/*
* Validate a given inode number.
*/
int
xfs_dir_ino_validate(
xfs_mount_t *mp,
xfs_ino_t ino)
{
xfs_agblock_t agblkno;
xfs_agino_t agino;
xfs_agnumber_t agno;
int ino_ok;
int ioff;
agno = XFS_INO_TO_AGNO(mp, ino);
agblkno = XFS_INO_TO_AGBNO(mp, ino);
ioff = XFS_INO_TO_OFFSET(mp, ino);
agino = XFS_OFFBNO_TO_AGINO(mp, agblkno, ioff);
ino_ok =
agno < mp->m_sb.sb_agcount &&
agblkno < mp->m_sb.sb_agblocks &&
agblkno != 0 &&
ioff < (1 << mp->m_sb.sb_inopblog) &&
XFS_AGINO_TO_INO(mp, agno, agino) == ino;
if (unlikely(XFS_TEST_ERROR(!ino_ok, mp, XFS_ERRTAG_DIR_INO_VALIDATE,
XFS_RANDOM_DIR_INO_VALIDATE))) {
xfs_warn(mp, "Invalid inode number 0x%Lx",
(unsigned long long) ino);
XFS_ERROR_REPORT("xfs_dir_ino_validate", XFS_ERRLEVEL_LOW, mp);
return XFS_ERROR(EFSCORRUPTED);
}
return 0;
}
/*
* Count fsblocks of the given fork.
*/
int /* error */
xfs_bmap_count_blocks(
xfs_trans_t *tp, /* transaction pointer */
xfs_inode_t *ip, /* incore inode */
int whichfork, /* data or attr fork */
int *count) /* out: count of blocks */
{
struct xfs_btree_block *block; /* current btree block */
xfs_fsblock_t bno; /* block # of "block" */
xfs_ifork_t *ifp; /* fork structure */
int level; /* btree level, for checking */
xfs_mount_t *mp; /* file system mount structure */
__be64 *pp; /* pointer to block address */
bno = NULLFSBLOCK;
mp = ip->i_mount;
ifp = XFS_IFORK_PTR(ip, whichfork);
if ( XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_EXTENTS ) {
xfs_bmap_count_leaves(ifp, 0,
ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t),
count);
return 0;
}
/*
* Root level must use BMAP_BROOT_PTR_ADDR macro to get ptr out.
*/
block = ifp->if_broot;
level = be16_to_cpu(block->bb_level);
ASSERT(level > 0);
pp = XFS_BMAP_BROOT_PTR_ADDR(mp, block, 1, ifp->if_broot_bytes);
bno = be64_to_cpu(*pp);
ASSERT(bno != NULLDFSBNO);
ASSERT(XFS_FSB_TO_AGNO(mp, bno) < mp->m_sb.sb_agcount);
ASSERT(XFS_FSB_TO_AGBNO(mp, bno) < mp->m_sb.sb_agblocks);
if (unlikely(xfs_bmap_count_tree(mp, tp, ifp, bno, level, count) < 0)) {
XFS_ERROR_REPORT("xfs_bmap_count_blocks(2)", XFS_ERRLEVEL_LOW,
mp);
return XFS_ERROR(EFSCORRUPTED);
}
return 0;
}
/*
* Unlock all of the transaction's items and free the transaction.
* The transaction must not have modified any of its items, because
* there is no way to restore them to their previous state.
*
* If the transaction has made a log reservation, make sure to release
* it as well.
*/
void
xfs_trans_cancel(
xfs_trans_t *tp,
int flags)
{
int log_flags;
#ifdef DEBUG
xfs_log_item_chunk_t *licp;
xfs_log_item_desc_t *lidp;
xfs_log_item_t *lip;
int i;
#endif
xfs_mount_t *mp = tp->t_mountp;
/*
* See if the caller is being too lazy to figure out if
* the transaction really needs an abort.
*/
if ((flags & XFS_TRANS_ABORT) && !(tp->t_flags & XFS_TRANS_DIRTY))
flags &= ~XFS_TRANS_ABORT;
/*
* See if the caller is relying on us to shut down the
* filesystem. This happens in paths where we detect
* corruption and decide to give up.
