+meta_guess:
+ /* calculate metadata allocation. */
+ if (di->i_xattr_loc) {
+ if (!xbs->xattr_bh) {
+ ret = ocfs2_read_xattr_block(inode,
+ le64_to_cpu(di->i_xattr_loc),
+ &bh);
+ if (ret) {
+ mlog_errno(ret);
+ goto out;
+ }
+
+ xb = (struct ocfs2_xattr_block *)bh->b_data;
+ } else
+ xb = (struct ocfs2_xattr_block *)xbs->xattr_bh->b_data;
+
+ /*
+ * If there is already an xattr tree, good, we can calculate
+ * like other b-trees. Otherwise we may have the chance of
+ * create a tree, the credit calculation is borrowed from
+ * ocfs2_calc_extend_credits with root_el = NULL. And the
+ * new tree will be cluster based, so no meta is needed.
+ */
+ if (le16_to_cpu(xb->xb_flags) & OCFS2_XATTR_INDEXED) {
+ struct ocfs2_extent_list *el =
+ &xb->xb_attrs.xb_root.xt_list;
+ meta_add += ocfs2_extend_meta_needed(el);
+ credits += ocfs2_calc_extend_credits(inode->i_sb,
+ el, 1);
+ } else
+ credits += OCFS2_SUBALLOC_ALLOC + 1;
+
+ /*
+ * This cluster will be used either for new bucket or for
+ * new xattr block.
+ * If the cluster size is the same as the bucket size, one
+ * more is needed since we may need to extend the bucket
+ * also.
+ */
+ clusters_add += 1;
+ credits += ocfs2_blocks_per_xattr_bucket(inode->i_sb);
+ if (OCFS2_XATTR_BUCKET_SIZE ==
+ OCFS2_SB(inode->i_sb)->s_clustersize) {
+ credits += ocfs2_blocks_per_xattr_bucket(inode->i_sb);
+ clusters_add += 1;
+ }
+ } else {
+ meta_add += 1;
+ credits += OCFS2_XATTR_BLOCK_CREATE_CREDITS;
+ }
+out:
+ if (clusters_need)
+ *clusters_need = clusters_add;
+ if (meta_need)
+ *meta_need = meta_add;
+ if (credits_need)
+ *credits_need = credits;
+ brelse(bh);
+ return ret;
+}
+
+static int ocfs2_init_xattr_set_ctxt(struct inode *inode,
+ struct ocfs2_dinode *di,
+ struct ocfs2_xattr_info *xi,
+ struct ocfs2_xattr_search *xis,
+ struct ocfs2_xattr_search *xbs,
+ struct ocfs2_xattr_set_ctxt *ctxt,
+ int extra_meta,
+ int *credits)
+{
+ int clusters_add, meta_add, ret;
+ struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+
+ memset(ctxt, 0, sizeof(struct ocfs2_xattr_set_ctxt));
+
+ ocfs2_init_dealloc_ctxt(&ctxt->dealloc);
+
+ ret = ocfs2_calc_xattr_set_need(inode, di, xi, xis, xbs,
+ &clusters_add, &meta_add, credits);
+ if (ret) {
+ mlog_errno(ret);
+ return ret;
+ }
+
+ meta_add += extra_meta;
+ mlog(0, "Set xattr %s, reserve meta blocks = %d, clusters = %d, "
+ "credits = %d\n", xi->xi_name, meta_add, clusters_add, *credits);
+
+ if (meta_add) {
+ ret = ocfs2_reserve_new_metadata_blocks(osb, meta_add,
+ &ctxt->meta_ac);
+ if (ret) {
+ mlog_errno(ret);
+ goto out;
+ }
+ }
+
+ if (clusters_add) {
+ ret = ocfs2_reserve_clusters(osb, clusters_add, &ctxt->data_ac);
+ if (ret)
+ mlog_errno(ret);
+ }
+out:
+ if (ret) {
+ if (ctxt->meta_ac) {
+ ocfs2_free_alloc_context(ctxt->meta_ac);
+ ctxt->meta_ac = NULL;
+ }
+
+ /*
+ * We cannot have an error and a non null ctxt->data_ac.
