/*
* 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;
}
/*
* Convert the shortform directory to block form.
*/
int /* error */
xfs_dir2_sf_to_block(
xfs_da_args_t *args) /* operation arguments */
{
xfs_dir2_db_t blkno; /* dir-relative block # (0) */
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 pointer */
xfs_dir2_data_entry_t *dep; /* data entry pointer */
xfs_inode_t *dp; /* incore directory inode */
int dummy; /* trash */
xfs_dir2_data_unused_t *dup; /* unused entry pointer */
int endoffset; /* end of data objects */
int error; /* error return value */
int i; /* index */
xfs_mount_t *mp; /* filesystem mount point */
int needlog; /* need to log block header */
int needscan; /* need to scan block freespc */
int newoffset; /* offset from current entry */
int offset; /* target block offset */
xfs_dir2_sf_entry_t *sfep; /* sf entry pointer */
xfs_dir2_sf_hdr_t *oldsfp; /* old shortform header */
xfs_dir2_sf_hdr_t *sfp; /* shortform header */
__be16 *tagp; /* end of data entry */
xfs_trans_t *tp; /* transaction pointer */
struct xfs_name name;
struct xfs_ifork *ifp;
trace_xfs_dir2_sf_to_block(args);
dp = args->dp;
tp = args->trans;
mp = dp->i_mount;
ifp = XFS_IFORK_PTR(dp, XFS_DATA_FORK);
ASSERT(ifp->if_flags & XFS_IFINLINE);
/*
* Bomb out if the shortform directory is way too short.
*/
if (dp->i_d.di_size < offsetof(xfs_dir2_sf_hdr_t, parent)) {
ASSERT(XFS_FORCED_SHUTDOWN(mp));
return -EIO;
}
oldsfp = (xfs_dir2_sf_hdr_t *)ifp->if_u1.if_data;
ASSERT(ifp->if_bytes == dp->i_d.di_size);
ASSERT(ifp->if_u1.if_data != NULL);
ASSERT(dp->i_d.di_size >= xfs_dir2_sf_hdr_size(oldsfp->i8count));
ASSERT(dp->i_d.di_nextents == 0);
/*
* Copy the directory into a temporary buffer.
* Then pitch the incore inode data so we can make extents.
*/
sfp = kmem_alloc(ifp->if_bytes, KM_SLEEP);
memcpy(sfp, oldsfp, ifp->if_bytes);
xfs_idata_realloc(dp, -ifp->if_bytes, XFS_DATA_FORK);
xfs_bmap_local_to_extents_empty(dp, XFS_DATA_FORK);
dp->i_d.di_size = 0;
/*
* Add block 0 to the inode.
*/
error = xfs_dir2_grow_inode(args, XFS_DIR2_DATA_SPACE, &blkno);
if (error) {
kmem_free(sfp);
return error;
}
/*
* Initialize the data block, then convert it to block format.
*/
error = xfs_dir3_data_init(args, blkno, &bp);
if (error) {
kmem_free(sfp);
return error;
}
xfs_dir3_block_init(mp, tp, bp, dp);
hdr = bp->b_addr;
/*
* Compute size of block "tail" area.
*/
i = (uint)sizeof(*btp) +
(sfp->count + 2) * (uint)sizeof(xfs_dir2_leaf_entry_t);
/*
* The whole thing is initialized to free by the init routine.
* Say we're using the leaf and tail area.
*/
dup = dp->d_ops->data_unused_p(hdr);
needlog = needscan = 0;
xfs_dir2_data_use_free(args, bp, dup, args->geo->blksize - i,
i, &needlog, &needscan);
ASSERT(needscan == 0);
/*
* Fill in the tail.
*/
btp = xfs_dir2_block_tail_p(args->geo, hdr);
btp->count = cpu_to_be32(sfp->count + 2); /* ., .. */
btp->stale = 0;
blp = xfs_dir2_block_leaf_p(btp);
endoffset = (uint)((char *)blp - (char *)hdr);
/*
* Remove the freespace, we'll manage it.
*/
xfs_dir2_data_use_free(args, bp, dup,
(xfs_dir2_data_aoff_t)((char *)dup - (char *)hdr),
be16_to_cpu(dup->length), &needlog, &needscan);
/*
* Create entry for .
