[PATCH 12/14] xfs: support non-power-of-two rtextsize with exchange-range

["Darrick J. Wong" <djwong@kernel.org>]

From: Darrick J. Wong <djwong@kernel.org>

The generic exchange-range alignment checks use (fast) bitmasking
operations to perform block alignment checks on the exchange parameters.
Unfortunately, bitmasks require that the alignment size be a power of
two.  This isn't true for realtime devices with a non-power-of-two
extent size, so we have to copy-pasta the generic checks using long
division for this to work properly.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/xfs_exchrange.c |   89 ++++++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 82 insertions(+), 7 deletions(-)


diff --git a/fs/xfs/xfs_exchrange.c b/fs/xfs/xfs_exchrange.c
index 23e668a192e0d..2d33c7de04f4c 100644
--- a/fs/xfs/xfs_exchrange.c
+++ b/fs/xfs/xfs_exchrange.c
@@ -563,6 +563,75 @@ xfs_exchange_range_finish(
 	return file_remove_privs(fxr->file2);
 }
 
+/*
+ * Check the alignment of an exchange request when the allocation unit size
+ * isn't a power of two.  The generic file-level helpers use (fast)
+ * bitmask-based alignment checks, but here we have to use slow long division.
+ */
+static int
+xfs_exchrange_check_rtalign(
+	const struct xfs_exchrange	*fxr,
+	struct xfs_inode		*ip1,
+	struct xfs_inode		*ip2,
+	unsigned int			alloc_unit)
+{
+	uint64_t			length = fxr->length;
+	uint64_t			blen;
+	loff_t				size1, size2;
+
+	size1 = i_size_read(VFS_I(ip1));
+	size2 = i_size_read(VFS_I(ip2));
+
+	/* The start of both ranges must be aligned to a rt extent. */
+	if (!isaligned_64(fxr->file1_offset, alloc_unit) ||
+	    !isaligned_64(fxr->file2_offset, alloc_unit))
+		return -EINVAL;
+
+	if (fxr->flags & XFS_EXCHANGE_RANGE_TO_EOF)
+		length = max_t(int64_t, size1 - fxr->file1_offset,
+					size2 - fxr->file2_offset);
+
+	/*
+	 * If the user wanted us to exchange up to the infile's EOF, round up
+	 * to the next rt extent boundary for this check.  Do the same for the
+	 * outfile.
+	 *
+	 * Otherwise, reject the range length if it's not rt extent aligned.
+	 * We already confirmed the starting offsets' rt extent block
+	 * alignment.
+	 */
+	if (fxr->file1_offset + length == size1)
+		blen = roundup_64(size1, alloc_unit) - fxr->file1_offset;
+	else if (fxr->file2_offset + length == size2)
+		blen = roundup_64(size2, alloc_unit) - fxr->file2_offset;
+	else if (!isaligned_64(length, alloc_unit))
+		return -EINVAL;
+	else
+		blen = length;
+
+	/* Don't allow overlapped exchanges within the same file. */
+	if (ip1 == ip2 &&
+	    fxr->file2_offset + blen > fxr->file1_offset &&
+	    fxr->file1_offset + blen > fxr->file2_offset)
+		return -EINVAL;
+
+	/*
+	 * Ensure that we don't exchange a partial EOF rt extent into the
+	 * middle of another file.
+	 */
+	if (isaligned_64(length, alloc_unit))
+		return 0;
+
+	blen = length;
+	if (fxr->file2_offset + length < size2)
+		blen = rounddown_64(blen, alloc_unit);
+
+	if (fxr->file1_offset + blen < size1)
+		blen = rounddown_64(blen, alloc_unit);
+
+	return blen == length ? 0 : -EINVAL;
+}
+
 /* Prepare two files to have their data exchanged. */
 STATIC int
 xfs_exchrange_prep(
@@ -570,6 +639,7 @@ xfs_exchrange_prep(
 	struct xfs_inode	*ip1,
 	struct xfs_inode	*ip2)
 {
+	struct xfs_mount	*mp = ip2->i_mount;
 	unsigned int		alloc_unit = xfs_inode_alloc_unitsize(ip2);
 	int			error;
 
@@ -579,13 +649,18 @@ xfs_exchrange_prep(
 	if (XFS_IS_REALTIME_INODE(ip1) != XFS_IS_REALTIME_INODE(ip2))
 		return -EINVAL;
 
-	/*
-	 * The alignment checks in the generic helpers cannot deal with
-	 * allocation units that are not powers of 2.  This can happen with the
-	 * realtime volume if the extent size is set.
-	 */
-	if (!is_power_of_2(alloc_unit))
-		return -EOPNOTSUPP;
+	/* Check non-power of two alignment issues, if necessary. */
+	if (!is_power_of_2(alloc_unit)) {
+		error = xfs_exchrange_check_rtalign(fxr, ip1, ip2, alloc_unit);
+		if (error)
+			return error;
+
+		/*
+		 * Do the generic file-level checks with the regular block
+		 * alignment.
+		 */
+		alloc_unit = mp->m_sb.sb_blocksize;
+	}
 
 	error = xfs_exchange_range_prep(fxr, alloc_unit);
 	if (error || fxr->length == 0)