/*
* 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;
}
/*
* Read the disk inode attributes into the in-core inode structure.
*
* For version 5 superblocks, if we are initialising a new inode and we are not
* utilising the XFS_MOUNT_IKEEP inode cluster mode, we can simple build the new
* inode core with a random generation number. If we are keeping inodes around,
* we need to read the inode cluster to get the existing generation number off
* disk. Further, if we are using version 4 superblocks (i.e. v1/v2 inode
* format) then log recovery is dependent on the di_flushiter field being
* initialised from the current on-disk value and hence we must also read the
* inode off disk.
*/
int
xfs_iread(
xfs_mount_t *mp,
xfs_trans_t *tp,
xfs_inode_t *ip,
uint iget_flags)
{
xfs_buf_t *bp;
xfs_dinode_t *dip;
int error;
/*
* Fill in the location information in the in-core inode.
*/
error = xfs_imap(mp, tp, ip->i_ino, &ip->i_imap, iget_flags);
if (error)
return error;
/* shortcut IO on inode allocation if possible */
if ((iget_flags & XFS_IGET_CREATE) &&
xfs_sb_version_hascrc(&mp->m_sb) &&
!(mp->m_flags & XFS_MOUNT_IKEEP)) {
/* initialise the on-disk inode core */
memset(&ip->i_d, 0, sizeof(ip->i_d));
ip->i_d.di_magic = XFS_DINODE_MAGIC;
ip->i_d.di_gen = prandom_u32();
if (xfs_sb_version_hascrc(&mp->m_sb)) {
ip->i_d.di_version = 3;
ip->i_d.di_ino = ip->i_ino;
uuid_copy(&ip->i_d.di_uuid, &mp->m_sb.sb_uuid);
} else
ip->i_d.di_version = 2;
return 0;
}
/*
* Get pointers to the on-disk inode and the buffer containing it.
*/
error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &dip, &bp, 0, iget_flags);
if (error)
return error;
/* even unallocated inodes are verified */
if (!xfs_dinode_verify(mp, ip, dip)) {
xfs_alert(mp, "%s: validation failed for inode %lld failed",
__func__, ip->i_ino);
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, dip);
error = -EFSCORRUPTED;
goto out_brelse;
}
/*
* If the on-disk inode is already linked to a directory
* entry, copy all of the inode into the in-core inode.
* xfs_iformat_fork() handles copying in the inode format
* specific information.
* Otherwise, just get the truly permanent information.
*/
if (dip->di_mode) {
xfs_dinode_from_disk(&ip->i_d, dip);
error = xfs_iformat_fork(ip, dip);
if (error) {
#ifdef DEBUG
xfs_alert(mp, "%s: xfs_iformat() returned error %d",
__func__, error);
#endif /* DEBUG */
goto out_brelse;
}
} else {
/*
* Partial initialisation of the in-core inode. Just the bits
* that xfs_ialloc won't overwrite or relies on being correct.
*/
ip->i_d.di_magic = be16_to_cpu(dip->di_magic);
ip->i_d.di_version = dip->di_version;
ip->i_d.di_gen = be32_to_cpu(dip->di_gen);
ip->i_d.di_flushiter = be16_to_cpu(dip->di_flushiter);
if (dip->di_version == 3) {
ip->i_d.di_ino = be64_to_cpu(dip->di_ino);
uuid_copy(&ip->i_d.di_uuid, &dip->di_uuid);
}
/*
* Make sure to pull in the mode here as well in
* case the inode is released without being used.
* This ensures that xfs_inactive() will see that
* the inode is already free and not try to mess
* with the uninitialized part of it.
*/
ip->i_d.di_mode = 0;
}
/*
* Automatically convert version 1 inode formats in memory to version 2
* inode format. If the inode is modified, it will get logged and
* rewritten as a version 2 inode. We can do this because we set the
* superblock feature bit for v2 inodes unconditionally during mount
* and it means the reast of the code can assume the inode version is 2
* or higher.
*/
if (ip->i_d.di_version == 1) {
ip->i_d.di_version = 2;
memset(&(ip->i_d.di_pad[0]), 0, sizeof(ip->i_d.di_pad));
ip->i_d.di_nlink = ip->i_d.di_onlink;
ip->i_d.di_onlink = 0;
xfs_set_projid(ip, 0);
}
ip->i_delayed_blks = 0;
/*
* Mark the buffer containing the inode as something to keep
* around for a while. This helps to keep recently accessed
* meta-data in-core longer.
