinas and Jason Gunthorpe [1] on v1. Many thanks for their
> > > valuable suggestions.
> > >
> > > Link: https://lore.kernel.org/lkml/20230907181459.18145-2-ankita@xxxxxxxxxx [1]
> >
> > That's a different series, no? It got merged at v9:
>
> I was confused by this too. v1 of that series included this patch, as
> that series went along it became focused only on enabling WC
> (Normal-NC) in a VM for device MMIO and this patch for device cachable
> memory was dropped off.
>
> There are two related things:
>   1) Device MMIO memory should be able to be Normal-NC in a VM. Already
>      merged
>   2) Device Cachable memory (ie CXL and pre-CXL coherently attached
>      memory) should be Normal Cachable in a VM, even if it doesn't have
>      struct page/etc. (this patch)
>
> IIRC this part was dropped off because of the MTE complexity that
> Catalin raised.
>
> Jason
Jason & Catalin: Thanks for the filler for the splitting.

So, I'm not sure I read what is needed to resolve this patch.
I read Will's reply to split it further and basically along what logical lines of functionality;
is there still an MTE complexity that has to be resolved/included in the series?

IOW, I'm looking for a complete, clear (set of) statement(s) that Ankit can implement to get this (requested) series moving forward, sooner than later;
it's already been a year+ to get to this point, and I don't want further ambiguity/uncertainty to drag it out more than needed.

Thanks... Don