+ */
+ }
+
+ return ret;
+}
+
+static int __ocfs2_xattr_set_handle(struct inode *inode,
+ struct ocfs2_dinode *di,
+ struct ocfs2_xattr_info *xi,
+ struct ocfs2_xattr_search *xis,
+ struct ocfs2_xattr_search *xbs,
+ struct ocfs2_xattr_set_ctxt *ctxt)
+{
+ int ret = 0, credits, old_found;
+
+ if (!xi->xi_value) {
+ /* Remove existing extended attribute */
+ if (!xis->not_found)
+ ret = ocfs2_xattr_ibody_set(inode, xi, xis, ctxt);
+ else if (!xbs->not_found)
+ ret = ocfs2_xattr_block_set(inode, xi, xbs, ctxt);
+ } else {
+ /* We always try to set extended attribute into inode first*/
+ ret = ocfs2_xattr_ibody_set(inode, xi, xis, ctxt);
+ if (!ret && !xbs->not_found) {
+ /*
+ * If succeed and that extended attribute existing in
+ * external block, then we will remove it.
+ */
+ xi->xi_value = NULL;
+ xi->xi_value_len = 0;
+
+ old_found = xis->not_found;
+ xis->not_found = -ENODATA;
+ ret = ocfs2_calc_xattr_set_need(inode,
+ di,
+ xi,
+ xis,
+ xbs,
+ NULL,
+ NULL,
+ &credits);
+ xis->not_found = old_found;
+ if (ret) {
+ mlog_errno(ret);
+ goto out;
+ }
+
+ ret = ocfs2_extend_trans(ctxt->handle, credits);
+ if (ret) {
+ mlog_errno(ret);
+ goto out;
+ }
+ ret = ocfs2_xattr_block_set(inode, xi, xbs, ctxt);
+ } else if ((ret == -ENOSPC) && !ctxt->set_abort) {
+ if (di->i_xattr_loc && !xbs->xattr_bh) {
+ ret = ocfs2_xattr_block_find(inode,
+ xi->xi_name_index,
+ xi->xi_name, xbs);
+ if (ret)
+ goto out;
+
+ old_found = xis->not_found;
+ xis->not_found = -ENODATA;
+ ret = ocfs2_calc_xattr_set_need(inode,
+ di,
+ xi,
+ xis,
+ xbs,
+ NULL,
+ NULL,
+ &credits);
+ xis->not_found = old_found;
+ if (ret) {
+ mlog_errno(ret);
+ goto out;
+ }
+
+ ret = ocfs2_extend_trans(ctxt->handle, credits);
+ if (ret) {
+ mlog_errno(ret);
+ goto out;
+ }
+ }
+ /*
+ * If no space in inode, we will set extended attribute
+ * into external block.
+ */
+ ret = ocfs2_xattr_block_set(inode, xi, xbs, ctxt);
+ if (ret)
+ goto out;
+ if (!xis->not_found) {
+ /*
+ * If succeed and that extended attribute
+ * existing in inode, we will remove it.
+ */
+ xi->xi_value = NULL;
+ xi->xi_value_len = 0;
+ xbs->not_found = -ENODATA;
+ ret = ocfs2_calc_xattr_set_need(inode,
+ di,
+ xi,
+ xis,
+ xbs,
+ NULL,
+ NULL,
+ &credits);
+ if (ret) {
+ mlog_errno(ret);
+ goto out;
+ }
+
+ ret = ocfs2_extend_trans(ctxt->handle, credits);
+ if (ret) {
+ mlog_errno(ret);
+ goto out;
+ }
+ ret = ocfs2_xattr_ibody_set(inode, xi,
+ xis, ctxt);
+ }
+ }
+ }
+
+ if (!ret) {
+ /* Update inode ctime. */
+ ret = ocfs2_journal_access_di(ctxt->handle, INODE_CACHE(inode),
+ xis->inode_bh,
+ OCFS2_JOURNAL_ACCESS_WRITE);
+ if (ret) {
+ mlog_errno(ret);
+ goto out;
+ }
+
+ inode->i_ctime = CURRENT_TIME;
+ di->i_ctime = cpu_to_le64(inode->i_ctime.tv_sec);
+ di->i_ctime_nsec = cpu_to_le32(inode->i_ctime.tv_nsec);
+ ocfs2_journal_dirty(ctxt->handle, xis->inode_bh);
+ }
+out:
+ return ret;
+}
+
+/*
+ * This function only called duing creating inode
+ * for init security/acl xattrs of the new inode.
+ * All transanction credits have been reserved in mknod.
