[PATCH v10.1 00/15] xfs: online scrub xref support

[PATCH v10.1 00/15] xfs: online scrub xref support

[Darrick J. Wong]

Hi all,

This is the tenth revision of a patchset that adds to XFS kernel
support for online metadata scrubbing and repair.  There aren't any
on-disk format changes.  The overview of the online scrub functionality
isn't any different than it was with the first kernel series, so I'll
dive into what's in this set.

Today's submission is the third of four parts; it adds to the various
metadata scrubbers the ability to cross-reference other metadata.  If
a given record has a corresponding record somewhere else (e.g. each
inobt record has a corresponding rmapbt record for inodes) or lacks a
corresponding record elsewhere (e.g. each bmbt record does /not/ match
to any bnobt records) then we can be far more certain of the
filesystem's correctness.  We try to augment each scrubber with as many
cross-reference checks as we possibly can, though we are careful to
avoid deadlocks by taking locks in the wrong order.  In particular, we
cannot check rmap records against inode bmbts (we lock inode and then
AG); we must only check inode bmbt records against the rmap.  This means
that the userspace driver program must be careful not to claim that the
scrub is finished unless it has scanned everything.

If you're going to start using this mess, you probably ought to just
pull from my git trees.  The kernel patches[1] should apply against
4.15-rc3.  xfsprogs[2] and xfstests[3] can be found in their usual
places.  The git trees contain all four series' worth of changes.

This is an extraordinary way to eat your data.  Enjoy!
Comments and questions are, as always, welcome.

--D

[1] https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=djwong-devel
[2] https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=djwong-devel
[3] https://git.kernel.org/cgit/linux/kernel/git/djwong/xfstests-dev.git/log/?h=djwong-devel

[PATCH 01/15] xfs: add scrub cross-referencing helpers for the free space btrees

[Darrick J. Wong]

From: Darrick J. Wong <darrick.wong@oracle.com>

Add a couple of functions to the free space btrees that will be used
to cross-reference metadata against the bnobt/cntbt, and a generic
btree function that provides the real implementation.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_alloc.c |   21 ++++++++++++++++++++-
 fs/xfs/libxfs/xfs_alloc.h |   10 ++++++++++
 fs/xfs/libxfs/xfs_btree.c |   29 +++++++++++++++++++++++++++++
 fs/xfs/libxfs/xfs_btree.h |    2 ++
 4 files changed, 61 insertions(+), 1 deletion(-)


diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 83ed771..82333fc 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -167,7 +167,7 @@ xfs_alloc_lookup_ge(
  * Lookup the first record less than or equal to [bno, len]
  * in the btree given by cur.
  */
-static int				/* error */
+int					/* error */
 xfs_alloc_lookup_le(
 	struct xfs_btree_cur	*cur,	/* btree cursor */
 	xfs_agblock_t		bno,	/* starting block of extent */
@@ -2981,3 +2981,22 @@ xfs_verify_fsbno(
 		return false;
 	return xfs_verify_agbno(mp, agno, XFS_FSB_TO_AGBNO(mp, fsbno));
 }
+
+/* Is there a record covering a given extent? */
+int
+xfs_alloc_has_record(
+	struct xfs_btree_cur	*cur,
+	xfs_agblock_t		bno,
+	xfs_extlen_t		len,
+	bool			*exists)
+{
+	union xfs_btree_irec	low;
+	union xfs_btree_irec	high;
+
+	memset(&low, 0, sizeof(low));
+	low.a.ar_startblock = bno;
+	memset(&high, 0xFF, sizeof(high));
+	high.a.ar_startblock = bno + len - 1;
+
+	return xfs_btree_has_record(cur, &low, &high, exists);
+}
diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h
index 7ba2d12..65a0caf 100644
--- a/fs/xfs/libxfs/xfs_alloc.h
+++ b/fs/xfs/libxfs/xfs_alloc.h
@@ -198,6 +198,13 @@ xfs_free_extent(
 	enum xfs_ag_resv_type	type);	/* block reservation type */
 
 int				/* error */
+xfs_alloc_lookup_le(
+	struct xfs_btree_cur	*cur,	/* btree cursor */
+	xfs_agblock_t		bno,	/* starting block of extent */
+	xfs_extlen_t		len,	/* length of extent */
+	int			*stat);	/* success/failure */
+
+int				/* error */
 xfs_alloc_lookup_ge(
 	struct xfs_btree_cur	*cur,	/* btree cursor */
 	xfs_agblock_t		bno,	/* starting block of extent */
@@ -237,4 +244,7 @@ bool xfs_verify_agbno(struct xfs_mount *mp, xfs_agnumber_t agno,
 		xfs_agblock_t agbno);
 bool xfs_verify_fsbno(struct xfs_mount *mp, xfs_fsblock_t fsbno);
 
+int xfs_alloc_has_record(struct xfs_btree_cur *cur, xfs_agblock_t bno,
+		xfs_extlen_t len, bool *exist);
+
 #endif	/* __XFS_ALLOC_H__ */
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index 5f33adf..e0bdff3 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -4953,3 +4953,32 @@ xfs_btree_diff_two_ptrs(
 		return (int64_t)be64_to_cpu(a->l) - be64_to_cpu(b->l);
 	return (int64_t)be32_to_cpu(a->s) - be32_to_cpu(b->s);
 }
+
+/* If there's an extent, we're done. */
+STATIC int
+xfs_btree_has_record_helper(
+	struct xfs_btree_cur		*cur,
+	union xfs_btree_rec		*rec,
+	void				*priv)
+{
+	return XFS_BTREE_QUERY_RANGE_ABORT;
+}
+
+/* Is there a record covering a given range of keys? */
+int
+xfs_btree_has_record(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_irec	*low,
+	union xfs_btree_irec	*high,
+	bool			*exists)
+{
+	int			error;
+
+	error = xfs_btree_query_range(cur, low, high,
+			&xfs_btree_has_record_helper, NULL);
+	if (error && error != XFS_BTREE_QUERY_RANGE_ABORT)
+		return error;
+	*exists = error == XFS_BTREE_QUERY_RANGE_ABORT;
+
+	return 0;
+}
diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h
index b57501c..551a2a0 100644
--- a/fs/xfs/libxfs/xfs_btree.h
+++ b/fs/xfs/libxfs/xfs_btree.h
@@ -545,5 +545,7 @@ void xfs_btree_get_keys(struct xfs_btree_cur *cur,
 		struct xfs_btree_block *block, union xfs_btree_key *key);
 union xfs_btree_key *xfs_btree_high_key_from_key(struct xfs_btree_cur *cur,
 		union xfs_btree_key *key);
+int xfs_btree_has_record(struct xfs_btree_cur *cur, union xfs_btree_irec *low,
+		union xfs_btree_irec *high, bool *exists);
 
 #endif	/* __XFS_BTREE_H__ */

[PATCH 02/15] xfs: add scrub cross-referencing helpers for the inode btrees

[Darrick J. Wong]

From: Darrick J. Wong <darrick.wong@oracle.com>

Add a couple of functions to the inode btrees that will be used
to cross-reference metadata against the inobt.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_ialloc.c |   99 ++++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/libxfs/xfs_ialloc.h |    6 +++
 2 files changed, 105 insertions(+)


diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index de3f04a..72b6b74 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -2755,3 +2755,102 @@ xfs_verify_dir_ino(
 		return false;
 	return xfs_verify_ino(mp, ino);
 }
+
+/* Is there an inode record covering a given range of inode numbers? */
+int
+xfs_ialloc_has_inode_record(
+	struct xfs_btree_cur	*cur,
+	xfs_agino_t		low,
+	xfs_agino_t		high,
+	bool			*exists)
+{
+	struct xfs_inobt_rec_incore	irec;
+	xfs_agino_t		agino;
+	uint16_t		holemask;
+	int			has;
+	int			i;
+	int			error;
+
+	*exists = false;
+	error = xfs_inobt_lookup(cur, low, XFS_LOOKUP_LE, &has);
+	while (error == 0 && has) {
+		error = xfs_inobt_get_rec(cur, &irec, &has);
+		if (error || irec.ir_startino > high)
+			break;
+
+		agino = irec.ir_startino;
+		holemask = irec.ir_holemask;
+		for (i = 0; i < XFS_INOBT_HOLEMASK_BITS; holemask >>= 1,
+				i++, agino += XFS_INODES_PER_HOLEMASK_BIT) {
+			if (holemask & 1)
+				continue;
+			if (agino + XFS_INODES_PER_HOLEMASK_BIT > low &&
+					agino <= high) {
+				*exists = true;
+				goto out;
+			}
+		}
+
+		error = xfs_btree_increment(cur, 0, &has);
+	}
+out:
+	return error;
+}
+
+/* Is there an inode record covering a given extent? */
+int
+xfs_ialloc_has_inodes_at_extent(
+	struct xfs_btree_cur	*cur,
+	xfs_agblock_t		bno,
+	xfs_extlen_t		len,
+	bool			*exists)
+{
+	xfs_agino_t		low;
+	xfs_agino_t		high;
+
+	low = XFS_OFFBNO_TO_AGINO(cur->bc_mp, bno, 0);
+	high = XFS_OFFBNO_TO_AGINO(cur->bc_mp, bno + len, 0) - 1;
+
+	return xfs_ialloc_has_inode_record(cur, low, high, exists);
+}
+
+struct xfs_ialloc_count_inodes {
+	xfs_agino_t			count;
+	xfs_agino_t			freecount;
+};
+
+/* Record inode counts across all inobt records. */
+STATIC int
+xfs_ialloc_count_inodes_helper(
+	struct xfs_btree_cur		*cur,
+	union xfs_btree_rec		*rec,
+	void				*priv)
+{
+	struct xfs_inobt_rec_incore	irec;
+	struct xfs_ialloc_count_inodes	*ci = priv;
+
+	xfs_inobt_btrec_to_irec(cur->bc_mp, rec, &irec);
+	ci->count += irec.ir_count;
+	ci->freecount += irec.ir_freecount;
+
+	return 0;
+}
+
+/* Count allocated and free inodes under an inobt. */
+int
+xfs_ialloc_count_inodes(
+	struct xfs_btree_cur		*cur,
+	xfs_agino_t			*count,
+	xfs_agino_t			*freecount)
+{
+	struct xfs_ialloc_count_inodes	ci = {0};
+	int				error;
+
+	ASSERT(cur->bc_btnum == XFS_BTNUM_INO);
+	error = xfs_btree_query_all(cur, xfs_ialloc_count_inodes_helper, &ci);
+	if (!error) {
+		*count = ci.count;
+		*freecount = ci.freecount;
+	}
+	return error;
+}
diff --git a/fs/xfs/libxfs/xfs_ialloc.h b/fs/xfs/libxfs/xfs_ialloc.h
index d2bdcd5..bf26efb 100644
--- a/fs/xfs/libxfs/xfs_ialloc.h
+++ b/fs/xfs/libxfs/xfs_ialloc.h
@@ -171,6 +171,12 @@ int xfs_read_agi(struct xfs_mount *mp, struct xfs_trans *tp,
 union xfs_btree_rec;
 void xfs_inobt_btrec_to_irec(struct xfs_mount *mp, union xfs_btree_rec *rec,
 		struct xfs_inobt_rec_incore *irec);
+int xfs_ialloc_has_inodes_at_extent(struct xfs_btree_cur *cur,
+		xfs_agblock_t bno, xfs_extlen_t len, bool *exists);
+int xfs_ialloc_has_inode_record(struct xfs_btree_cur *cur, xfs_agino_t low,
+		xfs_agino_t high, bool *exists);
+int xfs_ialloc_count_inodes(struct xfs_btree_cur *cur, xfs_agino_t *count,
+		xfs_agino_t *freecount);
 
 int xfs_ialloc_cluster_alignment(struct xfs_mount *mp);
 void xfs_ialloc_agino_range(struct xfs_mount *mp, xfs_agnumber_t agno,

[PATCH 03/15] xfs: add scrub cross-referencing helpers for the rmap btrees

[Darrick J. Wong]

From: Darrick J. Wong <darrick.wong@oracle.com>

Add a couple of functions to the rmap btrees that will be used
to cross-reference metadata against the rmapbt.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_rmap.c |   58 ++++++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/libxfs/xfs_rmap.h |    5 ++++
 2 files changed, 63 insertions(+)


diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c
index 50db920..ea78ec3 100644
--- a/fs/xfs/libxfs/xfs_rmap.c
+++ b/fs/xfs/libxfs/xfs_rmap.c
@@ -2387,3 +2387,61 @@ xfs_rmap_compare(
 	else
 		return 0;
 }
+
+/* Is there a record covering a given extent? */
+int
+xfs_rmap_has_record(
+	struct xfs_btree_cur	*cur,
+	xfs_agblock_t		bno,
+	xfs_extlen_t		len,
+	bool			*exists)
+{
+	union xfs_btree_irec	low;
+	union xfs_btree_irec	high;
+
+	memset(&low, 0, sizeof(low));
+	low.r.rm_startblock = bno;
+	memset(&high, 0xFF, sizeof(high));
+	high.r.rm_startblock = bno + len - 1;
+
+	return xfs_btree_has_record(cur, &low, &high, exists);
+}
+
+/* Is there a record covering a given extent? */
+int
+xfs_rmap_record_exists(
+	struct xfs_btree_cur	*cur,
+	xfs_agblock_t		bno,
+	xfs_extlen_t		len,
+	struct xfs_owner_info	*oinfo,
+	bool			*has_rmap)
+{
+	uint64_t		owner;
+	uint64_t		offset;
+	unsigned int		flags;
+	int			stat;
+	struct xfs_rmap_irec	irec;
+	int			error;
+
+	xfs_owner_info_unpack(oinfo, &owner, &offset, &flags);
+
+	error = xfs_rmap_lookup_le(cur, bno, len, owner, offset, flags, &stat);
+	if (error)
+		return error;
+	if (!stat) {
+		*has_rmap = false;
+		return 0;
+	}
+
+	error = xfs_rmap_get_rec(cur, &irec, &stat);
+	if (error)
+		return error;
+	if (!stat) {
+		*has_rmap = false;
+		return 0;
+	}
+
+	*has_rmap = (irec.rm_owner == owner && irec.rm_startblock <= bno &&
+		     irec.rm_startblock + irec.rm_blockcount >= bno + len);
+	return 0;
+}
diff --git a/fs/xfs/libxfs/xfs_rmap.h b/fs/xfs/libxfs/xfs_rmap.h
index 0fcd5b1..380e53b 100644
--- a/fs/xfs/libxfs/xfs_rmap.h
+++ b/fs/xfs/libxfs/xfs_rmap.h
@@ -233,5 +233,10 @@ int xfs_rmap_compare(const struct xfs_rmap_irec *a,
 union xfs_btree_rec;
 int xfs_rmap_btrec_to_irec(union xfs_btree_rec *rec,
 		struct xfs_rmap_irec *irec);
+int xfs_rmap_has_record(struct xfs_btree_cur *cur, xfs_agblock_t bno,
+		xfs_extlen_t len, bool *exists);
+int xfs_rmap_record_exists(struct xfs_btree_cur *cur, xfs_agblock_t bno,
+		xfs_extlen_t len, struct xfs_owner_info *oinfo,
+		bool *has_rmap);
 
 #endif	/* __XFS_RMAP_H__ */

[PATCH 04/15] xfs: add scrub cross-referencing helpers for the refcount btrees

[Darrick J. Wong]

From: Darrick J. Wong <darrick.wong@oracle.com>

Add a couple of functions to the refcount btrees that will be used
to cross-reference metadata against the refcountbt.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_refcount.c |   19 +++++++++++++++++++
 fs/xfs/libxfs/xfs_refcount.h |    3 +++
 2 files changed, 22 insertions(+)


diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c
index c40d267..bee68c2 100644
--- a/fs/xfs/libxfs/xfs_refcount.c
+++ b/fs/xfs/libxfs/xfs_refcount.c
@@ -1696,3 +1696,22 @@ xfs_refcount_recover_cow_leftovers(
 	xfs_trans_brelse(tp, agbp);
 	goto out_trans;
 }
+
+/* Is there a record covering a given extent? */
+int
+xfs_refcount_has_record(
+	struct xfs_btree_cur	*cur,
+	xfs_agblock_t		bno,
+	xfs_extlen_t		len,
+	bool			*exists)
+{
+	union xfs_btree_irec	low;
+	union xfs_btree_irec	high;
+
+	memset(&low, 0, sizeof(low));
+	low.rc.rc_startblock = bno;
+	memset(&high, 0xFF, sizeof(high));
+	high.rc.rc_startblock = bno + len - 1;
+
+	return xfs_btree_has_record(cur, &low, &high, exists);
+}
diff --git a/fs/xfs/libxfs/xfs_refcount.h b/fs/xfs/libxfs/xfs_refcount.h
index eafb9d1..2a731ac 100644
--- a/fs/xfs/libxfs/xfs_refcount.h
+++ b/fs/xfs/libxfs/xfs_refcount.h
@@ -83,4 +83,7 @@ static inline xfs_fileoff_t xfs_refcount_max_unmap(int log_res)
 	return (log_res * 3 / 4) / XFS_REFCOUNT_ITEM_OVERHEAD;
 }
 
+extern int xfs_refcount_has_record(struct xfs_btree_cur *cur,
+		xfs_agblock_t bno, xfs_extlen_t len, bool *exists);
+
 #endif	/* __XFS_REFCOUNT_H__ */

[PATCH 05/15] xfs: set up scrub cross-referencing helpers

[Darrick J. Wong]

From: Darrick J. Wong <darrick.wong@oracle.com>

Create some helper functions that we'll use later to deal with problems
we might encounter while cross referencing metadata with other metadata.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/scrub/btree.c  |   69 ++++++++++++++++++++-----
 fs/xfs/scrub/btree.h  |    9 +++
 fs/xfs/scrub/common.c |  138 +++++++++++++++++++++++++++++++++++++++++++++----
 fs/xfs/scrub/common.h |   22 ++++++++
 fs/xfs/scrub/scrub.c  |   10 ++++
 fs/xfs/scrub/trace.h  |   22 ++++++++
 6 files changed, 248 insertions(+), 22 deletions(-)


diff --git a/fs/xfs/scrub/btree.c b/fs/xfs/scrub/btree.c
index df07661..8d48b5b1 100644
--- a/fs/xfs/scrub/btree.c
+++ b/fs/xfs/scrub/btree.c
@@ -42,12 +42,14 @@
  * Check for btree operation errors.  See the section about handling
  * operational errors in common.c.
  */
-bool
-xfs_scrub_btree_process_error(
+static bool
+__xfs_scrub_btree_process_error(
 	struct xfs_scrub_context	*sc,
 	struct xfs_btree_cur		*cur,
 	int				level,
-	int				*error)
+	int				*error,
+	bool				xref,
+	void				*ret_ip)
 {
 	if (*error == 0)
 		return true;
@@ -60,36 +62,78 @@ xfs_scrub_btree_process_error(
 	case -EFSBADCRC:
 	case -EFSCORRUPTED:
 		/* Note the badness but don't abort. */
-		sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
+		sc->sm->sm_flags |= xfs_scrub_corrupt_flag(xref);
 		*error = 0;
 		/* fall through */
 	default:
 		if (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE)
 			trace_xfs_scrub_ifork_btree_op_error(sc, cur, level,
-					*error, __return_address);
+					*error, ret_ip);
 		else
 			trace_xfs_scrub_btree_op_error(sc, cur, level,
-					*error, __return_address);
+					*error, ret_ip);
 		break;
 	}
 	return false;
 }
 
+bool
+xfs_scrub_btree_process_error(
+	struct xfs_scrub_context	*sc,
+	struct xfs_btree_cur		*cur,
+	int				level,
+	int				*error)
+{
+	return __xfs_scrub_btree_process_error(sc, cur, level, error, false,
+			__return_address);
+}
+
+bool
+xfs_scrub_btree_xref_process_error(
+	struct xfs_scrub_context	*sc,
+	struct xfs_btree_cur		*cur,
+	int				level,
+	int				*error)
+{
+	return __xfs_scrub_btree_process_error(sc, cur, level, error, true,
+			__return_address);
+}
+
 /* Record btree block corruption. */
-void
-xfs_scrub_btree_set_corrupt(
+static void
+__xfs_scrub_btree_set_corrupt(
 	struct xfs_scrub_context	*sc,
 	struct xfs_btree_cur		*cur,
-	int				level)
+	int				level,
+	bool				xref,
+	void				*ret_ip)
 {
-	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
+	sc->sm->sm_flags |= xfs_scrub_corrupt_flag(xref);
 
 	if (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE)
 		trace_xfs_scrub_ifork_btree_error(sc, cur, level,
-				__return_address);
+				ret_ip);
 	else
 		trace_xfs_scrub_btree_error(sc, cur, level,
-				__return_address);
+				ret_ip);
+}
+
+void
+xfs_scrub_btree_set_corrupt(
+	struct xfs_scrub_context	*sc,
+	struct xfs_btree_cur		*cur,
+	int				level)
+{
+	__xfs_scrub_btree_set_corrupt(sc, cur, level, false, __return_address);
+}
+
+void
+xfs_scrub_btree_xref_set_corrupt(
+	struct xfs_scrub_context	*sc,
+	struct xfs_btree_cur		*cur,
+	int				level)
+{
+	__xfs_scrub_btree_set_corrupt(sc, cur, level, true, __return_address);
 }
 
 /*
@@ -512,5 +556,6 @@ xfs_scrub_btree(
 	}
 
 out:
+
 	return error;
 }
diff --git a/fs/xfs/scrub/btree.h b/fs/xfs/scrub/btree.h
index 4de825a6..e2b868e 100644
--- a/fs/xfs/scrub/btree.h
+++ b/fs/xfs/scrub/btree.h
@@ -26,10 +26,19 @@
 bool xfs_scrub_btree_process_error(struct xfs_scrub_context *sc,
 		struct xfs_btree_cur *cur, int level, int *error);
 
+/* Check for btree xref operation errors. */
+bool xfs_scrub_btree_xref_process_error(struct xfs_scrub_context *sc,
+				struct xfs_btree_cur *cur, int level,
+				int *error);
+
 /* Check for btree corruption. */
 void xfs_scrub_btree_set_corrupt(struct xfs_scrub_context *sc,
 		struct xfs_btree_cur *cur, int level);
 
+/* Check for btree xref discrepancies. */
+void xfs_scrub_btree_xref_set_corrupt(struct xfs_scrub_context *sc,
+		struct xfs_btree_cur *cur, int level);
+
 struct xfs_scrub_btree;
 typedef int (*xfs_scrub_btree_rec_fn)(
 	struct xfs_scrub_btree	*bs,
diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c
index 98452ad..effdcfa 100644
--- a/fs/xfs/scrub/common.c
+++ b/fs/xfs/scrub/common.c
@@ -78,12 +78,14 @@
  */
 
 /* Check for operational errors. */
-bool
-xfs_scrub_process_error(
+static bool
+__xfs_scrub_process_error(
 	struct xfs_scrub_context	*sc,
 	xfs_agnumber_t			agno,
 	xfs_agblock_t			bno,
-	int				*error)
+	int				*error,
+	bool				xref,
+	void				*ret_ip)
 {
 	switch (*error) {
 	case 0:
@@ -95,24 +97,48 @@ xfs_scrub_process_error(
 	case -EFSBADCRC:
 	case -EFSCORRUPTED:
 		/* Note the badness but don't abort. */
-		sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
+		sc->sm->sm_flags |= xfs_scrub_corrupt_flag(xref);
 		*error = 0;
 		/* fall through */
 	default:
 		trace_xfs_scrub_op_error(sc, agno, bno, *error,
-				__return_address);
+				ret_ip);
 		break;
 	}
 	return false;
 }
 
-/* Check for operational errors for a file offset. */
 bool
-xfs_scrub_fblock_process_error(
+xfs_scrub_process_error(
+	struct xfs_scrub_context	*sc,
+	xfs_agnumber_t			agno,
+	xfs_agblock_t			bno,
+	int				*error)
+{
+	return __xfs_scrub_process_error(sc, agno, bno, error, false,
+			__return_address);
+}
+
+bool
+xfs_scrub_xref_process_error(
+	struct xfs_scrub_context	*sc,
+	xfs_agnumber_t			agno,
+	xfs_agblock_t			bno,
+	int				*error)
+{
+	return __xfs_scrub_process_error(sc, agno, bno, error, true,
+			__return_address);
+}
+
+/* Check for operational errors for a file offset. */
+static bool
+__xfs_scrub_fblock_process_error(
 	struct xfs_scrub_context	*sc,
 	int				whichfork,
 	xfs_fileoff_t			offset,
-	int				*error)
+	int				*error,
+	bool				xref,
+	void				*ret_ip)
 {
 	switch (*error) {
 	case 0:
@@ -124,17 +150,39 @@ xfs_scrub_fblock_process_error(
 	case -EFSBADCRC:
 	case -EFSCORRUPTED:
 		/* Note the badness but don't abort. */
-		sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
+		sc->sm->sm_flags |= xfs_scrub_corrupt_flag(xref);
 		*error = 0;
 		/* fall through */
 	default:
 		trace_xfs_scrub_file_op_error(sc, whichfork, offset, *error,
-				__return_address);
+				ret_ip);
 		break;
 	}
 	return false;
 }
 
+bool
+xfs_scrub_fblock_process_error(
+	struct xfs_scrub_context	*sc,
+	int				whichfork,
+	xfs_fileoff_t			offset,
+	int				*error)
+{
+	return __xfs_scrub_fblock_process_error(sc, whichfork, offset, error,
+			false, __return_address);
+}
+
+bool
+xfs_scrub_fblock_xref_process_error(
+	struct xfs_scrub_context	*sc,
+	int				whichfork,
+	xfs_fileoff_t			offset,
+	int				*error)
+{
+	return __xfs_scrub_fblock_process_error(sc, whichfork, offset, error,
+			true, __return_address);
+}
+
 /*
  * Handling scrub corruption/optimization/warning checks.
  *
@@ -183,6 +231,16 @@ xfs_scrub_block_set_corrupt(
 	trace_xfs_scrub_block_error(sc, bp->b_bn, __return_address);
 }
 
+/* Record a corruption while cross-referencing. */
+void
+xfs_scrub_block_xref_set_corrupt(
+	struct xfs_scrub_context	*sc,
+	struct xfs_buf			*bp)
+{
+	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_XCORRUPT;
+	trace_xfs_scrub_block_error(sc, bp->b_bn, __return_address);
+}
+
 /*
  * Record a corrupt inode.  The trace data will include the block given
  * by bp if bp is given; otherwise it will use the block location of the
@@ -198,6 +256,17 @@ xfs_scrub_ino_set_corrupt(
 	trace_xfs_scrub_ino_error(sc, ino, bp ? bp->b_bn : 0, __return_address);
 }
 
+/* Record a corruption while cross-referencing with an inode. */
+void
+xfs_scrub_ino_xref_set_corrupt(
+	struct xfs_scrub_context	*sc,
+	xfs_ino_t			ino,
+	struct xfs_buf			*bp)
+{
+	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_XCORRUPT;
+	trace_xfs_scrub_ino_error(sc, ino, bp ? bp->b_bn : 0, __return_address);
+}
+
 /* Record corruption in a block indexed by a file fork. */
 void
 xfs_scrub_fblock_set_corrupt(
@@ -209,6 +278,17 @@ xfs_scrub_fblock_set_corrupt(
 	trace_xfs_scrub_fblock_error(sc, whichfork, offset, __return_address);
 }
 
+/* Record a corruption while cross-referencing a fork block. */
+void
+xfs_scrub_fblock_xref_set_corrupt(
+	struct xfs_scrub_context	*sc,
+	int				whichfork,
+	xfs_fileoff_t			offset)
+{
+	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_XCORRUPT;
+	trace_xfs_scrub_fblock_error(sc, whichfork, offset, __return_address);
+}
+
 /*
  * Warn about inodes that need administrative review but is not
  * incorrect.
@@ -564,3 +644,41 @@ xfs_scrub_setup_inode_contents(
 	/* scrub teardown will unlock and release the inode for us */
 	return error;
 }
+
+/*
+ * Predicate that decides if we need to evaluate the cross-reference check.
+ * If there was an error accessing the cross-reference btree, just delete
+ * the cursor and skip the check.
+ */
+bool
+xfs_scrub_should_xref(
+	struct xfs_scrub_context	*sc,
+	int				*error,
+	struct xfs_btree_cur		**curpp)
+{
+	/* If not a btree cross-reference, just check the error code. */
+	if (curpp == NULL) {
+		if (*error == 0)
+			return true;
+		goto fail;
+	}
+
+	ASSERT(*curpp != NULL);
+	/* If no error or we've already given up on xref, just bail out. */
+	if (*error == 0 || *curpp == NULL)
+		return true;
+
+	/* xref error, delete cursor and bail out. */
+	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_XFAIL;
+	xfs_btree_del_cursor(*curpp, XFS_BTREE_ERROR);
+	*curpp = NULL;
+fail:
+	trace_xfs_scrub_xref_error(sc, *error, __return_address);
+
+	/*
+	 * Errors encountered during cross-referencing with another
+	 * data structure should not cause this scrubber to abort.
+	 */
+	*error = 0;
+	return false;
+}
diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h
index fe12053..0e12a10 100644
--- a/fs/xfs/scrub/common.h
+++ b/fs/xfs/scrub/common.h
@@ -56,6 +56,11 @@ bool xfs_scrub_process_error(struct xfs_scrub_context *sc, xfs_agnumber_t agno,
 bool xfs_scrub_fblock_process_error(struct xfs_scrub_context *sc, int whichfork,
 		xfs_fileoff_t offset, int *error);
 
+bool xfs_scrub_xref_process_error(struct xfs_scrub_context *sc,
+		xfs_agnumber_t agno, xfs_agblock_t bno, int *error);
+bool xfs_scrub_fblock_xref_process_error(struct xfs_scrub_context *sc,
+		int whichfork, xfs_fileoff_t offset, int *error);
+
 void xfs_scrub_block_set_preen(struct xfs_scrub_context *sc,
 		struct xfs_buf *bp);
 void xfs_scrub_ino_set_preen(struct xfs_scrub_context *sc, xfs_ino_t ino,
@@ -68,6 +73,13 @@ void xfs_scrub_ino_set_corrupt(struct xfs_scrub_context *sc, xfs_ino_t ino,
 void xfs_scrub_fblock_set_corrupt(struct xfs_scrub_context *sc, int whichfork,
 		xfs_fileoff_t offset);
 
+void xfs_scrub_block_xref_set_corrupt(struct xfs_scrub_context *sc,
+		struct xfs_buf *bp);
+void xfs_scrub_ino_xref_set_corrupt(struct xfs_scrub_context *sc, xfs_ino_t ino,
+		struct xfs_buf *bp);
+void xfs_scrub_fblock_xref_set_corrupt(struct xfs_scrub_context *sc,
+		int whichfork, xfs_fileoff_t offset);
+
 void xfs_scrub_ino_set_warning(struct xfs_scrub_context *sc, xfs_ino_t ino,
 		struct xfs_buf *bp);
 void xfs_scrub_fblock_set_warning(struct xfs_scrub_context *sc, int whichfork,
@@ -76,6 +88,10 @@ void xfs_scrub_fblock_set_warning(struct xfs_scrub_context *sc, int whichfork,
 void xfs_scrub_set_incomplete(struct xfs_scrub_context *sc);
 int xfs_scrub_checkpoint_log(struct xfs_mount *mp);
 
+/* Are we set up for a cross-referencing operation? */
+bool xfs_scrub_should_xref(struct xfs_scrub_context *sc, int *error,
+			   struct xfs_btree_cur **curpp);
+
 /* Setup functions */
 int xfs_scrub_setup_fs(struct xfs_scrub_context *sc, struct xfs_inode *ip);
 int xfs_scrub_setup_ag_allocbt(struct xfs_scrub_context *sc,
@@ -139,4 +155,10 @@ int xfs_scrub_get_inode(struct xfs_scrub_context *sc, struct xfs_inode *ip_in);
 int xfs_scrub_setup_inode_contents(struct xfs_scrub_context *sc,
 				   struct xfs_inode *ip, unsigned int resblks);
 
+/* Figure out the correct corruption flag for whatever's wrong. */
+static inline __u32 xfs_scrub_corrupt_flag(bool xref)
+{
+	return xref ? XFS_SCRUB_OFLAG_XCORRUPT : XFS_SCRUB_OFLAG_CORRUPT;
+}
+
 #endif	/* __XFS_SCRUB_COMMON_H__ */
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index b98084d..93cbe5f 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -111,6 +111,16 @@
  * structure itself is corrupt, the CORRUPT flag will be set.  If
  * the metadata is correct but otherwise suboptimal, the PREEN flag
  * will be set.
+ *
+ * We perform secondary validation of filesystem metadata by
+ * cross-referencing every record with all other available metadata.
+ * For example, for block mapping extents, we verify that there are no
+ * records in the free space and inode btrees corresponding to that
+ * space extent and that there is a corresponding entry in the reverse
+ * mapping btree.  Inconsistent metadata is noted by setting the
+ * XCORRUPT flag; btree query function errors are noted by setting the
+ * XFAIL flag and deleting the cursor to prevent further attempts to
+ * cross-reference with a defective btree.
  */
 
 /*
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index c4ebfb5..81becf6 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -491,6 +491,28 @@ DEFINE_EVENT(xfs_scrub_sbtree_class, name, \
 DEFINE_SCRUB_SBTREE_EVENT(xfs_scrub_btree_rec);
 DEFINE_SCRUB_SBTREE_EVENT(xfs_scrub_btree_key);
 
+TRACE_EVENT(xfs_scrub_xref_error,
+	TP_PROTO(struct xfs_scrub_context *sc, int error, void *ret_ip),
+	TP_ARGS(sc, error, ret_ip),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(int, type)
+		__field(int, error)
+		__field(void *, ret_ip)
+	),
+	TP_fast_assign(
+		__entry->dev = sc->mp->m_super->s_dev;
+		__entry->type = sc->sm->sm_type;
+		__entry->error = error;
+		__entry->ret_ip = ret_ip;
+	),
+	TP_printk("dev %d:%d type %u xref error %d ret_ip %pF",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->type,
+		  __entry->error,
+		  __entry->ret_ip)
+);
+
 #endif /* _TRACE_XFS_SCRUB_TRACE_H */
 
 #undef TRACE_INCLUDE_PATH

[PATCH 06/15] xfs: check btree block ownership with bnobt/rmapbt when scrubbing btree

[Darrick J. Wong]

From: Darrick J. Wong <darrick.wong@oracle.com>

When scanning a metadata btree block, cross-reference the block location
with the free space btree and the reverse mapping btree to ensure that
the rmapbt knows about the block and the bnobt does not.  Add a
mechanism to defer checks when we happen to be scanning the bnobt/rmapbt
itself because it's less efficient to repeatedly clone and destroy the
cursor.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/scrub/btree.c |   92 ++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 92 insertions(+)


diff --git a/fs/xfs/scrub/btree.c b/fs/xfs/scrub/btree.c
index 8d48b5b1..40fc26f 100644
--- a/fs/xfs/scrub/btree.c
+++ b/fs/xfs/scrub/btree.c
@@ -359,6 +359,80 @@ xfs_scrub_btree_block_check_siblings(
 	return error;
 }
 
+struct check_owner {
+	struct list_head	list;
+	xfs_daddr_t		daddr;
+	int			level;
+};
+
+/*
+ * Make sure this btree block isn't in the free list and that there's
+ * an rmap record for it.
+ */
+STATIC int
+xfs_scrub_btree_check_block_owner(
+	struct xfs_scrub_btree		*bs,
+	int				level,
+	xfs_daddr_t			daddr)
+{
+	struct xfs_scrub_ag		sa = { 0 };
+	struct xfs_scrub_ag		*psa;
+	xfs_agnumber_t			agno;
+	int				error = 0;
+
+	agno = xfs_daddr_to_agno(bs->cur->bc_mp, daddr);
+
+	if (bs->cur->bc_flags & XFS_BTREE_LONG_PTRS) {
+		error = xfs_scrub_ag_init(bs->sc, agno, &sa);
+		if (!xfs_scrub_btree_xref_process_error(bs->sc, bs->cur,
+				level, &error))
+			return error;
+		psa = &sa;
+	} else {
+		psa = &bs->sc->sa;
+	}
+
+	if (psa == &sa)
+		xfs_scrub_ag_free(bs->sc, &sa);
+
+	return error;
+}
+
+/* Check the owner of a btree block. */
+STATIC int
+xfs_scrub_btree_check_owner(
+	struct xfs_scrub_btree		*bs,
+	int				level,
+	struct xfs_buf			*bp)
+{
+	struct xfs_btree_cur		*cur = bs->cur;
+	struct check_owner		*co;
+
+	if ((cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) && bp == NULL)
+		return 0;
+
+	/*
+	 * We want to cross-reference each btree block with the bnobt
+	 * and the rmapbt.  We cannot cross-reference the bnobt or
+	 * rmapbt while scanning the bnobt or rmapbt, respectively,
+	 * because we cannot alter the cursor and we'd prefer not to
+	 * duplicate cursors.  Therefore, save the buffer daddr for
+	 * later scanning.
+	 */
+	if (cur->bc_btnum == XFS_BTNUM_BNO || cur->bc_btnum == XFS_BTNUM_RMAP) {
+		co = kmem_alloc(sizeof(struct check_owner),
+				KM_MAYFAIL | KM_NOFS);
+		if (!co)
+			return -ENOMEM;
+		co->level = level;
+		co->daddr = XFS_BUF_ADDR(bp);
+		list_add_tail(&co->list, &bs->to_check);
+		return 0;
+	}
+
+	return xfs_scrub_btree_check_block_owner(bs, level, XFS_BUF_ADDR(bp));
+}
+
 /*
  * Grab and scrub a btree block given a btree pointer.  Returns block
  * and buffer pointers (if applicable) if they're ok to use.
@@ -395,6 +469,14 @@ xfs_scrub_btree_get_block(
 	}
 
 	/*
+	 * Check the block's owner; this function absorbs error codes
+	 * for us.
+	 */
+	error = xfs_scrub_btree_check_owner(bs, level, *pbp);
+	if (error)
+		return error;
+
+	/*
 	 * Check the block's siblings; this function absorbs error codes
 	 * for us.
 	 */
@@ -465,6 +547,8 @@ xfs_scrub_btree(
 	struct xfs_btree_block		*block;
 	int				level;
 	struct xfs_buf			*bp;
+	struct check_owner		*co;
+	struct check_owner		*n;
 	int				i;
 	int				error = 0;
 
@@ -556,6 +640,14 @@ xfs_scrub_btree(
 	}
 
 out:
+	/* Process deferred owner checks on btree blocks. */
+	list_for_each_entry_safe(co, n, &bs.to_check, list) {
+		if (!error)
+			error = xfs_scrub_btree_check_block_owner(&bs,
+					co->level, co->daddr);
+		list_del(&co->list);
+		kmem_free(co);
+	}
 
 	return error;
 }

[PATCH 07/15] xfs: introduce scrubber cross-referencing stubs

[Darrick J. Wong]

From: Darrick J. Wong <darrick.wong@oracle.com>

Create some stubs that will be used to cross-reference metadata records.
The actual cross-referencing will be filled in by subsequent patches.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/scrub/agheader.c |   65 ++++++++++++++++++++++++++++++++++++++++++++++-
 fs/xfs/scrub/alloc.c    |   14 ++++++++++
 fs/xfs/scrub/bmap.c     |   28 ++++++++++++++++++++
 fs/xfs/scrub/ialloc.c   |   17 ++++++++++++
 fs/xfs/scrub/inode.c    |   13 +++++++++
 fs/xfs/scrub/refcount.c |   15 +++++++++++
 fs/xfs/scrub/rmap.c     |   13 +++++++++
 7 files changed, 163 insertions(+), 2 deletions(-)


diff --git a/fs/xfs/scrub/agheader.c b/fs/xfs/scrub/agheader.c
index b599358..b4297e9 100644
--- a/fs/xfs/scrub/agheader.c
+++ b/fs/xfs/scrub/agheader.c
@@ -37,7 +37,10 @@
 #include "scrub/common.h"
 #include "scrub/trace.h"
 
-/* Walk all the blocks in the AGFL. */
+/*
+ * Walk all the blocks in the AGFL.  The fn function can return any negative
+ * error code or XFS_BTREE_QUERY_RANGE_ABORT.
+ */
 int
 xfs_scrub_walk_agfl(
 	struct xfs_scrub_context	*sc,
@@ -98,6 +101,14 @@ xfs_scrub_walk_agfl(
 
 /* Superblock */
 
+/* Cross-reference with the other btrees. */
+STATIC void
+xfs_scrub_superblock_xref(
+	struct xfs_scrub_context	*sc,
+	struct xfs_buf			*bp)
+{
+}
+
 /*
  * Scrub the filesystem superblock.
  *
@@ -370,11 +381,23 @@ xfs_scrub_superblock(
 			BBTOB(bp->b_length) - sizeof(struct xfs_dsb)))
 		xfs_scrub_block_set_corrupt(sc, bp);
 
+	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+		goto out;
+
+	xfs_scrub_superblock_xref(sc, bp);
+out:
 	return error;
 }
 
 /* AGF */
 
+/* Cross-reference with the other btrees. */
+STATIC void
+xfs_scrub_agf_xref(
+	struct xfs_scrub_context	*sc)
+{
+}
+
 /* Scrub the AGF. */
 int
 xfs_scrub_agf(
@@ -453,6 +476,10 @@ xfs_scrub_agf(
 	if (agfl_count != 0 && fl_count != agfl_count)
 		xfs_scrub_block_set_corrupt(sc, sc->sa.agf_bp);
 
+	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+		goto out;
+
+	xfs_scrub_agf_xref(sc);
 out:
 	return error;
 }
@@ -465,6 +492,14 @@ struct xfs_scrub_agfl_info {
 	xfs_agblock_t			*entries;
 };
 
+/* Cross-reference with the other btrees. */
+STATIC void
+xfs_scrub_agfl_block_xref(
+	struct xfs_scrub_context	*sc,
+	xfs_agblock_t			bno)
+{
+}
+
 /* Scrub an AGFL block. */
 STATIC int
 xfs_scrub_agfl_block(
@@ -482,6 +517,11 @@ xfs_scrub_agfl_block(
 	else
 		xfs_scrub_block_set_corrupt(sc, sc->sa.agfl_bp);
 
+	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+		goto out;
+
+	xfs_scrub_agfl_block_xref(sc, agbno);
+out:
 	return 0;
 }
 
@@ -496,6 +536,13 @@ xfs_scrub_agblock_cmp(
 	return (int)*a - (int)*b;
 }
 
+/* Cross-reference with the other btrees. */
+STATIC void
+xfs_scrub_agfl_xref(
+	struct xfs_scrub_context	*sc)
+{
+}
+
 /* Scrub the AGFL. */
 int
 xfs_scrub_agfl(
@@ -516,6 +563,11 @@ xfs_scrub_agfl(
 	if (!sc->sa.agf_bp)
 		return -EFSCORRUPTED;
 
+	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+		goto out;
+
+	xfs_scrub_agfl_xref(sc);
+
 	/* Allocate buffer to ensure uniqueness of AGFL entries. */
 	agf = XFS_BUF_TO_AGF(sc->sa.agf_bp);
 	agflcount = be32_to_cpu(agf->agf_flcount);
@@ -558,6 +610,13 @@ xfs_scrub_agfl(
 
 /* AGI */
 
+/* Cross-reference with the other btrees. */
+STATIC void
+xfs_scrub_agi_xref(
+	struct xfs_scrub_context	*sc)
+{
+}
+
 /* Scrub the AGI. */
 int
 xfs_scrub_agi(
@@ -636,6 +695,10 @@ xfs_scrub_agi(
 	if (agi->agi_pad32 != cpu_to_be32(0))
 		xfs_scrub_block_set_corrupt(sc, sc->sa.agi_bp);
 
+	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+		goto out;
+
+	xfs_scrub_agi_xref(sc);
 out:
 	return error;
 }
diff --git a/fs/xfs/scrub/alloc.c b/fs/xfs/scrub/alloc.c
index 059663e..0d95b84 100644
--- a/fs/xfs/scrub/alloc.c
+++ b/fs/xfs/scrub/alloc.c
@@ -50,6 +50,15 @@ xfs_scrub_setup_ag_allocbt(
 
 /* Free space btree scrubber. */
 
+/* Cross-reference with the other btrees. */
+STATIC void
+xfs_scrub_allocbt_xref(
+	struct xfs_scrub_context	*sc,
+	xfs_agblock_t			bno,
+	xfs_extlen_t			len)
+{
+}
+
 /* Scrub a bnobt/cntbt record. */
 STATIC int
 xfs_scrub_allocbt_rec(
@@ -70,6 +79,11 @@ xfs_scrub_allocbt_rec(
 	    !xfs_verify_agbno(mp, agno, bno + len - 1))
 		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
 
+	if (bs->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+		goto out;
+
+	xfs_scrub_allocbt_xref(bs->sc, bno, len);
+out:
 	return error;
 }
 
diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c
index 42fec0b..684f08b 100644
--- a/fs/xfs/scrub/bmap.c
+++ b/fs/xfs/scrub/bmap.c
@@ -99,6 +99,26 @@ struct xfs_scrub_bmap_info {
 	int				whichfork;
 };
 
+/* Cross-reference a single rtdev extent record. */
+STATIC void
+xfs_scrub_bmap_rt_extent_xref(
+	struct xfs_scrub_bmap_info	*info,
+	struct xfs_inode		*ip,
+	struct xfs_btree_cur		*cur,
+	struct xfs_bmbt_irec		*irec)
+{
+}
+
+/* Cross-reference a single datadev extent record. */
+STATIC void
+xfs_scrub_bmap_extent_xref(
+	struct xfs_scrub_bmap_info	*info,
+	struct xfs_inode		*ip,
+	struct xfs_btree_cur		*cur,
+	struct xfs_bmbt_irec		*irec)
+{
+}
+
 /* Scrub a single extent record. */
 STATIC int
 xfs_scrub_bmap_extent(
@@ -158,6 +178,14 @@ xfs_scrub_bmap_extent(
 		xfs_scrub_fblock_set_corrupt(info->sc, info->whichfork,
 				irec->br_startoff);
 
+	if (info->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+		goto out;
+
+	if (info->is_rt)
+		xfs_scrub_bmap_rt_extent_xref(info, ip, cur, irec);
+	else
+		xfs_scrub_bmap_extent_xref(info, ip, cur, irec);
+out:
 	info->lastoff = irec->br_startoff + irec->br_blockcount;
 	return error;
 }
diff --git a/fs/xfs/scrub/ialloc.c b/fs/xfs/scrub/ialloc.c
index 496d6f2..599d62a 100644
--- a/fs/xfs/scrub/ialloc.c
+++ b/fs/xfs/scrub/ialloc.c
@@ -58,6 +58,17 @@ xfs_scrub_setup_ag_iallocbt(
 
 /* Inode btree scrubber. */
 
+/* Cross-reference with the other btrees. */
+STATIC void
+xfs_scrub_iallocbt_chunk_xref(
+	struct xfs_scrub_context	*sc,
+	struct xfs_inobt_rec_incore	*irec,
+	xfs_agino_t			agino,
+	xfs_agblock_t			bno,
+	xfs_extlen_t			len)
+{
+}
+
 /* Is this chunk worth checking? */
 STATIC bool
 xfs_scrub_iallocbt_chunk(
@@ -76,6 +87,11 @@ xfs_scrub_iallocbt_chunk(
 	    !xfs_verify_agbno(mp, agno, bno + len - 1))
 		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
 
+	if (bs->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+		goto out;
+
+	xfs_scrub_iallocbt_chunk_xref(bs->sc, irec, agino, bno, len);
+out:
 	return true;
 }
 
@@ -303,7 +319,6 @@ xfs_scrub_iallocbt_rec(
 	error = xfs_scrub_iallocbt_check_freemask(bs, &irec);
 	if (error)
 		goto out;
-
 out:
 	return error;
 }
diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c
index 2be4b25..e31d981 100644
--- a/fs/xfs/scrub/inode.c
+++ b/fs/xfs/scrub/inode.c
@@ -577,6 +577,15 @@ xfs_scrub_inode_map_raw(
 	return error;
 }
 
+/* Cross-reference with the other btrees. */
+STATIC void
+xfs_scrub_inode_xref(
+	struct xfs_scrub_context	*sc,
+	xfs_ino_t			ino,
+	struct xfs_dinode		*dip)
+{
+}
+
 /* Scrub an inode. */
 int
 xfs_scrub_inode(
@@ -626,6 +635,10 @@ xfs_scrub_inode(
 			xfs_scrub_ino_set_preen(sc, ino, bp);
 	}
 
+	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+		goto out;
+
+	xfs_scrub_inode_xref(sc, ino, dip);
 out:
 	if (bp)
 		xfs_trans_brelse(sc->tp, bp);
diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c
index 2f88a8d..5a3aa9b 100644
--- a/fs/xfs/scrub/refcount.c
+++ b/fs/xfs/scrub/refcount.c
@@ -50,6 +50,16 @@ xfs_scrub_setup_ag_refcountbt(
 
 /* Reference count btree scrubber. */
 
+/* Cross-reference with the other btrees. */
+STATIC void
+xfs_scrub_refcountbt_xref(
+	struct xfs_scrub_context	*sc,
+	xfs_agblock_t			bno,
+	xfs_extlen_t			len,
+	xfs_nlink_t			refcount)
+{
+}
+
 /* Scrub a refcountbt record. */
 STATIC int
 xfs_scrub_refcountbt_rec(
@@ -83,6 +93,11 @@ xfs_scrub_refcountbt_rec(
 	if (refcount == 0)
 		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
 
+	if (bs->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+		goto out;
+
+	xfs_scrub_refcountbt_xref(bs->sc, bno, len, refcount);
+out:
 	return error;
 }
 
diff --git a/fs/xfs/scrub/rmap.c b/fs/xfs/scrub/rmap.c
index 97846c4..80edddb 100644
--- a/fs/xfs/scrub/rmap.c
+++ b/fs/xfs/scrub/rmap.c
@@ -51,6 +51,14 @@ xfs_scrub_setup_ag_rmapbt(
 
 /* Reverse-mapping scrubber. */
 
+/* Cross-reference with the other btrees. */
+STATIC void
+xfs_scrub_rmapbt_xref(
+	struct xfs_scrub_context	*sc,
+	struct xfs_rmap_irec		*irec)
+{
+}
+
 /* Scrub an rmapbt record. */
 STATIC int
 xfs_scrub_rmapbt_rec(
@@ -121,6 +129,11 @@ xfs_scrub_rmapbt_rec(
 		    irec.rm_owner > XFS_RMAP_OWN_FS)
 			xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
 	}
+
+	if (bs->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+		goto out;
+
+	xfs_scrub_rmapbt_xref(bs->sc, &irec);
 out:
 	return error;
 }

[PATCH 08/15] xfs: cross-reference with the bnobt

[Darrick J. Wong]

From: Darrick J. Wong <darrick.wong@oracle.com>

When we're scrubbing various btrees, cross-reference the records with
the bnobt to ensure that we don't also think the space is free.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/scrub/agheader.c |   84 +++++++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/alloc.c    |   19 +++++++++++
 fs/xfs/scrub/bmap.c     |   21 +++++++++++-
 fs/xfs/scrub/btree.c    |   12 +++++++
 fs/xfs/scrub/ialloc.c   |    1 +
 fs/xfs/scrub/inode.c    |   15 ++++++++
 fs/xfs/scrub/refcount.c |    1 +
 fs/xfs/scrub/rmap.c     |    4 ++
 fs/xfs/scrub/scrub.h    |    5 +++
 9 files changed, 161 insertions(+), 1 deletion(-)


diff --git a/fs/xfs/scrub/agheader.c b/fs/xfs/scrub/agheader.c
index b4297e9..6241475 100644
--- a/fs/xfs/scrub/agheader.c
+++ b/fs/xfs/scrub/agheader.c
@@ -107,6 +107,20 @@ xfs_scrub_superblock_xref(
 	struct xfs_scrub_context	*sc,
 	struct xfs_buf			*bp)
 {
+	struct xfs_mount		*mp = sc->mp;
+	xfs_agnumber_t			agno = sc->sm->sm_agno;
+	xfs_agblock_t			bno;
+	int				error;
+
+	bno = XFS_SB_BLOCK(mp);
+
+	error = xfs_scrub_ag_init(sc, agno, &sc->sa);
+	if (!xfs_scrub_xref_process_error(sc, agno, bno, &error))
+		return;
+
+	xfs_scrub_xref_not_free(sc, &sc->sa.bno_cur, bno, 1);
+
+	/* scrub teardown will take care of sc->sa for us */
 }
 
 /*
@@ -391,11 +405,51 @@ xfs_scrub_superblock(
 
 /* AGF */
 
+/* Tally freespace record lengths. */
+STATIC int
+xfs_scrub_agf_record_bno_lengths(
+	struct xfs_btree_cur		*cur,
+	struct xfs_alloc_rec_incore	*rec,
+	void				*priv)
+{
+	xfs_extlen_t			*blocks = priv;
+
+	(*blocks) += rec->ar_blockcount;
+	return 0;
+}
+
 /* Cross-reference with the other btrees. */
 STATIC void
 xfs_scrub_agf_xref(
 	struct xfs_scrub_context	*sc)
 {
+	struct xfs_mount		*mp = sc->mp;
+	struct xfs_agf			*agf = XFS_BUF_TO_AGF(sc->sa.agf_bp);
+	struct xfs_btree_cur		**pcur;
+	xfs_agblock_t			bno;
+	xfs_extlen_t			blocks;
+	int				error;
+
+	bno = XFS_AGF_BLOCK(mp);
+
+	error = xfs_scrub_ag_btcur_init(sc, &sc->sa);
+	if (error)
+		return;
+
+	xfs_scrub_xref_not_free(sc, &sc->sa.bno_cur, bno, 1);
+
+	/* Check agf_freeblks */
+	pcur = &sc->sa.bno_cur;
+	if (*pcur) {
+		blocks = 0;
+		error = xfs_alloc_query_all(*pcur,
+				xfs_scrub_agf_record_bno_lengths, &blocks);
+		if (xfs_scrub_should_xref(sc, &error, pcur) &&
+		    blocks != be32_to_cpu(agf->agf_freeblks))
+			xfs_scrub_block_xref_set_corrupt(sc, sc->sa.agf_bp);
+	}
+
+	/* scrub teardown will take care of sc->sa for us */
 }
 
 /* Scrub the AGF. */
@@ -498,6 +552,7 @@ xfs_scrub_agfl_block_xref(
 	struct xfs_scrub_context	*sc,
 	xfs_agblock_t			bno)
 {
+	xfs_scrub_xref_not_free(sc, &sc->sa.bno_cur, bno, 1);
 }
 
 /* Scrub an AGFL block. */
@@ -541,6 +596,22 @@ STATIC void
 xfs_scrub_agfl_xref(
 	struct xfs_scrub_context	*sc)
 {
+	struct xfs_mount		*mp = sc->mp;
+	xfs_agblock_t			bno;
+	int				error;
+
+	bno = XFS_AGFL_BLOCK(mp);
+
+	error = xfs_scrub_ag_btcur_init(sc, &sc->sa);
+	if (error)
+		return;
+
+	xfs_scrub_xref_not_free(sc, &sc->sa.bno_cur, bno, 1);
+
+	/*
+	 * Scrub teardown will take care of sc->sa for us.  Leave sc->sa
+	 * active so that the agfl block xref can use it too.
+	 */
 }
 
 /* Scrub the AGFL. */
@@ -615,6 +686,19 @@ STATIC void
 xfs_scrub_agi_xref(
 	struct xfs_scrub_context	*sc)
 {
+	struct xfs_mount		*mp = sc->mp;
+	xfs_agblock_t			bno;
+	int				error;
+
+	bno = XFS_AGI_BLOCK(mp);
+
+	error = xfs_scrub_ag_btcur_init(sc, &sc->sa);
+	if (error)
+		return;
+
+	xfs_scrub_xref_not_free(sc, &sc->sa.bno_cur, bno, 1);
+
+	/* scrub teardown will take care of sc->sa for us */
 }
 
 /* Scrub the AGI. */
diff --git a/fs/xfs/scrub/alloc.c b/fs/xfs/scrub/alloc.c
index 0d95b84..3d6f8cc 100644
--- a/fs/xfs/scrub/alloc.c
+++ b/fs/xfs/scrub/alloc.c
@@ -114,3 +114,22 @@ xfs_scrub_cntbt(
 {
 	return xfs_scrub_allocbt(sc, XFS_BTNUM_CNT);
 }
+
+/* xref check that the extent is not free */
+void
+xfs_scrub_xref_not_free(
+	struct xfs_scrub_context	*sc,
+	struct xfs_btree_cur		**pcur,
+	xfs_agblock_t			bno,
+	xfs_extlen_t			len)
+{
+	bool				is_freesp;
+	int				error;
+
+	if (!(*pcur))
+		return;
+
+	error = xfs_alloc_has_record(*pcur, bno, len, &is_freesp);
+	if (xfs_scrub_should_xref(sc, &error, pcur) && is_freesp)
+		xfs_scrub_btree_xref_set_corrupt(sc, *pcur, 0);
+}
diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c
index 684f08b..7ce135b 100644
--- a/fs/xfs/scrub/bmap.c
+++ b/fs/xfs/scrub/bmap.c
@@ -31,12 +31,12 @@
 #include "xfs_sb.h"
 #include "xfs_inode.h"
 #include "xfs_inode_fork.h"
-#include "xfs_alloc.h"
 #include "xfs_rtalloc.h"
 #include "xfs_bmap.h"
 #include "xfs_bmap_util.h"
 #include "xfs_bmap_btree.h"
 #include "xfs_rmap.h"
+#include "xfs_alloc.h"
 #include "scrub/xfs_scrub.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
@@ -117,6 +117,25 @@ xfs_scrub_bmap_extent_xref(
 	struct xfs_btree_cur		*cur,
 	struct xfs_bmbt_irec		*irec)
 {
+	struct xfs_scrub_ag		sa = { 0 };
+	struct xfs_mount		*mp = info->sc->mp;
+	xfs_agnumber_t			agno;
+	xfs_agblock_t			agbno;
+	xfs_extlen_t			len;
+	int				error;
+
+	agno = XFS_FSB_TO_AGNO(mp, irec->br_startblock);
+	agbno = XFS_FSB_TO_AGBNO(mp, irec->br_startblock);
+	len = irec->br_blockcount;
+
+	error = xfs_scrub_ag_init(info->sc, agno, &sa);
+	if (!xfs_scrub_fblock_process_error(info->sc, info->whichfork,
+			irec->br_startoff, &error))
+		return;
+
+	xfs_scrub_xref_not_free(info->sc, &sa.bno_cur, agbno, len);
+
+	xfs_scrub_ag_free(info->sc, &sa);
 }
 
 /* Scrub a single extent record. */
diff --git a/fs/xfs/scrub/btree.c b/fs/xfs/scrub/btree.c
index 40fc26f..67b6248 100644
--- a/fs/xfs/scrub/btree.c
+++ b/fs/xfs/scrub/btree.c
@@ -378,9 +378,12 @@ xfs_scrub_btree_check_block_owner(
 	struct xfs_scrub_ag		sa = { 0 };
 	struct xfs_scrub_ag		*psa;
 	xfs_agnumber_t			agno;
+	xfs_agblock_t			bno;
+	bool				is_freesp;
 	int				error = 0;
 
 	agno = xfs_daddr_to_agno(bs->cur->bc_mp, daddr);
+	bno = xfs_daddr_to_agbno(bs->cur->bc_mp, daddr);
 
 	if (bs->cur->bc_flags & XFS_BTREE_LONG_PTRS) {
 		error = xfs_scrub_ag_init(bs->sc, agno, &sa);
@@ -392,6 +395,15 @@ xfs_scrub_btree_check_block_owner(
 		psa = &bs->sc->sa;
 	}
 
+	/* Cross-reference with the bnobt. */
+	if (psa->bno_cur) {
+		error = xfs_alloc_has_record(psa->bno_cur, bno, 1, &is_freesp);
+		if (xfs_scrub_should_xref(bs->sc, &error, &psa->bno_cur) &&
+		    is_freesp)
+			xfs_scrub_btree_xref_set_corrupt(bs->sc, psa->bno_cur,
+					0);
+	}
+
 	if (psa == &sa)
 		xfs_scrub_ag_free(bs->sc, &sa);
 
diff --git a/fs/xfs/scrub/ialloc.c b/fs/xfs/scrub/ialloc.c
index 599d62a..4c4ef17c 100644
--- a/fs/xfs/scrub/ialloc.c
+++ b/fs/xfs/scrub/ialloc.c
@@ -67,6 +67,7 @@ xfs_scrub_iallocbt_chunk_xref(
 	xfs_agblock_t			bno,
 	xfs_extlen_t			len)
 {
+	xfs_scrub_xref_not_free(sc, &sc->sa.bno_cur, bno, len);
 }
 
 /* Is this chunk worth checking? */
diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c
index e31d981..e6038c1 100644
--- a/fs/xfs/scrub/inode.c
+++ b/fs/xfs/scrub/inode.c
@@ -584,6 +584,21 @@ xfs_scrub_inode_xref(
 	xfs_ino_t			ino,
 	struct xfs_dinode		*dip)
 {
+	struct xfs_scrub_ag		sa = { 0 };
+	xfs_agnumber_t			agno;
+	xfs_agblock_t			agbno;
+	int				error;
+
+	agno = XFS_INO_TO_AGNO(sc->mp, ino);
+	agbno = XFS_INO_TO_AGBNO(sc->mp, ino);
+
+	error = xfs_scrub_ag_init(sc, agno, &sa);
+	if (!xfs_scrub_xref_process_error(sc, agno, agbno, &error))
+		return;
+
+	xfs_scrub_xref_not_free(sc, &sa.bno_cur, agbno, 1);
+
+	xfs_scrub_ag_free(sc, &sa);
 }
 
 /* Scrub an inode. */
diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c
index 5a3aa9b..19c303d 100644
--- a/fs/xfs/scrub/refcount.c
+++ b/fs/xfs/scrub/refcount.c
@@ -58,6 +58,7 @@ xfs_scrub_refcountbt_xref(
 	xfs_extlen_t			len,
 	xfs_nlink_t			refcount)
 {
+	xfs_scrub_xref_not_free(sc, &sc->sa.bno_cur, bno, len);
 }
 
 /* Scrub a refcountbt record. */
diff --git a/fs/xfs/scrub/rmap.c b/fs/xfs/scrub/rmap.c
index 80edddb..5c9646b 100644
--- a/fs/xfs/scrub/rmap.c
+++ b/fs/xfs/scrub/rmap.c
@@ -57,6 +57,10 @@ xfs_scrub_rmapbt_xref(
 	struct xfs_scrub_context	*sc,
 	struct xfs_rmap_irec		*irec)
 {
+	xfs_agblock_t			bno = irec->rm_startblock;
+	xfs_extlen_t			len = irec->rm_blockcount;
+
+	xfs_scrub_xref_not_free(sc, &sc->sa.bno_cur, bno, len);
 }
 
 /* Scrub an rmapbt record. */
diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h
index 2a79614..e75ff0e 100644
--- a/fs/xfs/scrub/scrub.h
+++ b/fs/xfs/scrub/scrub.h
@@ -123,4 +123,9 @@ xfs_scrub_quota(struct xfs_scrub_context *sc)
 }
 #endif
 
+/* cross-referencing helpers */
+void xfs_scrub_xref_not_free(struct xfs_scrub_context *sc,
+		struct xfs_btree_cur **pcur, xfs_agblock_t bno,
+		xfs_extlen_t len);
+
 #endif	/* __XFS_SCRUB_SCRUB_H__ */

[PATCH 09/15] xfs: cross-reference bnobt records with cntbt

[Darrick J. Wong]

From: Darrick J. Wong <darrick.wong@oracle.com>

Scrub should make sure that each bnobt record has a corresponding
cntbt record.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/scrub/agheader.c |   26 ++++++++++++++++++++++++++
 fs/xfs/scrub/alloc.c    |   37 +++++++++++++++++++++++++++++++++++++
 2 files changed, 63 insertions(+)


diff --git a/fs/xfs/scrub/agheader.c b/fs/xfs/scrub/agheader.c
index 6241475..c7bfa20 100644
--- a/fs/xfs/scrub/agheader.c
+++ b/fs/xfs/scrub/agheader.c
@@ -428,6 +428,7 @@ xfs_scrub_agf_xref(
 	struct xfs_btree_cur		**pcur;
 	xfs_agblock_t			bno;
 	xfs_extlen_t			blocks;
+	int				have;
 	int				error;
 
 	bno = XFS_AGF_BLOCK(mp);
@@ -449,6 +450,31 @@ xfs_scrub_agf_xref(
 			xfs_scrub_block_xref_set_corrupt(sc, sc->sa.agf_bp);
 	}
 
+	/* Cross-reference with the cntbt. */
+	pcur = &sc->sa.cnt_cur;
+	while (*pcur) {
+		xfs_agblock_t		agbno;
+
+		/* Any freespace at all? */
+		error = xfs_alloc_lookup_le(*pcur, 0, -1U, &have);
+		if (!xfs_scrub_should_xref(sc, &error, pcur))
+			break;
+		if (!have) {
+			if (agf->agf_freeblks != be32_to_cpu(0))
+				xfs_scrub_block_xref_set_corrupt(sc,
+						sc->sa.agf_bp);
+			break;
+		}
+
+		/* Check agf_longest */
+		error = xfs_alloc_get_rec(*pcur, &agbno, &blocks, &have);
+		if (!xfs_scrub_should_xref(sc, &error, pcur))
+			break;
+		if (!have || blocks != be32_to_cpu(agf->agf_longest))
+			xfs_scrub_block_xref_set_corrupt(sc, sc->sa.agf_bp);
+		break;
+	}
+
 	/* scrub teardown will take care of sc->sa for us */
 }
 
diff --git a/fs/xfs/scrub/alloc.c b/fs/xfs/scrub/alloc.c
index 3d6f8cc..9a28e3d 100644
--- a/fs/xfs/scrub/alloc.c
+++ b/fs/xfs/scrub/alloc.c
@@ -31,6 +31,7 @@
 #include "xfs_sb.h"
 #include "xfs_alloc.h"
 #include "xfs_rmap.h"
+#include "xfs_alloc.h"
 #include "scrub/xfs_scrub.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
@@ -57,6 +58,42 @@ xfs_scrub_allocbt_xref(
 	xfs_agblock_t			bno,
 	xfs_extlen_t			len)
 {
+	struct xfs_btree_cur		**pcur;
+	struct xfs_scrub_ag		*psa = &sc->sa;
+	xfs_agblock_t			fbno;
+	xfs_extlen_t			flen;
+	int				has_otherrec;
+	int				error;
+
+	/*
+	 * Ensure there's a corresponding cntbt/bnobt record matching
+	 * this bnobt/cntbt record, respectively.
+	 */
+	if (sc->sm->sm_type == XFS_SCRUB_TYPE_BNOBT)
+		pcur = &psa->cnt_cur;
+	else
+		pcur = &psa->bno_cur;
+	while (*pcur) {
+		error = xfs_alloc_lookup_le(*pcur, bno, len, &has_otherrec);
+		if (!xfs_scrub_should_xref(sc, &error, pcur))
+			break;
+		if (!has_otherrec) {
+			xfs_scrub_btree_xref_set_corrupt(sc, *pcur, 0);
+			break;
+		}
+
+		error = xfs_alloc_get_rec(*pcur, &fbno, &flen, &has_otherrec);
+		if (!xfs_scrub_should_xref(sc, &error, pcur))
+			break;
+		if (!has_otherrec) {
+			xfs_scrub_btree_xref_set_corrupt(sc, *pcur, 0);
+			break;
+		}
+
+		if (fbno != bno || flen != len)
+			xfs_scrub_btree_xref_set_corrupt(sc, *pcur, 0);
+		break;
+	}
 }
 
 /* Scrub a bnobt/cntbt record. */

[PATCH 10/15] xfs: cross-reference inode btrees during scrub

[Darrick J. Wong]

From: Darrick J. Wong <darrick.wong@oracle.com>

Cross-reference the inode btrees with the other metadata when we
scrub the filesystem.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/scrub/agheader.c |   25 +++++++++++++++++++
 fs/xfs/scrub/alloc.c    |    3 ++
 fs/xfs/scrub/bmap.c     |    2 +
 fs/xfs/scrub/ialloc.c   |   63 +++++++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/inode.c    |    2 +
 fs/xfs/scrub/refcount.c |    2 +
 fs/xfs/scrub/rmap.c     |    6 ++++
 fs/xfs/scrub/scrub.h    |    6 ++++
 8 files changed, 109 insertions(+)


diff --git a/fs/xfs/scrub/agheader.c b/fs/xfs/scrub/agheader.c
index c7bfa20..1c2d521 100644
--- a/fs/xfs/scrub/agheader.c
+++ b/fs/xfs/scrub/agheader.c
@@ -119,6 +119,8 @@ xfs_scrub_superblock_xref(
 		return;
 
 	xfs_scrub_xref_not_free(sc, &sc->sa.bno_cur, bno, 1);
+	xfs_scrub_xref_not_inodes(sc, &sc->sa.ino_cur, bno, 1);
+	xfs_scrub_xref_not_inodes(sc, &sc->sa.fino_cur, bno, 1);
 
 	/* scrub teardown will take care of sc->sa for us */
 }
@@ -475,6 +477,9 @@ xfs_scrub_agf_xref(
 		break;
 	}
 
+	xfs_scrub_xref_not_inodes(sc, &sc->sa.ino_cur, bno, 1);
+	xfs_scrub_xref_not_inodes(sc, &sc->sa.fino_cur, bno, 1);
+
 	/* scrub teardown will take care of sc->sa for us */
 }
 
@@ -579,6 +584,8 @@ xfs_scrub_agfl_block_xref(
 	xfs_agblock_t			bno)
 {
 	xfs_scrub_xref_not_free(sc, &sc->sa.bno_cur, bno, 1);
+	xfs_scrub_xref_not_inodes(sc, &sc->sa.ino_cur, bno, 1);
+	xfs_scrub_xref_not_inodes(sc, &sc->sa.fino_cur, bno, 1);
 }
 
 /* Scrub an AGFL block. */
@@ -633,6 +640,8 @@ xfs_scrub_agfl_xref(
 		return;
 
 	xfs_scrub_xref_not_free(sc, &sc->sa.bno_cur, bno, 1);
+	xfs_scrub_xref_not_inodes(sc, &sc->sa.ino_cur, bno, 1);
+	xfs_scrub_xref_not_inodes(sc, &sc->sa.fino_cur, bno, 1);
 
 	/*
 	 * Scrub teardown will take care of sc->sa for us.  Leave sc->sa
@@ -713,7 +722,11 @@ xfs_scrub_agi_xref(
 	struct xfs_scrub_context	*sc)
 {
 	struct xfs_mount		*mp = sc->mp;
+	struct xfs_btree_cur		**pcur;
+	struct xfs_agi			*agi = XFS_BUF_TO_AGI(sc->sa.agi_bp);
 	xfs_agblock_t			bno;
+	xfs_agino_t			icount;
+	xfs_agino_t			freecount;
 	int				error;
 
 	bno = XFS_AGI_BLOCK(mp);
@@ -723,6 +736,18 @@ xfs_scrub_agi_xref(
 		return;
 
 	xfs_scrub_xref_not_free(sc, &sc->sa.bno_cur, bno, 1);
+	xfs_scrub_xref_not_inodes(sc, &sc->sa.ino_cur, bno, 1);
+	xfs_scrub_xref_not_inodes(sc, &sc->sa.fino_cur, bno, 1);
+
+	/* Check agi_count/agi_freecount */
+	pcur = &sc->sa.ino_cur;
+	if (*pcur) {
+		error = xfs_ialloc_count_inodes(*pcur, &icount, &freecount);
+		if (xfs_scrub_should_xref(sc, &error, pcur) &&
+		    (be32_to_cpu(agi->agi_count) != icount ||
+		     be32_to_cpu(agi->agi_freecount) != freecount))
+			xfs_scrub_block_xref_set_corrupt(sc, sc->sa.agi_bp);
+	}
 
 	/* scrub teardown will take care of sc->sa for us */
 }
diff --git a/fs/xfs/scrub/alloc.c b/fs/xfs/scrub/alloc.c
index 9a28e3d..cd709f4 100644
--- a/fs/xfs/scrub/alloc.c
+++ b/fs/xfs/scrub/alloc.c
@@ -94,6 +94,9 @@ xfs_scrub_allocbt_xref(
 			xfs_scrub_btree_xref_set_corrupt(sc, *pcur, 0);
 		break;
 	}
+
+	xfs_scrub_xref_not_inodes(sc, &sc->sa.ino_cur, bno, len);
+	xfs_scrub_xref_not_inodes(sc, &sc->sa.fino_cur, bno, len);
 }
 
 /* Scrub a bnobt/cntbt record. */
diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c
index 7ce135b..a0274d3 100644
--- a/fs/xfs/scrub/bmap.c
+++ b/fs/xfs/scrub/bmap.c
@@ -134,6 +134,8 @@ xfs_scrub_bmap_extent_xref(
 		return;
 
 	xfs_scrub_xref_not_free(info->sc, &sa.bno_cur, agbno, len);
+	xfs_scrub_xref_not_inodes(info->sc, &sa.ino_cur, agbno, len);
+	xfs_scrub_xref_not_inodes(info->sc, &sa.fino_cur, agbno, len);
 
 	xfs_scrub_ag_free(info->sc, &sa);
 }
diff --git a/fs/xfs/scrub/ialloc.c b/fs/xfs/scrub/ialloc.c
index 4c4ef17c..da07393 100644
--- a/fs/xfs/scrub/ialloc.c
+++ b/fs/xfs/scrub/ialloc.c
@@ -67,7 +67,29 @@ xfs_scrub_iallocbt_chunk_xref(
 	xfs_agblock_t			bno,
 	xfs_extlen_t			len)
 {
+	struct xfs_btree_cur		**pcur;
+	bool				has_irec;
+	int				error;
+
 	xfs_scrub_xref_not_free(sc, &sc->sa.bno_cur, bno, len);
+
+	/*
+	 * If we're checking the finobt, cross-reference with the inobt.
+	 * Otherwise we're checking the inobt; if there is an finobt,
+	 * make sure we have a record or not depending on freecount.
+	 */
+	if (sc->sm->sm_type == XFS_SCRUB_TYPE_FINOBT)
+		pcur = &sc->sa.ino_cur;
+	else
+		pcur = &sc->sa.fino_cur;
+	if (*pcur) {
+		error = xfs_ialloc_has_inode_record(*pcur,
+				agino, agino, &has_irec);
+		if (xfs_scrub_should_xref(sc, &error, pcur) &&
+		    ((irec->ir_freecount > 0 && !has_irec) ||
+		     (irec->ir_freecount == 0 && has_irec)))
+			xfs_scrub_btree_xref_set_corrupt(sc, *pcur, 0);
+	}
 }
 
 /* Is this chunk worth checking? */
@@ -351,3 +373,44 @@ xfs_scrub_finobt(
 {
 	return xfs_scrub_iallocbt(sc, XFS_BTNUM_FINO);
 }
+
+static inline void
+__xfs_scrub_xref_check_inodes(
+	struct xfs_scrub_context	*sc,
+	struct xfs_btree_cur		**pcur,
+	xfs_agblock_t			bno,
+	xfs_extlen_t			len,
+	bool				fs_ok)
+{
+	bool				has_inodes;
+	int				error;
+
+	if (!(*pcur))
+		return;
+
+	error = xfs_ialloc_has_inodes_at_extent(*pcur, bno, len, &has_inodes);
+	if (xfs_scrub_should_xref(sc, &error, pcur) && has_inodes != fs_ok)
+		xfs_scrub_btree_xref_set_corrupt(sc, *pcur, 0);
+}
+
+/* xref check that the extent is not covered by inodes */
+void
+xfs_scrub_xref_not_inodes(
+	struct xfs_scrub_context	*sc,
+	struct xfs_btree_cur		**pcur,
+	xfs_agblock_t			bno,
+	xfs_extlen_t			len)
+{
+	__xfs_scrub_xref_check_inodes(sc, pcur, bno, len, false);
+}
+
+/* xref check that the extent is covered by inodes */
+void
+xfs_scrub_xref_are_inodes(
+	struct xfs_scrub_context	*sc,
+	struct xfs_btree_cur		**pcur,
+	xfs_agblock_t			bno,
+	xfs_extlen_t			len)
+{
+	__xfs_scrub_xref_check_inodes(sc, pcur, bno, len, true);
+}
diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c
index e6038c1..bb5172c 100644
--- a/fs/xfs/scrub/inode.c
+++ b/fs/xfs/scrub/inode.c
@@ -597,6 +597,8 @@ xfs_scrub_inode_xref(
 		return;
 
 	xfs_scrub_xref_not_free(sc, &sa.bno_cur, agbno, 1);
+	xfs_scrub_xref_are_inodes(sc, &sc->sa.ino_cur, agbno, 1);
+	xfs_scrub_xref_are_inodes(sc, &sc->sa.fino_cur, agbno, 1);
 
 	xfs_scrub_ag_free(sc, &sa);
 }
diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c
index 19c303d..8add281 100644
--- a/fs/xfs/scrub/refcount.c
+++ b/fs/xfs/scrub/refcount.c
@@ -59,6 +59,8 @@ xfs_scrub_refcountbt_xref(
 	xfs_nlink_t			refcount)
 {
 	xfs_scrub_xref_not_free(sc, &sc->sa.bno_cur, bno, len);
+	xfs_scrub_xref_not_inodes(sc, &sc->sa.ino_cur, bno, len);
+	xfs_scrub_xref_not_inodes(sc, &sc->sa.fino_cur, bno, len);
 }
 
 /* Scrub a refcountbt record. */
diff --git a/fs/xfs/scrub/rmap.c b/fs/xfs/scrub/rmap.c
index 5c9646b..8d49556 100644
--- a/fs/xfs/scrub/rmap.c
+++ b/fs/xfs/scrub/rmap.c
@@ -61,6 +61,12 @@ xfs_scrub_rmapbt_xref(
 	xfs_extlen_t			len = irec->rm_blockcount;
 
 	xfs_scrub_xref_not_free(sc, &sc->sa.bno_cur, bno, len);
+	if (irec->rm_owner == XFS_RMAP_OWN_INODES) {
+		xfs_scrub_xref_are_inodes(sc, &sc->sa.ino_cur, bno, len);
+	} else {
+		xfs_scrub_xref_not_inodes(sc, &sc->sa.ino_cur, bno, len);
+		xfs_scrub_xref_not_inodes(sc, &sc->sa.fino_cur, bno, len);
+	}
 }
 
 /* Scrub an rmapbt record. */
diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h
index e75ff0e..768df35 100644
--- a/fs/xfs/scrub/scrub.h
+++ b/fs/xfs/scrub/scrub.h
@@ -127,5 +127,11 @@ xfs_scrub_quota(struct xfs_scrub_context *sc)
 void xfs_scrub_xref_not_free(struct xfs_scrub_context *sc,
 		struct xfs_btree_cur **pcur, xfs_agblock_t bno,
 		xfs_extlen_t len);
+void xfs_scrub_xref_not_inodes(struct xfs_scrub_context *sc,
+		struct xfs_btree_cur **pcur, xfs_agblock_t bno,
+		xfs_extlen_t len);
+void xfs_scrub_xref_are_inodes(struct xfs_scrub_context *sc,
+		struct xfs_btree_cur **pcur, xfs_agblock_t bno,
+		xfs_extlen_t len);
 
 #endif	/* __XFS_SCRUB_SCRUB_H__ */

[PATCH 11/15] xfs: cross-reference reverse-mapping btree

[Darrick J. Wong]

From: Darrick J. Wong <darrick.wong@oracle.com>

When scrubbing various btrees, we should cross-reference the records
with the reverse mapping btree and ensure that traversing the btree
finds the same number of blocks that the rmapbt thinks are owned by
that btree.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/scrub/agheader.c |   70 +++++++++++++++++++++++++++++++-
 fs/xfs/scrub/alloc.c    |    1 
 fs/xfs/scrub/bmap.c     |  102 +++++++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/btree.c    |    2 +
 fs/xfs/scrub/common.c   |   47 ++++++++++++++++++++++
 fs/xfs/scrub/common.h   |    4 ++
 fs/xfs/scrub/ialloc.c   |   74 ++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/inode.c    |    4 ++
 fs/xfs/scrub/rmap.c     |   64 +++++++++++++++++++++++++++++
 fs/xfs/scrub/scrub.h    |    9 ++++
 10 files changed, 374 insertions(+), 3 deletions(-)


diff --git a/fs/xfs/scrub/agheader.c b/fs/xfs/scrub/agheader.c
index 1c2d521..3e5bb78 100644
--- a/fs/xfs/scrub/agheader.c
+++ b/fs/xfs/scrub/agheader.c
@@ -32,6 +32,7 @@
 #include "xfs_inode.h"
 #include "xfs_alloc.h"
 #include "xfs_ialloc.h"
+#include "xfs_rmap.h"
 #include "scrub/xfs_scrub.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
@@ -107,6 +108,7 @@ xfs_scrub_superblock_xref(
 	struct xfs_scrub_context	*sc,
 	struct xfs_buf			*bp)
 {
+	struct xfs_owner_info		oinfo;
 	struct xfs_mount		*mp = sc->mp;
 	xfs_agnumber_t			agno = sc->sm->sm_agno;
 	xfs_agblock_t			bno;
@@ -121,6 +123,8 @@ xfs_scrub_superblock_xref(
 	xfs_scrub_xref_not_free(sc, &sc->sa.bno_cur, bno, 1);
 	xfs_scrub_xref_not_inodes(sc, &sc->sa.ino_cur, bno, 1);
 	xfs_scrub_xref_not_inodes(sc, &sc->sa.fino_cur, bno, 1);
+	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_FS);
+	xfs_scrub_xref_owned_by(sc, &sc->sa.rmap_cur, bno, 1, &oinfo);
 
 	/* scrub teardown will take care of sc->sa for us */
 }
@@ -420,11 +424,59 @@ xfs_scrub_agf_record_bno_lengths(
 	return 0;
 }
 
+/* Check the btree block counts in the AGF against the btrees. */
+STATIC void
+xfs_scrub_agf_xref_btreeblks(
+	struct xfs_scrub_context	*sc)
+{
+	struct xfs_btree_cur		**pcur;
+	struct xfs_agf			*agf = XFS_BUF_TO_AGF(sc->sa.agf_bp);
+	struct xfs_mount		*mp = sc->mp;
+	xfs_agblock_t			blocks;
+	xfs_agblock_t			btreeblks;
+	int				error;
+
+	/* Check agf_rmap_blocks; set up for agf_btreeblks check */
+	pcur = &sc->sa.rmap_cur;
+	if (*pcur) {
+		error = xfs_btree_count_blocks(*pcur, &blocks);
+		if (!xfs_scrub_should_xref(sc, &error, pcur))
+			return;
+		btreeblks = blocks - 1;
+		if (blocks != be32_to_cpu(agf->agf_rmap_blocks))
+			xfs_scrub_block_xref_set_corrupt(sc, sc->sa.agf_bp);
+	} else {
+		btreeblks = 0;
+	}
+
+	/*
+	 * No rmap cursor; we can't xref if we have the rmapbt feature.
+	 * We also can't do it if we're missing the free space btree cursors.
+	 */
+	if ((xfs_sb_version_hasrmapbt(&mp->m_sb) && !sc->sa.rmap_cur) ||
+	    !sc->sa.bno_cur || !sc->sa.cnt_cur)
+		return;
+
+	/* Check agf_btreeblks */
+	error = xfs_btree_count_blocks(sc->sa.bno_cur, &blocks);
+	if (xfs_scrub_should_xref(sc, &error, &sc->sa.bno_cur))
+		btreeblks += blocks - 1;
+
+	error = xfs_btree_count_blocks(sc->sa.cnt_cur, &blocks);
+	if (xfs_scrub_should_xref(sc, &error, &sc->sa.cnt_cur))
+		btreeblks += blocks - 1;
+
+	if (sc->sa.bno_cur && sc->sa.cnt_cur &&
+	    btreeblks != be32_to_cpu(agf->agf_btreeblks))
+		xfs_scrub_block_xref_set_corrupt(sc, sc->sa.agf_bp);
+}
+
 /* Cross-reference with the other btrees. */
 STATIC void
 xfs_scrub_agf_xref(
 	struct xfs_scrub_context	*sc)
 {
+	struct xfs_owner_info		oinfo;
 	struct xfs_mount		*mp = sc->mp;
 	struct xfs_agf			*agf = XFS_BUF_TO_AGF(sc->sa.agf_bp);
 	struct xfs_btree_cur		**pcur;
@@ -479,6 +531,9 @@ xfs_scrub_agf_xref(
 
 	xfs_scrub_xref_not_inodes(sc, &sc->sa.ino_cur, bno, 1);
 	xfs_scrub_xref_not_inodes(sc, &sc->sa.fino_cur, bno, 1);
+	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_FS);
+	xfs_scrub_xref_owned_by(sc, &sc->sa.rmap_cur, bno, 1, &oinfo);
+	xfs_scrub_agf_xref_btreeblks(sc);
 
 	/* scrub teardown will take care of sc->sa for us */
 }
@@ -572,6 +627,7 @@ xfs_scrub_agf(
 /* AGFL */
 
 struct xfs_scrub_agfl_info {
+	struct xfs_owner_info		oinfo;
 	unsigned int			sz_entries;
 	unsigned int			nr_entries;
 	xfs_agblock_t			*entries;
@@ -581,11 +637,13 @@ struct xfs_scrub_agfl_info {
 STATIC void
 xfs_scrub_agfl_block_xref(
 	struct xfs_scrub_context	*sc,
-	xfs_agblock_t			bno)
+	xfs_agblock_t			bno,
+	struct xfs_owner_info		*oinfo)
 {
 	xfs_scrub_xref_not_free(sc, &sc->sa.bno_cur, bno, 1);
 	xfs_scrub_xref_not_inodes(sc, &sc->sa.ino_cur, bno, 1);
 	xfs_scrub_xref_not_inodes(sc, &sc->sa.fino_cur, bno, 1);
+	xfs_scrub_xref_owned_by(sc, &sc->sa.rmap_cur, bno, 1, oinfo);
 }
 
 /* Scrub an AGFL block. */
@@ -608,7 +666,7 @@ xfs_scrub_agfl_block(
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		goto out;
 
-	xfs_scrub_agfl_block_xref(sc, agbno);
+	xfs_scrub_agfl_block_xref(sc, agbno, priv);
 out:
 	return 0;
 }
@@ -629,6 +687,7 @@ STATIC void
 xfs_scrub_agfl_xref(
 	struct xfs_scrub_context	*sc)
 {
+	struct xfs_owner_info		oinfo;
 	struct xfs_mount		*mp = sc->mp;
 	xfs_agblock_t			bno;
 	int				error;
@@ -642,6 +701,8 @@ xfs_scrub_agfl_xref(
 	xfs_scrub_xref_not_free(sc, &sc->sa.bno_cur, bno, 1);
 	xfs_scrub_xref_not_inodes(sc, &sc->sa.ino_cur, bno, 1);
 	xfs_scrub_xref_not_inodes(sc, &sc->sa.fino_cur, bno, 1);
+	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_FS);
+	xfs_scrub_xref_owned_by(sc, &sc->sa.rmap_cur, bno, 1, &oinfo);
 
 	/*
 	 * Scrub teardown will take care of sc->sa for us.  Leave sc->sa
@@ -689,6 +750,7 @@ xfs_scrub_agfl(
 	}
 
 	/* Check the blocks in the AGFL. */
+	xfs_rmap_ag_owner(&sai.oinfo, XFS_RMAP_OWN_AG);
 	error = xfs_scrub_walk_agfl(sc, xfs_scrub_agfl_block, &sai);
 	if (error)
 		goto out_free;
@@ -721,6 +783,7 @@ STATIC void
 xfs_scrub_agi_xref(
 	struct xfs_scrub_context	*sc)
 {
+	struct xfs_owner_info		oinfo;
 	struct xfs_mount		*mp = sc->mp;
 	struct xfs_btree_cur		**pcur;
 	struct xfs_agi			*agi = XFS_BUF_TO_AGI(sc->sa.agi_bp);
@@ -749,6 +812,9 @@ xfs_scrub_agi_xref(
 			xfs_scrub_block_xref_set_corrupt(sc, sc->sa.agi_bp);
 	}
 
+	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_FS);
+	xfs_scrub_xref_owned_by(sc, &sc->sa.rmap_cur, bno, 1, &oinfo);
+
 	/* scrub teardown will take care of sc->sa for us */
 }
 
diff --git a/fs/xfs/scrub/alloc.c b/fs/xfs/scrub/alloc.c
index cd709f4..a4046c1 100644
--- a/fs/xfs/scrub/alloc.c
+++ b/fs/xfs/scrub/alloc.c
@@ -97,6 +97,7 @@ xfs_scrub_allocbt_xref(
 
 	xfs_scrub_xref_not_inodes(sc, &sc->sa.ino_cur, bno, len);
 	xfs_scrub_xref_not_inodes(sc, &sc->sa.fino_cur, bno, len);
+	xfs_scrub_xref_no_rmap(sc, &sc->sa.rmap_cur, bno, len);
 }
 
 /* Scrub a bnobt/cntbt record. */
diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c
index a0274d3..f408193 100644
--- a/fs/xfs/scrub/bmap.c
+++ b/fs/xfs/scrub/bmap.c
@@ -99,6 +99,107 @@ struct xfs_scrub_bmap_info {
 	int				whichfork;
 };
 
+/* Make sure that we have rmapbt records for this extent. */
+STATIC void
+xfs_scrub_bmap_xref_rmap(
+	struct xfs_scrub_bmap_info	*info,
+	struct xfs_scrub_ag		*sa,
+	struct xfs_bmbt_irec		*irec,
+	xfs_fsblock_t			bno)
+{
+	struct xfs_rmap_irec		rmap;
+	uint64_t			owner;
+	xfs_fileoff_t			offset;
+	unsigned long long		rmap_end;
+	unsigned int			rflags;
+	int				has_rmap;
+	int				error;
+
+	if (!sa->rmap_cur)
+		return;
+
+	if (info->whichfork == XFS_COW_FORK) {
+		owner = XFS_RMAP_OWN_COW;
+		offset = 0;
+	} else {
+		owner = info->sc->ip->i_ino;
+		offset = irec->br_startoff;
+	}
+
+	/* Look for a corresponding rmap. */
+	rflags = 0;
+	if (info->whichfork == XFS_ATTR_FORK)
+		rflags |= XFS_RMAP_ATTR_FORK;
+
+	if (info->is_shared) {
+		error = xfs_rmap_lookup_le_range(sa->rmap_cur, bno, owner,
+				offset, rflags, &rmap,
+				&has_rmap);
+		if (!xfs_scrub_should_xref(info->sc, &error, &sa->rmap_cur))
+			return;
+		if (!has_rmap) {
+			xfs_scrub_fblock_xref_set_corrupt(info->sc,
+					info->whichfork, irec->br_startoff);
+			return;
+		}
+	} else {
+		error = xfs_rmap_lookup_le(sa->rmap_cur, bno, 0, owner,
+				offset, rflags, &has_rmap);
+		if (!xfs_scrub_should_xref(info->sc, &error, &sa->rmap_cur))
+			return;
+		if (!has_rmap) {
+			xfs_scrub_fblock_xref_set_corrupt(info->sc,
+					info->whichfork, irec->br_startoff);
+			return;
+		}
+
+		error = xfs_rmap_get_rec(sa->rmap_cur, &rmap, &has_rmap);
+		if (!xfs_scrub_should_xref(info->sc, &error, &sa->rmap_cur))
+			return;
+		if (!has_rmap) {
+			xfs_scrub_fblock_xref_set_corrupt(info->sc,
+					info->whichfork, irec->br_startoff);
+			return;
+		}
+	}
+
+	/* Check the rmap. */
+	rmap_end = (unsigned long long)rmap.rm_startblock + rmap.rm_blockcount;
+	if (rmap.rm_startblock > bno ||
+	    bno + irec->br_blockcount > rmap_end)
+		xfs_scrub_fblock_xref_set_corrupt(info->sc, info->whichfork,
+				irec->br_startoff);
+
+	if (owner != XFS_RMAP_OWN_COW) {
+		rmap_end = (unsigned long long)rmap.rm_offset +
+				rmap.rm_blockcount;
+		if (rmap.rm_offset > offset ||
+		    offset + irec->br_blockcount > rmap_end)
+			xfs_scrub_fblock_xref_set_corrupt(info->sc,
+					info->whichfork, irec->br_startoff);
+	} else {
+		/*
+		 * We don't set the unwritten flag for CoW
+		 * staging extent rmaps; everything is unwritten.
+		 */
+		irec->br_state = XFS_EXT_NORM;
+	}
+	if (rmap.rm_owner != owner)
+		xfs_scrub_fblock_xref_set_corrupt(info->sc, info->whichfork,
+				irec->br_startoff);
+	if (irec->br_state == XFS_EXT_UNWRITTEN &&
+	    !(rmap.rm_flags & XFS_RMAP_UNWRITTEN))
+		xfs_scrub_fblock_xref_set_corrupt(info->sc, info->whichfork,
+				irec->br_startoff);
+	if (info->whichfork == XFS_ATTR_FORK &&
+	    !(rmap.rm_flags & XFS_RMAP_ATTR_FORK))
+		xfs_scrub_fblock_xref_set_corrupt(info->sc, info->whichfork,
+				irec->br_startoff);
+	if (rmap.rm_flags & XFS_RMAP_BMBT_BLOCK)
+		xfs_scrub_fblock_xref_set_corrupt(info->sc, info->whichfork,
+				irec->br_startoff);
+}
+
 /* Cross-reference a single rtdev extent record. */
 STATIC void
 xfs_scrub_bmap_rt_extent_xref(
@@ -136,6 +237,7 @@ xfs_scrub_bmap_extent_xref(
 	xfs_scrub_xref_not_free(info->sc, &sa.bno_cur, agbno, len);
 	xfs_scrub_xref_not_inodes(info->sc, &sa.ino_cur, agbno, len);
 	xfs_scrub_xref_not_inodes(info->sc, &sa.fino_cur, agbno, len);
+	xfs_scrub_bmap_xref_rmap(info, &sa, irec, agbno);
 
 	xfs_scrub_ag_free(info->sc, &sa);
 }
diff --git a/fs/xfs/scrub/btree.c b/fs/xfs/scrub/btree.c
index 67b6248..26149cb 100644
--- a/fs/xfs/scrub/btree.c
+++ b/fs/xfs/scrub/btree.c
@@ -404,6 +404,8 @@ xfs_scrub_btree_check_block_owner(
 					0);
 	}
 
