/*
* Look up a name in a leaf attribute list structure.
*
* This leaf block cannot have a "remote" value, we only call this routine
* if bmap_one_block() says there is only one block (ie: no remote blks).
*/
STATIC int
xfs_attr_leaf_get(xfs_da_args_t *args)
{
struct xfs_buf *bp;
int error;
trace_xfs_attr_leaf_get(args);
args->blkno = 0;
error = xfs_attr3_leaf_read(args->trans, args->dp, args->blkno, -1, &bp);
if (error)
return error;
error = xfs_attr3_leaf_lookup_int(bp, args);
if (error != -EEXIST) {
xfs_trans_brelse(args->trans, bp);
return error;
}
error = xfs_attr3_leaf_getvalue(bp, args);
xfs_trans_brelse(args->trans, bp);
if (!error && (args->rmtblkno > 0) && !(args->flags & ATTR_KERNOVAL)) {
error = xfs_attr_rmtval_get(args);
}
return error;
}
/*
* Given an AG extent, find the lowest-numbered run of shared blocks
* within that range and return the range in fbno/flen. If
* find_end_of_shared is true, return the longest contiguous extent of
* shared blocks. If there are no shared extents, fbno and flen will
* be set to NULLAGBLOCK and 0, respectively.
*/
int
xfs_reflink_find_shared(
struct xfs_mount *mp,
struct xfs_trans *tp,
xfs_agnumber_t agno,
xfs_agblock_t agbno,
xfs_extlen_t aglen,
xfs_agblock_t *fbno,
xfs_extlen_t *flen,
bool find_end_of_shared)
{
struct xfs_buf *agbp;
struct xfs_btree_cur *cur;
int error;
error = xfs_alloc_read_agf(mp, tp, agno, 0, &agbp);
if (error)
return error;
if (!agbp)
return -ENOMEM;
cur = xfs_refcountbt_init_cursor(mp, tp, agbp, agno, NULL);
error = xfs_refcount_find_shared(cur, agbno, aglen, fbno, flen,
find_end_of_shared);
xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
xfs_trans_brelse(tp, agbp);
return error;
}
/* ARGSUSED */
STATIC int
xfs_qm_dqread(
xfs_trans_t **tpp,
xfs_dqid_t id,
xfs_dquot_t *dqp, /* dquot to get filled in */
uint flags)
{
xfs_disk_dquot_t *ddqp;
xfs_buf_t *bp;
int error;
xfs_trans_t *tp;
ASSERT(tpp);
/*
* get a pointer to the on-disk dquot and the buffer containing it
* dqp already knows its own type (GROUP/USER).
*/
xfs_dqtrace_entry(dqp, "DQREAD");
if ((error = xfs_qm_dqtobp(tpp, dqp, &ddqp, &bp, flags))) {
return (error);
}
tp = *tpp;
/* copy everything from disk dquot to the incore dquot */
memcpy(&dqp->q_core, ddqp, sizeof(xfs_disk_dquot_t));
ASSERT(be32_to_cpu(dqp->q_core.d_id) == id);
xfs_qm_dquot_logitem_init(dqp);
/*
* Reservation counters are defined as reservation plus current usage
* to avoid having to add everytime.
*/
dqp->q_res_bcount = be64_to_cpu(ddqp->d_bcount);
dqp->q_res_icount = be64_to_cpu(ddqp->d_icount);
dqp->q_res_rtbcount = be64_to_cpu(ddqp->d_rtbcount);
/* Mark the buf so that this will stay incore a little longer */
XFS_BUF_SET_VTYPE_REF(bp, B_FS_DQUOT, XFS_DQUOT_REF);
/*
* We got the buffer with a xfs_trans_read_buf() (in dqtobp())
* So we need to release with xfs_trans_brelse().
* The strategy here is identical to that of inodes; we lock
* the dquot in xfs_qm_dqget() before making it accessible to
* others. This is because dquots, like inodes, need a good level of
* concurrency, and we don't want to take locks on the entire buffers
* for dquot accesses.
* Note also that the dquot buffer may even be dirty at this point, if
* this particular dquot was repaired. We still aren't afraid to
* brelse it because we have the changes incore.
*/
ASSERT(XFS_BUF_ISBUSY(bp));
ASSERT(XFS_BUF_VALUSEMA(bp) <= 0);
xfs_trans_brelse(tp, bp);
return (error);
}
/*
* Indiscriminately delete the entire attribute fork
*
* Recurse (gasp!) through the attribute nodes until we find leaves.
* We're doing a depth-first traversal in order to invalidate everything.
*/
int
xfs_attr3_root_inactive(
struct xfs_trans **trans,
struct xfs_inode *dp)
{
struct xfs_da_blkinfo *info;
struct xfs_buf *bp;
xfs_daddr_t blkno;
int error;
/*
* Read block 0 to see what we have to work with.
* We only get here if we have extents, since we remove
* the extents in reverse order the extent containing
* block 0 must still be there.
*/
error = xfs_da3_node_read(*trans, dp, 0, -1, &bp, XFS_ATTR_FORK);
if (error)
return error;
blkno = bp->b_bn;
/*
* Invalidate the tree, even if the "tree" is only a single leaf block.
* This is a depth-first traversal!
*/
info = bp->b_addr;
switch (info->magic) {
case cpu_to_be16(XFS_DA_NODE_MAGIC):
case cpu_to_be16(XFS_DA3_NODE_MAGIC):
error = xfs_attr3_node_inactive(trans, dp, bp, 1);
break;
case cpu_to_be16(XFS_ATTR_LEAF_MAGIC):
case cpu_to_be16(XFS_ATTR3_LEAF_MAGIC):
error = xfs_attr3_leaf_inactive(trans, dp, bp);
break;
default:
error = -EIO;
xfs_trans_brelse(*trans, bp);
break;
}
if (error)
return error;
/*
* Invalidate the incore copy of the root block.
*/
error = xfs_da_get_buf(*trans, dp, 0, blkno, &bp, XFS_ATTR_FORK);
if (error)
return error;
xfs_trans_binval(*trans, bp); /* remove from cache */
/*
* Commit the invalidate and start the next transaction.
*/
error = xfs_trans_roll(trans, dp);
return error;
}
/*
* Remove a name from the leaf attribute list structure
*
* This leaf block cannot have a "remote" value, we only call this routine
* if bmap_one_block() says there is only one block (ie: no remote blks).
*/
STATIC int
xfs_attr_leaf_removename(xfs_da_args_t *args)
{
xfs_inode_t *dp;
struct xfs_buf *bp;
int error, committed, forkoff;
trace_xfs_attr_leaf_removename(args);
/*
* Remove the attribute.
*/
dp = args->dp;
args->blkno = 0;
error = xfs_attr3_leaf_read(args->trans, args->dp, args->blkno, -1, &bp);
if (error)
return error;
error = xfs_attr3_leaf_lookup_int(bp, args);
if (error == -ENOATTR) {
xfs_trans_brelse(args->trans, bp);
return error;
}
xfs_attr3_leaf_remove(bp, args);
/*
* If the result is small enough, shrink it all into the inode.
*/
if ((forkoff = xfs_attr_shortform_allfit(bp, dp))) {
xfs_bmap_init(args->flist, args->firstblock);
error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
/* bp is gone due to xfs_da_shrink_inode */
if (!error) {
error = xfs_bmap_finish(&args->trans, args->flist,
&committed);
}
if (error) {
ASSERT(committed);
args->trans = NULL;
xfs_bmap_cancel(args->flist);
return error;
}
/*
* bmap_finish() may have committed the last trans and started
* a new one. We need the inode to be in all transactions.
*/
if (committed)
xfs_trans_ijoin(args->trans, dp, 0);
}
return 0;
}
/* Clean up after calling xfs_rmap_finish_one. */
void
xfs_rmap_finish_one_cleanup(
struct xfs_trans *tp,
struct xfs_btree_cur *rcur,
int error)
{
struct xfs_buf *agbp;
if (rcur == NULL)
return;
agbp = rcur->bc_private.a.agbp;
xfs_btree_del_cursor(rcur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
if (error)
xfs_trans_brelse(tp, agbp);
}
/*
* Copy out attribute entries for attr_list(), for leaf attribute lists.
*/
STATIC int
xfs_attr_leaf_list(xfs_attr_list_context_t *context)
{
int error;
struct xfs_buf *bp;
trace_xfs_attr_leaf_list(context);
context->cursor->blkno = 0;
error = xfs_attr3_leaf_read(NULL, context->dp, 0, -1, &bp);
if (error)
return error;
error = xfs_attr3_leaf_list_int(bp, context);
xfs_trans_brelse(NULL, bp);
return error;
}
/*
* Look up a filename in a node attribute list.
*
* This routine gets called for any attribute fork that has more than one
* block, ie: both true Btree attr lists and for single-leaf-blocks with
* "remote" values taking up more blocks.
*/
STATIC int
xfs_attr_node_get(xfs_da_args_t *args)
{
xfs_da_state_t *state;
xfs_da_state_blk_t *blk;
int error, retval;
int i;
trace_xfs_attr_node_get(args);
state = xfs_da_state_alloc();
state->args = args;
state->mp = args->dp->i_mount;
/*
* Search to see if name exists, and get back a pointer to it.
*/
error = xfs_da3_node_lookup_int(state, &retval);
if (error) {
retval = error;
} else if (retval == -EEXIST) {
blk = &state->path.blk[ state->path.active-1 ];
ASSERT(blk->bp != NULL);
ASSERT(blk->magic == XFS_ATTR_LEAF_MAGIC);
/*
* Get the value, local or "remote"
*/
retval = xfs_attr3_leaf_getvalue(blk->bp, args);
if (!retval && (args->rmtblkno > 0)
&& !(args->flags & ATTR_KERNOVAL)) {
retval = xfs_attr_rmtval_get(args);
}
}
/*
* If not in a transaction, we have to release all the buffers.
*/
for (i = 0; i < state->path.active; i++) {
xfs_trans_brelse(args->trans, state->path.blk[i].bp);
state->path.blk[i].bp = NULL;
}
xfs_da_state_free(state);
return retval;
}
STATIC int
xfs_qm_dqrepair(
struct xfs_mount *mp,
struct xfs_trans *tp,
struct xfs_dquot *dqp,
xfs_dqid_t firstid,
struct xfs_buf **bpp)
{
int error;
struct xfs_disk_dquot *ddq;
struct xfs_dqblk *d;
int i;
/*
* Read the buffer without verification so we get the corrupted
* buffer returned to us. make sure we verify it on write, though.
*/
error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, dqp->q_blkno,
mp->m_quotainfo->qi_dqchunklen,
0, bpp, NULL);
if (error) {
ASSERT(*bpp == NULL);
return XFS_ERROR(error);
}
(*bpp)->b_ops = &xfs_dquot_buf_ops;
ASSERT(xfs_buf_islocked(*bpp));
d = (struct xfs_dqblk *)(*bpp)->b_addr;
/* Do the actual repair of dquots in this buffer */
for (i = 0; i < mp->m_quotainfo->qi_dqperchunk; i++) {
ddq = &d[i].dd_diskdq;
error = xfs_dqcheck(mp, ddq, firstid + i,
dqp->dq_flags & XFS_DQ_ALLTYPES,
XFS_QMOPT_DQREPAIR, "xfs_qm_dqrepair");
if (error) {
/* repair failed, we're screwed */
xfs_trans_brelse(tp, *bpp);
return XFS_ERROR(EIO);
}
}
return 0;
}
/*
* Remove a name from the leaf attribute list structure
*
* This leaf block cannot have a "remote" value, we only call this routine
* if bmap_one_block() says there is only one block (ie: no remote blks).
*/
STATIC int
xfs_attr_leaf_removename(xfs_da_args_t *args)
{
xfs_inode_t *dp;
struct xfs_buf *bp;
int error, forkoff;
trace_xfs_attr_leaf_removename(args);
/*
* Remove the attribute.
