xfs: strengthen rmapbt scrubbing [v24.5]

This series strengthens space allocation record cross referencing by
 using AG block bitmaps to compute the difference between space used
 according to the rmap records and the primary metadata, and reports
 cross-referencing errors for any discrepancies.
 
 Signed-off-by: Darrick J. Wong <djwong@kernel.org>
 -----BEGIN PGP SIGNATURE-----
 
 iHUEABYKAB0WIQQ2qTKExjcn+O1o2YRKO3ySh0YRpgUCZDYdqgAKCRBKO3ySh0YR
 pgQ8AP4uxtGQY7RXaJ6aKXTwqarZO9vwZyQiL/nFo1onGCHv4wD/cIwn7hvJmbnF
 7avZMCsYJlVFNAJUFZuACmz0v4PwWQ8=
 =KqDr
 -----END PGP SIGNATURE-----

Merge tag 'scrub-strengthen-rmap-checking-6.4_2023-04-11' of git://git.kernel.org/pub/scm/linux/kernel/git/djwong/xfs-linux into guilt/xfs-for-next

xfs: strengthen rmapbt scrubbing [v24.5]

This series strengthens space allocation record cross referencing by
using AG block bitmaps to compute the difference between space used
according to the rmap records and the primary metadata, and reports
cross-referencing errors for any discrepancies.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Dave Chinner <david@fromorbit.com>

fs/xfs/Makefile

@@ -148,6 +148,7 @@ xfs-y				+= $(addprefix scrub/, \
 				   agheader.o \
 				   alloc.o \
 				   attr.o \
+				   bitmap.o \
 				   bmap.o \
 				   btree.o \
 				   common.o \
@@ -172,7 +173,6 @@ xfs-$(CONFIG_XFS_QUOTA)		+= scrub/quota.o
 ifeq ($(CONFIG_XFS_ONLINE_REPAIR),y)
 xfs-y				+= $(addprefix scrub/, \
 				   agheader_repair.o \
-				   bitmap.o \
 				   repair.o \
 				   )
 endif

fs/xfs/scrub/bitmap.c

@@ -6,6 +6,7 @@
 #include "xfs.h"
 #include "xfs_fs.h"
 #include "xfs_shared.h"
+#include "xfs_bit.h"
 #include "xfs_format.h"
 #include "xfs_trans_resv.h"
 #include "xfs_mount.h"
@@ -262,6 +263,38 @@ xbitmap_disunion(
  * For the 300th record we just exit, with the list being [1, 4, 2, 3].
  */
 
+/* Mark a btree block to the agblock bitmap. */
+STATIC int
+xagb_bitmap_visit_btblock(
+	struct xfs_btree_cur	*cur,
+	int			level,
+	void			*priv)
+{
+	struct xagb_bitmap	*bitmap = priv;
+	struct xfs_buf		*bp;
+	xfs_fsblock_t		fsbno;
+	xfs_agblock_t		agbno;
+
+	xfs_btree_get_block(cur, level, &bp);
+	if (!bp)
+		return 0;
+
+	fsbno = XFS_DADDR_TO_FSB(cur->bc_mp, xfs_buf_daddr(bp));
+	agbno = XFS_FSB_TO_AGBNO(cur->bc_mp, fsbno);
+
+	return xagb_bitmap_set(bitmap, agbno, 1);
+}
+
+/* Mark all (per-AG) btree blocks in the agblock bitmap. */
+int
+xagb_bitmap_set_btblocks(
+	struct xagb_bitmap	*bitmap,
+	struct xfs_btree_cur	*cur)
+{
+	return xfs_btree_visit_blocks(cur, xagb_bitmap_visit_btblock,
+			XFS_BTREE_VISIT_ALL, bitmap);
+}
+
 /*
  * Record all the buffers pointed to by the btree cursor.  Callers already
  * engaged in a btree walk should call this function to capture the list of
@@ -396,3 +429,25 @@ xbitmap_empty(
 {
 	return bitmap->xb_root.rb_root.rb_node == NULL;
 }
+
+/* Is the start of the range set or clear?  And for how long? */
+bool
+xbitmap_test(
+	struct xbitmap		*bitmap,
+	uint64_t		start,
+	uint64_t		*len)
+{
+	struct xbitmap_node	*bn;
+	uint64_t		last = start + *len - 1;
+
+	bn = xbitmap_tree_iter_first(&bitmap->xb_root, start, last);
+	if (!bn)
+		return false;
+	if (bn->bn_start <= start) {
+		if (bn->bn_last < last)
+			*len = bn->bn_last - start + 1;
+		return true;
+	}
+	*len = bn->bn_start - start;
+	return false;
+}

