struct ocfs2_alloc_context *data_ac,
struct ocfs2_alloc_context *meta_ac,
struct buffer_head **new_bh);
+static int ocfs2_dir_indexed(struct inode *inode);
/*
* These are distinct checks because future versions of the file system will
* want to have a trailing dirent structure independent of indexing.
*/
-static int ocfs2_dir_has_trailer(struct inode *dir)
+static int ocfs2_supports_dir_trailer(struct inode *dir)
{
+ struct ocfs2_super *osb = OCFS2_SB(dir->i_sb);
+
if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL)
return 0;
- return ocfs2_meta_ecc(OCFS2_SB(dir->i_sb));
+ return ocfs2_meta_ecc(osb) || ocfs2_dir_indexed(dir);
}
-static int ocfs2_supports_dir_trailer(struct ocfs2_super *osb)
+/*
+ * "new' here refers to the point at which we're creating a new
+ * directory via "mkdir()", but also when we're expanding an inline
+ * directory. In either case, we don't yet have the indexing bit set
+ * on the directory, so the standard checks will fail in when metaecc
+ * is turned off. Only directory-initialization type functions should
+ * use this then. Everything else wants ocfs2_supports_dir_trailer()
+ */
+static int ocfs2_new_dir_wants_trailer(struct inode *dir)
{
- return ocfs2_meta_ecc(osb);
+ struct ocfs2_super *osb = OCFS2_SB(dir->i_sb);
+
+ return ocfs2_meta_ecc(osb) ||
+ ocfs2_supports_indexed_dirs(osb);
}
static inline unsigned int ocfs2_dir_trailer_blk_off(struct super_block *sb)
{
unsigned long toff = blklen - sizeof(struct ocfs2_dir_block_trailer);
- if (!ocfs2_dir_has_trailer(dir))
+ if (!ocfs2_supports_dir_trailer(dir))
return 0;
if (offset != toff)
}
static void ocfs2_init_dir_trailer(struct inode *inode,
- struct buffer_head *bh)
+ struct buffer_head *bh, u16 rec_len)
{
struct ocfs2_dir_block_trailer *trailer;
cpu_to_le16(sizeof(struct ocfs2_dir_block_trailer));
trailer->db_parent_dinode = cpu_to_le64(OCFS2_I(inode)->ip_blkno);
trailer->db_blkno = cpu_to_le64(bh->b_blocknr);
+ trailer->db_free_rec_len = cpu_to_le16(rec_len);
+}
+/*
+ * Link an unindexed block with a dir trailer structure into the index free
+ * list. This function will modify dirdata_bh, but assumes you've already
+ * passed it to the journal.
+ */
+static int ocfs2_dx_dir_link_trailer(struct inode *dir, handle_t *handle,
+ struct buffer_head *dx_root_bh,
+ struct buffer_head *dirdata_bh)
+{
+ int ret;
+ struct ocfs2_dx_root_block *dx_root;
+ struct ocfs2_dir_block_trailer *trailer;
+
+ ret = ocfs2_journal_access_dr(handle, INODE_CACHE(dir), dx_root_bh,
+ OCFS2_JOURNAL_ACCESS_WRITE);
+ if (ret) {
+ mlog_errno(ret);
+ goto out;
+ }
+ trailer = ocfs2_trailer_from_bh(dirdata_bh, dir->i_sb);
+ dx_root = (struct ocfs2_dx_root_block *)dx_root_bh->b_data;
+
+ trailer->db_free_next = dx_root->dr_free_blk;
+ dx_root->dr_free_blk = cpu_to_le64(dirdata_bh->b_blocknr);
+
+ ocfs2_journal_dirty(handle, dx_root_bh);
+
+out:
+ return ret;
+}
+
+static int ocfs2_free_list_at_root(struct ocfs2_dir_lookup_result *res)
+{
+ return res->dl_prev_leaf_bh == NULL;
}
void ocfs2_free_dir_lookup_result(struct ocfs2_dir_lookup_result *res)
brelse(res->dl_dx_root_bh);
brelse(res->dl_leaf_bh);
brelse(res->dl_dx_leaf_bh);
+ brelse(res->dl_prev_leaf_bh);
}
static int ocfs2_dir_indexed(struct inode *inode)
}
if (!(flags & OCFS2_BH_READAHEAD) &&
- ocfs2_dir_has_trailer(inode)) {
+ ocfs2_supports_dir_trailer(inode)) {
rc = ocfs2_check_dir_trailer(inode, tmp);
if (rc) {
if (!*bh)
int ret;
struct buffer_head *tmp = *bh;
- ret = ocfs2_read_block(dir, phys, &tmp, ocfs2_validate_dir_block);
+ ret = ocfs2_read_block(INODE_CACHE(dir), phys, &tmp,
+ ocfs2_validate_dir_block);
if (ret) {
mlog_errno(ret);
goto out;
u64 blkno = le64_to_cpu(di->i_dx_root);
struct buffer_head *tmp = *dx_root_bh;
- ret = ocfs2_read_block(dir, blkno, &tmp, ocfs2_validate_dx_root);
+ ret = ocfs2_read_block(INODE_CACHE(dir), blkno, &tmp,
+ ocfs2_validate_dx_root);
/* If ocfs2_read_block() got us a new bh, pass it up. */
if (!ret && !*dx_root_bh)
int ret;
struct buffer_head *tmp = *dx_leaf_bh;
- ret = ocfs2_read_block(dir, blkno, &tmp, ocfs2_validate_dx_leaf);
+ ret = ocfs2_read_block(INODE_CACHE(dir), blkno, &tmp,
+ ocfs2_validate_dx_leaf);
/* If ocfs2_read_block() got us a new bh, pass it up. */
if (!ret && !*dx_leaf_bh)
{
int ret;
- ret = ocfs2_read_blocks(dir, start, num, dx_leaf_bhs, 0,
+ ret = ocfs2_read_blocks(INODE_CACHE(dir), start, num, dx_leaf_bhs, 0,
ocfs2_validate_dx_leaf);
if (ret)
mlog_errno(ret);
struct ocfs2_extent_rec *rec = NULL;
if (el->l_tree_depth) {
- ret = ocfs2_find_leaf(inode, el, major_hash, &eb_bh);
+ ret = ocfs2_find_leaf(INODE_CACHE(inode), el, major_hash,
+ &eb_bh);
if (ret) {
mlog_errno(ret);
goto out;
if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL)
access = ocfs2_journal_access_di;
- ret = access(handle, dir, de_bh, OCFS2_JOURNAL_ACCESS_WRITE);
+ ret = access(handle, INODE_CACHE(dir), de_bh,
+ OCFS2_JOURNAL_ACCESS_WRITE);
if (ret) {
mlog_errno(ret);
goto out;
goto bail;
}
if (de == de_del) {
- status = access(handle, dir, bh,
+ status = access(handle, INODE_CACHE(dir), bh,
OCFS2_JOURNAL_ACCESS_WRITE);
if (status < 0) {
status = -EIO;
return status;
}
+static unsigned int ocfs2_figure_dirent_hole(struct ocfs2_dir_entry *de)
+{
+ unsigned int hole;
+
+ if (le64_to_cpu(de->inode) == 0)
+ hole = le16_to_cpu(de->rec_len);
+ else
+ hole = le16_to_cpu(de->rec_len) -
+ OCFS2_DIR_REC_LEN(de->name_len);
+
+ return hole;
+}
+
+static int ocfs2_find_max_rec_len(struct super_block *sb,
+ struct buffer_head *dirblock_bh)
+{
+ int size, this_hole, largest_hole = 0;
+ char *trailer, *de_buf, *limit, *start = dirblock_bh->b_data;
+ struct ocfs2_dir_entry *de;
+
+ trailer = (char *)ocfs2_trailer_from_bh(dirblock_bh, sb);
+ size = ocfs2_dir_trailer_blk_off(sb);
+ limit = start + size;
+ de_buf = start;
+ de = (struct ocfs2_dir_entry *)de_buf;
+ do {
+ if (de_buf != trailer) {
+ this_hole = ocfs2_figure_dirent_hole(de);
+ if (this_hole > largest_hole)
+ largest_hole = this_hole;
+ }
+
+ de_buf += le16_to_cpu(de->rec_len);
+ de = (struct ocfs2_dir_entry *)de_buf;
+ } while (de_buf < limit);
+
+ if (largest_hole >= OCFS2_DIR_MIN_REC_LEN)
+ return largest_hole;
+ return 0;
+}
+
static void ocfs2_dx_list_remove_entry(struct ocfs2_dx_entry_list *entry_list,
int index)
{
static int ocfs2_delete_entry_dx(handle_t *handle, struct inode *dir,
struct ocfs2_dir_lookup_result *lookup)
{
- int ret, index;
+ int ret, index, max_rec_len, add_to_free_list = 0;
struct buffer_head *dx_root_bh = lookup->dl_dx_root_bh;
struct buffer_head *leaf_bh = lookup->dl_leaf_bh;
struct ocfs2_dx_leaf *dx_leaf;
struct ocfs2_dx_entry *dx_entry = lookup->dl_dx_entry;
+ struct ocfs2_dir_block_trailer *trailer;
struct ocfs2_dx_root_block *dx_root;
struct ocfs2_dx_entry_list *entry_list;
+ /*
+ * This function gets a bit messy because we might have to
+ * modify the root block, regardless of whether the indexed
+ * entries are stored inline.