*/
dp = args->dp;
args->blkno = 0;
error = xfs_attr3_leaf_read(args->trans, args->dp, args->blkno, -1, &bp);
if (error)
return error;
error = xfs_attr3_leaf_lookup_int(bp, args);
if (error == -ENOATTR) {
xfs_trans_brelse(args->trans, bp);
return error;
}
xfs_attr3_leaf_remove(bp, args);
/*
* If the result is small enough, shrink it all into the inode.
*/
if ((forkoff = xfs_attr_shortform_allfit(bp, dp))) {
xfs_defer_init(args->dfops, args->firstblock);
error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
/* bp is gone due to xfs_da_shrink_inode */
if (!error)
error = xfs_defer_finish(&args->trans, args->dfops, dp);
if (error) {
args->trans = NULL;
xfs_defer_cancel(args->dfops);
return error;
}
}
return 0;
}
/*
* Look up an entry in the block. This is the external routine,
* xfs_dir2_block_lookup_int does the real work.
*/
int /* error */
xfs_dir2_block_lookup(
xfs_da_args_t *args) /* dir lookup arguments */
{
xfs_dir2_data_hdr_t *hdr; /* block header */
xfs_dir2_leaf_entry_t *blp; /* block leaf entries */
struct xfs_buf *bp; /* block buffer */
xfs_dir2_block_tail_t *btp; /* block tail */
xfs_dir2_data_entry_t *dep; /* block data entry */
xfs_inode_t *dp; /* incore inode */
int ent; /* entry index */
int error; /* error return value */
xfs_mount_t *mp; /* filesystem mount point */
trace_xfs_dir2_block_lookup(args);
/*
* Get the buffer, look up the entry.
* If not found (ENOENT) then return, have no buffer.
*/
if ((error = xfs_dir2_block_lookup_int(args, &bp, &ent)))
return error;
dp = args->dp;
mp = dp->i_mount;
hdr = bp->b_addr;
xfs_dir3_data_check(dp, bp);
btp = xfs_dir2_block_tail_p(args->geo, hdr);
blp = xfs_dir2_block_leaf_p(btp);
/*
* Get the offset from the leaf entry, to point to the data.
*/
dep = (xfs_dir2_data_entry_t *)((char *)hdr +
xfs_dir2_dataptr_to_off(args->geo,
be32_to_cpu(blp[ent].address)));
/*
* Fill in inode number, CI name if appropriate, release the block.
*/
args->inumber = be64_to_cpu(dep->inumber);
args->filetype = dp->d_ops->data_get_ftype(dep);
error = xfs_dir_cilookup_result(args, dep->name, dep->namelen);
xfs_trans_brelse(args->trans, bp);
return error;
}
/*
* Select an allocation group to look for a free inode in, based on the parent
* inode and then mode. Return the allocation group buffer.
*/
STATIC xfs_buf_t * /* allocation group buffer */
xfs_ialloc_ag_select(
xfs_trans_t *tp, /* transaction pointer */
xfs_ino_t parent, /* parent directory inode number */
mode_t mode, /* bits set to indicate file type */
int okalloc) /* ok to allocate more space */
{
xfs_buf_t *agbp; /* allocation group header buffer */
xfs_agnumber_t agcount; /* number of ag's in the filesystem */
xfs_agnumber_t agno; /* current ag number */
int flags; /* alloc buffer locking flags */
xfs_extlen_t ineed; /* blocks needed for inode allocation */
xfs_extlen_t longest = 0; /* longest extent available */
xfs_mount_t *mp; /* mount point structure */
int needspace; /* file mode implies space allocated */
xfs_perag_t *pag; /* per allocation group data */
xfs_agnumber_t pagno; /* parent (starting) ag number */
/*
* Files of these types need at least one block if length > 0
* (and they won't fit in the inode, but that's hard to figure out).
*/
needspace = S_ISDIR(mode) || S_ISREG(mode) || S_ISLNK(mode);
mp = tp->t_mountp;
agcount = mp->m_maxagi;
if (S_ISDIR(mode))
pagno = xfs_ialloc_next_ag(mp);
else {
pagno = XFS_INO_TO_AGNO(mp, parent);
if (pagno >= agcount)
pagno = 0;
}
ASSERT(pagno < agcount);
/*
* Loop through allocation groups, looking for one with a little
* free space in it. Note we don't look for free inodes, exactly.
* Instead, we include whether there is a need to allocate inodes
* to mean that blocks must be allocated for them,
* if none are currently free.
*/
agno = pagno;
flags = XFS_ALLOC_FLAG_TRYLOCK;
down_read(&mp->m_peraglock);
for (;;) {
pag = &mp->m_perag[agno];
if (!pag->pagi_init) {
if (xfs_ialloc_read_agi(mp, tp, agno, &agbp)) {
agbp = NULL;
goto nextag;
}
} else
agbp = NULL;
if (!pag->pagi_inodeok) {
xfs_ialloc_next_ag(mp);
goto unlock_nextag;
}
/*
* Is there enough free space for the file plus a block
* of inodes (if we need to allocate some)?
*/
ineed = pag->pagi_freecount ? 0 : XFS_IALLOC_BLOCKS(mp);
if (ineed && !pag->pagf_init) {
if (agbp == NULL &&
xfs_ialloc_read_agi(mp, tp, agno, &agbp)) {
agbp = NULL;
goto nextag;
}
(void)xfs_alloc_pagf_init(mp, tp, agno, flags);
}
if (!ineed || pag->pagf_init) {
if (ineed && !(longest = pag->pagf_longest))
longest = pag->pagf_flcount > 0;
if (!ineed ||
(pag->pagf_freeblks >= needspace + ineed &&
longest >= ineed &&
okalloc)) {
if (agbp == NULL &&
xfs_ialloc_read_agi(mp, tp, agno, &agbp)) {
agbp = NULL;
goto nextag;
}
up_read(&mp->m_peraglock);
return agbp;
}
}
unlock_nextag:
if (agbp)
xfs_trans_brelse(tp, agbp);
nextag:
/*
* No point in iterating over the rest, if we're shutting
* down.
*/
if (XFS_FORCED_SHUTDOWN(mp)) {
up_read(&mp->m_peraglock);
return NULL;
}
agno++;
if (agno >= agcount)
agno = 0;
if (agno == pagno) {
if (flags == 0) {
up_read(&mp->m_peraglock);
return NULL;
}
flags = 0;
}
}
}
/*
* Allocate an inode on disk.
* Mode is used to tell whether the new inode will need space, and whether
* it is a directory.
*
* The arguments IO_agbp and alloc_done are defined to work within
* the constraint of one allocation per transaction.
* xfs_dialloc() is designed to be called twice if it has to do an
* allocation to make more free inodes. On the first call,
* IO_agbp should be set to NULL. If an inode is available,
* i.e., xfs_dialloc() did not need to do an allocation, an inode
* number is returned. In this case, IO_agbp would be set to the
* current ag_buf and alloc_done set to false.
* If an allocation needed to be done, xfs_dialloc would return
* the current ag_buf in IO_agbp and set alloc_done to true.
* The caller should then commit the current transaction, allocate a new
* transaction, and call xfs_dialloc() again, passing in the previous
* value of IO_agbp. IO_agbp should be held across the transactions.
* Since the agbp is locked across the two calls, the second call is
* guaranteed to have a free inode available.
*
* Once we successfully pick an inode its number is returned and the
* on-disk data structures are updated. The inode itself is not read
* in, since doing so would break ordering constraints with xfs_reclaim.
*/
int
xfs_dialloc(
xfs_trans_t *tp, /* transaction pointer */
xfs_ino_t parent, /* parent inode (directory) */
mode_t mode, /* mode bits for new inode */
int okalloc, /* ok to allocate more space */
xfs_buf_t **IO_agbp, /* in/out ag header's buffer */
boolean_t *alloc_done, /* true if we needed to replenish
inode freelist */
xfs_ino_t *inop) /* inode number allocated */
{
xfs_agnumber_t agcount; /* number of allocation groups */
xfs_buf_t *agbp; /* allocation group header's buffer */
xfs_agnumber_t agno; /* allocation group number */
xfs_agi_t *agi; /* allocation group header structure */
xfs_btree_cur_t *cur; /* inode allocation btree cursor */
int error; /* error return value */
int i; /* result code */
int ialloced; /* inode allocation status */
int noroom = 0; /* no space for inode blk allocation */
xfs_ino_t ino; /* fs-relative inode to be returned */
/* REFERENCED */
int j; /* result code */
xfs_mount_t *mp; /* file system mount structure */
int offset; /* index of inode in chunk */
xfs_agino_t pagino; /* parent's a.g. relative inode # */
xfs_agnumber_t pagno; /* parent's allocation group number */
xfs_inobt_rec_incore_t rec; /* inode allocation record */
xfs_agnumber_t tagno; /* testing allocation group number */
xfs_btree_cur_t *tcur; /* temp cursor */
xfs_inobt_rec_incore_t trec; /* temp inode allocation record */
if (*IO_agbp == NULL) {
/*
* We do not have an agbp, so select an initial allocation
* group for inode allocation.
*/
agbp = xfs_ialloc_ag_select(tp, parent, mode, okalloc);
/*
* Couldn't find an allocation group satisfying the
* criteria, give up.
*/
if (!agbp) {
*inop = NULLFSINO;
return 0;
}
agi = XFS_BUF_TO_AGI(agbp);
ASSERT(be32_to_cpu(agi->agi_magicnum) == XFS_AGI_MAGIC);
} else {
/*
* Continue where we left off before. In this case, we
* know that the allocation group has free inodes.
*/
agbp = *IO_agbp;
agi = XFS_BUF_TO_AGI(agbp);
ASSERT(be32_to_cpu(agi->agi_magicnum) == XFS_AGI_MAGIC);
ASSERT(be32_to_cpu(agi->agi_freecount) > 0);
}
mp = tp->t_mountp;
agcount = mp->m_sb.sb_agcount;
agno = be32_to_cpu(agi->agi_seqno);
tagno = agno;
pagno = XFS_INO_TO_AGNO(mp, parent);
pagino = XFS_INO_TO_AGINO(mp, parent);
/*
* If we have already hit the ceiling of inode blocks then clear
* okalloc so we scan all available agi structures for a free
* inode.
*/
if (mp->m_maxicount &&
mp->m_sb.sb_icount + XFS_IALLOC_INODES(mp) > mp->m_maxicount) {
noroom = 1;
okalloc = 0;
}
/*
* Loop until we find an allocation group that either has free inodes
* or in which we can allocate some inodes. Iterate through the
* allocation groups upward, wrapping at the end.
*/
*alloc_done = B_FALSE;
while (!agi->agi_freecount) {
/*
* Don't do anything if we're not supposed to allocate
* any blocks, just go on to the next ag.
*/
if (okalloc) {
/*
* Try to allocate some new inodes in the allocation
* group.
*/
if ((error = xfs_ialloc_ag_alloc(tp, agbp, &ialloced))) {
xfs_trans_brelse(tp, agbp);
if (error == ENOSPC) {
*inop = NULLFSINO;
return 0;
} else
return error;
}
if (ialloced) {
/*
* We successfully allocated some inodes, return
* the current context to the caller so that it
* can commit the current transaction and call
* us again where we left off.
*/
ASSERT(be32_to_cpu(agi->agi_freecount) > 0);
*alloc_done = B_TRUE;
*IO_agbp = agbp;
*inop = NULLFSINO;
return 0;
}
}
/*
* If it failed, give up on this ag.
*/
xfs_trans_brelse(tp, agbp);
/*
* Go on to the next ag: get its ag header.
*/
nextag:
if (++tagno == agcount)
tagno = 0;
if (tagno == agno) {
*inop = NULLFSINO;
return noroom ? ENOSPC : 0;
}
down_read(&mp->m_peraglock);
if (mp->m_perag[tagno].pagi_inodeok == 0) {
up_read(&mp->m_peraglock);
goto nextag;
}
error = xfs_ialloc_read_agi(mp, tp, tagno, &agbp);
up_read(&mp->m_peraglock);
if (error)
goto nextag;
agi = XFS_BUF_TO_AGI(agbp);
ASSERT(be32_to_cpu(agi->agi_magicnum) == XFS_AGI_MAGIC);
}
/*
* Here with an allocation group that has a free inode.
