[v2,1/3] userfaultfd: UFFDIO_REMAP: rmap preparation

From: Andrea Arcangeli <aarcange@redhat.com>

As far as the rmap code is concerned, UFFDIO_REMAP only alters the
page->mapping and page->index. It does it while holding the page
lock. However folio_referenced() is doing rmap walks without taking the
folio lock first, so folio_lock_anon_vma_read() must be updated to
re-check that the folio->mapping didn't change after we obtained the
anon_vma read lock.

UFFDIO_REMAP takes the anon_vma lock for writing before altering the
folio->mapping, so if the folio->mapping is still the same after
obtaining the anon_vma read lock (without the folio lock), the rmap
walks can go ahead safely (and UFFDIO_REMAP will wait the rmap walk to
complete before proceeding).

UFFDIO_REMAP serializes against itself with the folio lock.

All other places taking the anon_vma lock while holding the mmap_lock
for writing, don't need to check if the folio->mapping has changed
after taking the anon_vma lock, regardless of the folio lock, because
UFFDIO_REMAP holds the mmap_lock for reading.

There's one constraint enforced to allow this simplification: the
source pages passed to UFFDIO_REMAP must be mapped only in one vma,
but this constraint is an acceptable tradeoff for UFFDIO_REMAP
users.

The source addresses passed to UFFDIO_REMAP can be set as
VM_DONTCOPY with MADV_DONTFORK to avoid any risk of the mapcount of
the pages increasing if some thread of the process forks() before
UFFDIO_REMAP run.

Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
---
 mm/rmap.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

On Thu, Sep 28, 2023 at 9:23 AM Peter Xu <peterx@redhat.com> wrote:
>
> Suren,
>
> Sorry to review so late.
>
> On Fri, Sep 22, 2023 at 06:31:44PM -0700, Suren Baghdasaryan wrote:
> > diff --git a/mm/rmap.c b/mm/rmap.c
> > index ec7f8e6c9e48..c1ebbd23fa61 100644
> > --- a/mm/rmap.c
> > +++ b/mm/rmap.c
> > @@ -542,6 +542,7 @@ struct anon_vma *folio_lock_anon_vma_read(struct folio *folio,
> >       struct anon_vma *root_anon_vma;
> >       unsigned long anon_mapping;
> >
> > +repeat:
> >       rcu_read_lock();
> >       anon_mapping = (unsigned long)READ_ONCE(folio->mapping);
> >       if ((anon_mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON)
> > @@ -586,6 +587,18 @@ struct anon_vma *folio_lock_anon_vma_read(struct folio *folio,
> >       rcu_read_unlock();
> >       anon_vma_lock_read(anon_vma);
> >
> > +     /*
> > +      * Check if UFFDIO_REMAP changed the anon_vma. This is needed
> > +      * because we don't assume the folio was locked.
> > +      */
> > +     if (unlikely((unsigned long) READ_ONCE(folio->mapping) !=
> > +                  anon_mapping)) {
> > +             anon_vma_unlock_read(anon_vma);
> > +             put_anon_vma(anon_vma);
> > +             anon_vma = NULL;
> > +             goto repeat;
> > +     }
>
> We have an open-coded fast path above this:
>
>         if (down_read_trylock(&root_anon_vma->rwsem)) {
>                 /*
>                  * If the folio is still mapped, then this anon_vma is still
>                  * its anon_vma, and holding the mutex ensures that it will
>                  * not go away, see anon_vma_free().
>                  */
>                 if (!folio_mapped(folio)) {
>                         up_read(&root_anon_vma->rwsem);
>                         anon_vma = NULL;
>                 }
>                 goto out;
>         }
>
> Would that also need such check?

Yes, I think they should be handled the same way. Will fix. Thanks!