+ */
+
+ /*
+ * *Only* set 'entry_list' here, based on where we're looking
+ * for the indexed entries. Later, we might still want to
+ * journal both blocks, based on free list state.
+ */
dx_root = (struct ocfs2_dx_root_block *)dx_root_bh->b_data;
if (ocfs2_dx_root_inline(dx_root)) {
entry_list = &dx_root->dr_entries;
}
/*
+ * We know that removal of this dirent will leave enough room
+ * for a new one, so add this block to the free list if it
+ * isn't already there.
+ */
+ trailer = ocfs2_trailer_from_bh(leaf_bh, dir->i_sb);
+ if (trailer->db_free_rec_len == 0)
+ add_to_free_list = 1;
+
+ /*
* Add the block holding our index into the journal before
* removing the unindexed entry. If we get an error return
* from __ocfs2_delete_entry(), then it hasn't removed the
* entry yet. Likewise, successful return means we *must*
* remove the indexed entry.
*
- * We're also careful to journal the root tree block here if
- * we're going to be adding to the start of the free list.
+ * We're also careful to journal the root tree block here as
+ * the entry count needs to be updated. Also, we might be
+ * adding to the start of the free list.
*/
- if (ocfs2_dx_root_inline(dx_root)) {
- ret = ocfs2_journal_access_dr(handle, dir, dx_root_bh,
- OCFS2_JOURNAL_ACCESS_WRITE);
- if (ret) {
- mlog_errno(ret);
- goto out;
- }
- } else {
- ret = ocfs2_journal_access_dl(handle, dir,
+ ret = ocfs2_journal_access_dr(handle, INODE_CACHE(dir), dx_root_bh,
+ OCFS2_JOURNAL_ACCESS_WRITE);
+ if (ret) {
+ mlog_errno(ret);
+ goto out;
+ }
+
+ if (!ocfs2_dx_root_inline(dx_root)) {
+ ret = ocfs2_journal_access_dl(handle, INODE_CACHE(dir),
lookup->dl_dx_leaf_bh,
OCFS2_JOURNAL_ACCESS_WRITE);
if (ret) {
goto out;
}
+ max_rec_len = ocfs2_find_max_rec_len(dir->i_sb, leaf_bh);
+ trailer->db_free_rec_len = cpu_to_le16(max_rec_len);
+ if (add_to_free_list) {
+ trailer->db_free_next = dx_root->dr_free_blk;
+ dx_root->dr_free_blk = cpu_to_le64(leaf_bh->b_blocknr);
+ ocfs2_journal_dirty(handle, dx_root_bh);
+ }
+
+ /* leaf_bh was journal_accessed for us in __ocfs2_delete_entry */
+ ocfs2_journal_dirty(handle, leaf_bh);
+
+ le32_add_cpu(&dx_root->dr_num_entries, -1);
+ ocfs2_journal_dirty(handle, dx_root_bh);
+
ocfs2_dx_list_remove_entry(entry_list, index);
- if (ocfs2_dx_root_inline(dx_root))
- ocfs2_journal_dirty(handle, dx_root_bh);
- else
+ if (!ocfs2_dx_root_inline(dx_root))
ocfs2_journal_dirty(handle, lookup->dl_dx_leaf_bh);
out:
int ret;
struct ocfs2_dx_leaf *dx_leaf;
- ret = ocfs2_journal_access_dl(handle, dir, dx_leaf_bh,
+ ret = ocfs2_journal_access_dl(handle, INODE_CACHE(dir), dx_leaf_bh,
OCFS2_JOURNAL_ACCESS_WRITE);
if (ret) {
mlog_errno(ret);
return ret;
}
-static int ocfs2_dx_inline_root_insert(struct inode *dir, handle_t *handle,
- struct ocfs2_dx_hinfo *hinfo,
- u64 dirent_blk,
- struct buffer_head *dx_root_bh)
+static void ocfs2_dx_inline_root_insert(struct inode *dir, handle_t *handle,
+ struct ocfs2_dx_hinfo *hinfo,
+ u64 dirent_blk,
+ struct ocfs2_dx_root_block *dx_root)
{
- int ret;
+ ocfs2_dx_entry_list_insert(&dx_root->dr_entries, hinfo, dirent_blk);
+}
+
+static int ocfs2_dx_dir_insert(struct inode *dir, handle_t *handle,
+ struct ocfs2_dir_lookup_result *lookup)
+{
+ int ret = 0;
struct ocfs2_dx_root_block *dx_root;
+ struct buffer_head *dx_root_bh = lookup->dl_dx_root_bh;
- ret = ocfs2_journal_access_dr(handle, dir, dx_root_bh,
+ ret = ocfs2_journal_access_dr(handle, INODE_CACHE(dir), dx_root_bh,
OCFS2_JOURNAL_ACCESS_WRITE);
if (ret) {
mlog_errno(ret);
goto out;
}
- dx_root = (struct ocfs2_dx_root_block *)dx_root_bh->b_data;
- ocfs2_dx_entry_list_insert(&dx_root->dr_entries, hinfo, dirent_blk);
+ dx_root = (struct ocfs2_dx_root_block *)lookup->dl_dx_root_bh->b_data;
+ if (ocfs2_dx_root_inline(dx_root)) {
+ ocfs2_dx_inline_root_insert(dir, handle,
+ &lookup->dl_hinfo,
+ lookup->dl_leaf_bh->b_blocknr,
+ dx_root);
+ } else {
+ ret = __ocfs2_dx_dir_leaf_insert(dir, handle, &lookup->dl_hinfo,
+ lookup->dl_leaf_bh->b_blocknr,
+ lookup->dl_dx_leaf_bh);
+ if (ret)
+ goto out;
+ }
+
+ le32_add_cpu(&dx_root->dr_num_entries, 1);
ocfs2_journal_dirty(handle, dx_root_bh);
out:
return ret;
}
-static int ocfs2_dx_dir_insert(struct inode *dir, handle_t *handle,
- struct ocfs2_dir_lookup_result *lookup)
+static void ocfs2_remove_block_from_free_list(struct inode *dir,
+ handle_t *handle,
+ struct ocfs2_dir_lookup_result *lookup)
{
+ struct ocfs2_dir_block_trailer *trailer, *prev;
struct ocfs2_dx_root_block *dx_root;
+ struct buffer_head *bh;
- dx_root = (struct ocfs2_dx_root_block *)lookup->dl_dx_root_bh->b_data;
- if (ocfs2_dx_root_inline(dx_root))
- return ocfs2_dx_inline_root_insert(dir, handle,
- &lookup->dl_hinfo,
- lookup->dl_leaf_bh->b_blocknr,
- lookup->dl_dx_root_bh);
-
- return __ocfs2_dx_dir_leaf_insert(dir, handle, &lookup->dl_hinfo,
