From 00e7b3bac1dc8961bd5aa9d39e79131c6bd81181 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Tue, 11 Apr 2023 18:59:55 -0700
Subject: xfs: give xfs_refcount_intent its own perag reference

Give the xfs_refcount_intent a passive reference to the perag structure
data.  This reference will be used to enable scrub intent draining
functionality in subsequent patches.  Any space being modified by a
refcount intent 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_refcount.c | 33 ++++++++++++++-------------------
 1 file changed, 14 insertions(+), 19 deletions(-)

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

diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c
index bcf46aa0d08b..6dc968618e66 100644
--- a/fs/xfs/libxfs/xfs_refcount.c
+++ b/fs/xfs/libxfs/xfs_refcount.c
@@ -1332,26 +1332,22 @@ xfs_refcount_finish_one(
 	xfs_agblock_t			bno;
 	unsigned long			nr_ops = 0;
 	int				shape_changes = 0;
-	struct xfs_perag		*pag;
 
-	pag = xfs_perag_get(mp, XFS_FSB_TO_AGNO(mp, ri->ri_startblock));
 	bno = XFS_FSB_TO_AGBNO(mp, ri->ri_startblock);
 
 	trace_xfs_refcount_deferred(mp, XFS_FSB_TO_AGNO(mp, ri->ri_startblock),
 			ri->ri_type, XFS_FSB_TO_AGBNO(mp, ri->ri_startblock),
 			ri->ri_blockcount);
 
-	if (XFS_TEST_ERROR(false, mp, XFS_ERRTAG_REFCOUNT_FINISH_ONE)) {
-		error = -EIO;
-		goto out_drop;
-	}
+	if (XFS_TEST_ERROR(false, mp, XFS_ERRTAG_REFCOUNT_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) {
 		nr_ops = rcur->bc_ag.refc.nr_ops;
 		shape_changes = rcur->bc_ag.refc.shape_changes;
 		xfs_refcount_finish_one_cleanup(tp, rcur, 0);
@@ -1359,12 +1355,12 @@ xfs_refcount_finish_one(
 		*pcur = NULL;
 	}
 	if (rcur == NULL) {
-		error = xfs_alloc_read_agf(pag, tp, XFS_ALLOC_FLAG_FREEING,
-				&agbp);
+		error = xfs_alloc_read_agf(ri->ri_pag, tp,
+				XFS_ALLOC_FLAG_FREEING, &agbp);
 		if (error)
-			goto out_drop;
+			return error;
 
-		rcur = xfs_refcountbt_init_cursor(mp, tp, agbp, pag);
+		rcur = xfs_refcountbt_init_cursor(mp, tp, agbp, ri->ri_pag);
 		rcur->bc_ag.refc.nr_ops = nr_ops;
 		rcur->bc_ag.refc.shape_changes = shape_changes;
 	}
@@ -1375,7 +1371,7 @@ xfs_refcount_finish_one(
 		error = xfs_refcount_adjust(rcur, &bno, &ri->ri_blockcount,
 				XFS_REFCOUNT_ADJUST_INCREASE);
 		if (error)
-			goto out_drop;
+			return error;
 		if (ri->ri_blockcount > 0)
 			error = xfs_refcount_continue_op(rcur, ri, bno);
 		break;
@@ -1383,31 +1379,29 @@ xfs_refcount_finish_one(
 		error = xfs_refcount_adjust(rcur, &bno, &ri->ri_blockcount,
 				XFS_REFCOUNT_ADJUST_DECREASE);
 		if (error)
-			goto out_drop;
+			return error;
 		if (ri->ri_blockcount > 0)
 			error = xfs_refcount_continue_op(rcur, ri, bno);
 		break;
 	case XFS_REFCOUNT_ALLOC_COW:
 		error = __xfs_refcount_cow_alloc(rcur, bno, ri->ri_blockcount);
 		if (error)
-			goto out_drop;
+			return error;
 		ri->ri_blockcount = 0;
 		break;
 	case XFS_REFCOUNT_FREE_COW:
 		error = __xfs_refcount_cow_free(rcur, bno, ri->ri_blockcount);
 		if (error)
-			goto out_drop;
+			return error;
 		ri->ri_blockcount = 0;
 		break;
 	default:
 		ASSERT(0);
-		error = -EFSCORRUPTED;
+		return -EFSCORRUPTED;
 	}
 	if (!error && ri->ri_blockcount > 0)
-		trace_xfs_refcount_finish_one_leftover(mp, pag->pag_agno,
+		trace_xfs_refcount_finish_one_leftover(mp, ri->ri_pag->pag_agno,
 				ri->ri_type, bno, ri->ri_blockcount);
-out_drop:
-	xfs_perag_put(pag);
 	return error;
 }
 
