1 files changed, 36 insertions, 16 deletions

diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index ac2e77ebb54c..fe2e2c930975 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -486,13 +486,11 @@ out_unlock:
 
 /*
  * Test whether it is appropriate to check an inode for and free post EOF
- * blocks. The 'force' parameter determines whether we should also consider
- * regular files that are marked preallocated or append-only.
+ * blocks.
  */
 bool
 xfs_can_free_eofblocks(
-	struct xfs_inode	*ip,
-	bool			force)
+	struct xfs_inode	*ip)
 {
 	struct xfs_bmbt_irec	imap;
 	struct xfs_mount	*mp = ip->i_mount;
@@ -526,11 +524,11 @@ xfs_can_free_eofblocks(
 		return false;
 
 	/*
-	 * Do not free real preallocated or append-only files unless the file
-	 * has delalloc blocks and we are forced to remove them.
+	 * Only free real extents for inodes with persistent preallocations or
+	 * the append-only flag.
 	 */
 	if (ip->i_diflags & (XFS_DIFLAG_PREALLOC | XFS_DIFLAG_APPEND))
-		if (!force || ip->i_delayed_blks == 0)
+		if (ip->i_delayed_blks == 0)
 			return false;
 
 	/*
@@ -584,6 +582,22 @@ xfs_free_eofblocks(
 	/* Wait on dio to ensure i_size has settled. */
 	inode_dio_wait(VFS_I(ip));
 
+	/*
+	 * For preallocated files only free delayed allocations.
+	 *
+	 * Note that this means we also leave speculative preallocations in
+	 * place for preallocated files.
+	 */
+	if (ip->i_diflags & (XFS_DIFLAG_PREALLOC | XFS_DIFLAG_APPEND)) {
+		if (ip->i_delayed_blks) {
+			xfs_bmap_punch_delalloc_range(ip,
+				round_up(XFS_ISIZE(ip), mp->m_sb.sb_blocksize),
+				LLONG_MAX);
+		}
+		xfs_inode_clear_eofblocks_tag(ip);
+		return 0;
+	}
+
 	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp);
 	if (error) {
 		ASSERT(xfs_is_shutdown(mp));
@@ -794,14 +808,18 @@ xfs_flush_unmap_range(
 	xfs_off_t		offset,
 	xfs_off_t		len)
 {
-	struct xfs_mount	*mp = ip->i_mount;
 	struct inode		*inode = VFS_I(ip);
 	xfs_off_t		rounding, start, end;
 	int			error;
 
-	rounding = max_t(xfs_off_t, mp->m_sb.sb_blocksize, PAGE_SIZE);
-	start = round_down(offset, rounding);
-	end = round_up(offset + len, rounding) - 1;
+	/*
+	 * Make sure we extend the flush out to extent alignment
+	 * boundaries so any extent range overlapping the start/end
+	 * of the modification we are about to do is clean and idle.
+	 */
+	rounding = max_t(xfs_off_t, xfs_inode_alloc_unitsize(ip), PAGE_SIZE);
+	start = rounddown_64(offset, rounding);
+	end = roundup_64(offset + len, rounding) - 1;
 
 	error = filemap_write_and_wait_range(inode->i_mapping, start, end);
 	if (error)
@@ -884,14 +902,14 @@ xfs_prepare_shift(
 	struct xfs_inode	*ip,
 	loff_t			offset)
 {
-	struct xfs_mount	*mp = ip->i_mount;
+	unsigned int		rounding;
 	int			error;
 
 	/*
 	 * Trim eofblocks to avoid shifting uninitialized post-eof preallocation
 	 * into the accessible region of the file.
 	 */
-	if (xfs_can_free_eofblocks(ip, true)) {
+	if (xfs_can_free_eofblocks(ip)) {
 		error = xfs_free_eofblocks(ip);
 		if (error)
 			return error;
@@ -902,11 +920,13 @@ xfs_prepare_shift(
 	 * with the full range of the operation. If we don't, a COW writeback
 	 * completion could race with an insert, front merge with the start
 	 * extent (after split) during the shift and corrupt the file. Start
-	 * with the block just prior to the start to stabilize the boundary.
+	 * with the allocation unit just prior to the start to stabilize the
+	 * boundary.
 	 */
-	offset = round_down(offset, mp->m_sb.sb_blocksize);
+	rounding = xfs_inode_alloc_unitsize(ip);
+	offset = rounddown_64(offset, rounding);
 	if (offset)
-		offset -= mp->m_sb.sb_blocksize;
+		offset -= rounding;
 
 	/*
 	 * Writeback and invalidate cache for the remainder of the file as we're