- lookup->dl_leaf_bh->b_blocknr,
- lookup->dl_dx_leaf_bh);
+ trailer = ocfs2_trailer_from_bh(lookup->dl_leaf_bh, dir->i_sb);
+
+ if (ocfs2_free_list_at_root(lookup)) {
+ bh = lookup->dl_dx_root_bh;
+ dx_root = (struct ocfs2_dx_root_block *)bh->b_data;
+ dx_root->dr_free_blk = trailer->db_free_next;
+ } else {
+ bh = lookup->dl_prev_leaf_bh;
+ prev = ocfs2_trailer_from_bh(bh, dir->i_sb);
+ prev->db_free_next = trailer->db_free_next;
+ }
+
+ trailer->db_free_rec_len = cpu_to_le16(0);
+ trailer->db_free_next = cpu_to_le64(0);
+
+ ocfs2_journal_dirty(handle, bh);
+ ocfs2_journal_dirty(handle, lookup->dl_leaf_bh);
+}
+
+/*
+ * This expects that a journal write has been reserved on
+ * lookup->dl_prev_leaf_bh or lookup->dl_dx_root_bh
+ */
+static void ocfs2_recalc_free_list(struct inode *dir, handle_t *handle,
+ struct ocfs2_dir_lookup_result *lookup)
+{
+ int max_rec_len;
+ struct ocfs2_dir_block_trailer *trailer;
+
+ /* Walk dl_leaf_bh to figure out what the new free rec_len is. */
+ max_rec_len = ocfs2_find_max_rec_len(dir->i_sb, lookup->dl_leaf_bh);
+ if (max_rec_len) {
+ /*
+ * There's still room in this block, so no need to remove it
+ * from the free list. In this case, we just want to update
+ * the rec len accounting.
+ */
+ trailer = ocfs2_trailer_from_bh(lookup->dl_leaf_bh, dir->i_sb);
+ trailer->db_free_rec_len = cpu_to_le16(max_rec_len);
+ ocfs2_journal_dirty(handle, lookup->dl_leaf_bh);
+ } else {
+ ocfs2_remove_block_from_free_list(dir, handle, lookup);
+ }
}
/* we don't always have a dentry for what we want to add, so people
if (!namelen)
return -EINVAL;
- if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
+ if (ocfs2_dir_indexed(dir)) {
+ struct buffer_head *bh;
+
+ /*
+ * An indexed dir may require that we update the free space
+ * list. Reserve a write to the previous node in the list so
+ * that we don't fail later.
+ *
+ * XXX: This can be either a dx_root_block, or an unindexed
+ * directory tree leaf block.
+ */
+ if (ocfs2_free_list_at_root(lookup)) {
+ bh = lookup->dl_dx_root_bh;
+ retval = ocfs2_journal_access_dr(handle,
+ INODE_CACHE(dir), bh,
+ OCFS2_JOURNAL_ACCESS_WRITE);
+ } else {
+ bh = lookup->dl_prev_leaf_bh;
+ retval = ocfs2_journal_access_db(handle,
+ INODE_CACHE(dir), bh,
+ OCFS2_JOURNAL_ACCESS_WRITE);
+ }
+ if (retval) {
+ mlog_errno(retval);
+ return retval;
+ }
+ } else if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
data_start = di->id2.i_data.id_data;
size = i_size_read(dir);
}
if (insert_bh == parent_fe_bh)
- status = ocfs2_journal_access_di(handle, dir,
+ status = ocfs2_journal_access_di(handle,
+ INODE_CACHE(dir),
insert_bh,
OCFS2_JOURNAL_ACCESS_WRITE);
else {
- status = ocfs2_journal_access_db(handle, dir,
+ status = ocfs2_journal_access_db(handle,
+ INODE_CACHE(dir),
insert_bh,
OCFS2_JOURNAL_ACCESS_WRITE);
de->name_len = namelen;
memcpy(de->name, name, namelen);
+ if (ocfs2_dir_indexed(dir))
+ ocfs2_recalc_free_list(dir, handle, lookup);
+
dir->i_version++;
status = ocfs2_journal_dirty(handle, insert_bh);
retval = 0;
unsigned seen_dot;
unsigned seen_dot_dot;
unsigned seen_other;
+ unsigned dx_dir;
};
static int ocfs2_empty_dir_filldir(void *priv, const char *name, int name_len,
loff_t pos, u64 ino, unsigned type)
/*
* Check the positions of "." and ".." records to be sure
* they're in the correct place.
+ *
+ * Indexed directories don't need to proceed past the first
+ * two entries, so we end the scan after seeing '..'. Despite
+ * that, we allow the scan to proceed In the event that we
+ * have a corrupted indexed directory (no dot or dot dot
+ * entries). This allows us to double check for existing
+ * entries which might not have been found in the index.
*/
if (name_len == 1 && !strncmp(".", name, 1) && pos == 0) {
p->seen_dot = 1;
if (name_len == 2 && !strncmp("..", name, 2) &&
pos == OCFS2_DIR_REC_LEN(1)) {
p->seen_dot_dot = 1;
+
+ if (p->dx_dir && p->seen_dot)
+ return 1;
+
return 0;
}
p->seen_other = 1;
return 1;
}
+
+static int ocfs2_empty_dir_dx(struct inode *inode,
+ struct ocfs2_empty_dir_priv *priv)
+{
+ int ret;
+ struct buffer_head *di_bh = NULL;
+ struct buffer_head *dx_root_bh = NULL;
+ struct ocfs2_dinode *di;
+ struct ocfs2_dx_root_block *dx_root;
+
+ priv->dx_dir = 1;
+
+ ret = ocfs2_read_inode_block(inode, &di_bh);
+ if (ret) {
+ mlog_errno(ret);
+ goto out;
+ }
+ di = (struct ocfs2_dinode *)di_bh->b_data;
+
+ ret = ocfs2_read_dx_root(inode, di, &dx_root_bh);
+ if (ret) {
+ mlog_errno(ret);
+ goto out;
+ }
+ dx_root = (struct ocfs2_dx_root_block *)dx_root_bh->b_data;
+
+ if (le32_to_cpu(dx_root->dr_num_entries) != 2)
+ priv->seen_other = 1;
+
+out:
+ brelse(di_bh);
+ brelse(dx_root_bh);
+ return ret;
+}
+
/*
* routine to check that the specified directory is empty (for rmdir)
*
* Returns 1 if dir is empty, zero otherwise.