@@ -1435,6 +1429,7 @@ __xfs_refcount_add(
 	ri->ri_startblock = startblock;
 	ri->ri_blockcount = blockcount;
 
+	xfs_refcount_update_get_group(tp->t_mountp, ri);
 	xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_REFCOUNT, &ri->ri_list);
 }
 
-- 
cgit v1.2.3


From 2b30cc0bf0589d1ea0506c019b9b81de77535c87 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: standardize ondisk to incore conversion for refcount btrees

Create a xfs_refcount_check_irec function to detect corruption in btree
records.  Fix all xfs_refcount_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_refcount.c | 45 ++++++++++++++++++++++++++++++--------------
 fs/xfs/libxfs/xfs_refcount.h |  2 ++
 fs/xfs/scrub/refcount.c      | 14 +++-----------
 3 files changed, 36 insertions(+), 25 deletions(-)

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

diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c
index 6dc968618e66..b77dea10c8bd 100644
--- a/fs/xfs/libxfs/xfs_refcount.c
+++ b/fs/xfs/libxfs/xfs_refcount.c
@@ -120,6 +120,30 @@ xfs_refcount_btrec_to_irec(
 	irec->rc_refcount = be32_to_cpu(rec->refc.rc_refcount);
 }
 
+/* Simple checks for refcount records. */
+xfs_failaddr_t
+xfs_refcount_check_irec(
+	struct xfs_btree_cur		*cur,
+	const struct xfs_refcount_irec	*irec)
+{
+	struct xfs_perag		*pag = cur->bc_ag.pag;
+
+	if (irec->rc_blockcount == 0 || irec->rc_blockcount > MAXREFCEXTLEN)
+		return __this_address;
+
+	if (!xfs_refcount_check_domain(irec))
+		return __this_address;
+
+	/* check for valid extent range, including overflow */
+	if (!xfs_verify_agbext(pag, irec->rc_startblock, irec->rc_blockcount))
+		return __this_address;
+
+	if (irec->rc_refcount == 0 || irec->rc_refcount > MAXREFCOUNT)
+		return __this_address;
+
+	return NULL;
+}
+
 /*
  * Get the data from the pointed-to record.
  */
@@ -132,6 +156,7 @@ xfs_refcount_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);
@@ -139,17 +164,8 @@ xfs_refcount_get_rec(
 		return error;
 
 	xfs_refcount_btrec_to_irec(rec, irec);
-	if (irec->rc_blockcount == 0 || irec->rc_blockcount > MAXREFCEXTLEN)
-		goto out_bad_rec;
-
-	if (!xfs_refcount_check_domain(irec))
-		goto out_bad_rec;
-
-	/* check for valid extent range, including overflow */
-	if (!xfs_verify_agbext(pag, irec->rc_startblock, irec->rc_blockcount))
-		goto out_bad_rec;
-
-	if (irec->rc_refcount == 0 || irec->rc_refcount > MAXREFCOUNT)
+	fa = xfs_refcount_check_irec(cur, irec);
+	if (fa)
 		goto out_bad_rec;
 
 	trace_xfs_refcount_get(cur->bc_mp, pag->pag_agno, irec);
@@ -157,8 +173,8 @@ xfs_refcount_get_rec(
 
 out_bad_rec:
 	xfs_warn(mp,
-		"Refcount BTree record corruption in AG %d detected!",
-		pag->pag_agno);
+		"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);
@@ -1871,7 +1887,8 @@ xfs_refcount_recover_extent(
 	INIT_LIST_HEAD(&rr->rr_list);
 	xfs_refcount_btrec_to_irec(rec, &rr->rr_rrec);
 