*/
dep = dp->d_ops->data_dot_entry_p(hdr);
dep->inumber = cpu_to_be64(dp->i_ino);
dep->namelen = 1;
dep->name[0] = '.';
dp->d_ops->data_put_ftype(dep, XFS_DIR3_FT_DIR);
tagp = dp->d_ops->data_entry_tag_p(dep);
*tagp = cpu_to_be16((char *)dep - (char *)hdr);
xfs_dir2_data_log_entry(args, bp, dep);
blp[0].hashval = cpu_to_be32(xfs_dir_hash_dot);
blp[0].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(
(char *)dep - (char *)hdr));
/*
* Create entry for ..
*/
dep = dp->d_ops->data_dotdot_entry_p(hdr);
dep->inumber = cpu_to_be64(dp->d_ops->sf_get_parent_ino(sfp));
dep->namelen = 2;
dep->name[0] = dep->name[1] = '.';
dp->d_ops->data_put_ftype(dep, XFS_DIR3_FT_DIR);
tagp = dp->d_ops->data_entry_tag_p(dep);
*tagp = cpu_to_be16((char *)dep - (char *)hdr);
xfs_dir2_data_log_entry(args, bp, dep);
blp[1].hashval = cpu_to_be32(xfs_dir_hash_dotdot);
blp[1].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(
(char *)dep - (char *)hdr));
offset = dp->d_ops->data_first_offset;
/*
* Loop over existing entries, stuff them in.
*/
i = 0;
if (!sfp->count)
sfep = NULL;
else
sfep = xfs_dir2_sf_firstentry(sfp);
/*
* Need to preserve the existing offset values in the sf directory.
* Insert holes (unused entries) where necessary.
*/
while (offset < endoffset) {
/*
* sfep is null when we reach the end of the list.
*/
if (sfep == NULL)
newoffset = endoffset;
else
newoffset = xfs_dir2_sf_get_offset(sfep);
/*
* There should be a hole here, make one.
*/
if (offset < newoffset) {
dup = (xfs_dir2_data_unused_t *)((char *)hdr + offset);
dup->freetag = cpu_to_be16(XFS_DIR2_DATA_FREE_TAG);
dup->length = cpu_to_be16(newoffset - offset);
*xfs_dir2_data_unused_tag_p(dup) = cpu_to_be16(
((char *)dup - (char *)hdr));
xfs_dir2_data_log_unused(args, bp, dup);
xfs_dir2_data_freeinsert(hdr,
dp->d_ops->data_bestfree_p(hdr),
dup, &dummy);
offset += be16_to_cpu(dup->length);
continue;
}
/*
* Copy a real entry.
*/
dep = (xfs_dir2_data_entry_t *)((char *)hdr + newoffset);
dep->inumber = cpu_to_be64(dp->d_ops->sf_get_ino(sfp, sfep));
dep->namelen = sfep->namelen;
dp->d_ops->data_put_ftype(dep, dp->d_ops->sf_get_ftype(sfep));
memcpy(dep->name, sfep->name, dep->namelen);
tagp = dp->d_ops->data_entry_tag_p(dep);
*tagp = cpu_to_be16((char *)dep - (char *)hdr);
xfs_dir2_data_log_entry(args, bp, dep);
name.name = sfep->name;
name.len = sfep->namelen;
blp[2 + i].hashval = cpu_to_be32(mp->m_dirnameops->
hashname(&name));
blp[2 + i].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(
(char *)dep - (char *)hdr));
offset = (int)((char *)(tagp + 1) - (char *)hdr);
if (++i == sfp->count)
sfep = NULL;
else
sfep = dp->d_ops->sf_nextentry(sfp, sfep);
}
/* Done with the temporary buffer */
kmem_free(sfp);
/*
* Sort the leaf entries by hash value.
*/
xfs_sort(blp, be32_to_cpu(btp->count), sizeof(*blp), xfs_dir2_block_sort);
/*
* Log the leaf entry area and tail.
* Already logged the header in data_init, ignore needlog.
*/
ASSERT(needscan == 0);
xfs_dir2_block_log_leaf(tp, bp, 0, be32_to_cpu(btp->count) - 1);
xfs_dir2_block_log_tail(tp, bp);
xfs_dir3_data_check(dp, bp);
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_free_t *bf; /* bestfree table in block */
xfs_dir2_block_t *block; /* directory block structure */
xfs_dir2_leaf_entry_t *blp; /* block leaf entries */
xfs_dabuf_t *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 */
xfs_mount_t *mp; /* filesystem mount point */
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;
mp = dp->i_mount;
/*
* Read the (one and only) directory block into dabuf bp.
*/
if ((error =
xfs_da_read_buf(tp, dp, mp->m_dirdatablk, -1, &bp, XFS_DATA_FORK))) {
return error;
}
ASSERT(bp != NULL);
block = bp->data;
/*
* Check the magic number, corrupted if wrong.