*
- * XXX: This is a performance problem
+ * XXX: This is a performance problem for unindexed directories.
*/
int ocfs2_empty_dir(struct inode *inode)
{
memset(&priv, 0, sizeof(priv));
+ if (ocfs2_dir_indexed(inode)) {
+ ret = ocfs2_empty_dir_dx(inode, &priv);
+ if (ret)
+ mlog_errno(ret);
+ /*
+ * We still run ocfs2_dir_foreach to get the checks
+ * for "." and "..".
+ */
+ }
+
ret = ocfs2_dir_foreach(inode, &start, &priv, ocfs2_empty_dir_filldir);
if (ret)
mlog_errno(ret);
struct ocfs2_inline_data *data = &di->id2.i_data;
unsigned int size = le16_to_cpu(data->id_count);
- ret = ocfs2_journal_access_di(handle, inode, di_bh,
+ ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), di_bh,
OCFS2_JOURNAL_ACCESS_WRITE);
if (ret) {
mlog_errno(ret);
mlog_entry_void();
- if (ocfs2_supports_dir_trailer(osb))
+ if (ocfs2_new_dir_wants_trailer(inode))
size = ocfs2_dir_trailer_blk_off(parent->i_sb);
status = ocfs2_do_extend_dir(osb->sb, handle, inode, fe_bh,
goto bail;
}
- ocfs2_set_new_buffer_uptodate(inode, new_bh);
+ ocfs2_set_new_buffer_uptodate(INODE_CACHE(inode), new_bh);
- status = ocfs2_journal_access_db(handle, inode, new_bh,
+ status = ocfs2_journal_access_db(handle, INODE_CACHE(inode), new_bh,
OCFS2_JOURNAL_ACCESS_CREATE);
if (status < 0) {
mlog_errno(status);
memset(new_bh->b_data, 0, osb->sb->s_blocksize);
de = ocfs2_fill_initial_dirents(inode, parent, new_bh->b_data, size);
- if (ocfs2_supports_dir_trailer(osb))
- ocfs2_init_dir_trailer(inode, new_bh);
+ if (ocfs2_new_dir_wants_trailer(inode)) {
+ int size = le16_to_cpu(de->rec_len);
+
+ /*
+ * Figure out the size of the hole left over after
+ * insertion of '.' and '..'. The trailer wants this
+ * information.
+ */
+ size -= OCFS2_DIR_REC_LEN(2);
+ size -= sizeof(struct ocfs2_dir_block_trailer);
+
+ ocfs2_init_dir_trailer(inode, new_bh, size);
+ }
status = ocfs2_journal_dirty(handle, new_bh);
if (status < 0) {
static int ocfs2_dx_dir_attach_index(struct ocfs2_super *osb,
handle_t *handle, struct inode *dir,
struct buffer_head *di_bh,
+ struct buffer_head *dirdata_bh,
struct ocfs2_alloc_context *meta_ac,
- int dx_inline,
+ int dx_inline, u32 num_entries,
struct buffer_head **ret_dx_root_bh)
{
int ret;
unsigned int num_bits;
struct buffer_head *dx_root_bh = NULL;
struct ocfs2_dx_root_block *dx_root;
+ struct ocfs2_dir_block_trailer *trailer =
+ ocfs2_trailer_from_bh(dirdata_bh, dir->i_sb);
ret = ocfs2_claim_metadata(osb, handle, meta_ac, 1, &dr_suballoc_bit,
&num_bits, &dr_blkno);
ret = -EIO;
goto out;
}
- ocfs2_set_new_buffer_uptodate(dir, dx_root_bh);
+ ocfs2_set_new_buffer_uptodate(INODE_CACHE(dir), dx_root_bh);
- ret = ocfs2_journal_access_dr(handle, dir, dx_root_bh,
+ ret = ocfs2_journal_access_dr(handle, INODE_CACHE(dir), dx_root_bh,
OCFS2_JOURNAL_ACCESS_CREATE);
if (ret < 0) {
mlog_errno(ret);
dx_root = (struct ocfs2_dx_root_block *)dx_root_bh->b_data;
memset(dx_root, 0, osb->sb->s_blocksize);
strcpy(dx_root->dr_signature, OCFS2_DX_ROOT_SIGNATURE);
- dx_root->dr_suballoc_slot = cpu_to_le16(osb->slot_num);
+ dx_root->dr_suballoc_slot = cpu_to_le16(meta_ac->ac_alloc_slot);
dx_root->dr_suballoc_bit = cpu_to_le16(dr_suballoc_bit);
dx_root->dr_fs_generation = cpu_to_le32(osb->fs_generation);
dx_root->dr_blkno = cpu_to_le64(dr_blkno);
dx_root->dr_dir_blkno = cpu_to_le64(OCFS2_I(dir)->ip_blkno);
+ dx_root->dr_num_entries = cpu_to_le32(num_entries);
+ if (le16_to_cpu(trailer->db_free_rec_len))
+ dx_root->dr_free_blk = cpu_to_le64(dirdata_bh->b_blocknr);
+ else
+ dx_root->dr_free_blk = cpu_to_le64(0);
if (dx_inline) {
dx_root->dr_flags |= OCFS2_DX_FLAG_INLINE;
if (ret)
mlog_errno(ret);
- ret = ocfs2_journal_access_di(handle, dir, di_bh,
+ ret = ocfs2_journal_access_di(handle, INODE_CACHE(dir), di_bh,
OCFS2_JOURNAL_ACCESS_CREATE);
if (ret) {
mlog_errno(ret);
}
dx_leaves[i] = bh;
- ocfs2_set_new_buffer_uptodate(dir, bh);
+ ocfs2_set_new_buffer_uptodate(INODE_CACHE(dir), bh);
- ret = ocfs2_journal_access_dl(handle, dir, bh,
+ ret = ocfs2_journal_access_dl(handle, INODE_CACHE(dir), bh,
OCFS2_JOURNAL_ACCESS_CREATE);
if (ret < 0) {
mlog_errno(ret);
{
int ret;
u64 phys_blkno;
- struct ocfs2_super *osb = OCFS2_SB(dir->i_sb);
ret = __ocfs2_dx_dir_new_cluster(dir, cpos, handle, data_ac, dx_leaves,
num_dx_leaves, &phys_blkno);
goto out;
}
- ret = ocfs2_insert_extent(osb, handle, dir, et, cpos, phys_blkno, 1, 0,
+ ret = ocfs2_insert_extent(handle, et, cpos, phys_blkno, 1, 0,
meta_ac);
if (ret)
mlog_errno(ret);
goto out;
}
- ret = ocfs2_dx_dir_attach_index(osb, handle, inode, di_bh,
- meta_ac, 1, &dx_root_bh);
+ ret = ocfs2_dx_dir_attach_index(osb, handle, inode, di_bh, leaf_bh,
+ meta_ac, 1, 2, &dx_root_bh);
if (ret) {
mlog_errno(ret);
goto out;
entry_list = &dx_root->dr_entries;
/* Buffer has been journaled for us by ocfs2_dx_dir_attach_index */
+ ocfs2_dx_dir_name_hash(inode, ".", 1, &hinfo);
ocfs2_dx_entry_list_insert(entry_list, &hinfo, leaf_bh->b_blocknr);
ocfs2_dx_dir_name_hash(inode, "..", 2, &hinfo);
handle_t *handle,
struct buffer_head **dx_leaves,
int num_dx_leaves,
+ u32 *num_dx_entries,
struct buffer_head *dirent_bh)
{
- int ret, namelen, i;
+ int ret = 0, namelen, i;
char *de_buf, *limit;
struct ocfs2_dir_entry *de;
struct buffer_head *dx_leaf_bh;
goto out;
}
+ *num_dx_entries = *num_dx_entries + 1;
+
inc:
de_buf += le16_to_cpu(de->rec_len);
}
out:
return ret;
}
- /*
+
+/*
* XXX: This expects dx_root_bh to already be part of the transaction.
