[PATCH] Introduce SEEK_DATA/SEEK_HOLE support V8

[Jeff Liu <jeff.liu@oracle.com>]

Hello,

This is the revised patch according to Dave's comments for V7.

Changes to V8:
--------------
1. If there is an internal error raised at extent reading routine, just
return it rather than ENXIO.
2. Add the commit message.
3. Remove the for(;;) loop since there is no continuous holes shown even
if create a Petabyte sparse file with hole extent length longer than
32-bit.  Thanks Dave for helping verify that!
4. In xfs_seek_data(), s/len/end/, looks 'end' is more meaningful here
to indicate the range of extents mapped.
5. Remove BUG() from xfs_seek_data() since xfs_bmapi_read() have found
any corruption during the lookup, it should not occurred at all.

Any comments are appreciated!

Thanks,
-Jeff


Signed-off-by: Jie Liu <jeff.liu@oracle.com>
---
 This patch adds lseek(2) SEEK_DATA/SEEK_HOLE functionality.

 fs/xfs/xfs_file.c |  135
++++++++++++++++++++++++++++++++++++++++++++++++++++-
 1 files changed, 134 insertions(+), 1 deletions(-)

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 753ed9b..1b3021c 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -1141,8 +1141,141 @@ xfs_vm_page_mkwrite(
 	return block_page_mkwrite(vma, vmf, xfs_get_blocks);
 }

+STATIC loff_t
+xfs_seek_data(
+	struct file		*file,
+	loff_t			start,
+	u32			type)
+{
+	struct inode		*inode = file->f_mapping->host;
+	struct xfs_inode	*ip = XFS_I(inode);
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_bmbt_irec	map[2];
+	int			nmap = 2;
+	loff_t			uninitialized_var(offset);
+	xfs_fsize_t		isize;
+	xfs_fileoff_t		fsbno;
+	xfs_filblks_t		end;
+	uint			lock;
+	int			error;
+
+	lock = xfs_ilock_map_shared(ip);
+
+	isize = i_size_read(inode);
+	if (start >= isize) {
+		error = ENXIO;
+		goto out_unlock;
+	}
+
+	fsbno = XFS_B_TO_FSBT(mp, start);
+
+	/*
+	 * Try to read extents from the first block indicated
+	 * by fsbno to the end block of the file.
+	 */
+	end = XFS_B_TO_FSB(mp, isize);
+
+	error = xfs_bmapi_read(ip, fsbno, end - fsbno, map, &nmap,
+			       XFS_BMAPI_ENTIRE);
+	if (error)
+		goto out_unlock;
+
+	/*
+	 * Treat unwritten extent as data extent since it might
+	 * contains dirty data in page cache.
+	 */
+	if (map[0].br_startblock != HOLESTARTBLOCK) {
+		offset = max_t(loff_t, start,
+			       XFS_FSB_TO_B(mp, map[0].br_startoff));
+	} else {
+		if (nmap == 1) {
+			error = ENXIO;
+			goto out_unlock;
+		}
+
+		offset = max_t(loff_t, start,
+			       XFS_FSB_TO_B(mp, map[1].br_startoff));
+	}
+
+	if (offset != file->f_pos)
+		file->f_pos = offset;
+
+out_unlock:
+	xfs_iunlock_map_shared(ip, lock);
+
+	if (error)
+		return -error;
+	return offset;
+}
+
+STATIC loff_t
+xfs_seek_hole(
+	struct file		*file,
+	loff_t			start,
+	u32			type)
+{
+	struct inode		*inode = file->f_mapping->host;
+	struct xfs_inode	*ip = XFS_I(inode);
+	struct xfs_mount	*mp = ip->i_mount;
+	loff_t			uninitialized_var(offset);
+	loff_t			holeoff;
+	xfs_fsize_t		isize;
+	xfs_fileoff_t		fsbno;
+	uint			lock;
+	int			error;
+
+	lock = xfs_ilock_map_shared(ip);
+
+	isize = i_size_read(inode);
+	if (start >= isize) {
+		error = ENXIO;
+		goto out_unlock;
+	}
+
+	fsbno = XFS_B_TO_FSBT(mp, start);
+	error = xfs_bmap_first_unused(NULL, ip, 1, &fsbno, XFS_DATA_FORK);
+	if (error)
+		goto out_unlock;
+
+	holeoff = XFS_FSB_TO_B(mp, fsbno);
+	if (holeoff <= start)
+		offset = start;
+	else
+		offset = min_t(loff_t, holeoff, isize);
+
+	if (offset != file->f_pos)
+		file->f_pos = offset;
+
+out_unlock:
+	xfs_iunlock_map_shared(ip, lock);
+
+	if (error)
+		return -error;
+	return offset;
+}
+
+STATIC loff_t
+xfs_file_llseek(
+	struct file	*file,
+	loff_t		offset,
+	int		origin)
+{
+	switch (origin) {
+	case SEEK_END:
+	case SEEK_CUR:
+	case SEEK_SET:
+		return generic_file_llseek(file, offset, origin);
+	case SEEK_DATA:
+		return xfs_seek_data(file, offset, origin);
+	case SEEK_HOLE:
+		return xfs_seek_hole(file, offset, origin);
+	default:
+		return -EINVAL;
+	}
+}
+
 const struct file_operations xfs_file_operations = {
-	.llseek		= generic_file_llseek,
+	.llseek		= xfs_file_llseek,
 	.read		= do_sync_read,
 	.write		= do_sync_write,
 	.aio_read	= xfs_file_aio_read,
-- 
1.7.9

_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs