From c13418e8eb375872ad297aeec5fa26277febc155 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Tue, 11 Apr 2023 18:59:54 -0700
Subject: xfs: give xfs_rmap_intent its own perag reference

Give the xfs_rmap_intent a passive reference to the perag structure
data.  This reference will be used to enable scrub intent draining
functionality in subsequent patches.  The space we're (reverse) mapping
is already allocated, so we need to be able to operate even if the AG is
being shrunk or offlined.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
---
 fs/xfs/libxfs/xfs_rmap.c | 29 +++++++++++------------------
 1 file changed, 11 insertions(+), 18 deletions(-)

(limited to 'fs/xfs/libxfs/xfs_rmap.c')

diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c
index df720041cd3d..c2624d11f041 100644
--- a/fs/xfs/libxfs/xfs_rmap.c
+++ b/fs/xfs/libxfs/xfs_rmap.c
@@ -2394,7 +2394,6 @@ xfs_rmap_finish_one(
 	struct xfs_btree_cur		**pcur)
 {
 	struct xfs_mount		*mp = tp->t_mountp;
-	struct xfs_perag		*pag;
 	struct xfs_btree_cur		*rcur;
 	struct xfs_buf			*agbp = NULL;
 	int				error = 0;
@@ -2402,26 +2401,22 @@ xfs_rmap_finish_one(
 	xfs_agblock_t			bno;
 	bool				unwritten;
 
-	pag = xfs_perag_get(mp, XFS_FSB_TO_AGNO(mp, ri->ri_bmap.br_startblock));
 	bno = XFS_FSB_TO_AGBNO(mp, ri->ri_bmap.br_startblock);
 
-	trace_xfs_rmap_deferred(mp, pag->pag_agno, ri->ri_type, bno,
+	trace_xfs_rmap_deferred(mp, ri->ri_pag->pag_agno, ri->ri_type, bno,
 			ri->ri_owner, ri->ri_whichfork,
 			ri->ri_bmap.br_startoff, ri->ri_bmap.br_blockcount,
 			ri->ri_bmap.br_state);
 
-	if (XFS_TEST_ERROR(false, mp, XFS_ERRTAG_RMAP_FINISH_ONE)) {
-		error = -EIO;
-		goto out_drop;
-	}
-
+	if (XFS_TEST_ERROR(false, mp, XFS_ERRTAG_RMAP_FINISH_ONE))
+		return -EIO;
 
 	/*
 	 * If we haven't gotten a cursor or the cursor AG doesn't match
 	 * the startblock, get one now.
 	 */
 	rcur = *pcur;
-	if (rcur != NULL && rcur->bc_ag.pag != pag) {
+	if (rcur != NULL && rcur->bc_ag.pag != ri->ri_pag) {
 		xfs_rmap_finish_one_cleanup(tp, rcur, 0);
 		rcur = NULL;
 		*pcur = NULL;
@@ -2432,15 +2427,13 @@ xfs_rmap_finish_one(
 		 * rmapbt, because a shape change could cause us to
 		 * allocate blocks.
 		 */
-		error = xfs_free_extent_fix_freelist(tp, pag, &agbp);
+		error = xfs_free_extent_fix_freelist(tp, ri->ri_pag, &agbp);
 		if (error)
-			goto out_drop;
-		if (XFS_IS_CORRUPT(tp->t_mountp, !agbp)) {
-			error = -EFSCORRUPTED;
-			goto out_drop;
-		}
+			return error;
+		if (XFS_IS_CORRUPT(tp->t_mountp, !agbp))
+			return -EFSCORRUPTED;
 
-		rcur = xfs_rmapbt_init_cursor(mp, tp, agbp, pag);
+		rcur = xfs_rmapbt_init_cursor(mp, tp, agbp, ri->ri_pag);
 	}
 	*pcur = rcur;
 
@@ -2480,8 +2473,7 @@ xfs_rmap_finish_one(
 		ASSERT(0);
 		error = -EFSCORRUPTED;
 	}
-out_drop:
-	xfs_perag_put(pag);
+
 	return error;
 }
 
@@ -2526,6 +2518,7 @@ __xfs_rmap_add(
 	ri->ri_whichfork = whichfork;
 	ri->ri_bmap = *bmap;
 
+	xfs_rmap_update_get_group(tp->t_mountp, ri);
 	xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_RMAP, &ri->ri_list);
 }
 
-- 
cgit 


From 39ab26d59f039c6190bbaa8118a8f0ffed84492a Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Tue, 11 Apr 2023 19:00:02 -0700
Subject: xfs: return a failure address from xfs_rmap_irec_offset_unpack

Currently, xfs_rmap_irec_offset_unpack returns only 0 or -EFSCORRUPTED.
Change this function to return the code address of a failed conversion
in preparation for the next patch, which standardizes localized record
checking and reporting code.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
---
 fs/xfs/libxfs/xfs_rmap.c |  9 ++++-----
 fs/xfs/libxfs/xfs_rmap.h |  9 +++++----
 fs/xfs/scrub/rmap.c      | 11 +++++------
 3 files changed, 14 insertions(+), 15 deletions(-)

(limited to 'fs/xfs/libxfs/xfs_rmap.c')

diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c
index c2624d11f041..830b38337cd5 100644
--- a/fs/xfs/libxfs/xfs_rmap.c
+++ b/fs/xfs/libxfs/xfs_rmap.c
@@ -193,7 +193,7 @@ done:
 }
 
 /* Convert an internal btree record to an rmap record. */
-int
+xfs_failaddr_t
 xfs_rmap_btrec_to_irec(
 	const union xfs_btree_rec	*rec,
 	struct xfs_rmap_irec		*irec)
@@ -2320,11 +2320,10 @@ xfs_rmap_query_range_helper(
 {
 	struct xfs_rmap_query_range_info	*query = priv;
 	struct xfs_rmap_irec			irec;
-	int					error;
 
-	error = xfs_rmap_btrec_to_irec(rec, &irec);
-	if (error)
-		return error;
+	if (xfs_rmap_btrec_to_irec(rec, &irec) != NULL)
+		return -EFSCORRUPTED;
+
 	return query->fn(cur, &irec, query->priv);
 }
 
diff --git a/fs/xfs/libxfs/xfs_rmap.h b/fs/xfs/libxfs/xfs_rmap.h
index 1472ae570a8a..6a08c403e8b7 100644
--- a/fs/xfs/libxfs/xfs_rmap.h
+++ b/fs/xfs/libxfs/xfs_rmap.h
@@ -62,13 +62,14 @@ xfs_rmap_irec_offset_pack(
 	return x;
 }
 
-static inline int
+static inline xfs_failaddr_t
 xfs_rmap_irec_offset_unpack(
 	__u64			offset,
 	struct xfs_rmap_irec	*irec)
 {
 	if (offset & ~(XFS_RMAP_OFF_MASK | XFS_RMAP_OFF_FLAGS))
-		return -EFSCORRUPTED;
+		return __this_address;
+
 	irec->rm_offset = XFS_RMAP_OFF(offset);
 	irec->rm_flags = 0;
 	if (offset & XFS_RMAP_OFF_ATTR_FORK)
@@ -77,7 +78,7 @@ xfs_rmap_irec_offset_unpack(
 		irec->rm_flags |= XFS_RMAP_BMBT_BLOCK;
 	if (offset & XFS_RMAP_OFF_UNWRITTEN)
 		irec->rm_flags |= XFS_RMAP_UNWRITTEN;
-	return 0;
+	return NULL;
 }
 
 static inline void
@@ -192,7 +193,7 @@ int xfs_rmap_lookup_le_range(struct xfs_btree_cur *cur, xfs_agblock_t bno,
 int xfs_rmap_compare(const struct xfs_rmap_irec *a,
 		const struct xfs_rmap_irec *b);
 union xfs_btree_rec;
-int xfs_rmap_btrec_to_irec(const union xfs_btree_rec *rec,
+xfs_failaddr_t xfs_rmap_btrec_to_irec(const 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);
diff --git a/fs/xfs/scrub/rmap.c b/fs/xfs/scrub/rmap.c
index c6e47ef4c79b..9f661c487beb 100644
--- a/fs/xfs/scrub/rmap.c
+++ b/fs/xfs/scrub/rmap.c
@@ -100,11 +100,11 @@ xchk_rmapbt_rec(
 	bool			is_unwritten;
 	bool			is_bmbt;
 	bool			is_attr;
-	int			error;
 
-	error = xfs_rmap_btrec_to_irec(rec, &irec);
-	if (!xchk_btree_process_error(bs->sc, bs->cur, 0, &error))
-		goto out;
+	if (xfs_rmap_btrec_to_irec(rec, &irec) != NULL) {
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
+		return 0;
+	}
 
 	/* Check extent. */
 	if (irec.rm_startblock + irec.rm_blockcount <= irec.rm_startblock)
@@ -159,8 +159,7 @@ xchk_rmapbt_rec(
 	}
 
 	xchk_rmapbt_xref(bs->sc, &irec);
-out:
-	return error;
+	return 0;
 }
 
 /* Scrub the rmap btree for some AG. */
-- 
cgit 


From c4e34172da26cb57f56c471728853d3a428ec832 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Tue, 11 Apr 2023 19:00:03 -0700
Subject: xfs: standardize ondisk to incore conversion for rmap btrees

Create a xfs_rmap_check_irec function to detect corruption in btree
records.  Fix all xfs_rmap_btrec_to_irec callsites to call the new
helper and bubble up corruption reports.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
---
 fs/xfs/libxfs/xfs_rmap.c | 62 ++++++++++++++++++++++++++++++------------------
 fs/xfs/libxfs/xfs_rmap.h |  3 +++
 fs/xfs/scrub/rmap.c      | 39 ++----------------------------
 3 files changed, 44 insertions(+), 60 deletions(-)

(limited to 'fs/xfs/libxfs/xfs_rmap.c')

diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c
index 830b38337cd5..5c7b081cef87 100644
--- a/fs/xfs/libxfs/xfs_rmap.c
+++ b/fs/xfs/libxfs/xfs_rmap.c
@@ -205,6 +205,36 @@ xfs_rmap_btrec_to_irec(
 			irec);
 }
 
+/* Simple checks for rmap records. */
+xfs_failaddr_t
+xfs_rmap_check_irec(
+	struct xfs_btree_cur		*cur,
+	const struct xfs_rmap_irec	*irec)
+{
+	struct xfs_mount		*mp = cur->bc_mp;
+
+	if (irec->rm_blockcount == 0)
+		return __this_address;
+	if (irec->rm_startblock <= XFS_AGFL_BLOCK(mp)) {
+		if (irec->rm_owner != XFS_RMAP_OWN_FS)
+			return __this_address;
+		if (irec->rm_blockcount != XFS_AGFL_BLOCK(mp) + 1)
+			return __this_address;
+	} else {
+		/* check for valid extent range, including overflow */
+		if (!xfs_verify_agbext(cur->bc_ag.pag, irec->rm_startblock,
+						       irec->rm_blockcount))
+			return __this_address;
+	}
+
+	if (!(xfs_verify_ino(mp, irec->rm_owner) ||
+	      (irec->rm_owner <= XFS_RMAP_OWN_FS &&
+	       irec->rm_owner >= XFS_RMAP_OWN_MIN)))
+		return __this_address;
+
+	return NULL;
+}
+
 /*
  * Get the data from the pointed-to record.
  */
@@ -217,39 +247,24 @@ xfs_rmap_get_rec(
 	struct xfs_mount	*mp = cur->bc_mp;
 	struct xfs_perag	*pag = cur->bc_ag.pag;
 	union xfs_btree_rec	*rec;
+	xfs_failaddr_t		fa;
 	int			error;
 
 	error = xfs_btree_get_rec(cur, &rec, stat);
 	if (error || !*stat)
 		return error;
 
-	if (xfs_rmap_btrec_to_irec(rec, irec))
-		goto out_bad_rec;
-
-	if (irec->rm_blockcount == 0)
-		goto out_bad_rec;
-	if (irec->rm_startblock <= XFS_AGFL_BLOCK(mp)) {
-		if (irec->rm_owner != XFS_RMAP_OWN_FS)
-			goto out_bad_rec;
-		if (irec->rm_blockcount != XFS_AGFL_BLOCK(mp) + 1)
-			goto out_bad_rec;
-	} else {
-		/* check for valid extent range, including overflow */
-		if (!xfs_verify_agbext(pag, irec->rm_startblock,
-					    irec->rm_blockcount))
-			goto out_bad_rec;
-	}
-
-	if (!(xfs_verify_ino(mp, irec->rm_owner) ||
-	      (irec->rm_owner <= XFS_RMAP_OWN_FS &&
-	       irec->rm_owner >= XFS_RMAP_OWN_MIN)))
+	fa = xfs_rmap_btrec_to_irec(rec, irec);
+	if (!fa)
+		fa = xfs_rmap_check_irec(cur, irec);
+	if (fa)
 		goto out_bad_rec;
 
 	return 0;
 out_bad_rec:
 	xfs_warn(mp,
-		"Reverse Mapping BTree record corruption in AG %d detected!",
-		pag->pag_agno);
+		"Reverse Mapping BTree record corruption in AG %d detected at %pS!",
+		pag->pag_agno, fa);
 	xfs_warn(mp,
 		"Owner 0x%llx, flags 0x%x, start block 0x%x block count 0x%x",
 		irec->rm_owner, irec->rm_flags, irec->rm_startblock,
@@ -2321,7 +2336,8 @@ xfs_rmap_query_range_helper(
 	struct xfs_rmap_query_range_info	*query = priv;
 	struct xfs_rmap_irec			irec;
 
-	if (xfs_rmap_btrec_to_irec(rec, &irec) != NULL)
+	if (xfs_rmap_btrec_to_irec(rec, &irec) != NULL ||
+	    xfs_rmap_check_irec(cur, &irec) != NULL)
 		return -EFSCORRUPTED;
 
 	return query->fn(cur, &irec, query->priv);
diff --git a/fs/xfs/libxfs/xfs_rmap.h b/fs/xfs/libxfs/xfs_rmap.h
index 6a08c403e8b7..7fb298bcc15f 100644
--- a/fs/xfs/libxfs/xfs_rmap.h
+++ b/fs/xfs/libxfs/xfs_rmap.h
@@ -195,6 +195,9 @@ int xfs_rmap_compare(const struct xfs_rmap_irec *a,
 union xfs_btree_rec;
 xfs_failaddr_t xfs_rmap_btrec_to_irec(const union xfs_btree_rec *rec,
 		struct xfs_rmap_irec *irec);
+xfs_failaddr_t xfs_rmap_check_irec(struct xfs_btree_cur *cur,
+		const 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,
diff --git a/fs/xfs/scrub/rmap.c b/fs/xfs/scrub/rmap.c
index 9f661c487beb..353cf9d90027 100644
--- a/fs/xfs/scrub/rmap.c
+++ b/fs/xfs/scrub/rmap.c
@@ -93,43 +93,18 @@ xchk_rmapbt_rec(
 	struct xchk_btree	*bs,
 	const union xfs_btree_rec *rec)
 {
-	struct xfs_mount	*mp = bs->cur->bc_mp;
 	struct xfs_rmap_irec	irec;
-	struct xfs_perag	*pag = bs->cur->bc_ag.pag;
 	bool			non_inode;
 	bool			is_unwritten;
 	bool			is_bmbt;
 	bool			is_attr;
 
-	if (xfs_rmap_btrec_to_irec(rec, &irec) != NULL) {
+	if (xfs_rmap_btrec_to_irec(rec, &irec) != NULL ||
+	    xfs_rmap_check_irec(bs->cur, &irec) != NULL) {
 		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 		return 0;
 	}
 
-	/* Check extent. */
-	if (irec.rm_startblock + irec.rm_blockcount <= irec.rm_startblock)
-		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
-
-	if (irec.rm_owner == XFS_RMAP_OWN_FS) {
-		/*
-		 * xfs_verify_agbno returns false for static fs metadata.
-		 * Since that only exists at the start of the AG, validate
-		 * that by hand.
-		 */
-		if (irec.rm_startblock != 0 ||
-		    irec.rm_blockcount != XFS_AGFL_BLOCK(mp) + 1)
-			xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
-	} else {
-		/*
-		 * Otherwise we must point somewhere past the static metadata
-		 * but before the end of the FS.  Run the regular check.
-		 */
-		if (!xfs_verify_agbno(pag, irec.rm_startblock) ||
-		    !xfs_verify_agbno(pag, irec.rm_startblock +
-				irec.rm_blockcount - 1))
-			xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
-	}
-
 	/* Check flags. */
 	non_inode = XFS_RMAP_NON_INODE_OWNER(irec.rm_owner);
 	is_bmbt = irec.rm_flags & XFS_RMAP_BMBT_BLOCK;
@@ -148,16 +123,6 @@ xchk_rmapbt_rec(
 	if (non_inode && (is_bmbt || is_unwritten || is_attr))
 		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 
-	if (!non_inode) {
-		if (!xfs_verify_ino(mp, irec.rm_owner))
-			xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
-	} else {
-		/* Non-inode owner within the magic values? */
-		if (irec.rm_owner <= XFS_RMAP_OWN_MIN ||
-		    irec.rm_owner > XFS_RMAP_OWN_FS)
-			xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
-	}
-
 	xchk_rmapbt_xref(bs->sc, &irec);
 	return 0;
 }
-- 
cgit 


From ee12eaaa435a7be17152ac50943ee77249de624a Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Tue, 11 Apr 2023 19:00:04 -0700
Subject: xfs: complain about bad records in query_range helpers

For every btree type except for the bmbt, refactor the code that
complains about bad records into a helper and make the ->query_range
helpers call it so that corruptions found via that avenue are logged.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
---
 fs/xfs/libxfs/xfs_alloc.c    | 38 +++++++++++++++++++++++---------------
 fs/xfs/libxfs/xfs_ialloc.c   | 38 ++++++++++++++++++++++++--------------
 fs/xfs/libxfs/xfs_refcount.c | 32 +++++++++++++++++++-------------
 fs/xfs/libxfs/xfs_rmap.c     | 40 +++++++++++++++++++++++++---------------
 4 files changed, 91 insertions(+), 57 deletions(-)

(limited to 'fs/xfs/libxfs/xfs_rmap.c')

diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 89c935cbcc4d..23f0acfc2a64 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -261,6 +261,24 @@ xfs_alloc_check_irec(
 	return NULL;
 }
 
+static inline int
+xfs_alloc_complain_bad_rec(
+	struct xfs_btree_cur		*cur,
+	xfs_failaddr_t			fa,
+	const struct xfs_alloc_rec_incore *irec)
+{
+	struct xfs_mount		*mp = cur->bc_mp;
+
+	xfs_warn(mp,
+		"%s Freespace BTree record corruption in AG %d detected at %pS!",
+		cur->bc_btnum == XFS_BTNUM_BNO ? "Block" : "Size",
+		cur->bc_ag.pag->pag_agno, fa);
+	xfs_warn(mp,
+		"start block 0x%x block count 0x%x", irec->ar_startblock,
+		irec->ar_blockcount);
+	return -EFSCORRUPTED;
+}
+
 /*
  * Get the data from the pointed-to record.
  */
@@ -272,8 +290,6 @@ xfs_alloc_get_rec(
 	int			*stat)	/* output: success/failure */
 {
 	struct xfs_alloc_rec_incore irec;
-	struct xfs_mount	*mp = cur->bc_mp;
-	struct xfs_perag	*pag = cur->bc_ag.pag;
 	union xfs_btree_rec	*rec;
 	xfs_failaddr_t		fa;
 	int			error;
@@ -285,21 +301,11 @@ xfs_alloc_get_rec(
 	xfs_alloc_btrec_to_irec(rec, &irec);
 	fa = xfs_alloc_check_irec(cur, &irec);
 	if (fa)
-		goto out_bad_rec;
+		return xfs_alloc_complain_bad_rec(cur, fa, &irec);
 
 	*bno = irec.ar_startblock;
 	*len = irec.ar_blockcount;
 	return 0;
-
-out_bad_rec:
-	xfs_warn(mp,
-		"%s Freespace BTree record corruption in AG %d detected at %pS!",
-		cur->bc_btnum == XFS_BTNUM_BNO ? "Block" : "Size",
-		pag->pag_agno, fa);
-	xfs_warn(mp,
-		"start block 0x%x block count 0x%x", irec.ar_startblock,
-		irec.ar_blockcount);
-	return -EFSCORRUPTED;
 }
 
 /*
@@ -3692,10 +3698,12 @@ xfs_alloc_query_range_helper(
 {
 	struct xfs_alloc_query_range_info	*query = priv;
 	struct xfs_alloc_rec_incore		irec;
+	xfs_failaddr_t				fa;
 
 	xfs_alloc_btrec_to_irec(rec, &irec);
-	if (xfs_alloc_check_irec(cur, &irec) != NULL)
-		return -EFSCORRUPTED;
+	fa = xfs_alloc_check_irec(cur, &irec);
+	if (fa)
+		return xfs_alloc_complain_bad_rec(cur, fa, &irec);
 
 	return query->fn(cur, &irec, query->priv);
 }
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index 32af8326ad76..b7dc8b81a133 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -122,6 +122,25 @@ xfs_inobt_check_irec(
 	return NULL;
 }
 
+static inline int
+xfs_inobt_complain_bad_rec(
+	struct xfs_btree_cur		*cur,
+	xfs_failaddr_t			fa,
+	const struct xfs_inobt_rec_incore *irec)
+{
+	struct xfs_mount		*mp = cur->bc_mp;
+
+	xfs_warn(mp,
+		"%s Inode BTree record corruption in AG %d detected at %pS!",
+		cur->bc_btnum == XFS_BTNUM_INO ? "Used" : "Free",
+		cur->bc_ag.pag->pag_agno, fa);
+	xfs_warn(mp,
+"start inode 0x%x, count 0x%x, free 0x%x freemask 0x%llx, holemask 0x%x",
+		irec->ir_startino, irec->ir_count, irec->ir_freecount,
+		irec->ir_free, irec->ir_holemask);
+	return -EFSCORRUPTED;
+}
+
 /*
  * Get the data from the pointed-to record.
  */
@@ -143,20 +162,9 @@ xfs_inobt_get_rec(
 	xfs_inobt_btrec_to_irec(mp, rec, irec);
 	fa = xfs_inobt_check_irec(cur, irec);
 	if (fa)
-		goto out_bad_rec;
+		return xfs_inobt_complain_bad_rec(cur, fa, irec);
 
 	return 0;
-
-out_bad_rec:
-	xfs_warn(mp,
-		"%s Inode BTree record corruption in AG %d detected at %pS!",
-		cur->bc_btnum == XFS_BTNUM_INO ? "Used" : "Free",
-		cur->bc_ag.pag->pag_agno, fa);
-	xfs_warn(mp,
-"start inode 0x%x, count 0x%x, free 0x%x freemask 0x%llx, holemask 0x%x",
-		irec->ir_startino, irec->ir_count, irec->ir_freecount,
-		irec->ir_free, irec->ir_holemask);
-	return -EFSCORRUPTED;
 }
 
 /*
@@ -2702,10 +2710,12 @@ xfs_ialloc_count_inodes_rec(
 {
 	struct xfs_inobt_rec_incore	irec;
 	struct xfs_ialloc_count_inodes	*ci = priv;
+	xfs_failaddr_t			fa;
 
 	xfs_inobt_btrec_to_irec(cur->bc_mp, rec, &irec);
-	if (xfs_inobt_check_irec(cur, &irec) != NULL)
-		return -EFSCORRUPTED;
+	fa = xfs_inobt_check_irec(cur, &irec);
+	if (fa)
+		return xfs_inobt_complain_bad_rec(cur, fa, &irec);
 
 	ci->count += irec.ir_count;
 	ci->freecount += irec.ir_freecount;
diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c
index b77dea10c8bd..335f84bef81c 100644
--- a/fs/xfs/libxfs/xfs_refcount.c
+++ b/fs/xfs/libxfs/xfs_refcount.c
@@ -144,6 +144,23 @@ xfs_refcount_check_irec(
 	return NULL;
 }
 
+static inline int
+xfs_refcount_complain_bad_rec(
+	struct xfs_btree_cur		*cur,
+	xfs_failaddr_t			fa,
+	const struct xfs_refcount_irec	*irec)
+{
+	struct xfs_mount		*mp = cur->bc_mp;
+
+	xfs_warn(mp,
+ "Refcount BTree record corruption in AG %d detected at %pS!",
+				cur->bc_ag.pag->pag_agno, fa);
+	xfs_warn(mp,
+		"Start block 0x%x, block count 0x%x, references 0x%x",
+		irec->rc_startblock, irec->rc_blockcount, irec->rc_refcount);
+	return -EFSCORRUPTED;
+}
+
 /*
  * Get the data from the pointed-to record.
  */
@@ -153,8 +170,6 @@ xfs_refcount_get_rec(
 	struct xfs_refcount_irec	*irec,
 	int				*stat)
 {
-	struct xfs_mount		*mp = cur->bc_mp;
-	struct xfs_perag		*pag = cur->bc_ag.pag;
 	union xfs_btree_rec		*rec;
 	xfs_failaddr_t			fa;
 	int				error;
@@ -166,19 +181,10 @@ xfs_refcount_get_rec(
 	xfs_refcount_btrec_to_irec(rec, irec);
 	fa = xfs_refcount_check_irec(cur, irec);
 	if (fa)
-		goto out_bad_rec;
+		return xfs_refcount_complain_bad_rec(cur, fa, irec);
 
-	trace_xfs_refcount_get(cur->bc_mp, pag->pag_agno, irec);
+	trace_xfs_refcount_get(cur->bc_mp, cur->bc_ag.pag->pag_agno, irec);
 	return 0;
-
-out_bad_rec:
-	xfs_warn(mp,
-		"Refcount BTree record corruption in AG %d detected at %pS!",
-		pag->pag_agno, fa);
-	xfs_warn(mp,
-		"Start block 0x%x, block count 0x%x, references 0x%x",
-		irec->rc_startblock, irec->rc_blockcount, irec->rc_refcount);
-	return -EFSCORRUPTED;
 }
 
 /*
diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c
index 5c7b081cef87..641114a023f2 100644
--- a/fs/xfs/libxfs/xfs_rmap.c
+++ b/fs/xfs/libxfs/xfs_rmap.c
@@ -235,6 +235,24 @@ xfs_rmap_check_irec(
 	return NULL;
 }
 
+static inline int
+xfs_rmap_complain_bad_rec(
+	struct xfs_btree_cur		*cur,
+	xfs_failaddr_t			fa,
+	const struct xfs_rmap_irec	*irec)
+{
+	struct xfs_mount		*mp = cur->bc_mp;
+
+	xfs_warn(mp,
+		"Reverse Mapping BTree record corruption in AG %d detected at %pS!",
+		cur->bc_ag.pag->pag_agno, fa);
+	xfs_warn(mp,
+		"Owner 0x%llx, flags 0x%x, start block 0x%x block count 0x%x",
+		irec->rm_owner, irec->rm_flags, irec->rm_startblock,
+		irec->rm_blockcount);
+	return -EFSCORRUPTED;
+}
+
 /*
  * Get the data from the pointed-to record.
  */
@@ -244,8 +262,6 @@ xfs_rmap_get_rec(
 	struct xfs_rmap_irec	*irec,
 	int			*stat)
 {
-	struct xfs_mount	*mp = cur->bc_mp;
-	struct xfs_perag	*pag = cur->bc_ag.pag;
 	union xfs_btree_rec	*rec;
 	xfs_failaddr_t		fa;
 	int			error;
@@ -258,18 +274,9 @@ xfs_rmap_get_rec(
 	if (!fa)
 		fa = xfs_rmap_check_irec(cur, irec);
 	if (fa)
-		goto out_bad_rec;
+		return xfs_rmap_complain_bad_rec(cur, fa, irec);
 
 	return 0;
-out_bad_rec:
-	xfs_warn(mp,
-		"Reverse Mapping BTree record corruption in AG %d detected at %pS!",
-		pag->pag_agno, fa);
-	xfs_warn(mp,
-		"Owner 0x%llx, flags 0x%x, start block 0x%x block count 0x%x",
-		irec->rm_owner, irec->rm_flags, irec->rm_startblock,
-		irec->rm_blockcount);
-	return -EFSCORRUPTED;
 }
 
 struct xfs_find_left_neighbor_info {
@@ -2335,10 +2342,13 @@ xfs_rmap_query_range_helper(
 {
 	struct xfs_rmap_query_range_info	*query = priv;
 	struct xfs_rmap_irec			irec;
+	xfs_failaddr_t				fa;
 
-	if (xfs_rmap_btrec_to_irec(rec, &irec) != NULL ||
-	    xfs_rmap_check_irec(cur, &irec) != NULL)
-		return -EFSCORRUPTED;
+	fa = xfs_rmap_btrec_to_irec(rec, &irec);
+	if (!fa)
+		fa = xfs_rmap_check_irec(cur, &irec);
+	if (fa)
+		return xfs_rmap_complain_bad_rec(cur, fa, &irec);
 
 	return query->fn(cur, &irec, query->priv);
 }
-- 
cgit 


From 7d7d6d2fd0444904f12e70d9c930556c4eb44337 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Tue, 11 Apr 2023 19:00:05 -0700
Subject: xfs: hoist rmap record flag checks from scrub

Move the rmap record flag checks from xchk_rmapbt_rec into
xfs_rmap_check_irec so that they are applied everywhere.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
---
 fs/xfs/libxfs/xfs_rmap.c | 22 ++++++++++++++++++++++
 fs/xfs/scrub/rmap.c      | 22 ----------------------
 2 files changed, 22 insertions(+), 22 deletions(-)

(limited to 'fs/xfs/libxfs/xfs_rmap.c')

diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c
index 641114a023f2..e66ecd794a84 100644
--- a/fs/xfs/libxfs/xfs_rmap.c
+++ b/fs/xfs/libxfs/xfs_rmap.c
@@ -212,6 +212,10 @@ xfs_rmap_check_irec(
 	const struct xfs_rmap_irec	*irec)
 {
 	struct xfs_mount		*mp = cur->bc_mp;
+	bool				is_inode;
+	bool				is_unwritten;
+	bool				is_bmbt;
+	bool				is_attr;
 
 	if (irec->rm_blockcount == 0)
 		return __this_address;
@@ -232,6 +236,24 @@ xfs_rmap_check_irec(
 	       irec->rm_owner >= XFS_RMAP_OWN_MIN)))
 		return __this_address;
 
+	/* Check flags. */
+	is_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 (is_bmbt && irec->rm_offset != 0)
+		return __this_address;
+
+	if (!is_inode && irec->rm_offset != 0)
+		return __this_address;
+
+	if (is_unwritten && (is_bmbt || !is_inode || is_attr))
+		return __this_address;
+
+	if (!is_inode && (is_bmbt || is_unwritten || is_attr))
+		return __this_address;
+
 	return NULL;
 }
 
diff --git a/fs/xfs/scrub/rmap.c b/fs/xfs/scrub/rmap.c
index 353cf9d90027..ef6e4b8546a6 100644
--- a/fs/xfs/scrub/rmap.c
+++ b/fs/xfs/scrub/rmap.c
@@ -94,10 +94,6 @@ xchk_rmapbt_rec(
 	const union xfs_btree_rec *rec)
 {
 	struct xfs_rmap_irec	irec;
-	bool			non_inode;
-	bool			is_unwritten;
-	bool			is_bmbt;
-	bool			is_attr;
 
 	if (xfs_rmap_btrec_to_irec(rec, &irec) != NULL ||
 	    xfs_rmap_check_irec(bs->cur, &irec) != NULL) {
@@ -105,24 +101,6 @@ xchk_rmapbt_rec(
 		return 0;
 	}
 
-	/* Check flags. */
-	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 (is_bmbt && irec.rm_offset != 0)
-		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
-
-	if (non_inode && irec.rm_offset != 0)
-		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
-
-	if (is_unwritten && (is_bmbt || non_inode || is_attr))
-		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
-
-	if (non_inode && (is_bmbt || is_unwritten || is_attr))
-		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
-
 	xchk_rmapbt_xref(bs->sc, &irec);
 	return 0;
 }
-- 
cgit 


From e774b2ea0bb130d00e3cb1c29cd91028d0c0c83d Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Tue, 11 Apr 2023 19:00:06 -0700
Subject: xfs: hoist rmap record flag checks from scrub

Move the rmap record flag checks from xchk_rmapbt_rec into
xfs_rmap_check_irec so that they are applied everywhere.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
---
 fs/xfs/libxfs/xfs_rmap.c | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'fs/xfs/libxfs/xfs_rmap.c')

diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c
index e66ecd794a84..da008d317f83 100644
--- a/fs/xfs/libxfs/xfs_rmap.c
+++ b/fs/xfs/libxfs/xfs_rmap.c
@@ -254,6 +254,11 @@ xfs_rmap_check_irec(
 	if (!is_inode && (is_bmbt || is_unwritten || is_attr))
 		return __this_address;
 
+	/* Check for a valid fork offset, if applicable. */
+	if (is_inode && !is_bmbt &&
+	    !xfs_verify_fileext(mp, irec->rm_offset, irec->rm_blockcount))
+		return __this_address;
+
 	return NULL;
 }
 
-- 
cgit 


From 6abc7aef85b1f42cb39a3149f4ab64ca255e41e6 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Tue, 11 Apr 2023 19:00:10 -0700
Subject: xfs: replace xfs_btree_has_record with a general keyspace scanner

The current implementation of xfs_btree_has_record returns true if it
finds /any/ record within the given range.  Unfortunately, that's not
sufficient for scrub.  We want to be able to tell if a range of keyspace
for a btree is devoid of records, is totally mapped to records, or is
somewhere in between.  By forcing this to be a boolean, we conflated
sparseness and fullness, which caused scrub to return incorrect results.
Fix the API so that we can tell the caller which of those three is the
current state.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
---
 fs/xfs/libxfs/xfs_alloc.c          |  11 ++--
 fs/xfs/libxfs/xfs_alloc.h          |   4 +-
 fs/xfs/libxfs/xfs_alloc_btree.c    |  12 +++++
 fs/xfs/libxfs/xfs_bmap_btree.c     |  11 ++++
 fs/xfs/libxfs/xfs_btree.c          | 108 ++++++++++++++++++++++++++++++++-----
 fs/xfs/libxfs/xfs_btree.h          |  44 ++++++++++++++-
 fs/xfs/libxfs/xfs_ialloc_btree.c   |  12 +++++
 fs/xfs/libxfs/xfs_refcount.c       |  11 ++--
 fs/xfs/libxfs/xfs_refcount.h       |   4 +-
 fs/xfs/libxfs/xfs_refcount_btree.c |  11 ++++
 fs/xfs/libxfs/xfs_rmap.c           |  12 +++--
 fs/xfs/libxfs/xfs_rmap.h           |   4 +-
 fs/xfs/libxfs/xfs_rmap_btree.c     |  16 ++++++
 fs/xfs/libxfs/xfs_types.h          |  12 +++++
 fs/xfs/scrub/alloc.c               |   6 +--
 fs/xfs/scrub/refcount.c            |   8 +--
 fs/xfs/scrub/rmap.c                |   6 +--
 17 files changed, 249 insertions(+), 43 deletions(-)

(limited to 'fs/xfs/libxfs/xfs_rmap.c')

diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 23f0acfc2a64..34c8501d86d0 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -3745,13 +3745,16 @@ xfs_alloc_query_all(
 	return xfs_btree_query_all(cur, xfs_alloc_query_range_helper, &query);
 }
 
-/* Is there a record covering a given extent? */
+/*
+ * Scan part of the keyspace of the free space and tell us if the area has no
+ * records, is fully mapped by records, or is partially filled.
+ */
 int
-xfs_alloc_has_record(
+xfs_alloc_has_records(
 	struct xfs_btree_cur	*cur,
 	xfs_agblock_t		bno,
 	xfs_extlen_t		len,
-	bool			*exists)
+	enum xbtree_recpacking	*outcome)
 {
 	union xfs_btree_irec	low;
 	union xfs_btree_irec	high;
@@ -3761,7 +3764,7 @@ xfs_alloc_has_record(
 	memset(&high, 0xFF, sizeof(high));
 	high.a.ar_startblock = bno + len - 1;
 
-	return xfs_btree_has_record(cur, &low, &high, exists);
+	return xfs_btree_has_records(cur, &low, &high, outcome);
 }
 
 /*
diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h
index 56bd05900b35..5dbb25546d0b 100644
--- a/fs/xfs/libxfs/xfs_alloc.h
+++ b/fs/xfs/libxfs/xfs_alloc.h
@@ -213,8 +213,8 @@ int xfs_alloc_query_range(struct xfs_btree_cur *cur,
 int xfs_alloc_query_all(struct xfs_btree_cur *cur, xfs_alloc_query_range_fn fn,
 		void *priv);
 
-int xfs_alloc_has_record(struct xfs_btree_cur *cur, xfs_agblock_t bno,
-		xfs_extlen_t len, bool *exist);
+int xfs_alloc_has_records(struct xfs_btree_cur *cur, xfs_agblock_t bno,
+		xfs_extlen_t len, enum xbtree_recpacking *outcome);
 
 typedef int (*xfs_agfl_walk_fn)(struct xfs_mount *mp, xfs_agblock_t bno,
 		void *priv);
diff --git a/fs/xfs/libxfs/xfs_alloc_btree.c b/fs/xfs/libxfs/xfs_alloc_btree.c
index 8e8416c14cec..be80c57aeddc 100644
--- a/fs/xfs/libxfs/xfs_alloc_btree.c
+++ b/fs/xfs/libxfs/xfs_alloc_btree.c
@@ -423,6 +423,16 @@ xfs_cntbt_recs_inorder(
 		 be32_to_cpu(r2->alloc.ar_startblock));
 }
 
+STATIC enum xbtree_key_contig
+xfs_allocbt_keys_contiguous(
+	struct xfs_btree_cur		*cur,
+	const union xfs_btree_key	*key1,
+	const union xfs_btree_key	*key2)
+{
+	return xbtree_key_contig(be32_to_cpu(key1->alloc.ar_startblock),
+				 be32_to_cpu(key2->alloc.ar_startblock));
+}
+
 static const struct xfs_btree_ops xfs_bnobt_ops = {
 	.rec_len		= sizeof(xfs_alloc_rec_t),
 	.key_len		= sizeof(xfs_alloc_key_t),
@@ -443,6 +453,7 @@ static const struct xfs_btree_ops xfs_bnobt_ops = {
 	.diff_two_keys		= xfs_bnobt_diff_two_keys,
 	.keys_inorder		= xfs_bnobt_keys_inorder,
 	.recs_inorder		= xfs_bnobt_recs_inorder,
+	.keys_contiguous	= xfs_allocbt_keys_contiguous,
 };
 
 static const struct xfs_btree_ops xfs_cntbt_ops = {
@@ -465,6 +476,7 @@ static const struct xfs_btree_ops xfs_cntbt_ops = {
 	.diff_two_keys		= xfs_cntbt_diff_two_keys,
 	.keys_inorder		= xfs_cntbt_keys_inorder,
 	.recs_inorder		= xfs_cntbt_recs_inorder,
+	.keys_contiguous	= NULL, /* not needed right now */
 };
 
