+static noinline int lookup_tree_block_ref(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ struct btrfs_path *path,
+ u64 bytenr, u64 parent,
+ u64 root_objectid)
+{
+ struct btrfs_key key;
+ int ret;
+
+ key.objectid = bytenr;
+ if (parent) {
+ key.type = BTRFS_SHARED_BLOCK_REF_KEY;
+ key.offset = parent;
+ } else {
+ key.type = BTRFS_TREE_BLOCK_REF_KEY;
+ key.offset = root_objectid;
+ }
+
+ ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
+ if (ret > 0)
+ ret = -ENOENT;
+#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
+ if (ret == -ENOENT && parent) {
+ btrfs_release_path(path);
+ key.type = BTRFS_EXTENT_REF_V0_KEY;
+ ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
+ if (ret > 0)
+ ret = -ENOENT;
+ }
+#endif
+ return ret;
+}
+
+static noinline int insert_tree_block_ref(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ struct btrfs_path *path,
+ u64 bytenr, u64 parent,
+ u64 root_objectid)
+{
+ struct btrfs_key key;
+ int ret;
+
+ key.objectid = bytenr;
+ if (parent) {
+ key.type = BTRFS_SHARED_BLOCK_REF_KEY;
+ key.offset = parent;
+ } else {
+ key.type = BTRFS_TREE_BLOCK_REF_KEY;
+ key.offset = root_objectid;
+ }
+
+ ret = btrfs_insert_empty_item(trans, root, path, &key, 0);
+
+ btrfs_release_path(path);
+ return ret;
+}
+
+static inline int extent_ref_type(u64 parent, u64 owner)
+{
+ int type;
+ if (owner < BTRFS_FIRST_FREE_OBJECTID) {
+ if (parent > 0)
+ type = BTRFS_SHARED_BLOCK_REF_KEY;
+ else
+ type = BTRFS_TREE_BLOCK_REF_KEY;
+ } else {
+ if (parent > 0)
+ type = BTRFS_SHARED_DATA_REF_KEY;
+ else
+ type = BTRFS_EXTENT_DATA_REF_KEY;
+ }
+ return type;
+}
+
+static int lookup_inline_extent_backref(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ struct btrfs_path *path,
+ struct btrfs_extent_inline_ref **ref_ret,
+ u64 bytenr, u64 num_bytes,
+ u64 parent, u64 root_objectid,
+ u64 owner, u64 offset, int insert)
+{
+ struct btrfs_key key;
+ struct extent_buffer *leaf;
+ struct btrfs_extent_item *ei;
+ struct btrfs_extent_inline_ref *iref;
+ u64 flags;
+ u32 item_size;
+ unsigned long ptr;
+ unsigned long end;
+ int extra_size;
+ int type;
+ int want;
+ int ret;
+ int err = 0;
+ int skinny_metadata =
+ btrfs_fs_incompat(root->fs_info, SKINNY_METADATA);
+
+ key.objectid = bytenr;
+ key.type = BTRFS_EXTENT_ITEM_KEY;
+ key.offset = num_bytes;
+
+ want = extent_ref_type(parent, owner);
+ if (insert)
+ extra_size = btrfs_extent_inline_ref_size(want);
+ else
+ extra_size = -1;
+
+ if (owner < BTRFS_FIRST_FREE_OBJECTID && skinny_metadata) {
+ key.type = BTRFS_METADATA_ITEM_KEY;
+ key.offset = owner;
+ } else if (skinny_metadata) {
+ skinny_metadata = 0;
+ }
+
+again:
+ ret = btrfs_search_slot(trans, root, &key, path, extra_size, 1);
+ if (ret < 0) {
+ err = ret;
+ goto out;
+ }
+
+ /*
+ * We may be a newly converted file system which still has the old fat
+ * extent entries for metadata, so try and see if we have one of those.
+ */
+ if (ret > 0 && skinny_metadata) {
+ skinny_metadata = 0;
+ if (path->slots[0]) {
+ path->slots[0]--;
+ btrfs_item_key_to_cpu(path->nodes[0], &key,
+ path->slots[0]);
+ if (key.objectid == bytenr &&
+ key.type == BTRFS_EXTENT_ITEM_KEY &&
+ key.offset == num_bytes)
+ ret = 0;
+ }
+ if (ret) {
+ key.type = BTRFS_EXTENT_ITEM_KEY;
+ key.offset = num_bytes;
+ btrfs_release_path(path);
+ goto again;
+ }
+ }
+
+ if (ret) {
+ printf("Failed to find [%llu, %u, %llu]\n", key.objectid, key.type, key.offset);
+ return -ENOENT;
+ }
+
+ BUG_ON(ret);
+
+ leaf = path->nodes[0];
+ item_size = btrfs_item_size_nr(leaf, path->slots[0]);
+#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
+ if (item_size < sizeof(*ei)) {
+ if (!insert) {
+ err = -ENOENT;
+ goto out;
+ }
+ ret = convert_extent_item_v0(trans, root, path, owner,
+ extra_size);
+ if (ret < 0) {
+ err = ret;
+ goto out;
+ }
+ leaf = path->nodes[0];
+ item_size = btrfs_item_size_nr(leaf, path->slots[0]);
+ }
+#endif
+ if (item_size < sizeof(*ei)) {
+ printf("Size is %u, needs to be %u, slot %d\n",
+ (unsigned)item_size,
+ (unsigned)sizeof(*ei), path->slots[0]);
+ btrfs_print_leaf(root, leaf);
+ return -EINVAL;
+ }
+ BUG_ON(item_size < sizeof(*ei));
+
+ ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item);
+ flags = btrfs_extent_flags(leaf, ei);
+
+ ptr = (unsigned long)(ei + 1);
+ end = (unsigned long)ei + item_size;
+
+ if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK && !skinny_metadata) {
+ ptr += sizeof(struct btrfs_tree_block_info);
+ BUG_ON(ptr > end);
+ } else if (!(flags & BTRFS_EXTENT_FLAG_TREE_BLOCK)) {
+ if (!(flags & BTRFS_EXTENT_FLAG_DATA)) {
+ return -EIO;
+ }
+ }
+
+ err = -ENOENT;
+ while (1) {
+ if (ptr >= end) {
+ WARN_ON(ptr > end);
+ break;
+ }
+ iref = (struct btrfs_extent_inline_ref *)ptr;
+ type = btrfs_extent_inline_ref_type(leaf, iref);
+ if (want < type)
+ break;
+ if (want > type) {
+ ptr += btrfs_extent_inline_ref_size(type);
+ continue;
+ }
+
+ if (type == BTRFS_EXTENT_DATA_REF_KEY) {
+ struct btrfs_extent_data_ref *dref;
+ dref = (struct btrfs_extent_data_ref *)(&iref->offset);
+ if (match_extent_data_ref(leaf, dref, root_objectid,
+ owner, offset)) {
+ err = 0;
+ break;
+ }
+ if (hash_extent_data_ref_item(leaf, dref) <
+ hash_extent_data_ref(root_objectid, owner, offset))
+ break;
+ } else {
+ u64 ref_offset;
+ ref_offset = btrfs_extent_inline_ref_offset(leaf, iref);
+ if (parent > 0) {
+ if (parent == ref_offset) {
+ err = 0;
+ break;
+ }
+ if (ref_offset < parent)
+ break;
+ } else {
+ if (root_objectid == ref_offset) {
+ err = 0;
+ break;
+ }
+ if (ref_offset < root_objectid)
+ break;
+ }
+ }
+ ptr += btrfs_extent_inline_ref_size(type);
+ }
+ if (err == -ENOENT && insert) {
+ if (item_size + extra_size >=
+ BTRFS_MAX_EXTENT_ITEM_SIZE(root)) {
+ err = -EAGAIN;
+ goto out;
+ }
+ /*
+ * To add new inline back ref, we have to make sure
+ * there is no corresponding back ref item.
