ext2: Move direct-io to use iomap

This patch converts ext2 direct-io path to iomap interface.
- This also takes care of DIO_SKIP_HOLES part in which we return -ENOTBLK
  from ext2_iomap_begin(), in case if the write is done on a hole.
- This fallbacks to buffered-io in case of DIO_SKIP_HOLES or in case of
  a partial write or if any error is detected in ext2_iomap_end().
  We try to return -ENOTBLK in such cases.
- For any unaligned or extending DIO writes, we pass
  IOMAP_DIO_FORCE_WAIT flag to ensure synchronous writes.
- For extending writes we set IOMAP_F_DIRTY in ext2_iomap_begin because
  otherwise with dsync writes on devices that support FUA, generic_write_sync
  won't be called and we might miss inode metadata updates.
- Since ext2 already now uses _nolock vartiant of sync write. Hence
  there is no inode lock problem with iomap in this patch.
- ext2_iomap_ops are now being shared by DIO, DAX & fiemap path

Tested-by: Disha Goel <disgoel@linux.ibm.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Ritesh Harjani (IBM) <ritesh.list@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Message-Id: <610b672a52f2a7ff6dc550fd14d0f995806232a5.1682069716.git.ritesh.list@gmail.com>

1 files changed, 34 insertions, 19 deletions

diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index dc76147e7b07..75983215c7a1 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -56,7 +56,7 @@ static inline int ext2_inode_is_fast_symlink(struct inode *inode)
 
 static void ext2_truncate_blocks(struct inode *inode, loff_t offset);
 
-static void ext2_write_failed(struct address_space *mapping, loff_t to)
+void ext2_write_failed(struct address_space *mapping, loff_t to)
 {
 	struct inode *inode = mapping->host;
 
@@ -809,9 +809,27 @@ static int ext2_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 	bool new = false, boundary = false;
 	u32 bno;
 	int ret;
+	bool create = flags & IOMAP_WRITE;
+
+	/*
+	 * For writes that could fill holes inside i_size on a
+	 * DIO_SKIP_HOLES filesystem we forbid block creations: only
+	 * overwrites are permitted.
+	 */
+	if ((flags & IOMAP_DIRECT) &&
+	    (first_block << blkbits) < i_size_read(inode))
+		create = 0;
+
+	/*
+	 * Writes that span EOF might trigger an IO size update on completion,
+	 * so consider them to be dirty for the purposes of O_DSYNC even if
+	 * there is no other metadata changes pending or have been made here.
+	 */
+	if ((flags & IOMAP_WRITE) && offset + length > i_size_read(inode))
+		iomap->flags |= IOMAP_F_DIRTY;
 
 	ret = ext2_get_blocks(inode, first_block, max_blocks,
-			&bno, &new, &boundary, flags & IOMAP_WRITE);
+			&bno, &new, &boundary, create);
 	if (ret < 0)
 		return ret;
 
@@ -823,6 +841,12 @@ static int ext2_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 		iomap->bdev = inode->i_sb->s_bdev;
 
 	if (ret == 0) {
+		/*
+		 * Switch to buffered-io for writing to holes in a non-extent
+		 * based filesystem to avoid stale data exposure problem.
+		 */
+		if (!create && (flags & IOMAP_WRITE) && (flags & IOMAP_DIRECT))
+			return -ENOTBLK;
 		iomap->type = IOMAP_HOLE;
 		iomap->addr = IOMAP_NULL_ADDR;
 		iomap->length = 1 << blkbits;
@@ -844,6 +868,13 @@ static int
 ext2_iomap_end(struct inode *inode, loff_t offset, loff_t length,
 		ssize_t written, unsigned flags, struct iomap *iomap)
 {
+	/*
+	 * Switch to buffered-io in case of any error.
+	 * Blocks allocated can be used by the buffered-io path.
+	 */
+	if ((flags & IOMAP_DIRECT) && (flags & IOMAP_WRITE) && written == 0)
+		return -ENOTBLK;
+
 	if (iomap->type == IOMAP_MAPPED &&
 	    written < length &&
 	    (flags & IOMAP_WRITE))
@@ -908,22 +939,6 @@ static sector_t ext2_bmap(struct address_space *mapping, sector_t block)
 	return generic_block_bmap(mapping,block,ext2_get_block);
 }
 
-static ssize_t
-ext2_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
-{
-	struct file *file = iocb->ki_filp;
-	struct address_space *mapping = file->f_mapping;
-	struct inode *inode = mapping->host;
-	size_t count = iov_iter_count(iter);
-	loff_t offset = iocb->ki_pos;
-	ssize_t ret;
-
-	ret = blockdev_direct_IO(iocb, inode, iter, ext2_get_block);
-	if (ret < 0 && iov_iter_rw(iter) == WRITE)
-		ext2_write_failed(mapping, offset + count);
-	return ret;
-}
-
 static int
 ext2_writepages(struct address_space *mapping, struct writeback_control *wbc)
 {
@@ -946,7 +961,7 @@ const struct address_space_operations ext2_aops = {
 	.write_begin		= ext2_write_begin,
 	.write_end		= ext2_write_end,
 	.bmap			= ext2_bmap,
-	.direct_IO		= ext2_direct_IO,
+	.direct_IO		= noop_direct_IO,
 	.writepages		= ext2_writepages,
 	.migrate_folio		= buffer_migrate_folio,
 	.is_partially_uptodate	= block_is_partially_uptodate,