summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorDarrick J. Wong <darrick.wong@oracle.com>2017-10-18 07:37:40 +0300
committerDarrick J. Wong <darrick.wong@oracle.com>2017-10-27 01:38:25 +0300
commit3daa664191375db6a4a0cced75183aa3ca96cbda (patch)
tree52a4191c74dddbb9527b1984a09dfc2569e2b098
parentefa7a99ce1f8615aca7b0ff3122a1ae14e4d1cdc (diff)
downloadlinux-3daa664191375db6a4a0cced75183aa3ca96cbda.tar.xz
xfs: scrub inode btrees
Check the records of the inode btrees to make sure that the values make sense given the inode records themselves. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Dave Chinner <dchinner@redhat.com>
-rw-r--r--fs/xfs/Makefile1
-rw-r--r--fs/xfs/libxfs/xfs_format.h2
-rw-r--r--fs/xfs/libxfs/xfs_fs.h4
-rw-r--r--fs/xfs/scrub/common.c29
-rw-r--r--fs/xfs/scrub/common.h3
-rw-r--r--fs/xfs/scrub/ialloc.c337
-rw-r--r--fs/xfs/scrub/scrub.c9
-rw-r--r--fs/xfs/scrub/scrub.h2
8 files changed, 385 insertions, 2 deletions
diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 9cf08090a6a4..09232f6bcc7e 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -147,6 +147,7 @@ xfs-y += $(addprefix scrub/, \
alloc.o \
btree.o \
common.o \
+ ialloc.o \
scrub.o \
)
endif
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index 23229f0c5b15..154c3dd6499b 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -518,7 +518,7 @@ static inline int xfs_sb_version_hasftype(struct xfs_sb *sbp)
(sbp->sb_features2 & XFS_SB_VERSION2_FTYPE));
}
-static inline int xfs_sb_version_hasfinobt(xfs_sb_t *sbp)
+static inline bool xfs_sb_version_hasfinobt(xfs_sb_t *sbp)
{
return (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5) &&
(sbp->sb_features_ro_compat & XFS_SB_FEAT_RO_COMPAT_FINOBT);
diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h
index 1e23d13e7b51..74df6ecfe5dc 100644
--- a/fs/xfs/libxfs/xfs_fs.h
+++ b/fs/xfs/libxfs/xfs_fs.h
@@ -490,9 +490,11 @@ struct xfs_scrub_metadata {
#define XFS_SCRUB_TYPE_AGI 4 /* AG inode header */
#define XFS_SCRUB_TYPE_BNOBT 5 /* freesp by block btree */
#define XFS_SCRUB_TYPE_CNTBT 6 /* freesp by length btree */
+#define XFS_SCRUB_TYPE_INOBT 7 /* inode btree */
+#define XFS_SCRUB_TYPE_FINOBT 8 /* free inode btree */
/* Number of scrub subcommands. */
-#define XFS_SCRUB_TYPE_NR 7
+#define XFS_SCRUB_TYPE_NR 9
/* i: Repair this metadata. */
#define XFS_SCRUB_IFLAG_REPAIR (1 << 0)
diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c
index 018127ad5018..39165c3556cd 100644
--- a/fs/xfs/scrub/common.c
+++ b/fs/xfs/scrub/common.c
@@ -40,6 +40,8 @@
#include "xfs_refcount_btree.h"
#include "xfs_rmap.h"
#include "xfs_rmap_btree.h"
+#include "xfs_log.h"
+#include "xfs_trans_priv.h"
#include "scrub/xfs_scrub.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
@@ -451,11 +453,38 @@ xfs_scrub_setup_ag_btree(
struct xfs_inode *ip,
bool force_log)
{
+ struct xfs_mount *mp = sc->mp;
int error;
+ /*
+ * If the caller asks us to checkpont the log, do so. This
+ * expensive operation should be performed infrequently and only
+ * as a last resort. Any caller that sets force_log should
+ * document why they need to do so.