fs/xfs/scrub/bitmap.h

@@ -38,5 +38,77 @@ int xbitmap_walk_bits(struct xbitmap *bitmap, xbitmap_walk_bits_fn fn,
 		void *priv);
 
 bool xbitmap_empty(struct xbitmap *bitmap);
+bool xbitmap_test(struct xbitmap *bitmap, uint64_t start, uint64_t *len);
+
+/* Bitmaps, but for type-checked for xfs_agblock_t */
+
+struct xagb_bitmap {
+	struct xbitmap	agbitmap;
+};
+
+static inline void xagb_bitmap_init(struct xagb_bitmap *bitmap)
+{
+	xbitmap_init(&bitmap->agbitmap);
+}
+
+static inline void xagb_bitmap_destroy(struct xagb_bitmap *bitmap)
+{
+	xbitmap_destroy(&bitmap->agbitmap);
+}
+
+static inline int xagb_bitmap_clear(struct xagb_bitmap *bitmap,
+		xfs_agblock_t start, xfs_extlen_t len)
+{
+	return xbitmap_clear(&bitmap->agbitmap, start, len);
+}
+static inline int xagb_bitmap_set(struct xagb_bitmap *bitmap,
+		xfs_agblock_t start, xfs_extlen_t len)
+{
+	return xbitmap_set(&bitmap->agbitmap, start, len);
+}
+
+static inline bool
+xagb_bitmap_test(
+	struct xagb_bitmap	*bitmap,
+	xfs_agblock_t		start,
+	xfs_extlen_t		*len)
+{
+	uint64_t		biglen = *len;
+	bool			ret;
+
+	ret = xbitmap_test(&bitmap->agbitmap, start, &biglen);
+
+	if (start + biglen >= UINT_MAX) {
+		ASSERT(0);
+		biglen = UINT_MAX - start;
+	}
+
+	*len = biglen;
+	return ret;
+}
+
+static inline int xagb_bitmap_disunion(struct xagb_bitmap *bitmap,
+		struct xagb_bitmap *sub)
+{
+	return xbitmap_disunion(&bitmap->agbitmap, &sub->agbitmap);
+}
+
+static inline uint32_t xagb_bitmap_hweight(struct xagb_bitmap *bitmap)
+{
+	return xbitmap_hweight(&bitmap->agbitmap);
+}
+static inline bool xagb_bitmap_empty(struct xagb_bitmap *bitmap)
+{
+	return xbitmap_empty(&bitmap->agbitmap);
+}
+
+static inline int xagb_bitmap_walk(struct xagb_bitmap *bitmap,
+		xbitmap_walk_fn fn, void *priv)
+{
+	return xbitmap_walk(&bitmap->agbitmap, fn, priv);
+}
+
+int xagb_bitmap_set_btblocks(struct xagb_bitmap *bitmap,
+		struct xfs_btree_cur *cur);
 
 #endif	/* __XFS_SCRUB_BITMAP_H__ */

fs/xfs/scrub/repair.h

@@ -31,6 +31,7 @@ int xrep_init_btblock(struct xfs_scrub *sc, xfs_fsblock_t fsb,
 		const struct xfs_buf_ops *ops);
 
 struct xbitmap;
+struct xagb_bitmap;
 
 int xrep_fix_freelist(struct xfs_scrub *sc, bool can_shrink);
 int xrep_invalidate_blocks(struct xfs_scrub *sc, struct xbitmap *btlist);

fs/xfs/scrub/rmap.c

@@ -7,15 +7,23 @@
 #include "xfs_fs.h"
 #include "xfs_shared.h"
 #include "xfs_format.h"
+#include "xfs_log_format.h"
 #include "xfs_trans_resv.h"
 #include "xfs_mount.h"
+#include "xfs_trans.h"
 #include "xfs_btree.h"
 #include "xfs_rmap.h"
 #include "xfs_refcount.h"
+#include "xfs_ag.h"
+#include "xfs_bit.h"
+#include "xfs_alloc.h"
+#include "xfs_alloc_btree.h"
+#include "xfs_ialloc_btree.h"
+#include "xfs_refcount_btree.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/btree.h"
-#include "xfs_ag.h"
+#include "scrub/bitmap.h"
 