-	if (XFS_IS_CORRUPT(cur->bc_mp,
+	if (xfs_refcount_check_irec(cur, &rr->rr_rrec) != NULL ||
+	    XFS_IS_CORRUPT(cur->bc_mp,
 			   rr->rr_rrec.rc_domain != XFS_REFC_DOMAIN_COW)) {
 		kfree(rr);
 		return -EFSCORRUPTED;
diff --git a/fs/xfs/libxfs/xfs_refcount.h b/fs/xfs/libxfs/xfs_refcount.h
index c89f0fcd1ee3..fc0b58d4c379 100644
--- a/fs/xfs/libxfs/xfs_refcount.h
+++ b/fs/xfs/libxfs/xfs_refcount.h
@@ -117,6 +117,8 @@ extern int xfs_refcount_has_record(struct xfs_btree_cur *cur,
 union xfs_btree_rec;
 extern void xfs_refcount_btrec_to_irec(const union xfs_btree_rec *rec,
 		struct xfs_refcount_irec *irec);
+xfs_failaddr_t xfs_refcount_check_irec(struct xfs_btree_cur *cur,
+		const struct xfs_refcount_irec *irec);
 extern int xfs_refcount_insert(struct xfs_btree_cur *cur,
 		struct xfs_refcount_irec *irec, int *stat);
 
diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c
index 6f649cc01310..4d77049dfce2 100644
--- a/fs/xfs/scrub/refcount.c
+++ b/fs/xfs/scrub/refcount.c
@@ -340,24 +340,16 @@ xchk_refcountbt_rec(
 {
 	struct xfs_refcount_irec irec;
 	xfs_agblock_t		*cow_blocks = bs->private;
-	struct xfs_perag	*pag = bs->cur->bc_ag.pag;
 
 	xfs_refcount_btrec_to_irec(rec, &irec);
-
-	/* Check the domain and refcount are not incompatible. */
-	if (!xfs_refcount_check_domain(&irec))
+	if (xfs_refcount_check_irec(bs->cur, &irec) != NULL) {
 		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
+		return 0;
+	}
 
 	if (irec.rc_domain == XFS_REFC_DOMAIN_COW)
 		(*cow_blocks) += irec.rc_blockcount;
 
-	/* Check the extent. */
-	if (!xfs_verify_agbext(pag, irec.rc_startblock, irec.rc_blockcount))
-		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
-
-	if (irec.rc_refcount == 0)
-		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
-
 	xchk_refcountbt_xref(bs->sc, &irec);
 
 	return 0;
-- 
cgit v1.2.3


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_refcount.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 v1.2.3


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_refcount.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 v1.2.3


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_refcount.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 v1.2.3


From 7dfee17b13e5024c5c0ab1911859ded4182de3e5 Mon Sep 17 00:00:00 2001
From: Dave Chinner <dchinner@redhat.com>
Date: Mon, 5 Jun 2023 14:48:15 +1000
Subject: xfs: validate block number being freed before adding to xefi

Bad things happen in defered extent freeing operations if it is
passed a bad block number in the xefi. This can come from a bogus
agno/agbno pair from deferred agfl freeing, or just a bad fsbno
being passed to __xfs_free_extent_later(). Either way, it's very
difficult to diagnose where a null perag oops in EFI creation
is coming from when the operation that queued the xefi has already
been completed and there's no longer any trace of it around....