*/
if (unlikely(be32_to_cpu(block->hdr.magic) != XFS_DIR2_BLOCK_MAGIC)) {
XFS_CORRUPTION_ERROR("xfs_dir2_block_addname",
XFS_ERRLEVEL_LOW, mp, block);
xfs_da_brelse(tp, bp);
return XFS_ERROR(EFSCORRUPTED);
}
len = xfs_dir2_data_entsize(args->namelen);
/*
* Set up pointers to parts of the block.
*/
bf = block->hdr.bestfree;
btp = xfs_dir2_block_tail_p(mp, block);
blp = xfs_dir2_block_leaf_p(btp);
/*
* No stale entries? Need space for entry and new leaf.
*/
if (!btp->stale) {
/*
* Tag just before the first leaf entry.
*/
tagp = (__be16 *)blp - 1;
/*
* Data object just before the first leaf entry.
*/
enddup = (xfs_dir2_data_unused_t *)((char *)block + be16_to_cpu(*tagp));
/*
* If it's not free then can't do this add without cleaning up:
* the space before the first leaf entry needs to be free so it
* can be expanded to hold the pointer to the new entry.
*/
if (be16_to_cpu(enddup->freetag) != XFS_DIR2_DATA_FREE_TAG)
dup = enddup = NULL;
/*
* Check out the biggest freespace and see if it's the same one.
*/
else {
dup = (xfs_dir2_data_unused_t *)
((char *)block + be16_to_cpu(bf[0].offset));
if (dup == enddup) {
/*
* It is the biggest freespace, is it too small
* to hold the new leaf too?
*/
if (be16_to_cpu(dup->length) < len + (uint)sizeof(*blp)) {
/*
* Yes, we use the second-largest
* entry instead if it works.
*/
if (be16_to_cpu(bf[1].length) >= len)
dup = (xfs_dir2_data_unused_t *)
((char *)block +
be16_to_cpu(bf[1].offset));
else
dup = NULL;
}
} else {
/*
* Not the same free entry,
* just check its length.
*/
if (be16_to_cpu(dup->length) < len) {
dup = NULL;
}
}
}
compact = 0;
}
/*
* If there are stale entries we'll use one for the leaf.
* Is the biggest entry enough to avoid compaction?
*/
else if (be16_to_cpu(bf[0].length) >= len) {
dup = (xfs_dir2_data_unused_t *)
((char *)block + be16_to_cpu(bf[0].offset));
compact = 0;
}
/*
* Will need to compact to make this work.
*/
else {
/*
* Tag just before the first leaf entry.
*/
tagp = (__be16 *)blp - 1;
/*
* Data object just before the first leaf entry.
*/
dup = (xfs_dir2_data_unused_t *)((char *)block + be16_to_cpu(*tagp));
/*
* If it's not free then the data will go where the
* leaf data starts now, if it works at all.
*/
if (be16_to_cpu(dup->freetag) == XFS_DIR2_DATA_FREE_TAG) {
if (be16_to_cpu(dup->length) + (be32_to_cpu(btp->stale) - 1) *
(uint)sizeof(*blp) < len)
dup = NULL;
} else if ((be32_to_cpu(btp->stale) - 1) * (uint)sizeof(*blp) < len)
dup = NULL;
else
dup = (xfs_dir2_data_unused_t *)blp;
compact = 1;
}
/*
* If this isn't a real add, we're done with the buffer.
*/
if (args->op_flags & XFS_DA_OP_JUSTCHECK)
xfs_da_brelse(tp, bp);
/*
* If we don't have space for the new entry & leaf ...
*/
if (!dup) {
/*
* Not trying to actually do anything, or don't have
* a space reservation: return no-space.
*/
if ((args->op_flags & XFS_DA_OP_JUSTCHECK) || args->total == 0)
return XFS_ERROR(ENOSPC);
/*
* Convert to the next larger format.
* Then add the new entry in that format.
*/
error = xfs_dir2_block_to_leaf(args, bp);
xfs_da_buf_done(bp);
if (error)
return error;
return xfs_dir2_leaf_addname(args);
}
/*
* Just checking, and it would work, so say so.
*/
if (args->op_flags & XFS_DA_OP_JUSTCHECK)
return 0;
needlog = needscan = 0;
/*
* If need to compact the leaf entries, do it now.
* Leave the highest-numbered stale entry stale.
* XXX should be the one closest to mid but mid is not yet computed.