+ */
+int ocfs2_xattr_set_handle(handle_t *handle,
+ struct inode *inode,
+ struct buffer_head *di_bh,
+ int name_index,
+ const char *name,
+ const void *value,
+ size_t value_len,
+ int flags,
+ struct ocfs2_alloc_context *meta_ac,
+ struct ocfs2_alloc_context *data_ac)
+{
+ struct ocfs2_dinode *di;
+ int ret;
+
+ struct ocfs2_xattr_info xi = {
+ .xi_name_index = name_index,
+ .xi_name = name,
+ .xi_name_len = strlen(name),
+ .xi_value = value,
+ .xi_value_len = value_len,
+ };
+
+ struct ocfs2_xattr_search xis = {
+ .not_found = -ENODATA,
+ };
+
+ struct ocfs2_xattr_search xbs = {
+ .not_found = -ENODATA,
+ };
+
+ struct ocfs2_xattr_set_ctxt ctxt = {
+ .handle = handle,
+ .meta_ac = meta_ac,
+ .data_ac = data_ac,
+ };
+
+ if (!ocfs2_supports_xattr(OCFS2_SB(inode->i_sb)))
+ return -EOPNOTSUPP;
+
+ /*
+ * In extreme situation, may need xattr bucket when
+ * block size is too small. And we have already reserved
+ * the credits for bucket in mknod.
+ */
+ if (inode->i_sb->s_blocksize == OCFS2_MIN_BLOCKSIZE) {
+ xbs.bucket = ocfs2_xattr_bucket_new(inode);
+ if (!xbs.bucket) {
+ mlog_errno(-ENOMEM);
+ return -ENOMEM;
+ }
+ }
+
+ xis.inode_bh = xbs.inode_bh = di_bh;
+ di = (struct ocfs2_dinode *)di_bh->b_data;
+
+ down_write(&OCFS2_I(inode)->ip_xattr_sem);
+
+ ret = ocfs2_xattr_ibody_find(inode, name_index, name, &xis);
+ if (ret)
+ goto cleanup;
+ if (xis.not_found) {
+ ret = ocfs2_xattr_block_find(inode, name_index, name, &xbs);
+ if (ret)
+ goto cleanup;
+ }
+
+ ret = __ocfs2_xattr_set_handle(inode, di, &xi, &xis, &xbs, &ctxt);
+
+cleanup:
+ up_write(&OCFS2_I(inode)->ip_xattr_sem);
+ brelse(xbs.xattr_bh);
+ ocfs2_xattr_bucket_free(xbs.bucket);
+
+ return ret;
+}
+
+/*
+ * ocfs2_xattr_set()
+ *
+ * Set, replace or remove an extended attribute for this inode.
+ * value is NULL to remove an existing extended attribute, else either
+ * create or replace an extended attribute.
+ */
+int ocfs2_xattr_set(struct inode *inode,
+ int name_index,
+ const char *name,
+ const void *value,
+ size_t value_len,
+ int flags)
+{
+ struct buffer_head *di_bh = NULL;
+ struct ocfs2_dinode *di;
+ int ret, credits, ref_meta = 0, ref_credits = 0;
+ struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+ struct inode *tl_inode = osb->osb_tl_inode;
+ struct ocfs2_xattr_set_ctxt ctxt = { NULL, NULL, };
+ struct ocfs2_refcount_tree *ref_tree = NULL;
+
+ struct ocfs2_xattr_info xi = {
+ .xi_name_index = name_index,
+ .xi_name = name,
+ .xi_name_len = strlen(name),
+ .xi_value = value,
+ .xi_value_len = value_len,
+ };
+
+ struct ocfs2_xattr_search xis = {
+ .not_found = -ENODATA,
+ };
+
+ struct ocfs2_xattr_search xbs = {
+ .not_found = -ENODATA,
+ };
+
+ if (!ocfs2_supports_xattr(OCFS2_SB(inode->i_sb)))
+ return -EOPNOTSUPP;
+
+ /*
+ * Only xbs will be used on indexed trees. xis doesn't need a
+ * bucket.
+ */
+ xbs.bucket = ocfs2_xattr_bucket_new(inode);
+ if (!xbs.bucket) {
+ mlog_errno(-ENOMEM);
+ return -ENOMEM;
+ }
+
+ ret = ocfs2_inode_lock(inode, &di_bh, 1);
+ if (ret < 0) {
+ mlog_errno(ret);
+ goto cleanup_nolock;
+ }
+ xis.inode_bh = xbs.inode_bh = di_bh;
+ di = (struct ocfs2_dinode *)di_bh->b_data;
+
+ down_write(&OCFS2_I(inode)->ip_xattr_sem);
+ /*
+ * Scan inode and external block to find the same name
+ * extended attribute and collect search infomation.