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Dave Chinner <david@fromorbit.com>
---
 fs/xfs/libxfs/xfs_ag.c         |  5 ++++-
 fs/xfs/libxfs/xfs_alloc.c      | 16 +++++++++++++---
 fs/xfs/libxfs/xfs_alloc.h      |  6 +++---
 fs/xfs/libxfs/xfs_bmap.c       | 10 ++++++++--
 fs/xfs/libxfs/xfs_bmap_btree.c |  7 +++++--
 fs/xfs/libxfs/xfs_ialloc.c     | 24 ++++++++++++++++--------
 fs/xfs/libxfs/xfs_refcount.c   | 13 ++++++++++---
 fs/xfs/xfs_reflink.c           |  4 +++-
 8 files changed, 62 insertions(+), 23 deletions(-)

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

diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c
index 9b373a0c7aaf..ee84835ebc66 100644
--- a/fs/xfs/libxfs/xfs_ag.c
+++ b/fs/xfs/libxfs/xfs_ag.c
@@ -984,7 +984,10 @@ xfs_ag_shrink_space(
 		if (err2 != -ENOSPC)
 			goto resv_err;
 
-		__xfs_free_extent_later(*tpp, args.fsbno, delta, NULL, true);
+		err2 = __xfs_free_extent_later(*tpp, args.fsbno, delta, NULL,
+				true);
+		if (err2)
+			goto resv_err;
 
 		/*
 		 * Roll the transaction before trying to re-init the per-ag
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 643d17877832..c20fe99405d8 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -2431,7 +2431,7 @@ xfs_agfl_reset(
  * the real allocation can proceed. Deferring the free disconnects freeing up
  * the AGFL slot from freeing the block.
  */
-STATIC void
+static int
 xfs_defer_agfl_block(
 	struct xfs_trans		*tp,
 	xfs_agnumber_t			agno,
@@ -2450,17 +2450,21 @@ xfs_defer_agfl_block(
 	xefi->xefi_blockcount = 1;
 	xefi->xefi_owner = oinfo->oi_owner;
 
+	if (XFS_IS_CORRUPT(mp, !xfs_verify_fsbno(mp, xefi->xefi_startblock)))
+		return -EFSCORRUPTED;
+
 	trace_xfs_agfl_free_defer(mp, agno, 0, agbno, 1);
 
 	xfs_extent_free_get_group(mp, xefi);
 	xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_AGFL_FREE, &xefi->xefi_list);
+	return 0;
 }
 
 /*
  * Add the extent to the list of extents to be free at transaction end.
  * The list is maintained sorted (by block number).
  */
-void
+int
 __xfs_free_extent_later(
 	struct xfs_trans		*tp,
 	xfs_fsblock_t			bno,
@@ -2487,6 +2491,9 @@ __xfs_free_extent_later(
 #endif
 	ASSERT(xfs_extfree_item_cache != NULL);
 
+	if (XFS_IS_CORRUPT(mp, !xfs_verify_fsbext(mp, bno, len)))
+		return -EFSCORRUPTED;
+
 	xefi = kmem_cache_zalloc(xfs_extfree_item_cache,
 			       GFP_KERNEL | __GFP_NOFAIL);
 	xefi->xefi_startblock = bno;
@@ -2510,6 +2517,7 @@ __xfs_free_extent_later(
 
 	xfs_extent_free_get_group(mp, xefi);
 	xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_FREE, &xefi->xefi_list);
+	return 0;
 }
 
 #ifdef DEBUG
@@ -2670,7 +2678,9 @@ xfs_alloc_fix_freelist(
 			goto out_agbp_relse;
 
 		/* defer agfl frees */
-		xfs_defer_agfl_block(tp, args->agno, bno, &targs.oinfo);
+		error = xfs_defer_agfl_block(tp, args->agno, bno, &targs.oinfo);
+		if (error)
+			goto out_agbp_relse;
 	}
 
 	targs.tp = tp;
diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h
index 5dbb25546d0b..85ac470be0da 100644
--- a/fs/xfs/libxfs/xfs_alloc.h
+++ b/fs/xfs/libxfs/xfs_alloc.h
@@ -230,7 +230,7 @@ xfs_buf_to_agfl_bno(
 	return bp->b_addr;
 }
 
-void __xfs_free_extent_later(struct xfs_trans *tp, xfs_fsblock_t bno,
+int __xfs_free_extent_later(struct xfs_trans *tp, xfs_fsblock_t bno,
 		xfs_filblks_t len, const struct xfs_owner_info *oinfo,
 		bool skip_discard);
 