* Reset agno since we may have chosen a new ag in the
* loop above.
*/
agno = tagno;
*IO_agbp = NULL;
cur = xfs_btree_init_cursor(mp, tp, agbp, be32_to_cpu(agi->agi_seqno),
XFS_BTNUM_INO, (xfs_inode_t *)0, 0);
/*
* If pagino is 0 (this is the root inode allocation) use newino.
* This must work because we've just allocated some.
*/
if (!pagino)
pagino = be32_to_cpu(agi->agi_newino);
#ifdef DEBUG
if (cur->bc_nlevels == 1) {
int freecount = 0;
if ((error = xfs_inobt_lookup_ge(cur, 0, 0, 0, &i)))
goto error0;
XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
do {
if ((error = xfs_inobt_get_rec(cur, &rec.ir_startino,
&rec.ir_freecount, &rec.ir_free, &i)))
goto error0;
XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
freecount += rec.ir_freecount;
if ((error = xfs_inobt_increment(cur, 0, &i)))
goto error0;
} while (i == 1);
ASSERT(freecount == be32_to_cpu(agi->agi_freecount) ||
XFS_FORCED_SHUTDOWN(mp));
}
#endif
/*
* If in the same a.g. as the parent, try to get near the parent.
*/
if (pagno == agno) {
if ((error = xfs_inobt_lookup_le(cur, pagino, 0, 0, &i)))
goto error0;
if (i != 0 &&
(error = xfs_inobt_get_rec(cur, &rec.ir_startino,
&rec.ir_freecount, &rec.ir_free, &j)) == 0 &&
j == 1 &&
rec.ir_freecount > 0) {
/*
* Found a free inode in the same chunk
* as parent, done.
*/
}
/*
* In the same a.g. as parent, but parent's chunk is full.
*/
else {
int doneleft; /* done, to the left */
int doneright; /* done, to the right */
if (error)
goto error0;
ASSERT(i == 1);
ASSERT(j == 1);
/*
* Duplicate the cursor, search left & right
* simultaneously.
*/
if ((error = xfs_btree_dup_cursor(cur, &tcur)))
goto error0;
/*
* Search left with tcur, back up 1 record.
*/
if ((error = xfs_inobt_decrement(tcur, 0, &i)))
goto error1;
doneleft = !i;
if (!doneleft) {
if ((error = xfs_inobt_get_rec(tcur,
&trec.ir_startino,
&trec.ir_freecount,
&trec.ir_free, &i)))
goto error1;
XFS_WANT_CORRUPTED_GOTO(i == 1, error1);
}
/*
* Search right with cur, go forward 1 record.
*/
if ((error = xfs_inobt_increment(cur, 0, &i)))
goto error1;
doneright = !i;
if (!doneright) {
if ((error = xfs_inobt_get_rec(cur,
&rec.ir_startino,
&rec.ir_freecount,
&rec.ir_free, &i)))
goto error1;
XFS_WANT_CORRUPTED_GOTO(i == 1, error1);
}
/*
* Loop until we find the closest inode chunk
* with a free one.
*/
while (!doneleft || !doneright) {
int useleft; /* using left inode
chunk this time */
/*
* Figure out which block is closer,
* if both are valid.
*/
if (!doneleft && !doneright)
useleft =
pagino -
(trec.ir_startino +
XFS_INODES_PER_CHUNK - 1) <
rec.ir_startino - pagino;
else
useleft = !doneleft;
/*
* If checking the left, does it have
* free inodes?
*/
if (useleft && trec.ir_freecount) {
/*
* Yes, set it up as the chunk to use.
*/
rec = trec;
xfs_btree_del_cursor(cur,
XFS_BTREE_NOERROR);
cur = tcur;
break;
}
/*
* If checking the right, does it have
* free inodes?
*/
if (!useleft && rec.ir_freecount) {
/*
* Yes, it's already set up.
*/
xfs_btree_del_cursor(tcur,
XFS_BTREE_NOERROR);
break;
}
/*
* If used the left, get another one
* further left.
*/
if (useleft) {
if ((error = xfs_inobt_decrement(tcur, 0,
&i)))
goto error1;
doneleft = !i;
if (!doneleft) {
if ((error = xfs_inobt_get_rec(
tcur,
&trec.ir_startino,
&trec.ir_freecount,
&trec.ir_free, &i)))
goto error1;
XFS_WANT_CORRUPTED_GOTO(i == 1,
error1);
}
}
/*
* If used the right, get another one
* further right.
*/
else {
if ((error = xfs_inobt_increment(cur, 0,
&i)))
goto error1;
doneright = !i;
if (!doneright) {
if ((error = xfs_inobt_get_rec(
cur,
&rec.ir_startino,
&rec.ir_freecount,
&rec.ir_free, &i)))
goto error1;
XFS_WANT_CORRUPTED_GOTO(i == 1,
error1);
}
}
}
ASSERT(!doneleft || !doneright);
}
}
/*
* In a different a.g. from the parent.
* See if the most recently allocated block has any free.
*/
else if (be32_to_cpu(agi->agi_newino) != NULLAGINO) {
if ((error = xfs_inobt_lookup_eq(cur,
be32_to_cpu(agi->agi_newino), 0, 0, &i)))
goto error0;
if (i == 1 &&
(error = xfs_inobt_get_rec(cur, &rec.ir_startino,
&rec.ir_freecount, &rec.ir_free, &j)) == 0 &&
j == 1 &&
rec.ir_freecount > 0) {
/*
* The last chunk allocated in the group still has
* a free inode.
*/
}
/*
* None left in the last group, search the whole a.g.
*/
else {
if (error)
goto error0;
if ((error = xfs_inobt_lookup_ge(cur, 0, 0, 0, &i)))
goto error0;
ASSERT(i == 1);
for (;;) {
if ((error = xfs_inobt_get_rec(cur,
&rec.ir_startino,
&rec.ir_freecount, &rec.ir_free,
&i)))
goto error0;
XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
if (rec.ir_freecount > 0)
break;
if ((error = xfs_inobt_increment(cur, 0, &i)))
goto error0;
XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
}
}
}
offset = XFS_IALLOC_FIND_FREE(&rec.ir_free);
ASSERT(offset >= 0);
ASSERT(offset < XFS_INODES_PER_CHUNK);
ASSERT((XFS_AGINO_TO_OFFSET(mp, rec.ir_startino) %
XFS_INODES_PER_CHUNK) == 0);
ino = XFS_AGINO_TO_INO(mp, agno, rec.ir_startino + offset);
XFS_INOBT_CLR_FREE(&rec, offset);
rec.ir_freecount--;
if ((error = xfs_inobt_update(cur, rec.ir_startino, rec.ir_freecount,
rec.ir_free)))
goto error0;
be32_add_cpu(&agi->agi_freecount, -1);
xfs_ialloc_log_agi(tp, agbp, XFS_AGI_FREECOUNT);
down_read(&mp->m_peraglock);
mp->m_perag[tagno].pagi_freecount--;
up_read(&mp->m_peraglock);
#ifdef DEBUG
if (cur->bc_nlevels == 1) {
int freecount = 0;
if ((error = xfs_inobt_lookup_ge(cur, 0, 0, 0, &i)))
goto error0;
do {
if ((error = xfs_inobt_get_rec(cur, &rec.ir_startino,
&rec.ir_freecount, &rec.ir_free, &i)))
goto error0;
XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
freecount += rec.ir_freecount;
if ((error = xfs_inobt_increment(cur, 0, &i)))
goto error0;
} while (i == 1);
ASSERT(freecount == be32_to_cpu(agi->agi_freecount) ||
XFS_FORCED_SHUTDOWN(mp));
}
#endif
xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
xfs_trans_mod_sb(tp, XFS_TRANS_SB_IFREE, -1);
*inop = ino;
return 0;
error1:
xfs_btree_del_cursor(tcur, XFS_BTREE_ERROR);
error0:
xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
return error;
}
/*
* Read in the ondisk dquot using dqtobp() then copy it to an incore version,
* and release the buffer immediately.
*
* If XFS_QMOPT_DQALLOC is set, allocate a dquot on disk if it needed.
*/
int
xfs_qm_dqread(
struct xfs_mount *mp,
xfs_dqid_t id,
uint type,
uint flags,
struct xfs_dquot **O_dqpp)
{
struct xfs_dquot *dqp;
struct xfs_disk_dquot *ddqp;
struct xfs_buf *bp;
struct xfs_trans *tp = NULL;
int error;
int cancelflags = 0;
dqp = kmem_zone_zalloc(xfs_qm_dqzone, KM_SLEEP);
dqp->dq_flags = type;
dqp->q_core.d_id = cpu_to_be32(id);
dqp->q_mount = mp;
INIT_LIST_HEAD(&dqp->q_lru);
mutex_init(&dqp->q_qlock);
init_waitqueue_head(&dqp->q_pinwait);
/*
* Because we want to use a counting completion, complete
* the flush completion once to allow a single access to
* the flush completion without blocking.
*/
init_completion(&dqp->q_flush);
complete(&dqp->q_flush);
/*
* Make sure group quotas have a different lock class than user
* quotas.
*/
switch (type) {
case XFS_DQ_USER:
/* uses the default lock class */
break;
case XFS_DQ_GROUP:
lockdep_set_class(&dqp->q_qlock, &xfs_dquot_group_class);
break;
case XFS_DQ_PROJ:
lockdep_set_class(&dqp->q_qlock, &xfs_dquot_project_class);
break;
default:
ASSERT(0);
break;
}
XFS_STATS_INC(xs_qm_dquot);
trace_xfs_dqread(dqp);
if (flags & XFS_QMOPT_DQALLOC) {
tp = xfs_trans_alloc(mp, XFS_TRANS_QM_DQALLOC);
error = xfs_trans_reserve(tp, &M_RES(mp)->tr_qm_dqalloc,
XFS_QM_DQALLOC_SPACE_RES(mp), 0);
if (error)
goto error1;
cancelflags = XFS_TRANS_RELEASE_LOG_RES;
}
/*
* get a pointer to the on-disk dquot and the buffer containing it
* dqp already knows its own type (GROUP/USER).
*/
error = xfs_qm_dqtobp(&tp, dqp, &ddqp, &bp, flags);
if (error) {
/*
* This can happen if quotas got turned off (ESRCH),
* or if the dquot didn't exist on disk and we ask to
* allocate (ENOENT).
*/
trace_xfs_dqread_fail(dqp);
cancelflags |= XFS_TRANS_ABORT;
goto error1;
}
/* copy everything from disk dquot to the incore dquot */
memcpy(&dqp->q_core, ddqp, sizeof(xfs_disk_dquot_t));
xfs_qm_dquot_logitem_init(dqp);
/*
* Reservation counters are defined as reservation plus current usage
* to avoid having to add every time.
*/
dqp->q_res_bcount = be64_to_cpu(ddqp->d_bcount);
dqp->q_res_icount = be64_to_cpu(ddqp->d_icount);
dqp->q_res_rtbcount = be64_to_cpu(ddqp->d_rtbcount);
/* initialize the dquot speculative prealloc thresholds */
xfs_dquot_set_prealloc_limits(dqp);
/* Mark the buf so that this will stay incore a little longer */
xfs_buf_set_ref(bp, XFS_DQUOT_REF);
/*
* We got the buffer with a xfs_trans_read_buf() (in dqtobp())
* So we need to release with xfs_trans_brelse().
* The strategy here is identical to that of inodes; we lock
* the dquot in xfs_qm_dqget() before making it accessible to
* others. This is because dquots, like inodes, need a good level of
* concurrency, and we don't want to take locks on the entire buffers
* for dquot accesses.
* Note also that the dquot buffer may even be dirty at this point, if
* this particular dquot was repaired. We still aren't afraid to
* brelse it because we have the changes incore.
*/
ASSERT(xfs_buf_islocked(bp));
xfs_trans_brelse(tp, bp);
if (tp) {
error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
if (error)
goto error0;
}
*O_dqpp = dqp;
return error;
error1:
if (tp)
xfs_trans_cancel(tp, cancelflags);
error0:
xfs_qm_dqdestroy(dqp);
*O_dqpp = NULL;
return error;
}
/*
* Allocate an inode on disk.