+ */
+ if (force_log) {
+ error = xfs_scrub_checkpoint_log(mp);
+ if (error)
+ return error;
+ }
+
error = xfs_scrub_setup_ag_header(sc, ip);
if (error)
return error;
return xfs_scrub_ag_init(sc, sc->sm->sm_agno, &sc->sa);
}
+
+/* Push everything out of the log onto disk. */
+int
+xfs_scrub_checkpoint_log(
+ struct xfs_mount *mp)
+{
+ int error;
+
+ error = _xfs_log_force(mp, XFS_LOG_SYNC, NULL);
+ if (error)
+ return error;
+ xfs_ail_push_all_sync(mp->m_ail);
+ return 0;
+}
diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h
index 372a84437ad1..17830b8bf9e5 100644
--- a/fs/xfs/scrub/common.h
+++ b/fs/xfs/scrub/common.h
@@ -73,6 +73,7 @@ void xfs_scrub_fblock_set_warning(struct xfs_scrub_context *sc, int whichfork,
xfs_fileoff_t offset);
void xfs_scrub_set_incomplete(struct xfs_scrub_context *sc);
+int xfs_scrub_checkpoint_log(struct xfs_mount *mp);
/* Setup functions */
int xfs_scrub_setup_fs(struct xfs_scrub_context *sc, struct xfs_inode *ip);
@@ -80,6 +81,8 @@ int xfs_scrub_setup_ag_header(struct xfs_scrub_context *sc,
struct xfs_inode *ip);
int xfs_scrub_setup_ag_allocbt(struct xfs_scrub_context *sc,
struct xfs_inode *ip);
+int xfs_scrub_setup_ag_iallocbt(struct xfs_scrub_context *sc,
+ struct xfs_inode *ip);
void xfs_scrub_ag_free(struct xfs_scrub_context *sc, struct xfs_scrub_ag *sa);
diff --git a/fs/xfs/scrub/ialloc.c b/fs/xfs/scrub/ialloc.c
new file mode 100644
index 000000000000..496d6f2fbb9e
--- /dev/null
+++ b/fs/xfs/scrub/ialloc.c
@@ -0,0 +1,337 @@
+/*
+ * Copyright (C) 2017 Oracle. All Rights Reserved.
+ *
+ * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it would be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write the Free Software Foundation,
+ * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301, USA.
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_defer.h"
+#include "xfs_btree.h"
+#include "xfs_bit.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_sb.h"
+#include "xfs_inode.h"
+#include "xfs_alloc.h"
+#include "xfs_ialloc.h"
+#include "xfs_ialloc_btree.h"
+#include "xfs_icache.h"
+#include "xfs_rmap.h"
+#include "xfs_log.h"
+#include "xfs_trans_priv.h"
+#include "scrub/xfs_scrub.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/btree.h"
+#include "scrub/trace.h"
+
+/*
+ * Set us up to scrub inode btrees.
+ * If we detect a discrepancy between the inobt and the inode,
+ * try again after forcing logged inode cores out to disk.
+ */
+int
+xfs_scrub_setup_ag_iallocbt(
+ struct xfs_scrub_context *sc,
+ struct xfs_inode *ip)
+{
+ return xfs_scrub_setup_ag_btree(sc, ip, sc->try_harder);
+}
+
+/* Inode btree scrubber. */
+
+/* Is this chunk worth checking? */
+STATIC bool
+xfs_scrub_iallocbt_chunk(
+ struct xfs_scrub_btree *bs,
+ struct xfs_inobt_rec_incore *irec,
+ xfs_agino_t agino,
+ xfs_extlen_t len)
+{
+ struct xfs_mount *mp = bs->cur->bc_mp;
+ xfs_agnumber_t agno = bs->cur->bc_private.a.agno;
+ xfs_agblock_t bno;
+
+ bno = XFS_AGINO_TO_AGBNO(mp, agino);
+ if (bno + len <= bno ||
+ !xfs_verify_agbno(mp, agno, bno) ||
+ !xfs_verify_agbno(mp, agno, bno + len - 1))
+ xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+
+ return true;
+}
+
+/* Count the number of free inodes. */
+static unsigned int
+xfs_scrub_iallocbt_freecount(
+ xfs_inofree_t freemask)
+{
+ BUILD_BUG_ON(sizeof(freemask) != sizeof(__u64));
+ return hweight64(freemask);
+}
+
+/* Check a particular inode with ir_free. */
+STATIC int
+xfs_scrub_iallocbt_check_cluster_freemask(
+ struct xfs_scrub_btree *bs,
+ xfs_ino_t fsino,
+ xfs_agino_t chunkino,
+ xfs_agino_t clusterino,
+ struct xfs_inobt_rec_incore *irec,
+ struct xfs_buf *bp)
+{
+ struct xfs_dinode *dip;
+ struct xfs_mount *mp = bs->cur->bc_mp;
+ bool inode_is_free = false;
+ bool freemask_ok;
+ bool inuse;
+ int error = 0;
+
+ if (xfs_scrub_should_terminate(bs->sc, &error))
+ return error;
+
+ dip = xfs_buf_offset(bp, clusterino * mp->m_sb.sb_inodesize);
+ if (be16_to_cpu(dip->di_magic) != XFS_DINODE_MAGIC ||
+ (dip->di_version >= 3 &&
+ be64_to_cpu(dip->di_ino) != fsino + clusterino)) {
+ xfs_scrub_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);
+ if (error == -ENODATA) {
+ /* Not cached, just read the disk buffer */
+ freemask_ok = inode_is_free ^ !!(dip->di_mode);
+ if (!bs->sc->try_harder && !freemask_ok)
+ return -EDEADLOCK;
+ } else if (error < 0) {
+ /*
+ * Inode is only half assembled, or there was an IO error,
+ * or the verifier failed, so don't bother trying to check.
