xfs: detect unwritten bit set in rmapbt node block keysrmap-btree-fix-key-handling-6.4_2023-04-12rmap-btree-fix-key-handling-6.4_2023-04-11

In the last patch, we changed the rmapbt code to remove the UNWRITTEN
bit when creating an rmapbt key from an rmapbt record, and we changed
the rmapbt key comparison code to start considering the ATTR and BMBT
flags during lookup.  This brought the behavior of the rmapbt
implementation in line with its specification.

However, there may exist filesystems that have the unwritten bit still
set in the rmapbt keys.  We should detect these situations and flag the
rmapbt as one that would benefit from optimization.  Eventually, online
repair will be able to do something in response to this.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>

3 files changed, 65 insertions, 0 deletions

diff --git a/fs/xfs/scrub/btree.c b/fs/xfs/scrub/btree.c
index 626282dbe2e3..de4b29ae0839 100644
--- a/fs/xfs/scrub/btree.c
+++ b/fs/xfs/scrub/btree.c
@@ -119,6 +119,16 @@ xchk_btree_xref_set_corrupt(
 			__return_address);
 }
 
+void
+xchk_btree_set_preen(
+	struct xfs_scrub	*sc,
+	struct xfs_btree_cur	*cur,
+	int			level)
+{
+	__xchk_btree_set_corrupt(sc, cur, level, XFS_SCRUB_OFLAG_PREEN,
+			__return_address);
+}
+
 /*
  * Make sure this record is in order and doesn't stray outside of the parent
  * keys.
diff --git a/fs/xfs/scrub/btree.h b/fs/xfs/scrub/btree.h
index 70461885c6c7..639e44e7544f 100644
--- a/fs/xfs/scrub/btree.h
+++ b/fs/xfs/scrub/btree.h
@@ -19,6 +19,8 @@ bool xchk_btree_xref_process_error(struct xfs_scrub *sc,
 /* Check for btree corruption. */
 void xchk_btree_set_corrupt(struct xfs_scrub *sc,
 		struct xfs_btree_cur *cur, int level);
+void xchk_btree_set_preen(struct xfs_scrub *sc, struct xfs_btree_cur *cur,
+		int level);
 
 /* Check for btree xref discrepancies. */
 void xchk_btree_xref_set_corrupt(struct xfs_scrub *sc,
diff --git a/fs/xfs/scrub/rmap.c b/fs/xfs/scrub/rmap.c
index ef6e4b8546a6..8e78e1bc9eef 100644
--- a/fs/xfs/scrub/rmap.c
+++ b/fs/xfs/scrub/rmap.c
@@ -87,6 +87,58 @@ xchk_rmapbt_xref(
 		xchk_rmapbt_xref_refc(sc, irec);
 }
 
+/*
+ * Check for bogus UNWRITTEN flags in the rmapbt node block keys.
+ *
+ * In reverse mapping records, the file mapping extent state
+ * (XFS_RMAP_OFF_UNWRITTEN) is a record attribute, not a key field.  It is not
+ * involved in lookups in any way.  In older kernels, the functions that
+ * convert rmapbt records to keys forgot to filter out the extent state bit,
+ * even though the key comparison functions have filtered the flag correctly.
+ * If we spot an rmap key with the unwritten bit set in rm_offset, we should
+ * mark the btree as needing optimization to rebuild the btree without those
+ * flags.
+ */
+STATIC void
+xchk_rmapbt_check_unwritten_in_keyflags(
+	struct xchk_btree	*bs)
+{
+	struct xfs_scrub	*sc = bs->sc;
+	struct xfs_btree_cur	*cur = bs->cur;
+	struct xfs_btree_block	*keyblock;
+	union xfs_btree_key	*lkey, *hkey;
+	__be64			badflag = cpu_to_be64(XFS_RMAP_OFF_UNWRITTEN);
+	unsigned int		level;
+
+	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_PREEN)
+		return;
+
+	for (level = 1; level < cur->bc_nlevels; level++) {
+		struct xfs_buf	*bp;
+		unsigned int	ptr;
+
+		/* Only check the first time we've seen this node block. */
+		if (cur->bc_levels[level].ptr > 1)
+			continue;
+
+		keyblock = xfs_btree_get_block(cur, level, &bp);
+		for (ptr = 1; ptr <= be16_to_cpu(keyblock->bb_numrecs); ptr++) {
+			lkey = xfs_btree_key_addr(cur, ptr, keyblock);
+
+			if (lkey->rmap.rm_offset & badflag) {
+				xchk_btree_set_preen(sc, cur, level);
+				break;
+			}
+
+			hkey = xfs_btree_high_key_addr(cur, ptr, keyblock);
+			if (hkey->rmap.rm_offset & badflag) {
+				xchk_btree_set_preen(sc, cur, level);
+				break;
+			}
+		}
+	}
+}
+
 /* Scrub an rmapbt record. */
 STATIC int
 xchk_rmapbt_rec(
@@ -101,6 +153,7 @@ xchk_rmapbt_rec(
 		return 0;
 	}
 
+	xchk_rmapbt_check_unwritten_in_keyflags(bs);
 	xchk_rmapbt_xref(bs->sc, &irec);
 	return 0;
 }