* Mode is used to tell whether the new inode will need space, and whether
* it is a directory.
*
* The arguments IO_agbp and alloc_done are defined to work within
* the constraint of one allocation per transaction.
* xfs_dialloc() is designed to be called twice if it has to do an
* allocation to make more free inodes. On the first call,
* IO_agbp should be set to NULL. If an inode is available,
* i.e., xfs_dialloc() did not need to do an allocation, an inode
* number is returned. In this case, IO_agbp would be set to the
* current ag_buf and alloc_done set to false.
* If an allocation needed to be done, xfs_dialloc would return
* the current ag_buf in IO_agbp and set alloc_done to true.
* The caller should then commit the current transaction, allocate a new
* transaction, and call xfs_dialloc() again, passing in the previous
* value of IO_agbp. IO_agbp should be held across the transactions.
* Since the agbp is locked across the two calls, the second call is
* guaranteed to have a free inode available.
*
* Once we successfully pick an inode its number is returned and the
* on-disk data structures are updated. The inode itself is not read
* in, since doing so would break ordering constraints with xfs_reclaim.
*/
int
xfs_dialloc(
xfs_trans_t *tp, /* transaction pointer */
xfs_ino_t parent, /* parent inode (directory) */
umode_t mode, /* mode bits for new inode */
int okalloc, /* ok to allocate more space */
xfs_buf_t **IO_agbp, /* in/out ag header's buffer */
boolean_t *alloc_done, /* true if we needed to replenish
inode freelist */
xfs_ino_t *inop) /* inode number allocated */
{
xfs_agnumber_t agcount; /* number of allocation groups */
xfs_buf_t *agbp; /* allocation group header's buffer */
xfs_agnumber_t agno; /* allocation group number */
xfs_agi_t *agi; /* allocation group header structure */
xfs_btree_cur_t *cur; /* inode allocation btree cursor */
int error; /* error return value */
int i; /* result code */
int ialloced; /* inode allocation status */
int noroom = 0; /* no space for inode blk allocation */
xfs_ino_t ino; /* fs-relative inode to be returned */
/* REFERENCED */
int j; /* result code */
xfs_mount_t *mp; /* file system mount structure */
int offset; /* index of inode in chunk */
xfs_agino_t pagino; /* parent's AG relative inode # */
xfs_agnumber_t pagno; /* parent's AG number */
xfs_inobt_rec_incore_t rec; /* inode allocation record */
xfs_agnumber_t tagno; /* testing allocation group number */
xfs_btree_cur_t *tcur; /* temp cursor */
xfs_inobt_rec_incore_t trec; /* temp inode allocation record */
struct xfs_perag *pag;
if (*IO_agbp == NULL) {
/*
* We do not have an agbp, so select an initial allocation
* group for inode allocation.
*/
agbp = xfs_ialloc_ag_select(tp, parent, mode, okalloc);
/*
* Couldn't find an allocation group satisfying the
* criteria, give up.
*/
if (!agbp) {
*inop = NULLFSINO;
return 0;
}
agi = XFS_BUF_TO_AGI(agbp);
ASSERT(agi->agi_magicnum == cpu_to_be32(XFS_AGI_MAGIC));
} else {
/*
* Continue where we left off before. In this case, we
* know that the allocation group has free inodes.
*/
agbp = *IO_agbp;
agi = XFS_BUF_TO_AGI(agbp);
ASSERT(agi->agi_magicnum == cpu_to_be32(XFS_AGI_MAGIC));
ASSERT(be32_to_cpu(agi->agi_freecount) > 0);
}
mp = tp->t_mountp;
agcount = mp->m_sb.sb_agcount;
agno = be32_to_cpu(agi->agi_seqno);
tagno = agno;
pagno = XFS_INO_TO_AGNO(mp, parent);
pagino = XFS_INO_TO_AGINO(mp, parent);
/*
* If we have already hit the ceiling of inode blocks then clear
* okalloc so we scan all available agi structures for a free
* inode.
*/
if (mp->m_maxicount &&
mp->m_sb.sb_icount + XFS_IALLOC_INODES(mp) > mp->m_maxicount) {
noroom = 1;
okalloc = 0;
}
/*
* Loop until we find an allocation group that either has free inodes
* or in which we can allocate some inodes. Iterate through the
* allocation groups upward, wrapping at the end.
*/
*alloc_done = B_FALSE;
while (!agi->agi_freecount) {
/*
* Don't do anything if we're not supposed to allocate
* any blocks, just go on to the next ag.
*/
if (okalloc) {
/*
* Try to allocate some new inodes in the allocation
* group.
*/
if ((error = xfs_ialloc_ag_alloc(tp, agbp, &ialloced))) {
xfs_trans_brelse(tp, agbp);
if (error == ENOSPC) {
*inop = NULLFSINO;
return 0;
} else
return error;
}
if (ialloced) {
/*
* We successfully allocated some inodes, return
* the current context to the caller so that it
* can commit the current transaction and call
* us again where we left off.
*/
ASSERT(be32_to_cpu(agi->agi_freecount) > 0);
*alloc_done = B_TRUE;
*IO_agbp = agbp;
*inop = NULLFSINO;
return 0;
}
}
/*
* If it failed, give up on this ag.
*/
xfs_trans_brelse(tp, agbp);
/*
* Go on to the next ag: get its ag header.
*/
nextag:
if (++tagno == agcount)
tagno = 0;
if (tagno == agno) {
*inop = NULLFSINO;
return noroom ? ENOSPC : 0;
}
pag = xfs_perag_get(mp, tagno);
if (pag->pagi_inodeok == 0) {
xfs_perag_put(pag);
goto nextag;
}
error = xfs_ialloc_read_agi(mp, tp, tagno, &agbp);
xfs_perag_put(pag);
if (error)
goto nextag;
agi = XFS_BUF_TO_AGI(agbp);
ASSERT(agi->agi_magicnum == cpu_to_be32(XFS_AGI_MAGIC));
}
/*
* Here with an allocation group that has a free inode.
* Reset agno since we may have chosen a new ag in the
* loop above.
*/
agno = tagno;
*IO_agbp = NULL;
pag = xfs_perag_get(mp, agno);
restart_pagno:
cur = xfs_inobt_init_cursor(mp, tp, agbp, be32_to_cpu(agi->agi_seqno));
/*
* If pagino is 0 (this is the root inode allocation) use newino.
* This must work because we've just allocated some.
*/
if (!pagino)
pagino = be32_to_cpu(agi->agi_newino);
error = xfs_check_agi_freecount(cur, agi);
if (error)
goto error0;
/*
* If in the same AG as the parent, try to get near the parent.
*/
if (pagno == agno) {
int doneleft; /* done, to the left */
int doneright; /* done, to the right */
int searchdistance = 10;
error = xfs_inobt_lookup(cur, pagino, XFS_LOOKUP_LE, &i);
if (error)
goto error0;
XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
error = xfs_inobt_get_rec(cur, &rec, &j);
if (error)
goto error0;
XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
if (rec.ir_freecount > 0) {
/*
* Found a free inode in the same chunk
* as the parent, done.
*/
goto alloc_inode;
}
/*
* In the same AG as parent, but parent's chunk is full.
*/
/* duplicate the cursor, search left & right simultaneously */
error = xfs_btree_dup_cursor(cur, &tcur);
if (error)
goto error0;
/*
* Skip to last blocks looked up if same parent inode.
*/
if (pagino != NULLAGINO &&
pag->pagl_pagino == pagino &&
pag->pagl_leftrec != NULLAGINO &&
pag->pagl_rightrec != NULLAGINO) {
error = xfs_ialloc_get_rec(tcur, pag->pagl_leftrec,
&trec, &doneleft, 1);
if (error)
goto error1;
error = xfs_ialloc_get_rec(cur, pag->pagl_rightrec,
&rec, &doneright, 0);
if (error)
goto error1;
} else {
/* search left with tcur, back up 1 record */
error = xfs_ialloc_next_rec(tcur, &trec, &doneleft, 1);
if (error)
goto error1;
/* search right with cur, go forward 1 record. */
error = xfs_ialloc_next_rec(cur, &rec, &doneright, 0);
if (error)
goto error1;
}
/*
* Loop until we find an inode chunk with a free inode.
*/
while (!doneleft || !doneright) {
int useleft; /* using left inode chunk this time */
if (!--searchdistance) {
/*
* Not in range - save last search
* location and allocate a new inode
*/
xfs_btree_del_cursor(tcur, XFS_BTREE_NOERROR);
pag->pagl_leftrec = trec.ir_startino;
pag->pagl_rightrec = rec.ir_startino;
pag->pagl_pagino = pagino;
goto newino;
}
/* figure out the closer block if both are valid. */
if (!doneleft && !doneright) {
useleft = pagino -
(trec.ir_startino + XFS_INODES_PER_CHUNK - 1) <
rec.ir_startino - pagino;
} else {
useleft = !doneleft;
}
/* free inodes to the left? */
if (useleft && trec.ir_freecount) {
rec = trec;
xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
cur = tcur;
pag->pagl_leftrec = trec.ir_startino;
pag->pagl_rightrec = rec.ir_startino;
pag->pagl_pagino = pagino;
goto alloc_inode;
}
/* free inodes to the right? */
if (!useleft && rec.ir_freecount) {
xfs_btree_del_cursor(tcur, XFS_BTREE_NOERROR);
pag->pagl_leftrec = trec.ir_startino;
pag->pagl_rightrec = rec.ir_startino;
pag->pagl_pagino = pagino;
goto alloc_inode;
}
/* get next record to check */
if (useleft) {
error = xfs_ialloc_next_rec(tcur, &trec,
&doneleft, 1);
} else {
error = xfs_ialloc_next_rec(cur, &rec,
&doneright, 0);
}
if (error)
goto error1;
}
/*
* We've reached the end of the btree. because
* we are only searching a small chunk of the
* btree each search, there is obviously free
* inodes closer to the parent inode than we
* are now. restart the search again.
*/
pag->pagl_pagino = NULLAGINO;
pag->pagl_leftrec = NULLAGINO;
pag->pagl_rightrec = NULLAGINO;
xfs_btree_del_cursor(tcur, XFS_BTREE_NOERROR);
xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
goto restart_pagno;
}
/*
* In a different AG from the parent.
* See if the most recently allocated block has any free.
*/
newino:
if (agi->agi_newino != cpu_to_be32(NULLAGINO)) {
error = xfs_inobt_lookup(cur, be32_to_cpu(agi->agi_newino),
XFS_LOOKUP_EQ, &i);
if (error)
goto error0;
if (i == 1) {
error = xfs_inobt_get_rec(cur, &rec, &j);
if (error)
goto error0;
if (j == 1 && rec.ir_freecount > 0) {
/*
* The last chunk allocated in the group
* still has a free inode.