*/
static void ocfs2_dx_dir_index_root_block(struct inode *dir,
ocfs2_dx_entry_list_insert(&dx_root->dr_entries, &hinfo,
dirent_blk);
+
+ le32_add_cpu(&dx_root->dr_num_entries, 1);
inc:
de_buf += le16_to_cpu(de->rec_len);
}
* expansion from an inline directory to one with extents. The first dir block
* in that case is taken from the inline data portion of the inode block.
*
+ * This will also return the largest amount of contiguous space for a dirent
+ * in the block. That value is *not* necessarily the last dirent, even after
+ * expansion. The directory indexing code wants this value for free space
+ * accounting. We do this here since we're already walking the entire dir
+ * block.
+ *
* We add the dir trailer if this filesystem wants it.
*/
-static void ocfs2_expand_last_dirent(char *start, unsigned int old_size,
- struct super_block *sb)
+static unsigned int ocfs2_expand_last_dirent(char *start, unsigned int old_size,
+ struct inode *dir)
{
+ struct super_block *sb = dir->i_sb;
struct ocfs2_dir_entry *de;
struct ocfs2_dir_entry *prev_de;
char *de_buf, *limit;
unsigned int new_size = sb->s_blocksize;
- unsigned int bytes;
+ unsigned int bytes, this_hole;
+ unsigned int largest_hole = 0;
- if (ocfs2_supports_dir_trailer(OCFS2_SB(sb)))
+ if (ocfs2_new_dir_wants_trailer(dir))
new_size = ocfs2_dir_trailer_blk_off(sb);
bytes = new_size - old_size;
de_buf = start;
de = (struct ocfs2_dir_entry *)de_buf;
do {
+ this_hole = ocfs2_figure_dirent_hole(de);
+ if (this_hole > largest_hole)
+ largest_hole = this_hole;
+
prev_de = de;
de_buf += le16_to_cpu(de->rec_len);
de = (struct ocfs2_dir_entry *)de_buf;
} while (de_buf < limit);
le16_add_cpu(&prev_de->rec_len, bytes);
+
+ /* We need to double check this after modification of the final
+ * dirent. */
+ this_hole = ocfs2_figure_dirent_hole(prev_de);
+ if (this_hole > largest_hole)
+ largest_hole = this_hole;
+
+ if (largest_hole >= OCFS2_DIR_MIN_REC_LEN)
+ return largest_hole;
+ return 0;
}
/*
struct ocfs2_dir_lookup_result *lookup,
struct buffer_head **first_block_bh)
{
- u32 alloc, dx_alloc, bit_off, len;
+ u32 alloc, dx_alloc, bit_off, len, num_dx_entries = 0;
struct super_block *sb = dir->i_sb;
int ret, i, num_dx_leaves = 0, dx_inline = 0,
credits = ocfs2_inline_to_extents_credits(sb);
struct ocfs2_extent_tree dx_et;
int did_quota = 0, bytes_allocated = 0;
- ocfs2_init_dinode_extent_tree(&et, dir, di_bh);
+ ocfs2_init_dinode_extent_tree(&et, INODE_CACHE(dir), di_bh);
alloc = ocfs2_clusters_for_bytes(sb, bytes);
dx_alloc = 0;
+ down_write(&oi->ip_alloc_sem);
+
if (ocfs2_supports_indexed_dirs(osb)) {
credits += ocfs2_add_dir_index_credits(sb);
*/
BUG_ON(alloc > 2);
- ret = ocfs2_reserve_clusters(osb, alloc, &data_ac);
+ ret = ocfs2_reserve_clusters(osb, alloc + dx_alloc, &data_ac);
if (ret) {
mlog_errno(ret);
goto out;
}
- down_write(&oi->ip_alloc_sem);
-
/*
* Prepare for worst case allocation scenario of two separate
* extents in the unindexed tree.
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
mlog_errno(ret);
- goto out_sem;
+ goto out;
}
- if (vfs_dq_alloc_space_nodirty(dir,
- ocfs2_clusters_to_bytes(osb->sb,
- alloc + dx_alloc))) {
- ret = -EDQUOT;
+ ret = dquot_alloc_space_nodirty(dir,
+ ocfs2_clusters_to_bytes(osb->sb, alloc + dx_alloc));
+ if (ret)
goto out_commit;
- }
did_quota = 1;
if (ocfs2_supports_indexed_dirs(osb) && !dx_inline) {
goto out_commit;
}
- ocfs2_set_new_buffer_uptodate(dir, dirdata_bh);
+ ocfs2_set_new_buffer_uptodate(INODE_CACHE(dir), dirdata_bh);
- ret = ocfs2_journal_access_db(handle, dir, dirdata_bh,
+ ret = ocfs2_journal_access_db(handle, INODE_CACHE(dir), dirdata_bh,
OCFS2_JOURNAL_ACCESS_CREATE);
if (ret) {
mlog_errno(ret);
memcpy(dirdata_bh->b_data, di->id2.i_data.id_data, i_size_read(dir));
memset(dirdata_bh->b_data + i_size_read(dir), 0,
sb->s_blocksize - i_size_read(dir));
- ocfs2_expand_last_dirent(dirdata_bh->b_data, i_size_read(dir), sb);
- if (ocfs2_supports_dir_trailer(osb))
- ocfs2_init_dir_trailer(dir, dirdata_bh);
+ i = ocfs2_expand_last_dirent(dirdata_bh->b_data, i_size_read(dir), dir);
+ if (ocfs2_new_dir_wants_trailer(dir)) {
+ /*
+ * Prepare the dir trailer up front. It will otherwise look
+ * like a valid dirent. Even if inserting the index fails
+ * (unlikely), then all we'll have done is given first dir
+ * block a small amount of fragmentation.
+ */
+ ocfs2_init_dir_trailer(dir, dirdata_bh, i);
+ }
ret = ocfs2_journal_dirty(handle, dirdata_bh);
if (ret) {
/*
* Dx dirs with an external cluster need to do this up
* front. Inline dx root's get handled later, after
- * we've allocated our root block.
+ * we've allocated our root block. We get passed back
+ * a total number of items so that dr_num_entries can
+ * be correctly set once the dx_root has been
+ * allocated.
*/
ret = ocfs2_dx_dir_index_block(dir, handle, dx_leaves,
- num_dx_leaves, dirdata_bh);
+ num_dx_leaves, &num_dx_entries,
+ dirdata_bh);
if (ret) {
mlog_errno(ret);
goto out_commit;
* We let the later dirent insert modify c/mtime - to the user
* the data hasn't changed.
*/
- ret = ocfs2_journal_access_di(handle, dir, di_bh,
+ ret = ocfs2_journal_access_di(handle, INODE_CACHE(dir), di_bh,
OCFS2_JOURNAL_ACCESS_CREATE);
if (ret) {
mlog_errno(ret);
* This should never fail as our extent list is empty and all
* related blocks have been journaled already.
