1 files changed, 243 insertions, 87 deletions

diff --git a/fs/xfs/scrub/ialloc.c b/fs/xfs/scrub/ialloc.c
index 882dc56c5c21..700114f79a7d 100644
--- a/fs/xfs/scrub/ialloc.c
+++ b/fs/xfs/scrub/ialloc.c
@@ -47,6 +47,12 @@ xchk_setup_ag_iallocbt(
 struct xchk_iallocbt {
 	/* Number of inodes we see while scanning inobt. */
 	unsigned long long	inodes;
+
+	/* Expected next startino, for big block filesystems. */
+	xfs_agino_t		next_startino;
+
+	/* Expected end of the current inode cluster. */
+	xfs_agino_t		next_cluster_ino;
 };
 
 /*
@@ -128,41 +134,57 @@ xchk_iallocbt_freecount(
 	return hweight64(freemask);
 }
 
-/* Check a particular inode with ir_free. */
+/*
+ * Check that an inode's allocation status matches ir_free in the inobt
+ * record.  First we try querying the in-core inode state, and if the inode
+ * isn't loaded we examine the on-disk inode directly.
+ *
+ * Since there can be 1:M and M:1 mappings between inobt records and inode
+ * clusters, we pass in the inode location information as an inobt record;
+ * the index of an inode cluster within the inobt record (as well as the
+ * cluster buffer itself); and the index of the inode within the cluster.
+ *
+ * @irec is the inobt record.
+ * @irec_ino is the inode offset from the start of the record.
+ * @dip is the on-disk inode.
+ */
 STATIC int
-xchk_iallocbt_check_cluster_freemask(
+xchk_iallocbt_check_cluster_ifree(
 	struct xchk_btree		*bs,
-	xfs_ino_t			fsino,
-	xfs_agino_t			chunkino,
-	xfs_agino_t			clusterino,
 	struct xfs_inobt_rec_incore	*irec,
-	struct xfs_buf			*bp)
+	unsigned int			irec_ino,
+	struct xfs_dinode		*dip)
 {
-	struct xfs_dinode		*dip;
 	struct xfs_mount		*mp = bs->cur->bc_mp;
-	bool				inode_is_free = false;
+	xfs_ino_t			fsino;
+	xfs_agino_t			agino;
+	bool				irec_free;
+	bool				ino_inuse;
 	bool				freemask_ok;
-	bool				inuse;
 	int				error = 0;
 
 	if (xchk_should_terminate(bs->sc, &error))
 		return error;
 
-	dip = xfs_buf_offset(bp, clusterino * mp->m_sb.sb_inodesize);
+	/*
+	 * Given an inobt record and the offset of an inode from the start of
+	 * the record, compute which fs inode we're talking about.
+	 */
+	agino = irec->ir_startino + irec_ino;
+	fsino = XFS_AGINO_TO_INO(mp, bs->cur->bc_private.a.agno, agino);
+	irec_free = (irec->ir_free & XFS_INOBT_MASK(irec_ino));
+
 	if (be16_to_cpu(dip->di_magic) != XFS_DINODE_MAGIC ||
-	    (dip->di_version >= 3 &&
-	     be64_to_cpu(dip->di_ino) != fsino + clusterino)) {
+	    (dip->di_version >= 3 && be64_to_cpu(dip->di_ino) != fsino)) {
 		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 		goto out;
 	}
 
-	if (irec->ir_free & XFS_INOBT_MASK(chunkino + clusterino))
-		inode_is_free = true;
-	error = xfs_icache_inode_is_allocated(mp, bs->cur->bc_tp,
-			fsino + clusterino, &inuse);
+	error = xfs_icache_inode_is_allocated(mp, bs->cur->bc_tp, fsino,
+			&ino_inuse);
 	if (error == -ENODATA) {
 		/* Not cached, just read the disk buffer */
-		freemask_ok = inode_is_free ^ !!(dip->di_mode);
+		freemask_ok = irec_free ^ !!(dip->di_mode);
 		if (!bs->sc->try_harder && !freemask_ok)
 			return -EDEADLOCK;
 	} else if (error < 0) {
@@ -174,7 +196,7 @@ xchk_iallocbt_check_cluster_freemask(
 		goto out;
 	} else {
 		/* Inode is all there. */
-		freemask_ok = inode_is_free ^ inuse;
+		freemask_ok = irec_free ^ ino_inuse;
 	}
 	if (!freemask_ok)
 		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
@@ -182,86 +204,221 @@ out:
 	return 0;
 }
 
