iomap: move the iomap_dio_rw ->end_io callback into a structure

Add a new iomap_dio_ops structure that for now just contains the end_io
handler.  This avoid storing the function pointer in a mutable structure,
which is a possible exploit vector for kernel code execution, and prepares
for adding a submit_io handler that btrfs needs.

Signed-off-by: Christoph Hellwig <[email protected]>
Reviewed-by: Darrick J. Wong <[email protected]>
Signed-off-by: Darrick J. Wong <[email protected]>

fs/iomap/direct-io.c

@@ -24,7 +24,7 @@
 
 struct iomap_dio {
 	struct kiocb		*iocb;
-	iomap_dio_end_io_t	*end_io;
+	const struct iomap_dio_ops *dops;
 	loff_t			i_size;
 	loff_t			size;
 	atomic_t		ref;
@@ -72,15 +72,14 @@ static void iomap_dio_submit_bio(struct iomap_dio *dio, struct iomap *iomap,
 
 static ssize_t iomap_dio_complete(struct iomap_dio *dio)
 {
+	const struct iomap_dio_ops *dops = dio->dops;
 	struct kiocb *iocb = dio->iocb;
 	struct inode *inode = file_inode(iocb->ki_filp);
 	loff_t offset = iocb->ki_pos;
-	ssize_t ret;
+	ssize_t ret = dio->error;
 
-	if (dio->end_io)
-		ret = dio->end_io(iocb, dio->size, dio->error, dio->flags);
-	else
-		ret = dio->error;
+	if (dops && dops->end_io)
+		ret = dops->end_io(iocb, dio->size, ret, dio->flags);
 
 	if (likely(!ret)) {
 		ret = dio->size;
@@ -98,9 +97,9 @@ static ssize_t iomap_dio_complete(struct iomap_dio *dio)
 	 * one is a pretty crazy thing to do, so we don't support it 100%.  If
 	 * this invalidation fails, tough, the write still worked...
 	 *
-	 * And this page cache invalidation has to be after dio->end_io(), as
-	 * some filesystems convert unwritten extents to real allocations in
-	 * end_io() when necessary, otherwise a racing buffer read would cache
+	 * And this page cache invalidation has to be after ->end_io(), as some
+	 * filesystems convert unwritten extents to real allocations in
+	 * ->end_io() when necessary, otherwise a racing buffer read would cache
 	 * zeros from unwritten extents.
 	 */
 	if (!dio->error &&
@@ -393,7 +392,7 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
  */
 ssize_t
 iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
-		const struct iomap_ops *ops, iomap_dio_end_io_t end_io)
+		const struct iomap_ops *ops, const struct iomap_dio_ops *dops)
 {
 	struct address_space *mapping = iocb->ki_filp->f_mapping;
 	struct inode *inode = file_inode(iocb->ki_filp);
@@ -418,7 +417,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	atomic_set(&dio->ref, 1);
 	dio->size = 0;
 	dio->i_size = i_size_read(inode);
-	dio->end_io = end_io;
+	dio->dops = dops;
 	dio->error = 0;
 	dio->flags = 0;
 

fs/xfs/xfs_file.c

@@ -442,6 +442,10 @@ xfs_dio_write_end_io(
 	return error;
 }
 
+static const struct iomap_dio_ops xfs_dio_write_ops = {
+	.end_io		= xfs_dio_write_end_io,
+};
+
 /*
  * xfs_file_dio_aio_write - handle direct IO writes
  *
@@ -542,7 +546,7 @@ xfs_file_dio_aio_write(
 	}
 
 	trace_xfs_file_direct_write(ip, count, iocb->ki_pos);
-	ret = iomap_dio_rw(iocb, from, &xfs_iomap_ops, xfs_dio_write_end_io);
+	ret = iomap_dio_rw(iocb, from, &xfs_iomap_ops, &xfs_dio_write_ops);
 
 	/*
 	 * If unaligned, this is the only IO in-flight. If it has not yet

include/linux/iomap.h

@@ -188,10 +188,14 @@ sector_t iomap_bmap(struct address_space *mapping, sector_t bno,
  */
 #define IOMAP_DIO_UNWRITTEN	(1 << 0)	/* covers unwritten extent(s) */
 #define IOMAP_DIO_COW		(1 << 1)	/* covers COW extent(s) */
-typedef int (iomap_dio_end_io_t)(struct kiocb *iocb, ssize_t size, int error,
-				 unsigned int flags);
+
+struct iomap_dio_ops {
+	int (*end_io)(struct kiocb *iocb, ssize_t size, int error,
+		      unsigned flags);
+};
+
 ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
-		const struct iomap_ops *ops, iomap_dio_end_io_t end_io);
+		const struct iomap_ops *ops, const struct iomap_dio_ops *dops);
 int iomap_dio_iopoll(struct kiocb *kiocb, bool spin);
 
 #ifdef CONFIG_SWAP