Re: [PATCH v1 0/4] smaps / mm/gup: fix gup_can_follow_protnone fallout

[David Hildenbrand <david@redhat.com>]

On 28.07.23 22:23, Linus Torvalds wrote:
> On Fri, 28 Jul 2023 at 12:39, Peter Xu <peterx@redhat.com> wrote:
>>
>> But then does it means that any gup-only user will have numa balancing
>> completely disabled?
> 
> Why would we ever care about a GUP-only user?
> 
> Who knows where the actual access is coming from? It might be some
> device that is on a different node entirely.
> 
> And even if the access is local from the CPU, it
> 
>   (a) might have happened after we moved somewhere else
> 
>   (b) who cares about the extra possible NUMA overhead when we just
> wasted *thousands* of cycles on GUP?
> 
> So NUMA balancing really doesn't seem to make sense for GUP anyway as
> far as I can see.

I do agree regarding many GUP users.

But at least for KVM (and probably some others, but most probably KVM is 
the most important GUP user) it does make sense and we have to find a 
way to keep that working.

At least, removing it creates significantly more harm than having it, 
guaranteed :)

So would you rather favor a FOLL_NUMA that has to be passed from the 
outside by selected callers or a FOLL_NUMA that is set on the GUP path 
unconditionally (but left clear for follow_page())?

-- 
Cheers,

David / dhildenb