*/
goto alloc_inode;
}
}
}
/*
* None left in the last group, search the whole AG
*/
error = xfs_inobt_lookup(cur, 0, XFS_LOOKUP_GE, &i);
if (error)
goto error0;
XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
for (;;) {
error = xfs_inobt_get_rec(cur, &rec, &i);
if (error)
goto error0;
XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
if (rec.ir_freecount > 0)
break;
error = xfs_btree_increment(cur, 0, &i);
if (error)
goto error0;
XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
}
alloc_inode:
offset = xfs_ialloc_find_free(&rec.ir_free);
ASSERT(offset >= 0);
ASSERT(offset < XFS_INODES_PER_CHUNK);
ASSERT((XFS_AGINO_TO_OFFSET(mp, rec.ir_startino) %
XFS_INODES_PER_CHUNK) == 0);
ino = XFS_AGINO_TO_INO(mp, agno, rec.ir_startino + offset);
rec.ir_free &= ~XFS_INOBT_MASK(offset);
rec.ir_freecount--;
error = xfs_inobt_update(cur, &rec);
if (error)
goto error0;
be32_add_cpu(&agi->agi_freecount, -1);
xfs_ialloc_log_agi(tp, agbp, XFS_AGI_FREECOUNT);
pag->pagi_freecount--;
error = xfs_check_agi_freecount(cur, agi);
if (error)
goto error0;
xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
xfs_trans_mod_sb(tp, XFS_TRANS_SB_IFREE, -1);
xfs_perag_put(pag);
*inop = ino;
return 0;
error1:
xfs_btree_del_cursor(tcur, XFS_BTREE_ERROR);
error0:
xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
xfs_perag_put(pag);
return error;
}
int
xfs_attr_set(
struct xfs_inode *dp,
const unsigned char *name,
unsigned char *value,
int valuelen,
int flags)
{
struct xfs_mount *mp = dp->i_mount;
struct xfs_buf *leaf_bp = NULL;
struct xfs_da_args args;
struct xfs_trans_res tres;
int rsvd = (flags & ATTR_ROOT) != 0;
int error, err2, local;
XFS_STATS_INC(mp, xs_attr_set);
if (XFS_FORCED_SHUTDOWN(dp->i_mount))
return -EIO;
error = xfs_attr_args_init(&args, dp, name, flags);
if (error)
return error;
args.value = value;
args.valuelen = valuelen;
args.op_flags = XFS_DA_OP_ADDNAME | XFS_DA_OP_OKNOENT;
args.total = xfs_attr_calc_size(&args, &local);
error = xfs_qm_dqattach(dp);
if (error)
return error;
/*
* If the inode doesn't have an attribute fork, add one.
* (inode must not be locked when we call this routine)
*/
if (XFS_IFORK_Q(dp) == 0) {
int sf_size = sizeof(xfs_attr_sf_hdr_t) +
XFS_ATTR_SF_ENTSIZE_BYNAME(args.namelen, valuelen);
error = xfs_bmap_add_attrfork(dp, sf_size, rsvd);
if (error)
return error;
}
tres.tr_logres = M_RES(mp)->tr_attrsetm.tr_logres +
M_RES(mp)->tr_attrsetrt.tr_logres * args.total;
tres.tr_logcount = XFS_ATTRSET_LOG_COUNT;
tres.tr_logflags = XFS_TRANS_PERM_LOG_RES;
/*
* Root fork attributes can use reserved data blocks for this
* operation if necessary
*/
error = xfs_trans_alloc(mp, &tres, args.total, 0,
rsvd ? XFS_TRANS_RESERVE : 0, &args.trans);
if (error)
return error;
xfs_ilock(dp, XFS_ILOCK_EXCL);
error = xfs_trans_reserve_quota_nblks(args.trans, dp, args.total, 0,
rsvd ? XFS_QMOPT_RES_REGBLKS | XFS_QMOPT_FORCE_RES :
XFS_QMOPT_RES_REGBLKS);
if (error) {
xfs_iunlock(dp, XFS_ILOCK_EXCL);
xfs_trans_cancel(args.trans);
return error;
}
xfs_trans_ijoin(args.trans, dp, 0);
/*
* If the attribute list is non-existent or a shortform list,
* upgrade it to a single-leaf-block attribute list.
*/
if (dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL ||
(dp->i_d.di_aformat == XFS_DINODE_FMT_EXTENTS &&
dp->i_d.di_anextents == 0)) {
/*
* Build initial attribute list (if required).
*/
if (dp->i_d.di_aformat == XFS_DINODE_FMT_EXTENTS)
xfs_attr_shortform_create(&args);
/*
* Try to add the attr to the attribute list in
* the inode.
*/
error = xfs_attr_shortform_addname(&args);
if (error != -ENOSPC) {
/*
* Commit the shortform mods, and we're done.
* NOTE: this is also the error path (EEXIST, etc).
*/
ASSERT(args.trans != NULL);
/*
* If this is a synchronous mount, make sure that
* the transaction goes to disk before returning
* to the user.
*/
if (mp->m_flags & XFS_MOUNT_WSYNC)
xfs_trans_set_sync(args.trans);
if (!error && (flags & ATTR_KERNOTIME) == 0) {
xfs_trans_ichgtime(args.trans, dp,
XFS_ICHGTIME_CHG);
}
err2 = xfs_trans_commit(args.trans);
xfs_iunlock(dp, XFS_ILOCK_EXCL);
return error ? error : err2;
}
/*
* It won't fit in the shortform, transform to a leaf block.
* GROT: another possible req'mt for a double-split btree op.
*/
error = xfs_attr_shortform_to_leaf(&args, &leaf_bp);
if (error)
goto out;
/*
* Prevent the leaf buffer from being unlocked so that a
* concurrent AIL push cannot grab the half-baked leaf
* buffer and run into problems with the write verifier.
*/
xfs_trans_bhold(args.trans, leaf_bp);
error = xfs_defer_finish(&args.trans);
if (error)
goto out;
/*
* Commit the leaf transformation. We'll need another (linked)
* transaction to add the new attribute to the leaf, which
* means that we have to hold & join the leaf buffer here too.
*/
error = xfs_trans_roll_inode(&args.trans, dp);
if (error)
goto out;
xfs_trans_bjoin(args.trans, leaf_bp);
leaf_bp = NULL;
}
if (xfs_bmap_one_block(dp, XFS_ATTR_FORK))
error = xfs_attr_leaf_addname(&args);
else
error = xfs_attr_node_addname(&args);
if (error)
goto out;
/*
* If this is a synchronous mount, make sure that the
* transaction goes to disk before returning to the user.
*/
if (mp->m_flags & XFS_MOUNT_WSYNC)
xfs_trans_set_sync(args.trans);
if ((flags & ATTR_KERNOTIME) == 0)
xfs_trans_ichgtime(args.trans, dp, XFS_ICHGTIME_CHG);
/*
* Commit the last in the sequence of transactions.
*/
xfs_trans_log_inode(args.trans, dp, XFS_ILOG_CORE);
error = xfs_trans_commit(args.trans);
xfs_iunlock(dp, XFS_ILOCK_EXCL);
return error;
out:
if (leaf_bp)
xfs_trans_brelse(args.trans, leaf_bp);
if (args.trans)
xfs_trans_cancel(args.trans);
xfs_iunlock(dp, XFS_ILOCK_EXCL);
return error;
}
/*
* Add a name to the leaf attribute list structure
*
* This leaf block cannot have a "remote" value, we only call this routine
* if bmap_one_block() says there is only one block (ie: no remote blks).
*/
STATIC int
xfs_attr_leaf_addname(
struct xfs_da_args *args)
{
struct xfs_inode *dp;
struct xfs_buf *bp;
int retval, error, forkoff;
trace_xfs_attr_leaf_addname(args);
/*
* Read the (only) block in the attribute list in.
*/
dp = args->dp;
args->blkno = 0;
error = xfs_attr3_leaf_read(args->trans, args->dp, args->blkno, -1, &bp);
if (error)
return error;
/*
* Look up the given attribute in the leaf block. Figure out if
* the given flags produce an error or call for an atomic rename.
*/
retval = xfs_attr3_leaf_lookup_int(bp, args);
if ((args->flags & ATTR_REPLACE) && (retval == -ENOATTR)) {
xfs_trans_brelse(args->trans, bp);
return retval;
} else if (retval == -EEXIST) {
if (args->flags & ATTR_CREATE) { /* pure create op */
xfs_trans_brelse(args->trans, bp);
return retval;
}
trace_xfs_attr_leaf_replace(args);
/* save the attribute state for later removal*/
args->op_flags |= XFS_DA_OP_RENAME; /* an atomic rename */
args->blkno2 = args->blkno; /* set 2nd entry info*/
args->index2 = args->index;
args->rmtblkno2 = args->rmtblkno;
args->rmtblkcnt2 = args->rmtblkcnt;
args->rmtvaluelen2 = args->rmtvaluelen;
/*
* clear the remote attr state now that it is saved so that the
* values reflect the state of the attribute we are about to
* add, not the attribute we just found and will remove later.
*/
args->rmtblkno = 0;
args->rmtblkcnt = 0;
args->rmtvaluelen = 0;
}
/*
* Add the attribute to the leaf block, transitioning to a Btree
* if required.
*/
retval = xfs_attr3_leaf_add(bp, args);
if (retval == -ENOSPC) {
/*
* Promote the attribute list to the Btree format, then
* Commit that transaction so that the node_addname() call
* can manage its own transactions.
*/
error = xfs_attr3_leaf_to_node(args);
if (error)
return error;
error = xfs_defer_finish(&args->trans);
if (error)
return error;
/*
* Commit the current trans (including the inode) and start
* a new one.
*/
error = xfs_trans_roll_inode(&args->trans, dp);
if (error)
return error;
/*
* Fob the whole rest of the problem off on the Btree code.
*/
error = xfs_attr_node_addname(args);
return error;
}
/*
* Commit the transaction that added the attr name so that
* later routines can manage their own transactions.
*/
error = xfs_trans_roll_inode(&args->trans, dp);
if (error)
return error;
/*
* If there was an out-of-line value, allocate the blocks we
* identified for its storage and copy the value. This is done
* after we create the attribute so that we don't overflow the
* maximum size of a transaction and/or hit a deadlock.
*/
if (args->rmtblkno > 0) {
error = xfs_attr_rmtval_set(args);
if (error)
return error;
}
/*
* If this is an atomic rename operation, we must "flip" the
* incomplete flags on the "new" and "old" attribute/value pairs
* so that one disappears and one appears atomically. Then we
* must remove the "old" attribute/value pair.
*/
if (args->op_flags & XFS_DA_OP_RENAME) {
/*
* In a separate transaction, set the incomplete flag on the
* "old" attr and clear the incomplete flag on the "new" attr.
*/
error = xfs_attr3_leaf_flipflags(args);
if (error)
return error;
/*
* Dismantle the "old" attribute/value pair by removing
* a "remote" value (if it exists).
*/
args->index = args->index2;
args->blkno = args->blkno2;
args->rmtblkno = args->rmtblkno2;
args->rmtblkcnt = args->rmtblkcnt2;
args->rmtvaluelen = args->rmtvaluelen2;
if (args->rmtblkno) {
error = xfs_attr_rmtval_remove(args);
if (error)
return error;
}
/*
* Read in the block containing the "old" attr, then
* remove the "old" attr from that block (neat, huh!)
*/
error = xfs_attr3_leaf_read(args->trans, args->dp, args->blkno,
-1, &bp);
if (error)
return error;
xfs_attr3_leaf_remove(bp, args);
/*
* If the result is small enough, shrink it all into the inode.
*/
if ((forkoff = xfs_attr_shortform_allfit(bp, dp))) {
error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
/* bp is gone due to xfs_da_shrink_inode */
if (error)
return error;
error = xfs_defer_finish(&args->trans);
if (error)
return error;
}
/*
* Commit the remove and start the next trans in series.
*/
error = xfs_trans_roll_inode(&args->trans, dp);
} else if (args->rmtblkno > 0) {
/*
* Added a "remote" value, just clear the incomplete flag.
*/
error = xfs_attr3_leaf_clearflag(args);
}
return error;
}
/*
* Remove a name from a B-tree attribute list.
*
* This will involve walking down the Btree, and may involve joining
* leaf nodes and even joining intermediate nodes up to and including
* the root node (a special case of an intermediate node).
*/
STATIC int
xfs_attr_node_removename(
struct xfs_da_args *args)
{
struct xfs_da_state *state;
struct xfs_da_state_blk *blk;
struct xfs_inode *dp;
struct xfs_buf *bp;
int retval, error, forkoff;
trace_xfs_attr_node_removename(args);
/*
* Tie a string around our finger to remind us where we are.
*/
dp = args->dp;
state = xfs_da_state_alloc();
state->args = args;
state->mp = dp->i_mount;
/*
* Search to see if name exists, and get back a pointer to it.
*/
error = xfs_da3_node_lookup_int(state, &retval);
if (error || (retval != -EEXIST)) {
if (error == 0)
error = retval;
goto out;
}
/*
* If there is an out-of-line value, de-allocate the blocks.