@@ -254,14 +254,14 @@ void xfs_extent_free_get_group(struct xfs_mount *mp,
 #define XFS_EFI_ATTR_FORK	(1U << 1) /* freeing attr fork block */
 #define XFS_EFI_BMBT_BLOCK	(1U << 2) /* freeing bmap btree block */
 
-static inline void
+static inline int
 xfs_free_extent_later(
 	struct xfs_trans		*tp,
 	xfs_fsblock_t			bno,
 	xfs_filblks_t			len,
 	const struct xfs_owner_info	*oinfo)
 {
-	__xfs_free_extent_later(tp, bno, len, oinfo, false);
+	return __xfs_free_extent_later(tp, bno, len, oinfo, false);
 }
 
 
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index cd8870a16fd1..fef35696adb7 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -572,8 +572,12 @@ xfs_bmap_btree_to_extents(
 	cblock = XFS_BUF_TO_BLOCK(cbp);
 	if ((error = xfs_btree_check_block(cur, cblock, 0, cbp)))
 		return error;
+
 	xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, whichfork);
-	xfs_free_extent_later(cur->bc_tp, cbno, 1, &oinfo);
+	error = xfs_free_extent_later(cur->bc_tp, cbno, 1, &oinfo);
+	if (error)
+		return error;
+
 	ip->i_nblocks--;
 	xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L);
 	xfs_trans_binval(tp, cbp);
@@ -5230,10 +5234,12 @@ xfs_bmap_del_extent_real(
 		if (xfs_is_reflink_inode(ip) && whichfork == XFS_DATA_FORK) {
 			xfs_refcount_decrease_extent(tp, del);
 		} else {
-			__xfs_free_extent_later(tp, del->br_startblock,
+			error = __xfs_free_extent_later(tp, del->br_startblock,
 					del->br_blockcount, NULL,
 					(bflags & XFS_BMAPI_NODISCARD) ||
 					del->br_state == XFS_EXT_UNWRITTEN);
+			if (error)
+				goto done;
 		}
 	}
 
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index 1b40e5f8b1ec..36564ae3084f 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -268,11 +268,14 @@ xfs_bmbt_free_block(
 	struct xfs_trans	*tp = cur->bc_tp;
 	xfs_fsblock_t		fsbno = XFS_DADDR_TO_FSB(mp, xfs_buf_daddr(bp));
 	struct xfs_owner_info	oinfo;
+	int			error;
 
 	xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, cur->bc_ino.whichfork);
-	xfs_free_extent_later(cur->bc_tp, fsbno, 1, &oinfo);
-	ip->i_nblocks--;
+	error = xfs_free_extent_later(cur->bc_tp, fsbno, 1, &oinfo);
+	if (error)
+		return error;
 
+	ip->i_nblocks--;
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 	xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L);
 	return 0;
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index a16d5de16933..34600f94c2f4 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -1834,7 +1834,7 @@ retry:
  * might be sparse and only free the regions that are allocated as part of the
  * chunk.
  */
-STATIC void
+static int
 xfs_difree_inode_chunk(
 	struct xfs_trans		*tp,
 	xfs_agnumber_t			agno,
@@ -1851,10 +1851,10 @@ xfs_difree_inode_chunk(
 
 	if (!xfs_inobt_issparse(rec->ir_holemask)) {
 		/* not sparse, calculate extent info directly */
-		xfs_free_extent_later(tp, XFS_AGB_TO_FSB(mp, agno, sagbno),
-				  M_IGEO(mp)->ialloc_blks,
-				  &XFS_RMAP_OINFO_INODES);
-		return;
+		return xfs_free_extent_later(tp,
+				XFS_AGB_TO_FSB(mp, agno, sagbno),
+				M_IGEO(mp)->ialloc_blks,
+				&XFS_RMAP_OINFO_INODES);
 	}
 