+ * For simplicity, we just do not add new inline back
+ * ref if there is any back ref item.
+ */
+ if (find_next_key(path, &key) == 0 && key.objectid == bytenr &&
+ key.type < BTRFS_BLOCK_GROUP_ITEM_KEY) {
+ err = -EAGAIN;
+ goto out;
+ }
+ }
+ *ref_ret = (struct btrfs_extent_inline_ref *)ptr;
+out:
+ return err;
+}
+
+static int setup_inline_extent_backref(struct btrfs_root *root,
+ struct btrfs_path *path,
+ struct btrfs_extent_inline_ref *iref,
+ u64 parent, u64 root_objectid,
+ u64 owner, u64 offset, int refs_to_add)
+{
+ struct extent_buffer *leaf;
+ struct btrfs_extent_item *ei;
+ unsigned long ptr;
+ unsigned long end;
+ unsigned long item_offset;
+ u64 refs;
+ int size;
+ int type;
+ int ret;
+
+ leaf = path->nodes[0];
+ ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item);
+ item_offset = (unsigned long)iref - (unsigned long)ei;
+
+ type = extent_ref_type(parent, owner);
+ size = btrfs_extent_inline_ref_size(type);
+
+ ret = btrfs_extend_item(root, path, size);
+ BUG_ON(ret);
+
+ ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item);
+ refs = btrfs_extent_refs(leaf, ei);
+ refs += refs_to_add;
+ btrfs_set_extent_refs(leaf, ei, refs);
+
+ ptr = (unsigned long)ei + item_offset;
+ end = (unsigned long)ei + btrfs_item_size_nr(leaf, path->slots[0]);
+ if (ptr < end - size)
+ memmove_extent_buffer(leaf, ptr + size, ptr,
+ end - size - ptr);
+
+ iref = (struct btrfs_extent_inline_ref *)ptr;
+ btrfs_set_extent_inline_ref_type(leaf, iref, type);
+ if (type == BTRFS_EXTENT_DATA_REF_KEY) {
+ struct btrfs_extent_data_ref *dref;
+ dref = (struct btrfs_extent_data_ref *)(&iref->offset);
+ btrfs_set_extent_data_ref_root(leaf, dref, root_objectid);
+ btrfs_set_extent_data_ref_objectid(leaf, dref, owner);
+ btrfs_set_extent_data_ref_offset(leaf, dref, offset);
+ btrfs_set_extent_data_ref_count(leaf, dref, refs_to_add);
+ } else if (type == BTRFS_SHARED_DATA_REF_KEY) {
+ struct btrfs_shared_data_ref *sref;
+ sref = (struct btrfs_shared_data_ref *)(iref + 1);
+ btrfs_set_shared_data_ref_count(leaf, sref, refs_to_add);
+ btrfs_set_extent_inline_ref_offset(leaf, iref, parent);
+ } else if (type == BTRFS_SHARED_BLOCK_REF_KEY) {
+ btrfs_set_extent_inline_ref_offset(leaf, iref, parent);
+ } else {
+ btrfs_set_extent_inline_ref_offset(leaf, iref, root_objectid);
+ }
+ btrfs_mark_buffer_dirty(leaf);
+ return 0;
+}
+
+static int lookup_extent_backref(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ struct btrfs_path *path,
+ struct btrfs_extent_inline_ref **ref_ret,
+ u64 bytenr, u64 num_bytes, u64 parent,
+ u64 root_objectid, u64 owner, u64 offset)
+{
+ int ret;
+
+ ret = lookup_inline_extent_backref(trans, root, path, ref_ret,
+ bytenr, num_bytes, parent,
+ root_objectid, owner, offset, 0);
+ if (ret != -ENOENT)
+ return ret;
+
+ btrfs_release_path(path);
+ *ref_ret = NULL;
+
+ if (owner < BTRFS_FIRST_FREE_OBJECTID) {
+ ret = lookup_tree_block_ref(trans, root, path, bytenr, parent,
+ root_objectid);
+ } else {
+ ret = lookup_extent_data_ref(trans, root, path, bytenr, parent,
+ root_objectid, owner, offset);
+ }
+ return ret;
+}
+
+static int update_inline_extent_backref(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ struct btrfs_path *path,
+ struct btrfs_extent_inline_ref *iref,
+ int refs_to_mod)
+{
+ struct extent_buffer *leaf;
+ struct btrfs_extent_item *ei;
+ struct btrfs_extent_data_ref *dref = NULL;
+ struct btrfs_shared_data_ref *sref = NULL;
+ unsigned long ptr;
+ unsigned long end;
+ u32 item_size;
+ int size;
+ int type;
+ int ret;
+ u64 refs;
+
+ leaf = path->nodes[0];
+ ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item);
+ refs = btrfs_extent_refs(leaf, ei);
+ WARN_ON(refs_to_mod < 0 && refs + refs_to_mod <= 0);
+ refs += refs_to_mod;
+ btrfs_set_extent_refs(leaf, ei, refs);
+
+ type = btrfs_extent_inline_ref_type(leaf, iref);
+
+ if (type == BTRFS_EXTENT_DATA_REF_KEY) {
+ dref = (struct btrfs_extent_data_ref *)(&iref->offset);
+ refs = btrfs_extent_data_ref_count(leaf, dref);
+ } else if (type == BTRFS_SHARED_DATA_REF_KEY) {
+ sref = (struct btrfs_shared_data_ref *)(iref + 1);
+ refs = btrfs_shared_data_ref_count(leaf, sref);
+ } else {
+ refs = 1;
+ BUG_ON(refs_to_mod != -1);
+ }
+
+ BUG_ON(refs_to_mod < 0 && refs < -refs_to_mod);
+ refs += refs_to_mod;
+
+ if (refs > 0) {
+ if (type == BTRFS_EXTENT_DATA_REF_KEY)
+ btrfs_set_extent_data_ref_count(leaf, dref, refs);
+ else
+ btrfs_set_shared_data_ref_count(leaf, sref, refs);
+ } else {
+ size = btrfs_extent_inline_ref_size(type);
+ item_size = btrfs_item_size_nr(leaf, path->slots[0]);
+ ptr = (unsigned long)iref;
+ end = (unsigned long)ei + item_size;
+ if (ptr + size < end)
+ memmove_extent_buffer(leaf, ptr, ptr + size,
+ end - ptr - size);
+ item_size -= size;
+ ret = btrfs_truncate_item(root, path, item_size, 1);
+ BUG_ON(ret);
+ }
+ btrfs_mark_buffer_dirty(leaf);
+ return 0;
+}
+
+static int insert_inline_extent_backref(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ struct btrfs_path *path,
+ u64 bytenr, u64 num_bytes, u64 parent,
+ u64 root_objectid, u64 owner,
+ u64 offset, int refs_to_add)
+{
+ struct btrfs_extent_inline_ref *iref;
+ int ret;
+
+ ret = lookup_inline_extent_backref(trans, root, path, &iref,
+ bytenr, num_bytes, parent,
+ root_objectid, owner, offset, 1);
+ if (ret == 0) {
+ BUG_ON(owner < BTRFS_FIRST_FREE_OBJECTID);
+ ret = update_inline_extent_backref(trans, root, path, iref,
+ refs_to_add);
+ } else if (ret == -ENOENT) {
+ ret = setup_inline_extent_backref(root, path, iref,
+ parent, root_objectid,
+ owner, offset, refs_to_add);
+ }
+ return ret;
+}
+
+static int insert_extent_backref(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ struct btrfs_path *path,
+ u64 bytenr, u64 parent, u64 root_objectid,
