Re: [PATCH v2 1/1] mm/rmap: fix soft-dirty and uffd-wp bit loss when remapping zero-filled mTHP subpage to shared zeropage

[Dev Jain]

On 30/09/25 10:52 am, Lance Yang wrote:
> On 2025/9/30 12:50, Dev Jain wrote:
> > On 30/09/25 10:03 am, Lance Yang wrote:
> > > From: Lance Yang <lance.yang@xxxxxxxxx>
> > >
> > > When splitting an mTHP and replacing a zero-filled subpage with the 
> > > shared
> > > zeropage, try_to_map_unused_to_zeropage() currently drops several 
> > > important
> > > PTE bits.
> > >
> > > For userspace tools like CRIU, which rely on the soft-dirty 
> > > mechanism for
> > > incremental snapshots, losing the soft-dirty bit means modified 
> > > pages are
> > > missed, leading to inconsistent memory state after restore.
> > >
> > > As pointed out by David, the more critical uffd-wp bit is also dropped.
> > > This breaks the userfaultfd write-protection mechanism, causing writes
> > > to be silently missed by monitoring applications, which can lead to 
> > > data
> > > corruption.
> > >
> > > Preserve both the soft-dirty and uffd-wp bits from the old PTE when
> > > creating the new zeropage mapping to ensure they are correctly tracked.
> > >
> > > Cc: <stable@xxxxxxxxxxxxxxx>
> > > Fixes: b1f202060afe ("mm: remap unused subpages to shared zeropage 
> > > when splitting isolated thp")
> > > Suggested-by: David Hildenbrand <david@xxxxxxxxxx>
> > > Suggested-by: Dev Jain <dev.jain@xxxxxxx>
> > > Acked-by: David Hildenbrand <david@xxxxxxxxxx>
> > > Signed-off-by: Lance Yang <lance.yang@xxxxxxxxx>
> > > ---
> > > v1 -> v2:
> > >   - Avoid calling ptep_get() multiple times (per Dev)
> > >   - Double-check the uffd-wp bit (per David)
> > >   - Collect Acked-by from David - thanks!
> > >   - https://lore.kernel.org/linux-mm/20250928044855.76359-1- 
> > > lance.yang@xxxxxxxxx/
> > >
> > >   mm/migrate.c | 9 ++++++++-
> > >   1 file changed, 8 insertions(+), 1 deletion(-)
> > >
> > > diff --git a/mm/migrate.c b/mm/migrate.c
> > > index ce83c2c3c287..50aa91d9ab4e 100644
> > > --- a/mm/migrate.c
> > > +++ b/mm/migrate.c
> > > @@ -300,13 +300,14 @@ static bool 
> > > try_to_map_unused_to_zeropage(struct page_vma_mapped_walk *pvmw,
> > >                         unsigned long idx)
> > >   {
> > >       struct page *page = folio_page(folio, idx);
> > > +    pte_t oldpte = ptep_get(pvmw->pte);
> >
> > What I meant to say was, you can pass oldpte from 
> > remove_migration_pte to this
> > function. Basically define old_pte = ptep_get(pvmw.pte) in the 
> > declarations of
> > the start of the while block in remove_migration_pte and remove the 
> > existing
> > one. That will ensure ptep_get() gets called only once per iteration.
>
> Ah, got it. Thanks for the clarification!
>
> IIUC, you mean something like this:
>
> ```
> diff --git a/mm/migrate.c b/mm/migrate.c
> index ce83c2c3c287..bafd8cb3bebe 100644
> --- a/mm/migrate.c
> +++ b/mm/migrate.c
> @@ -297,6 +297,7 @@ bool isolate_folio_to_list(struct folio *folio, 
> struct list_head *list)
>
>  static bool try_to_map_unused_to_zeropage(struct page_vma_mapped_walk 
> *pvmw,
>                        struct folio *folio,
> +                      pte_t old_pte,
>                        unsigned long idx)
>  {
>      struct page *page = folio_page(folio, idx);
> @@ -306,7 +307,7 @@ static bool try_to_map_unused_to_zeropage(struct 
> page_vma_mapped_walk *pvmw,
>          return false;
>      VM_BUG_ON_PAGE(!PageAnon(page), page);
>      VM_BUG_ON_PAGE(!PageLocked(page), page);
> -    VM_BUG_ON_PAGE(pte_present(ptep_get(pvmw->pte)), page);
> +    VM_BUG_ON_PAGE(pte_present(old_pte), page);
>
>      if (folio_test_mlocked(folio) || (pvmw->vma->vm_flags & 
> VM_LOCKED) ||
>          mm_forbids_zeropage(pvmw->vma->vm_mm))
> @@ -322,6 +323,12 @@ static bool try_to_map_unused_to_zeropage(struct 
> page_vma_mapped_walk *pvmw,
>
>      newpte = pte_mkspecial(pfn_pte(my_zero_pfn(pvmw->address),
>                      pvmw->vma->vm_page_prot));
> +
> +    if (pte_swp_soft_dirty(old_pte))
> +        newpte = pte_mksoft_dirty(newpte);
> +    if (pte_swp_uffd_wp(old_pte))
> +        newpte = pte_mkuffd_wp(newpte);
> +
>      set_pte_at(pvmw->vma->vm_mm, pvmw->address, pvmw->pte, newpte);
>
>      dec_mm_counter(pvmw->vma->vm_mm, mm_counter(folio));
> @@ -344,7 +351,7 @@ static bool remove_migration_pte(struct folio *folio,
>
>      while (page_vma_mapped_walk(&pvmw)) {
>          rmap_t rmap_flags = RMAP_NONE;
> -        pte_t old_pte;
> +        pte_t old_pte = ptep_get(pvmw.pte);
>          pte_t pte;
>          swp_entry_t entry;
>          struct page *new;
> @@ -365,12 +372,11 @@ static bool remove_migration_pte(struct folio 
> *folio,
>          }
>  #endif
>          if (rmap_walk_arg->map_unused_to_zeropage &&
> -            try_to_map_unused_to_zeropage(&pvmw, folio, idx))
> +            try_to_map_unused_to_zeropage(&pvmw, folio, old_pte, idx))
>              continue;
>
>          folio_get(folio);
>          pte = mk_pte(new, READ_ONCE(vma->vm_page_prot));
> -        old_pte = ptep_get(pvmw.pte);
>
>          entry = pte_to_swp_entry(old_pte);
>          if (!is_migration_entry_young(entry))
> ```
>
> ptep_get() gets called only once per iteration, right?

Yup.