*/
if ((tp->t_flags & XFS_TRANS_DIRTY) && !XFS_FORCED_SHUTDOWN(mp)) {
XFS_ERROR_REPORT("xfs_trans_cancel", XFS_ERRLEVEL_LOW, mp);
xfs_force_shutdown(mp, XFS_CORRUPT_INCORE);
}
#ifdef DEBUG
if (!(flags & XFS_TRANS_ABORT)) {
licp = &(tp->t_items);
while (licp != NULL) {
lidp = licp->lic_descs;
for (i = 0; i < licp->lic_unused; i++, lidp++) {
if (XFS_LIC_ISFREE(licp, i)) {
continue;
}
lip = lidp->lid_item;
if (!XFS_FORCED_SHUTDOWN(mp))
ASSERT(!(lip->li_type == XFS_LI_EFD));
}
licp = licp->lic_next;
}
}
#endif
xfs_trans_unreserve_and_mod_sb(tp);
XFS_TRANS_UNRESERVE_AND_MOD_DQUOTS(mp, tp);
if (tp->t_ticket) {
if (flags & XFS_TRANS_RELEASE_LOG_RES) {
ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
log_flags = XFS_LOG_REL_PERM_RESERV;
} else {
log_flags = 0;
}
xfs_log_done(mp, tp->t_ticket, NULL, log_flags);
}
/* mark this thread as no longer being in a transaction */
PFLAGS_RESTORE_FSTRANS(&tp->t_pflags);
xfs_trans_free_items(tp, flags);
xfs_trans_free_busy(tp);
xfs_trans_free(tp);
}
/*
* Get inode's extents as described in bmv, and format for output.
* Calls formatter to fill the user's buffer until all extents
* are mapped, until the passed-in bmv->bmv_count slots have
* been filled, or until the formatter short-circuits the loop,
* if it is tracking filled-in extents on its own.
*/
int /* error code */
xfs_getbmap(
xfs_inode_t *ip,
struct getbmapx *bmv, /* user bmap structure */
xfs_bmap_format_t formatter, /* format to user */
void *arg) /* formatter arg */
{
__int64_t bmvend; /* last block requested */
int error = 0; /* return value */
__int64_t fixlen; /* length for -1 case */
int i; /* extent number */
int lock; /* lock state */
xfs_bmbt_irec_t *map; /* buffer for user's data */
xfs_mount_t *mp; /* file system mount point */
int nex; /* # of user extents can do */
int nexleft; /* # of user extents left */
int subnex; /* # of bmapi's can do */
int nmap; /* number of map entries */
struct getbmapx *out; /* output structure */
int whichfork; /* data or attr fork */
int prealloced; /* this is a file with
* preallocated data space */
int iflags; /* interface flags */
int bmapi_flags; /* flags for xfs_bmapi */
int cur_ext = 0;
mp = ip->i_mount;
iflags = bmv->bmv_iflags;
whichfork = iflags & BMV_IF_ATTRFORK ? XFS_ATTR_FORK : XFS_DATA_FORK;
if (whichfork == XFS_ATTR_FORK) {
if (XFS_IFORK_Q(ip)) {
if (ip->i_d.di_aformat != XFS_DINODE_FMT_EXTENTS &&
ip->i_d.di_aformat != XFS_DINODE_FMT_BTREE &&
ip->i_d.di_aformat != XFS_DINODE_FMT_LOCAL)
return XFS_ERROR(EINVAL);
} else if (unlikely(
ip->i_d.di_aformat != 0 &&
ip->i_d.di_aformat != XFS_DINODE_FMT_EXTENTS)) {
XFS_ERROR_REPORT("xfs_getbmap", XFS_ERRLEVEL_LOW,
ip->i_mount);
return XFS_ERROR(EFSCORRUPTED);
}
prealloced = 0;
fixlen = 1LL << 32;
} else {
if (ip->i_d.di_format != XFS_DINODE_FMT_EXTENTS &&
ip->i_d.di_format != XFS_DINODE_FMT_BTREE &&
ip->i_d.di_format != XFS_DINODE_FMT_LOCAL)
return XFS_ERROR(EINVAL);
if (xfs_get_extsz_hint(ip) ||
ip->i_d.di_flags & (XFS_DIFLAG_PREALLOC|XFS_DIFLAG_APPEND)){
prealloced = 1;
