[PATCH v3 02/10] iov_iter: add iterator type for dmabuf maps

David Laight david.laight.linux at gmail.com
Wed May 13 03:05:57 PDT 2026


On Wed, 29 Apr 2026 16:25:48 +0100
Pavel Begunkov <asml.silence at gmail.com> wrote:

> Introduce a new iterator type for dmabuf maps. The map in an opaque
> object with internals and format specific to the subsystem / driver, and
> only it can use that subsystem / driver for issuing IO. The task of the
> middle layers is to pass the map / iterator further down, maybe doing
> basic splitting and length checking. The iterator can only be used by
> operations of the file the associated map was created for.
> 
> Suggested-by: Keith Busch <kbusch at kernel.org>
> Signed-off-by: Pavel Begunkov <asml.silence at gmail.com>
> ---
>  include/linux/uio.h | 11 +++++++++++
>  lib/iov_iter.c      | 29 +++++++++++++++++++++++------
>  2 files changed, 34 insertions(+), 6 deletions(-)
> 
> diff --git a/include/linux/uio.h b/include/linux/uio.h
> index a9bc5b3067e3..75051aed70de 100644
> --- a/include/linux/uio.h
> +++ b/include/linux/uio.h
> @@ -12,6 +12,7 @@
>  
>  struct page;
>  struct folio_queue;
> +struct io_dmabuf_map;
>  
>  typedef unsigned int __bitwise iov_iter_extraction_t;
>  
> @@ -29,6 +30,7 @@ enum iter_type {
>  	ITER_FOLIOQ,
>  	ITER_XARRAY,
>  	ITER_DISCARD,
> +	ITER_DMABUF_MAP,
>  };
>  
>  #define ITER_SOURCE	1	// == WRITE
> @@ -71,6 +73,7 @@ struct iov_iter {
>  				const struct folio_queue *folioq;
>  				struct xarray *xarray;
>  				void __user *ubuf;
> +				struct io_dmabuf_map *dmabuf_map;
>  			};
>  			size_t count;
>  		};
> @@ -155,6 +158,11 @@ static inline bool iov_iter_is_xarray(const struct iov_iter *i)
>  	return iov_iter_type(i) == ITER_XARRAY;
>  }
>  
> +static inline bool iov_iter_is_dmabuf_map(const struct iov_iter *i)
> +{
> +	return iov_iter_type(i) == ITER_DMABUF_MAP;
> +}
> +
>  static inline unsigned char iov_iter_rw(const struct iov_iter *i)
>  {
>  	return i->data_source ? WRITE : READ;
> @@ -300,6 +308,9 @@ void iov_iter_folio_queue(struct iov_iter *i, unsigned int direction,
>  			  unsigned int first_slot, unsigned int offset, size_t count);
>  void iov_iter_xarray(struct iov_iter *i, unsigned int direction, struct xarray *xarray,
>  		     loff_t start, size_t count);
> +void iov_iter_dmabuf_map(struct iov_iter *i, unsigned int direction,
> +			struct io_dmabuf_map *map,
> +			loff_t off, size_t count);
>  ssize_t iov_iter_get_pages2(struct iov_iter *i, struct page **pages,
>  			size_t maxsize, unsigned maxpages, size_t *start);
>  ssize_t iov_iter_get_pages_alloc2(struct iov_iter *i, struct page ***pages,
> diff --git a/lib/iov_iter.c b/lib/iov_iter.c
> index 243662af1af7..e2253684b991 100644
> --- a/lib/iov_iter.c
> +++ b/lib/iov_iter.c
> @@ -575,7 +575,8 @@ void iov_iter_advance(struct iov_iter *i, size_t size)
>  {
>  	if (unlikely(i->count < size))
>  		size = i->count;
> -	if (likely(iter_is_ubuf(i)) || unlikely(iov_iter_is_xarray(i))) {
> +	if (likely(iter_is_ubuf(i)) || unlikely(iov_iter_is_xarray(i)) ||
> +	    unlikely(iov_iter_is_dmabuf_map(i))) {


Doesn't the extra check add more code to all the non-ubuf cases?
This could be fixed by either making iter_type a bitmask (with one bit set)
or writing an iter_is_one_of(i, ITER_xxx, ITER_yyy) define that uses
'(1 << i->iter_type) & ((1 << ITER_xxx) | ...)'
(look at the the nolibc printf code for an example).