-/* Make sure the free mask is consistent with what the inodes think. */
+/*
+ * Check that the holemask and freemask of a hypothetical inode cluster match
+ * what's actually on disk.  If sparse inodes are enabled, the cluster does
+ * not actually have to map to inodes if the corresponding holemask bit is set.
+ *
+ * @cluster_base is the first inode in the cluster within the @irec.
+ */
 STATIC int
-xchk_iallocbt_check_freemask(
+xchk_iallocbt_check_cluster(
 	struct xchk_btree		*bs,
-	struct xfs_inobt_rec_incore	*irec)
+	struct xfs_inobt_rec_incore	*irec,
+	unsigned int			cluster_base)
 {
 	struct xfs_imap			imap;
 	struct xfs_mount		*mp = bs->cur->bc_mp;
 	struct xfs_dinode		*dip;
-	struct xfs_buf			*bp;
-	xfs_ino_t			fsino;
-	xfs_agino_t			nr_inodes;
-	xfs_agino_t			agino;
-	xfs_agino_t			chunkino;
-	xfs_agino_t			clusterino;
+	struct xfs_buf			*cluster_bp;
+	unsigned int			nr_inodes;
+	xfs_agnumber_t			agno = bs->cur->bc_private.a.agno;
 	xfs_agblock_t			agbno;
-	uint16_t			holemask;
+	unsigned int			cluster_index;
+	uint16_t			cluster_mask = 0;
 	uint16_t			ir_holemask;
 	int				error = 0;
 
-	/* Make sure the freemask matches the inode records. */
-	nr_inodes = mp->m_inodes_per_cluster;
-
-	for (agino = irec->ir_startino;
-	     agino < irec->ir_startino + XFS_INODES_PER_CHUNK;
-	     agino += mp->m_inodes_per_cluster) {
-		fsino = XFS_AGINO_TO_INO(mp, bs->cur->bc_private.a.agno, agino);
-		chunkino = agino - irec->ir_startino;
-		agbno = XFS_AGINO_TO_AGBNO(mp, agino);
-
-		/* Compute the holemask mask for this cluster. */
-		for (clusterino = 0, holemask = 0; clusterino < nr_inodes;
-		     clusterino += XFS_INODES_PER_HOLEMASK_BIT)
-			holemask |= XFS_INOBT_MASK((chunkino + clusterino) /
-					XFS_INODES_PER_HOLEMASK_BIT);
-
-		/* The whole cluster must be a hole or not a hole. */
-		ir_holemask = (irec->ir_holemask & holemask);
-		if (ir_holemask != holemask && ir_holemask != 0) {
+	nr_inodes = min_t(unsigned int, XFS_INODES_PER_CHUNK,
+			mp->m_inodes_per_cluster);
+
+	/* Map this inode cluster */
+	agbno = XFS_AGINO_TO_AGBNO(mp, irec->ir_startino + cluster_base);
+
+	/* Compute a bitmask for this cluster that can be used for holemask. */
+	for (cluster_index = 0;
+	     cluster_index < nr_inodes;
+	     cluster_index += XFS_INODES_PER_HOLEMASK_BIT)
+		cluster_mask |= XFS_INOBT_MASK((cluster_base + cluster_index) /
+				XFS_INODES_PER_HOLEMASK_BIT);
+
+	/*
+	 * Map the first inode of this cluster to a buffer and offset.
+	 * Be careful about inobt records that don't align with the start of
+	 * the inode buffer when block sizes are large enough to hold multiple
+	 * inode chunks.  When this happens, cluster_base will be zero but
+	 * ir_startino can be large enough to make im_boffset nonzero.
+	 */
+	ir_holemask = (irec->ir_holemask & cluster_mask);
+	imap.im_blkno = XFS_AGB_TO_DADDR(mp, agno, agbno);
+	imap.im_len = XFS_FSB_TO_BB(mp, mp->m_blocks_per_cluster);
+	imap.im_boffset = XFS_INO_TO_OFFSET(mp, irec->ir_startino);
+
+	if (imap.im_boffset != 0 && cluster_base != 0) {
+		ASSERT(imap.im_boffset == 0 || cluster_base == 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
+		return 0;
+	}
+
+	trace_xchk_iallocbt_check_cluster(mp, agno, irec->ir_startino,
+			imap.im_blkno, imap.im_len, cluster_base, nr_inodes,
+			cluster_mask, ir_holemask,
+			XFS_INO_TO_OFFSET(mp, irec->ir_startino +
+					  cluster_base));
+
+	/* The whole cluster must be a hole or not a hole. */
+	if (ir_holemask != cluster_mask && ir_holemask != 0) {
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
+		return 0;
+	}
+
+	/* If any part of this is a hole, skip it. */
+	if (ir_holemask) {
+		xchk_xref_is_not_owned_by(bs->sc, agbno,
+				mp->m_blocks_per_cluster,
+				&XFS_RMAP_OINFO_INODES);
+		return 0;
+	}
+
+	xchk_xref_is_owned_by(bs->sc, agbno, mp->m_blocks_per_cluster,
+			&XFS_RMAP_OINFO_INODES);
+
+	/* Grab the inode cluster buffer. */
+	error = xfs_imap_to_bp(mp, bs->cur->bc_tp, &imap, &dip, &cluster_bp,
+			0, 0);
+	if (!xchk_btree_xref_process_error(bs->sc, bs->cur, 0, &error))
+		return error;
+
+	/* Check free status of each inode within this cluster. */
+	for (cluster_index = 0; cluster_index < nr_inodes; cluster_index++) {
+		struct xfs_dinode	*dip;
+
+		if (imap.im_boffset >= BBTOB(cluster_bp->b_length)) {
 			xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
-			continue;
+			break;
 		}
 