*/
xfs_buf_set_ref(bp, XFS_INO_REF);
/*
* Use xfs_trans_brelse() to release the buffer containing the on-disk
* inode, because it was acquired with xfs_trans_read_buf() in
* xfs_imap_to_bp() above. If tp is NULL, this is just a normal
* brelse(). If we're within a transaction, then xfs_trans_brelse()
* will only release the buffer if it is not dirty within the
* transaction. It will be OK to release the buffer in this case,
* because inodes on disk are never destroyed and we will be locking the
* new in-core inode before putting it in the cache where other
* processes can find it. Thus we don't have to worry about the inode
* being changed just because we released the buffer.
*/
out_brelse:
xfs_trans_brelse(tp, bp);
return error;
}
/*
* Read the disk inode attributes into the in-core inode structure.
*
* For version 5 superblocks, if we are initialising a new inode and we are not
* utilising the XFS_MOUNT_IKEEP inode cluster mode, we can simple build the new
* inode core with a random generation number. If we are keeping inodes around,
* we need to read the inode cluster to get the existing generation number off
* disk. Further, if we are using version 4 superblocks (i.e. v1/v2 inode
* format) then log recovery is dependent on the di_flushiter field being
* initialised from the current on-disk value and hence we must also read the
* inode off disk.
*/
int
xfs_iread(
xfs_mount_t *mp,
xfs_trans_t *tp,
xfs_inode_t *ip,
uint iget_flags)
{
xfs_buf_t *bp;
xfs_dinode_t *dip;
xfs_failaddr_t fa;
int error;
/*
* Fill in the location information in the in-core inode.
*/
error = xfs_imap(mp, tp, ip->i_ino, &ip->i_imap, iget_flags);
if (error)
return error;
/* shortcut IO on inode allocation if possible */
if ((iget_flags & XFS_IGET_CREATE) &&
xfs_sb_version_hascrc(&mp->m_sb) &&
!(mp->m_flags & XFS_MOUNT_IKEEP)) {
/* initialise the on-disk inode core */
memset(&ip->i_d, 0, sizeof(ip->i_d));
VFS_I(ip)->i_generation = prandom_u32();
ip->i_d.di_version = 3;
return 0;
}
/*
* Get pointers to the on-disk inode and the buffer containing it.
*/
error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &dip, &bp, 0, iget_flags);
if (error)
return error;
/* even unallocated inodes are verified */
fa = xfs_dinode_verify(mp, ip->i_ino, dip);
if (fa) {
xfs_inode_verifier_error(ip, -EFSCORRUPTED, "dinode", dip,
sizeof(*dip), fa);
error = -EFSCORRUPTED;
goto out_brelse;
}
/*
* If the on-disk inode is already linked to a directory
* entry, copy all of the inode into the in-core inode.
* xfs_iformat_fork() handles copying in the inode format
* specific information.
* Otherwise, just get the truly permanent information.
*/
if (dip->di_mode) {
xfs_inode_from_disk(ip, dip);
error = xfs_iformat_fork(ip, dip);
if (error) {
#ifdef DEBUG
xfs_alert(mp, "%s: xfs_iformat() returned error %d",
__func__, error);
#endif /* DEBUG */
goto out_brelse;
}
} else {
/*
* Partial initialisation of the in-core inode. Just the bits
* that xfs_ialloc won't overwrite or relies on being correct.
*/
ip->i_d.di_version = dip->di_version;
VFS_I(ip)->i_generation = be32_to_cpu(dip->di_gen);
ip->i_d.di_flushiter = be16_to_cpu(dip->di_flushiter);
/*
* Make sure to pull in the mode here as well in
* case the inode is released without being used.
* This ensures that xfs_inactive() will see that
* the inode is already free and not try to mess
* with the uninitialized part of it.
*/
VFS_I(ip)->i_mode = 0;
}
ASSERT(ip->i_d.di_version >= 2);
ip->i_delayed_blks = 0;
/*
* Mark the buffer containing the inode as something to keep
* around for a while. This helps to keep recently accessed
* meta-data in-core longer.
*/
xfs_buf_set_ref(bp, XFS_INO_REF);
/*
* Use xfs_trans_brelse() to release the buffer containing the on-disk
* inode, because it was acquired with xfs_trans_read_buf() in
* xfs_imap_to_bp() above. If tp is NULL, this is just a normal
* brelse(). If we're within a transaction, then xfs_trans_brelse()
* will only release the buffer if it is not dirty within the
* transaction. It will be OK to release the buffer in this case,
* because inodes on disk are never destroyed and we will be locking the
* new in-core inode before putting it in the cache where other
* processes can find it. Thus we don't have to worry about the inode
* being changed just because we released the buffer.
*/
out_brelse:
xfs_trans_brelse(tp, bp);
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;
}