* This is done before we remove the attribute so that we don't
* overflow the maximum size of a transaction and/or hit a deadlock.
*/
blk = &state->path.blk[ state->path.active-1 ];
ASSERT(blk->bp != NULL);
ASSERT(blk->magic == XFS_ATTR_LEAF_MAGIC);
if (args->rmtblkno > 0) {
/*
* Fill in disk block numbers in the state structure
* so that we can get the buffers back after we commit
* several transactions in the following calls.
*/
error = xfs_attr_fillstate(state);
if (error)
goto out;
/*
* Mark the attribute as INCOMPLETE, then bunmapi() the
* remote value.
*/
error = xfs_attr3_leaf_setflag(args);
if (error)
goto out;
error = xfs_attr_rmtval_remove(args);
if (error)
goto out;
/*
* Refill the state structure with buffers, the prior calls
* released our buffers.
*/
error = xfs_attr_refillstate(state);
if (error)
goto out;
}
/*
* Remove the name and update the hashvals in the tree.
*/
blk = &state->path.blk[ state->path.active-1 ];
ASSERT(blk->magic == XFS_ATTR_LEAF_MAGIC);
retval = xfs_attr3_leaf_remove(blk->bp, args);
xfs_da3_fixhashpath(state, &state->path);
/*
* Check to see if the tree needs to be collapsed.
*/
if (retval && (state->path.active > 1)) {
error = xfs_da3_join(state);
if (error)
goto out;
error = xfs_defer_finish(&args->trans);
if (error)
goto out;
/*
* Commit the Btree join operation and start a new trans.
*/
error = xfs_trans_roll_inode(&args->trans, dp);
if (error)
goto out;
}
/*
* If the result is small enough, push it all into the inode.
*/
if (xfs_bmap_one_block(dp, XFS_ATTR_FORK)) {
/*
* Have to get rid of the copy of this dabuf in the state.
*/
ASSERT(state->path.active == 1);
ASSERT(state->path.blk[0].bp);
state->path.blk[0].bp = NULL;
error = xfs_attr3_leaf_read(args->trans, args->dp, 0, -1, &bp);
if (error)
goto out;
if ((forkoff = xfs_attr_shortform_allfit(bp, dp))) {
error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
/* bp is gone due to xfs_da_shrink_inode */
if (error)
goto out;
error = xfs_defer_finish(&args->trans);
if (error)
goto out;
} else
xfs_trans_brelse(args->trans, bp);
}
error = 0;
out:
xfs_da_state_free(state);
return error;
}
STATIC int
xfs_attr_node_list(xfs_attr_list_context_t *context)
{
attrlist_cursor_kern_t *cursor;
xfs_attr_leafblock_t *leaf;
xfs_da_intnode_t *node;
struct xfs_attr3_icleaf_hdr leafhdr;
struct xfs_da3_icnode_hdr nodehdr;
struct xfs_da_node_entry *btree;
int error, i;
struct xfs_buf *bp;
struct xfs_inode *dp = context->dp;
struct xfs_mount *mp = dp->i_mount;
trace_xfs_attr_node_list(context);
cursor = context->cursor;
cursor->initted = 1;
/*
* Do all sorts of validation on the passed-in cursor structure.
* If anything is amiss, ignore the cursor and look up the hashval
* starting from the btree root.
*/
bp = NULL;
if (cursor->blkno > 0) {
error = xfs_da3_node_read(NULL, dp, cursor->blkno, -1,
&bp, XFS_ATTR_FORK);
if ((error != 0) && (error != -EFSCORRUPTED))
return error;
if (bp) {
struct xfs_attr_leaf_entry *entries;
node = bp->b_addr;
switch (be16_to_cpu(node->hdr.info.magic)) {
case XFS_DA_NODE_MAGIC:
case XFS_DA3_NODE_MAGIC:
trace_xfs_attr_list_wrong_blk(context);
xfs_trans_brelse(NULL, bp);
bp = NULL;
break;
case XFS_ATTR_LEAF_MAGIC:
case XFS_ATTR3_LEAF_MAGIC:
leaf = bp->b_addr;
xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo,
&leafhdr, leaf);
entries = xfs_attr3_leaf_entryp(leaf);
if (cursor->hashval > be32_to_cpu(
entries[leafhdr.count - 1].hashval)) {
trace_xfs_attr_list_wrong_blk(context);
xfs_trans_brelse(NULL, bp);
bp = NULL;
} else if (cursor->hashval <= be32_to_cpu(
entries[0].hashval)) {
trace_xfs_attr_list_wrong_blk(context);
xfs_trans_brelse(NULL, bp);
bp = NULL;
}
break;
default:
trace_xfs_attr_list_wrong_blk(context);
xfs_trans_brelse(NULL, bp);
bp = NULL;
}
}
}
/*
* We did not find what we expected given the cursor's contents,
* so we start from the top and work down based on the hash value.
* Note that start of node block is same as start of leaf block.
*/
if (bp == NULL) {
cursor->blkno = 0;
for (;;) {
__uint16_t magic;
error = xfs_da3_node_read(NULL, dp,
cursor->blkno, -1, &bp,
XFS_ATTR_FORK);
if (error)
return error;
node = bp->b_addr;
magic = be16_to_cpu(node->hdr.info.magic);
if (magic == XFS_ATTR_LEAF_MAGIC ||
magic == XFS_ATTR3_LEAF_MAGIC)
break;
if (magic != XFS_DA_NODE_MAGIC &&
magic != XFS_DA3_NODE_MAGIC) {
XFS_CORRUPTION_ERROR("xfs_attr_node_list(3)",
XFS_ERRLEVEL_LOW,
context->dp->i_mount,
node);
xfs_trans_brelse(NULL, bp);
return -EFSCORRUPTED;
}
dp->d_ops->node_hdr_from_disk(&nodehdr, node);
btree = dp->d_ops->node_tree_p(node);
for (i = 0; i < nodehdr.count; btree++, i++) {
if (cursor->hashval
<= be32_to_cpu(btree->hashval)) {
cursor->blkno = be32_to_cpu(btree->before);
trace_xfs_attr_list_node_descend(context,
btree);
break;
}
}
if (i == nodehdr.count) {
xfs_trans_brelse(NULL, bp);
return 0;
}
xfs_trans_brelse(NULL, bp);
}
}
ASSERT(bp != NULL);
/*
* Roll upward through the blocks, processing each leaf block in
* order. As long as there is space in the result buffer, keep
* adding the information.
*/
for (;;) {
leaf = bp->b_addr;
error = xfs_attr3_leaf_list_int(bp, context);
if (error) {
xfs_trans_brelse(NULL, bp);
return error;
}
xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &leafhdr, leaf);
if (context->seen_enough || leafhdr.forw == 0)
break;
cursor->blkno = leafhdr.forw;
xfs_trans_brelse(NULL, bp);
error = xfs_attr3_leaf_read(NULL, dp, cursor->blkno, -1, &bp);
if (error)
return error;
}
xfs_trans_brelse(NULL, bp);
return 0;
}
/*
* Internal block lookup routine.
*/
static int /* error */
xfs_dir2_block_lookup_int(
xfs_da_args_t *args, /* dir lookup arguments */
struct xfs_buf **bpp, /* returned block buffer */
int *entno) /* returned entry number */
{
xfs_dir2_dataptr_t addr; /* data entry address */
xfs_dir2_data_hdr_t *hdr; /* block header */
xfs_dir2_leaf_entry_t *blp; /* block leaf entries */
struct xfs_buf *bp; /* block buffer */
xfs_dir2_block_tail_t *btp; /* block tail */
xfs_dir2_data_entry_t *dep; /* block data entry */
xfs_inode_t *dp; /* incore inode */
int error; /* error return value */
xfs_dahash_t hash; /* found hash value */
int high; /* binary search high index */
int low; /* binary search low index */
int mid; /* binary search current idx */
xfs_mount_t *mp; /* filesystem mount point */
xfs_trans_t *tp; /* transaction pointer */
enum xfs_dacmp cmp; /* comparison result */
dp = args->dp;
tp = args->trans;
mp = dp->i_mount;
error = xfs_dir3_block_read(tp, dp, &bp);
if (error)
return error;
hdr = bp->b_addr;
xfs_dir3_data_check(dp, bp);
btp = xfs_dir2_block_tail_p(args->geo, hdr);
blp = xfs_dir2_block_leaf_p(btp);
/*
* Loop doing a binary search for our hash value.
* Find our entry, ENOENT if it's not there.
*/
for (low = 0, high = be32_to_cpu(btp->count) - 1; ; ) {
ASSERT(low <= high);
mid = (low + high) >> 1;
if ((hash = be32_to_cpu(blp[mid].hashval)) == args->hashval)
break;
if (hash < args->hashval)
low = mid + 1;
else
high = mid - 1;
if (low > high) {
ASSERT(args->op_flags & XFS_DA_OP_OKNOENT);
xfs_trans_brelse(tp, bp);
return -ENOENT;
}
}
/*
* Back up to the first one with the right hash value.
*/
while (mid > 0 && be32_to_cpu(blp[mid - 1].hashval) == args->hashval) {
mid--;
}
/*
* Now loop forward through all the entries with the
* right hash value looking for our name.
*/
do {
if ((addr = be32_to_cpu(blp[mid].address)) == XFS_DIR2_NULL_DATAPTR)
continue;
/*
* Get pointer to the entry from the leaf.
*/
dep = (xfs_dir2_data_entry_t *)
((char *)hdr + xfs_dir2_dataptr_to_off(args->geo, addr));
/*
* Compare name and if it's an exact match, return the index
* and buffer. If it's the first case-insensitive match, store
* the index and buffer and continue looking for an exact match.
*/
cmp = mp->m_dirnameops->compname(args, dep->name, dep->namelen);
if (cmp != XFS_CMP_DIFFERENT && cmp != args->cmpresult) {
args->cmpresult = cmp;
*bpp = bp;
*entno = mid;
if (cmp == XFS_CMP_EXACT)
return 0;
}
} while (++mid < be32_to_cpu(btp->count) &&
be32_to_cpu(blp[mid].hashval) == hash);
ASSERT(args->op_flags & XFS_DA_OP_OKNOENT);
/*
* Here, we can only be doing a lookup (not a rename or replace).
* If a case-insensitive match was found earlier, return success.
*/
if (args->cmpresult == XFS_CMP_CASE)
return 0;
/*
* No match, release the buffer and return ENOENT.
*/
xfs_trans_brelse(tp, bp);
return -ENOENT;
}
/* Execute a getfsmap query against the regular data device. */
STATIC int
__xfs_getfsmap_datadev(
struct xfs_trans *tp,
struct xfs_fsmap *keys,
struct xfs_getfsmap_info *info,
int (*query_fn)(struct xfs_trans *,
struct xfs_getfsmap_info *,
struct xfs_btree_cur **,
void *),
void *priv)
{
struct xfs_mount *mp = tp->t_mountp;
struct xfs_btree_cur *bt_cur = NULL;
xfs_fsblock_t start_fsb;
xfs_fsblock_t end_fsb;
xfs_agnumber_t start_ag;
xfs_agnumber_t end_ag;
xfs_daddr_t eofs;
int error = 0;
eofs = XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks);
if (keys[0].fmr_physical >= eofs)
return 0;
if (keys[1].fmr_physical >= eofs)
keys[1].fmr_physical = eofs - 1;
start_fsb = XFS_DADDR_TO_FSB(mp, keys[0].fmr_physical);
end_fsb = XFS_DADDR_TO_FSB(mp, keys[1].fmr_physical);
/*
* Convert the fsmap low/high keys to AG based keys. Initialize
* low to the fsmap low key and max out the high key to the end
* of the AG.