+ u64 owner, u64 offset, int refs_to_add)
+{
+ int ret;
+
+ if (owner >= BTRFS_FIRST_FREE_OBJECTID) {
+ ret = insert_extent_data_ref(trans, root, path, bytenr,
+ parent, root_objectid,
+ owner, offset, refs_to_add);
+ } else {
+ BUG_ON(refs_to_add != 1);
+ ret = insert_tree_block_ref(trans, root, path, bytenr,
+ parent, root_objectid);
+ }
+ return ret;
+}
+
+static int remove_extent_backref(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ struct btrfs_path *path,
+ struct btrfs_extent_inline_ref *iref,
+ int refs_to_drop, int is_data)
+{
+ int ret;
+
+ BUG_ON(!is_data && refs_to_drop != 1);
+ if (iref) {
+ ret = update_inline_extent_backref(trans, root, path, iref,
+ -refs_to_drop);
+ } else if (is_data) {
+ ret = remove_extent_data_ref(trans, root, path, refs_to_drop);
+ } else {
+ ret = btrfs_del_item(trans, root, path);
+ }
+ return ret;
+}
+
+int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ u64 bytenr, u64 num_bytes, u64 parent,
+ u64 root_objectid, u64 owner, u64 offset)
+{
+ struct btrfs_path *path;
+ struct extent_buffer *leaf;
+ struct btrfs_extent_item *item;
+ u64 refs;
+ int ret;
+ int err = 0;
+
+ path = btrfs_alloc_path();
+ if (!path)
+ return -ENOMEM;
+
+ path->reada = 1;
+
+ ret = insert_inline_extent_backref(trans, root->fs_info->extent_root,
+ path, bytenr, num_bytes, parent,
+ root_objectid, owner, offset, 1);
+ if (ret == 0)
+ goto out;
+
+ if (ret != -EAGAIN) {
+ err = ret;
+ goto out;
+ }
+
+ leaf = path->nodes[0];
+ item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item);
+ refs = btrfs_extent_refs(leaf, item);
+ btrfs_set_extent_refs(leaf, item, refs + 1);
+
+ btrfs_mark_buffer_dirty(leaf);
+ btrfs_release_path(path);
+
+ path->reada = 1;
+
+ /* now insert the actual backref */
+ ret = insert_extent_backref(trans, root->fs_info->extent_root,
+ path, bytenr, parent, root_objectid,
+ owner, offset, 1);
+ if (ret)
+ err = ret;
+out:
+ btrfs_free_path(path);
+ finish_current_insert(trans, root->fs_info->extent_root);
+ del_pending_extents(trans, root->fs_info->extent_root);
+ BUG_ON(err);
+ return err;
+}
+
+int btrfs_extent_post_op(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root)
+{
+ finish_current_insert(trans, root->fs_info->extent_root);
+ del_pending_extents(trans, root->fs_info->extent_root);
+ return 0;
+}
+
+int btrfs_lookup_extent_info(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root, u64 bytenr,
+ u64 offset, int metadata, u64 *refs, u64 *flags)
+{
+ struct btrfs_path *path;
+ int ret;
+ struct btrfs_key key;
+ struct extent_buffer *l;
+ struct btrfs_extent_item *item;
+ u32 item_size;
+ u64 num_refs;
+ u64 extent_flags;
+
+ if (metadata &&
+ !btrfs_fs_incompat(root->fs_info, SKINNY_METADATA)) {
+ offset = root->fs_info->nodesize;
+ metadata = 0;
+ }
+
+ path = btrfs_alloc_path();
+ if (!path)
+ return -ENOMEM;
+ path->reada = 1;
+
+ key.objectid = bytenr;
+ key.offset = offset;
+ if (metadata)
+ key.type = BTRFS_METADATA_ITEM_KEY;
+ else
+ key.type = BTRFS_EXTENT_ITEM_KEY;
+
+again:
+ ret = btrfs_search_slot(trans, root->fs_info->extent_root, &key, path,
+ 0, 0);
+ if (ret < 0)
+ goto out;
+
+ /*
+ * Deal with the fact that we may have mixed SKINNY and normal refs. If
+ * we didn't find what we wanted check and see if we have a normal ref
+ * right next to us, or re-search if we are on the edge of the leaf just
+ * to make sure.
+ */
+ if (ret > 0 && metadata) {
+ if (path->slots[0]) {
+ path->slots[0]--;
+ btrfs_item_key_to_cpu(path->nodes[0], &key,
+ path->slots[0]);
+ if (key.objectid == bytenr &&
+ key.type == BTRFS_EXTENT_ITEM_KEY &&
+ key.offset == root->fs_info->nodesize)
+ ret = 0;
+ }
+
+ if (ret) {
+ btrfs_release_path(path);
+ key.type = BTRFS_EXTENT_ITEM_KEY;
+ key.offset = root->fs_info->nodesize;
+ metadata = 0;
+ goto again;
+ }
+ }
+
+ if (ret != 0) {
+ ret = -EIO;
+ goto out;
+ }
+
+ l = path->nodes[0];
+ item_size = btrfs_item_size_nr(l, path->slots[0]);
+ if (item_size >= sizeof(*item)) {
+ item = btrfs_item_ptr(l, path->slots[0],
+ struct btrfs_extent_item);
+ num_refs = btrfs_extent_refs(l, item);
+ extent_flags = btrfs_extent_flags(l, item);
+ } else {
+#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
+ struct btrfs_extent_item_v0 *ei0;
+ BUG_ON(item_size != sizeof(*ei0));
+ ei0 = btrfs_item_ptr(l, path->slots[0],
+ struct btrfs_extent_item_v0);
+ num_refs = btrfs_extent_refs_v0(l, ei0);
+ /* FIXME: this isn't correct for data */
+ extent_flags = BTRFS_BLOCK_FLAG_FULL_BACKREF;
+#else
+ BUG();
+#endif
+ }
+ item = btrfs_item_ptr(l, path->slots[0], struct btrfs_extent_item);
+ if (refs)
+ *refs = num_refs;
+ if (flags)
+ *flags = extent_flags;
+out:
+ btrfs_free_path(path);
+ return ret;
+}
+
+int btrfs_set_block_flags(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ u64 bytenr, int level, u64 flags)
+{
+ struct btrfs_path *path;
+ int ret;
+ struct btrfs_key key;
+ struct extent_buffer *l;
+ struct btrfs_extent_item *item;
+ u32 item_size;
+ int skinny_metadata =
+ btrfs_fs_incompat(root->fs_info, SKINNY_METADATA);
+
+ path = btrfs_alloc_path();
+ if (!path)
+ return -ENOMEM;
+ path->reada = 1;
+
+ key.objectid = bytenr;
+ if (skinny_metadata) {
+ key.offset = level;
+ key.type = BTRFS_METADATA_ITEM_KEY;
+ } else {
+ key.offset = root->fs_info->nodesize;
+ key.type = BTRFS_EXTENT_ITEM_KEY;
+ }
+
+again:
+ ret = btrfs_search_slot(trans, root->fs_info->extent_root, &key, path,
+ 0, 0);
+ if (ret < 0)
+ goto out;
+
+ if (ret > 0 && skinny_metadata) {
+ skinny_metadata = 0;
+ if (path->slots[0]) {
+ path->slots[0]--;
+ btrfs_item_key_to_cpu(path->nodes[0], &key,
+ path->slots[0]);
+ if (key.objectid == bytenr &&
+ key.offset == root->fs_info->nodesize &&
+ key.type == BTRFS_EXTENT_ITEM_KEY)
+ ret = 0;
+ }
+ if (ret) {