fixlen = mp->m_super->s_maxbytes;
} else {
prealloced = 0;
fixlen = XFS_ISIZE(ip);
}
}
if (bmv->bmv_length == -1) {
fixlen = XFS_FSB_TO_BB(mp, XFS_B_TO_FSB(mp, fixlen));
bmv->bmv_length =
max_t(__int64_t, fixlen - bmv->bmv_offset, 0);
} else if (bmv->bmv_length == 0) {
bmv->bmv_entries = 0;
return 0;
} else if (bmv->bmv_length < 0) {
return XFS_ERROR(EINVAL);
}
nex = bmv->bmv_count - 1;
if (nex <= 0)
return XFS_ERROR(EINVAL);
bmvend = bmv->bmv_offset + bmv->bmv_length;
if (bmv->bmv_count > ULONG_MAX / sizeof(struct getbmapx))
return XFS_ERROR(ENOMEM);
out = kmem_zalloc_large(bmv->bmv_count * sizeof(struct getbmapx), 0);
if (!out)
return XFS_ERROR(ENOMEM);
xfs_ilock(ip, XFS_IOLOCK_SHARED);
if (whichfork == XFS_DATA_FORK) {
if (!(iflags & BMV_IF_DELALLOC) &&
(ip->i_delayed_blks || XFS_ISIZE(ip) > ip->i_d.di_size)) {
error = -filemap_write_and_wait(VFS_I(ip)->i_mapping);
if (error)
goto out_unlock_iolock;
/*
* Even after flushing the inode, there can still be
* delalloc blocks on the inode beyond EOF due to
* speculative preallocation. These are not removed
* until the release function is called or the inode
* is inactivated. Hence we cannot assert here that
* ip->i_delayed_blks == 0.
*/
}
lock = xfs_ilock_data_map_shared(ip);
} else {
lock = xfs_ilock_attr_map_shared(ip);
}
/*
* Don't let nex be bigger than the number of extents
* we can have assuming alternating holes and real extents.
*/
if (nex > XFS_IFORK_NEXTENTS(ip, whichfork) * 2 + 1)
nex = XFS_IFORK_NEXTENTS(ip, whichfork) * 2 + 1;
bmapi_flags = xfs_bmapi_aflag(whichfork);
if (!(iflags & BMV_IF_PREALLOC))
bmapi_flags |= XFS_BMAPI_IGSTATE;
/*
* Allocate enough space to handle "subnex" maps at a time.
*/
error = ENOMEM;
subnex = 16;
map = kmem_alloc(subnex * sizeof(*map), KM_MAYFAIL | KM_NOFS);
if (!map)
goto out_unlock_ilock;
bmv->bmv_entries = 0;
if (XFS_IFORK_NEXTENTS(ip, whichfork) == 0 &&
(whichfork == XFS_ATTR_FORK || !(iflags & BMV_IF_DELALLOC))) {
error = 0;
goto out_free_map;
}
nexleft = nex;
do {
nmap = (nexleft > subnex) ? subnex : nexleft;
error = xfs_bmapi_read(ip, XFS_BB_TO_FSBT(mp, bmv->bmv_offset),
XFS_BB_TO_FSB(mp, bmv->bmv_length),
map, &nmap, bmapi_flags);
if (error)
goto out_free_map;
ASSERT(nmap <= subnex);
for (i = 0; i < nmap && nexleft && bmv->bmv_length; i++) {
out[cur_ext].bmv_oflags = 0;
if (map[i].br_state == XFS_EXT_UNWRITTEN)
out[cur_ext].bmv_oflags |= BMV_OF_PREALLOC;
else if (map[i].br_startblock == DELAYSTARTBLOCK)
out[cur_ext].bmv_oflags |= BMV_OF_DELALLOC;
out[cur_ext].bmv_offset =
XFS_FSB_TO_BB(mp, map[i].br_startoff);
out[cur_ext].bmv_length =
XFS_FSB_TO_BB(mp, map[i].br_blockcount);
out[cur_ext].bmv_unused1 = 0;
out[cur_ext].bmv_unused2 = 0;
/*
* delayed allocation extents that start beyond EOF can
* occur due to speculative EOF allocation when the
* delalloc extent is larger than the largest freespace
* extent at conversion time. These extents cannot be
* converted by data writeback, so can exist here even
* if we are not supposed to be finding delalloc
* extents.
