Re: [PATCH v4 3/4] mm: Support batched unmap for lazyfree large folios during reclamation

[Barry Song <21cnbao@gmail.com>]

On Wed, Jun 25, 2025 at 10:43 PM David Hildenbrand <david@redhat.com> wrote:
>
> On 25.06.25 12:38, Barry Song wrote:
> >>> diff --git a/mm/rmap.c b/mm/rmap.c
> >>> index fb63d9256f09..241d55a92a47 100644
> >>> --- a/mm/rmap.c
> >>> +++ b/mm/rmap.c
> >>> @@ -1847,12 +1847,25 @@ void folio_remove_rmap_pud(struct folio *folio, struct page *page,
> >>>
> >>>    /* We support batch unmapping of PTEs for lazyfree large folios */
> >>>    static inline bool can_batch_unmap_folio_ptes(unsigned long addr,
> >>> -                     struct folio *folio, pte_t *ptep)
> >>> +                                           struct folio *folio, pte_t *ptep,
> >>> +                                           struct vm_area_struct *vma)
> >>>    {
> >>>        const fpb_t fpb_flags = FPB_IGNORE_DIRTY | FPB_IGNORE_SOFT_DIRTY;
> >>> +     unsigned long next_pmd, vma_end, end_addr;
> >>>        int max_nr = folio_nr_pages(folio);
> >>>        pte_t pte = ptep_get(ptep);
> >>>
> >>> +     /*
> >>> +      * Limit the batch scan within a single VMA and within a single
> >>> +      * page table.
> >>> +      */
> >>> +     vma_end = vma->vm_end;
> >>> +     next_pmd = ALIGN(addr + 1, PMD_SIZE);
> >>> +     end_addr = addr + (unsigned long)max_nr * PAGE_SIZE;
> >>> +
> >>> +     if (end_addr > min(next_pmd, vma_end))
> >>> +             return false;
> >>
> >> May I suggest that we clean all that up as we fix it?
> >>
> >> Maybe something like this:
> >>
> >> diff --git a/mm/rmap.c b/mm/rmap.c
> >> index 3b74bb19c11dd..11fbddc6ad8d6 100644
> >> --- a/mm/rmap.c
> >> +++ b/mm/rmap.c
> >> @@ -1845,23 +1845,38 @@ void folio_remove_rmap_pud(struct folio *folio, struct page *page,
> >>    #endif
> >>    }
> >>
> >> -/* We support batch unmapping of PTEs for lazyfree large folios */
> >> -static inline bool can_batch_unmap_folio_ptes(unsigned long addr,
> >> -                       struct folio *folio, pte_t *ptep)
> >> +static inline unsigned int folio_unmap_pte_batch(struct folio *folio,
> >> +               struct page_vma_mapped_walk *pvmw, enum ttu_flags flags,
> >> +               pte_t pte)
> >>    {
> >>           const fpb_t fpb_flags = FPB_IGNORE_DIRTY | FPB_IGNORE_SOFT_DIRTY;
> >> -       int max_nr = folio_nr_pages(folio);
> >> -       pte_t pte = ptep_get(ptep);
> >> +       struct vm_area_struct *vma = pvmw->vma;
> >> +       unsigned long end_addr, addr = pvmw->address;
> >> +       unsigned int max_nr;
> >> +
> >> +       if (flags & TTU_HWPOISON)
> >> +               return 1;
> >> +       if (!folio_test_large(folio))
> >> +               return 1;
> >> +
> >> +       /* We may only batch within a single VMA and a single page table. */
> >> +       end_addr = min_t(unsigned long, ALIGN(addr + 1, PMD_SIZE), vma->vm_end);
> >
> > Is this pmd_addr_end()?
> >
>
> Yes, that could be reused as well here.
>
> >> +       max_nr = (end_addr - addr) >> PAGE_SHIFT;
> >>
> >> +       /* We only support lazyfree batching for now ... */
> >>           if (!folio_test_anon(folio) || folio_test_swapbacked(folio))
> >> -               return false;
> >> +               return 1;
> >>           if (pte_unused(pte))
> >> -               return false;
> >> -       if (pte_pfn(pte) != folio_pfn(folio))
> >> -               return false;
> >> +               return 1;
> >> +       /* ... where we must be able to batch the whole folio. */
> >> +       if (pte_pfn(pte) != folio_pfn(folio) || max_nr != folio_nr_pages(folio))
> >> +               return 1;
> >> +       max_nr = folio_pte_batch(folio, addr, pvmw->pte, pte, max_nr, fpb_flags,
> >> +                                NULL, NULL, NULL);
> >>
> >> -       return folio_pte_batch(folio, addr, ptep, pte, max_nr, fpb_flags, NULL,
> >> -                              NULL, NULL) == max_nr;
> >> +       if (max_nr != folio_nr_pages(folio))
> >> +               return 1;
> >> +       return max_nr;
> >>    }
> >>
> >>    /*
> >> @@ -2024,9 +2039,7 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
> >>                           if (pte_dirty(pteval))
> >>                                   folio_mark_dirty(folio);
> >>                   } else if (likely(pte_present(pteval))) {
> >> -                       if (folio_test_large(folio) && !(flags & TTU_HWPOISON) &&
> >> -                           can_batch_unmap_folio_ptes(address, folio, pvmw.pte))
> >> -                               nr_pages = folio_nr_pages(folio);
> >> +                       nr_pages = folio_unmap_pte_batch(folio, &pvmw, flags, pteval);
> >>                           end_addr = address + nr_pages * PAGE_SIZE;
> >>                           flush_cache_range(vma, address, end_addr);
> >>
> >>
> >> Note that I don't quite understand why we have to batch the whole thing or fallback to
> >> individual pages. Why can't we perform other batches that span only some PTEs? What's special
> >> about 1 PTE vs. 2 PTEs vs. all PTEs?
> >>
> >>
> >> Can someone enlighten me why that is required?
> >
> > It's probably not a strict requirement — I thought cases where the
> > count is greater than 1 but less than nr_pages might not provide much
> > practical benefit, except perhaps in very rare edge cases, since
> > madv_free() already calls split_folio().
>
> Okay, but it makes the code more complicated. If there is no reason to
> prevent the batching, we should drop it.

It's not necessarily more complex, since page_vma_mapped_walk() still
has to check each PTE individually and can't skip ahead based on nr.
With nr_pages batched, we can exit the loop early in one go.

Thanks
Barry