-		/* If any part of this is a hole, skip it. */
-		if (ir_holemask) {
-			xchk_xref_is_not_owned_by(bs->sc, agbno,
-					mp->m_blocks_per_cluster,
-					&XFS_RMAP_OINFO_INODES);
-			continue;
+		dip = xfs_buf_offset(cluster_bp, imap.im_boffset);
+		error = xchk_iallocbt_check_cluster_ifree(bs, irec,
+				cluster_base + cluster_index, dip);
+		if (error)
+			break;
+		imap.im_boffset += mp->m_sb.sb_inodesize;
+	}
+
+	xfs_trans_brelse(bs->cur->bc_tp, cluster_bp);
+	return error;
+}
+
+/*
+ * For all the inode clusters that could map to this inobt record, make sure
+ * that the holemask makes sense and that the allocation status of each inode
+ * matches the freemask.
+ */
+STATIC int
+xchk_iallocbt_check_clusters(
+	struct xchk_btree		*bs,
+	struct xfs_inobt_rec_incore	*irec)
+{
+	unsigned int			cluster_base;
+	int				error = 0;
+
+	/*
+	 * For the common case where this inobt record maps to multiple inode
+	 * clusters this will call _check_cluster for each cluster.
+	 *
+	 * For the case that multiple inobt records map to a single cluster,
+	 * this will call _check_cluster once.
+	 */
+	for (cluster_base = 0;
+	     cluster_base < XFS_INODES_PER_CHUNK;
+	     cluster_base += bs->sc->mp->m_inodes_per_cluster) {
+		error = xchk_iallocbt_check_cluster(bs, irec, cluster_base);
+		if (error)
+			break;
+	}
+
+	return error;
+}
+
+/*
+ * Make sure this inode btree record is aligned properly.  Because a fs block
+ * contains multiple inodes, we check that the inobt record is aligned to the
+ * correct inode, not just the correct block on disk.  This results in a finer
+ * grained corruption check.
+ */
+STATIC void
+xchk_iallocbt_rec_alignment(
+	struct xchk_btree		*bs,
+	struct xfs_inobt_rec_incore	*irec)
+{
+	struct xfs_mount		*mp = bs->sc->mp;
+	struct xchk_iallocbt		*iabt = bs->private;
+
+	/*
+	 * finobt records have different positioning requirements than inobt
+	 * records: each finobt record must have a corresponding inobt record.
+	 * That is checked in the xref function, so for now we only catch the
+	 * obvious case where the record isn't at all aligned properly.
+	 *
+	 * Note that if a fs block contains more than a single chunk of inodes,
+	 * we will have finobt records only for those chunks containing free
+	 * inodes, and therefore expect chunk alignment of finobt records.
+	 * Otherwise, we expect that the finobt record is aligned to the
+	 * cluster alignment as told by the superblock.
+	 */
+	if (bs->cur->bc_btnum == XFS_BTNUM_FINO) {
+		unsigned int	imask;
+
+		imask = min_t(unsigned int, XFS_INODES_PER_CHUNK,
+				mp->m_cluster_align_inodes) - 1;
+		if (irec->ir_startino & imask)
+			xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
+		return;
+	}
+
+	if (iabt->next_startino != NULLAGINO) {
+		/*
+		 * We're midway through a cluster of inodes that is mapped by
+		 * multiple inobt records.  Did we get the record for the next
+		 * irec in the sequence?
+		 */
+		if (irec->ir_startino != iabt->next_startino) {
+			xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
+			return;
 		}
 
