[14/27] xfs_repair: flag suspect long-format btree blocks

Commit Message

Darrick J. Wong Feb. 6, 2025, 10:53 p.m. UTC

From: Darrick J. Wong <[e-mail]>

Pass a "suspect" counter through scan_lbtree just like we do for
short-format btree blocks, and increment its value when we encounter
blocks with bad CRCs or outright corruption.  This makes it so that
repair actually catches bmbt blocks with bad crcs or other verifier
errors.

Signed-off-by: "Darrick J. Wong" <[e-mail]>
---
 repair/dinode.c |    2 +-
 repair/scan.c   |   15 ++++++++++++---
 repair/scan.h   |    3 +++
 3 files changed, 16 insertions(+), 4 deletions(-)

Comments

Christoph Hellwig Feb. 7, 2025, 5:21 a.m. UTC | #1

Looks good:

Reviewed-by: Christoph Hellwig <[e-mail]>

Patch

diff --git a/repair/dinode.c b/repair/dinode.c
index 9ab193bc5fe973..4eafb2324909e1 100644
--- a/repair/dinode.c
+++ b/repair/dinode.c
@@ -923,7 +923,7 @@  _("bad bmap btree ptr 0x%" PRIx64 " in ino %" PRIu64 "\n"),
 
 		if (scan_lbtree(get_unaligned_be64(&pp[i]), level, scan_bmapbt,
 				type, whichfork, lino, tot, nex, blkmapp,
-				&cursor, 1, check_dups, magic,
+				&cursor, 0, 1, check_dups, magic,
 				(void *)zap_metadata, &xfs_bmbt_buf_ops))
 			return(1);
 		/*
diff --git a/repair/scan.c b/repair/scan.c
index 88fbda6b83f61a..cd44a9b14f3a1c 100644
--- a/repair/scan.c
+++ b/repair/scan.c
@@ -136,6 +136,7 @@  scan_lbtree(
 				xfs_extnum_t		*nex,
 				blkmap_t		**blkmapp,
 				bmap_cursor_t		*bm_cursor,
+				int			suspect,
 				int			isroot,
 				int			check_dups,
 				int			*dirty,
@@ -148,6 +149,7 @@  scan_lbtree(
 	xfs_extnum_t	*nex,
 	blkmap_t	**blkmapp,
 	bmap_cursor_t	*bm_cursor,
+	int		suspect,
 	int		isroot,
 	int		check_dups,
 	uint64_t	magic,
@@ -167,6 +169,12 @@  scan_lbtree(
 			XFS_FSB_TO_AGBNO(mp, root));
 		return(1);
 	}
+	if (bp->b_error == -EFSBADCRC || bp->b_error == -EFSCORRUPTED) {
+		do_warn(_("btree block %d/%d is suspect, error %d\n"),
+			XFS_FSB_TO_AGNO(mp, root),
+			XFS_FSB_TO_AGBNO(mp, root), bp->b_error);
+		suspect++;
+	}
 
 	/*
 	 * only check for bad CRC here - caller will determine if there
@@ -182,7 +190,7 @@  scan_lbtree(
 
 	err = (*func)(XFS_BUF_TO_BLOCK(bp), nlevels - 1,
 			type, whichfork, root, ino, tot, nex, blkmapp,
-			bm_cursor, isroot, check_dups, &dirty,
+			bm_cursor, suspect, isroot, check_dups, &dirty,
 			magic, priv);
 
 	ASSERT(dirty == 0 || (dirty && !no_modify));
@@ -209,6 +217,7 @@  scan_bmapbt(
 	xfs_extnum_t		*nex,
 	blkmap_t		**blkmapp,
 	bmap_cursor_t		*bm_cursor,
+	int			suspect,
 	int			isroot,
 	int			check_dups,
 	int			*dirty,
@@ -505,7 +514,7 @@  _("bad bmap btree ptr 0x%llx in ino %" PRIu64 "\n"),
 
 		err = scan_lbtree(be64_to_cpu(pp[i]), level, scan_bmapbt,
 				type, whichfork, ino, tot, nex, blkmapp,
-				bm_cursor, 0, check_dups, magic, priv,
+				bm_cursor, suspect, 0, check_dups, magic, priv,
 				&xfs_bmbt_buf_ops);
 		if (err)
 			return(1);
@@ -573,7 +582,7 @@  _("bad fwd (right) sibling pointer (saw %" PRIu64 " should be NULLFSBLOCK)\n"
 				be64_to_cpu(pkey[numrecs - 1].br_startoff);
 	}
 
-	return(0);
+	return suspect > 0 ? 1 : 0;
 }
 
 static void
diff --git a/repair/scan.h b/repair/scan.h
index 4da788becbef66..aeaf9f1a7f4ba9 100644
--- a/repair/scan.h
+++ b/repair/scan.h
@@ -23,6 +23,7 @@  int scan_lbtree(
 				xfs_extnum_t		*nex,
 				struct blkmap		**blkmapp,
 				bmap_cursor_t		*bm_cursor,
+				int			suspect,
 				int			isroot,
 				int			check_dups,
 				int			*dirty,
@@ -35,6 +36,7 @@  int scan_lbtree(
 	xfs_extnum_t	*nex,
 	struct blkmap	**blkmapp,
 	bmap_cursor_t	*bm_cursor,
+	int		suspect,
 	int		isroot,
 	int		check_dups,
 	uint64_t	magic,
@@ -52,6 +54,7 @@  int scan_bmapbt(
 	xfs_extnum_t		*nex,
 	struct blkmap		**blkmapp,
 	bmap_cursor_t		*bm_cursor,
+	int			suspect,
 	int			isroot,
 	int			check_dups,
 	int			*dirty,