Re: [PATCHv6 11/30] x86/tdx: Handle in-kernel MMIO

[Dave Hansen]

On 3/15/22 19:08, Kirill A. Shutemov wrote:
> In other words, even if all of the work was done to paravirtualize all
> x86 MMIO users and virtio, this approach would still be needed. There
> is essentially no way to get rid of this code.
...
> == Patching TDX drivers ==
...> This approach will be adopted in the future, removing the bulk of
> MMIO #VEs. The #VE-based MMIO will remain serving non-virtio use cases.

I still don't like this very much, but I can't argue with my own logic. :)

BTW, TDX folks...  I expect you to, today, start coming up with a
comprehensive list of the MMIO-induced #VE's and the reasoning why they
should or should not be paravirtualized.  You're going to get grumpy
maintainers if this is done haphazardly as one-offs when users hit
performance issues.

Reviewed-by: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>