*/
if (compact) {
int fromidx; /* source leaf index */
int toidx; /* target leaf index */
for (fromidx = toidx = be32_to_cpu(btp->count) - 1,
highstale = lfloghigh = -1;
fromidx >= 0;
fromidx--) {
if (be32_to_cpu(blp[fromidx].address) == XFS_DIR2_NULL_DATAPTR) {
if (highstale == -1)
highstale = toidx;
else {
if (lfloghigh == -1)
lfloghigh = toidx;
continue;
}
}
if (fromidx < toidx)
blp[toidx] = blp[fromidx];
toidx--;
}
lfloglow = toidx + 1 - (be32_to_cpu(btp->stale) - 1);
lfloghigh -= be32_to_cpu(btp->stale) - 1;
be32_add_cpu(&btp->count, -(be32_to_cpu(btp->stale) - 1));
xfs_dir2_data_make_free(tp, bp,
(xfs_dir2_data_aoff_t)((char *)blp - (char *)block),
(xfs_dir2_data_aoff_t)((be32_to_cpu(btp->stale) - 1) * sizeof(*blp)),
&needlog, &needscan);
blp += be32_to_cpu(btp->stale) - 1;
btp->stale = cpu_to_be32(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(mp, (xfs_dir2_data_t *)block, &needlog);
needscan = 0;
}
}
/*
* Set leaf logging boundaries to impossible state.
* For the no-stale case they're set explicitly.
*/
else if (btp->stale) {
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(tp, bp, enddup,
(xfs_dir2_data_aoff_t)
((char *)enddup - (char *)block + 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(mp, (xfs_dir2_data_t *)block,
&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 &&
be32_to_cpu(blp[lowstale].address) != XFS_DIR2_NULL_DATAPTR;
lowstale--)
continue;
for (highstale = mid + 1;
highstale < be32_to_cpu(btp->count) &&
be32_to_cpu(blp[highstale].address) != 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(mp,
(char *)dep - (char *)block));
xfs_dir2_block_log_leaf(tp, bp, lfloglow, lfloghigh);
/*
* Mark space for the data entry used.
*/
xfs_dir2_data_use_free(tp, bp, dup,
(xfs_dir2_data_aoff_t)((char *)dup - (char *)block),
(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);
tagp = xfs_dir2_data_entry_tag_p(dep);
*tagp = cpu_to_be16((char *)dep - (char *)block);
/*
* Clean up the bestfree array and log the header, tail, and entry.
*/
if (needscan)
xfs_dir2_data_freescan(mp, (xfs_dir2_data_t *)block, &needlog);
if (needlog)
xfs_dir2_data_log_header(tp, bp);
xfs_dir2_block_log_tail(tp, bp);
xfs_dir2_data_log_entry(tp, bp, dep);
xfs_dir2_data_check(dp, bp);
xfs_da_buf_done(bp);
return 0;
}
/*
* Getdents (readdir) for leaf and node directories.
* This reads the data blocks only, so is the same for both forms.
*/
int /* error */
xfs_dir2_leaf_getdents(
xfs_inode_t *dp, /* incore directory inode */
void *dirent,
size_t bufsize,
xfs_off_t *offset,
filldir_t filldir)
{
xfs_dabuf_t *bp; /* data block buffer */
int byteoff; /* offset in current block */
xfs_dir2_db_t curdb; /* db for current block */
xfs_dir2_off_t curoff; /* current overall offset */
xfs_dir2_data_t *data; /* data block structure */
xfs_dir2_data_entry_t *dep; /* data entry */
xfs_dir2_data_unused_t *dup; /* unused entry */
int error = 0; /* error return value */
int i; /* temporary loop index */
int j; /* temporary loop index */
int length; /* temporary length value */
xfs_bmbt_irec_t *map; /* map vector for blocks */
xfs_extlen_t map_blocks; /* number of fsbs in map */
xfs_dablk_t map_off; /* last mapped file offset */
int map_size; /* total entries in *map */
int map_valid; /* valid entries in *map */
xfs_mount_t *mp; /* filesystem mount point */
xfs_dir2_off_t newoff; /* new curoff after new blk */
int nmap; /* mappings to ask xfs_bmapi */
char *ptr = NULL; /* pointer to current data */
int ra_current; /* number of read-ahead blks */
int ra_index; /* *map index for read-ahead */
int ra_offset; /* map entry offset for ra */
int ra_want; /* readahead count wanted */
/*
* If the offset is at or past the largest allowed value,
* give up right away.