+ */
+ ret = ocfs2_xattr_ibody_find(inode, name_index, name, &xis);
+ if (ret)
+ goto cleanup;
+ if (xis.not_found) {
+ ret = ocfs2_xattr_block_find(inode, name_index, name, &xbs);
+ if (ret)
+ goto cleanup;
+ }
+
+ if (xis.not_found && xbs.not_found) {
+ ret = -ENODATA;
+ if (flags & XATTR_REPLACE)
+ goto cleanup;
+ ret = 0;
+ if (!value)
+ goto cleanup;
+ } else {
+ ret = -EEXIST;
+ if (flags & XATTR_CREATE)
+ goto cleanup;
+ }
+
+ /* Check whether the value is refcounted and do some prepartion. */
+ if (OCFS2_I(inode)->ip_dyn_features & OCFS2_HAS_REFCOUNT_FL &&
+ (!xis.not_found || !xbs.not_found)) {
+ ret = ocfs2_prepare_refcount_xattr(inode, di, &xi,
+ &xis, &xbs, &ref_tree,
+ &ref_meta, &ref_credits);
+ if (ret) {
+ mlog_errno(ret);
+ goto cleanup;
+ }
+ }
+
+ mutex_lock(&tl_inode->i_mutex);
+
+ if (ocfs2_truncate_log_needs_flush(osb)) {
+ ret = __ocfs2_flush_truncate_log(osb);
+ if (ret < 0) {
+ mutex_unlock(&tl_inode->i_mutex);
+ mlog_errno(ret);
+ goto cleanup;
+ }
+ }
+ mutex_unlock(&tl_inode->i_mutex);
+
+ ret = ocfs2_init_xattr_set_ctxt(inode, di, &xi, &xis,
+ &xbs, &ctxt, ref_meta, &credits);
+ if (ret) {
+ mlog_errno(ret);
+ goto cleanup;
+ }
+
+ /* we need to update inode's ctime field, so add credit for it. */
+ credits += OCFS2_INODE_UPDATE_CREDITS;
+ ctxt.handle = ocfs2_start_trans(osb, credits + ref_credits);
+ if (IS_ERR(ctxt.handle)) {
+ ret = PTR_ERR(ctxt.handle);
+ mlog_errno(ret);
+ goto cleanup;
+ }
+
+ ret = __ocfs2_xattr_set_handle(inode, di, &xi, &xis, &xbs, &ctxt);
+
+ ocfs2_commit_trans(osb, ctxt.handle);
+
+ if (ctxt.data_ac)
+ ocfs2_free_alloc_context(ctxt.data_ac);
+ if (ctxt.meta_ac)
+ ocfs2_free_alloc_context(ctxt.meta_ac);
+ if (ocfs2_dealloc_has_cluster(&ctxt.dealloc))
+ ocfs2_schedule_truncate_log_flush(osb, 1);
+ ocfs2_run_deallocs(osb, &ctxt.dealloc);
+
+cleanup:
+ if (ref_tree)
+ ocfs2_unlock_refcount_tree(osb, ref_tree, 1);
+ up_write(&OCFS2_I(inode)->ip_xattr_sem);
+ if (!value && !ret) {
+ ret = ocfs2_try_remove_refcount_tree(inode, di_bh);
+ if (ret)
+ mlog_errno(ret);
+ }
+ ocfs2_inode_unlock(inode, 1);
+cleanup_nolock:
+ brelse(di_bh);
+ brelse(xbs.xattr_bh);
+ ocfs2_xattr_bucket_free(xbs.bucket);
+
+ return ret;
+}
+
+/*
+ * Find the xattr extent rec which may contains name_hash.
+ * e_cpos will be the first name hash of the xattr rec.
+ * el must be the ocfs2_xattr_header.xb_attrs.xb_root.xt_list.
