Re: [PATCH RFC 04/17] userfaultfd: introduce mfill_get_vma() and mfill_put_vma()

[Peter Xu <peterx@redhat.com>]

Hi, Mike,

On Tue, Jan 27, 2026 at 09:29:23PM +0200, Mike Rapoport wrote:
> From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
> 
> Split the code that finds, locks and verifies VMA from mfill_atomic()
> into a helper function.
> 
> This function will be used later during refactoring of
> mfill_atomic_pte_copy().
> 
> Add a counterpart mfill_put_vma() helper that unlocks the VMA and
> releases map_changing_lock.
> 
> Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
> ---
>  mm/userfaultfd.c | 124 ++++++++++++++++++++++++++++-------------------
>  1 file changed, 73 insertions(+), 51 deletions(-)
> 
> diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
> index 9dd285b13f3b..45d8f04aaf4f 100644
> --- a/mm/userfaultfd.c
> +++ b/mm/userfaultfd.c
> @@ -157,6 +157,73 @@ static void uffd_mfill_unlock(struct vm_area_struct *vma)
>  }
>  #endif
>  
> +static void mfill_put_vma(struct mfill_state *state)
> +{
> +	up_read(&state->ctx->map_changing_lock);
> +	uffd_mfill_unlock(state->vma);
> +	state->vma = NULL;
> +}
> +
> +static int mfill_get_vma(struct mfill_state *state)
> +{
> +	struct userfaultfd_ctx *ctx = state->ctx;
> +	uffd_flags_t flags = state->flags;
> +	struct vm_area_struct *dst_vma;
> +	int err;
> +
> +	/*
> +	 * Make sure the vma is not shared, that the dst range is
> +	 * both valid and fully within a single existing vma.
> +	 */
> +	dst_vma = uffd_mfill_lock(ctx->mm, state->dst_start, state->len);
> +	if (IS_ERR(dst_vma))
> +		return PTR_ERR(dst_vma);
> +
> +	/*
> +	 * 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
> +	 */
> +	down_read(&ctx->map_changing_lock);
> +	err = -EAGAIN;
> +	if (atomic_read(&ctx->mmap_changing))
> +		goto out_unlock;
> +
> +	err = -EINVAL;
> +
> +	/*
> +	 * shmem_zero_setup is invoked in mmap for MAP_ANONYMOUS|MAP_SHARED but
> +	 * it will overwrite vm_ops, so vma_is_anonymous must return false.
> +	 */
> +	if (WARN_ON_ONCE(vma_is_anonymous(dst_vma) &&
> +	    dst_vma->vm_flags & VM_SHARED))
> +		goto out_unlock;
> +
> +	/*
> +	 * validate 'mode' now that we know the dst_vma: don't allow
> +	 * a wrprotect copy if the userfaultfd didn't register as WP.
> +	 */
> +	if ((flags & MFILL_ATOMIC_WP) && !(dst_vma->vm_flags & VM_UFFD_WP))
> +		goto out_unlock;
> +
> +	if (is_vm_hugetlb_page(dst_vma))
> +		goto out;
> +
> +	if (!vma_is_anonymous(dst_vma) && !vma_is_shmem(dst_vma))
> +		goto out_unlock;
> +	if (!vma_is_shmem(dst_vma) &&
> +	    uffd_flags_mode_is(flags, MFILL_ATOMIC_CONTINUE))
> +		goto out_unlock;

IMHO it's a bit weird to check for vma permissions in a get_vma() function.

Also, in the follow up patch it'll be also reused in
mfill_copy_folio_retry() which doesn't need to check vma permission.

Maybe we can introduce mfill_vma_check() for these two checks? Then we can
also drop the slightly weird is_vm_hugetlb_page() check (and "out" label)
above.