>
> > +
> >       if (atomic_dec_and_test(&anon_vma->refcount)) {
> >               /*
> >                * Oops, we held the last refcount, release the lock
> > --
> > 2.42.0.515.g380fc7ccd1-goog
> >
>
> --
> Peter Xu
>

On Mon, Oct 02, 2023 at 04:42:50PM +0200, David Hildenbrand wrote:
> On 23.09.23 03:31, Suren Baghdasaryan wrote:
> > From: Andrea Arcangeli <aarcange@redhat.com>
> > 
> > As far as the rmap code is concerned, UFFDIO_REMAP only alters the
> > page->mapping and page->index. It does it while holding the page
> > lock. However folio_referenced() is doing rmap walks without taking the
> > folio lock first, so folio_lock_anon_vma_read() must be updated to
> > re-check that the folio->mapping didn't change after we obtained the
> > anon_vma read lock.
> 
> I'm curious: why don't we need this for existing users of
> page_move_anon_rmap()? What's special about UFFDIO_REMAP?

Totally no expert on anon vma so I'm prone to errors, but IIUC the
difference here is root anon vma cannot change in page_move_anon_rmap(),
while UFFDIO_REMAP can.

Thanks,

On Mon, Oct 2, 2023 at 10:30 AM David Hildenbrand <david@redhat.com> wrote:
>
> On 02.10.23 17:23, Peter Xu wrote:
> > On Mon, Oct 02, 2023 at 04:42:50PM +0200, David Hildenbrand wrote:
> >> On 23.09.23 03:31, Suren Baghdasaryan wrote:
> >>> From: Andrea Arcangeli <aarcange@redhat.com>
> >>>
> >>> As far as the rmap code is concerned, UFFDIO_REMAP only alters the
> >>> page->mapping and page->index. It does it while holding the page
> >>> lock. However folio_referenced() is doing rmap walks without taking the
> >>> folio lock first, so folio_lock_anon_vma_read() must be updated to
> >>> re-check that the folio->mapping didn't change after we obtained the
> >>> anon_vma read lock.
> >>
> >> I'm curious: why don't we need this for existing users of
> >> page_move_anon_rmap()? What's special about UFFDIO_REMAP?
> >
> > Totally no expert on anon vma so I'm prone to errors, but IIUC the
> > difference here is root anon vma cannot change in page_move_anon_rmap(),
> > while UFFDIO_REMAP can.
>
> That does sound reasonable, thanks.
>
> Probably we can do better with the patch description (once [1] is used
> to move the folio to the other anon_vma).

I'll develop the next version with your patches in the baseline.
Hopefully by the time of my posting your patches will be in the
mm-unstable.

>
> "mm/rmap: support move to different root anon_vma in folio_move_anon_rmap()
>
> For now, folio_move_anon_rmap() was only used to move a folio to a
> different anon_vma after fork(), whereby the root anon_vma stayed
> unchanged. For that, it was sufficient to hold the page lock when
> calling folio_move_anon_rmap().
>
> However, we want to make use of folio_move_anon_rmap() to move folios
> between VMAs that have a different root anon_vma. As folio_referenced()
> performs an RMAP walk without holding the page lock but only holding the
> anon_vma in read mode, holding the page lock is insufficient.
>
> When moving to an anon_vma with a different root anon_vma, we'll have to
> hold both, the page lock and the anon_vma lock in write mode.
> Consequently, whenever we succeeded in folio_lock_anon_vma_read() to
> read-lock the anon_vma, we have to re-check if the mapping was changed
> in the meantime. If that was the case, we have to retry.
>
> Note that folio_move_anon_rmap() must only be called if the anon page is
> exclusive to a process, and must not be called on KSM folios.
>
> This is a preparation for UFFDIO_REMAP, which will hold the page lock,
> the anon_vma lock in write mode, and the mmap_lock in read mode.
> "

Thanks for taking time to write this up! Looks really clear to me.
I'll reuse it.

>
> In addition, we should document these locking details for
> folio_move_anon_rmap() and probably not mention UFFDIO_REMAP in the
> comment in folio_lock_anon_vma_read(), but instead say
> "folio_move_anon_rmap() might have changed the anon_vma as we might not
> hold the page lock here."

Sounds good. Will add.

>
>
> [1] https://lkml.kernel.org/r/20231002142949.235104-3-david@redhat.com
>
> --
> Cheers,
>
> David / dhildenb
>