 /* Allocate most of a new allocation btree cursor. */
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index b8ad95050c9b..3edf314a55e2 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -500,6 +500,16 @@ xfs_bmbt_recs_inorder(
 		xfs_bmbt_disk_get_startoff(&r2->bmbt);
 }
 
+STATIC enum xbtree_key_contig
+xfs_bmbt_keys_contiguous(
+	struct xfs_btree_cur		*cur,
+	const union xfs_btree_key	*key1,
+	const union xfs_btree_key	*key2)
+{
+	return xbtree_key_contig(be64_to_cpu(key1->bmbt.br_startoff),
+				 be64_to_cpu(key2->bmbt.br_startoff));
+}
+
 static const struct xfs_btree_ops xfs_bmbt_ops = {
 	.rec_len		= sizeof(xfs_bmbt_rec_t),
 	.key_len		= sizeof(xfs_bmbt_key_t),
@@ -520,6 +530,7 @@ static const struct xfs_btree_ops xfs_bmbt_ops = {
 	.buf_ops		= &xfs_bmbt_buf_ops,
 	.keys_inorder		= xfs_bmbt_keys_inorder,
 	.recs_inorder		= xfs_bmbt_recs_inorder,
+	.keys_contiguous	= xfs_bmbt_keys_contiguous,
 };
 
 /*
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index 92c610850fac..afbd3bcdf567 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -5025,34 +5025,116 @@ xfs_btree_diff_two_ptrs(
 	return (int64_t)be32_to_cpu(a->s) - be32_to_cpu(b->s);
 }
 
-/* If there's an extent, we're done. */
+struct xfs_btree_has_records {
+	/* Keys for the start and end of the range we want to know about. */
+	union xfs_btree_key		start_key;
+	union xfs_btree_key		end_key;
+
+	/* Highest record key we've seen so far. */
+	union xfs_btree_key		high_key;
+
+	enum xbtree_recpacking		outcome;
+};
+
 STATIC int
-xfs_btree_has_record_helper(
+xfs_btree_has_records_helper(
 	struct xfs_btree_cur		*cur,
 	const union xfs_btree_rec	*rec,
 	void				*priv)
 {
-	return -ECANCELED;
+	union xfs_btree_key		rec_key;
+	union xfs_btree_key		rec_high_key;
+	struct xfs_btree_has_records	*info = priv;
+	enum xbtree_key_contig		key_contig;
+
+	cur->bc_ops->init_key_from_rec(&rec_key, rec);
+
+	if (info->outcome == XBTREE_RECPACKING_EMPTY) {
+		info->outcome = XBTREE_RECPACKING_SPARSE;
+
+		/*
+		 * If the first record we find does not overlap the start key,
+		 * then there is a hole at the start of the search range.
+		 * Classify this as sparse and stop immediately.
+		 */
+		if (xfs_btree_keycmp_lt(cur, &info->start_key, &rec_key))
+			return -ECANCELED;
+	} else {
+		/*
+		 * If a subsequent record does not overlap with the any record
+		 * we've seen so far, there is a hole in the middle of the
+		 * search range.  Classify this as sparse and stop.
+		 * If the keys overlap and this btree does not allow overlap,
+		 * signal corruption.
+		 */
+		key_contig = cur->bc_ops->keys_contiguous(cur, &info->high_key,
+					&rec_key);
+		if (key_contig == XBTREE_KEY_OVERLAP &&
+				!(cur->bc_flags & XFS_BTREE_OVERLAPPING))
+			return -EFSCORRUPTED;
+		if (key_contig == XBTREE_KEY_GAP)
+			return -ECANCELED;
+	}
+
+	/*
+	 * If high_key(rec) is larger than any other high key we've seen,
+	 * remember it for later.
+	 */
+	cur->bc_ops->init_high_key_from_rec(&rec_high_key, rec);
+	if (xfs_btree_keycmp_gt(cur, &rec_high_key, &info->high_key))
+		info->high_key = rec_high_key; /* struct copy */
+
+	return 0;
 }
 
-/* Is there a record covering a given range of keys? */
+/*
+ * Scan part of the keyspace of a btree and tell us if that keyspace does not
+ * map to any records; is fully mapped to records; or is partially mapped to
+ * records.  This is the btree record equivalent to determining if a file is
+ * sparse.
+ */
 int
-xfs_btree_has_record(
+xfs_btree_has_records(
 	struct xfs_btree_cur		*cur,
 	const union xfs_btree_irec	*low,
 	const union xfs_btree_irec	*high,
-	bool				*exists)
+	enum xbtree_recpacking		*outcome)
 {
+	struct xfs_btree_has_records	info = {
+		.outcome		= XBTREE_RECPACKING_EMPTY,
+	};
 	int				error;
 
-	error = xfs_btree_query_range(cur, low, high,
-			&xfs_btree_has_record_helper, NULL);
-	if (error == -ECANCELED) {
-		*exists = true;
-		return 0;
+	/* Not all btrees support this operation. */
+	if (!cur->bc_ops->keys_contiguous) {
+		ASSERT(0);
+		return -EOPNOTSUPP;
 	}
-	*exists = false;
-	return error;
+
+	xfs_btree_key_from_irec(cur, &info.start_key, low);
+	xfs_btree_key_from_irec(cur, &info.end_key, high);
+
+	error = xfs_btree_query_range(cur, low, high,
+			xfs_btree_has_records_helper, &info);
+	if (error == -ECANCELED)
+		goto out;
+	if (error)
+		return error;
+
+	if (info.outcome == XBTREE_RECPACKING_EMPTY)
+		goto out;
+
+	/*
+	 * If the largest high_key(rec) we saw during the walk is greater than
+	 * the end of the search range, classify this as full.  Otherwise,
+	 * there is a hole at the end of the search range.
+	 */
+	if (xfs_btree_keycmp_ge(cur, &info.high_key, &info.end_key))
+		info.outcome = XBTREE_RECPACKING_FULL;
+
+out:
+	*outcome = info.outcome;
+	return 0;
 }
 
 /* Are there more records in this btree? */
diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h
index f5aa4b893ee7..66431f351bb2 100644
--- a/fs/xfs/libxfs/xfs_btree.h
+++ b/fs/xfs/libxfs/xfs_btree.h
@@ -90,6 +90,27 @@ uint32_t xfs_btree_magic(int crc, xfs_btnum_t btnum);
 #define XFS_BTREE_STATS_ADD(cur, stat, val)	\
 	XFS_STATS_ADD_OFF((cur)->bc_mp, (cur)->bc_statoff + __XBTS_ ## stat, val)
 
+enum xbtree_key_contig {
+	XBTREE_KEY_GAP = 0,
+	XBTREE_KEY_CONTIGUOUS,
+	XBTREE_KEY_OVERLAP,
+};
+
+/*
+ * Decide if these two numeric btree key fields are contiguous, overlapping,
+ * or if there's a gap between them.  @x should be the field from the high
+ * key and @y should be the field from the low key.
+ */
+static inline enum xbtree_key_contig xbtree_key_contig(uint64_t x, uint64_t y)
+{
+	x++;
+	if (x < y)
+		return XBTREE_KEY_GAP;
+	if (x == y)
+		return XBTREE_KEY_CONTIGUOUS;
+	return XBTREE_KEY_OVERLAP;
+}
+
 struct xfs_btree_ops {
 	/* size of the key and record structures */
 	size_t	key_len;
@@ -157,6 +178,19 @@ struct xfs_btree_ops {
 	int	(*recs_inorder)(struct xfs_btree_cur *cur,
 				const union xfs_btree_rec *r1,
 				const union xfs_btree_rec *r2);
+
+	/*
+	 * Are these two btree keys immediately adjacent?
+	 *
+	 * Given two btree keys @key1 and @key2, decide if it is impossible for
+	 * there to be a third btree key K satisfying the relationship
+	 * @key1 < K < @key2.  To determine if two btree records are
+	 * immediately adjacent, @key1 should be the high key of the first
+	 * record and @key2 should be the low key of the second record.
+	 */
+	enum xbtree_key_contig (*keys_contiguous)(struct xfs_btree_cur *cur,
+			       const union xfs_btree_key *key1,
+			       const union xfs_btree_key *key2);
 };
 
 /*
@@ -540,9 +574,15 @@ 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,
+typedef bool (*xfs_btree_key_gap_fn)(struct xfs_btree_cur *cur,
+		const union xfs_btree_key *key1,
+		const union xfs_btree_key *key2);
+
+int xfs_btree_has_records(struct xfs_btree_cur *cur,
 		const union xfs_btree_irec *low,
-		const union xfs_btree_irec *high, bool *exists);
+		const union xfs_btree_irec *high,
+		enum xbtree_recpacking *outcome);
+
 bool xfs_btree_has_more_records(struct xfs_btree_cur *cur);
 struct xfs_ifork *xfs_btree_ifork_ptr(struct xfs_btree_cur *cur);
 
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c
index f900c056b82c..dd1fad8c3304 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.c
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.c
@@ -383,6 +383,16 @@ xfs_inobt_recs_inorder(
 		be32_to_cpu(r2->inobt.ir_startino);
 }
 
+STATIC enum xbtree_key_contig
+xfs_inobt_keys_contiguous(
+	struct xfs_btree_cur		*cur,
+	const union xfs_btree_key	*key1,
+	const union xfs_btree_key	*key2)
+{
+	return xbtree_key_contig(be32_to_cpu(key1->inobt.ir_startino),
+				 be32_to_cpu(key2->inobt.ir_startino));
+}
+
 static const struct xfs_btree_ops xfs_inobt_ops = {
 	.rec_len		= sizeof(xfs_inobt_rec_t),
 	.key_len		= sizeof(xfs_inobt_key_t),
@@ -402,6 +412,7 @@ static const struct xfs_btree_ops xfs_inobt_ops = {
 	.diff_two_keys		= xfs_inobt_diff_two_keys,
 	.keys_inorder		= xfs_inobt_keys_inorder,
 	.recs_inorder		= xfs_inobt_recs_inorder,
+	.keys_contiguous	= xfs_inobt_keys_contiguous,
 };
 
 static const struct xfs_btree_ops xfs_finobt_ops = {
@@ -423,6 +434,7 @@ static const struct xfs_btree_ops xfs_finobt_ops = {
 	.diff_two_keys		= xfs_inobt_diff_two_keys,
 	.keys_inorder		= xfs_inobt_keys_inorder,
 	.recs_inorder		= xfs_inobt_recs_inorder,
+	.keys_contiguous	= xfs_inobt_keys_contiguous,
 };
 
 /*
diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c
index 335f84bef81c..94377b59ba44 100644
--- a/fs/xfs/libxfs/xfs_refcount.c
+++ b/fs/xfs/libxfs/xfs_refcount.c
@@ -1998,14 +1998,17 @@ out_free:
 	return error;
 }
 
-/* Is there a record covering a given extent? */
+/*
+ * Scan part of the keyspace of the refcount records and tell us if the area
+ * has no records, is fully mapped by records, or is partially filled.
+ */
 int
-xfs_refcount_has_record(
+xfs_refcount_has_records(
 	struct xfs_btree_cur	*cur,
 	enum xfs_refc_domain	domain,
 	xfs_agblock_t		bno,
 	xfs_extlen_t		len,
-	bool			*exists)
+	enum xbtree_recpacking	*outcome)
 {
 	union xfs_btree_irec	low;
 	union xfs_btree_irec	high;
@@ -2016,7 +2019,7 @@ xfs_refcount_has_record(
 	high.rc.rc_startblock = bno + len - 1;
 	low.rc.rc_domain = high.rc.rc_domain = domain;
 
-	return xfs_btree_has_record(cur, &low, &high, exists);
+	return xfs_btree_has_records(cur, &low, &high, outcome);
 }
 
 int __init
diff --git a/fs/xfs/libxfs/xfs_refcount.h b/fs/xfs/libxfs/xfs_refcount.h
index fc0b58d4c379..783cd89ca195 100644
--- a/fs/xfs/libxfs/xfs_refcount.h
+++ b/fs/xfs/libxfs/xfs_refcount.h
@@ -111,9 +111,9 @@ extern int xfs_refcount_recover_cow_leftovers(struct xfs_mount *mp,
  */
 #define XFS_REFCOUNT_ITEM_OVERHEAD	32
 
-extern int xfs_refcount_has_record(struct xfs_btree_cur *cur,
+extern int xfs_refcount_has_records(struct xfs_btree_cur *cur,
 		enum xfs_refc_domain domain, xfs_agblock_t bno,
-		xfs_extlen_t len, bool *exists);
+		xfs_extlen_t len, enum xbtree_recpacking *outcome);
 union xfs_btree_rec;
 extern void xfs_refcount_btrec_to_irec(const union xfs_btree_rec *rec,
 		struct xfs_refcount_irec *irec);
diff --git a/fs/xfs/libxfs/xfs_refcount_btree.c b/fs/xfs/libxfs/xfs_refcount_btree.c
index 03d2b01487a1..1628eecb53fd 100644
--- a/fs/xfs/libxfs/xfs_refcount_btree.c
+++ b/fs/xfs/libxfs/xfs_refcount_btree.c
@@ -300,6 +300,16 @@ xfs_refcountbt_recs_inorder(
 		be32_to_cpu(r2->refc.rc_startblock);
 }
 
+STATIC enum xbtree_key_contig
+xfs_refcountbt_keys_contiguous(
+	struct xfs_btree_cur		*cur,
+	const union xfs_btree_key	*key1,
+	const union xfs_btree_key	*key2)
+{
+	return xbtree_key_contig(be32_to_cpu(key1->refc.rc_startblock),
+				 be32_to_cpu(key2->refc.rc_startblock));
+}
+
 static const struct xfs_btree_ops xfs_refcountbt_ops = {
 	.rec_len		= sizeof(struct xfs_refcount_rec),
 	.key_len		= sizeof(struct xfs_refcount_key),
@@ -319,6 +329,7 @@ static const struct xfs_btree_ops xfs_refcountbt_ops = {
 	.diff_two_keys		= xfs_refcountbt_diff_two_keys,
 	.keys_inorder		= xfs_refcountbt_keys_inorder,
 	.recs_inorder		= xfs_refcountbt_recs_inorder,
+	.keys_contiguous	= xfs_refcountbt_keys_contiguous,
 };
 
 /*
diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c
index da008d317f83..e616b964f11c 100644
--- a/fs/xfs/libxfs/xfs_rmap.c
+++ b/fs/xfs/libxfs/xfs_rmap.c
@@ -2709,13 +2709,17 @@ xfs_rmap_compare(
 		return 0;
 }
 
-/* Is there a record covering a given extent? */
+/*
+ * Scan the physical storage part of the keyspace of the reverse mapping index
+ * and tell us if the area has no records, is fully mapped by records, or is
+ * partially filled.
+ */
 int
-xfs_rmap_has_record(
+xfs_rmap_has_records(
 	struct xfs_btree_cur	*cur,
 	xfs_agblock_t		bno,
 	xfs_extlen_t		len,
-	bool			*exists)
+	enum xbtree_recpacking	*outcome)
 {
 	union xfs_btree_irec	low;
 	union xfs_btree_irec	high;
@@ -2725,7 +2729,7 @@ xfs_rmap_has_record(
 	memset(&high, 0xFF, sizeof(high));
 	high.r.rm_startblock = bno + len - 1;
 
-	return xfs_btree_has_record(cur, &low, &high, exists);
+	return xfs_btree_has_records(cur, &low, &high, outcome);
 }
 
 /*
diff --git a/fs/xfs/libxfs/xfs_rmap.h b/fs/xfs/libxfs/xfs_rmap.h
index 7fb298bcc15f..4cbe50cf522e 100644
--- a/fs/xfs/libxfs/xfs_rmap.h
+++ b/fs/xfs/libxfs/xfs_rmap.h
@@ -198,8 +198,8 @@ xfs_failaddr_t xfs_rmap_btrec_to_irec(const union xfs_btree_rec *rec,
 xfs_failaddr_t xfs_rmap_check_irec(struct xfs_btree_cur *cur,
 		const 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_has_records(struct xfs_btree_cur *cur, xfs_agblock_t bno,
+		xfs_extlen_t len, enum xbtree_recpacking *outcome);
 int xfs_rmap_record_exists(struct xfs_btree_cur *cur, xfs_agblock_t bno,
 		xfs_extlen_t len, const struct xfs_owner_info *oinfo,
 		bool *has_rmap);
diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c
index 84e2b692f034..66beb87caf1a 100644
--- a/fs/xfs/libxfs/xfs_rmap_btree.c
+++ b/fs/xfs/libxfs/xfs_rmap_btree.c
@@ -444,6 +444,21 @@ xfs_rmapbt_recs_inorder(
 	return 0;
 }
 
+STATIC enum xbtree_key_contig
+xfs_rmapbt_keys_contiguous(
+	struct xfs_btree_cur		*cur,
+	const union xfs_btree_key	*key1,
+	const union xfs_btree_key	*key2)
+{
+	/*
+	 * We only support checking contiguity of the physical space component.
+	 * If any callers ever need more specificity than that, they'll have to
+	 * implement it here.
+	 */
+	return xbtree_key_contig(be32_to_cpu(key1->rmap.rm_startblock),
+				 be32_to_cpu(key2->rmap.rm_startblock));
+}
+
 static const struct xfs_btree_ops xfs_rmapbt_ops = {
 	.rec_len		= sizeof(struct xfs_rmap_rec),
 	.key_len		= 2 * sizeof(struct xfs_rmap_key),
@@ -463,6 +478,7 @@ static const struct xfs_btree_ops xfs_rmapbt_ops = {
 	.diff_two_keys		= xfs_rmapbt_diff_two_keys,
 	.keys_inorder		= xfs_rmapbt_keys_inorder,
 	.recs_inorder		= xfs_rmapbt_recs_inorder,
+	.keys_contiguous	= xfs_rmapbt_keys_contiguous,
 };
 
 static struct xfs_btree_cur *
diff --git a/fs/xfs/libxfs/xfs_types.h b/fs/xfs/libxfs/xfs_types.h
index 5ebdda7e1078..851220021484 100644
--- a/fs/xfs/libxfs/xfs_types.h
+++ b/fs/xfs/libxfs/xfs_types.h
@@ -204,6 +204,18 @@ enum xfs_ag_resv_type {
 	XFS_AG_RESV_RMAPBT,
 };
 
+/* Results of scanning a btree keyspace to check occupancy. */
+enum xbtree_recpacking {
+	/* None of the keyspace maps to records. */
+	XBTREE_RECPACKING_EMPTY = 0,
+
+	/* Some, but not all, of the keyspace maps to records. */
+	XBTREE_RECPACKING_SPARSE,
+
+	/* The entire keyspace maps to records. */
+	XBTREE_RECPACKING_FULL,
+};
+
 /*
  * Type verifier functions
  */
diff --git a/fs/xfs/scrub/alloc.c b/fs/xfs/scrub/alloc.c
index 53de04c6027c..5920fe051543 100644
--- a/fs/xfs/scrub/alloc.c
+++ b/fs/xfs/scrub/alloc.c
@@ -144,15 +144,15 @@ xchk_xref_is_used_space(
 	xfs_agblock_t		agbno,
 	xfs_extlen_t		len)
 {
-	bool			is_freesp;
+	enum xbtree_recpacking	outcome;
 	int			error;
 
 	if (!sc->sa.bno_cur || xchk_skip_xref(sc->sm))
 		return;
 
-	error = xfs_alloc_has_record(sc->sa.bno_cur, agbno, len, &is_freesp);
+	error = xfs_alloc_has_records(sc->sa.bno_cur, agbno, len, &outcome);
 	if (!xchk_should_check_xref(sc, &error, &sc->sa.bno_cur))
 		return;
-	if (is_freesp)
+	if (outcome != XBTREE_RECPACKING_EMPTY)
 		xchk_btree_xref_set_corrupt(sc, sc->sa.bno_cur, 0);
 }
diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c
index 4d77049dfce2..ed47c570c658 100644
--- a/fs/xfs/scrub/refcount.c
+++ b/fs/xfs/scrub/refcount.c
@@ -457,16 +457,16 @@ xchk_xref_is_not_shared(
 	xfs_agblock_t		agbno,
 	xfs_extlen_t		len)
 {
-	bool			shared;
+	enum xbtree_recpacking	outcome;
 	int			error;
 
 	if (!sc->sa.refc_cur || xchk_skip_xref(sc->sm))
 		return;
 
-	error = xfs_refcount_has_record(sc->sa.refc_cur, XFS_REFC_DOMAIN_SHARED,
-			agbno, len, &shared);
+	error = xfs_refcount_has_records(sc->sa.refc_cur,
+			XFS_REFC_DOMAIN_SHARED, agbno, len, &outcome);
 	if (!xchk_should_check_xref(sc, &error, &sc->sa.refc_cur))
 		return;
-	if (shared)
+	if (outcome != XBTREE_RECPACKING_EMPTY)
 		xchk_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0);
 }
diff --git a/fs/xfs/scrub/rmap.c b/fs/xfs/scrub/rmap.c
index 8e78e1bc9eef..2f9e4f77db6b 100644
--- a/fs/xfs/scrub/rmap.c
+++ b/fs/xfs/scrub/rmap.c
@@ -219,15 +219,15 @@ xchk_xref_has_no_owner(
 	xfs_agblock_t		bno,
 	xfs_extlen_t		len)
 {
-	bool			has_rmap;
+	enum xbtree_recpacking	outcome;
 	int			error;
 
 	if (!sc->sa.rmap_cur || xchk_skip_xref(sc->sm))
 		return;
 
-	error = xfs_rmap_has_record(sc->sa.rmap_cur, bno, len, &has_rmap);
+	error = xfs_rmap_has_records(sc->sa.rmap_cur, bno, len, &outcome);
 	if (!xchk_should_check_xref(sc, &error, &sc->sa.rmap_cur))
 		return;
-	if (has_rmap)
+	if (outcome != XBTREE_RECPACKING_EMPTY)
 		xchk_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
 }
-- 
cgit 


From 4a200a0978288f919aba3f015f374f6ed279e658 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Tue, 11 Apr 2023 19:00:11 -0700
Subject: xfs: implement masked btree key comparisons for _has_records scans

For keyspace fullness scans, we want to be able to mask off the parts of
the key that we don't care about.  For most btree types we /do/ want the
full keyspace, but for checking that a given space usage also has a full
complement of rmapbt records (even if different/multiple owners) we need
this masking so that we only track sparseness of rm_startblock, not the
whole keyspace (which is extremely sparse).

Augment the ->diff_two_keys and ->keys_contiguous helpers to take a
third union xfs_btree_key argument, and wire up xfs_rmap_has_records to
pass this through.  This third "mask" argument should contain a nonzero
value in each structure field that should be used in the key comparisons
done during the scan.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
---
 fs/xfs/libxfs/xfs_alloc.c          |  2 +-
 fs/xfs/libxfs/xfs_alloc_btree.c    | 18 +++++++++++---
 fs/xfs/libxfs/xfs_bmap_btree.c     | 10 ++++++--
 fs/xfs/libxfs/xfs_btree.c          | 24 +++++++++++++++---
 fs/xfs/libxfs/xfs_btree.h          | 50 +++++++++++++++++++++++++++++++++-----
 fs/xfs/libxfs/xfs_ialloc_btree.c   | 12 ++++++---
 fs/xfs/libxfs/xfs_refcount.c       |  2 +-
 fs/xfs/libxfs/xfs_refcount_btree.c | 12 ++++++---
 fs/xfs/libxfs/xfs_rmap.c           |  5 +++-
 fs/xfs/libxfs/xfs_rmap_btree.c     | 47 +++++++++++++++++++++++------------
 10 files changed, 142 insertions(+), 40 deletions(-)

(limited to 'fs/xfs/libxfs/xfs_rmap.c')

diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 34c8501d86d0..fdfa08cbf4db 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -3764,7 +3764,7 @@ xfs_alloc_has_records(
 	memset(&high, 0xFF, sizeof(high));
 	high.a.ar_startblock = bno + len - 1;
 
-	return xfs_btree_has_records(cur, &low, &high, outcome);
+	return xfs_btree_has_records(cur, &low, &high, NULL, outcome);
 }
 
 /*
diff --git a/fs/xfs/libxfs/xfs_alloc_btree.c b/fs/xfs/libxfs/xfs_alloc_btree.c
index be80c57aeddc..c65228efed4a 100644
--- a/fs/xfs/libxfs/xfs_alloc_btree.c
+++ b/fs/xfs/libxfs/xfs_alloc_btree.c
@@ -260,20 +260,27 @@ STATIC int64_t
 xfs_bnobt_diff_two_keys(
 	struct xfs_btree_cur		*cur,
 	const union xfs_btree_key	*k1,
-	const union xfs_btree_key	*k2)
+	const union xfs_btree_key	*k2,
+	const union xfs_btree_key	*mask)
 {
+	ASSERT(!mask || mask->alloc.ar_startblock);
+
 	return (int64_t)be32_to_cpu(k1->alloc.ar_startblock) -
-			  be32_to_cpu(k2->alloc.ar_startblock);
+			be32_to_cpu(k2->alloc.ar_startblock);
 }
 
 STATIC int64_t
 xfs_cntbt_diff_two_keys(
 	struct xfs_btree_cur		*cur,
 	const union xfs_btree_key	*k1,
-	const union xfs_btree_key	*k2)
+	const union xfs_btree_key	*k2,
+	const union xfs_btree_key	*mask)
 {
 	int64_t				diff;
 
+	ASSERT(!mask || (mask->alloc.ar_blockcount &&
+			 mask->alloc.ar_startblock));
+
 	diff =  be32_to_cpu(k1->alloc.ar_blockcount) -
 		be32_to_cpu(k2->alloc.ar_blockcount);
 	if (diff)
@@ -427,8 +434,11 @@ STATIC enum xbtree_key_contig
 xfs_allocbt_keys_contiguous(
 	struct xfs_btree_cur		*cur,
 	const union xfs_btree_key	*key1,
-	const union xfs_btree_key	*key2)
+	const union xfs_btree_key	*key2,
+	const union xfs_btree_key	*mask)
 {
+	ASSERT(!mask || mask->alloc.ar_startblock);
+
 	return xbtree_key_contig(be32_to_cpu(key1->alloc.ar_startblock),
 				 be32_to_cpu(key2->alloc.ar_startblock));
 }
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index 3edf314a55e2..1b40e5f8b1ec 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -382,11 +382,14 @@ STATIC int64_t
 xfs_bmbt_diff_two_keys(
 	struct xfs_btree_cur		*cur,
 	const union xfs_btree_key	*k1,
-	const union xfs_btree_key	*k2)
+	const union xfs_btree_key	*k2,
+	const union xfs_btree_key	*mask)
 {
 	uint64_t			a = be64_to_cpu(k1->bmbt.br_startoff);
 	uint64_t			b = be64_to_cpu(k2->bmbt.br_startoff);
 
+	ASSERT(!mask || mask->bmbt.br_startoff);
+
 	/*
 	 * Note: This routine previously casted a and b to int64 and subtracted
 	 * them to generate a result.  This lead to problems if b was the
@@ -504,8 +507,11 @@ STATIC enum xbtree_key_contig
 xfs_bmbt_keys_contiguous(
 	struct xfs_btree_cur		*cur,
 	const union xfs_btree_key	*key1,
-	const union xfs_btree_key	*key2)
+	const union xfs_btree_key	*key2,
+	const union xfs_btree_key	*mask)
 {
+	ASSERT(!mask || mask->bmbt.br_startoff);
+
 	return xbtree_key_contig(be64_to_cpu(key1->bmbt.br_startoff),
 				 be64_to_cpu(key2->bmbt.br_startoff));
 }
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index afbd3bcdf567..6a6503ab0cd7 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -5030,6 +5030,9 @@ struct xfs_btree_has_records {
 	union xfs_btree_key		start_key;
 	union xfs_btree_key		end_key;
 
+	/* Mask for key comparisons, if desired. */
+	const union xfs_btree_key	*key_mask;
+
 	/* Highest record key we've seen so far. */
 	union xfs_btree_key		high_key;
 
@@ -5057,7 +5060,8 @@ xfs_btree_has_records_helper(
 		 * then there is a hole at the start of the search range.
 		 * Classify this as sparse and stop immediately.
 		 */
-		if (xfs_btree_keycmp_lt(cur, &info->start_key, &rec_key))
+		if (xfs_btree_masked_keycmp_lt(cur, &info->start_key, &rec_key,
+					info->key_mask))
 			return -ECANCELED;
 	} else {
 		/*
@@ -5068,7 +5072,7 @@ xfs_btree_has_records_helper(
 		 * signal corruption.
 		 */
 		key_contig = cur->bc_ops->keys_contiguous(cur, &info->high_key,
-					&rec_key);
+					&rec_key, info->key_mask);
 		if (key_contig == XBTREE_KEY_OVERLAP &&
 				!(cur->bc_flags & XFS_BTREE_OVERLAPPING))
 			return -EFSCORRUPTED;
@@ -5081,7 +5085,8 @@ xfs_btree_has_records_helper(
 	 * remember it for later.
 	 */
 	cur->bc_ops->init_high_key_from_rec(&rec_high_key, rec);
-	if (xfs_btree_keycmp_gt(cur, &rec_high_key, &info->high_key))
+	if (xfs_btree_masked_keycmp_gt(cur, &rec_high_key, &info->high_key,
+				info->key_mask))
 		info->high_key = rec_high_key; /* struct copy */
 
 	return 0;
@@ -5092,16 +5097,26 @@ xfs_btree_has_records_helper(
  * map to any records; is fully mapped to records; or is partially mapped to
  * records.  This is the btree record equivalent to determining if a file is
  * sparse.
+ *
+ * For most btree types, the record scan should use all available btree key
+ * fields to compare the keys encountered.  These callers should pass NULL for
+ * @mask.  However, some callers (e.g.  scanning physical space in the rmapbt)
+ * want to ignore some part of the btree record keyspace when performing the
+ * comparison.  These callers should pass in a union xfs_btree_key object with
+ * the fields that *should* be a part of the comparison set to any nonzero
+ * value, and the rest zeroed.
  */
 int
 xfs_btree_has_records(
 	struct xfs_btree_cur		*cur,
 	const union xfs_btree_irec	*low,
 	const union xfs_btree_irec	*high,
+	const union xfs_btree_key	*mask,
 	enum xbtree_recpacking		*outcome)
 {
 	struct xfs_btree_has_records	info = {
 		.outcome		= XBTREE_RECPACKING_EMPTY,
+		.key_mask		= mask,
 	};
 	int				error;
 
@@ -5129,7 +5144,8 @@ xfs_btree_has_records(
 	 * the end of the search range, classify this as full.  Otherwise,
 	 * there is a hole at the end of the search range.
 	 */
-	if (xfs_btree_keycmp_ge(cur, &info.high_key, &info.end_key))
+	if (xfs_btree_masked_keycmp_ge(cur, &info.high_key, &info.end_key,
+				mask))
 		info.outcome = XBTREE_RECPACKING_FULL;
 
 out:
diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h
index 66431f351bb2..a2aa36b23e25 100644
--- a/fs/xfs/libxfs/xfs_btree.h
+++ b/fs/xfs/libxfs/xfs_btree.h
@@ -161,11 +161,14 @@ struct xfs_btree_ops {
 
 	/*
 	 * Difference between key2 and key1 -- positive if key1 > key2,
-	 * negative if key1 < key2, and zero if equal.
+	 * negative if key1 < key2, and zero if equal.  If the @mask parameter
+	 * is non NULL, each key field to be used in the comparison must
+	 * contain a nonzero value.
 	 */
 	int64_t (*diff_two_keys)(struct xfs_btree_cur *cur,
 				 const union xfs_btree_key *key1,
-				 const union xfs_btree_key *key2);
+				 const union xfs_btree_key *key2,
+				 const union xfs_btree_key *mask);
 
 	const struct xfs_buf_ops	*buf_ops;
 
@@ -187,10 +190,13 @@ struct xfs_btree_ops {
 	 * @key1 < K < @key2.  To determine if two btree records are
 	 * immediately adjacent, @key1 should be the high key of the first
 	 * record and @key2 should be the low key of the second record.
+	 * If the @mask parameter is non NULL, each key field to be used in the
+	 * comparison must contain a nonzero value.
 	 */
 	enum xbtree_key_contig (*keys_contiguous)(struct xfs_btree_cur *cur,
 			       const union xfs_btree_key *key1,
-			       const union xfs_btree_key *key2);
+			       const union xfs_btree_key *key2,
+			       const union xfs_btree_key *mask);
 };
 
 /*
@@ -581,6 +587,7 @@ typedef bool (*xfs_btree_key_gap_fn)(struct xfs_btree_cur *cur,
 int xfs_btree_has_records(struct xfs_btree_cur *cur,
 		const union xfs_btree_irec *low,
 		const union xfs_btree_irec *high,
+		const union xfs_btree_key *mask,
 		enum xbtree_recpacking *outcome);
 
 bool xfs_btree_has_more_records(struct xfs_btree_cur *cur);
@@ -593,7 +600,7 @@ xfs_btree_keycmp_lt(
 	const union xfs_btree_key	*key1,
 	const union xfs_btree_key	*key2)
 {
-	return cur->bc_ops->diff_two_keys(cur, key1, key2) < 0;
+	return cur->bc_ops->diff_two_keys(cur, key1, key2, NULL) < 0;
 }
 
 static inline bool
@@ -602,7 +609,7 @@ xfs_btree_keycmp_gt(
 	const union xfs_btree_key	*key1,
 	const union xfs_btree_key	*key2)
 {
-	return cur->bc_ops->diff_two_keys(cur, key1, key2) > 0;
+	return cur->bc_ops->diff_two_keys(cur, key1, key2, NULL) > 0;
 }
 
 static inline bool
@@ -611,7 +618,7 @@ xfs_btree_keycmp_eq(
 	const union xfs_btree_key	*key1,
 	const union xfs_btree_key	*key2)
 {
-	return cur->bc_ops->diff_two_keys(cur, key1, key2) == 0;
+	return cur->bc_ops->diff_two_keys(cur, key1, key2, NULL) == 0;
 }
 
 static inline bool
@@ -641,6 +648,37 @@ xfs_btree_keycmp_ne(
 	return !xfs_btree_keycmp_eq(cur, key1, key2);
 }
 
+/* Masked key comparison helpers */
+static inline bool
+xfs_btree_masked_keycmp_lt(
+	struct xfs_btree_cur		*cur,
+	const union xfs_btree_key	*key1,
+	const union xfs_btree_key	*key2,
+	const union xfs_btree_key	*mask)
+{
+	return cur->bc_ops->diff_two_keys(cur, key1, key2, mask) < 0;
+}
+
+static inline bool
+xfs_btree_masked_keycmp_gt(
+	struct xfs_btree_cur		*cur,
+	const union xfs_btree_key	*key1,
+	const union xfs_btree_key	*key2,
+	const union xfs_btree_key	*mask)
+{
+	return cur->bc_ops->diff_two_keys(cur, key1, key2, mask) > 0;
+}
+
+static inline bool
+xfs_btree_masked_keycmp_ge(
+	struct xfs_btree_cur		*cur,
+	const union xfs_btree_key	*key1,
+	const union xfs_btree_key	*key2,
+	const union xfs_btree_key	*mask)
+{
+	return !xfs_btree_masked_keycmp_lt(cur, key1, key2, mask);
+}
+
 /* Does this cursor point to the last block in the given level? */
 static inline bool
 xfs_btree_islastblock(
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c
index dd1fad8c3304..5a945ae21b5d 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.c
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.c
@@ -269,10 +269,13 @@ STATIC int64_t
 xfs_inobt_diff_two_keys(
 	struct xfs_btree_cur		*cur,
 	const union xfs_btree_key	*k1,
-	const union xfs_btree_key	*k2)
+	const union xfs_btree_key	*k2,
+	const union xfs_btree_key	*mask)
 {
+	ASSERT(!mask || mask->inobt.ir_startino);
+
 	return (int64_t)be32_to_cpu(k1->inobt.ir_startino) -
-			  be32_to_cpu(k2->inobt.ir_startino);
+			be32_to_cpu(k2->inobt.ir_startino);
 }
 
 static xfs_failaddr_t
@@ -387,8 +390,11 @@ STATIC enum xbtree_key_contig
 xfs_inobt_keys_contiguous(
 	struct xfs_btree_cur		*cur,
 	const union xfs_btree_key	*key1,
-	const union xfs_btree_key	*key2)
+	const union xfs_btree_key	*key2,
+	const union xfs_btree_key	*mask)
 {
+	ASSERT(!mask || mask->inobt.ir_startino);
+
 	return xbtree_key_contig(be32_to_cpu(key1->inobt.ir_startino),
 				 be32_to_cpu(key2->inobt.ir_startino));
 }
diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c
index 94377b59ba44..c1c65774dcc2 100644
--- a/fs/xfs/libxfs/xfs_refcount.c
+++ b/fs/xfs/libxfs/xfs_refcount.c
@@ -2019,7 +2019,7 @@ xfs_refcount_has_records(
 	high.rc.rc_startblock = bno + len - 1;
 	low.rc.rc_domain = high.rc.rc_domain = domain;
 
-	return xfs_btree_has_records(cur, &low, &high, outcome);
+	return xfs_btree_has_records(cur, &low, &high, NULL, outcome);
 }
 
 int __init
diff --git a/fs/xfs/libxfs/xfs_refcount_btree.c b/fs/xfs/libxfs/xfs_refcount_btree.c
index 1628eecb53fd..d4afc5f4e6a5 100644
--- a/fs/xfs/libxfs/xfs_refcount_btree.c
+++ b/fs/xfs/libxfs/xfs_refcount_btree.c
@@ -202,10 +202,13 @@ STATIC int64_t
 xfs_refcountbt_diff_two_keys(
 	struct xfs_btree_cur		*cur,
 	const union xfs_btree_key	*k1,
-	const union xfs_btree_key	*k2)
+	const union xfs_btree_key	*k2,
+	const union xfs_btree_key	*mask)
 {
+	ASSERT(!mask || mask->refc.rc_startblock);
+
 	return (int64_t)be32_to_cpu(k1->refc.rc_startblock) -
-			  be32_to_cpu(k2->refc.rc_startblock);
+			be32_to_cpu(k2->refc.rc_startblock);
 }
 
 STATIC xfs_failaddr_t
@@ -304,8 +307,11 @@ STATIC enum xbtree_key_contig
 xfs_refcountbt_keys_contiguous(
 	struct xfs_btree_cur		*cur,
 	const union xfs_btree_key	*key1,
-	const union xfs_btree_key	*key2)
+	const union xfs_btree_key	*key2,
+	const union xfs_btree_key	*mask)
 {
+	ASSERT(!mask || mask->refc.rc_startblock);
+
 	return xbtree_key_contig(be32_to_cpu(key1->refc.rc_startblock),
 				 be32_to_cpu(key2->refc.rc_startblock));
 }
diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c
index e616b964f11c..308b81f321eb 100644
--- a/fs/xfs/libxfs/xfs_rmap.c
+++ b/fs/xfs/libxfs/xfs_rmap.c
@@ -2721,6 +2721,9 @@ xfs_rmap_has_records(
 	xfs_extlen_t		len,
 	enum xbtree_recpacking	*outcome)
 {
+	union xfs_btree_key	mask = {
+		.rmap.rm_startblock = cpu_to_be32(-1U),
+	};
 	union xfs_btree_irec	low;
 	union xfs_btree_irec	high;
 
@@ -2729,7 +2732,7 @@ xfs_rmap_has_records(
 	memset(&high, 0xFF, sizeof(high));
 	high.r.rm_startblock = bno + len - 1;
 
-	return xfs_btree_has_records(cur, &low, &high, outcome);
+	return xfs_btree_has_records(cur, &low, &high, &mask, outcome);
 }
 
 /*
diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c
index 66beb87caf1a..6c81b20e97d2 100644
--- a/fs/xfs/libxfs/xfs_rmap_btree.c
+++ b/fs/xfs/libxfs/xfs_rmap_btree.c
@@ -273,31 +273,43 @@ STATIC int64_t
 xfs_rmapbt_diff_two_keys(
 	struct xfs_btree_cur		*cur,
 	const union xfs_btree_key	*k1,
-	const union xfs_btree_key	*k2)
+	const union xfs_btree_key	*k2,
+	const union xfs_btree_key	*mask)
 {
 	const struct xfs_rmap_key	*kp1 = &k1->rmap;
 	const struct xfs_rmap_key	*kp2 = &k2->rmap;
 	int64_t				d;
 	__u64				x, y;
 
+	/* Doesn't make sense to mask off the physical space part */
+	ASSERT(!mask || mask->rmap.rm_startblock);
+
 	d = (int64_t)be32_to_cpu(kp1->rm_startblock) -
-		       be32_to_cpu(kp2->rm_startblock);
+		     be32_to_cpu(kp2->rm_startblock);
 	if (d)
 		return d;
 
-	x = be64_to_cpu(kp1->rm_owner);
-	y = be64_to_cpu(kp2->rm_owner);
-	if (x > y)
-		return 1;
-	else if (y > x)
-		return -1;
+	if (!mask || mask->rmap.rm_owner) {
+		x = be64_to_cpu(kp1->rm_owner);
+		y = be64_to_cpu(kp2->rm_owner);
+		if (x > y)
+			return 1;
+		else if (y > x)
+			return -1;
+	}
+
+	if (!mask || mask->rmap.rm_offset) {
+		/* Doesn't make sense to allow offset but not owner */
+		ASSERT(!mask || mask->rmap.rm_owner);
+
+		x = offset_keymask(be64_to_cpu(kp1->rm_offset));
+		y = offset_keymask(be64_to_cpu(kp2->rm_offset));
+		if (x > y)
+			return 1;
+		else if (y > x)
+			return -1;
+	}
 
-	x = offset_keymask(be64_to_cpu(kp1->rm_offset));
-	y = offset_keymask(be64_to_cpu(kp2->rm_offset));
-	if (x > y)
-		return 1;
-	else if (y > x)
-		return -1;
 	return 0;
 }
 
@@ -448,13 +460,18 @@ STATIC enum xbtree_key_contig
 xfs_rmapbt_keys_contiguous(
 	struct xfs_btree_cur		*cur,
 	const union xfs_btree_key	*key1,
-	const union xfs_btree_key	*key2)
+	const union xfs_btree_key	*key2,
+	const union xfs_btree_key	*mask)
 {
+	ASSERT(!mask || mask->rmap.rm_startblock);
+
 	/*
 	 * We only support checking contiguity of the physical space component.
 	 * If any callers ever need more specificity than that, they'll have to
 	 * implement it here.
 	 */
+	ASSERT(!mask || (!mask->rmap.rm_owner && !mask->rmap.rm_offset));
+
 	return xbtree_key_contig(be32_to_cpu(key1->rmap.rm_startblock),
 				 be32_to_cpu(key2->rmap.rm_startblock));
 }
-- 
cgit 


From 69115f775f6e8e972a40aa6aa1523bcb0b252b1c Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Tue, 11 Apr 2023 19:00:15 -0700
Subject: xfs: teach scrub to check for sole ownership of metadata objects

Strengthen online scrub's checking even further by enabling us to check
that a range of blocks are owned solely by a given owner.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
---
 fs/xfs/libxfs/xfs_rmap.c | 192 ++++++++++++++++++++++++++++++++---------------
 fs/xfs/libxfs/xfs_rmap.h |  18 ++++-
 fs/xfs/scrub/agheader.c  |  10 +--
 fs/xfs/scrub/btree.c     |   2 +-
 fs/xfs/scrub/ialloc.c    |   4 +-
 fs/xfs/scrub/inode.c     |   2 +-
 fs/xfs/scrub/rmap.c      |  45 +++++------
 fs/xfs/scrub/scrub.h     |   2 +-
 8 files changed, 182 insertions(+), 93 deletions(-)

(limited to 'fs/xfs/libxfs/xfs_rmap.c')

diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c
index 308b81f321eb..f4dc23b3b837 100644
--- a/fs/xfs/libxfs/xfs_rmap.c
+++ b/fs/xfs/libxfs/xfs_rmap.c
@@ -2735,65 +2735,141 @@ xfs_rmap_has_records(
 	return xfs_btree_has_records(cur, &low, &high, &mask, outcome);
 }
 
-/*
- * Is there a record for this owner completely covering a given physical
- * extent?  If so, *has_rmap will be set to true.  If there is no record
- * or the record only covers part of the range, we set *has_rmap to false.
- * This function doesn't perform range lookups or offset checks, so it is
- * not suitable for checking data fork blocks.
- */
-int
-xfs_rmap_record_exists(
-	struct xfs_btree_cur		*cur,
+struct xfs_rmap_ownercount {
+	/* Owner that we're looking for. */
+	struct xfs_rmap_irec	good;
+
+	/* rmap search keys */
+	struct xfs_rmap_irec	low;
+	struct xfs_rmap_irec	high;
+
+	struct xfs_rmap_matches	*results;
+
+	/* Stop early if we find a nonmatch? */
+	bool			stop_on_nonmatch;
+};
+
+/* Does this rmap represent space that can have multiple owners? */
+static inline bool
+xfs_rmap_shareable(
+	struct xfs_mount		*mp,
+	const struct xfs_rmap_irec	*rmap)
+{
+	if (!xfs_has_reflink(mp))
+		return false;
+	if (XFS_RMAP_NON_INODE_OWNER(rmap->rm_owner))
+		return false;
+	if (rmap->rm_flags & (XFS_RMAP_ATTR_FORK |
+			      XFS_RMAP_BMBT_BLOCK))
+		return false;
+	return true;
+}
+
+static inline void
+xfs_rmap_ownercount_init(
+	struct xfs_rmap_ownercount	*roc,
 	xfs_agblock_t			bno,
 	xfs_extlen_t			len,
 	const struct xfs_owner_info	*oinfo,
-	bool				*has_rmap)
+	struct xfs_rmap_matches		*results)
 {
-	uint64_t			owner;
-	uint64_t			offset;
-	unsigned int			flags;
-	int				has_record;
-	struct xfs_rmap_irec		irec;
-	int				error;
+	memset(roc, 0, sizeof(*roc));
+	roc->results = results;
+
+	roc->low.rm_startblock = bno;
+	memset(&roc->high, 0xFF, sizeof(roc->high));
+	roc->high.rm_startblock = bno + len - 1;
+
+	memset(results, 0, sizeof(*results));
+	roc->good.rm_startblock = bno;
+	roc->good.rm_blockcount = len;
+	roc->good.rm_owner = oinfo->oi_owner;
+	roc->good.rm_offset = oinfo->oi_offset;
+	if (oinfo->oi_flags & XFS_OWNER_INFO_ATTR_FORK)
+		roc->good.rm_flags |= XFS_RMAP_ATTR_FORK;
+	if (oinfo->oi_flags & XFS_OWNER_INFO_BMBT_BLOCK)
+		roc->good.rm_flags |= XFS_RMAP_BMBT_BLOCK;
+}
 
-	xfs_owner_info_unpack(oinfo, &owner, &offset, &flags);
-	ASSERT(XFS_RMAP_NON_INODE_OWNER(owner) ||
-	       (flags & XFS_RMAP_BMBT_BLOCK));
+/* Figure out if this is a match for the owner. */
+STATIC int
+xfs_rmap_count_owners_helper(
+	struct xfs_btree_cur		*cur,
+	const struct xfs_rmap_irec	*rec,
+	void				*priv)
+{
+	struct xfs_rmap_ownercount	*roc = priv;
+	struct xfs_rmap_irec		check = *rec;
+	unsigned int			keyflags;
+	bool				filedata;
+	int64_t				delta;
+
+	filedata = !XFS_RMAP_NON_INODE_OWNER(check.rm_owner) &&
+		   !(check.rm_flags & XFS_RMAP_BMBT_BLOCK);
+
+	/* Trim the part of check that comes before the comparison range. */
+	delta = (int64_t)roc->good.rm_startblock - check.rm_startblock;
+	if (delta > 0) {
+		check.rm_startblock += delta;
+		check.rm_blockcount -= delta;
+		if (filedata)
+			check.rm_offset += delta;
+	}
 
-	error = xfs_rmap_lookup_le(cur, bno, owner, offset, flags, &irec,
-			&has_record);
-	if (error)
-		return error;
-	if (!has_record) {
-		*has_rmap = false;
-		return 0;
+	/* Trim the part of check that comes after the comparison range. */
+	delta = (check.rm_startblock + check.rm_blockcount) -
+		(roc->good.rm_startblock + roc->good.rm_blockcount);
+	if (delta > 0)
+		check.rm_blockcount -= delta;
+
+	/* Don't care about unwritten status for establishing ownership. */
+	keyflags = check.rm_flags & (XFS_RMAP_ATTR_FORK | XFS_RMAP_BMBT_BLOCK);
+
+	if (check.rm_startblock	== roc->good.rm_startblock &&
+	    check.rm_blockcount	== roc->good.rm_blockcount &&
+	    check.rm_owner	== roc->good.rm_owner &&
+	    check.rm_offset	== roc->good.rm_offset &&
+	    keyflags		== roc->good.rm_flags) {
+		roc->results->matches++;
+	} else {
+		roc->results->non_owner_matches++;
+		if (xfs_rmap_shareable(cur->bc_mp, &roc->good) ^
+		    xfs_rmap_shareable(cur->bc_mp, &check))
+			roc->results->bad_non_owner_matches++;
 	}
 
-	*has_rmap = (irec.rm_owner == owner && irec.rm_startblock <= bno &&
-		     irec.rm_startblock + irec.rm_blockcount >= bno + len);
+	if (roc->results->non_owner_matches && roc->stop_on_nonmatch)
+		return -ECANCELED;
+
 	return 0;
 }
 
-struct xfs_rmap_key_state {
-	uint64_t			owner;
-	uint64_t			offset;
-	unsigned int			flags;
-};
-
-/* For each rmap given, figure out if it doesn't match the key we want. */
-STATIC int
-xfs_rmap_has_other_keys_helper(
+/* Count the number of owners and non-owners of this range of blocks. */
+int
+xfs_rmap_count_owners(
 	struct xfs_btree_cur		*cur,
-	const struct xfs_rmap_irec	*rec,
-	void				*priv)
+	xfs_agblock_t			bno,
+	xfs_extlen_t			len,
+	const struct xfs_owner_info	*oinfo,
+	struct xfs_rmap_matches		*results)
 {
-	struct xfs_rmap_key_state	*rks = priv;
+	struct xfs_rmap_ownercount	roc;
+	int				error;
 
-	if (rks->owner == rec->rm_owner && rks->offset == rec->rm_offset &&
-	    ((rks->flags & rec->rm_flags) & XFS_RMAP_KEY_FLAGS) == rks->flags)
-		return 0;
-	return -ECANCELED;
+	xfs_rmap_ownercount_init(&roc, bno, len, oinfo, results);
+	error = xfs_rmap_query_range(cur, &roc.low, &roc.high,
+			xfs_rmap_count_owners_helper, &roc);
+	if (error)
+		return error;
+
+	/*
+	 * There can't be any non-owner rmaps that conflict with the given
+	 * owner if we didn't find any rmaps matching the owner.
+	 */
+	if (!results->matches)
+		results->bad_non_owner_matches = 0;
+
+	return 0;
 }
 
 /*
@@ -2806,28 +2882,26 @@ xfs_rmap_has_other_keys(
 	xfs_agblock_t			bno,
 	xfs_extlen_t			len,
 	const struct xfs_owner_info	*oinfo,
-	bool				*has_rmap)
+	bool				*has_other)
 {
-	struct xfs_rmap_irec		low = {0};
-	struct xfs_rmap_irec		high;
-	struct xfs_rmap_key_state	rks;
+	struct xfs_rmap_matches		res;
+	struct xfs_rmap_ownercount	roc;
 	int				error;
 