*/
if (*offset >= XFS_DIR2_MAX_DATAPTR)
return 0;
mp = dp->i_mount;
/*
* Set up to bmap a number of blocks based on the caller's
* buffer size, the directory block size, and the filesystem
* block size.
*/
map_size = howmany(bufsize + mp->m_dirblksize, mp->m_sb.sb_blocksize);
map = kmem_alloc(map_size * sizeof(*map), KM_SLEEP);
map_valid = ra_index = ra_offset = ra_current = map_blocks = 0;
bp = NULL;
/*
* Inside the loop we keep the main offset value as a byte offset
* in the directory file.
*/
curoff = xfs_dir2_dataptr_to_byte(mp, *offset);
/*
* Force this conversion through db so we truncate the offset
* down to get the start of the data block.
*/
map_off = xfs_dir2_db_to_da(mp, xfs_dir2_byte_to_db(mp, curoff));
/*
* Loop over directory entries until we reach the end offset.
* Get more blocks and readahead as necessary.
*/
while (curoff < XFS_DIR2_LEAF_OFFSET) {
/*
* If we have no buffer, or we're off the end of the
* current buffer, need to get another one.
*/
if (!bp || ptr >= (char *)bp->data + mp->m_dirblksize) {
/*
* If we have a buffer, we need to release it and
* take it out of the mapping.
*/
if (bp) {
xfs_da_brelse(NULL, bp);
bp = NULL;
map_blocks -= mp->m_dirblkfsbs;
/*
* Loop to get rid of the extents for the
* directory block.
*/
for (i = mp->m_dirblkfsbs; i > 0; ) {
j = MIN((int)map->br_blockcount, i);
map->br_blockcount -= j;
map->br_startblock += j;
map->br_startoff += j;
/*
* If mapping is done, pitch it from
* the table.
*/
if (!map->br_blockcount && --map_valid)
memmove(&map[0], &map[1],
sizeof(map[0]) *
map_valid);
i -= j;
}
}
/*
* Recalculate the readahead blocks wanted.
*/
ra_want = howmany(bufsize + mp->m_dirblksize,
mp->m_sb.sb_blocksize) - 1;
ASSERT(ra_want >= 0);
/*
* If we don't have as many as we want, and we haven't
* run out of data blocks, get some more mappings.
*/
if (1 + ra_want > map_blocks &&
map_off <
xfs_dir2_byte_to_da(mp, XFS_DIR2_LEAF_OFFSET)) {
/*
* Get more bmaps, fill in after the ones
* we already have in the table.
*/
nmap = map_size - map_valid;
error = xfs_bmapi(NULL, dp,
map_off,
xfs_dir2_byte_to_da(mp,
XFS_DIR2_LEAF_OFFSET) - map_off,
XFS_BMAPI_METADATA, NULL, 0,
&map[map_valid], &nmap, NULL, NULL);
/*
* Don't know if we should ignore this or
* try to return an error.
* The trouble with returning errors
* is that readdir will just stop without
* actually passing the error through.
*/
if (error)
break; /* XXX */
/*
* If we got all the mappings we asked for,
* set the final map offset based on the
* last bmap value received.
* Otherwise, we've reached the end.
*/
if (nmap == map_size - map_valid)
map_off =
map[map_valid + nmap - 1].br_startoff +
map[map_valid + nmap - 1].br_blockcount;
else
map_off =
xfs_dir2_byte_to_da(mp,
XFS_DIR2_LEAF_OFFSET);
/*
* Look for holes in the mapping, and
* eliminate them. Count up the valid blocks.
*/
for (i = map_valid; i < map_valid + nmap; ) {
if (map[i].br_startblock ==
HOLESTARTBLOCK) {
nmap--;
length = map_valid + nmap - i;
if (length)
memmove(&map[i],
&map[i + 1],
sizeof(map[i]) *
length);
} else {
map_blocks +=
map[i].br_blockcount;
i++;
}
}
map_valid += nmap;
}
/*
* No valid mappings, so no more data blocks.
*/
if (!map_valid) {
curoff = xfs_dir2_da_to_byte(mp, map_off);
break;
}
/*
* Read the directory block starting at the first
* mapping.
*/
curdb = xfs_dir2_da_to_db(mp, map->br_startoff);
error = xfs_da_read_buf(NULL, dp, map->br_startoff,
map->br_blockcount >= mp->m_dirblkfsbs ?
XFS_FSB_TO_DADDR(mp, map->br_startblock) :
-1,
&bp, XFS_DATA_FORK);
/*
* Should just skip over the data block instead
* of giving up.