 /*
  * Set us up to scrub reverse mapping btrees.
@@ -45,6 +53,16 @@ struct xchk_rmap {
 	 * that could be one.
 	 */
 	struct xfs_rmap_irec	prev_rec;
+
+	/* Bitmaps containing all blocks for each type of AG metadata. */
+	struct xagb_bitmap	fs_owned;
+	struct xagb_bitmap	log_owned;
+	struct xagb_bitmap	ag_owned;
+	struct xagb_bitmap	inobt_owned;
+	struct xagb_bitmap	refcbt_owned;
+
+	/* Did we complete the AG space metadata bitmaps? */
+	bool			bitmaps_complete;
 };
 
 /* Cross-reference a rmap against the refcount btree. */
@@ -249,6 +267,77 @@ xchk_rmapbt_check_mergeable(
 	memcpy(&cr->prev_rec, irec, sizeof(struct xfs_rmap_irec));
 }
 
+/* Compare an rmap for AG metadata against the metadata walk. */
+STATIC int
+xchk_rmapbt_mark_bitmap(
+	struct xchk_btree		*bs,
+	struct xchk_rmap		*cr,
+	const struct xfs_rmap_irec	*irec)
+{
+	struct xfs_scrub		*sc = bs->sc;
+	struct xagb_bitmap		*bmp = NULL;
+	xfs_extlen_t			fsbcount = irec->rm_blockcount;
+
+	/*
+	 * Skip corrupt records.  It is essential that we detect records in the
+	 * btree that cannot overlap but do, flag those as CORRUPT, and skip
+	 * the bitmap comparison to avoid generating false XCORRUPT reports.
+	 */
+	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+		return 0;
+
+	/*
+	 * If the AG metadata walk didn't complete, there's no point in
+	 * comparing against partial results.
+	 */
+	if (!cr->bitmaps_complete)
+		return 0;
+
+	switch (irec->rm_owner) {
+	case XFS_RMAP_OWN_FS:
+		bmp = &cr->fs_owned;
+		break;
+	case XFS_RMAP_OWN_LOG:
+		bmp = &cr->log_owned;
+		break;
+	case XFS_RMAP_OWN_AG:
+		bmp = &cr->ag_owned;
+		break;
+	case XFS_RMAP_OWN_INOBT:
+		bmp = &cr->inobt_owned;
+		break;
+	case XFS_RMAP_OWN_REFC:
+		bmp = &cr->refcbt_owned;
+		break;
+	}
+
+	if (!bmp)
+		return 0;
+
+	if (xagb_bitmap_test(bmp, irec->rm_startblock, &fsbcount)) {
+		/*
+		 * The start of this reverse mapping corresponds to a set
+		 * region in the bitmap.  If the mapping covers more area than
+		 * the set region, then it covers space that wasn't found by
+		 * the AG metadata walk.
+		 */
+		if (fsbcount < irec->rm_blockcount)
+			xchk_btree_xref_set_corrupt(bs->sc,
+					bs->sc->sa.rmap_cur, 0);
+	} else {
+		/*
+		 * The start of this reverse mapping does not correspond to a
+		 * completely set region in the bitmap.  The region wasn't
+		 * fully set by walking the AG metadata, so this is a
+		 * cross-referencing corruption.
+		 */
+		xchk_btree_xref_set_corrupt(bs->sc, bs->sc->sa.rmap_cur, 0);
+	}
+
+	/* Unset the region so that we can detect missing rmap records. */
+	return xagb_bitmap_clear(bmp, irec->rm_startblock, irec->rm_blockcount);
+}
+
 /* Scrub an rmapbt record. */
 STATIC int
 xchk_rmapbt_rec(
@@ -268,9 +357,180 @@ xchk_rmapbt_rec(
 	xchk_rmapbt_check_mergeable(bs, cr, &irec);
 	xchk_rmapbt_check_overlapping(bs, cr, &irec);
 	xchk_rmapbt_xref(bs->sc, &irec);
+
+	return xchk_rmapbt_mark_bitmap(bs, cr, &irec);
+}
+
+/* Add an AGFL block to the rmap list. */
+STATIC int
+xchk_rmapbt_walk_agfl(
+	struct xfs_mount	*mp,
+	xfs_agblock_t		agbno,
+	void			*priv)
+{
+	struct xagb_bitmap	*bitmap = priv;
+
+	return xagb_bitmap_set(bitmap, agbno, 1);
+}
+
+/*
+ * Set up bitmaps mapping all the AG metadata to compare with the rmapbt