-	xfs_owner_info_unpack(oinfo, &rks.owner, &rks.offset, &rks.flags);
-	*has_rmap = false;
-
-	low.rm_startblock = bno;
-	memset(&high, 0xFF, sizeof(high));
-	high.rm_startblock = bno + len - 1;
+	xfs_rmap_ownercount_init(&roc, bno, len, oinfo, &res);
+	roc.stop_on_nonmatch = true;
 
-	error = xfs_rmap_query_range(cur, &low, &high,
-			xfs_rmap_has_other_keys_helper, &rks);
+	error = xfs_rmap_query_range(cur, &roc.low, &roc.high,
+			xfs_rmap_count_owners_helper, &roc);
 	if (error == -ECANCELED) {
-		*has_rmap = true;
+		*has_other = true;
 		return 0;
 	}
+	if (error)
+		return error;
 
-	return error;
+	*has_other = false;
+	return 0;
 }
 
 const struct xfs_owner_info XFS_RMAP_OINFO_SKIP_UPDATE = {
diff --git a/fs/xfs/libxfs/xfs_rmap.h b/fs/xfs/libxfs/xfs_rmap.h
index 4cbe50cf522e..3c98d9d50afb 100644
--- a/fs/xfs/libxfs/xfs_rmap.h
+++ b/fs/xfs/libxfs/xfs_rmap.h
@@ -200,12 +200,24 @@ xfs_failaddr_t xfs_rmap_check_irec(struct xfs_btree_cur *cur,
 
 int xfs_rmap_has_records(struct xfs_btree_cur *cur, xfs_agblock_t bno,
 		xfs_extlen_t len, enum xbtree_recpacking *outcome);
-int xfs_rmap_record_exists(struct xfs_btree_cur *cur, xfs_agblock_t bno,
+
+struct xfs_rmap_matches {
+	/* Number of owner matches. */
+	unsigned long long	matches;
+
+	/* Number of non-owner matches. */
+	unsigned long long	non_owner_matches;
+
+	/* Number of non-owner matches that conflict with the owner matches. */
+	unsigned long long	bad_non_owner_matches;
+};
+
+int xfs_rmap_count_owners(struct xfs_btree_cur *cur, xfs_agblock_t bno,
 		xfs_extlen_t len, const struct xfs_owner_info *oinfo,
-		bool *has_rmap);
+		struct xfs_rmap_matches *rmatch);
 int xfs_rmap_has_other_keys(struct xfs_btree_cur *cur, xfs_agblock_t bno,
 		xfs_extlen_t len, const struct xfs_owner_info *oinfo,
-		bool *has_rmap);
+		bool *has_other);
 int xfs_rmap_map_raw(struct xfs_btree_cur *cur, struct xfs_rmap_irec *rmap);
 
 extern const struct xfs_owner_info XFS_RMAP_OINFO_SKIP_UPDATE;
diff --git a/fs/xfs/scrub/agheader.c b/fs/xfs/scrub/agheader.c
index 1a84153afa91..6c6e5eba42c8 100644
--- a/fs/xfs/scrub/agheader.c
+++ b/fs/xfs/scrub/agheader.c
@@ -51,7 +51,7 @@ xchk_superblock_xref(
 
 	xchk_xref_is_used_space(sc, agbno, 1);
 	xchk_xref_is_not_inode_chunk(sc, agbno, 1);
-	xchk_xref_is_owned_by(sc, agbno, 1, &XFS_RMAP_OINFO_FS);
+	xchk_xref_is_only_owned_by(sc, agbno, 1, &XFS_RMAP_OINFO_FS);
 	xchk_xref_is_not_shared(sc, agbno, 1);
 	xchk_xref_is_not_cow_staging(sc, agbno, 1);
 
@@ -515,7 +515,7 @@ xchk_agf_xref(
 	xchk_agf_xref_freeblks(sc);
 	xchk_agf_xref_cntbt(sc);
 	xchk_xref_is_not_inode_chunk(sc, agbno, 1);
-	xchk_xref_is_owned_by(sc, agbno, 1, &XFS_RMAP_OINFO_FS);
+	xchk_xref_is_only_owned_by(sc, agbno, 1, &XFS_RMAP_OINFO_FS);
 	xchk_agf_xref_btreeblks(sc);
 	xchk_xref_is_not_shared(sc, agbno, 1);
 	xchk_xref_is_not_cow_staging(sc, agbno, 1);
@@ -644,7 +644,7 @@ xchk_agfl_block_xref(
 
 	xchk_xref_is_used_space(sc, agbno, 1);
 	xchk_xref_is_not_inode_chunk(sc, agbno, 1);
-	xchk_xref_is_owned_by(sc, agbno, 1, &XFS_RMAP_OINFO_AG);
+	xchk_xref_is_only_owned_by(sc, agbno, 1, &XFS_RMAP_OINFO_AG);
 	xchk_xref_is_not_shared(sc, agbno, 1);
 	xchk_xref_is_not_cow_staging(sc, agbno, 1);
 }
@@ -701,7 +701,7 @@ xchk_agfl_xref(
 
 	xchk_xref_is_used_space(sc, agbno, 1);
 	xchk_xref_is_not_inode_chunk(sc, agbno, 1);
-	xchk_xref_is_owned_by(sc, agbno, 1, &XFS_RMAP_OINFO_FS);
+	xchk_xref_is_only_owned_by(sc, agbno, 1, &XFS_RMAP_OINFO_FS);
 	xchk_xref_is_not_shared(sc, agbno, 1);
 	xchk_xref_is_not_cow_staging(sc, agbno, 1);
 
@@ -857,7 +857,7 @@ xchk_agi_xref(
 	xchk_xref_is_used_space(sc, agbno, 1);
 	xchk_xref_is_not_inode_chunk(sc, agbno, 1);
 	xchk_agi_xref_icounts(sc);
-	xchk_xref_is_owned_by(sc, agbno, 1, &XFS_RMAP_OINFO_FS);
+	xchk_xref_is_only_owned_by(sc, agbno, 1, &XFS_RMAP_OINFO_FS);
 	xchk_xref_is_not_shared(sc, agbno, 1);
 	xchk_xref_is_not_cow_staging(sc, agbno, 1);
 	xchk_agi_xref_fiblocks(sc);
diff --git a/fs/xfs/scrub/btree.c b/fs/xfs/scrub/btree.c
index 1165dc05a179..1935b9ce1885 100644
--- a/fs/xfs/scrub/btree.c
+++ b/fs/xfs/scrub/btree.c
@@ -402,7 +402,7 @@ xchk_btree_check_block_owner(
 	if (!bs->sc->sa.bno_cur && btnum == XFS_BTNUM_BNO)
 		bs->cur = NULL;
 
-	xchk_xref_is_owned_by(bs->sc, agbno, 1, bs->oinfo);
+	xchk_xref_is_only_owned_by(bs->sc, agbno, 1, bs->oinfo);
 	if (!bs->sc->sa.rmap_cur && btnum == XFS_BTNUM_RMAP)
 		bs->cur = NULL;
 
diff --git a/fs/xfs/scrub/ialloc.c b/fs/xfs/scrub/ialloc.c
index fda96b536730..575f22a02ebe 100644
--- a/fs/xfs/scrub/ialloc.c
+++ b/fs/xfs/scrub/ialloc.c
@@ -276,7 +276,7 @@ xchk_iallocbt_chunk(
 		xchk_inobt_chunk_xref_finobt(sc, irec, agino, nr_inodes);
 	else
 		xchk_finobt_chunk_xref_inobt(sc, irec, agino, nr_inodes);
-	xchk_xref_is_owned_by(sc, agbno, len, &XFS_RMAP_OINFO_INODES);
+	xchk_xref_is_only_owned_by(sc, agbno, len, &XFS_RMAP_OINFO_INODES);
 	xchk_xref_is_not_shared(sc, agbno, len);
 	xchk_xref_is_not_cow_staging(sc, agbno, len);
 	return true;
@@ -428,7 +428,7 @@ xchk_iallocbt_check_cluster(
 		return 0;
 	}
 
-	xchk_xref_is_owned_by(bs->sc, agbno, M_IGEO(mp)->blocks_per_cluster,
+	xchk_xref_is_only_owned_by(bs->sc, agbno, M_IGEO(mp)->blocks_per_cluster,
 			&XFS_RMAP_OINFO_INODES);
 
 	/* Grab the inode cluster buffer. */
diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c
index 50ebd72f6d95..2db96c8a71dc 100644
--- a/fs/xfs/scrub/inode.c
+++ b/fs/xfs/scrub/inode.c
@@ -556,7 +556,7 @@ xchk_inode_xref(
 
 	xchk_xref_is_used_space(sc, agbno, 1);
 	xchk_inode_xref_finobt(sc, ino);
-	xchk_xref_is_owned_by(sc, agbno, 1, &XFS_RMAP_OINFO_INODES);
+	xchk_xref_is_only_owned_by(sc, agbno, 1, &XFS_RMAP_OINFO_INODES);
 	xchk_xref_is_not_shared(sc, agbno, 1);
 	xchk_xref_is_not_cow_staging(sc, agbno, 1);
 	xchk_inode_xref_bmap(sc, dip);
diff --git a/fs/xfs/scrub/rmap.c b/fs/xfs/scrub/rmap.c
index 2f9e4f77db6b..18b64287158e 100644
--- a/fs/xfs/scrub/rmap.c
+++ b/fs/xfs/scrub/rmap.c
@@ -167,38 +167,29 @@ xchk_rmapbt(
 			&XFS_RMAP_OINFO_AG, NULL);
 }
 
-/* xref check that the extent is owned by a given owner */
-static inline void
-xchk_xref_check_owner(
+/* xref check that the extent is owned only by a given owner */
+void
+xchk_xref_is_only_owned_by(
 	struct xfs_scrub		*sc,
 	xfs_agblock_t			bno,
 	xfs_extlen_t			len,
-	const struct xfs_owner_info	*oinfo,
-	bool				should_have_rmap)
+	const struct xfs_owner_info	*oinfo)
 {
-	bool				has_rmap;
+	struct xfs_rmap_matches		res;
 	int				error;
 
 	if (!sc->sa.rmap_cur || xchk_skip_xref(sc->sm))
 		return;
 
-	error = xfs_rmap_record_exists(sc->sa.rmap_cur, bno, len, oinfo,
-			&has_rmap);
+	error = xfs_rmap_count_owners(sc->sa.rmap_cur, bno, len, oinfo, &res);
 	if (!xchk_should_check_xref(sc, &error, &sc->sa.rmap_cur))
 		return;
-	if (has_rmap != should_have_rmap)
+	if (res.matches != 1)
+		xchk_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
+	if (res.bad_non_owner_matches)
+		xchk_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
+	if (res.non_owner_matches)
 		xchk_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
-}
-
-/* xref check that the extent is owned by a given owner */
-void
-xchk_xref_is_owned_by(
-	struct xfs_scrub		*sc,
-	xfs_agblock_t			bno,
-	xfs_extlen_t			len,
-	const struct xfs_owner_info	*oinfo)
-{
-	xchk_xref_check_owner(sc, bno, len, oinfo, true);
 }
 
 /* xref check that the extent is not owned by a given owner */
@@ -209,7 +200,19 @@ xchk_xref_is_not_owned_by(
 	xfs_extlen_t			len,
 	const struct xfs_owner_info	*oinfo)
 {
-	xchk_xref_check_owner(sc, bno, len, oinfo, false);
+	struct xfs_rmap_matches		res;
+	int				error;
+
+	if (!sc->sa.rmap_cur || xchk_skip_xref(sc->sm))
+		return;
+
+	error = xfs_rmap_count_owners(sc->sa.rmap_cur, bno, len, oinfo, &res);
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.rmap_cur))
+		return;
+	if (res.matches != 0)
+		xchk_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
+	if (res.bad_non_owner_matches)
+		xchk_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
 }
 
 /* xref check that the extent has no reverse mapping at all */
diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h
index b6f452eb9645..c519927355fe 100644
--- a/fs/xfs/scrub/scrub.h
+++ b/fs/xfs/scrub/scrub.h
@@ -162,7 +162,7 @@ void xchk_xref_is_not_inode_chunk(struct xfs_scrub *sc, xfs_agblock_t agbno,
 		xfs_extlen_t len);
 void xchk_xref_is_inode_chunk(struct xfs_scrub *sc, xfs_agblock_t agbno,
 		xfs_extlen_t len);
-void xchk_xref_is_owned_by(struct xfs_scrub *sc, xfs_agblock_t agbno,
+void xchk_xref_is_only_owned_by(struct xfs_scrub *sc, xfs_agblock_t agbno,
 		xfs_extlen_t len, const struct xfs_owner_info *oinfo);
 void xchk_xref_is_not_owned_by(struct xfs_scrub *sc, xfs_agblock_t agbno,
 		xfs_extlen_t len, const struct xfs_owner_info *oinfo);
-- 
cgit