*/
if (error)
break; /* XXX */
/*
* Adjust the current amount of read-ahead: we just
* read a block that was previously ra.
*/
if (ra_current)
ra_current -= mp->m_dirblkfsbs;
/*
* Do we need more readahead?
*/
for (ra_index = ra_offset = i = 0;
ra_want > ra_current && i < map_blocks;
i += mp->m_dirblkfsbs) {
ASSERT(ra_index < map_valid);
/*
* Read-ahead a contiguous directory block.
*/
if (i > ra_current &&
map[ra_index].br_blockcount >=
mp->m_dirblkfsbs) {
//TODO: make sure this is right, should readahead be
//replaced by readbuf?
//xfs_buf_readahead(mp->m_ddev_targp,
// XFS_FSB_TO_DADDR(mp,
// map[ra_index].br_startblock +
// ra_offset),
// (int)BTOBB(mp->m_dirblksize));
//TODO: figure out flags, flags =0
//libxfs_readbuf(mp->m_dev,
// XFS_FSB_TO_DADDR(mp,
// map[ra_index].br_startblock +
// ra_offset),
// (int)BTOBB(mp->m_dirblksize), 0);
ra_current = i;
}
/*
* Read-ahead a non-contiguous directory block.
* This doesn't use our mapping, but this
* is a very rare case.
*/
else if (i > ra_current) {
(void)xfs_da_reada_buf(NULL, dp,
map[ra_index].br_startoff +
ra_offset, XFS_DATA_FORK);
ra_current = i;
}
/*
* Advance offset through the mapping table.
*/
for (j = 0; j < mp->m_dirblkfsbs; j++) {
/*
* The rest of this extent but not
* more than a dir block.
*/
length = MIN(mp->m_dirblkfsbs,
(int)(map[ra_index].br_blockcount -
ra_offset));
j += length;
ra_offset += length;
/*
* Advance to the next mapping if
* this one is used up.
*/
if (ra_offset ==
map[ra_index].br_blockcount) {
ra_offset = 0;
ra_index++;
}
}
}
/*
* Having done a read, we need to set a new offset.
*/
newoff = xfs_dir2_db_off_to_byte(mp, curdb, 0);
/*
* Start of the current block.
*/
if (curoff < newoff)
curoff = newoff;
/*
* Make sure we're in the right block.
*/
else if (curoff > newoff)
ASSERT(xfs_dir2_byte_to_db(mp, curoff) ==
curdb);
data = bp->data;
xfs_dir2_data_check(dp, bp);
/*
* Find our position in the block.
*/
ptr = (char *)&data->u;
byteoff = xfs_dir2_byte_to_off(mp, curoff);
/*
* Skip past the header.
*/
if (byteoff == 0)
curoff += (uint)sizeof(data->hdr);
/*
* Skip past entries until we reach our offset.
*/
else {
while ((char *)ptr - (char *)data < byteoff) {
dup = (xfs_dir2_data_unused_t *)ptr;
if (be16_to_cpu(dup->freetag)
== XFS_DIR2_DATA_FREE_TAG) {
length = be16_to_cpu(dup->length);
ptr += length;
continue;
}
dep = (xfs_dir2_data_entry_t *)ptr;
length =
xfs_dir2_data_entsize(dep->namelen);
ptr += length;
}
/*
* Now set our real offset.
*/
curoff =
xfs_dir2_db_off_to_byte(mp,
xfs_dir2_byte_to_db(mp, curoff),
(char *)ptr - (char *)data);
if (ptr >= (char *)data + mp->m_dirblksize) {
continue;
}
}
}
/*
* We have a pointer to an entry.
* Is it a live one?
*/
dup = (xfs_dir2_data_unused_t *)ptr;
/*
* No, it's unused, skip over it.
*/
if (be16_to_cpu(dup->freetag) == XFS_DIR2_DATA_FREE_TAG) {
length = be16_to_cpu(dup->length);
ptr += length;
curoff += length;
continue;
}
dep = (xfs_dir2_data_entry_t *)ptr;
length = xfs_dir2_data_entsize(dep->namelen);
if (filldir(dirent, (char *)dep->name, dep->namelen,
xfs_dir2_byte_to_dataptr(mp, curoff) & 0x7fffffff,
be64_to_cpu(dep->inumber), DT_UNKNOWN))
break;
/*
* Advance to next entry in the block.
*/
ptr += length;
curoff += length;
/* bufsize may have just been a guess; don't go negative */
bufsize = bufsize > length ? bufsize - length : 0;
}
/*
* All done. Set output offset value to current offset.