+ btrfs_release_path(path);
+ key.offset = root->fs_info->nodesize;
+ key.type = BTRFS_EXTENT_ITEM_KEY;
+ goto again;
+ }
+ }
+
+ if (ret != 0) {
+ btrfs_print_leaf(root, path->nodes[0]);
+ printk("failed to find block number %Lu\n",
+ (unsigned long long)bytenr);
+ BUG();
+ }
+ l = path->nodes[0];
+ item_size = btrfs_item_size_nr(l, path->slots[0]);
+#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
+ if (item_size < sizeof(*item)) {
+ ret = convert_extent_item_v0(trans, root->fs_info->extent_root,
+ path, (u64)-1, 0);
+ if (ret < 0)
+ goto out;
+
+ l = path->nodes[0];
+ item_size = btrfs_item_size_nr(l, path->slots[0]);
+ }
+#endif
+ BUG_ON(item_size < sizeof(*item));
+ item = btrfs_item_ptr(l, path->slots[0], struct btrfs_extent_item);
+ flags |= btrfs_extent_flags(l, item);
+ btrfs_set_extent_flags(l, item, flags);
+out:
+ btrfs_free_path(path);
+ finish_current_insert(trans, root->fs_info->extent_root);
+ del_pending_extents(trans, root->fs_info->extent_root);
+ return ret;
+}
+
+static int __btrfs_mod_ref(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ struct extent_buffer *buf,
+ int record_parent, int inc)
+{
+ u64 bytenr;
+ u64 num_bytes;
+ u64 parent;
+ u64 ref_root;
+ u32 nritems;
+ struct btrfs_key key;
+ struct btrfs_file_extent_item *fi;
+ int i;
+ int level;
+ int ret = 0;
+ int (*process_func)(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ u64, u64, u64, u64, u64, u64);
+
+ ref_root = btrfs_header_owner(buf);
+ nritems = btrfs_header_nritems(buf);
+ level = btrfs_header_level(buf);
+
+ if (!root->ref_cows && level == 0)
+ return 0;
+
+ if (inc)
+ process_func = btrfs_inc_extent_ref;
+ else
+ process_func = btrfs_free_extent;
+
+ if (record_parent)
+ parent = buf->start;
+ else
+ parent = 0;
+
+ for (i = 0; i < nritems; i++) {
+ cond_resched();
+ if (level == 0) {
+ btrfs_item_key_to_cpu(buf, &key, i);
+ if (key.type != BTRFS_EXTENT_DATA_KEY)
+ continue;
+ fi = btrfs_item_ptr(buf, i,
+ struct btrfs_file_extent_item);
+ if (btrfs_file_extent_type(buf, fi) ==
+ BTRFS_FILE_EXTENT_INLINE)
+ continue;
+ bytenr = btrfs_file_extent_disk_bytenr(buf, fi);
+ if (bytenr == 0)
+ continue;
+
+ num_bytes = btrfs_file_extent_disk_num_bytes(buf, fi);
+ key.offset -= btrfs_file_extent_offset(buf, fi);
+ ret = process_func(trans, root, bytenr, num_bytes,
+ parent, ref_root, key.objectid,
+ key.offset);
+ if (ret) {
+ WARN_ON(1);
+ goto fail;
+ }
+ } else {
+ bytenr = btrfs_node_blockptr(buf, i);
+ num_bytes = root->fs_info->nodesize;
+ ret = process_func(trans, root, bytenr, num_bytes,
+ parent, ref_root, level - 1, 0);
+ if (ret) {
+ WARN_ON(1);
+ goto fail;
+ }
+ }
+ }
+ return 0;
+fail:
+ WARN_ON(1);
+ return ret;
+}
+
+int btrfs_inc_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
+ struct extent_buffer *buf, int record_parent)
+{
+ return __btrfs_mod_ref(trans, root, buf, record_parent, 1);
+}
+
+int btrfs_dec_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
+ struct extent_buffer *buf, int record_parent)
+{
+ return __btrfs_mod_ref(trans, root, buf, record_parent, 0);
+}
+
+static int write_one_cache_group(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ struct btrfs_path *path,
+ struct btrfs_block_group_cache *cache)
+{
+ int ret;
+ int pending_ret;
+ struct btrfs_root *extent_root = root->fs_info->extent_root;
+ unsigned long bi;
+ struct extent_buffer *leaf;
+
+ ret = btrfs_search_slot(trans, extent_root, &cache->key, path, 0, 1);
+ if (ret < 0)
+ goto fail;
+ BUG_ON(ret);
+
+ leaf = path->nodes[0];
+ bi = btrfs_item_ptr_offset(leaf, path->slots[0]);
+ write_extent_buffer(leaf, &cache->item, bi, sizeof(cache->item));
+ btrfs_mark_buffer_dirty(leaf);
+ btrfs_release_path(path);
+fail:
+ finish_current_insert(trans, extent_root);
+ pending_ret = del_pending_extents(trans, extent_root);
+ if (ret)
+ return ret;
+ if (pending_ret)
+ return pending_ret;
+ return 0;
+
+}
+
+int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root)
+{
+ struct extent_io_tree *block_group_cache;
+ struct btrfs_block_group_cache *cache;
+ int ret;
+ struct btrfs_path *path;
+ u64 last = 0;
+ u64 start;
+ u64 end;
+ u64 ptr;
+
+ block_group_cache = &root->fs_info->block_group_cache;
+ path = btrfs_alloc_path();
+ if (!path)
+ return -ENOMEM;
+
+ while(1) {
+ ret = find_first_extent_bit(block_group_cache, last,
+ &start, &end, BLOCK_GROUP_DIRTY);
+ if (ret) {
+ if (last == 0)
+ break;
+ last = 0;
+ continue;
+ }
+
+ last = end + 1;
+ ret = get_state_private(block_group_cache, start, &ptr);
+ BUG_ON(ret);
+
+ clear_extent_bits(block_group_cache, start, end,
+ BLOCK_GROUP_DIRTY);
+
+ cache = (struct btrfs_block_group_cache *)(unsigned long)ptr;
+ ret = write_one_cache_group(trans, root, path, cache);
+ }
+ btrfs_free_path(path);
+ return 0;
+}
+
+static struct btrfs_space_info *__find_space_info(struct btrfs_fs_info *info,
+ u64 flags)
+{
+ struct btrfs_space_info *found;
+
+ flags &= BTRFS_BLOCK_GROUP_TYPE_MASK;
+
+ list_for_each_entry(found, &info->space_info, list) {
+ if (found->flags & flags)
+ return found;
+ }
+ return NULL;
+
+}
+
+static int free_space_info(struct btrfs_fs_info *fs_info, u64 flags,
+ u64 total_bytes, u64 bytes_used,
+ struct btrfs_space_info **space_info)
+{
+ struct btrfs_space_info *found;
+
+ /* only support free block group which is empty */
+ if (bytes_used)
+ return -ENOTEMPTY;
+
+ found = __find_space_info(fs_info, flags);
+ if (!found)
+ return -ENOENT;
+ if (found->total_bytes < total_bytes) {
+ fprintf(stderr,
+ "WARNING: bad space info to free %llu only have %llu\n",
+ total_bytes, found->total_bytes);
+ return -EINVAL;
+ }
+ found->total_bytes -= total_bytes;
+ if (space_info)
+ *space_info = found;
+ return 0;
+}
+
+static int update_space_info(struct btrfs_fs_info *info, u64 flags,