+ */
+static int ocfs2_xattr_get_rec(struct inode *inode,
+ u32 name_hash,
+ u64 *p_blkno,
+ u32 *e_cpos,
+ u32 *num_clusters,
+ struct ocfs2_extent_list *el)
+{
+ int ret = 0, i;
+ struct buffer_head *eb_bh = NULL;
+ struct ocfs2_extent_block *eb;
+ struct ocfs2_extent_rec *rec = NULL;
+ u64 e_blkno = 0;
+
+ if (el->l_tree_depth) {
+ ret = ocfs2_find_leaf(INODE_CACHE(inode), el, name_hash,
+ &eb_bh);
+ if (ret) {
+ mlog_errno(ret);
+ goto out;
+ }
+
+ eb = (struct ocfs2_extent_block *) eb_bh->b_data;
+ el = &eb->h_list;
+
+ if (el->l_tree_depth) {
+ ocfs2_error(inode->i_sb,
+ "Inode %lu has non zero tree depth in "
+ "xattr tree block %llu\n", inode->i_ino,
+ (unsigned long long)eb_bh->b_blocknr);
+ ret = -EROFS;
+ goto out;
+ }
+ }
+
+ for (i = le16_to_cpu(el->l_next_free_rec) - 1; i >= 0; i--) {
+ rec = &el->l_recs[i];
+
+ if (le32_to_cpu(rec->e_cpos) <= name_hash) {
+ e_blkno = le64_to_cpu(rec->e_blkno);
+ break;
+ }
+ }
+
+ if (!e_blkno) {
+ ocfs2_error(inode->i_sb, "Inode %lu has bad extent "
+ "record (%u, %u, 0) in xattr", inode->i_ino,
+ le32_to_cpu(rec->e_cpos),
+ ocfs2_rec_clusters(el, rec));
+ ret = -EROFS;
+ goto out;
+ }
+
+ *p_blkno = le64_to_cpu(rec->e_blkno);
+ *num_clusters = le16_to_cpu(rec->e_leaf_clusters);
+ if (e_cpos)
+ *e_cpos = le32_to_cpu(rec->e_cpos);
+out:
+ brelse(eb_bh);
+ return ret;
+}
+
+typedef int (xattr_bucket_func)(struct inode *inode,
+ struct ocfs2_xattr_bucket *bucket,
+ void *para);
+
+static int ocfs2_find_xe_in_bucket(struct inode *inode,
+ struct ocfs2_xattr_bucket *bucket,
+ int name_index,
+ const char *name,
+ u32 name_hash,
+ u16 *xe_index,
+ int *found)
+{
+ int i, ret = 0, cmp = 1, block_off, new_offset;
+ struct ocfs2_xattr_header *xh = bucket_xh(bucket);
+ size_t name_len = strlen(name);
+ struct ocfs2_xattr_entry *xe = NULL;
+ char *xe_name;
+
+ /*
+ * We don't use binary search in the bucket because there
+ * may be multiple entries with the same name hash.
+ */
+ for (i = 0; i < le16_to_cpu(xh->xh_count); i++) {
+ xe = &xh->xh_entries[i];
+
+ if (name_hash > le32_to_cpu(xe->xe_name_hash))
+ continue;
+ else if (name_hash < le32_to_cpu(xe->xe_name_hash))
+ break;
+
+ cmp = name_index - ocfs2_xattr_get_type(xe);
+ if (!cmp)
+ cmp = name_len - xe->xe_name_len;
+ if (cmp)
+ continue;
+
+ ret = ocfs2_xattr_bucket_get_name_value(inode->i_sb,
+ xh,
+ i,
+ &block_off,
+ &new_offset);
+ if (ret) {
+ mlog_errno(ret);
+ break;
+ }
+
+
+ xe_name = bucket_block(bucket, block_off) + new_offset;
+ if (!memcmp(name, xe_name, name_len)) {
+ *xe_index = i;
+ *found = 1;
+ ret = 0;
+ break;
+ }
+ }
+
+ return ret;
+}
+
+/*
+ * Find the specified xattr entry in a series of buckets.
+ * This series start from p_blkno and last for num_clusters.
+ * The ocfs2_xattr_header.xh_num_buckets of the first bucket contains
+ * the num of the valid buckets.
+ *
+ * Return the buffer_head this xattr should reside in. And if the xattr's
+ * hash is in the gap of 2 buckets, return the lower bucket.