*/
if (curoff > xfs_dir2_dataptr_to_byte(mp, XFS_DIR2_MAX_DATAPTR))
*offset = XFS_DIR2_MAX_DATAPTR & 0x7fffffff;
else
*offset = xfs_dir2_byte_to_dataptr(mp, curoff) & 0x7fffffff;
kmem_free(map);
if (bp)
xfs_da_brelse(NULL, bp);
return error;
}
/*
* Convert the shortform directory to block form.
*/
int /* error */
xfs_dir2_sf_to_block(
xfs_da_args_t *args) /* operation arguments */
{
xfs_dir2_db_t blkno; /* dir-relative block # (0) */
xfs_dir2_block_t *block; /* block structure */
xfs_dir2_leaf_entry_t *blp; /* block leaf entries */
xfs_dabuf_t *bp; /* block buffer */
xfs_dir2_block_tail_t *btp; /* block tail pointer */
char *buf; /* sf buffer */
int buf_len;
xfs_dir2_data_entry_t *dep; /* data entry pointer */
xfs_inode_t *dp; /* incore directory inode */
int dummy; /* trash */
xfs_dir2_data_unused_t *dup; /* unused entry pointer */
int endoffset; /* end of data objects */
int error; /* error return value */
int i; /* index */
xfs_mount_t *mp; /* filesystem mount point */
int needlog; /* need to log block header */
int needscan; /* need to scan block freespc */
int newoffset; /* offset from current entry */
int offset; /* target block offset */
xfs_dir2_sf_entry_t *sfep; /* sf entry pointer */
xfs_dir2_sf_t *sfp; /* shortform structure */
__be16 *tagp; /* end of data entry */
xfs_trans_t *tp; /* transaction pointer */
struct xfs_name name;
trace_xfs_dir2_sf_to_block(args);
dp = args->dp;
tp = args->trans;
mp = dp->i_mount;
ASSERT(dp->i_df.if_flags & XFS_IFINLINE);
/*
* Bomb out if the shortform directory is way too short.
*/
if (dp->i_d.di_size < offsetof(xfs_dir2_sf_hdr_t, parent)) {
ASSERT(XFS_FORCED_SHUTDOWN(mp));
return XFS_ERROR(EIO);
}
ASSERT(dp->i_df.if_bytes == dp->i_d.di_size);
ASSERT(dp->i_df.if_u1.if_data != NULL);
sfp = (xfs_dir2_sf_t *)dp->i_df.if_u1.if_data;
ASSERT(dp->i_d.di_size >= xfs_dir2_sf_hdr_size(sfp->hdr.i8count));
/*
* Copy the directory into the stack buffer.
* Then pitch the incore inode data so we can make extents.
*/
buf_len = dp->i_df.if_bytes;
buf = kmem_alloc(buf_len, KM_SLEEP);
memcpy(buf, sfp, buf_len);
xfs_idata_realloc(dp, -buf_len, XFS_DATA_FORK);
dp->i_d.di_size = 0;
xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE);
/*
* Reset pointer - old sfp is gone.
*/
sfp = (xfs_dir2_sf_t *)buf;
/*
* Add block 0 to the inode.
*/
error = xfs_dir2_grow_inode(args, XFS_DIR2_DATA_SPACE, &blkno);
if (error) {
kmem_free(buf);
return error;
}
/*
* Initialize the data block.
*/
error = xfs_dir2_data_init(args, blkno, &bp);
if (error) {
kmem_free(buf);
return error;
}
block = bp->data;
block->hdr.magic = cpu_to_be32(XFS_DIR2_BLOCK_MAGIC);
/*
* Compute size of block "tail" area.
*/
i = (uint)sizeof(*btp) +
(sfp->hdr.count + 2) * (uint)sizeof(xfs_dir2_leaf_entry_t);
/*
* The whole thing is initialized to free by the init routine.
* Say we're using the leaf and tail area.
*/
dup = (xfs_dir2_data_unused_t *)block->u;
needlog = needscan = 0;
xfs_dir2_data_use_free(tp, bp, dup, mp->m_dirblksize - i, i, &needlog,
&needscan);
ASSERT(needscan == 0);
/*
* Fill in the tail.
*/
btp = xfs_dir2_block_tail_p(mp, block);
btp->count = cpu_to_be32(sfp->hdr.count + 2); /* ., .. */
btp->stale = 0;
blp = xfs_dir2_block_leaf_p(btp);
endoffset = (uint)((char *)blp - (char *)block);
/*
* Remove the freespace, we'll manage it.