-		xchk_xref_is_owned_by(bs->sc, agbno, mp->m_blocks_per_cluster,
-				&XFS_RMAP_OINFO_INODES);
+		iabt->next_startino += XFS_INODES_PER_CHUNK;
 
-		/* Grab the inode cluster buffer. */
-		imap.im_blkno = XFS_AGB_TO_DADDR(mp, bs->cur->bc_private.a.agno,
-				agbno);
-		imap.im_len = XFS_FSB_TO_BB(mp, mp->m_blocks_per_cluster);
-		imap.im_boffset = 0;
-
-		error = xfs_imap_to_bp(mp, bs->cur->bc_tp, &imap,
-				&dip, &bp, 0, 0);
-		if (!xchk_btree_xref_process_error(bs->sc, bs->cur, 0,
-				&error))
-			continue;
-
-		/* Which inodes are free? */
-		for (clusterino = 0; clusterino < nr_inodes; clusterino++) {
-			error = xchk_iallocbt_check_cluster_freemask(bs,
-					fsino, chunkino, clusterino, irec, bp);
-			if (error) {
-				xfs_trans_brelse(bs->cur->bc_tp, bp);
-				return error;
-			}
+		/* Are we done with the cluster? */
+		if (iabt->next_startino >= iabt->next_cluster_ino) {
+			iabt->next_startino = NULLAGINO;
+			iabt->next_cluster_ino = NULLAGINO;
 		}
+		return;
+	}
+
+	/* inobt records must be aligned to cluster and inoalignmnt size. */
+	if (irec->ir_startino & (mp->m_cluster_align_inodes - 1)) {
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
+		return;
+	}
 
-		xfs_trans_brelse(bs->cur->bc_tp, bp);
+	if (irec->ir_startino & (mp->m_inodes_per_cluster - 1)) {
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
+		return;
 	}
 
-	return error;
+	if (mp->m_inodes_per_cluster <= XFS_INODES_PER_CHUNK)
+		return;
+
+	/*
+	 * If this is the start of an inode cluster that can be mapped by
+	 * multiple inobt records, the next inobt record must follow exactly
+	 * after this one.
+	 */
+	iabt->next_startino = irec->ir_startino + XFS_INODES_PER_CHUNK;
+	iabt->next_cluster_ino = irec->ir_startino + mp->m_inodes_per_cluster;
 }
 
 /* Scrub an inobt/finobt record. */
@@ -276,7 +433,6 @@ xchk_iallocbt_rec(
 	uint64_t			holes;
 	xfs_agnumber_t			agno = bs->cur->bc_private.a.agno;
 	xfs_agino_t			agino;
-	xfs_agblock_t			agbno;
 	xfs_extlen_t			len;
 	int				holecount;
 	int				i;
@@ -303,11 +459,9 @@ xchk_iallocbt_rec(
 		goto out;
 	}
 
-	/* Make sure this record is aligned to cluster and inoalignmnt size. */
-	agbno = XFS_AGINO_TO_AGBNO(mp, irec.ir_startino);
-	if ((agbno & (mp->m_cluster_align - 1)) ||
-	    (agbno & (mp->m_blocks_per_cluster - 1)))
-		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
+	xchk_iallocbt_rec_alignment(bs, &irec);
+	if (bs->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+		goto out;
 
 	iabt->inodes += irec.ir_count;
 
@@ -320,7 +474,7 @@ xchk_iallocbt_rec(
 
 		if (!xchk_iallocbt_chunk(bs, &irec, agino, len))
 			goto out;
-		goto check_freemask;
+		goto check_clusters;
 	}
 
 	/* Check each chunk of a sparse inode cluster. */
@@ -346,8 +500,8 @@ xchk_iallocbt_rec(
 	    holecount + irec.ir_count != XFS_INODES_PER_CHUNK)
 		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 
-check_freemask:
-	error = xchk_iallocbt_check_freemask(bs, &irec);
+check_clusters:
+	error = xchk_iallocbt_check_clusters(bs, &irec);
 	if (error)
 		goto out;
 
@@ -429,6 +583,8 @@ xchk_iallocbt(
 	struct xfs_btree_cur	*cur;
 	struct xchk_iallocbt	iabt = {
 		.inodes		= 0,
+		.next_startino	= NULLAGINO,
+		.next_cluster_ino = NULLAGINO,
 	};
 	int			error;