+ u64 total_bytes, u64 bytes_used,
+ struct btrfs_space_info **space_info)
+{
+ struct btrfs_space_info *found;
+
+ found = __find_space_info(info, flags);
+ if (found) {
+ found->total_bytes += total_bytes;
+ found->bytes_used += bytes_used;
+ if (found->total_bytes < found->bytes_used) {
+ fprintf(stderr, "warning, bad space info total_bytes "
+ "%llu used %llu\n",
+ (unsigned long long)found->total_bytes,
+ (unsigned long long)found->bytes_used);
+ }
+ *space_info = found;
+ return 0;
+ }
+ found = kmalloc(sizeof(*found), GFP_NOFS);
+ if (!found)
+ return -ENOMEM;
+
+ list_add(&found->list, &info->space_info);
+ found->flags = flags & BTRFS_BLOCK_GROUP_TYPE_MASK;
+ found->total_bytes = total_bytes;
+ found->bytes_used = bytes_used;
+ found->bytes_pinned = 0;
+ found->full = 0;
+ *space_info = found;
+ return 0;
+}
+
+
+static void set_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags)
+{
+ u64 extra_flags = flags & (BTRFS_BLOCK_GROUP_RAID0 |
+ BTRFS_BLOCK_GROUP_RAID1 |
+ BTRFS_BLOCK_GROUP_RAID10 |
+ BTRFS_BLOCK_GROUP_RAID5 |
+ BTRFS_BLOCK_GROUP_RAID6 |
+ BTRFS_BLOCK_GROUP_DUP);
+ if (extra_flags) {
+ if (flags & BTRFS_BLOCK_GROUP_DATA)
+ fs_info->avail_data_alloc_bits |= extra_flags;
+ if (flags & BTRFS_BLOCK_GROUP_METADATA)
+ fs_info->avail_metadata_alloc_bits |= extra_flags;
+ if (flags & BTRFS_BLOCK_GROUP_SYSTEM)
+ fs_info->avail_system_alloc_bits |= extra_flags;
+ }
+}
+
+static int do_chunk_alloc(struct btrfs_trans_handle *trans,
+ struct btrfs_fs_info *fs_info, u64 alloc_bytes,
+ u64 flags)
+{
+ struct btrfs_space_info *space_info;
+ u64 thresh;
+ u64 start;
+ u64 num_bytes;
+ int ret;
+
+ space_info = __find_space_info(fs_info, flags);
+ if (!space_info) {
+ ret = update_space_info(fs_info, flags, 0, 0, &space_info);
+ BUG_ON(ret);
+ }
+ BUG_ON(!space_info);
+
+ if (space_info->full)
+ return 0;
+
+ thresh = div_factor(space_info->total_bytes, 7);
+ if ((space_info->bytes_used + space_info->bytes_pinned + alloc_bytes) <
+ thresh)
+ return 0;
+
+ /*
+ * Avoid allocating given chunk type
+ */
+ if (fs_info->avoid_meta_chunk_alloc &&
+ (flags & BTRFS_BLOCK_GROUP_METADATA))
+ return 0;
+ if (fs_info->avoid_sys_chunk_alloc &&
+ (flags & BTRFS_BLOCK_GROUP_SYSTEM))
+ return 0;
+
+ ret = btrfs_alloc_chunk(trans, fs_info, &start, &num_bytes,
+ space_info->flags);
+ if (ret == -ENOSPC) {
+ space_info->full = 1;
+ return 0;
+ }
+
+ BUG_ON(ret);
+
+ ret = btrfs_make_block_group(trans, fs_info, 0, space_info->flags,
+ start, num_bytes);
+ BUG_ON(ret);
+ return 0;
+}
+
+static int update_block_group(struct btrfs_root *root,
+ u64 bytenr, u64 num_bytes, int alloc,
+ int mark_free)
+{
+ struct btrfs_block_group_cache *cache;
+ struct btrfs_fs_info *info = root->fs_info;
+ u64 total = num_bytes;
+ u64 old_val;
+ u64 byte_in_group;
+ u64 start;
+ u64 end;
+
+ /* block accounting for super block */
+ old_val = btrfs_super_bytes_used(info->super_copy);
+ if (alloc)
+ old_val += num_bytes;
+ else
+ old_val -= num_bytes;
+ btrfs_set_super_bytes_used(info->super_copy, old_val);
+
+ /* block accounting for root item */
+ old_val = btrfs_root_used(&root->root_item);
+ if (alloc)
+ old_val += num_bytes;
+ else
+ old_val -= num_bytes;
+ btrfs_set_root_used(&root->root_item, old_val);
+
+ while(total) {
+ cache = btrfs_lookup_block_group(info, bytenr);
+ if (!cache) {
+ return -1;
+ }
+ byte_in_group = bytenr - cache->key.objectid;
+ WARN_ON(byte_in_group > cache->key.offset);
+ start = cache->key.objectid;
+ end = start + cache->key.offset - 1;
+ set_extent_bits(&info->block_group_cache, start, end,
+ BLOCK_GROUP_DIRTY);
+
+ old_val = btrfs_block_group_used(&cache->item);
+ num_bytes = min(total, cache->key.offset - byte_in_group);
+
+ if (alloc) {
+ old_val += num_bytes;
+ cache->space_info->bytes_used += num_bytes;
+ } else {
+ old_val -= num_bytes;
+ cache->space_info->bytes_used -= num_bytes;
+ if (mark_free) {
+ set_extent_dirty(&info->free_space_cache,
+ bytenr, bytenr + num_bytes - 1);
+ }
+ }
+ btrfs_set_block_group_used(&cache->item, old_val);
+ total -= num_bytes;
+ bytenr += num_bytes;
+ }
+ return 0;
+}
+
+static int update_pinned_extents(struct btrfs_root *root,
+ u64 bytenr, u64 num, int pin)
+{
+ u64 len;
+ struct btrfs_block_group_cache *cache;
+ struct btrfs_fs_info *fs_info = root->fs_info;
+
+ if (pin) {
+ set_extent_dirty(&fs_info->pinned_extents,
+ bytenr, bytenr + num - 1);
+ } else {
+ clear_extent_dirty(&fs_info->pinned_extents,
+ bytenr, bytenr + num - 1);
+ }
+ while (num > 0) {
+ cache = btrfs_lookup_block_group(fs_info, bytenr);
+ if (!cache) {
+ len = min((u64)fs_info->sectorsize, num);
+ goto next;
+ }
+ WARN_ON(!cache);
+ len = min(num, cache->key.offset -
+ (bytenr - cache->key.objectid));
+ if (pin) {
+ cache->pinned += len;
+ cache->space_info->bytes_pinned += len;
+ fs_info->total_pinned += len;
+ } else {
+ cache->pinned -= len;
+ cache->space_info->bytes_pinned -= len;
+ fs_info->total_pinned -= len;
+ }
+next:
+ bytenr += len;
+ num -= len;
+ }
+ return 0;
+}
+
+int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ struct extent_io_tree *unpin)
+{
+ u64 start;
+ u64 end;
+ int ret;
+ struct extent_io_tree *free_space_cache;
+ free_space_cache = &root->fs_info->free_space_cache;
+
+ while(1) {
+ ret = find_first_extent_bit(unpin, 0, &start, &end,
+ EXTENT_DIRTY);
+ if (ret)
+ break;
+ update_pinned_extents(root, start, end + 1 - start, 0);
+ clear_extent_dirty(unpin, start, end);
+ set_extent_dirty(free_space_cache, start, end);
+ }
+ return 0;
+}
+
+static int extent_root_pending_ops(struct btrfs_fs_info *info)
+{
+ u64 start;
+ u64 end;
+ int ret;
+
+ ret = find_first_extent_bit(&info->extent_ins, 0, &start,
+ &end, EXTENT_LOCKED);
+ if (!ret) {