*/
xfs_dir2_data_use_free(tp, bp, dup,
(xfs_dir2_data_aoff_t)((char *)dup - (char *)block),
be16_to_cpu(dup->length), &needlog, &needscan);
/*
* Create entry for .
*/
dep = (xfs_dir2_data_entry_t *)
((char *)block + XFS_DIR2_DATA_DOT_OFFSET);
dep->inumber = cpu_to_be64(dp->i_ino);
dep->namelen = 1;
dep->name[0] = '.';
tagp = xfs_dir2_data_entry_tag_p(dep);
*tagp = cpu_to_be16((char *)dep - (char *)block);
xfs_dir2_data_log_entry(tp, bp, dep);
blp[0].hashval = cpu_to_be32(xfs_dir_hash_dot);
blp[0].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(mp,
(char *)dep - (char *)block));
/*
* Create entry for ..
*/
dep = (xfs_dir2_data_entry_t *)
((char *)block + XFS_DIR2_DATA_DOTDOT_OFFSET);
dep->inumber = cpu_to_be64(xfs_dir2_sf_get_inumber(sfp, &sfp->hdr.parent));
dep->namelen = 2;
dep->name[0] = dep->name[1] = '.';
tagp = xfs_dir2_data_entry_tag_p(dep);
*tagp = cpu_to_be16((char *)dep - (char *)block);
xfs_dir2_data_log_entry(tp, bp, dep);
blp[1].hashval = cpu_to_be32(xfs_dir_hash_dotdot);
blp[1].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(mp,
(char *)dep - (char *)block));
offset = XFS_DIR2_DATA_FIRST_OFFSET;
/*
* Loop over existing entries, stuff them in.
*/
if ((i = 0) == sfp->hdr.count)
sfep = NULL;
else
sfep = xfs_dir2_sf_firstentry(sfp);
/*
* Need to preserve the existing offset values in the sf directory.
* Insert holes (unused entries) where necessary.
*/
while (offset < endoffset) {
/*
* sfep is null when we reach the end of the list.
*/
if (sfep == NULL)
newoffset = endoffset;
else
newoffset = xfs_dir2_sf_get_offset(sfep);
/*
* There should be a hole here, make one.
*/
if (offset < newoffset) {
dup = (xfs_dir2_data_unused_t *)
((char *)block + offset);
dup->freetag = cpu_to_be16(XFS_DIR2_DATA_FREE_TAG);
dup->length = cpu_to_be16(newoffset - offset);
*xfs_dir2_data_unused_tag_p(dup) = cpu_to_be16(
((char *)dup - (char *)block));
xfs_dir2_data_log_unused(tp, bp, dup);
(void)xfs_dir2_data_freeinsert((xfs_dir2_data_t *)block,
dup, &dummy);
offset += be16_to_cpu(dup->length);
continue;
}
/*
* Copy a real entry.
*/
dep = (xfs_dir2_data_entry_t *)((char *)block + newoffset);
dep->inumber = cpu_to_be64(xfs_dir2_sf_get_inumber(sfp,
xfs_dir2_sf_inumberp(sfep)));
dep->namelen = sfep->namelen;
memcpy(dep->name, sfep->name, dep->namelen);
tagp = xfs_dir2_data_entry_tag_p(dep);
*tagp = cpu_to_be16((char *)dep - (char *)block);
xfs_dir2_data_log_entry(tp, bp, dep);
name.name = sfep->name;
name.len = sfep->namelen;
blp[2 + i].hashval = cpu_to_be32(mp->m_dirnameops->
hashname(&name));
blp[2 + i].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(mp,
(char *)dep - (char *)block));
offset = (int)((char *)(tagp + 1) - (char *)block);
if (++i == sfp->hdr.count)
sfep = NULL;
else
sfep = xfs_dir2_sf_nextentry(sfp, sfep);
}
/* Done with the temporary buffer */
kmem_free(buf);
/*
* Sort the leaf entries by hash value.
*/
xfs_sort(blp, be32_to_cpu(btp->count), sizeof(*blp), xfs_dir2_block_sort);
/*
* Log the leaf entry area and tail.
* Already logged the header in data_init, ignore needlog.
*/
ASSERT(needscan == 0);
xfs_dir2_block_log_leaf(tp, bp, 0, be32_to_cpu(btp->count) - 1);
xfs_dir2_block_log_tail(tp, bp);
xfs_dir2_data_check(dp, bp);
xfs_da_buf_done(bp);
return 0;
}
