/*
* 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_ifree(
struct xchk_btree *bs,
struct xfs_inobt_rec_incore *irec,
unsigned int irec_ino,
struct xfs_dinode *dip)
{
struct xfs_mount *mp = bs->cur->bc_mp;
xfs_ino_t fsino;
xfs_agino_t agino;
bool irec_free;
bool ino_inuse;
bool freemask_ok;
int error = 0;
if (xchk_should_terminate(bs->sc, &error))
return error;
/*
* 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)) {
xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
goto out;
}
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 = irec_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 = irec_free ^ ino_inuse;
}
if (!freemask_ok)
xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
out:
return 0;
}
/*
* Lookup the inode chunk that the given inode lives in and then get the record
* if we found the chunk. If the inode was not the last in the chunk and there
* are some left allocated, update the data for the pointed-to record as well as
* return the count of grabbed inodes.
*/
STATIC int
xfs_bulkstat_grab_ichunk(
struct xfs_btree_cur *cur, /* btree cursor */
xfs_agino_t agino, /* starting inode of chunk */
int *icount,/* return # of inodes grabbed */
struct xfs_inobt_rec_incore *irec) /* btree record */
{
int idx; /* index into inode chunk */
int stat;
int error = 0;
/* Lookup the inode chunk that this inode lives in */
error = xfs_inobt_lookup(cur, agino, XFS_LOOKUP_LE, &stat);
if (error)
return error;
if (!stat) {
*icount = 0;
return error;
}
/* Get the record, should always work */
error = xfs_inobt_get_rec(cur, irec, &stat);
if (error)
return error;
XFS_WANT_CORRUPTED_RETURN(cur->bc_mp, stat == 1);
/* Check if the record contains the inode in request */
if (irec->ir_startino + XFS_INODES_PER_CHUNK <= agino) {
*icount = 0;
return 0;
}
idx = agino - irec->ir_startino + 1;
if (idx < XFS_INODES_PER_CHUNK &&
(xfs_inobt_maskn(idx, XFS_INODES_PER_CHUNK - idx) & ~irec->ir_free)) {
int i;
/* We got a right chunk with some left inodes allocated at it.
* Grab the chunk record. Mark all the uninteresting inodes
* free -- because they're before our start point.
*/
for (i = 0; i < idx; i++) {
if (XFS_INOBT_MASK(i) & ~irec->ir_free)
irec->ir_freecount++;
}
irec->ir_free |= xfs_inobt_maskn(0, idx);
*icount = irec->ir_count - irec->ir_freecount;
}
return 0;
}
/* 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 finobt doesn't think this inode is free.
* We don't have to check the inobt ourselves because we got the inode via
* IGET_UNTRUSTED, which checks the inobt for us.
*/
static void
xchk_inode_xref_finobt(
struct xfs_scrub *sc,
xfs_ino_t ino)
{
struct xfs_inobt_rec_incore rec;
xfs_agino_t agino;
int has_record;
int error;
if (!sc->sa.fino_cur || xchk_skip_xref(sc->sm))
return;
agino = XFS_INO_TO_AGINO(sc->mp, ino);
/*
* Try to get the finobt record. If we can't get it, then we're
* in good shape.
*/
error = xfs_inobt_lookup(sc->sa.fino_cur, agino, XFS_LOOKUP_LE,
&has_record);
if (!xchk_should_check_xref(sc, &error, &sc->sa.fino_cur) ||
!has_record)
return;
error = xfs_inobt_get_rec(sc->sa.fino_cur, &rec, &has_record);
if (!xchk_should_check_xref(sc, &error, &sc->sa.fino_cur) ||
!has_record)
return;
/*
* Otherwise, make sure this record either doesn't cover this inode,
* or that it does but it's marked present.
*/
if (rec.ir_startino > agino ||
rec.ir_startino + XFS_INODES_PER_CHUNK <= agino)
return;
if (rec.ir_free & XFS_INOBT_MASK(agino - rec.ir_startino))
xchk_btree_xref_set_corrupt(sc, sc->sa.fino_cur, 0);
}
/*
* 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_cluster(
struct xchk_btree *bs,
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 *cluster_bp;
unsigned int nr_inodes;
xfs_agnumber_t agno = bs->cur->bc_private.a.agno;
xfs_agblock_t agbno;
unsigned int cluster_index;
uint16_t cluster_mask = 0;
uint16_t ir_holemask;
int error = 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);
break;
}
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;
}
xfs_inofree_t
xfs_inobt_mask(int i)
{
return XFS_INOBT_MASK(i);
}
/*
* Process inodes in chunk with a pointer to a formatter function
* that will iget the inode and fill in the appropriate structure.
*/
static int
xfs_bulkstat_ag_ichunk(
struct xfs_mount *mp,
xfs_agnumber_t agno,
struct xfs_inobt_rec_incore *irbp,
bulkstat_one_pf formatter,
size_t statstruct_size,
struct xfs_bulkstat_agichunk *acp,
xfs_agino_t *last_agino)
{
char __user **ubufp = acp->ac_ubuffer;
int chunkidx;
int error = 0;
xfs_agino_t agino = irbp->ir_startino;
for (chunkidx = 0; chunkidx < XFS_INODES_PER_CHUNK;
chunkidx++, agino++) {
int fmterror;
int ubused;
/* inode won't fit in buffer, we are done */
if (acp->ac_ubleft < statstruct_size)
break;
/* Skip if this inode is free */
if (XFS_INOBT_MASK(chunkidx) & irbp->ir_free)
continue;
/* Get the inode and fill in a single buffer */
ubused = statstruct_size;
error = formatter(mp, XFS_AGINO_TO_INO(mp, agno, agino),
*ubufp, acp->ac_ubleft, &ubused, &fmterror);
if (fmterror == BULKSTAT_RV_GIVEUP ||
(error && error != -ENOENT && error != -EINVAL)) {
acp->ac_ubleft = 0;
ASSERT(error);
break;
}
/* be careful not to leak error if at end of chunk */
if (fmterror == BULKSTAT_RV_NOTHING || error) {
error = 0;
continue;
}
*ubufp += ubused;
acp->ac_ubleft -= ubused;
acp->ac_ubelem++;
}
/*
* Post-update *last_agino. At this point, agino will always point one
* inode past the last inode we processed successfully. Hence we
* substract that inode when setting the *last_agino cursor so that we
* return the correct cookie to userspace. On the next bulkstat call,
* the inode under the lastino cookie will be skipped as we have already
* processed it here.
*/
*last_agino = agino - 1;
return error;
}
/* 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;
}