*/
- ret = ocfs2_insert_extent(osb, handle, dir, &et, 0, blkno, len,
+ ret = ocfs2_insert_extent(handle, &et, 0, blkno, len,
0, NULL);
if (ret) {
mlog_errno(ret);
if (ocfs2_supports_indexed_dirs(osb)) {
ret = ocfs2_dx_dir_attach_index(osb, handle, dir, di_bh,
- meta_ac, dx_inline,
- &dx_root_bh);
+ dirdata_bh, meta_ac, dx_inline,
+ num_dx_entries, &dx_root_bh);
if (ret) {
mlog_errno(ret);
goto out_commit;
ocfs2_dx_dir_index_root_block(dir, dx_root_bh,
dirdata_bh);
} else {
- ocfs2_init_dx_root_extent_tree(&dx_et, dir, dx_root_bh);
- ret = ocfs2_insert_extent(osb, handle, dir, &dx_et, 0,
+ ocfs2_init_dx_root_extent_tree(&dx_et,
+ INODE_CACHE(dir),
+ dx_root_bh);
+ ret = ocfs2_insert_extent(handle, &dx_et, 0,
dx_insert_blkno, 1, 0, NULL);
if (ret)
mlog_errno(ret);
}
blkno = ocfs2_clusters_to_blocks(dir->i_sb, bit_off);
- ret = ocfs2_insert_extent(osb, handle, dir, &et, 1,
+ ret = ocfs2_insert_extent(handle, &et, 1,
blkno, len, 0, NULL);
if (ret) {
mlog_errno(ret);
out_commit:
if (ret < 0 && did_quota)
- vfs_dq_free_space_nodirty(dir, bytes_allocated);
+ dquot_free_space_nodirty(dir, bytes_allocated);
ocfs2_commit_trans(osb, handle);
-out_sem:
- up_write(&oi->ip_alloc_sem);
-
out:
+ up_write(&oi->ip_alloc_sem);
if (data_ac)
ocfs2_free_alloc_context(data_ac);
if (meta_ac)
if (extend) {
u32 offset = OCFS2_I(dir)->ip_clusters;
- if (vfs_dq_alloc_space_nodirty(dir,
- ocfs2_clusters_to_bytes(sb, 1))) {
- status = -EDQUOT;
+ status = dquot_alloc_space_nodirty(dir,
+ ocfs2_clusters_to_bytes(sb, 1));
+ if (status)
goto bail;
- }
did_quota = 1;
status = ocfs2_add_inode_data(OCFS2_SB(sb), dir, &offset,
status = 0;
bail:
if (did_quota && status < 0)
- vfs_dq_free_space_nodirty(dir, ocfs2_clusters_to_bytes(sb, 1));
+ dquot_free_space_nodirty(dir, ocfs2_clusters_to_bytes(sb, 1));
mlog_exit(status);
return status;
}
* is to be turned into an extent based one. The size of the dirent to
* insert might be larger than the space gained by growing to just one
* block, so we may have to grow the inode by two blocks in that case.
+ *
+ * If the directory is already indexed, dx_root_bh must be provided.
*/
static int ocfs2_extend_dir(struct ocfs2_super *osb,
struct inode *dir,
struct ocfs2_dir_entry * de;
struct super_block *sb = osb->sb;
struct ocfs2_extent_tree et;
+ struct buffer_head *dx_root_bh = lookup->dl_dx_root_bh;
mlog_entry_void();
if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
+ /*
+ * This would be a code error as an inline directory should
+ * never have an index root.
+ */
+ BUG_ON(dx_root_bh);
+
status = ocfs2_expand_inline_dir(dir, parent_fe_bh,
blocks_wanted, lookup,
&new_bh);
goto bail;
}
+ /* Expansion from inline to an indexed directory will
+ * have given us this. */
+ dx_root_bh = lookup->dl_dx_root_bh;
+
if (blocks_wanted == 1) {
/*
* If the new dirent will fit inside the space
brelse(new_bh);
new_bh = NULL;
+ down_write(&OCFS2_I(dir)->ip_alloc_sem);
+ drop_alloc_sem = 1;
dir_i_size = i_size_read(dir);
credits = OCFS2_SIMPLE_DIR_EXTEND_CREDITS;
goto do_extend;
}
+ down_write(&OCFS2_I(dir)->ip_alloc_sem);
+ drop_alloc_sem = 1;
dir_i_size = i_size_read(dir);
mlog(0, "extending dir %llu (i_size = %lld)\n",
(unsigned long long)OCFS2_I(dir)->ip_blkno, dir_i_size);
spin_lock(&OCFS2_I(dir)->ip_lock);
if (dir_i_size == ocfs2_clusters_to_bytes(sb, OCFS2_I(dir)->ip_clusters)) {
spin_unlock(&OCFS2_I(dir)->ip_lock);
- ocfs2_init_dinode_extent_tree(&et, dir, parent_fe_bh);
- num_free_extents = ocfs2_num_free_extents(osb, dir, &et);
+ ocfs2_init_dinode_extent_tree(&et, INODE_CACHE(dir),
+ parent_fe_bh);
+ num_free_extents = ocfs2_num_free_extents(osb, &et);
if (num_free_extents < 0) {
status = num_free_extents;
mlog_errno(status);
}
do_extend:
- down_write(&OCFS2_I(dir)->ip_alloc_sem);
- drop_alloc_sem = 1;
+ if (ocfs2_dir_indexed(dir))
+ credits++; /* For attaching the new dirent block to the
+ * dx_root */
handle = ocfs2_start_trans(osb, credits);
if (IS_ERR(handle)) {
goto bail;
}
- ocfs2_set_new_buffer_uptodate(dir, new_bh);
+ ocfs2_set_new_buffer_uptodate(INODE_CACHE(dir), new_bh);
- status = ocfs2_journal_access_db(handle, dir, new_bh,
+ status = ocfs2_journal_access_db(handle, INODE_CACHE(dir), new_bh,
OCFS2_JOURNAL_ACCESS_CREATE);
if (status < 0) {
mlog_errno(status);
de = (struct ocfs2_dir_entry *) new_bh->b_data;
de->inode = 0;
- if (ocfs2_dir_has_trailer(dir)) {
+ if (ocfs2_supports_dir_trailer(dir)) {
de->rec_len = cpu_to_le16(ocfs2_dir_trailer_blk_off(sb));
- ocfs2_init_dir_trailer(dir, new_bh);
+
+ ocfs2_init_dir_trailer(dir, new_bh, le16_to_cpu(de->rec_len));
+
+ if (ocfs2_dir_indexed(dir)) {
+ status = ocfs2_dx_dir_link_trailer(dir, handle,
+ dx_root_bh, new_bh);
+ if (status) {
+ mlog_errno(status);
+ goto bail;
+ }
+ }
} else {
de->rec_len = cpu_to_le16(sb->s_blocksize);
}
*new_de_bh = new_bh;
get_bh(*new_de_bh);
bail:
- if (drop_alloc_sem)
- up_write(&OCFS2_I(dir)->ip_alloc_sem);
if (handle)
ocfs2_commit_trans(osb, handle);
+ if (drop_alloc_sem)
+ up_write(&OCFS2_I(dir)->ip_alloc_sem);
if (data_ac)
ocfs2_free_alloc_context(data_ac);
* This calculates how many free bytes we'd have in block zero, should
* this function force expansion to an extent tree.