+	xfs_scrub_xref_owned_by(bs->sc, &psa->rmap_cur, bno, 1, bs->oinfo);
+
 	if (psa == &sa)
 		xfs_scrub_ag_free(bs->sc, &sa);
 
diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c
index effdcfa..c36a91b 100644
--- a/fs/xfs/scrub/common.c
+++ b/fs/xfs/scrub/common.c
@@ -325,6 +325,53 @@ xfs_scrub_set_incomplete(
 }
 
 /*
+ * rmap scrubbing -- compute the number of blocks with a given owner,
+ * at least according to the reverse mapping data.
+ */
+
+struct xfs_scrub_rmap_ownedby_info {
+	struct xfs_owner_info	*oinfo;
+	xfs_filblks_t		*blocks;
+};
+
+STATIC int
+xfs_scrub_count_rmap_ownedby_helper(
+	struct xfs_btree_cur			*cur,
+	struct xfs_rmap_irec			*rec,
+	void					*priv)
+{
+	struct xfs_scrub_rmap_ownedby_info	*sroi = priv;
+
+	if (rec->rm_owner == sroi->oinfo->oi_owner &&
+	    (XFS_RMAP_NON_INODE_OWNER(rec->rm_owner) ||
+	     !!(rec->rm_flags & XFS_RMAP_ATTR_FORK) ==
+	     !!(sroi->oinfo->oi_flags & XFS_OWNER_INFO_ATTR_FORK)))
+		(*sroi->blocks) += rec->rm_blockcount;
+	return 0;
+}
+
+/*
+ * Calculate the number of blocks the rmap thinks are owned by something.
+ * The caller should pass us an rmapbt cursor.
+ */
+int
+xfs_scrub_count_rmap_ownedby_ag(
+	struct xfs_scrub_context		*sc,
+	struct xfs_btree_cur			*cur,
+	struct xfs_owner_info			*oinfo,
+	xfs_filblks_t				*blocks)
+{
+	struct xfs_scrub_rmap_ownedby_info	sroi;
+
+	sroi.oinfo = oinfo;
+	*blocks = 0;
+	sroi.blocks = blocks;
+
+	return xfs_rmap_query_all(cur, xfs_scrub_count_rmap_ownedby_helper,
+			&sroi);
+}
+
+/*
  * AG scrubbing
  *
  * These helpers facilitate locking an allocation group's header
diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h
index 0e12a10..4f6a6e1 100644
--- a/fs/xfs/scrub/common.h
+++ b/fs/xfs/scrub/common.h
@@ -148,6 +148,10 @@ int xfs_scrub_walk_agfl(struct xfs_scrub_context *sc,
 			int (*fn)(struct xfs_scrub_context *, xfs_agblock_t bno,
 				  void *),
 			void *priv);
+int xfs_scrub_count_rmap_ownedby_ag(struct xfs_scrub_context *sc,
+				    struct xfs_btree_cur *cur,
+				    struct xfs_owner_info *oinfo,
+				    xfs_filblks_t *blocks);
 
 int xfs_scrub_setup_ag_btree(struct xfs_scrub_context *sc,
 			     struct xfs_inode *ip, bool force_log);
diff --git a/fs/xfs/scrub/ialloc.c b/fs/xfs/scrub/ialloc.c
index da07393..d4b7f13 100644
--- a/fs/xfs/scrub/ialloc.c
+++ b/fs/xfs/scrub/ialloc.c
@@ -67,6 +67,7 @@ xfs_scrub_iallocbt_chunk_xref(
 	xfs_agblock_t			bno,
 	xfs_extlen_t			len)
 {
+	struct xfs_owner_info		oinfo;
 	struct xfs_btree_cur		**pcur;
 	bool				has_irec;
 	int				error;
@@ -90,6 +91,9 @@ xfs_scrub_iallocbt_chunk_xref(
 		     (irec->ir_freecount == 0 && has_irec)))
 			xfs_scrub_btree_xref_set_corrupt(sc, *pcur, 0);
 	}
+
+	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_INODES);
+	xfs_scrub_xref_owned_by(sc, &sc->sa.rmap_cur, bno, len, &oinfo);
 }
 
 /* Is this chunk worth checking? */
@@ -228,6 +232,14 @@ xfs_scrub_iallocbt_check_freemask(
 			continue;
 		}
 
+		if (ir_holemask == 0)
+			xfs_scrub_xref_owned_by(bs->sc, &bs->sc->sa.rmap_cur,
+					agbno, blks_per_cluster, &oinfo);
+		else
+			xfs_scrub_xref_not_owned_by(bs->sc,
+					&bs->sc->sa.rmap_cur,
+					agbno, blks_per_cluster, &oinfo);
+
 		/* If any part of this is a hole, skip it. */
 		if (ir_holemask)
 			continue;
@@ -266,6 +278,7 @@ xfs_scrub_iallocbt_rec(
 	union xfs_btree_rec		*rec)
 {
 	struct xfs_mount		*mp = bs->cur->bc_mp;
+	xfs_filblks_t			*inode_blocks = bs->private;
 	struct xfs_inobt_rec_incore	irec;
 	uint64_t			holes;
 	xfs_agnumber_t			agno = bs->cur->bc_private.a.agno;
@@ -302,6 +315,8 @@ xfs_scrub_iallocbt_rec(
 	if ((agbno & (xfs_ialloc_cluster_alignment(mp) - 1)) ||
 	    (agbno & (xfs_icluster_size_fsb(mp) - 1)))
 		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+	*inode_blocks += XFS_B_TO_FSB(mp,
+			irec.ir_count * mp->m_sb.sb_inodesize);
 
 	/* Handle non-sparse inodes */
 	if (!xfs_inobt_issparse(irec.ir_holemask)) {
@@ -346,6 +361,53 @@ xfs_scrub_iallocbt_rec(
 	return error;
 }
 
+/*
+ * Make sure the inode btrees are as large as the rmap thinks they are.
+ * Don't bother if we're missing btree cursors, as we're already corrupt.
+ */
+STATIC void
+xfs_scrub_iallocbt_xref_rmap(
+	struct xfs_scrub_context	*sc,
+	int				which,
+	struct xfs_owner_info		*oinfo,
+	xfs_filblks_t			inode_blocks)
+{
+	xfs_filblks_t			blocks;
+	xfs_extlen_t			inobt_blocks = 0;
+	xfs_extlen_t			finobt_blocks = 0;
+	int				error;
+
+	if (!sc->sa.ino_cur || !sc->sa.rmap_cur)
+		return;
+
+	/* Check that we saw as many inobt blocks as the rmap says. */
+	error = xfs_btree_count_blocks(sc->sa.ino_cur, &inobt_blocks);
+	if (error)
+		return;
+
+	if (xfs_sb_version_hasfinobt(&sc->mp->m_sb)) {
+		if (!sc->sa.fino_cur)
+			return;
+		error = xfs_btree_count_blocks(sc->sa.fino_cur, &finobt_blocks);
+		if (error)
+			return;
+	}
+
+	error = xfs_scrub_count_rmap_ownedby_ag(sc, sc->sa.rmap_cur, oinfo,
+			&blocks);
+	if (xfs_scrub_should_xref(sc, &error, &sc->sa.rmap_cur) &&
+	    blocks != inobt_blocks + finobt_blocks)
+		xfs_scrub_block_set_corrupt(sc, sc->sa.agi_bp);
+
+	/* Check that we saw as many inode blocks as the rmap knows about. */
+	xfs_rmap_ag_owner(oinfo, XFS_RMAP_OWN_INODES);
+	error = xfs_scrub_count_rmap_ownedby_ag(sc, sc->sa.rmap_cur, oinfo,
+			&blocks);
+	if (xfs_scrub_should_xref(sc, &error, &sc->sa.rmap_cur) &&
+	    blocks != inode_blocks)
+		xfs_scrub_block_set_corrupt(sc, sc->sa.agi_bp);
+}
+
 /* Scrub the inode btrees for some AG. */
 STATIC int
 xfs_scrub_iallocbt(
@@ -354,10 +416,20 @@ xfs_scrub_iallocbt(
 {
 	struct xfs_btree_cur		*cur;
 	struct xfs_owner_info		oinfo;
+	xfs_filblks_t			inode_blocks = 0;
+	int				error;
 
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_INOBT);
 	cur = which == XFS_BTNUM_INO ? sc->sa.ino_cur : sc->sa.fino_cur;
-	return xfs_scrub_btree(sc, cur, xfs_scrub_iallocbt_rec, &oinfo, NULL);
+	error = xfs_scrub_btree(sc, cur, xfs_scrub_iallocbt_rec, &oinfo,
+			&inode_blocks);
+	if (error)
+		return error;
+
+	if (which == XFS_BTNUM_INO)
+		xfs_scrub_iallocbt_xref_rmap(sc, which, &oinfo, inode_blocks);
+
+	return error;
 }
 
 int
diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c
index bb5172c..830d44a 100644
--- a/fs/xfs/scrub/inode.c
+++ b/fs/xfs/scrub/inode.c
@@ -36,6 +36,7 @@
 #include "xfs_ialloc.h"
 #include "xfs_da_format.h"
 #include "xfs_reflink.h"
+#include "xfs_rmap.h"
 #include "scrub/xfs_scrub.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
@@ -585,6 +586,7 @@ xfs_scrub_inode_xref(
 	struct xfs_dinode		*dip)
 {
 	struct xfs_scrub_ag		sa = { 0 };
+	struct xfs_owner_info		oinfo;
 	xfs_agnumber_t			agno;
 	xfs_agblock_t			agbno;
 	int				error;
@@ -599,6 +601,8 @@ xfs_scrub_inode_xref(
 	xfs_scrub_xref_not_free(sc, &sa.bno_cur, agbno, 1);
 	xfs_scrub_xref_are_inodes(sc, &sc->sa.ino_cur, agbno, 1);
 	xfs_scrub_xref_are_inodes(sc, &sc->sa.fino_cur, agbno, 1);
+	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_INODES);
+	xfs_scrub_xref_owned_by(sc, &sc->sa.rmap_cur, agbno, 1, &oinfo);
 
 	xfs_scrub_ag_free(sc, &sa);
 }
diff --git a/fs/xfs/scrub/rmap.c b/fs/xfs/scrub/rmap.c
index 8d49556..7970e73 100644
--- a/fs/xfs/scrub/rmap.c
+++ b/fs/xfs/scrub/rmap.c
@@ -159,3 +159,67 @@ xfs_scrub_rmapbt(
 	return xfs_scrub_btree(sc, sc->sa.rmap_cur, xfs_scrub_rmapbt_rec,
 			&oinfo, NULL);
 }
+
+/* xref check that the extent is owned by a given owner */
+static inline void
+xfs_scrub_xref_check_owner(
+	struct xfs_scrub_context	*sc,
+	struct xfs_btree_cur		**pcur,
+	xfs_agblock_t			bno,
+	xfs_extlen_t			len,
+	struct xfs_owner_info		*oinfo,
+	bool				fs_ok)
+{
+	bool				has_rmap;
+	int				error;
+
+	if (!(*pcur))
+		return;
+
+	error = xfs_rmap_record_exists(*pcur, bno, len, oinfo, &has_rmap);
+	if (xfs_scrub_should_xref(sc, &error, pcur) && has_rmap != fs_ok)
+		xfs_scrub_btree_xref_set_corrupt(sc, *pcur, 0);
+}
+
+/* xref check that the extent is owned by a given owner */
+void
+xfs_scrub_xref_owned_by(
+	struct xfs_scrub_context	*sc,
+	struct xfs_btree_cur		**pcur,
+	xfs_agblock_t			bno,
+	xfs_extlen_t			len,
+	struct xfs_owner_info		*oinfo)
+{
+	xfs_scrub_xref_check_owner(sc, pcur, bno, len, oinfo, true);
+}
+
+/* xref check that the extent is not owned by a given owner */
+void
+xfs_scrub_xref_not_owned_by(
+	struct xfs_scrub_context	*sc,
+	struct xfs_btree_cur		**pcur,
+	xfs_agblock_t			bno,
+	xfs_extlen_t			len,
+	struct xfs_owner_info		*oinfo)
+{
+	xfs_scrub_xref_check_owner(sc, pcur, bno, len, oinfo, false);
+}
+
+/* xref check that the extent has no reverse mapping at all */
+void
+xfs_scrub_xref_no_rmap(
+	struct xfs_scrub_context	*sc,
+	struct xfs_btree_cur		**pcur,
+	xfs_agblock_t			bno,
+	xfs_extlen_t			len)
+{
+	bool				has_rmap;
+	int				error;
+
+	if (!(*pcur))
+		return;
+
+	error = xfs_rmap_has_record(*pcur, bno, len, &has_rmap);
+	if (xfs_scrub_should_xref(sc, &error, pcur) && has_rmap)
+		xfs_scrub_btree_xref_set_corrupt(sc, *pcur, 0);
+}
diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h
index 768df35..4789dba 100644
--- a/fs/xfs/scrub/scrub.h
+++ b/fs/xfs/scrub/scrub.h
@@ -133,5 +133,14 @@ void xfs_scrub_xref_not_inodes(struct xfs_scrub_context *sc,
 void xfs_scrub_xref_are_inodes(struct xfs_scrub_context *sc,
 		struct xfs_btree_cur **pcur, xfs_agblock_t bno,
 		xfs_extlen_t len);
+void xfs_scrub_xref_owned_by(struct xfs_scrub_context *sc,
+		struct xfs_btree_cur **pcur, xfs_agblock_t bno,
+		xfs_extlen_t len, struct xfs_owner_info *oinfo);
+void xfs_scrub_xref_not_owned_by(struct xfs_scrub_context *sc,
+		struct xfs_btree_cur **pcur, xfs_agblock_t bno,
+		xfs_extlen_t len, struct xfs_owner_info *oinfo);
+void xfs_scrub_xref_no_rmap(struct xfs_scrub_context *sc,
+		struct xfs_btree_cur **pcur, xfs_agblock_t bno,
+		xfs_extlen_t len);
 
 #endif	/* __XFS_SCRUB_SCRUB_H__ */

[PATCH 12/15] xfs: cross-reference the rmapbt data with the refcountbt

[Darrick J. Wong]

From: Darrick J. Wong <darrick.wong@oracle.com>

Cross reference the refcount data with the rmap data to check that the
number of rmaps for a given block match the refcount of that block, and
that CoW blocks (which are owned entirely by the refcountbt) are tracked
as well.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/scrub/refcount.c |  315 +++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 313 insertions(+), 2 deletions(-)


diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c
index 8add281..6efae58 100644
--- a/fs/xfs/scrub/refcount.c
+++ b/fs/xfs/scrub/refcount.c
@@ -50,6 +50,274 @@ xfs_scrub_setup_ag_refcountbt(
 