+ ret = find_first_extent_bit(&info->pending_del, 0, &start, &end,
+ EXTENT_LOCKED);
+ }
+ return ret == 0;
+
+}
+static int finish_current_insert(struct btrfs_trans_handle *trans,
+ struct btrfs_root *extent_root)
+{
+ u64 start;
+ u64 end;
+ u64 priv;
+ struct btrfs_fs_info *info = extent_root->fs_info;
+ struct pending_extent_op *extent_op;
+ struct btrfs_key key;
+ int ret;
+ int skinny_metadata =
+ btrfs_fs_incompat(extent_root->fs_info, SKINNY_METADATA);
+
+ while(1) {
+ ret = find_first_extent_bit(&info->extent_ins, 0, &start,
+ &end, EXTENT_LOCKED);
+ if (ret)
+ break;
+
+ ret = get_state_private(&info->extent_ins, start, &priv);
+ BUG_ON(ret);
+ extent_op = (struct pending_extent_op *)(unsigned long)priv;
+
+ if (extent_op->type == PENDING_EXTENT_INSERT) {
+ key.objectid = start;
+ if (skinny_metadata) {
+ key.offset = extent_op->level;
+ key.type = BTRFS_METADATA_ITEM_KEY;
+ } else {
+ key.offset = extent_op->num_bytes;
+ key.type = BTRFS_EXTENT_ITEM_KEY;
+ }
+ ret = alloc_reserved_tree_block(trans, extent_root,
+ extent_root->root_key.objectid,
+ trans->transid,
+ extent_op->flags,
+ &extent_op->key,
+ extent_op->level, &key);
+ BUG_ON(ret);
+ } else {
+ BUG_ON(1);
+ }
+
+ clear_extent_bits(&info->extent_ins, start, end, EXTENT_LOCKED);
+ kfree(extent_op);
+ }
+ return 0;
+}
+
+static int pin_down_bytes(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ u64 bytenr, u64 num_bytes, int is_data)
+{
+ int err = 0;
+ struct extent_buffer *buf;
+
+ if (is_data)
+ goto pinit;
+
+ buf = btrfs_find_tree_block(root->fs_info, bytenr, num_bytes);
+ if (!buf)
+ goto pinit;
+
+ /* we can reuse a block if it hasn't been written
+ * and it is from this transaction. We can't
+ * reuse anything from the tree log root because
+ * it has tiny sub-transactions.
+ */
+ if (btrfs_buffer_uptodate(buf, 0)) {
+ u64 header_owner = btrfs_header_owner(buf);
+ u64 header_transid = btrfs_header_generation(buf);
+ if (header_owner != BTRFS_TREE_LOG_OBJECTID &&
+ header_transid == trans->transid &&
+ !btrfs_header_flag(buf, BTRFS_HEADER_FLAG_WRITTEN)) {
+ clean_tree_block(NULL, root, buf);
+ free_extent_buffer(buf);
+ return 1;
+ }
+ }
+ free_extent_buffer(buf);
+pinit:
+ update_pinned_extents(root, bytenr, num_bytes, 1);
+
+ BUG_ON(err < 0);
+ return 0;
+}
+
+void btrfs_pin_extent(struct btrfs_fs_info *fs_info,
+ u64 bytenr, u64 num_bytes)
+{
+ update_pinned_extents(fs_info->extent_root, bytenr, num_bytes, 1);
+}
+
+void btrfs_unpin_extent(struct btrfs_fs_info *fs_info,
+ u64 bytenr, u64 num_bytes)
+{
+ update_pinned_extents(fs_info->extent_root, bytenr, num_bytes, 0);
+}
+
+/*
+ * remove an extent from the root, returns 0 on success
+ */
+static int __free_extent(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ u64 bytenr, u64 num_bytes, u64 parent,
+ u64 root_objectid, u64 owner_objectid,
+ u64 owner_offset, int refs_to_drop)
+{
+
+ struct btrfs_key key;
+ struct btrfs_path *path;
+ struct btrfs_root *extent_root = root->fs_info->extent_root;
+ struct extent_buffer *leaf;
+ struct btrfs_extent_item *ei;
+ struct btrfs_extent_inline_ref *iref;
+ int ret;
+ int is_data;
+ int extent_slot = 0;
+ int found_extent = 0;
+ int num_to_del = 1;
+ u32 item_size;
+ u64 refs;
+ int skinny_metadata =
+ btrfs_fs_incompat(extent_root->fs_info, SKINNY_METADATA);
+
+ if (root->fs_info->free_extent_hook) {
+ root->fs_info->free_extent_hook(trans, root, bytenr, num_bytes,
+ parent, root_objectid, owner_objectid,
+ owner_offset, refs_to_drop);
+
+ }
+ path = btrfs_alloc_path();
+ if (!path)
+ return -ENOMEM;
+
+ path->reada = 1;
+
+ is_data = owner_objectid >= BTRFS_FIRST_FREE_OBJECTID;
+ if (is_data)
+ skinny_metadata = 0;
+ BUG_ON(!is_data && refs_to_drop != 1);
+
+ ret = lookup_extent_backref(trans, extent_root, path, &iref,
+ bytenr, num_bytes, parent,
+ root_objectid, owner_objectid,
+ owner_offset);
+ if (ret == 0) {
+ extent_slot = path->slots[0];
+ while (extent_slot >= 0) {
+ btrfs_item_key_to_cpu(path->nodes[0], &key,
+ extent_slot);
+ if (key.objectid != bytenr)
+ break;
+ if (key.type == BTRFS_EXTENT_ITEM_KEY &&
+ key.offset == num_bytes) {
+ found_extent = 1;
+ break;
+ }
+ if (key.type == BTRFS_METADATA_ITEM_KEY &&
+ key.offset == owner_objectid) {
+ found_extent = 1;
+ break;
+ }
+ if (path->slots[0] - extent_slot > 5)
+ break;
+ extent_slot--;
+ }
+#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
+ item_size = btrfs_item_size_nr(path->nodes[0], extent_slot);
+ if (found_extent && item_size < sizeof(*ei))
+ found_extent = 0;
+#endif
+ if (!found_extent) {
+ BUG_ON(iref);
+ ret = remove_extent_backref(trans, extent_root, path,
+ NULL, refs_to_drop,
+ is_data);
+ BUG_ON(ret);
+ btrfs_release_path(path);
+
+ key.objectid = bytenr;
+
+ if (skinny_metadata) {
+ key.type = BTRFS_METADATA_ITEM_KEY;
+ key.offset = owner_objectid;
+ } else {
+ key.type = BTRFS_EXTENT_ITEM_KEY;
+ key.offset = num_bytes;
+ }
+
+ ret = btrfs_search_slot(trans, extent_root,
+ &key, path, -1, 1);
+ if (ret > 0 && skinny_metadata && path->slots[0]) {
+ path->slots[0]--;
+ btrfs_item_key_to_cpu(path->nodes[0],
+ &key,
+ path->slots[0]);
+ if (key.objectid == bytenr &&
+ key.type == BTRFS_EXTENT_ITEM_KEY &&
+ key.offset == num_bytes)
+ ret = 0;
+ }
+
+ if (ret > 0 && skinny_metadata) {
+ skinny_metadata = 0;
+ btrfs_release_path(path);
+ key.type = BTRFS_EXTENT_ITEM_KEY;
+ key.offset = num_bytes;
+ ret = btrfs_search_slot(trans, extent_root,
+ &key, path, -1, 1);
+ }
+
+ if (ret) {
+ printk(KERN_ERR "umm, got %d back from search"
+ ", was looking for %llu\n", ret,
+ (unsigned long long)bytenr);
+ btrfs_print_leaf(extent_root, path->nodes[0]);
+ }
+ BUG_ON(ret);
+ extent_slot = path->slots[0];
+ }
+ } else {
+ printk(KERN_ERR "btrfs unable to find ref byte nr %llu "