*/
- if (ocfs2_supports_dir_trailer(OCFS2_SB(sb)))
+ if (ocfs2_new_dir_wants_trailer(dir))
free_space = ocfs2_dir_trailer_blk_off(sb) - i_size_read(dir);
else
free_space = dir->i_sb->s_blocksize - i_size_read(dir);
(unsigned long long)OCFS2_I(dir)->ip_blkno,
(unsigned long long)leaf_blkno, insert_hash);
- ocfs2_init_dx_root_extent_tree(&et, dir, dx_root_bh);
+ ocfs2_init_dx_root_extent_tree(&et, INODE_CACHE(dir), dx_root_bh);
dx_root = (struct ocfs2_dx_root_block *)dx_root_bh->b_data;
/*
goto out;
}
- if (vfs_dq_alloc_space_nodirty(dir,
- ocfs2_clusters_to_bytes(dir->i_sb, 1))) {
- ret = -EDQUOT;
+ ret = dquot_alloc_space_nodirty(dir,
+ ocfs2_clusters_to_bytes(dir->i_sb, 1));
+ if (ret)
goto out_commit;
- }
did_quota = 1;
- ret = ocfs2_journal_access_dl(handle, dir, dx_leaf_bh,
+ ret = ocfs2_journal_access_dl(handle, INODE_CACHE(dir), dx_leaf_bh,
OCFS2_JOURNAL_ACCESS_WRITE);
if (ret) {
mlog_errno(ret);
goto out_commit;
}
- orig_leaves_start = leaf_blkno & ~(osb->s_clustersize_bits -
- osb->sb->s_blocksize_bits);
+ orig_leaves_start = ocfs2_block_to_cluster_start(dir->i_sb, leaf_blkno);
ret = ocfs2_read_dx_leaves(dir, orig_leaves_start, num_dx_leaves,
orig_dx_leaves);
if (ret) {
}
for (i = 0; i < num_dx_leaves; i++) {
- ret = ocfs2_journal_access_dl(handle, dir, orig_dx_leaves[i],
+ ret = ocfs2_journal_access_dl(handle, INODE_CACHE(dir),
+ orig_dx_leaves[i],
OCFS2_JOURNAL_ACCESS_WRITE);
if (ret) {
mlog_errno(ret);
out_commit:
if (ret < 0 && did_quota)
- vfs_dq_free_space_nodirty(dir,
+ dquot_free_space_nodirty(dir,
ocfs2_clusters_to_bytes(dir->i_sb, 1));
ocfs2_commit_trans(osb, handle);
return ret;
}
+static int ocfs2_find_dir_space_dx(struct ocfs2_super *osb, struct inode *dir,
+ struct buffer_head *di_bh,
+ struct buffer_head *dx_root_bh,
+ const char *name, int namelen,
+ struct ocfs2_dir_lookup_result *lookup)
+{
+ int ret, rebalanced = 0;
+ struct ocfs2_dx_root_block *dx_root;
+ struct buffer_head *dx_leaf_bh = NULL;
+ struct ocfs2_dx_leaf *dx_leaf;
+ u64 blkno;
+ u32 leaf_cpos;
+
+ dx_root = (struct ocfs2_dx_root_block *)dx_root_bh->b_data;
+
+restart_search:
+ ret = ocfs2_dx_dir_lookup(dir, &dx_root->dr_list, &lookup->dl_hinfo,
+ &leaf_cpos, &blkno);
+ if (ret) {
+ mlog_errno(ret);
+ goto out;
+ }
+
+ ret = ocfs2_read_dx_leaf(dir, blkno, &dx_leaf_bh);
+ if (ret) {
+ mlog_errno(ret);
+ goto out;
+ }
+
+ dx_leaf = (struct ocfs2_dx_leaf *)dx_leaf_bh->b_data;
+
+ if (le16_to_cpu(dx_leaf->dl_list.de_num_used) >=
+ le16_to_cpu(dx_leaf->dl_list.de_count)) {
+ if (rebalanced) {
+ /*
+ * Rebalancing should have provided us with
+ * space in an appropriate leaf.
+ *
+ * XXX: Is this an abnormal condition then?
+ * Should we print a message here?
+ */
+ ret = -ENOSPC;
+ goto out;
+ }
+
+ ret = ocfs2_dx_dir_rebalance(osb, dir, dx_root_bh, dx_leaf_bh,
+ &lookup->dl_hinfo, leaf_cpos,
+ blkno);
+ if (ret) {
+ if (ret != -ENOSPC)
+ mlog_errno(ret);
+ goto out;
+ }
+
+ /*
+ * Restart the lookup. The rebalance might have
+ * changed which block our item fits into. Mark our
+ * progress, so we only execute this once.
+ */
+ brelse(dx_leaf_bh);
+ dx_leaf_bh = NULL;
+ rebalanced = 1;
+ goto restart_search;
+ }
+
+ lookup->dl_dx_leaf_bh = dx_leaf_bh;
+ dx_leaf_bh = NULL;
+
+out:
+ brelse(dx_leaf_bh);
+ return ret;
+}
+
+static int ocfs2_search_dx_free_list(struct inode *dir,
+ struct buffer_head *dx_root_bh,
+ int namelen,
+ struct ocfs2_dir_lookup_result *lookup)
+{
+ int ret = -ENOSPC;
+ struct buffer_head *leaf_bh = NULL, *prev_leaf_bh = NULL;
+ struct ocfs2_dir_block_trailer *db;
+ u64 next_block;
+ int rec_len = OCFS2_DIR_REC_LEN(namelen);
+ struct ocfs2_dx_root_block *dx_root;
+
+ dx_root = (struct ocfs2_dx_root_block *)dx_root_bh->b_data;
+ next_block = le64_to_cpu(dx_root->dr_free_blk);
+
+ while (next_block) {
+ brelse(prev_leaf_bh);
+ prev_leaf_bh = leaf_bh;
+ leaf_bh = NULL;
+
+ ret = ocfs2_read_dir_block_direct(dir, next_block, &leaf_bh);
+ if (ret) {
+ mlog_errno(ret);
+ goto out;
+ }
+
+ db = ocfs2_trailer_from_bh(leaf_bh, dir->i_sb);
+ if (rec_len <= le16_to_cpu(db->db_free_rec_len)) {
+ lookup->dl_leaf_bh = leaf_bh;
+ lookup->dl_prev_leaf_bh = prev_leaf_bh;
+ leaf_bh = NULL;
+ prev_leaf_bh = NULL;
+ break;
+ }
+
+ next_block = le64_to_cpu(db->db_free_next);
+ }
+
+ if (!next_block)
+ ret = -ENOSPC;
+
+out:
+
+ brelse(leaf_bh);
+ brelse(prev_leaf_bh);
+ return ret;
+}
+
static int ocfs2_expand_inline_dx_root(struct inode *dir,
struct buffer_head *dx_root_bh)
{
goto out;
}
- if (vfs_dq_alloc_space_nodirty(dir,
- ocfs2_clusters_to_bytes(osb->sb, 1))) {
- ret = -EDQUOT;
+ ret = dquot_alloc_space_nodirty(dir,
+ ocfs2_clusters_to_bytes(osb->sb, 1));
+ if (ret)
goto out_commit;
- }
did_quota = 1;
/*
* failure to add the dx_root_bh to the journal won't result
* us losing clusters.