 /* Reference count btree scrubber. */
 
+/*
+ * Confirming Reference Counts via Reverse Mappings
+ *
+ * We want to count the reverse mappings overlapping a refcount record
+ * (bno, len, refcount), allowing for the possibility that some of the
+ * overlap may come from smaller adjoining reverse mappings, while some
+ * comes from single extents which overlap the range entirely.  The
+ * outer loop is as follows:
+ *
+ * 1. For all reverse mappings overlapping the refcount extent,
+ *    a. If a given rmap completely overlaps, mark it as seen.
+ *    b. Otherwise, record the fragment for later processing.
+ *
+ * Once we've seen all the rmaps, we know that for all blocks in the
+ * refcount record we want to find $refcount owners and we've already
+ * visited $seen extents that overlap all the blocks.  Therefore, we
+ * need to find ($refcount - $seen) owners for every block in the
+ * extent; call that quantity $target_nr.  Proceed as follows:
+ *
+ * 2. Pull the first $target_nr fragments from the list; all of them
+ *    should start at or before the start of the extent.
+ *    Call this subset of fragments the working set.
+ * 3. Until there are no more unprocessed fragments,
+ *    a. Find the shortest fragments in the set and remove them.
+ *    b. Note the block number of the end of these fragments.
+ *    c. Pull the same number of fragments from the list.  All of these
+ *       fragments should start at the block number recorded in the
+ *       previous step.
+ *    d. Put those fragments in the set.
+ * 4. Check that there are $target_nr fragments remaining in the list,
+ *    and that they all end at or beyond the end of the refcount extent.
+ *
+ * If the refcount is correct, all the check conditions in the algorithm
+ * should always hold true.  If not, the refcount is incorrect.
+ */
+struct xfs_scrub_refcnt_frag {
+	struct list_head		list;
+	struct xfs_rmap_irec		rm;
+};
+
+struct xfs_scrub_refcnt_check {
+	struct xfs_scrub_context	*sc;
+	struct list_head		fragments;
+
+	/* refcount extent we're examining */
+	xfs_agblock_t			bno;
+	xfs_extlen_t			len;
+	xfs_nlink_t			refcount;
+
+	/* number of owners seen */
+	xfs_nlink_t			seen;
+};
+
+/*
+ * Decide if the given rmap is large enough that we can redeem it
+ * towards refcount verification now, or if it's a fragment, in
+ * which case we'll hang onto it in the hopes that we'll later
+ * discover that we've collected exactly the correct number of
+ * fragments as the refcountbt says we should have.
+ */
+STATIC int
+xfs_scrub_refcountbt_rmap_check(
+	struct xfs_btree_cur		*cur,
+	struct xfs_rmap_irec		*rec,
+	void				*priv)
+{
+	struct xfs_scrub_refcnt_check	*refchk = priv;
+	struct xfs_scrub_refcnt_frag	*frag;
+	xfs_agblock_t			rm_last;
+	xfs_agblock_t			rc_last;
+	int				error = 0;
+
+	if (xfs_scrub_should_terminate(refchk->sc, &error))
+		return error;
+
+	rm_last = rec->rm_startblock + rec->rm_blockcount - 1;
+	rc_last = refchk->bno + refchk->len - 1;
+
+	/* Confirm that a single-owner refc extent is a CoW stage. */
+	if (refchk->refcount == 1 && rec->rm_owner != XFS_RMAP_OWN_COW) {
+		xfs_scrub_btree_xref_set_corrupt(refchk->sc, cur, 0);
+		return 0;
+	}
+
+	if (rec->rm_startblock <= refchk->bno && rm_last >= rc_last) {
+		/*
+		 * The rmap overlaps the refcount record, so we can confirm
+		 * one refcount owner seen.
+		 */
+		refchk->seen++;
+	} else {
+		/*
+		 * This rmap covers only part of the refcount record, so
+		 * save the fragment for later processing.
+		 */
+		frag = kmem_alloc(sizeof(struct xfs_scrub_refcnt_frag),
+				KM_MAYFAIL | KM_NOFS);
+		if (!frag)
+			return -ENOMEM;
+		memcpy(&frag->rm, rec, sizeof(frag->rm));
+		list_add_tail(&frag->list, &refchk->fragments);
+	}
+
+	return 0;
+}
+
+/*
+ * Given a bunch of rmap fragments, iterate through them, keeping
+ * a running tally of the refcount.  If this ever deviates from
+ * what we expect (which is the refcountbt's refcount minus the
+ * number of extents that totally covered the refcountbt extent),
+ * we have a refcountbt error.
+ */
+STATIC void
+xfs_scrub_refcountbt_process_rmap_fragments(
+	struct xfs_scrub_refcnt_check	*refchk)
+{
+	struct list_head		worklist;
+	struct xfs_scrub_refcnt_frag	*frag;
+	struct xfs_scrub_refcnt_frag	*n;
+	xfs_agblock_t			bno;
+	xfs_agblock_t			rbno;
+	xfs_agblock_t			next_rbno;
+	xfs_nlink_t			nr;
+	xfs_nlink_t			target_nr;
+
+	target_nr = refchk->refcount - refchk->seen;
+	if (target_nr == 0)
+		return;
+
+	/*
+	 * There are (refchk->rc.rc_refcount - refchk->nr refcount)
+	 * references we haven't found yet.  Pull that many off the
+	 * fragment list and figure out where the smallest rmap ends
+	 * (and therefore the next rmap should start).  All the rmaps
+	 * we pull off should start at or before the beginning of the
+	 * refcount record's range.
+	 */
+	INIT_LIST_HEAD(&worklist);
+	rbno = NULLAGBLOCK;
+	nr = 1;
+
+	/* Find all the rmaps that start at or before the refc extent. */
+	list_for_each_entry_safe(frag, n, &refchk->fragments, list) {
+		if (frag->rm.rm_startblock > refchk->bno)
+			goto done;
+		bno = frag->rm.rm_startblock + frag->rm.rm_blockcount;
+		if (rbno > bno)
+			rbno = bno;
+		list_del(&frag->list);
+		list_add_tail(&frag->list, &worklist);
+		if (nr == target_nr)
+			break;
+		nr++;
+	}
+
+	/*
+	 * We should have found exactly $target_nr rmap fragments starting
+	 * at or before the refcount extent.
+	 */
+	if (nr != target_nr)
+		goto done;
+
+	while (!list_empty(&refchk->fragments)) {
+		/* Discard any fragments ending at rbno. */
+		nr = 0;
+		next_rbno = NULLAGBLOCK;
+		list_for_each_entry_safe(frag, n, &worklist, list) {
+			bno = frag->rm.rm_startblock + frag->rm.rm_blockcount;
+			if (bno != rbno) {
+				if (next_rbno > bno)
+					next_rbno = bno;
+				continue;
+			}
+			list_del(&frag->list);
+			kmem_free(frag);
+			nr++;
+		}
+
+		/* Empty list?  We're done. */
+		if (list_empty(&refchk->fragments))
+			break;
+
+		/* Try to add nr rmaps starting at rbno to the worklist. */
+		list_for_each_entry_safe(frag, n, &refchk->fragments, list) {
+			bno = frag->rm.rm_startblock + frag->rm.rm_blockcount;
+			if (frag->rm.rm_startblock != rbno)
+				goto done;
+			list_del(&frag->list);
+			list_add_tail(&frag->list, &worklist);
+			if (next_rbno > bno)
+				next_rbno = bno;
+			nr--;
+			if (nr == 0)
+				break;
+		}
+
+		rbno = next_rbno;
+	}
+
+	/*
+	 * Make sure the last extent we processed ends at or beyond
+	 * the end of the refcount extent.
+	 */
+	if (rbno < refchk->bno + refchk->len)
+		goto done;
+
+	/* Actually record us having seen the remaining refcount. */
+	refchk->seen = refchk->refcount;
+done:
+	/* Delete fragments and work list. */
+	list_for_each_entry_safe(frag, n, &worklist, list) {
+		list_del(&frag->list);
+		kmem_free(frag);
+	}
+	list_for_each_entry_safe(frag, n, &refchk->fragments, list) {
+		list_del(&frag->list);
+		kmem_free(frag);
+	}
+}
+
+/* Use the rmap entries covering this extent to verify the refcount. */
+STATIC void
+xfs_scrub_refcountbt_xref_rmap(
+	struct xfs_scrub_context	*sc,
+	xfs_agblock_t			bno,
+	xfs_extlen_t			len,
+	xfs_nlink_t			refcount)
+{
+	struct xfs_scrub_refcnt_check	refchk = {
+		.sc = sc,
+		.bno = bno,
+		.len = len,
+		.refcount = refcount,
+		.seen = 0,
+	};
+	struct xfs_rmap_irec		low;
+	struct xfs_rmap_irec		high;
+	struct xfs_scrub_refcnt_frag	*frag;
+	struct xfs_scrub_refcnt_frag	*n;
+	int				error;
+
+	if (!sc->sa.rmap_cur)
+		return;
+
+	/* Cross-reference with the rmapbt to confirm the refcount. */
+	memset(&low, 0, sizeof(low));
+	low.rm_startblock = bno;
+	memset(&high, 0xFF, sizeof(high));
+	high.rm_startblock = bno + len - 1;
+
+	INIT_LIST_HEAD(&refchk.fragments);
+	error = xfs_rmap_query_range(sc->sa.rmap_cur, &low, &high,
+			&xfs_scrub_refcountbt_rmap_check, &refchk);
+	if (!xfs_scrub_should_xref(sc, &error, &sc->sa.rmap_cur))
+		goto out_free;
+
+	xfs_scrub_refcountbt_process_rmap_fragments(&refchk);
+	if (refcount != refchk.seen)
+		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
+
+out_free:
+	list_for_each_entry_safe(frag, n, &refchk.fragments, list) {
+		list_del(&frag->list);
+		kmem_free(frag);
+	}
+}
+
 /* Cross-reference with the other btrees. */
 STATIC void
 xfs_scrub_refcountbt_xref(
@@ -61,6 +329,7 @@ xfs_scrub_refcountbt_xref(
 	xfs_scrub_xref_not_free(sc, &sc->sa.bno_cur, bno, len);
 	xfs_scrub_xref_not_inodes(sc, &sc->sa.ino_cur, bno, len);
 	xfs_scrub_xref_not_inodes(sc, &sc->sa.fino_cur, bno, len);
+	xfs_scrub_refcountbt_xref_rmap(sc, bno, len, refcount);
 }
 
 /* Scrub a refcountbt record. */
@@ -70,6 +339,7 @@ xfs_scrub_refcountbt_rec(
 	union xfs_btree_rec		*rec)
 {
 	struct xfs_mount		*mp = bs->cur->bc_mp;
+	xfs_agblock_t			*cow_blocks = bs->private;
 	xfs_agnumber_t			agno = bs->cur->bc_private.a.agno;
 	xfs_agblock_t			bno;
 	xfs_extlen_t			len;
@@ -85,6 +355,8 @@ xfs_scrub_refcountbt_rec(
 	has_cowflag = (bno & XFS_REFC_COW_START);
 	if ((refcount == 1 && !has_cowflag) || (refcount != 1 && has_cowflag))
 		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+	if (has_cowflag)
+		(*cow_blocks) += len;
 
 	/* Check the extent. */
 	bno &= ~XFS_REFC_COW_START;
@@ -104,14 +376,53 @@ xfs_scrub_refcountbt_rec(
 	return error;
 }
 
+/* Make sure we have as many refc blocks as the rmap says. */
+STATIC void
+xfs_scrub_refcount_xref_rmap(
+	struct xfs_scrub_context	*sc,
+	struct xfs_owner_info		*oinfo,
+	xfs_filblks_t			cow_blocks)
+{
+	xfs_extlen_t			refcbt_blocks = 0;
+	xfs_filblks_t			blocks;
+	int				error;
+
+	/* Check that we saw as many refcbt blocks as the rmap knows about. */
+	error = xfs_btree_count_blocks(sc->sa.refc_cur, &refcbt_blocks);
+	if (!xfs_scrub_btree_process_error(sc, sc->sa.refc_cur, 0, &error))
+		return;
+	error = xfs_scrub_count_rmap_ownedby_ag(sc, sc->sa.rmap_cur, oinfo,
+			&blocks);
+	if (xfs_scrub_should_xref(sc, &error, &sc->sa.rmap_cur) &&
+	    blocks != refcbt_blocks)
+		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
+
+	/* Check that we saw as many cow blocks as the rmap knows about. */
+	xfs_rmap_ag_owner(oinfo, XFS_RMAP_OWN_COW);
+	error = xfs_scrub_count_rmap_ownedby_ag(sc, sc->sa.rmap_cur, oinfo,
+			&blocks);
+	if (xfs_scrub_should_xref(sc, &error, &sc->sa.rmap_cur) &&
+	    blocks != cow_blocks)
+		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
+}
+
 /* Scrub the refcount btree for some AG. */
 int
 xfs_scrub_refcountbt(
 	struct xfs_scrub_context	*sc)
 {
 	struct xfs_owner_info		oinfo;
+	xfs_agblock_t			cow_blocks = 0;
+	int				error;
 
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_REFC);
-	return xfs_scrub_btree(sc, sc->sa.refc_cur, xfs_scrub_refcountbt_rec,
-			&oinfo, NULL);
+	error = xfs_scrub_btree(sc, sc->sa.refc_cur, xfs_scrub_refcountbt_rec,
+			&oinfo, &cow_blocks);
+	if (error)
+		return error;
+
+	if (sc->sa.rmap_cur)
+		xfs_scrub_refcount_xref_rmap(sc, &oinfo, cow_blocks);
+
+	return error;
 }

[PATCH 13/15] xfs: cross-reference refcount btree during scrub

[Darrick J. Wong]

From: Darrick J. Wong <darrick.wong@oracle.com>

During metadata btree scrub, we should cross-reference with the
reference counts.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/scrub/agheader.c |   14 ++++++++
 fs/xfs/scrub/alloc.c    |    1 +
 fs/xfs/scrub/bmap.c     |   79 +++++++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/ialloc.c   |    1 +
 fs/xfs/scrub/inode.c    |    1 +
 fs/xfs/scrub/refcount.c |   67 ++++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/rmap.c     |   40 ++++++++++++++++++++++++
 fs/xfs/scrub/scrub.h    |    6 ++++
 8 files changed, 209 insertions(+)


diff --git a/fs/xfs/scrub/agheader.c b/fs/xfs/scrub/agheader.c
index 3e5bb78..1503cbc 100644
--- a/fs/xfs/scrub/agheader.c
+++ b/fs/xfs/scrub/agheader.c
@@ -125,6 +125,7 @@ xfs_scrub_superblock_xref(
 	xfs_scrub_xref_not_inodes(sc, &sc->sa.fino_cur, bno, 1);
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_FS);
 	xfs_scrub_xref_owned_by(sc, &sc->sa.rmap_cur, bno, 1, &oinfo);
+	xfs_scrub_xref_not_shared(sc, &sc->sa.refc_cur, bno, 1);
 
 	/* scrub teardown will take care of sc->sa for us */
 }
@@ -534,6 +535,16 @@ xfs_scrub_agf_xref(
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_FS);
 	xfs_scrub_xref_owned_by(sc, &sc->sa.rmap_cur, bno, 1, &oinfo);
 	xfs_scrub_agf_xref_btreeblks(sc);
+	xfs_scrub_xref_not_shared(sc, &sc->sa.refc_cur, bno, 1);
+
+	/* Check agf_refcount_blocks against tree size */
+	pcur = &sc->sa.refc_cur;
+	if (*pcur) {
+		error = xfs_btree_count_blocks(*pcur, &blocks);
+		if (xfs_scrub_should_xref(sc, &error, pcur) &&
+		    blocks != be32_to_cpu(agf->agf_refcount_blocks))
+			xfs_scrub_block_xref_set_corrupt(sc, sc->sa.agf_bp);
+	}
 
 	/* scrub teardown will take care of sc->sa for us */
 }
@@ -644,6 +655,7 @@ xfs_scrub_agfl_block_xref(
 	xfs_scrub_xref_not_inodes(sc, &sc->sa.ino_cur, bno, 1);
 	xfs_scrub_xref_not_inodes(sc, &sc->sa.fino_cur, bno, 1);
 	xfs_scrub_xref_owned_by(sc, &sc->sa.rmap_cur, bno, 1, oinfo);
+	xfs_scrub_xref_not_shared(sc, &sc->sa.refc_cur, bno, 1);
 }
 
 /* Scrub an AGFL block. */
@@ -703,6 +715,7 @@ xfs_scrub_agfl_xref(
 	xfs_scrub_xref_not_inodes(sc, &sc->sa.fino_cur, bno, 1);
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_FS);
 	xfs_scrub_xref_owned_by(sc, &sc->sa.rmap_cur, bno, 1, &oinfo);
+	xfs_scrub_xref_not_shared(sc, &sc->sa.refc_cur, bno, 1);
 
 	/*
 	 * Scrub teardown will take care of sc->sa for us.  Leave sc->sa
@@ -814,6 +827,7 @@ xfs_scrub_agi_xref(
 
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_FS);
 	xfs_scrub_xref_owned_by(sc, &sc->sa.rmap_cur, bno, 1, &oinfo);
+	xfs_scrub_xref_not_shared(sc, &sc->sa.refc_cur, bno, 1);
 
 	/* scrub teardown will take care of sc->sa for us */
 }
diff --git a/fs/xfs/scrub/alloc.c b/fs/xfs/scrub/alloc.c
index a4046c1..d1dd9b7 100644
--- a/fs/xfs/scrub/alloc.c
+++ b/fs/xfs/scrub/alloc.c
@@ -98,6 +98,7 @@ xfs_scrub_allocbt_xref(
 	xfs_scrub_xref_not_inodes(sc, &sc->sa.ino_cur, bno, len);
 	xfs_scrub_xref_not_inodes(sc, &sc->sa.fino_cur, bno, len);
 	xfs_scrub_xref_no_rmap(sc, &sc->sa.rmap_cur, bno, len);
+	xfs_scrub_xref_not_shared(sc, &sc->sa.refc_cur, bno, len);
 }
 
 /* Scrub a bnobt/cntbt record. */
diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c
index f408193..2b99f06 100644
--- a/fs/xfs/scrub/bmap.c
+++ b/fs/xfs/scrub/bmap.c
@@ -37,6 +37,7 @@
 #include "xfs_bmap_btree.h"
 #include "xfs_rmap.h"
 #include "xfs_alloc.h"
+#include "xfs_refcount.h"
 #include "scrub/xfs_scrub.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
@@ -200,6 +201,73 @@ xfs_scrub_bmap_xref_rmap(
 				irec->br_startoff);
 }
 
