Re: [PATCH v2 20/26] userfaultfd: wp: support write protection for userfault vma range

[Mike Rapoport <rppt@linux.ibm.com>]

On Tue, Feb 12, 2019 at 10:56:26AM +0800, Peter Xu wrote:
> From: Shaohua Li <shli@fb.com>
> 
> Add API to enable/disable writeprotect a vma range. Unlike mprotect,
> this doesn't split/merge vmas.
> 
> Cc: Andrea Arcangeli <aarcange@redhat.com>
> Cc: Rik van Riel <riel@redhat.com>
> Cc: Kirill A. Shutemov <kirill@shutemov.name>
> Cc: Mel Gorman <mgorman@suse.de>
> Cc: Hugh Dickins <hughd@google.com>
> Cc: Johannes Weiner <hannes@cmpxchg.org>
> Signed-off-by: Shaohua Li <shli@fb.com>
> Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
> [peterx:
>  - use the helper to find VMA;
>  - return -ENOENT if not found to match mcopy case;
>  - use the new MM_CP_UFFD_WP* flags for change_protection
>  - check against mmap_changing for failures]
> Signed-off-by: Peter Xu <peterx@redhat.com>
> ---
>  include/linux/userfaultfd_k.h |  3 ++
>  mm/userfaultfd.c              | 54 +++++++++++++++++++++++++++++++++++
>  2 files changed, 57 insertions(+)
> 
> diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
> index 765ce884cec0..8f6e6ed544fb 100644
> --- a/include/linux/userfaultfd_k.h
> +++ b/include/linux/userfaultfd_k.h
> @@ -39,6 +39,9 @@ extern ssize_t mfill_zeropage(struct mm_struct *dst_mm,
>  			      unsigned long dst_start,
>  			      unsigned long len,
>  			      bool *mmap_changing);
> +extern int mwriteprotect_range(struct mm_struct *dst_mm,
> +			       unsigned long start, unsigned long len,
> +			       bool enable_wp, bool *mmap_changing);
> 
>  /* mm helpers */
>  static inline bool is_mergeable_vm_userfaultfd_ctx(struct vm_area_struct *vma,
> diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
> index fefa81c301b7..529d180bb4d7 100644
> --- a/mm/userfaultfd.c
> +++ b/mm/userfaultfd.c
> @@ -639,3 +639,57 @@ ssize_t mfill_zeropage(struct mm_struct *dst_mm, unsigned long start,
>  {
>  	return __mcopy_atomic(dst_mm, start, 0, len, true, mmap_changing, 0);
>  }
> +
> +int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start,
> +			unsigned long len, bool enable_wp, bool *mmap_changing)
> +{
> +	struct vm_area_struct *dst_vma;
> +	pgprot_t newprot;
> +	int err;
> +
> +	/*
> +	 * Sanitize the command parameters:
> +	 */
> +	BUG_ON(start & ~PAGE_MASK);
> +	BUG_ON(len & ~PAGE_MASK);
> +
> +	/* Does the address range wrap, or is the span zero-sized? */
> +	BUG_ON(start + len <= start);

I'd replace these BUG_ON()s with

	if (WARN_ON())
		 return -EINVAL;

> +
> +	down_read(&dst_mm->mmap_sem);
> +
> +	/*
> +	 * If memory mappings are changing because of non-cooperative
> +	 * operation (e.g. mremap) running in parallel, bail out and
> +	 * request the user to retry later
> +	 */
> +	err = -EAGAIN;
> +	if (mmap_changing && READ_ONCE(*mmap_changing))
> +		goto out_unlock;
> +
> +	err = -ENOENT;
> +	dst_vma = vma_find_uffd(dst_mm, start, len);
> +	/*
> +	 * Make sure the vma is not shared, that the dst range is
> +	 * both valid and fully within a single existing vma.
> +	 */
> +	if (!dst_vma || (dst_vma->vm_flags & VM_SHARED))
> +		goto out_unlock;
> +	if (!userfaultfd_wp(dst_vma))
> +		goto out_unlock;
> +	if (!vma_is_anonymous(dst_vma))
> +		goto out_unlock;
> +
> +	if (enable_wp)
> +		newprot = vm_get_page_prot(dst_vma->vm_flags & ~(VM_WRITE));
> +	else
> +		newprot = vm_get_page_prot(dst_vma->vm_flags);
> +
> +	change_protection(dst_vma, start, start + len, newprot,
> +			  enable_wp ? MM_CP_UFFD_WP : MM_CP_UFFD_WP_RESOLVE);
> +
> +	err = 0;
> +out_unlock:
> +	up_read(&dst_mm->mmap_sem);
> +	return err;
> +}
> -- 
> 2.17.1
> 

-- 
Sincerely yours,
Mike.