>  		i->iov_offset += size;
>  		i->count -= size;
>  	} else if (likely(iter_is_iovec(i) || iov_iter_is_kvec(i))) {
> @@ -631,7 +632,8 @@ void iov_iter_revert(struct iov_iter *i, size_t unroll)
>  		return;
>  	}
>  	unroll -= i->iov_offset;
> -	if (iov_iter_is_xarray(i) || iter_is_ubuf(i)) {
> +	if (iov_iter_is_xarray(i) || iter_is_ubuf(i) ||

iter_is_ubuf() should have been first here.

-- David

> +	    iov_iter_is_dmabuf_map(i)) {
>  		BUG(); /* We should never go beyond the start of the specified
>  			* range since we might then be straying into pages that
>  			* aren't pinned.
> @@ -775,6 +777,20 @@ void iov_iter_xarray(struct iov_iter *i, unsigned int direction,
>  }
>  EXPORT_SYMBOL(iov_iter_xarray);
>  
> +void iov_iter_dmabuf_map(struct iov_iter *i, unsigned int direction,
> +			 struct io_dmabuf_map *map,
> +			 loff_t off, size_t count)
> +{
> +	WARN_ON(direction & ~(READ | WRITE));
> +	*i = (struct iov_iter){
> +		.iter_type = ITER_DMABUF_MAP,
> +		.data_source = direction,
> +		.dmabuf_map = map,
> +		.count = count,
> +		.iov_offset = off,
> +	};
> +}
> +
>  /**
>   * iov_iter_discard - Initialise an I/O iterator that discards data
>   * @i: The iterator to initialise.
> @@ -841,7 +857,7 @@ static unsigned long iov_iter_alignment_bvec(const struct iov_iter *i)
>  
>  unsigned long iov_iter_alignment(const struct iov_iter *i)
>  {
> -	if (likely(iter_is_ubuf(i))) {
> +	if (likely(iter_is_ubuf(i)) || iov_iter_is_dmabuf_map(i)) {
>  		size_t size = i->count;
>  		if (size)
>  			return ((unsigned long)i->ubuf + i->iov_offset) | size;
> @@ -872,7 +888,7 @@ unsigned long iov_iter_gap_alignment(const struct iov_iter *i)
>  	size_t size = i->count;
>  	unsigned k;
>  
> -	if (iter_is_ubuf(i))
> +	if (iter_is_ubuf(i) || iov_iter_is_dmabuf_map(i))
>  		return 0;
>  
>  	if (WARN_ON(!iter_is_iovec(i)))
> @@ -1469,11 +1485,12 @@ EXPORT_SYMBOL_GPL(import_ubuf);
>  void iov_iter_restore(struct iov_iter *i, struct iov_iter_state *state)
>  {
>  	if (WARN_ON_ONCE(!iov_iter_is_bvec(i) && !iter_is_iovec(i) &&
> -			 !iter_is_ubuf(i)) && !iov_iter_is_kvec(i))
> +			 !iter_is_ubuf(i) && !iov_iter_is_kvec(i) &&
> +			 !iov_iter_is_dmabuf_map(i)))
>  		return;
>  	i->iov_offset = state->iov_offset;
>  	i->count = state->count;
> -	if (iter_is_ubuf(i))
> +	if (iter_is_ubuf(i) || iov_iter_is_dmabuf_map(i))
>  		return;
>  	/*
>  	 * For the *vec iters, nr_segs + iov is constant - if we increment




More information about the Linux-nvme mailing list