2 files changed, 69 insertions, 10 deletions

diff --git a/fs/xfs/libxfs/xfs_exchmaps.c b/fs/xfs/libxfs/xfs_exchmaps.c
index f58240466b1c..7fa244228750 100644
--- a/fs/xfs/libxfs/xfs_exchmaps.c
+++ b/fs/xfs/libxfs/xfs_exchmaps.c
@@ -152,12 +152,7 @@ xfs_exchmaps_check_forks(
 	    ifp2->if_format == XFS_DINODE_FMT_LOCAL)
 		return -EINVAL;
 
-	/* We don't support realtime data forks yet. */
-	if (!XFS_IS_REALTIME_INODE(req->ip1))
-		return 0;
-	if (whichfork == XFS_ATTR_FORK)
-		return 0;
-	return -EINVAL;
+	return 0;
 }
 
 #ifdef CONFIG_XFS_QUOTA
@@ -198,6 +193,8 @@ xfs_exchmaps_can_skip_mapping(
 	struct xfs_exchmaps_intent	*xmi,
 	struct xfs_bmbt_irec		*irec)
 {
+	struct xfs_mount		*mp = xmi->xmi_ip1->i_mount;
+
 	/* Do not skip this mapping if the caller did not tell us to. */
 	if (!(xmi->xmi_flags & XFS_EXCHMAPS_INO1_WRITTEN))
 		return false;
@@ -209,11 +206,64 @@ xfs_exchmaps_can_skip_mapping(
 	/*
 	 * The mapping is unwritten or a hole.  It cannot be a delalloc
 	 * reservation because we already excluded those.  It cannot be an
-	 * unwritten mapping with dirty page cache because we flushed the page
-	 * cache.  We don't support realtime files yet, so we needn't (yet)
-	 * deal with them.
+	 * unwritten extent with dirty page cache because we flushed the page
+	 * cache.  For files where the allocation unit is 1FSB (files on the
+	 * data dev, rt files if the extent size is 1FSB), we can safely
+	 * skip this mapping.
 	 */
-	return true;
+	if (!xfs_inode_has_bigrtalloc(xmi->xmi_ip1))
+		return true;
+
+	/*
+	 * For a realtime file with a multi-fsb allocation unit, the decision
+	 * is trickier because we can only swap full allocation units.
+	 * Unwritten mappings can appear in the middle of an rtx if the rtx is
+	 * partially written, but they can also appear for preallocations.
+	 *
+	 * If the mapping is a hole, skip it entirely.  Holes should align with
+	 * rtx boundaries.
+	 */
+	if (!xfs_bmap_is_real_extent(irec))
+		return true;
+
+	/*
+	 * All mappings below this point are unwritten.
+	 *
+	 * - If the beginning is not aligned to an rtx, trim the end of the
+	 *   mapping so that it does not cross an rtx boundary, and swap it.
+	 *
+	 * - If both ends are aligned to an rtx, skip the entire mapping.
+	 */
+	if (!isaligned_64(irec->br_startoff, mp->m_sb.sb_rextsize)) {
+		xfs_fileoff_t	new_end;
+
+		new_end = roundup_64(irec->br_startoff, mp->m_sb.sb_rextsize);
+		irec->br_blockcount = min(irec->br_blockcount,
+					  new_end - irec->br_startoff);
+		return false;
+	}
+	if (isaligned_64(irec->br_blockcount, mp->m_sb.sb_rextsize))
+		return true;
+
+	/*
+	 * All mappings below this point are unwritten, start on an rtx
+	 * boundary, and do not end on an rtx boundary.
+	 *
+	 * - If the mapping is longer than one rtx, trim the end of the mapping
+	 *   down to an rtx boundary and skip it.
+	 *
+	 * - The mapping is shorter than one rtx.  Swap it.
+	 */
+	if (irec->br_blockcount > mp->m_sb.sb_rextsize) {
+		xfs_fileoff_t	new_end;
+
+		new_end = rounddown_64(irec->br_startoff + irec->br_blockcount,
+				mp->m_sb.sb_rextsize);
+		irec->br_blockcount = new_end - irec->br_startoff;
+		return true;
+	}
+
+	return false;
 }
 
 /*
diff --git a/fs/xfs/xfs_exchrange.c b/fs/xfs/xfs_exchrange.c
index 0fc95e6471cb..90baf12bd97f 100644
--- a/fs/xfs/xfs_exchrange.c
+++ b/fs/xfs/xfs_exchrange.c
@@ -21,6 +21,7 @@
 #include "xfs_sb.h"
 #include "xfs_icache.h"
 #include "xfs_log.h"
+#include "xfs_rtbitmap.h"
 #include <linux/fsnotify.h>
 
 /* Lock (and optionally join) two inodes for a file range exchange. */
@@ -182,6 +183,14 @@ xfs_exchrange_mappings(
 	if (fxr->flags & XFS_EXCHANGE_RANGE_FILE1_WRITTEN)
 		req.flags |= XFS_EXCHMAPS_INO1_WRITTEN;
 
+	/*
+	 * Round the request length up to the nearest file allocation unit.
+	 * The prep function already checked that the request offsets and
+	 * length in @fxr are safe to round up.
+	 */
+	if (xfs_inode_has_bigrtalloc(ip2))
+		req.blockcount = xfs_rtb_roundup_rtx(mp, req.blockcount);
+
 	error = xfs_exchrange_estimate(&req);
 	if (error)
 		return error;