+ * The inode scrubber can deal with this.
+ */
+ goto out;
+ } else {
+ /* Inode is all there. */
+ freemask_ok = inode_is_free ^ inuse;
+ }
+ if (!freemask_ok)
+ xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+out:
+ return 0;
+}
+
+/* Make sure the free mask is consistent with what the inodes think. */
+STATIC int
+xfs_scrub_iallocbt_check_freemask(
+ struct xfs_scrub_btree *bs,
+ struct xfs_inobt_rec_incore *irec)
+{
+ struct xfs_owner_info oinfo;
+ 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;
+ xfs_agblock_t agbno;
+ int blks_per_cluster;
+ uint16_t holemask;
+ uint16_t ir_holemask;
+ int error = 0;
+
+ /* Make sure the freemask matches the inode records. */
+ blks_per_cluster = xfs_icluster_size_fsb(mp);
+ nr_inodes = XFS_OFFBNO_TO_AGINO(mp, blks_per_cluster, 0);
+ xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_INODES);
+
+ for (agino = irec->ir_startino;
+ agino < irec->ir_startino + XFS_INODES_PER_CHUNK;
+ agino += blks_per_cluster * mp->m_sb.sb_inopblock) {
+ 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) {
+ xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+ continue;
+ }
+
+ /* If any part of this is a hole, skip it. */
+ if (ir_holemask)
+ continue;
+
+ /* 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, blks_per_cluster);
+ imap.im_boffset = 0;
+
+ error = xfs_imap_to_bp(mp, bs->cur->bc_tp, &imap,
+ &dip, &bp, 0, 0);
+ if (!xfs_scrub_btree_process_error(bs->sc, bs->cur, 0, &error))
+ continue;
+
+ /* Which inodes are free? */
+ for (clusterino = 0; clusterino < nr_inodes; clusterino++) {
+ error = xfs_scrub_iallocbt_check_cluster_freemask(bs,
+ fsino, chunkino, clusterino, irec, bp);
+ if (error) {
+ xfs_trans_brelse(bs->cur->bc_tp, bp);
+ return error;
+ }
+ }
+
+ xfs_trans_brelse(bs->cur->bc_tp, bp);
+ }
+
+ return error;
+}
+
+/* Scrub an inobt/finobt record. */
+STATIC int
+xfs_scrub_iallocbt_rec(
+ struct xfs_scrub_btree *bs,
+ union xfs_btree_rec *rec)
+{
+ struct xfs_mount *mp = bs->cur->bc_mp;
+ struct xfs_inobt_rec_incore irec;
+ 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;
+ int error = 0;
+ unsigned int real_freecount;
+ uint16_t holemask;
+
+ xfs_inobt_btrec_to_irec(mp, rec, &irec);
+
+ if (irec.ir_count > XFS_INODES_PER_CHUNK ||
+ irec.ir_freecount > XFS_INODES_PER_CHUNK)
+ xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+
+ real_freecount = irec.ir_freecount +
+ (XFS_INODES_PER_CHUNK - irec.ir_count);
+ if (real_freecount != xfs_scrub_iallocbt_freecount(irec.ir_free))
+ xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+
+ agino = irec.ir_startino;
+ /* Record has to be properly aligned within the AG. */
+ if (!xfs_verify_agino(mp, agno, agino) ||
+ !xfs_verify_agino(mp, agno, agino + XFS_INODES_PER_CHUNK - 1)) {
+ xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+ goto out;
+ }
+
+ /* Make sure this record is aligned to cluster and inoalignmnt size. */
+ agbno = XFS_AGINO_TO_AGBNO(mp, irec.ir_startino);
+ if ((agbno & (xfs_ialloc_cluster_alignment(mp) - 1)) ||
