[RFC 4/4] xfs: support dma-buf registered buffers for direct I/O

[Anuj Gupta <anuj1072538@gmail.com>]

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

Add the init_dma_buf_io_ctx fop for XFS files.
XFS picks the device and calls the iomap layer with
the relevant device.

Refuse the iterator from every CPU-copy path: DAX, buffered
fallback from a -ENOTBLK direct write, and read/writes
without O_DIRECT.

If a file is switched between the data and realtime devices
after registration, the block layer cross-device check refuses
the I/O.

Signed-off-by: Nitesh Shetty <nj.shetty@samsung.com>
---
 fs/xfs/xfs_file.c | 30 ++++++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 426a67b813a7..f97d5acfaf68 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -340,6 +340,11 @@ xfs_file_read_iter(
 	if (xfs_is_shutdown(mp))
 		return -EIO;
 
+	/* a device mapping can only be read by a direct I/O bio */
+	if (iov_iter_is_dmabuf_map(to) &&
+	    (IS_DAX(inode) || !(iocb->ki_flags & IOCB_DIRECT)))
+		return -EOPNOTSUPP;
+
 	if (IS_DAX(inode))
 		ret = xfs_file_dax_read(iocb, to);
 	else if (iocb->ki_flags & IOCB_DIRECT)
@@ -1196,6 +1201,11 @@ xfs_file_write_iter(
 			return ret;
 	}
 
+	/* a device mapping can only be written by a direct I/O bio */
+	if (iov_iter_is_dmabuf_map(from) &&
+	    (IS_DAX(inode) || !(iocb->ki_flags & IOCB_DIRECT)))
+		return -EOPNOTSUPP;
+
 	if (IS_DAX(inode))
 		return xfs_file_dax_write(iocb, from);
 
@@ -1209,6 +1219,9 @@ xfs_file_write_iter(
 		ret = xfs_file_dio_write(iocb, from);
 		if (ret != -ENOTBLK)
 			return ret;
+		/* the page cache cannot copy from a device mapping */
+		if (iov_iter_is_dmabuf_map(from))
+			return -EOPNOTSUPP;
 	}
 
 	if (xfs_is_zoned_inode(ip))
@@ -2173,10 +2186,27 @@ xfs_file_mmap_prepare(
 	return 0;
 }
 
+/*
+ * A realtime file's data lives on the realtime device, anything else on the
+ * data device. If a file is switched between them after registration, the
+ * block layer cross-device check refuses the I/O.
+ */
+static int
+xfs_file_init_dma_buf_io_ctx(
+	struct file		*file,
+	struct dma_buf_io_ctx	*ctx)
+{
+	struct xfs_inode	*ip = XFS_I(file_inode(file));
+
+	return iomap_file_init_dma_buf_io_ctx(file,
+			xfs_inode_buftarg(ip)->bt_bdev, ctx);
+}
+
 const struct file_operations xfs_file_operations = {
 	.llseek		= xfs_file_llseek,
 	.read_iter	= xfs_file_read_iter,
 	.write_iter	= xfs_file_write_iter,
+	.init_dma_buf_io_ctx = xfs_file_init_dma_buf_io_ctx,
 	.splice_read	= xfs_file_splice_read,
 	.splice_write	= iter_file_splice_write,
 	.iopoll		= iocb_bio_iopoll,
-- 
2.43.0