+ * records.
+ *
+ * Grab our own btree cursors here if the scrub setup function didn't give us a
+ * btree cursor due to reports of poor health.  We need to find out if the
+ * rmapbt disagrees with primary metadata btrees to tag the rmapbt as being
+ * XCORRUPT.
+ */
+STATIC int
+xchk_rmapbt_walk_ag_metadata(
+	struct xfs_scrub	*sc,
+	struct xchk_rmap	*cr)
+{
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_buf		*agfl_bp;
+	struct xfs_agf		*agf = sc->sa.agf_bp->b_addr;
+	struct xfs_btree_cur	*cur;
+	int			error;
+
+	/* OWN_FS: AG headers */
+	error = xagb_bitmap_set(&cr->fs_owned, XFS_SB_BLOCK(mp),
+			XFS_AGFL_BLOCK(mp) - XFS_SB_BLOCK(mp) + 1);
+	if (error)
+		goto out;
+
+	/* OWN_LOG: Internal log */
+	if (xfs_ag_contains_log(mp, sc->sa.pag->pag_agno)) {
+		error = xagb_bitmap_set(&cr->log_owned,
+				XFS_FSB_TO_AGBNO(mp, mp->m_sb.sb_logstart),
+				mp->m_sb.sb_logblocks);
+		if (error)
+			goto out;
+	}
+
+	/* OWN_AG: bnobt, cntbt, rmapbt, and AGFL */
+	cur = sc->sa.bno_cur;
+	if (!cur)
+		cur = xfs_allocbt_init_cursor(sc->mp, sc->tp, sc->sa.agf_bp,
+				sc->sa.pag, XFS_BTNUM_BNO);
+	error = xagb_bitmap_set_btblocks(&cr->ag_owned, cur);
+	if (cur != sc->sa.bno_cur)
+		xfs_btree_del_cursor(cur, error);
+	if (error)
+		goto out;
+
+	cur = sc->sa.cnt_cur;
+	if (!cur)
+		cur = xfs_allocbt_init_cursor(sc->mp, sc->tp, sc->sa.agf_bp,
+				sc->sa.pag, XFS_BTNUM_CNT);
+	error = xagb_bitmap_set_btblocks(&cr->ag_owned, cur);
+	if (cur != sc->sa.cnt_cur)
+		xfs_btree_del_cursor(cur, error);
+	if (error)
+		goto out;
+
+	error = xagb_bitmap_set_btblocks(&cr->ag_owned, sc->sa.rmap_cur);
+	if (error)
+		goto out;
+
+	error = xfs_alloc_read_agfl(sc->sa.pag, sc->tp, &agfl_bp);
+	if (error)
+		goto out;
+
+	error = xfs_agfl_walk(sc->mp, agf, agfl_bp, xchk_rmapbt_walk_agfl,
+			&cr->ag_owned);
+	xfs_trans_brelse(sc->tp, agfl_bp);
+	if (error)
+		goto out;
+
+	/* OWN_INOBT: inobt, finobt */
+	cur = sc->sa.ino_cur;
+	if (!cur)
+		cur = xfs_inobt_init_cursor(sc->sa.pag, sc->tp, sc->sa.agi_bp,
+				XFS_BTNUM_INO);
+	error = xagb_bitmap_set_btblocks(&cr->inobt_owned, cur);
+	if (cur != sc->sa.ino_cur)
+		xfs_btree_del_cursor(cur, error);
+	if (error)
+		goto out;
+
+	if (xfs_has_finobt(sc->mp)) {
+		cur = sc->sa.fino_cur;
+		if (!cur)
+			cur = xfs_inobt_init_cursor(sc->sa.pag, sc->tp,
+					sc->sa.agi_bp, XFS_BTNUM_FINO);
+		error = xagb_bitmap_set_btblocks(&cr->inobt_owned, cur);
+		if (cur != sc->sa.fino_cur)
+			xfs_btree_del_cursor(cur, error);
+		if (error)
+			goto out;
+	}
+
+	/* OWN_REFC: refcountbt */
+	if (xfs_has_reflink(sc->mp)) {
+		cur = sc->sa.refc_cur;
+		if (!cur)
+			cur = xfs_refcountbt_init_cursor(sc->mp, sc->tp,
+					sc->sa.agf_bp, sc->sa.pag);
+		error = xagb_bitmap_set_btblocks(&cr->refcbt_owned, cur);
+		if (cur != sc->sa.refc_cur)
+			xfs_btree_del_cursor(cur, error);
+		if (error)
+			goto out;
+	}
+
+out:
+	/*
+	 * If there's an error, set XFAIL and disable the bitmap
+	 * cross-referencing checks, but proceed with the scrub anyway.
+	 */
+	if (error)
+		xchk_btree_xref_process_error(sc, sc->sa.rmap_cur,
+				sc->sa.rmap_cur->bc_nlevels - 1, &error);
+	else
+		cr->bitmaps_complete = true;
 	return 0;
 }
 