+ (agbno & (xfs_icluster_size_fsb(mp) - 1)))
+ xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+
+ /* Handle non-sparse inodes */
+ if (!xfs_inobt_issparse(irec.ir_holemask)) {
+ len = XFS_B_TO_FSB(mp,
+ XFS_INODES_PER_CHUNK * mp->m_sb.sb_inodesize);
+ if (irec.ir_count != XFS_INODES_PER_CHUNK)
+ xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+
+ if (!xfs_scrub_iallocbt_chunk(bs, &irec, agino, len))
+ goto out;
+ goto check_freemask;
+ }
+
+ /* Check each chunk of a sparse inode cluster. */
+ holemask = irec.ir_holemask;
+ holecount = 0;
+ len = XFS_B_TO_FSB(mp,
+ XFS_INODES_PER_HOLEMASK_BIT * mp->m_sb.sb_inodesize);
+ holes = ~xfs_inobt_irec_to_allocmask(&irec);
+ if ((holes & irec.ir_free) != holes ||
+ irec.ir_freecount > irec.ir_count)
+ xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+
+ for (i = 0; i < XFS_INOBT_HOLEMASK_BITS; i++) {
+ if (holemask & 1)
+ holecount += XFS_INODES_PER_HOLEMASK_BIT;
+ else if (!xfs_scrub_iallocbt_chunk(bs, &irec, agino, len))
+ break;
+ holemask >>= 1;
+ agino += XFS_INODES_PER_HOLEMASK_BIT;
+ }
+
+ if (holecount > XFS_INODES_PER_CHUNK ||
+ holecount + irec.ir_count != XFS_INODES_PER_CHUNK)
+ xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+
+check_freemask:
+ error = xfs_scrub_iallocbt_check_freemask(bs, &irec);
+ if (error)
+ goto out;
+
+out:
+ return error;
+}
+
+/* Scrub the inode btrees for some AG. */
+STATIC int
+xfs_scrub_iallocbt(
+ struct xfs_scrub_context *sc,
+ xfs_btnum_t which)
+{
+ struct xfs_btree_cur *cur;
+ struct xfs_owner_info oinfo;
+
+ xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_INOBT);
+ cur = which == XFS_BTNUM_INO ? sc->sa.ino_cur : sc->sa.fino_cur;
+ return xfs_scrub_btree(sc, cur, xfs_scrub_iallocbt_rec, &oinfo, NULL);
+}
+
+int
+xfs_scrub_inobt(
+ struct xfs_scrub_context *sc)
+{
+ return xfs_scrub_iallocbt(sc, XFS_BTNUM_INO);
+}
+
+int
+xfs_scrub_finobt(
+ struct xfs_scrub_context *sc)
+{
+ return xfs_scrub_iallocbt(sc, XFS_BTNUM_FINO);
+}
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index 4398b34614d7..1303194941f3 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -182,6 +182,15 @@ static const struct xfs_scrub_meta_ops meta_scrub_ops[] = {
.setup = xfs_scrub_setup_ag_allocbt,
.scrub = xfs_scrub_cntbt,
},
+ { /* inobt */
+ .setup = xfs_scrub_setup_ag_iallocbt,
+ .scrub = xfs_scrub_inobt,
+ },
+ { /* finobt */
+ .setup = xfs_scrub_setup_ag_iallocbt,
+ .scrub = xfs_scrub_finobt,
+ .has = xfs_sb_version_hasfinobt,
+ },
};
/* This isn't a stable feature, warn once per day. */
diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h
index a4af99c9f5ec..5d97453008a0 100644
--- a/fs/xfs/scrub/scrub.h
+++ b/fs/xfs/scrub/scrub.h
@@ -73,5 +73,7 @@ int xfs_scrub_agfl(struct xfs_scrub_context *sc);
int xfs_scrub_agi(struct xfs_scrub_context *sc);
int xfs_scrub_bnobt(struct xfs_scrub_context *sc);
int xfs_scrub_cntbt(struct xfs_scrub_context *sc);
+int xfs_scrub_inobt(struct xfs_scrub_context *sc);
+int xfs_scrub_finobt(struct xfs_scrub_context *sc);
#endif /* __XFS_SCRUB_SCRUB_H__ */