Merge tag 'for-7.4/io_uring-dmabuf-20261023' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux

Pull io_uring dma-buf support from Jens Axboe:
 "This adds native dma-buf support to the I/O path, exposed through
  io_uring. It's been in development for a while and should be ready to
  go now.

   - dma-buf file I/O infrastructure: a dma_buf_io_ctx created through a
     new ->init_dma_buf_io_ctx file operation, and a dma_buf_io_map
     holding the device DMA mapping. The two are split so a mapping can
     be invalidated and re-established underneath a live context, with
     the map counting in-flight requests so it can be torn down safely.

   - A new iov_iter type for dmabuf maps, and a dma map backed bio type
     for the block layer, with raw block device support on top.

   - nvme-pci backend implementing dma-buf backed requests, including
     SGL support.

   - io_uring dmabuf backed registered buffers, built on a reworked
     buffer registration structure with an extended update path, regbuf
     import flags, an uncloneable flag for buffer types that can't be
     cloned, and cloning support for registered dma-bufs"

* tag 'for-7.4/io_uring-dmabuf-20261023' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux:
  io_uring/dma-buf: don't fail fixed buffers without dma-buf support
  nvme-pci: detach dma-bufs only on removal
  block: reject dma-bufs larger than 4GiB
  io_uring/dma-buf: allow cloning registered dma-bufs
  dma-buf-io: document dma_buf_io_init_map
  dma-buf-io: fix typos in kernel docs
  block: fix indention for dma-buf checks
  io_uring/rsrc: add dmabuf backed registered buffers
  io_uring/rsrc: add regbuf import flags
  io_uring/rsrc: add uncloneable regbuf flag
  io_uring/rsrc: extend buffer update
  io_uring/rsrc: introduce buf registration structure
  nvme-pci: add SGL support for the dmabuf path
  nvme-pci: implement dma-buf backed requests
  nvme-pci: rename nvme_pci_sgl_set_data to nvme_pci_dma_iter_set_sgl
  block: add dma-buf support for raw bdev
  block: introduce dma map backed bio type
  block: always adjust bi_offset on bio_advance_iter
  iov_iter: add iterator type for dmabuf maps
  dma-buf: introduce initial file I/O infrastructure

1 files changed, 23 insertions, 6 deletions

diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index 2072c04e99d0..6831a5d9396e 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))) {
 		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) ||
+	    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 dma_buf_io_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.
@@ -856,7 +872,7 @@ unsigned long iov_iter_alignment(const struct iov_iter *i)
 		return iov_iter_alignment_bvec(i);
 
 	/* With both xarray and folioq types, we're dealing with whole folios. */
-	if (iov_iter_is_folioq(i))
+	if (iov_iter_is_folioq(i) || iov_iter_is_dmabuf_map(i))
 		return i->iov_offset | i->count;
 	if (iov_iter_is_xarray(i))
 		return (i->xarray_start + i->iov_offset) | i->count;
@@ -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