*/
if (map[i].br_startblock == DELAYSTARTBLOCK &&
map[i].br_startoff <= XFS_B_TO_FSB(mp, XFS_ISIZE(ip)))
ASSERT((iflags & BMV_IF_DELALLOC) != 0);
if (map[i].br_startblock == HOLESTARTBLOCK &&
whichfork == XFS_ATTR_FORK) {
/* came to the end of attribute fork */
out[cur_ext].bmv_oflags |= BMV_OF_LAST;
goto out_free_map;
}
if (!xfs_getbmapx_fix_eof_hole(ip, &out[cur_ext],
prealloced, bmvend,
map[i].br_startblock))
goto out_free_map;
bmv->bmv_offset =
out[cur_ext].bmv_offset +
out[cur_ext].bmv_length;
bmv->bmv_length =
max_t(__int64_t, 0, bmvend - bmv->bmv_offset);
/*
* In case we don't want to return the hole,
* don't increase cur_ext so that we can reuse
* it in the next loop.
*/
if ((iflags & BMV_IF_NO_HOLES) &&
map[i].br_startblock == HOLESTARTBLOCK) {
memset(&out[cur_ext], 0, sizeof(out[cur_ext]));
continue;
}
nexleft--;
bmv->bmv_entries++;
cur_ext++;
}
} while (nmap && nexleft && bmv->bmv_length);
out_free_map:
kmem_free(map);
out_unlock_ilock:
xfs_iunlock(ip, lock);
out_unlock_iolock:
xfs_iunlock(ip, XFS_IOLOCK_SHARED);
for (i = 0; i < cur_ext; i++) {
int full = 0; /* user array is full */
/* format results & advance arg */
error = formatter(&arg, &out[i], &full);
if (error || full)
break;
}
kmem_free(out);
return error;
}
/*
* Recursively walks each level of a btree
* to count total fsblocks in use.
*/
STATIC int /* error */
xfs_bmap_count_tree(
xfs_mount_t *mp, /* file system mount point */
xfs_trans_t *tp, /* transaction pointer */
xfs_ifork_t *ifp, /* inode fork pointer */
xfs_fsblock_t blockno, /* file system block number */
int levelin, /* level in btree */
int *count) /* Count of blocks */
{
int error;
xfs_buf_t *bp, *nbp;
int level = levelin;
__be64 *pp;
xfs_fsblock_t bno = blockno;
xfs_fsblock_t nextbno;
struct xfs_btree_block *block, *nextblock;
int numrecs;
error = xfs_btree_read_bufl(mp, tp, bno, 0, &bp, XFS_BMAP_BTREE_REF,
&xfs_bmbt_buf_ops);
if (error)
return error;
*count += 1;
block = XFS_BUF_TO_BLOCK(bp);
if (--level) {
/* Not at node above leaves, count this level of nodes */
nextbno = be64_to_cpu(block->bb_u.l.bb_rightsib);
while (nextbno != NULLFSBLOCK) {
error = xfs_btree_read_bufl(mp, tp, nextbno, 0, &nbp,
XFS_BMAP_BTREE_REF,
&xfs_bmbt_buf_ops);
if (error)
return error;
*count += 1;
nextblock = XFS_BUF_TO_BLOCK(nbp);
nextbno = be64_to_cpu(nextblock->bb_u.l.bb_rightsib);
xfs_trans_brelse(tp, nbp);
}
/* Dive to the next level */
pp = XFS_BMBT_PTR_ADDR(mp, block, 1, mp->m_bmap_dmxr[1]);
bno = be64_to_cpu(*pp);
if (unlikely((error =
xfs_bmap_count_tree(mp, tp, ifp, bno, level, count)) < 0)) {
xfs_trans_brelse(tp, bp);
XFS_ERROR_REPORT("xfs_bmap_count_tree(1)",
XFS_ERRLEVEL_LOW, mp);
return XFS_ERROR(EFSCORRUPTED);
}
xfs_trans_brelse(tp, bp);
} else {
/* count all level 1 nodes and their leaves */
for (;;) {
nextbno = be64_to_cpu(block->bb_u.l.bb_rightsib);
numrecs = be16_to_cpu(block->bb_numrecs);
xfs_bmap_disk_count_leaves(mp, block, numrecs, count);
xfs_trans_brelse(tp, bp);
if (nextbno == NULLFSBLOCK)
break;
bno = nextbno;
error = xfs_btree_read_bufl(mp, tp, bno, 0, &bp,
XFS_BMAP_BTREE_REF,
&xfs_bmbt_buf_ops);
if (error)
return error;
*count += 1;
block = XFS_BUF_TO_BLOCK(bp);
}
}
return 0;
}
/*
* Check the consistency of the data block.