+ */
+static int ocfs2_xattr_bucket_find(struct inode *inode,
+ int name_index,
+ const char *name,
+ u32 name_hash,
+ u64 p_blkno,
+ u32 first_hash,
+ u32 num_clusters,
+ struct ocfs2_xattr_search *xs)
+{
+ int ret, found = 0;
+ struct ocfs2_xattr_header *xh = NULL;
+ struct ocfs2_xattr_entry *xe = NULL;
+ u16 index = 0;
+ u16 blk_per_bucket = ocfs2_blocks_per_xattr_bucket(inode->i_sb);
+ int low_bucket = 0, bucket, high_bucket;
+ struct ocfs2_xattr_bucket *search;
+ u32 last_hash;
+ u64 blkno, lower_blkno = 0;
+
+ search = ocfs2_xattr_bucket_new(inode);
+ if (!search) {
+ ret = -ENOMEM;
+ mlog_errno(ret);
+ goto out;
+ }
+
+ ret = ocfs2_read_xattr_bucket(search, p_blkno);
+ if (ret) {
+ mlog_errno(ret);
+ goto out;
+ }
+
+ xh = bucket_xh(search);
+ high_bucket = le16_to_cpu(xh->xh_num_buckets) - 1;
+ while (low_bucket <= high_bucket) {
+ ocfs2_xattr_bucket_relse(search);
+
+ bucket = (low_bucket + high_bucket) / 2;
+ blkno = p_blkno + bucket * blk_per_bucket;
+ ret = ocfs2_read_xattr_bucket(search, blkno);
+ if (ret) {
+ mlog_errno(ret);
+ goto out;
+ }
+
+ xh = bucket_xh(search);
+ xe = &xh->xh_entries[0];
+ if (name_hash < le32_to_cpu(xe->xe_name_hash)) {
+ high_bucket = bucket - 1;
+ continue;
+ }
+
+ /*
+ * Check whether the hash of the last entry in our
+ * bucket is larger than the search one. for an empty
+ * bucket, the last one is also the first one.
+ */
+ if (xh->xh_count)
+ xe = &xh->xh_entries[le16_to_cpu(xh->xh_count) - 1];
+
+ last_hash = le32_to_cpu(xe->xe_name_hash);
+
+ /* record lower_blkno which may be the insert place. */
+ lower_blkno = blkno;
+
+ if (name_hash > le32_to_cpu(xe->xe_name_hash)) {
+ low_bucket = bucket + 1;
+ continue;
+ }
+
+ /* the searched xattr should reside in this bucket if exists. */
+ ret = ocfs2_find_xe_in_bucket(inode, search,
+ name_index, name, name_hash,
+ &index, &found);
+ if (ret) {
+ mlog_errno(ret);
+ goto out;
+ }
+ break;
+ }
+
+ /*
+ * Record the bucket we have found.
+ * When the xattr's hash value is in the gap of 2 buckets, we will
+ * always set it to the previous bucket.
+ */
+ if (!lower_blkno)
+ lower_blkno = p_blkno;
+
+ /* This should be in cache - we just read it during the search */
+ ret = ocfs2_read_xattr_bucket(xs->bucket, lower_blkno);
+ if (ret) {
+ mlog_errno(ret);
+ goto out;
+ }
+
+ xs->header = bucket_xh(xs->bucket);
+ xs->base = bucket_block(xs->bucket, 0);
+ xs->end = xs->base + inode->i_sb->s_blocksize;
+
+ if (found) {
+ xs->here = &xs->header->xh_entries[index];
+ mlog(0, "find xattr %s in bucket %llu, entry = %u\n", name,
+ (unsigned long long)bucket_blkno(xs->bucket), index);
+ } else
+ ret = -ENODATA;
+
+out:
+ ocfs2_xattr_bucket_free(search);
+ return ret;
+}
+
+static int ocfs2_xattr_index_block_find(struct inode *inode,
+ struct buffer_head *root_bh,
+ int name_index,
+ const char *name,
+ struct ocfs2_xattr_search *xs)
+{
+ int ret;
+ struct ocfs2_xattr_block *xb =
+ (struct ocfs2_xattr_block *)root_bh->b_data;
+ struct ocfs2_xattr_tree_root *xb_root = &xb->xb_attrs.xb_root;
+ struct ocfs2_extent_list *el = &xb_root->xt_list;
+ u64 p_blkno = 0;
+ u32 first_hash, num_clusters = 0;
+ u32 name_hash = ocfs2_xattr_name_hash(inode, name, strlen(name));