+/* Make sure the refcount records match this data fork extent. */
+STATIC void
+xfs_scrub_bmap_xref_refcount_data(
+	struct xfs_scrub_bmap_info	*info,
+	struct xfs_scrub_ag		*sa,
+	struct xfs_bmbt_irec		*irec,
+	xfs_fsblock_t			bno)
+{
+	xfs_agblock_t			fbno;
+	xfs_extlen_t			flen;
+	int				error;
+
+	if (!sa->refc_cur)
+		return;
+
+	/* If this is shared, the inode flag must be set. */
+	error = xfs_refcount_find_shared(sa->refc_cur, bno,
+			irec->br_blockcount, &fbno, &flen, false);
+	if (!xfs_scrub_should_xref(info->sc, &error, &sa->refc_cur))
+		return;
+
+	if (flen != 0 && !xfs_is_reflink_inode(info->sc->ip))
+		xfs_scrub_fblock_xref_set_corrupt(info->sc, info->whichfork,
+				irec->br_startoff);
+}
+
+/* Make sure the refcount records match this attr fork extent. */
+STATIC void
+xfs_scrub_bmap_xref_refcount_attr(
+	struct xfs_scrub_bmap_info	*info,
+	struct xfs_scrub_ag		*sa,
+	struct xfs_bmbt_irec		*irec,
+	xfs_fsblock_t			bno)
+{
+	xfs_agblock_t			fbno;
+	xfs_extlen_t			flen;
+	int				error;
+
+	if (!sa->refc_cur)
+		return;
+
+	/* No shared attr fork extents */
+	error = xfs_refcount_find_shared(sa->refc_cur, bno,
+			irec->br_blockcount, &fbno, &flen, false);
+	if (!xfs_scrub_should_xref(info->sc, &error, &sa->refc_cur))
+		return;
+
+	if (flen != 0)
+		xfs_scrub_fblock_xref_set_corrupt(info->sc, info->whichfork,
+				irec->br_startoff);
+}
+
+/* Make sure the refcount records match this CoW fork extent. */
+STATIC void
+xfs_scrub_bmap_xref_refcount_cow(
+	struct xfs_scrub_bmap_info	*info,
+	struct xfs_scrub_ag		*sa,
+	struct xfs_bmbt_irec		*irec,
+	xfs_fsblock_t			bno)
+{
+	if (!sa->refc_cur)
+		return;
+
+	xfs_scrub_xref_has_cow_staging(info->sc, &sa->refc_cur, bno,
+			irec->br_blockcount);
+}
+
 /* Cross-reference a single rtdev extent record. */
 STATIC void
 xfs_scrub_bmap_rt_extent_xref(
@@ -238,6 +306,17 @@ xfs_scrub_bmap_extent_xref(
 	xfs_scrub_xref_not_inodes(info->sc, &sa.ino_cur, agbno, len);
 	xfs_scrub_xref_not_inodes(info->sc, &sa.fino_cur, agbno, len);
 	xfs_scrub_bmap_xref_rmap(info, &sa, irec, agbno);
+	switch (info->whichfork) {
+	case XFS_DATA_FORK:
+		xfs_scrub_bmap_xref_refcount_data(info, &sa, irec, agbno);
+		break;
+	case XFS_ATTR_FORK:
+		xfs_scrub_bmap_xref_refcount_attr(info, &sa, irec, agbno);
+		break;
+	case XFS_COW_FORK:
+		xfs_scrub_bmap_xref_refcount_cow(info, &sa, irec, agbno);
+		break;
+	}
 
 	xfs_scrub_ag_free(info->sc, &sa);
 }
diff --git a/fs/xfs/scrub/ialloc.c b/fs/xfs/scrub/ialloc.c
index d4b7f13..367dd5f 100644
--- a/fs/xfs/scrub/ialloc.c
+++ b/fs/xfs/scrub/ialloc.c
@@ -94,6 +94,7 @@ xfs_scrub_iallocbt_chunk_xref(
 
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_INODES);
 	xfs_scrub_xref_owned_by(sc, &sc->sa.rmap_cur, bno, len, &oinfo);
+	xfs_scrub_xref_not_shared(sc, &sc->sa.refc_cur, bno, len);
 }
 
 /* Is this chunk worth checking? */
diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c
index 830d44a..6ea2c96 100644
--- a/fs/xfs/scrub/inode.c
+++ b/fs/xfs/scrub/inode.c
@@ -603,6 +603,7 @@ xfs_scrub_inode_xref(
 	xfs_scrub_xref_are_inodes(sc, &sc->sa.fino_cur, agbno, 1);
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_INODES);
 	xfs_scrub_xref_owned_by(sc, &sc->sa.rmap_cur, agbno, 1, &oinfo);
+	xfs_scrub_xref_not_shared(sc, &sc->sa.refc_cur, agbno, 1);
 
 	xfs_scrub_ag_free(sc, &sa);
 }
diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c
index 6efae58..dd54435 100644
--- a/fs/xfs/scrub/refcount.c
+++ b/fs/xfs/scrub/refcount.c
@@ -31,6 +31,7 @@
 #include "xfs_sb.h"
 #include "xfs_alloc.h"
 #include "xfs_rmap.h"
+#include "xfs_refcount.h"
 #include "scrub/xfs_scrub.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
@@ -426,3 +427,69 @@ xfs_scrub_refcountbt(
 
 	return error;
 }
+
+/* xref check that a cow staging extent is marked in the refcountbt. */
+void
+xfs_scrub_xref_has_cow_staging(
+	struct xfs_scrub_context	*sc,
+	struct xfs_btree_cur		**pcur,
+	xfs_agblock_t			bno,
+	xfs_extlen_t			len)
+{
+	struct xfs_refcount_irec	rc;
+	bool				has_cowflag;
+	int				has_refcount;
+	int				error;
+
+	if (!(*pcur))
+		return;
+
+	/* Find the CoW staging extent. */
+	error = xfs_refcount_lookup_le(*pcur, bno + XFS_REFC_COW_START,
+			&has_refcount);
+	if (!xfs_scrub_should_xref(sc, &error, pcur))
+		return;
+	if (!has_refcount) {
+		xfs_scrub_btree_xref_set_corrupt(sc, *pcur, 0);
+		return;
+	}
+
+	error = xfs_refcount_get_rec(*pcur, &rc, &has_refcount);
+	if (!xfs_scrub_should_xref(sc, &error, pcur))
+		return;
+	if (!has_refcount) {
+		xfs_scrub_btree_xref_set_corrupt(sc, *pcur, 0);
+		return;
+	}
+
+	/* CoW flag must be set, refcount must be 1. */
+	has_cowflag = (rc.rc_startblock & XFS_REFC_COW_START);
+	if (!has_cowflag || rc.rc_refcount != 1)
+		xfs_scrub_btree_xref_set_corrupt(sc, *pcur, 0);
+
+	/* Must be at least as long as what was passed in */
+	if (rc.rc_blockcount < len)
+		xfs_scrub_btree_xref_set_corrupt(sc, *pcur, 0);
+}
+
+/*
+ * xref check that the extent is not shared.  Only file data blocks
+ * can have multiple owners.
+ */
+void
+xfs_scrub_xref_not_shared(
+	struct xfs_scrub_context	*sc,
+	struct xfs_btree_cur		**pcur,
+	xfs_agblock_t			bno,
+	xfs_extlen_t			len)
+{
+	bool				shared;
+	int				error;
+
+	if (!(*pcur))
+		return;
+
+	error = xfs_refcount_has_record(*pcur, bno, len, &shared);
+	if (xfs_scrub_should_xref(sc, &error, pcur) && shared)
+		xfs_scrub_btree_xref_set_corrupt(sc, *pcur, 0);
+}
diff --git a/fs/xfs/scrub/rmap.c b/fs/xfs/scrub/rmap.c
index 7970e73..fee31e9 100644
--- a/fs/xfs/scrub/rmap.c
+++ b/fs/xfs/scrub/rmap.c
@@ -32,6 +32,7 @@
 #include "xfs_alloc.h"
 #include "xfs_ialloc.h"
 #include "xfs_rmap.h"
+#include "xfs_refcount.h"
 #include "scrub/xfs_scrub.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
@@ -51,6 +52,43 @@ xfs_scrub_setup_ag_rmapbt(
 
 /* Reverse-mapping scrubber. */
 
+/* Cross-reference a rmap against the refcount btree. */
+STATIC void
+xfs_scrub_rmapbt_xref_refc(
+	struct xfs_scrub_context	*sc,
+	struct xfs_btree_cur		**pcur,
+	struct xfs_rmap_irec		*irec)
+{
+	xfs_agblock_t			fbno;
+	xfs_extlen_t			flen;
+	bool				non_inode;
+	bool				is_bmbt;
+	bool				is_attr;
+	bool				is_unwritten;
+	int				error;
+
+	if (!(*pcur))
+		return;
+
+	if (irec->rm_owner == XFS_RMAP_OWN_COW) {
+		xfs_scrub_xref_has_cow_staging(sc, pcur, irec->rm_startblock,
+				irec->rm_blockcount);
+		return;
+	}
+
+	non_inode = XFS_RMAP_NON_INODE_OWNER(irec->rm_owner);
+	is_bmbt = irec->rm_flags & XFS_RMAP_BMBT_BLOCK;
+	is_attr = irec->rm_flags & XFS_RMAP_ATTR_FORK;
+	is_unwritten = irec->rm_flags & XFS_RMAP_UNWRITTEN;
+
+	/* If this is shared, must be a data fork extent. */
+	error = xfs_refcount_find_shared(*pcur, irec->rm_startblock,
+			irec->rm_blockcount, &fbno, &flen, false);
+	if (xfs_scrub_should_xref(sc, &error, pcur) &&
+	    flen != 0 && (non_inode || is_attr || is_bmbt || is_unwritten))
+		xfs_scrub_btree_xref_set_corrupt(sc, *pcur, 0);
+}
+
 /* Cross-reference with the other btrees. */
 STATIC void
 xfs_scrub_rmapbt_xref(
@@ -67,6 +105,8 @@ xfs_scrub_rmapbt_xref(
 		xfs_scrub_xref_not_inodes(sc, &sc->sa.ino_cur, bno, len);
 		xfs_scrub_xref_not_inodes(sc, &sc->sa.fino_cur, bno, len);
 	}
+
+	xfs_scrub_rmapbt_xref_refc(sc, &sc->sa.refc_cur, irec);
 }
 
 /* Scrub an rmapbt record. */
diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h
index 4789dba..83cdcd8 100644
--- a/fs/xfs/scrub/scrub.h
+++ b/fs/xfs/scrub/scrub.h
@@ -142,5 +142,11 @@ void xfs_scrub_xref_not_owned_by(struct xfs_scrub_context *sc,
 void xfs_scrub_xref_no_rmap(struct xfs_scrub_context *sc,
 		struct xfs_btree_cur **pcur, xfs_agblock_t bno,
 		xfs_extlen_t len);
+void xfs_scrub_xref_has_cow_staging(struct xfs_scrub_context *sc,
+		struct xfs_btree_cur **pcur, xfs_agblock_t bno,
+		xfs_extlen_t len);
+void xfs_scrub_xref_not_shared(struct xfs_scrub_context *sc,
+		struct xfs_btree_cur **pcur, xfs_agblock_t bno,
+		xfs_extlen_t len);
 
 #endif	/* __XFS_SCRUB_SCRUB_H__ */

[PATCH 14/15] xfs: cross-reference the realtime bitmap

[Darrick J. Wong]

From: Darrick J. Wong <darrick.wong@oracle.com>

While we're scrubbing various btrees, cross-reference the records
with the other metadata.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_rtbitmap.c |   30 ++++++++++++++++++++++++++++++
 fs/xfs/scrub/bmap.c          |    2 ++
 fs/xfs/scrub/rtbitmap.c      |   20 ++++++++++++++++++++
 fs/xfs/scrub/scrub.h         |    6 ++++++
 fs/xfs/xfs_rtalloc.h         |    4 ++++
 5 files changed, 62 insertions(+)


diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c
index 3fb29a5..a3f25a2 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.c
+++ b/fs/xfs/libxfs/xfs_rtbitmap.c
@@ -1097,3 +1097,33 @@ xfs_verify_rtbno(
 {
 	return rtbno < mp->m_sb.sb_rblocks;
 }
+
+/* Is the given extent all free? */
+int
+xfs_rtalloc_extent_is_free(
+	struct xfs_mount		*mp,
+	struct xfs_trans		*tp,
+	xfs_rtblock_t			start,
+	xfs_rtblock_t			len,
+	bool				*is_free)
+{
+	xfs_rtblock_t			end;
+	xfs_extlen_t			clen;
+	int				matches;
+	int				error;
+
+	*is_free = false;
+	while (len) {
+		clen = len > ~0U ? ~0U : len;
+		error = xfs_rtcheck_range(mp, tp, start, clen, 1, &end,
+				&matches);
+		if (error || !matches || end < start + clen)
+			return error;
+
+		len -= end - start;
+		start = end + 1;
+	}
+
+	*is_free = true;
+	return error;
+}
diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c
index 2b99f06..1e5ab53 100644
--- a/fs/xfs/scrub/bmap.c
+++ b/fs/xfs/scrub/bmap.c
@@ -276,6 +276,8 @@ xfs_scrub_bmap_rt_extent_xref(
 	struct xfs_btree_cur		*cur,
 	struct xfs_bmbt_irec		*irec)
 {
+	xfs_scrub_xref_not_rtfree(info->sc, irec->br_startblock,
+			irec->br_blockcount);
 }
 
 /* Cross-reference a single datadev extent record. */
diff --git a/fs/xfs/scrub/rtbitmap.c b/fs/xfs/scrub/rtbitmap.c
index 6860d5d..bdf1484 100644
--- a/fs/xfs/scrub/rtbitmap.c
+++ b/fs/xfs/scrub/rtbitmap.c
@@ -98,3 +98,23 @@ xfs_scrub_rtsummary(
 	/* XXX: implement this some day */
 	return -ENOENT;
 }
+
+
+/* xref check that the extent is not free in the rtbitmap */
+void
+xfs_scrub_xref_not_rtfree(
+	struct xfs_scrub_context	*sc,
+	xfs_fsblock_t			fsbno,
+	xfs_fsblock_t			len)
+{
+	bool				is_free;
+	int				error;
+
+	xfs_ilock(sc->mp->m_rbmip, XFS_ILOCK_SHARED | XFS_ILOCK_RTBITMAP);
+	error = xfs_rtalloc_extent_is_free(sc->mp, sc->tp, fsbno, len,
+			&is_free);
+	if (xfs_scrub_should_xref(sc, &error, NULL) && is_free)
+		xfs_scrub_ino_xref_set_corrupt(sc, sc->mp->m_rbmip->i_ino,
+				NULL);
+	xfs_iunlock(sc->mp->m_rbmip, XFS_ILOCK_SHARED | XFS_ILOCK_RTBITMAP);
+}
diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h
index 83cdcd8..91cc094 100644
--- a/fs/xfs/scrub/scrub.h
+++ b/fs/xfs/scrub/scrub.h
@@ -148,5 +148,11 @@ void xfs_scrub_xref_has_cow_staging(struct xfs_scrub_context *sc,
 void xfs_scrub_xref_not_shared(struct xfs_scrub_context *sc,
 		struct xfs_btree_cur **pcur, xfs_agblock_t bno,
 		xfs_extlen_t len);
+#ifdef CONFIG_XFS_RT
+void xfs_scrub_xref_not_rtfree(struct xfs_scrub_context *sc,
+		xfs_fsblock_t fsbno, xfs_fsblock_t len);
+#else
+# define xfs_scrub_xref_not_rtfree(sc, fsbno, len)	do { } while (0)
+#endif
 
 #endif	/* __XFS_SCRUB_SCRUB_H__ */
diff --git a/fs/xfs/xfs_rtalloc.h b/fs/xfs/xfs_rtalloc.h
index 3f30f84..540d506 100644
--- a/fs/xfs/xfs_rtalloc.h
+++ b/fs/xfs/xfs_rtalloc.h
@@ -139,6 +139,9 @@ int xfs_rtalloc_query_all(struct xfs_trans *tp,
 			  xfs_rtalloc_query_range_fn fn,
 			  void *priv);
 bool xfs_verify_rtbno(struct xfs_mount *mp, xfs_rtblock_t rtbno);
+int xfs_rtalloc_extent_is_free(struct xfs_mount *mp, struct xfs_trans *tp,
+			       xfs_rtblock_t start, xfs_rtblock_t len,
+			       bool *is_free);
 #else
 # define xfs_rtallocate_extent(t,b,min,max,l,f,p,rb)    (ENOSYS)
 # define xfs_rtfree_extent(t,b,l)                       (ENOSYS)
@@ -148,6 +151,7 @@ bool xfs_verify_rtbno(struct xfs_mount *mp, xfs_rtblock_t rtbno);
 # define xfs_rtalloc_query_all(t,f,p)                   (ENOSYS)
 # define xfs_rtbuf_get(m,t,b,i,p)                       (ENOSYS)
 # define xfs_verify_rtbno(m, r)			(false)
+# define xfs_rtalloc_extent_is_free(m,t,s,l,i)          (ENOSYS)
 static inline int		/* error */
 xfs_rtmount_init(
 	xfs_mount_t	*mp)	/* file system mount structure */

[PATCH 15/15] xfs: cross-reference the block mappings when possible

[Darrick J. Wong]

From: Darrick J. Wong <darrick.wong@oracle.com>

Use an inode's block mappings to cross-reference inode block counters.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/scrub/inode.c |   34 ++++++++++++++++++++++++++++++++++
 1 file changed, 34 insertions(+)


diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c
index 6ea2c96..18588fb 100644
--- a/fs/xfs/scrub/inode.c
+++ b/fs/xfs/scrub/inode.c
@@ -37,6 +37,8 @@
 #include "xfs_da_format.h"
 #include "xfs_reflink.h"
 #include "xfs_rmap.h"
+#include "xfs_bmap.h"
+#include "xfs_bmap_util.h"
 #include "scrub/xfs_scrub.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
@@ -578,6 +580,37 @@ xfs_scrub_inode_map_raw(
 	return error;
 }
 
+/* Cross reference the inode fields with the forks. */
+STATIC void
+xfs_scrub_inode_xref_bmap(
+	struct xfs_scrub_context	*sc,
+	struct xfs_dinode		*dip)
+{
+	xfs_extnum_t			nextents;
+	xfs_filblks_t			count;
+	xfs_filblks_t			acount;
+	int				error;
+
+	/* Walk all the extents to check nextents/naextents/nblocks. */
+	error = xfs_bmap_count_blocks(sc->tp, sc->ip, XFS_DATA_FORK,
+			&nextents, &count);
+	if (!xfs_scrub_should_xref(sc, &error, NULL))
+		return;
+	if (nextents < be32_to_cpu(dip->di_nextents))
+		xfs_scrub_ino_xref_set_corrupt(sc, sc->ip->i_ino, NULL);
+
+	error = xfs_bmap_count_blocks(sc->tp, sc->ip, XFS_ATTR_FORK,
+			&nextents, &acount);
+	if (!xfs_scrub_should_xref(sc, &error, NULL))
+		return;
+	if (nextents != be16_to_cpu(dip->di_anextents))
+		xfs_scrub_ino_xref_set_corrupt(sc, sc->ip->i_ino, NULL);
+
+	/* Check nblocks against the inode. */
+	if (count + acount != be64_to_cpu(dip->di_nblocks))
+		xfs_scrub_ino_xref_set_corrupt(sc, sc->ip->i_ino, NULL);
+}
+
 /* Cross-reference with the other btrees. */
 STATIC void
 xfs_scrub_inode_xref(
@@ -604,6 +637,7 @@ xfs_scrub_inode_xref(
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_INODES);
 	xfs_scrub_xref_owned_by(sc, &sc->sa.rmap_cur, agbno, 1, &oinfo);
 	xfs_scrub_xref_not_shared(sc, &sc->sa.refc_cur, agbno, 1);
+	xfs_scrub_inode_xref_bmap(sc, dip);
 
 	xfs_scrub_ag_free(sc, &sa);
 }