* The input can also be a block-format directory.
* Return 0 is the buffer is good, otherwise an error.
*/
int
__xfs_dir3_data_check(
struct xfs_inode *dp, /* incore inode pointer */
struct xfs_buf *bp) /* data block's buffer */
{
xfs_dir2_dataptr_t addr; /* addr for leaf lookup */
xfs_dir2_data_free_t *bf; /* bestfree table */
xfs_dir2_block_tail_t *btp=NULL; /* block tail */
int count; /* count of entries found */
xfs_dir2_data_hdr_t *hdr; /* data block header */
xfs_dir2_data_entry_t *dep; /* data entry */
xfs_dir2_data_free_t *dfp; /* bestfree entry */
xfs_dir2_data_unused_t *dup; /* unused entry */
char *endp; /* end of useful data */
int freeseen; /* mask of bestfrees seen */
xfs_dahash_t hash; /* hash of current name */
int i; /* leaf index */
int lastfree; /* last entry was unused */
xfs_dir2_leaf_entry_t *lep=NULL; /* block leaf entries */
xfs_mount_t *mp; /* filesystem mount point */
char *p; /* current data position */
int stale; /* count of stale leaves */
struct xfs_name name;
const struct xfs_dir_ops *ops;
struct xfs_da_geometry *geo;
mp = bp->b_target->bt_mount;
geo = mp->m_dir_geo;
/*
* We can be passed a null dp here from a verifier, so we need to go the
* hard way to get them.
*/
ops = xfs_dir_get_ops(mp, dp);
hdr = bp->b_addr;
p = (char *)ops->data_entry_p(hdr);
switch (hdr->magic) {
case cpu_to_be32(XFS_DIR3_BLOCK_MAGIC):
case cpu_to_be32(XFS_DIR2_BLOCK_MAGIC):
btp = xfs_dir2_block_tail_p(geo, hdr);
lep = xfs_dir2_block_leaf_p(btp);
endp = (char *)lep;
/*
* The number of leaf entries is limited by the size of the
* block and the amount of space used by the data entries.
* We don't know how much space is used by the data entries yet,
* so just ensure that the count falls somewhere inside the
* block right now.
*/
XFS_WANT_CORRUPTED_RETURN(mp, be32_to_cpu(btp->count) <
((char *)btp - p) / sizeof(struct xfs_dir2_leaf_entry));
break;
case cpu_to_be32(XFS_DIR3_DATA_MAGIC):
case cpu_to_be32(XFS_DIR2_DATA_MAGIC):
endp = (char *)hdr + geo->blksize;
break;
default:
XFS_ERROR_REPORT("Bad Magic", XFS_ERRLEVEL_LOW, mp);
return -EFSCORRUPTED;
}
/*
* Account for zero bestfree entries.