+ "parent %llu root %llu owner %llu offset %llu\n",
+ (unsigned long long)bytenr,
+ (unsigned long long)parent,
+ (unsigned long long)root_objectid,
+ (unsigned long long)owner_objectid,
+ (unsigned long long)owner_offset);
+ ret = -EIO;
+ goto fail;
+ }
+
+ leaf = path->nodes[0];
+ item_size = btrfs_item_size_nr(leaf, extent_slot);
+#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
+ if (item_size < sizeof(*ei)) {
+ BUG_ON(found_extent || extent_slot != path->slots[0]);
+ ret = convert_extent_item_v0(trans, extent_root, path,
+ owner_objectid, 0);
+ BUG_ON(ret < 0);
+
+ btrfs_release_path(path);
+
+ key.objectid = bytenr;
+ key.type = BTRFS_EXTENT_ITEM_KEY;
+ key.offset = num_bytes;
+
+ ret = btrfs_search_slot(trans, extent_root, &key, path,
+ -1, 1);
+ if (ret) {
+ printk(KERN_ERR "umm, got %d back from search"
+ ", was looking for %llu\n", ret,
+ (unsigned long long)bytenr);
+ btrfs_print_leaf(extent_root, path->nodes[0]);
+ }
+ BUG_ON(ret);
+ extent_slot = path->slots[0];
+ leaf = path->nodes[0];
+ item_size = btrfs_item_size_nr(leaf, extent_slot);
+ }
+#endif
+ BUG_ON(item_size < sizeof(*ei));
+ ei = btrfs_item_ptr(leaf, extent_slot,
+ struct btrfs_extent_item);
+ if (owner_objectid < BTRFS_FIRST_FREE_OBJECTID &&
+ key.type == BTRFS_EXTENT_ITEM_KEY) {
+ struct btrfs_tree_block_info *bi;
+ BUG_ON(item_size < sizeof(*ei) + sizeof(*bi));
+ bi = (struct btrfs_tree_block_info *)(ei + 1);
+ WARN_ON(owner_objectid != btrfs_tree_block_level(leaf, bi));
+ }
+
+ refs = btrfs_extent_refs(leaf, ei);
+ BUG_ON(refs < refs_to_drop);
+ refs -= refs_to_drop;
+
+ if (refs > 0) {
+ /*
+ * In the case of inline back ref, reference count will
+ * be updated by remove_extent_backref
+ */
+ if (iref) {
+ BUG_ON(!found_extent);
+ } else {
+ btrfs_set_extent_refs(leaf, ei, refs);
+ btrfs_mark_buffer_dirty(leaf);
+ }
+ if (found_extent) {
+ ret = remove_extent_backref(trans, extent_root, path,
+ iref, refs_to_drop,
+ is_data);
+ BUG_ON(ret);
+ }
+ } else {
+ int mark_free = 0;
+ int pin = 1;
+
+ if (found_extent) {
+ BUG_ON(is_data && refs_to_drop !=
+ extent_data_ref_count(path, iref));
+ if (iref) {
+ BUG_ON(path->slots[0] != extent_slot);
+ } else {
+ BUG_ON(path->slots[0] != extent_slot + 1);
+ path->slots[0] = extent_slot;
+ num_to_del = 2;
+ }
+ }
+
+ if (pin) {
+ ret = pin_down_bytes(trans, root, bytenr, num_bytes,
+ is_data);
+ if (ret > 0)
+ mark_free = 1;
+ BUG_ON(ret < 0);
+ }
+
+ ret = btrfs_del_items(trans, extent_root, path, path->slots[0],
+ num_to_del);
+ BUG_ON(ret);
+ btrfs_release_path(path);
+
+ if (is_data) {
+ ret = btrfs_del_csums(trans, root, bytenr, num_bytes);
+ BUG_ON(ret);
+ }
+
+ update_block_group(root, bytenr, num_bytes, 0, mark_free);
+ }
+fail:
+ btrfs_free_path(path);
+ finish_current_insert(trans, extent_root);
+ return ret;
+}
+
+/*
+ * find all the blocks marked as pending in the radix tree and remove
+ * them from the extent map
+ */
+static int del_pending_extents(struct btrfs_trans_handle *trans, struct
+ btrfs_root *extent_root)
+{
+ int ret;
+ int err = 0;
+ u64 start;
+ u64 end;
+ u64 priv;
+ struct extent_io_tree *pending_del;
+ struct extent_io_tree *extent_ins;
+ struct pending_extent_op *extent_op;
+
+ extent_ins = &extent_root->fs_info->extent_ins;
+ pending_del = &extent_root->fs_info->pending_del;
+
+ while(1) {
+ ret = find_first_extent_bit(pending_del, 0, &start, &end,
+ EXTENT_LOCKED);
+ if (ret)
+ break;
+
+ ret = get_state_private(pending_del, start, &priv);
+ BUG_ON(ret);
+ extent_op = (struct pending_extent_op *)(unsigned long)priv;
+
+ clear_extent_bits(pending_del, start, end, EXTENT_LOCKED);
+
+ if (!test_range_bit(extent_ins, start, end,
+ EXTENT_LOCKED, 0)) {
+ ret = __free_extent(trans, extent_root,
+ start, end + 1 - start, 0,
+ extent_root->root_key.objectid,
+ extent_op->level, 0, 1);
+ kfree(extent_op);
+ } else {
+ kfree(extent_op);
+ ret = get_state_private(extent_ins, start, &priv);
+ BUG_ON(ret);
+ extent_op = (struct pending_extent_op *)
+ (unsigned long)priv;
+
+ clear_extent_bits(extent_ins, start, end,
+ EXTENT_LOCKED);
+
+ if (extent_op->type == PENDING_BACKREF_UPDATE)
+ BUG_ON(1);
+
+ kfree(extent_op);
+ }
+ if (ret)
+ err = ret;
+ }
+ return err;
+}
+
+
+int btrfs_free_tree_block(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ struct extent_buffer *buf,
+ u64 parent, int last_ref)
+{
+ return btrfs_free_extent(trans, root, buf->start, buf->len, parent,
+ root->root_key.objectid,
+ btrfs_header_level(buf), 0);
+}
+
+/*
+ * remove an extent from the root, returns 0 on success
+ */
+
+int btrfs_free_extent(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ u64 bytenr, u64 num_bytes, u64 parent,
+ u64 root_objectid, u64 owner, u64 offset)
+{
+ struct btrfs_root *extent_root = root->fs_info->extent_root;
+ int pending_ret;
+ int ret;
+
+ WARN_ON(num_bytes < root->fs_info->sectorsize);
+ if (root == extent_root) {
+ struct pending_extent_op *extent_op;
+
+ extent_op = kmalloc(sizeof(*extent_op), GFP_NOFS);
+ BUG_ON(!extent_op);
+
+ extent_op->type = PENDING_EXTENT_DELETE;
+ extent_op->bytenr = bytenr;
+ extent_op->num_bytes = num_bytes;
+ extent_op->level = (int)owner;
+
+ set_extent_bits(&root->fs_info->pending_del,
+ bytenr, bytenr + num_bytes - 1,
+ EXTENT_LOCKED);
+ set_state_private(&root->fs_info->pending_del,
+ bytenr, (unsigned long)extent_op);
+ return 0;
+ }
+ ret = __free_extent(trans, root, bytenr, num_bytes, parent,
+ root_objectid, owner, offset, 1);
+ pending_ret = del_pending_extents(trans, root->fs_info->extent_root);
+ return ret ? ret : pending_ret;
+}
+
+static u64 stripe_align(struct btrfs_root *root, u64 val)
+{
+ return round_up(val, (u64)root->fs_info->stripesize);
+}
+
+/*
+ * walks the btree of allocated extents and find a hole of a given size.
