Re: [PATCH v6 06/16] mm: allow vma_start_read_locked/vma_start_read_locked_nested to fail

[Lokesh Gidra]

On Mon, Dec 16, 2024 at 11:24 AM Suren Baghdasaryan <surenb@xxxxxxxxxx> wrote:
>
> With upcoming replacement of vm_lock with vm_refcnt, we need to handle a
> possibility of vma_start_read_locked/vma_start_read_locked_nested failing
> due to refcount overflow. Prepare for such possibility by changing these
> APIs and adjusting their users.
>
> Signed-off-by: Suren Baghdasaryan <surenb@xxxxxxxxxx>
> Cc: Lokesh Gidra <lokeshgidra@xxxxxxxxxx>
> ---
>  include/linux/mm.h |  6 ++++--
>  mm/userfaultfd.c   | 17 ++++++++++++-----
>  2 files changed, 16 insertions(+), 7 deletions(-)
>
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index 689f5a1e2181..0ecd321c50b7 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -747,10 +747,11 @@ static inline bool vma_start_read(struct vm_area_struct *vma)
>   * not be used in such cases because it might fail due to mm_lock_seq overflow.
>   * This functionality is used to obtain vma read lock and drop the mmap read lock.
>   */
> -static inline void vma_start_read_locked_nested(struct vm_area_struct *vma, int subclass)
> +static inline bool vma_start_read_locked_nested(struct vm_area_struct *vma, int subclass)
>  {
>         mmap_assert_locked(vma->vm_mm);
>         down_read_nested(&vma->vm_lock.lock, subclass);
> +       return true;
>  }
>
>  /*
> @@ -759,10 +760,11 @@ static inline void vma_start_read_locked_nested(struct vm_area_struct *vma, int
>   * not be used in such cases because it might fail due to mm_lock_seq overflow.
>   * This functionality is used to obtain vma read lock and drop the mmap read lock.
>   */
> -static inline void vma_start_read_locked(struct vm_area_struct *vma)
> +static inline bool vma_start_read_locked(struct vm_area_struct *vma)
>  {
>         mmap_assert_locked(vma->vm_mm);
>         down_read(&vma->vm_lock.lock);
> +       return true;
>  }
>
>  static inline void vma_end_read(struct vm_area_struct *vma)
> diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
> index bc9a66ec6a6e..79e8ae676f75 100644
> --- a/mm/userfaultfd.c
> +++ b/mm/userfaultfd.c
> @@ -85,7 +85,8 @@ static struct vm_area_struct *uffd_lock_vma(struct mm_struct *mm,
>         mmap_read_lock(mm);
>         vma = find_vma_and_prepare_anon(mm, address);
>         if (!IS_ERR(vma))
> -               vma_start_read_locked(vma);
> +               if (!vma_start_read_locked(vma))
> +                       vma = ERR_PTR(-EAGAIN);
>
>         mmap_read_unlock(mm);
>         return vma;
> @@ -1483,10 +1484,16 @@ static int uffd_move_lock(struct mm_struct *mm,
>         mmap_read_lock(mm);
>         err = find_vmas_mm_locked(mm, dst_start, src_start, dst_vmap, src_vmap);
>         if (!err) {
> -               vma_start_read_locked(*dst_vmap);
> -               if (*dst_vmap != *src_vmap)
> -                       vma_start_read_locked_nested(*src_vmap,
> -                                               SINGLE_DEPTH_NESTING);
> +               if (!vma_start_read_locked(*dst_vmap)) {

I think you mistakenly reversed the condition. This block should be
executed if we manage to lock dst_vma successfully.
> +                       if (*dst_vmap != *src_vmap) {
> +                               if (!vma_start_read_locked_nested(*src_vmap,
> +                                                       SINGLE_DEPTH_NESTING)) {
> +                                       vma_end_read(*dst_vmap);
> +                                       err = -EAGAIN;
> +                               }
> +                       }
> +               } else
> +                       err = -EAGAIN;
>         }
>         mmap_read_unlock(mm);
>         return err;
> --
> 2.47.1.613.gc27f4b7a9f-goog
>