+
+ if (le16_to_cpu(el->l_next_free_rec) == 0)
+ return -ENODATA;
+
+ mlog(0, "find xattr %s, hash = %u, index = %d in xattr tree\n",
+ name, name_hash, name_index);
+
+ ret = ocfs2_xattr_get_rec(inode, name_hash, &p_blkno, &first_hash,
+ &num_clusters, el);
+ if (ret) {
+ mlog_errno(ret);
+ goto out;
+ }
+
+ BUG_ON(p_blkno == 0 || num_clusters == 0 || first_hash > name_hash);
+
+ mlog(0, "find xattr extent rec %u clusters from %llu, the first hash "
+ "in the rec is %u\n", num_clusters, (unsigned long long)p_blkno,
+ first_hash);
+
+ ret = ocfs2_xattr_bucket_find(inode, name_index, name, name_hash,
+ p_blkno, first_hash, num_clusters, xs);
+
+out:
+ return ret;
+}
+
+static int ocfs2_iterate_xattr_buckets(struct inode *inode,
+ u64 blkno,
+ u32 clusters,
+ xattr_bucket_func *func,
+ void *para)
+{
+ int i, ret = 0;
+ u32 bpc = ocfs2_xattr_buckets_per_cluster(OCFS2_SB(inode->i_sb));
+ u32 num_buckets = clusters * bpc;
+ struct ocfs2_xattr_bucket *bucket;
+
+ bucket = ocfs2_xattr_bucket_new(inode);
+ if (!bucket) {
+ mlog_errno(-ENOMEM);
+ return -ENOMEM;
+ }
+
+ mlog(0, "iterating xattr buckets in %u clusters starting from %llu\n",
+ clusters, (unsigned long long)blkno);
+
+ for (i = 0; i < num_buckets; i++, blkno += bucket->bu_blocks) {
+ ret = ocfs2_read_xattr_bucket(bucket, blkno);
+ if (ret) {
+ mlog_errno(ret);
+ break;
+ }
+
+ /*
+ * The real bucket num in this series of blocks is stored
+ * in the 1st bucket.
+ */
+ if (i == 0)
+ num_buckets = le16_to_cpu(bucket_xh(bucket)->xh_num_buckets);
+
+ mlog(0, "iterating xattr bucket %llu, first hash %u\n",
+ (unsigned long long)blkno,
+ le32_to_cpu(bucket_xh(bucket)->xh_entries[0].xe_name_hash));
+ if (func) {
+ ret = func(inode, bucket, para);
+ if (ret && ret != -ERANGE)
+ mlog_errno(ret);
+ /* Fall through to bucket_relse() */
+ }
+
+ ocfs2_xattr_bucket_relse(bucket);
+ if (ret)
+ break;
+ }
+
+ ocfs2_xattr_bucket_free(bucket);
+ return ret;
+}
+
+struct ocfs2_xattr_tree_list {
+ char *buffer;
+ size_t buffer_size;
+ size_t result;
+};
+
+static int ocfs2_xattr_bucket_get_name_value(struct super_block *sb,
+ struct ocfs2_xattr_header *xh,
+ int index,
+ int *block_off,
+ int *new_offset)
+{
+ u16 name_offset;
+
+ if (index < 0 || index >= le16_to_cpu(xh->xh_count))
+ return -EINVAL;
+
+ name_offset = le16_to_cpu(xh->xh_entries[index].xe_name_offset);
+
+ *block_off = name_offset >> sb->s_blocksize_bits;
+ *new_offset = name_offset % sb->s_blocksize;
+
+ return 0;
+}
+
+static int ocfs2_list_xattr_bucket(struct inode *inode,
+ struct ocfs2_xattr_bucket *bucket,
+ void *para)
+{
+ int ret = 0, type;
+ struct ocfs2_xattr_tree_list *xl = (struct ocfs2_xattr_tree_list *)para;
+ int i, block_off, new_offset;
+ const char *prefix, *name;
+
+ for (i = 0 ; i < le16_to_cpu(bucket_xh(bucket)->xh_count); i++) {
+ struct ocfs2_xattr_entry *entry = &bucket_xh(bucket)->xh_entries[i];
+ type = ocfs2_xattr_get_type(entry);
+ prefix = ocfs2_xattr_prefix(type);
+
+ if (prefix) {
+ ret = ocfs2_xattr_bucket_get_name_value(inode->i_sb,
+ bucket_xh(bucket),
+ i,
+ &block_off,
+ &new_offset);
+ if (ret)
+ break;
+
+ name = (const char *)bucket_block(bucket, block_off) +
