[RFC 3/4] iomap: add dma-buf direct I/O guards and registration helper

[Anuj Gupta <anuj1072538@gmail.com>]

From: Nitesh Shetty <nj.shetty@samsung.com>

Direct I/O copies data from the CPU in three places, zero-filling
holes, inline data, and bounce pages. A dma-buf iterator has no
CPU-visible pages, so refuse it.

Reads that encounter a hole or unwritten extent therefore return
-EOPNOTSUPP for the entire operation, even if I/O for an earlier mapped
extent was already submitted.

Also add iomap_file_init_dma_buf_io_ctx(), so filesystems can register
without open-coding the DAX check. The filesystem picks the device,
iomap does the rest.

Signed-off-by: Nitesh Shetty <nj.shetty@samsung.com>
Signed-off-by: Anuj Gupta <anuj20.g@samsung.com>
---
 fs/iomap/direct-io.c  | 31 ++++++++++++++++++++++++++++++-
 include/linux/iomap.h |  3 +++
 2 files changed, 33 insertions(+), 1 deletion(-)

diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index 8b4039d16ce8..fc40f4367ee7 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -427,6 +427,10 @@ static int iomap_dio_bio_iter(struct iomap_iter *iter, struct iomap_dio *dio)
 	unsigned int alignment;
 	ssize_t ret = 0;
 
+	if (iov_iter_is_dmabuf_map(dio->submit.iter) &&
+	    (iomap->flags & IOMAP_F_INTEGRITY))
+		return -EOPNOTSUPP;
+
 	/*
 	 * File systems that write out of place and always allocate new blocks
 	 * need each bio to be block aligned as that's the unit of allocation.
@@ -595,7 +599,13 @@ static int iomap_dio_bio_iter(struct iomap_iter *iter, struct iomap_dio *dio)
 
 static int iomap_dio_hole_iter(struct iomap_iter *iter, struct iomap_dio *dio)
 {
-	loff_t length = iov_iter_zero(iomap_length(iter), dio->submit.iter);
+	loff_t length;
+
+	/* a device mapping cannot be zeroed from the CPU */
+	if (iov_iter_is_dmabuf_map(dio->submit.iter))
+		return -EOPNOTSUPP;
+
+	length = iov_iter_zero(iomap_length(iter), dio->submit.iter);
 
 	dio->size += length;
 	if (!length)
@@ -612,6 +622,10 @@ static int iomap_dio_inline_iter(struct iomap_iter *iomi, struct iomap_dio *dio)
 	loff_t pos = iomi->pos;
 	u64 copied;
 
+	/* inline data is copied from the CPU, which a device mapping bypasses */
+	if (iov_iter_is_dmabuf_map(iter))
+		return -EOPNOTSUPP;
+
 	if (WARN_ON_ONCE(!inline_data))
 		return -EIO;
 
@@ -710,6 +724,10 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	if (!iomi.len)
 		return NULL;
 
+	/* bouncing copies the data from the CPU, which a device mapping bypasses */
+	if (iov_iter_is_dmabuf_map(iter) && (dio_flags & IOMAP_DIO_BOUNCE))
+		return ERR_PTR(-EOPNOTSUPP);
+
 	dio = kmalloc_obj(*dio);
 	if (!dio)
 		return ERR_PTR(-ENOMEM);
@@ -915,6 +933,17 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 }
 EXPORT_SYMBOL_GPL(iomap_dio_rw);
 
+int iomap_file_init_dma_buf_io_ctx(struct file *file, struct block_device *bdev,
+				   struct dma_buf_io_ctx *ctx)
+{
+	struct inode *inode = file_inode(file);
+
+	if (IS_DAX(inode))
+		return -EOPNOTSUPP;
+	return bdev_init_dma_buf_io_ctx(file, bdev, ctx);
+}
+EXPORT_SYMBOL_GPL(iomap_file_init_dma_buf_io_ctx);
+
 struct iomap_dio_simple {
 	struct kiocb		*iocb;
 	size_t			size;
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index bc7ae6327dbf..ce97df81c644 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -682,6 +682,9 @@ struct iomap_dio *__iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 ssize_t iomap_dio_complete(struct iomap_dio *dio);
 void iomap_dio_bio_end_io(struct bio *bio);
 
+int iomap_file_init_dma_buf_io_ctx(struct file *file, struct block_device *bdev,
+				   struct dma_buf_io_ctx *ctx);
+
 /*
  * Fast path for small, block-aligned direct I/Os that map to a single
  * contiguous on-disk extent.
-- 
2.43.0