*/
bf = ops->data_bestfree_p(hdr);
count = lastfree = freeseen = 0;
if (!bf[0].length) {
XFS_WANT_CORRUPTED_RETURN(mp, !bf[0].offset);
freeseen |= 1 << 0;
}
if (!bf[1].length) {
XFS_WANT_CORRUPTED_RETURN(mp, !bf[1].offset);
freeseen |= 1 << 1;
}
if (!bf[2].length) {
XFS_WANT_CORRUPTED_RETURN(mp, !bf[2].offset);
freeseen |= 1 << 2;
}
XFS_WANT_CORRUPTED_RETURN(mp, be16_to_cpu(bf[0].length) >=
be16_to_cpu(bf[1].length));
XFS_WANT_CORRUPTED_RETURN(mp, be16_to_cpu(bf[1].length) >=
be16_to_cpu(bf[2].length));
/*
* Loop over the data/unused entries.
*/
while (p < endp) {
dup = (xfs_dir2_data_unused_t *)p;
/*
* If it's unused, look for the space in the bestfree table.
* If we find it, account for that, else make sure it
* doesn't need to be there.
*/
if (be16_to_cpu(dup->freetag) == XFS_DIR2_DATA_FREE_TAG) {
XFS_WANT_CORRUPTED_RETURN(mp, lastfree == 0);
XFS_WANT_CORRUPTED_RETURN(mp,
be16_to_cpu(*xfs_dir2_data_unused_tag_p(dup)) ==
(char *)dup - (char *)hdr);
dfp = xfs_dir2_data_freefind(hdr, bf, dup);
if (dfp) {
i = (int)(dfp - bf);
XFS_WANT_CORRUPTED_RETURN(mp,
(freeseen & (1 << i)) == 0);
freeseen |= 1 << i;
} else {
XFS_WANT_CORRUPTED_RETURN(mp,
be16_to_cpu(dup->length) <=
be16_to_cpu(bf[2].length));
}
p += be16_to_cpu(dup->length);
lastfree = 1;
continue;
}
/*
* It's a real entry. Validate the fields.
* If this is a block directory then make sure it's
* in the leaf section of the block.
* The linear search is crude but this is DEBUG code.
*/
dep = (xfs_dir2_data_entry_t *)p;
XFS_WANT_CORRUPTED_RETURN(mp, dep->namelen != 0);
XFS_WANT_CORRUPTED_RETURN(mp,
!xfs_dir_ino_validate(mp, be64_to_cpu(dep->inumber)));
XFS_WANT_CORRUPTED_RETURN(mp,
be16_to_cpu(*ops->data_entry_tag_p(dep)) ==
(char *)dep - (char *)hdr);
XFS_WANT_CORRUPTED_RETURN(mp,
ops->data_get_ftype(dep) < XFS_DIR3_FT_MAX);
count++;
lastfree = 0;
if (hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC) ||
hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC)) {
addr = xfs_dir2_db_off_to_dataptr(geo, geo->datablk,
(xfs_dir2_data_aoff_t)
((char *)dep - (char *)hdr));
name.name = dep->name;
name.len = dep->namelen;
hash = mp->m_dirnameops->hashname(&name);
for (i = 0; i < be32_to_cpu(btp->count); i++) {
if (be32_to_cpu(lep[i].address) == addr &&
be32_to_cpu(lep[i].hashval) == hash)
break;
}
XFS_WANT_CORRUPTED_RETURN(mp,
i < be32_to_cpu(btp->count));
}
p += ops->data_entsize(dep->namelen);
}
/*
* Need to have seen all the entries and all the bestfree slots.
*/
XFS_WANT_CORRUPTED_RETURN(mp, freeseen == 7);
if (hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC) ||
hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC)) {
for (i = stale = 0; i < be32_to_cpu(btp->count); i++) {
if (lep[i].address ==
cpu_to_be32(XFS_DIR2_NULL_DATAPTR))
stale++;
if (i > 0)
XFS_WANT_CORRUPTED_RETURN(mp,
be32_to_cpu(lep[i].hashval) >=
be32_to_cpu(lep[i - 1].hashval));
}
XFS_WANT_CORRUPTED_RETURN(mp, count ==
be32_to_cpu(btp->count) - be32_to_cpu(btp->stale));
XFS_WANT_CORRUPTED_RETURN(mp, stale == be32_to_cpu(btp->stale));
}
return 0;
}