*/
- ret = ocfs2_journal_access_dr(handle, dir, dx_root_bh,
+ ret = ocfs2_journal_access_dr(handle, INODE_CACHE(dir), dx_root_bh,
OCFS2_JOURNAL_ACCESS_WRITE);
if (ret) {
mlog_errno(ret);
/* This should never fail considering we start with an empty
* dx_root. */
- ocfs2_init_dx_root_extent_tree(&et, dir, dx_root_bh);
- ret = ocfs2_insert_extent(osb, handle, dir, &et, 0,
- insert_blkno, 1, 0, NULL);
+ ocfs2_init_dx_root_extent_tree(&et, INODE_CACHE(dir), dx_root_bh);
+ ret = ocfs2_insert_extent(handle, &et, 0, insert_blkno, 1, 0, NULL);
if (ret)
mlog_errno(ret);
did_quota = 0;
out_commit:
if (ret < 0 && did_quota)
- vfs_dq_free_space_nodirty(dir,
+ dquot_free_space_nodirty(dir,
ocfs2_clusters_to_bytes(dir->i_sb, 1));
ocfs2_commit_trans(osb, handle);
return 0;
}
-static int ocfs2_find_dir_space_dx(struct ocfs2_super *osb, struct inode *dir,
- struct buffer_head *di_bh, const char *name,
- int namelen,
- struct ocfs2_dir_lookup_result *lookup)
+static int ocfs2_prepare_dx_dir_for_insert(struct inode *dir,
+ struct buffer_head *di_bh,
+ const char *name,
+ int namelen,
+ struct ocfs2_dir_lookup_result *lookup)
{
- int ret, rebalanced = 0;
+ int ret, free_dx_root = 1;
+ struct ocfs2_super *osb = OCFS2_SB(dir->i_sb);
struct buffer_head *dx_root_bh = NULL;
- struct ocfs2_dx_root_block *dx_root;
- struct buffer_head *dx_leaf_bh = NULL;
- struct ocfs2_dx_leaf *dx_leaf;
+ struct buffer_head *leaf_bh = NULL;
struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
- u64 blkno;
- u32 leaf_cpos;
+ struct ocfs2_dx_root_block *dx_root;
ret = ocfs2_read_dx_root(dir, di, &dx_root_bh);
if (ret) {
}
dx_root = (struct ocfs2_dx_root_block *)dx_root_bh->b_data;
+ if (le32_to_cpu(dx_root->dr_num_entries) == OCFS2_DX_ENTRIES_MAX) {
+ ret = -ENOSPC;
+ mlog_errno(ret);
+ goto out;
+ }
+
if (ocfs2_dx_root_inline(dx_root)) {
ret = ocfs2_inline_dx_has_space(dx_root_bh);
}
}
-restart_search:
- ret = ocfs2_dx_dir_lookup(dir, &dx_root->dr_list, &lookup->dl_hinfo,
- &leaf_cpos, &blkno);
+ /*
+ * Insert preparation for an indexed directory is split into two
+ * steps. The call to find_dir_space_dx reserves room in the index for
+ * an additional item. If we run out of space there, it's a real error
+ * we can't continue on.
+ */
+ ret = ocfs2_find_dir_space_dx(osb, dir, di_bh, dx_root_bh, name,
+ namelen, lookup);
if (ret) {
mlog_errno(ret);
goto out;
}
- ret = ocfs2_read_dx_leaf(dir, blkno, &dx_leaf_bh);
- if (ret) {
+search_el:
+ /*
+ * Next, we need to find space in the unindexed tree. This call
+ * searches using the free space linked list. If the unindexed tree
+ * lacks sufficient space, we'll expand it below. The expansion code
+ * is smart enough to add any new blocks to the free space list.
+ */
+ ret = ocfs2_search_dx_free_list(dir, dx_root_bh, namelen, lookup);
+ if (ret && ret != -ENOSPC) {
mlog_errno(ret);
goto out;
}
- dx_leaf = (struct ocfs2_dx_leaf *)dx_leaf_bh->b_data;
+ /* Do this up here - ocfs2_extend_dir might need the dx_root */
+ lookup->dl_dx_root_bh = dx_root_bh;
+ free_dx_root = 0;
- if (le16_to_cpu(dx_leaf->dl_list.de_num_used) >=
- le16_to_cpu(dx_leaf->dl_list.de_count)) {
- if (rebalanced) {
- /*
- * Rebalancing should have provided us with
- * space in an appropriate leaf.
- *
- * XXX: Is this an abnormal condition then?
- * Should we print a message here?
- */
- ret = -ENOSPC;
- goto out;
- }
+ if (ret == -ENOSPC) {
+ ret = ocfs2_extend_dir(osb, dir, di_bh, 1, lookup, &leaf_bh);
- ret = ocfs2_dx_dir_rebalance(osb, dir, dx_root_bh, dx_leaf_bh,
- &lookup->dl_hinfo, leaf_cpos,
- blkno);
if (ret) {
- if (ret != -ENOSPC)
- mlog_errno(ret);
+ mlog_errno(ret);
goto out;
}
/*
- * Restart the lookup. The rebalance might have
- * changed which block our item fits into. Mark our
- * progress, so we only execute this once.
+ * We make the assumption here that new leaf blocks are added
+ * to the front of our free list.
*/
- brelse(dx_leaf_bh);
- dx_leaf_bh = NULL;
- rebalanced = 1;
- goto restart_search;
+ lookup->dl_prev_leaf_bh = NULL;
+ lookup->dl_leaf_bh = leaf_bh;
}
-search_el:
- lookup->dl_dx_leaf_bh = dx_leaf_bh;
- dx_leaf_bh = NULL;
- lookup->dl_dx_root_bh = dx_root_bh;
- dx_root_bh = NULL;
-
out:
- brelse(dx_leaf_bh);
- brelse(dx_root_bh);
+ if (free_dx_root)
+ brelse(dx_root_bh);
return ret;
}
ocfs2_dx_dir_name_hash(dir, name, namelen, &lookup->dl_hinfo);
if (ocfs2_dir_indexed(dir)) {
- ret = ocfs2_find_dir_space_dx(osb, dir, parent_fe_bh, name,
- namelen, lookup);
- if (ret) {
+ ret = ocfs2_prepare_dx_dir_for_insert(dir, parent_fe_bh,
+ name, namelen, lookup);
+ if (ret)
mlog_errno(ret);
- goto out;
- }
-
- /*
- * We intentionally fall through so that the unindexed
- * tree can also be prepared.
- */
+ goto out;
}
if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
goto out_unlock;
}
- ret = ocfs2_journal_access_di(handle, dir, di_bh,
+ ret = ocfs2_journal_access_di(handle, INODE_CACHE(dir), di_bh,
OCFS2_JOURNAL_ACCESS_WRITE);
if (ret) {
mlog_errno(ret);
if (ocfs2_dx_root_inline(dx_root))
goto remove_index;
- ocfs2_init_dx_root_extent_tree(&et, dir, dx_root_bh);
+ ocfs2_init_dx_root_extent_tree(&et, INODE_CACHE(dir), dx_root_bh);
/* XXX: What if dr_clusters is too large? */
while (le32_to_cpu(dx_root->dr_clusters)) {
goto out;
}
- ocfs2_remove_from_cache(dir, dx_root_bh);
+ ocfs2_remove_from_cache(INODE_CACHE(dir), dx_root_bh);
out:
ocfs2_schedule_truncate_log_flush(osb, 1);
ocfs2_run_deallocs(osb, &dealloc);