+ new_offset;
+ ret = ocfs2_xattr_list_entry(xl->buffer,
+ xl->buffer_size,
+ &xl->result,
+ prefix, name,
+ entry->xe_name_len);
+ if (ret)
+ break;
+ }
+ }
+
+ return ret;
+}
+
+static int ocfs2_iterate_xattr_index_block(struct inode *inode,
+ struct buffer_head *blk_bh,
+ xattr_tree_rec_func *rec_func,
+ void *para)
+{
+ struct ocfs2_xattr_block *xb =
+ (struct ocfs2_xattr_block *)blk_bh->b_data;
+ struct ocfs2_extent_list *el = &xb->xb_attrs.xb_root.xt_list;
+ int ret = 0;
+ u32 name_hash = UINT_MAX, e_cpos = 0, num_clusters = 0;
+ u64 p_blkno = 0;
+
+ if (!el->l_next_free_rec || !rec_func)
+ return 0;
+
+ while (name_hash > 0) {
+ ret = ocfs2_xattr_get_rec(inode, name_hash, &p_blkno,
+ &e_cpos, &num_clusters, el);
+ if (ret) {
+ mlog_errno(ret);
+ break;
+ }
+
+ ret = rec_func(inode, blk_bh, p_blkno, e_cpos,
+ num_clusters, para);
+ if (ret) {
+ if (ret != -ERANGE)
+ mlog_errno(ret);
+ break;
+ }
+
+ if (e_cpos == 0)
+ break;
+
+ name_hash = e_cpos - 1;
+ }
+
+ return ret;
+
+}
+
+static int ocfs2_list_xattr_tree_rec(struct inode *inode,
+ struct buffer_head *root_bh,
+ u64 blkno, u32 cpos, u32 len, void *para)
+{
+ return ocfs2_iterate_xattr_buckets(inode, blkno, len,
+ ocfs2_list_xattr_bucket, para);
+}
+
+static int ocfs2_xattr_tree_list_index_block(struct inode *inode,
+ struct buffer_head *blk_bh,
+ char *buffer,
+ size_t buffer_size)
+{
+ int ret;
+ struct ocfs2_xattr_tree_list xl = {
+ .buffer = buffer,
+ .buffer_size = buffer_size,
+ .result = 0,
+ };
+
+ ret = ocfs2_iterate_xattr_index_block(inode, blk_bh,
+ ocfs2_list_xattr_tree_rec, &xl);
+ if (ret) {
+ mlog_errno(ret);
+ goto out;
+ }
+
+ ret = xl.result;
+out:
+ return ret;
+}
+
+static int cmp_xe(const void *a, const void *b)
+{
+ const struct ocfs2_xattr_entry *l = a, *r = b;
+ u32 l_hash = le32_to_cpu(l->xe_name_hash);
+ u32 r_hash = le32_to_cpu(r->xe_name_hash);
+
+ if (l_hash > r_hash)
+ return 1;
+ if (l_hash < r_hash)
+ return -1;
+ return 0;
+}
+
+static void swap_xe(void *a, void *b, int size)
+{
+ struct ocfs2_xattr_entry *l = a, *r = b, tmp;
+
+ tmp = *l;
+ memcpy(l, r, sizeof(struct ocfs2_xattr_entry));
+ memcpy(r, &tmp, sizeof(struct ocfs2_xattr_entry));
+}
+
+/*
+ * When the ocfs2_xattr_block is filled up, new bucket will be created
+ * and all the xattr entries will be moved to the new bucket.
+ * The header goes at the start of the bucket, and the names+values are
+ * filled from the end. This is why *target starts as the last buffer.
+ * Note: we need to sort the entries since they are not saved in order
+ * in the ocfs2_xattr_block.
+ */
+static void ocfs2_cp_xattr_block_to_bucket(struct inode *inode,
+ struct buffer_head *xb_bh,
+ struct ocfs2_xattr_bucket *bucket)
+{
+ int i, blocksize = inode->i_sb->s_blocksize;
+ int blks = ocfs2_blocks_per_xattr_bucket(inode->i_sb);
+ u16 offset, size, off_change;
+ struct ocfs2_xattr_entry *xe;
+ struct ocfs2_xattr_block *xb =
+ (struct ocfs2_xattr_block *)xb_bh->b_data;
+ struct ocfs2_xattr_header *xb_xh = &xb->xb_attrs.xb_header;
+ struct ocfs2_xattr_header *xh = bucket_xh(bucket);
+ u16 count = le16_to_cpu(xb_xh->xh_count);
+ char *src = xb_bh->b_data;
+ char *target = bucket_block(bucket, blks - 1);