 	/* holemask is only 16-bits (fits in an unsigned long) */
@@ -1871,6 +1871,8 @@ xfs_difree_inode_chunk(
 						XFS_INOBT_HOLEMASK_BITS);
 	nextbit = startidx + 1;
 	while (startidx < XFS_INOBT_HOLEMASK_BITS) {
+		int error;
+
 		nextbit = find_next_zero_bit(holemask, XFS_INOBT_HOLEMASK_BITS,
 					     nextbit);
 		/*
@@ -1896,8 +1898,11 @@ xfs_difree_inode_chunk(
 
 		ASSERT(agbno % mp->m_sb.sb_spino_align == 0);
 		ASSERT(contigblk % mp->m_sb.sb_spino_align == 0);
-		xfs_free_extent_later(tp, XFS_AGB_TO_FSB(mp, agno, agbno),
-				  contigblk, &XFS_RMAP_OINFO_INODES);
+		error = xfs_free_extent_later(tp,
+				XFS_AGB_TO_FSB(mp, agno, agbno),
+				contigblk, &XFS_RMAP_OINFO_INODES);
+		if (error)
+			return error;
 
 		/* reset range to current bit and carry on... */
 		startidx = endidx = nextbit;
@@ -1905,6 +1910,7 @@ xfs_difree_inode_chunk(
 next:
 		nextbit++;
 	}
+	return 0;
 }
 
 STATIC int
@@ -2003,7 +2009,9 @@ xfs_difree_inobt(
 			goto error0;
 		}
 
-		xfs_difree_inode_chunk(tp, pag->pag_agno, &rec);
+		error = xfs_difree_inode_chunk(tp, pag->pag_agno, &rec);
+		if (error)
+			goto error0;
 	} else {
 		xic->deleted = false;
 
diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c
index c1c65774dcc2..b6e21433925c 100644
--- a/fs/xfs/libxfs/xfs_refcount.c
+++ b/fs/xfs/libxfs/xfs_refcount.c
@@ -1151,8 +1151,10 @@ xfs_refcount_adjust_extents(
 				fsbno = XFS_AGB_TO_FSB(cur->bc_mp,
 						cur->bc_ag.pag->pag_agno,
 						tmp.rc_startblock);
-				xfs_free_extent_later(cur->bc_tp, fsbno,
+				error = xfs_free_extent_later(cur->bc_tp, fsbno,
 						  tmp.rc_blockcount, NULL);
+				if (error)
+					goto out_error;
 			}
 
 			(*agbno) += tmp.rc_blockcount;
@@ -1210,8 +1212,10 @@ xfs_refcount_adjust_extents(
 			fsbno = XFS_AGB_TO_FSB(cur->bc_mp,
 					cur->bc_ag.pag->pag_agno,
 					ext.rc_startblock);
-			xfs_free_extent_later(cur->bc_tp, fsbno,
+			error = xfs_free_extent_later(cur->bc_tp, fsbno,
 					ext.rc_blockcount, NULL);
+			if (error)
+				goto out_error;
 		}
 
 skip:
@@ -1976,7 +1980,10 @@ xfs_refcount_recover_cow_leftovers(
 				rr->rr_rrec.rc_blockcount);
 
 		/* Free the block. */
-		xfs_free_extent_later(tp, fsb, rr->rr_rrec.rc_blockcount, NULL);
+		error = xfs_free_extent_later(tp, fsb,
+				rr->rr_rrec.rc_blockcount, NULL);
+		if (error)
+			goto out_trans;
 
 		error = xfs_trans_commit(tp);
 		if (error)
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index f5dc46ce9803..abcc559f3c64 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -616,8 +616,10 @@ xfs_reflink_cancel_cow_blocks(
 			xfs_refcount_free_cow_extent(*tpp, del.br_startblock,
 					del.br_blockcount);
 
-			xfs_free_extent_later(*tpp, del.br_startblock,
+			error = xfs_free_extent_later(*tpp, del.br_startblock,
 					  del.br_blockcount, NULL);
+			if (error)
+				break;
 
 			/* Roll the transaction */
 			error = xfs_defer_finish(tpp);
-- 
cgit v1.2.3