Re: [PATCH v2 1/1] mm/vmscan: avoid split PMD-mapped THP during shrink_folio_list()

[Lance Yang <ioworker0@gmail.com>]

On Thu, Apr 25, 2024 at 5:25 PM David Hildenbrand <david@redhat.com> wrote:
>
> >> I was wondering if we can better integrate that into the pagewalk below.
> >>
> >> That is, don't do the TTU_SPLIT_HUGE_PMD immediately. Start the pagewalk
> >> first. If we walk a PMD, try to unmap it. Only if that fails, split it.
> >
> > Nice. Thanks for the suggestion!
> > I'll work on integrating it into the pagewalk as you suggested.
> >
> >>
> >> Less working on "vma + address" and instead directly on PMDs.
> >
> > Yes, some of the work on "vma + address" can be avoided :)
>
> Doing the conditional split while in the pagewalk will be the
> interesting bit to sort out (we temporarily have to drop the PTL and
> start once again from that now-PTE-mapped page table). But it should be
> a reasonable thing to have.

Yep, it's an interesting challenge for me, but definitely worth tackling ;)

>
> Please let us know if you run into bigger issues with that!

Thanks, I'll do my best to sort it out and reach out for help if needed :p

>
> See walk_pmd_range() as an inspiration where we call split_huge_pmd().

Thanks for your suggestion! I'll take a closer look at it.

Thanks again for clarifying!
Lance

>
> --
> Cheers,
>
> David / dhildenb
>