> +
> +out:
> +	state->vma = dst_vma;
> +	return 0;
> +
> +out_unlock:
> +	mfill_put_vma(state);
> +	return err;
> +}
> +
>  static pmd_t *mm_alloc_pmd(struct mm_struct *mm, unsigned long address)
>  {
>  	pgd_t *pgd;
> @@ -768,8 +835,6 @@ static __always_inline ssize_t mfill_atomic(struct userfaultfd_ctx *ctx,
>  		.src_addr = src_start,
>  		.dst_addr = dst_start,
>  	};
> -	struct mm_struct *dst_mm = ctx->mm;
> -	struct vm_area_struct *dst_vma;
>  	long copied = 0;
>  	ssize_t err;
>  
> @@ -784,57 +849,17 @@ static __always_inline ssize_t mfill_atomic(struct userfaultfd_ctx *ctx,
>  	VM_WARN_ON_ONCE(dst_start + len <= dst_start);
>  
>  retry:
> -	/*
> -	 * Make sure the vma is not shared, that the dst range is
> -	 * both valid and fully within a single existing vma.
> -	 */
> -	dst_vma = uffd_mfill_lock(dst_mm, dst_start, len);
> -	if (IS_ERR(dst_vma)) {
> -		err = PTR_ERR(dst_vma);
> +	err = mfill_get_vma(&state);
> +	if (err)
>  		goto out;
> -	}
> -
> -	/*
> -	 * 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
> -	 */
> -	down_read(&ctx->map_changing_lock);
> -	err = -EAGAIN;
> -	if (atomic_read(&ctx->mmap_changing))
> -		goto out_unlock;
> -
> -	err = -EINVAL;
> -	/*
> -	 * shmem_zero_setup is invoked in mmap for MAP_ANONYMOUS|MAP_SHARED but
> -	 * it will overwrite vm_ops, so vma_is_anonymous must return false.
> -	 */
> -	if (WARN_ON_ONCE(vma_is_anonymous(dst_vma) &&
> -	    dst_vma->vm_flags & VM_SHARED))
> -		goto out_unlock;
> -
> -	/*
> -	 * validate 'mode' now that we know the dst_vma: don't allow
> -	 * a wrprotect copy if the userfaultfd didn't register as WP.
> -	 */
> -	if ((flags & MFILL_ATOMIC_WP) && !(dst_vma->vm_flags & VM_UFFD_WP))
> -		goto out_unlock;
>  
>  	/*
>  	 * If this is a HUGETLB vma, pass off to appropriate routine
>  	 */
> -	if (is_vm_hugetlb_page(dst_vma))
> -		return  mfill_atomic_hugetlb(ctx, dst_vma, dst_start,
> +	if (is_vm_hugetlb_page(state.vma))
> +		return  mfill_atomic_hugetlb(ctx, state.vma, dst_start,
>  					     src_start, len, flags);
>  
> -	if (!vma_is_anonymous(dst_vma) && !vma_is_shmem(dst_vma))
> -		goto out_unlock;
> -	if (!vma_is_shmem(dst_vma) &&
> -	    uffd_flags_mode_is(flags, MFILL_ATOMIC_CONTINUE))
> -		goto out_unlock;
> -
> -	state.vma = dst_vma;
> -
>  	while (state.src_addr < src_start + len) {
>  		VM_WARN_ON_ONCE(state.dst_addr >= dst_start + len);
>  
> @@ -853,8 +878,7 @@ static __always_inline ssize_t mfill_atomic(struct userfaultfd_ctx *ctx,
>  		if (unlikely(err == -ENOENT)) {
>  			void *kaddr;
>  
> -			up_read(&ctx->map_changing_lock);
> -			uffd_mfill_unlock(state.vma);
> +			mfill_put_vma(&state);
>  			VM_WARN_ON_ONCE(!state.folio);
>  
>  			kaddr = kmap_local_folio(state.folio, 0);
> @@ -883,9 +907,7 @@ static __always_inline ssize_t mfill_atomic(struct userfaultfd_ctx *ctx,
>  			break;
>  	}
>  
> -out_unlock:
> -	up_read(&ctx->map_changing_lock);
> -	uffd_mfill_unlock(state.vma);
> +	mfill_put_vma(&state);
>  out:
>  	if (state.folio)
>  		folio_put(state.folio);
> -- 
> 2.51.0
> 

-- 
Peter Xu