[PATCH v7 05/13] block: add dma-buf support for raw bdev

[Pavel Begunkov]

Add a simple proxy implementation of init_dma_buf_io_ctx() forwarding
the call to a new struct block_device_operations operation. Also reject
dma-buf backed iterators for buffered IO.

Reviewed-by: Christoph Hellwig <hch at lst.de>
[pavel: reject dma-buf without O_DIRECT]
Signed-off-by: Pavel Begunkov <asml.silence at gmail.com>
---
 block/fops.c           | 25 ++++++++++++++++++++++++-
 include/linux/blkdev.h |  2 ++
 2 files changed, 26 insertions(+), 1 deletion(-)

diff --git a/block/fops.c b/block/fops.c
index 641621db700f..d05a78d0919a 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -783,7 +783,8 @@ static ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
 
 	if (iocb->ki_flags & IOCB_DIRECT) {
 		ret = blkdev_direct_write(iocb, from);
-		if (ret >= 0 && iov_iter_count(from)) {
+		if (ret >= 0 && iov_iter_count(from) &&
+		    !iov_iter_is_dmabuf_map(from)) {
 			ret = direct_write_fallback(iocb, from, ret,
 					blkdev_buffered_write(iocb, from));
 			need_sync = true;
@@ -796,6 +797,9 @@ static ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
 			need_sync = true;
 		}
 	} else {
+		if (unlikely(iov_iter_is_dmabuf_map(from)))
+			return -EOPNOTSUPP;
+
 		/*
 		 * Take i_rwsem and invalidate_lock to avoid racing with
 		 * set_blocksize changing i_blkbits/folio order and punching
@@ -851,6 +855,11 @@ static ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to)
 		if (ret < 0 || !count)
 			goto reexpand;
 	}
+	if (unlikely(iov_iter_is_dmabuf_map(to))) {
+		if (!ret)
+			ret = -EOPNOTSUPP;
+		goto reexpand;
+	}
 
 	/*
 	 * Take i_rwsem and invalidate_lock to avoid racing with set_blocksize
@@ -954,6 +963,19 @@ static int blkdev_mmap_prepare(struct vm_area_desc *desc)
 	return generic_file_mmap_prepare(desc);
 }
 
+static int blkdev_init_dma_buf_io_ctx(struct file *file,
+				      struct dma_buf_io_ctx *ctx)
+{
+	struct block_device *bdev = file_bdev(file);
+	struct gendisk *disk = bdev->bd_disk;
+
+	if (!(file->f_flags & O_DIRECT))
+		return -EINVAL;
+	if (!disk->fops->init_dma_buf_io_ctx)
+		return -EOPNOTSUPP;
+	return disk->fops->init_dma_buf_io_ctx(bdev, ctx);
+}
+
 const struct file_operations def_blk_fops = {
 	.open		= blkdev_open,
 	.release	= blkdev_release,
@@ -972,6 +994,7 @@ const struct file_operations def_blk_fops = {
 	.fallocate	= blkdev_fallocate,
 	.uring_cmd	= blkdev_uring_cmd,
 	.fop_flags	= FOP_BUFFER_RASYNC | FOP_DONTCACHE,
+	.init_dma_buf_io_ctx = blkdev_init_dma_buf_io_ctx,
 };
 
 static __init int blkdev_init(void)
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index d003a9d2d1f6..2d5c30823aab 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1599,6 +1599,8 @@ struct block_device_operations {
 	/* returns the length of the identifier or a negative errno: */
 	int (*get_unique_id)(struct gendisk *disk, u8 id[16],
 			enum blk_unique_id id_type);
+	int (*init_dma_buf_io_ctx)(struct block_device *,
+				   struct dma_buf_io_ctx *);
 	struct module *owner;
 	const struct pr_ops *pr_ops;
 
-- 
2.54.0