+/*
+ * Check for set regions in the bitmaps; if there are any, the rmap records do
+ * not describe all the AG metadata.
+ */
+STATIC void
+xchk_rmapbt_check_bitmaps(
+	struct xfs_scrub	*sc,
+	struct xchk_rmap	*cr)
+{
+	struct xfs_btree_cur	*cur = sc->sa.rmap_cur;
+	unsigned int		level;
+
+	if (sc->sm->sm_flags & (XFS_SCRUB_OFLAG_CORRUPT |
+				XFS_SCRUB_OFLAG_XFAIL))
+		return;
+	if (!cur)
+		return;
+	level = cur->bc_nlevels - 1;
+
+	/*
+	 * Any bitmap with bits still set indicates that the reverse mapping
+	 * doesn't cover the entire primary structure.
+	 */
+	if (xagb_bitmap_hweight(&cr->fs_owned) != 0)
+		xchk_btree_xref_set_corrupt(sc, cur, level);
+
+	if (xagb_bitmap_hweight(&cr->log_owned) != 0)
+		xchk_btree_xref_set_corrupt(sc, cur, level);
+
+	if (xagb_bitmap_hweight(&cr->ag_owned) != 0)
+		xchk_btree_xref_set_corrupt(sc, cur, level);
+
+	if (xagb_bitmap_hweight(&cr->inobt_owned) != 0)
+		xchk_btree_xref_set_corrupt(sc, cur, level);
+
+	if (xagb_bitmap_hweight(&cr->refcbt_owned) != 0)
+		xchk_btree_xref_set_corrupt(sc, cur, level);
+}
+
 /* Scrub the rmap btree for some AG. */
 int
 xchk_rmapbt(
@@ -283,8 +543,29 @@ xchk_rmapbt(
 	if (!cr)
 		return -ENOMEM;
 
+	xagb_bitmap_init(&cr->fs_owned);
+	xagb_bitmap_init(&cr->log_owned);
+	xagb_bitmap_init(&cr->ag_owned);
+	xagb_bitmap_init(&cr->inobt_owned);
+	xagb_bitmap_init(&cr->refcbt_owned);
+
+	error = xchk_rmapbt_walk_ag_metadata(sc, cr);
+	if (error)
+		goto out;
+
 	error = xchk_btree(sc, sc->sa.rmap_cur, xchk_rmapbt_rec,
 			&XFS_RMAP_OINFO_AG, cr);
+	if (error)
+		goto out;
+
+	xchk_rmapbt_check_bitmaps(sc, cr);
+
+out:
+	xagb_bitmap_destroy(&cr->refcbt_owned);
+	xagb_bitmap_destroy(&cr->inobt_owned);
+	xagb_bitmap_destroy(&cr->ag_owned);
+	xagb_bitmap_destroy(&cr->log_owned);
+	xagb_bitmap_destroy(&cr->fs_owned);
 	kfree(cr);
 	return error;
 }