*/
info->low.rm_startblock = XFS_FSB_TO_AGBNO(mp, start_fsb);
info->low.rm_offset = XFS_BB_TO_FSBT(mp, keys[0].fmr_offset);
error = xfs_fsmap_owner_to_rmap(&info->low, &keys[0]);
if (error)
return error;
info->low.rm_blockcount = 0;
xfs_getfsmap_set_irec_flags(&info->low, &keys[0]);
info->high.rm_startblock = -1U;
info->high.rm_owner = ULLONG_MAX;
info->high.rm_offset = ULLONG_MAX;
info->high.rm_blockcount = 0;
info->high.rm_flags = XFS_RMAP_KEY_FLAGS | XFS_RMAP_REC_FLAGS;
start_ag = XFS_FSB_TO_AGNO(mp, start_fsb);
end_ag = XFS_FSB_TO_AGNO(mp, end_fsb);
/* Query each AG */
for (info->agno = start_ag; info->agno <= end_ag; info->agno++) {
/*
* Set the AG high key from the fsmap high key if this
* is the last AG that we're querying.
*/
if (info->agno == end_ag) {
info->high.rm_startblock = XFS_FSB_TO_AGBNO(mp,
end_fsb);
info->high.rm_offset = XFS_BB_TO_FSBT(mp,
keys[1].fmr_offset);
error = xfs_fsmap_owner_to_rmap(&info->high, &keys[1]);
if (error)
goto err;
xfs_getfsmap_set_irec_flags(&info->high, &keys[1]);
}
if (bt_cur) {
xfs_btree_del_cursor(bt_cur, XFS_BTREE_NOERROR);
bt_cur = NULL;
xfs_trans_brelse(tp, info->agf_bp);
info->agf_bp = NULL;
}
error = xfs_alloc_read_agf(mp, tp, info->agno, 0,
&info->agf_bp);
if (error)
goto err;
trace_xfs_fsmap_low_key(mp, info->dev, info->agno, &info->low);
trace_xfs_fsmap_high_key(mp, info->dev, info->agno,
&info->high);
error = query_fn(tp, info, &bt_cur, priv);
if (error)
goto err;
/*
* Set the AG low key to the start of the AG prior to
* moving on to the next AG.
*/
if (info->agno == start_ag) {
info->low.rm_startblock = 0;
info->low.rm_owner = 0;
info->low.rm_offset = 0;
info->low.rm_flags = 0;
}
}
/* Report any gap at the end of the AG */
info->last = true;
error = query_fn(tp, info, &bt_cur, priv);
if (error)
goto err;
err:
if (bt_cur)
xfs_btree_del_cursor(bt_cur, error < 0 ? XFS_BTREE_ERROR :
XFS_BTREE_NOERROR);
if (info->agf_bp) {
xfs_trans_brelse(tp, info->agf_bp);
info->agf_bp = NULL;
}
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;
}
/*
* Searching forward from start to limit, find the first block whose
* allocated/free state is different from start's.
*/
int
xfs_rtfind_forw(
xfs_mount_t *mp, /* file system mount point */
xfs_trans_t *tp, /* transaction pointer */
xfs_rtblock_t start, /* starting block to look at */
xfs_rtblock_t limit, /* last block to look at */
xfs_rtblock_t *rtblock) /* out: start block found */
{
xfs_rtword_t *b; /* current word in buffer */
int bit; /* bit number in the word */
xfs_rtblock_t block; /* bitmap block number */
xfs_buf_t *bp; /* buf for the block */
xfs_rtword_t *bufp; /* starting word in buffer */
int error; /* error value */
xfs_rtblock_t i; /* current bit number rel. to start */
xfs_rtblock_t lastbit; /* last useful bit in the word */
xfs_rtblock_t len; /* length of inspected area */
xfs_rtword_t mask; /* mask of relevant bits for value */
xfs_rtword_t want; /* mask for "good" values */
xfs_rtword_t wdiff; /* difference from wanted value */
int word; /* word number in the buffer */
/*
* Compute and read in starting bitmap block for starting block.
*/
block = XFS_BITTOBLOCK(mp, start);
error = xfs_rtbuf_get(mp, tp, block, 0, &bp);
if (error) {
return error;
}
bufp = bp->b_addr;
/*
* Get the first word's index & point to it.
*/
word = XFS_BITTOWORD(mp, start);
b = &bufp[word];
bit = (int)(start & (XFS_NBWORD - 1));
len = limit - start + 1;
/*
* Compute match value, based on the bit at start: if 1 (free)
* then all-ones, else all-zeroes.
*/
want = (*b & ((xfs_rtword_t)1 << bit)) ? -1 : 0;
/*
* If the starting position is not word-aligned, deal with the
* partial word.
*/
if (bit) {
/*
* Calculate last (rightmost) bit number to look at,
* and mask for all the relevant bits in this word.
*/
lastbit = XFS_RTMIN(bit + len, XFS_NBWORD);
mask = (((xfs_rtword_t)1 << (lastbit - bit)) - 1) << bit;
/*
* Calculate the difference between the value there
* and what we're looking for.
*/
if ((wdiff = (*b ^ want) & mask)) {
/*
* Different. Mark where we are and return.
*/
xfs_trans_brelse(tp, bp);
i = XFS_RTLOBIT(wdiff) - bit;
*rtblock = start + i - 1;
return 0;
}
i = lastbit - bit;
/*
* Go on to next block if that's where the next word is
* and we need the next word.
*/
if (++word == XFS_BLOCKWSIZE(mp) && i < len) {
/*
* If done with this block, get the previous one.
*/
xfs_trans_brelse(tp, bp);
error = xfs_rtbuf_get(mp, tp, ++block, 0, &bp);
if (error) {
return error;
}
b = bufp = bp->b_addr;
word = 0;
} else {
/*
* Go on to the previous word in the buffer.
*/
b++;
}
} else {
/*
* Starting on a word boundary, no partial word.
*/
i = 0;
}
/*
* Loop over whole words in buffers. When we use up one buffer
* we move on to the next one.
*/
while (len - i >= XFS_NBWORD) {
/*
* Compute difference between actual and desired value.
*/
if ((wdiff = *b ^ want)) {
/*
* Different, mark where we are and return.
*/
xfs_trans_brelse(tp, bp);
i += XFS_RTLOBIT(wdiff);
*rtblock = start + i - 1;
return 0;
}
i += XFS_NBWORD;
/*
* Go on to next block if that's where the next word is
* and we need the next word.
*/
if (++word == XFS_BLOCKWSIZE(mp) && i < len) {
/*
* If done with this block, get the next one.
*/
xfs_trans_brelse(tp, bp);
error = xfs_rtbuf_get(mp, tp, ++block, 0, &bp);
if (error) {
return error;
}
b = bufp = bp->b_addr;
word = 0;
} else {
/*
* Go on to the next word in the buffer.
*/
b++;
}
}
/*
* If not ending on a word boundary, deal with the last
* (partial) word.
*/
if ((lastbit = len - i)) {
/*
* Calculate mask for all the relevant bits in this word.
*/
mask = ((xfs_rtword_t)1 << lastbit) - 1;
/*
* Compute difference between actual and desired value.
*/
if ((wdiff = (*b ^ want) & mask)) {
/*
* Different, mark where we are and return.
*/
xfs_trans_brelse(tp, bp);
i += XFS_RTLOBIT(wdiff);
*rtblock = start + i - 1;
return 0;
} else
i = len;
}
/*
* No match, return that we scanned the whole area.
*/
xfs_trans_brelse(tp, bp);
*rtblock = start + i - 1;
return 0;
}
/*
* Maps a dquot to the buffer containing its on-disk version.
* This returns a ptr to the buffer containing the on-disk dquot
* in the bpp param, and a ptr to the on-disk dquot within that buffer
*/
STATIC int
xfs_qm_dqtobp(
xfs_trans_t **tpp,
xfs_dquot_t *dqp,
xfs_disk_dquot_t **O_ddpp,
xfs_buf_t **O_bpp,
uint flags)
{
xfs_bmbt_irec_t map;
int nmaps, error;
xfs_buf_t *bp;
xfs_inode_t *quotip;
xfs_mount_t *mp;
xfs_disk_dquot_t *ddq;
xfs_dqid_t id;
boolean_t newdquot;
xfs_trans_t *tp = (tpp ? *tpp : NULL);
mp = dqp->q_mount;
id = be32_to_cpu(dqp->q_core.d_id);
nmaps = 1;
newdquot = B_FALSE;
/*
* If we don't know where the dquot lives, find out.
*/
if (dqp->q_blkno == (xfs_daddr_t) 0) {
/* We use the id as an index */
dqp->q_fileoffset = (xfs_fileoff_t)id / XFS_QM_DQPERBLK(mp);
nmaps = 1;
quotip = XFS_DQ_TO_QIP(dqp);
xfs_ilock(quotip, XFS_ILOCK_SHARED);
/*
* Return if this type of quotas is turned off while we didn't
* have an inode lock
*/
if (XFS_IS_THIS_QUOTA_OFF(dqp)) {
xfs_iunlock(quotip, XFS_ILOCK_SHARED);
return (ESRCH);
}
/*
* Find the block map; no allocations yet
*/
error = xfs_bmapi(NULL, quotip, dqp->q_fileoffset,
XFS_DQUOT_CLUSTER_SIZE_FSB,
XFS_BMAPI_METADATA,
NULL, 0, &map, &nmaps, NULL);
xfs_iunlock(quotip, XFS_ILOCK_SHARED);
if (error)
return (error);
ASSERT(nmaps == 1);
ASSERT(map.br_blockcount == 1);
/*
* offset of dquot in the (fixed sized) dquot chunk.
*/
dqp->q_bufoffset = (id % XFS_QM_DQPERBLK(mp)) *
sizeof(xfs_dqblk_t);
if (map.br_startblock == HOLESTARTBLOCK) {
/*
* We don't allocate unless we're asked to
*/
if (!(flags & XFS_QMOPT_DQALLOC))
return (ENOENT);
ASSERT(tp);
if ((error = xfs_qm_dqalloc(tpp, mp, dqp, quotip,
dqp->q_fileoffset, &bp)))
return (error);
tp = *tpp;
newdquot = B_TRUE;
} else {
/*
* store the blkno etc so that we don't have to do the
* mapping all the time
*/
dqp->q_blkno = XFS_FSB_TO_DADDR(mp, map.br_startblock);
}
}
ASSERT(dqp->q_blkno != DELAYSTARTBLOCK);
ASSERT(dqp->q_blkno != HOLESTARTBLOCK);
/*
* Read in the buffer, unless we've just done the allocation
* (in which case we already have the buf).
*/
if (! newdquot) {
xfs_dqtrace_entry(dqp, "DQTOBP READBUF");
if ((error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
dqp->q_blkno,
XFS_QI_DQCHUNKLEN(mp),
0, &bp))) {
return (error);
}
if (error || !bp)
return XFS_ERROR(error);
}
ASSERT(XFS_BUF_ISBUSY(bp));
ASSERT(XFS_BUF_VALUSEMA(bp) <= 0);
/*
* calculate the location of the dquot inside the buffer.
*/
ddq = (xfs_disk_dquot_t *)((char *)XFS_BUF_PTR(bp) + dqp->q_bufoffset);
/*
* A simple sanity check in case we got a corrupted dquot...
*/
if (xfs_qm_dqcheck(ddq, id, dqp->dq_flags & XFS_DQ_ALLTYPES,
flags & (XFS_QMOPT_DQREPAIR|XFS_QMOPT_DOWARN),
"dqtobp")) {
if (!(flags & XFS_QMOPT_DQREPAIR)) {
xfs_trans_brelse(tp, bp);
return XFS_ERROR(EIO);
}
XFS_BUF_BUSY(bp); /* We dirtied this */
}
*O_bpp = bp;
*O_ddpp = ddq;
return (0);
}
/*
* 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;
}
/*
* Readdir for block directories.
*/
int /* error */
xfs_dir2_block_getdents(
xfs_inode_t *dp, /* incore inode */
void *dirent,
xfs_off_t *offset,
filldir_t filldir)
{
xfs_dir2_data_hdr_t *hdr; /* block header */
struct xfs_buf *bp; /* buffer for block */
xfs_dir2_block_tail_t *btp; /* block tail */
xfs_dir2_data_entry_t *dep; /* block data entry */
xfs_dir2_data_unused_t *dup; /* block unused entry */
char *endptr; /* end of the data entries */
int error; /* error return value */
xfs_mount_t *mp; /* filesystem mount point */
char *ptr; /* current data entry */
int wantoff; /* starting block offset */
xfs_off_t cook;
mp = dp->i_mount;
/*
* If the block number in the offset is out of range, we're done.
*/
if (xfs_dir2_dataptr_to_db(mp, *offset) > mp->m_dirdatablk)
return 0;
error = xfs_dir2_block_read(NULL, dp, &bp);
if (error)
return error;
/*
* Extract the byte offset we start at from the seek pointer.
* We'll skip entries before this.
*/
wantoff = xfs_dir2_dataptr_to_off(mp, *offset);
hdr = bp->b_addr;
xfs_dir2_data_check(dp, bp);
/*
* Set up values for the loop.
*/
btp = xfs_dir2_block_tail_p(mp, hdr);
ptr = (char *)(hdr + 1);
endptr = (char *)xfs_dir2_block_leaf_p(btp);
/*
* Loop over the data portion of the block.
* Each object is a real entry (dep) or an unused one (dup).
*/
while (ptr < endptr) {
dup = (xfs_dir2_data_unused_t *)ptr;
/*
* Unused, skip it.
*/
if (be16_to_cpu(dup->freetag) == XFS_DIR2_DATA_FREE_TAG) {
ptr += be16_to_cpu(dup->length);
continue;
}
dep = (xfs_dir2_data_entry_t *)ptr;
/*
* Bump pointer for the next iteration.
*/
ptr += xfs_dir2_data_entsize(dep->namelen);
/*
* The entry is before the desired starting point, skip it.
*/
if ((char *)dep - (char *)hdr < wantoff)
continue;
cook = xfs_dir2_db_off_to_dataptr(mp, mp->m_dirdatablk,
(char *)dep - (char *)hdr);
/*
* If it didn't fit, set the final offset to here & return.
*/
if (filldir(dirent, (char *)dep->name, dep->namelen,
cook & 0x7fffffff, be64_to_cpu(dep->inumber),
DT_UNKNOWN)) {
*offset = cook & 0x7fffffff;
xfs_trans_brelse(NULL, bp);
return 0;
}
}
/*
* Reached the end of the block.
* Set the offset to a non-existent block 1 and return.
*/
*offset = xfs_dir2_db_off_to_dataptr(mp, mp->m_dirdatablk + 1, 0) &
0x7fffffff;
xfs_trans_brelse(NULL, bp);
return 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;
}
/*
* 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;
}
/*
* Read and/or modify the summary information for a given extent size,
* bitmap block combination.
* Keeps track of a current summary block, so we don't keep reading
* it from the buffer cache.
*
* Summary information is returned in *sum if specified.
* If no delta is specified, returns summary only.
*/
int
xfs_rtmodify_summary_int(
xfs_mount_t *mp, /* file system mount structure */
xfs_trans_t *tp, /* transaction pointer */
int log, /* log2 of extent size */
xfs_rtblock_t bbno, /* bitmap block number */
int delta, /* change to make to summary info */
xfs_buf_t **rbpp, /* in/out: summary block buffer */
xfs_fsblock_t *rsb, /* in/out: summary block number */
xfs_suminfo_t *sum) /* out: summary info for this block */
{
xfs_buf_t *bp; /* buffer for the summary block */
int error; /* error value */
xfs_fsblock_t sb; /* summary fsblock */
int so; /* index into the summary file */
xfs_suminfo_t *sp; /* pointer to returned data */
/*
* Compute entry number in the summary file.
*/
so = XFS_SUMOFFS(mp, log, bbno);
/*
* Compute the block number in the summary file.
*/
sb = XFS_SUMOFFSTOBLOCK(mp, so);
/*
* If we have an old buffer, and the block number matches, use that.
*/
if (*rbpp && *rsb == sb)
bp = *rbpp;
/*
* Otherwise we have to get the buffer.
*/
else {
/*
* If there was an old one, get rid of it first.
*/
if (*rbpp)
xfs_trans_brelse(tp, *rbpp);
error = xfs_rtbuf_get(mp, tp, sb, 1, &bp);
if (error) {
return error;
}
/*
* Remember this buffer and block for the next call.
*/
*rbpp = bp;
*rsb = sb;
}
/*
* Point to the summary information, modify/log it, and/or copy it out.
*/
sp = XFS_SUMPTR(mp, bp, so);
if (delta) {
uint first = (uint)((char *)sp - (char *)bp->b_addr);
*sp += delta;
xfs_trans_log_buf(tp, bp, first, first + sizeof(*sp) - 1);
}
if (sum)
*sum = *sp;
return 0;
}
/*
* Add an entry to a block directory.
*/
int /* error */
xfs_dir2_block_addname(
xfs_da_args_t *args) /* directory op arguments */
{
xfs_dir2_data_hdr_t *hdr; /* block header */
xfs_dir2_leaf_entry_t *blp; /* block leaf entries */
struct xfs_buf *bp; /* buffer for block */
xfs_dir2_block_tail_t *btp; /* block tail */
int compact; /* need to compact leaf ents */
xfs_dir2_data_entry_t *dep; /* block data entry */
xfs_inode_t *dp; /* directory inode */
xfs_dir2_data_unused_t *dup; /* block unused entry */
int error; /* error return value */
xfs_dir2_data_unused_t *enddup=NULL; /* unused at end of data */
xfs_dahash_t hash; /* hash value of found entry */
int high; /* high index for binary srch */
int highstale; /* high stale index */
int lfloghigh=0; /* last final leaf to log */
int lfloglow=0; /* first final leaf to log */
int len; /* length of the new entry */
int low; /* low index for binary srch */
int lowstale; /* low stale index */
int mid=0; /* midpoint for binary srch */
int needlog; /* need to log header */
int needscan; /* need to rescan freespace */
__be16 *tagp; /* pointer to tag value */
xfs_trans_t *tp; /* transaction structure */
trace_xfs_dir2_block_addname(args);
dp = args->dp;
tp = args->trans;
/* Read the (one and only) directory block into bp. */
error = xfs_dir3_block_read(tp, dp, &bp);
if (error)
return error;
len = dp->d_ops->data_entsize(args->namelen);
/*
* Set up pointers to parts of the block.
*/
hdr = bp->b_addr;
btp = xfs_dir2_block_tail_p(args->geo, hdr);
blp = xfs_dir2_block_leaf_p(btp);
/*
* Find out if we can reuse stale entries or whether we need extra
* space for entry and new leaf.
*/
xfs_dir2_block_need_space(dp, hdr, btp, blp, &tagp, &dup,
&enddup, &compact, len);
/*
* Done everything we need for a space check now.
*/
if (args->op_flags & XFS_DA_OP_JUSTCHECK) {
xfs_trans_brelse(tp, bp);
if (!dup)
return -ENOSPC;
return 0;
}
/*
* If we don't have space for the new entry & leaf ...
*/
if (!dup) {
/* Don't have a space reservation: return no-space. */
if (args->total == 0)
return -ENOSPC;
/*
* Convert to the next larger format.
* Then add the new entry in that format.
*/
error = xfs_dir2_block_to_leaf(args, bp);
if (error)
return error;
return xfs_dir2_leaf_addname(args);
}
needlog = needscan = 0;
/*
* If need to compact the leaf entries, do it now.
*/
if (compact) {
xfs_dir2_block_compact(args, bp, hdr, btp, blp, &needlog,
&lfloghigh, &lfloglow);
/* recalculate blp post-compaction */
blp = xfs_dir2_block_leaf_p(btp);
} else if (btp->stale) {
/*
* Set leaf logging boundaries to impossible state.
* For the no-stale case they're set explicitly.
*/
lfloglow = be32_to_cpu(btp->count);
lfloghigh = -1;
}
/*
* Find the slot that's first lower than our hash value, -1 if none.
*/
for (low = 0, high = be32_to_cpu(btp->count) - 1; low <= high; ) {
mid = (low + high) >> 1;
if ((hash = be32_to_cpu(blp[mid].hashval)) == args->hashval)
break;
if (hash < args->hashval)
low = mid + 1;
else
high = mid - 1;
}
while (mid >= 0 && be32_to_cpu(blp[mid].hashval) >= args->hashval) {
mid--;
}
/*
* No stale entries, will use enddup space to hold new leaf.
*/
if (!btp->stale) {
/*
* Mark the space needed for the new leaf entry, now in use.
*/
xfs_dir2_data_use_free(args, bp, enddup,
(xfs_dir2_data_aoff_t)
((char *)enddup - (char *)hdr + be16_to_cpu(enddup->length) -
sizeof(*blp)),
(xfs_dir2_data_aoff_t)sizeof(*blp),
&needlog, &needscan);
/*
* Update the tail (entry count).
*/
be32_add_cpu(&btp->count, 1);
/*
* If we now need to rebuild the bestfree map, do so.
* This needs to happen before the next call to use_free.
*/
if (needscan) {
xfs_dir2_data_freescan(dp, hdr, &needlog);
needscan = 0;
}
/*
* Adjust pointer to the first leaf entry, we're about to move
* the table up one to open up space for the new leaf entry.
* Then adjust our index to match.
*/
blp--;
mid++;
if (mid)
memmove(blp, &blp[1], mid * sizeof(*blp));
lfloglow = 0;
lfloghigh = mid;
}
/*
* Use a stale leaf for our new entry.
*/
else {
for (lowstale = mid;
lowstale >= 0 &&
blp[lowstale].address !=
cpu_to_be32(XFS_DIR2_NULL_DATAPTR);
lowstale--)
continue;
for (highstale = mid + 1;
highstale < be32_to_cpu(btp->count) &&
blp[highstale].address !=
cpu_to_be32(XFS_DIR2_NULL_DATAPTR) &&
(lowstale < 0 || mid - lowstale > highstale - mid);
highstale++)
continue;
/*
* Move entries toward the low-numbered stale entry.
*/
if (lowstale >= 0 &&
(highstale == be32_to_cpu(btp->count) ||
mid - lowstale <= highstale - mid)) {
if (mid - lowstale)
memmove(&blp[lowstale], &blp[lowstale + 1],
(mid - lowstale) * sizeof(*blp));
lfloglow = MIN(lowstale, lfloglow);
lfloghigh = MAX(mid, lfloghigh);
}
/*
* Move entries toward the high-numbered stale entry.
*/
else {
ASSERT(highstale < be32_to_cpu(btp->count));
mid++;
if (highstale - mid)
memmove(&blp[mid + 1], &blp[mid],
(highstale - mid) * sizeof(*blp));
lfloglow = MIN(mid, lfloglow);
lfloghigh = MAX(highstale, lfloghigh);
}
be32_add_cpu(&btp->stale, -1);
}
/*
* Point to the new data entry.
*/
dep = (xfs_dir2_data_entry_t *)dup;
/*
* Fill in the leaf entry.
*/
blp[mid].hashval = cpu_to_be32(args->hashval);
blp[mid].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(
(char *)dep - (char *)hdr));
xfs_dir2_block_log_leaf(tp, bp, lfloglow, lfloghigh);
/*
* Mark space for the data entry used.
*/
xfs_dir2_data_use_free(args, bp, dup,
(xfs_dir2_data_aoff_t)((char *)dup - (char *)hdr),
(xfs_dir2_data_aoff_t)len, &needlog, &needscan);
/*
* Create the new data entry.
*/
dep->inumber = cpu_to_be64(args->inumber);
dep->namelen = args->namelen;
memcpy(dep->name, args->name, args->namelen);
dp->d_ops->data_put_ftype(dep, args->filetype);
tagp = dp->d_ops->data_entry_tag_p(dep);
*tagp = cpu_to_be16((char *)dep - (char *)hdr);
/*
* Clean up the bestfree array and log the header, tail, and entry.
*/
if (needscan)
xfs_dir2_data_freescan(dp, hdr, &needlog);
if (needlog)
xfs_dir2_data_log_header(args, bp);
xfs_dir2_block_log_tail(tp, bp);
xfs_dir2_data_log_entry(args, bp, dep);
xfs_dir3_data_check(dp, bp);
return 0;
}