+ * The key ins is changed to record the hole:
+ * ins->objectid == block start
+ * ins->flags = BTRFS_EXTENT_ITEM_KEY
+ * ins->offset == number of blocks
+ * Any available blocks before search_start are skipped.
+ */
+static int noinline find_free_extent(struct btrfs_trans_handle *trans,
+ struct btrfs_root *orig_root,
+ u64 num_bytes, u64 empty_size,
+ u64 search_start, u64 search_end,
+ u64 hint_byte, struct btrfs_key *ins,
+ u64 exclude_start, u64 exclude_nr,
+ int data)
+{
+ int ret;
+ u64 orig_search_start = search_start;
+ struct btrfs_root * root = orig_root->fs_info->extent_root;
+ struct btrfs_fs_info *info = root->fs_info;
+ u64 total_needed = num_bytes;
+ struct btrfs_block_group_cache *block_group;
+ int full_scan = 0;
+ int wrapped = 0;
+
+ WARN_ON(num_bytes < info->sectorsize);
+ ins->type = BTRFS_EXTENT_ITEM_KEY;
+
+ search_start = stripe_align(root, search_start);
+
+ if (hint_byte) {
+ block_group = btrfs_lookup_first_block_group(info, hint_byte);
+ if (!block_group)
+ hint_byte = search_start;
+ block_group = btrfs_find_block_group(root, block_group,
+ hint_byte, data, 1);
+ } else {
+ block_group = btrfs_find_block_group(root,
+ trans->block_group,
+ search_start, data, 1);
+ }
+
+ total_needed += empty_size;
+
+check_failed:
+ search_start = stripe_align(root, search_start);
+ if (!block_group) {
+ block_group = btrfs_lookup_first_block_group(info,
+ search_start);
+ if (!block_group)
+ block_group = btrfs_lookup_first_block_group(info,
+ orig_search_start);
+ }
+ ret = find_search_start(root, &block_group, &search_start,
+ total_needed, data);
+ if (ret)
+ goto new_group;
+
+ ins->objectid = search_start;
+ ins->offset = num_bytes;
+
+ if (ins->objectid + num_bytes >
+ block_group->key.objectid + block_group->key.offset) {
+ search_start = block_group->key.objectid +
+ block_group->key.offset;
+ goto new_group;
+ }
+
+ if (test_range_bit(&info->extent_ins, ins->objectid,
+ ins->objectid + num_bytes -1, EXTENT_LOCKED, 0)) {
+ search_start = ins->objectid + num_bytes;
+ goto new_group;
+ }
+
+ if (test_range_bit(&info->pinned_extents, ins->objectid,
+ ins->objectid + num_bytes -1, EXTENT_DIRTY, 0)) {
+ search_start = ins->objectid + num_bytes;
+ goto new_group;
+ }
+
+ if (info->excluded_extents &&
+ test_range_bit(info->excluded_extents, ins->objectid,
+ ins->objectid + num_bytes -1, EXTENT_DIRTY, 0)) {
+ search_start = ins->objectid + num_bytes;
+ goto new_group;
+ }
+
+ if (exclude_nr > 0 && (ins->objectid + num_bytes > exclude_start &&
+ ins->objectid < exclude_start + exclude_nr)) {
+ search_start = exclude_start + exclude_nr;
+ goto new_group;
+ }
+
+ if (!(data & BTRFS_BLOCK_GROUP_DATA)) {
+ if (check_crossing_stripes(info, ins->objectid, num_bytes)) {
+ struct btrfs_block_group_cache *bg_cache;
+ u64 bg_offset;
+
+ bg_cache = btrfs_lookup_block_group(info, ins->objectid);
+ if (!bg_cache)
+ goto no_bg_cache;
+ bg_offset = ins->objectid - bg_cache->key.objectid;
+
+ search_start = round_up(
+ bg_offset + num_bytes, BTRFS_STRIPE_LEN) +
+ bg_cache->key.objectid;
+ goto new_group;
+ }
+no_bg_cache:
+ block_group = btrfs_lookup_block_group(info, ins->objectid);
+ if (block_group)
+ trans->block_group = block_group;
+ }
+ ins->offset = num_bytes;
+ return 0;
+
+new_group:
+ block_group = btrfs_lookup_first_block_group(info, search_start);
+ if (!block_group) {
+ search_start = orig_search_start;
+ if (full_scan) {
+ ret = -ENOSPC;
+ goto error;
+ }
+ if (wrapped) {
+ if (!full_scan)
+ total_needed -= empty_size;
+ full_scan = 1;
+ } else
+ wrapped = 1;
+ }
+ cond_resched();
+ block_group = btrfs_find_block_group(root, block_group,
+ search_start, data, 0);
+ goto check_failed;
+
+error:
+ return ret;
+}
+
+int btrfs_reserve_extent(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ u64 num_bytes, u64 empty_size,
+ u64 hint_byte, u64 search_end,
+ struct btrfs_key *ins, bool is_data)
+{
+ int ret;
+ u64 search_start = 0;
+ u64 alloc_profile;
+ u64 profile;
+ struct btrfs_fs_info *info = root->fs_info;
+
+ if (is_data) {
+ alloc_profile = info->avail_data_alloc_bits &
+ info->data_alloc_profile;
+ profile = BTRFS_BLOCK_GROUP_DATA | alloc_profile;
+ } else if (info->system_allocs == 1 || root == info->chunk_root) {
+ alloc_profile = info->avail_system_alloc_bits &
+ info->system_alloc_profile;
+ profile = BTRFS_BLOCK_GROUP_SYSTEM | alloc_profile;
+ } else {
+ alloc_profile = info->avail_metadata_alloc_bits &
+ info->metadata_alloc_profile;
+ profile = BTRFS_BLOCK_GROUP_METADATA | alloc_profile;
+ }
+
+ if (root->ref_cows) {
+ if (!(profile & BTRFS_BLOCK_GROUP_METADATA)) {
+ ret = do_chunk_alloc(trans, info,
+ num_bytes,
+ BTRFS_BLOCK_GROUP_METADATA);
+ BUG_ON(ret);
+ }
+ ret = do_chunk_alloc(trans, info,
+ num_bytes + SZ_2M, profile);
+ BUG_ON(ret);
+ }
+
+ WARN_ON(num_bytes < info->sectorsize);
+ ret = find_free_extent(trans, root, num_bytes, empty_size,
+ search_start, search_end, hint_byte, ins,
+ trans->alloc_exclude_start,
+ trans->alloc_exclude_nr, profile);
+ if (ret < 0)
+ return ret;
+ clear_extent_dirty(&info->free_space_cache,
+ ins->objectid, ins->objectid + ins->offset - 1);
+ return ret;
+}
+
+static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ u64 root_objectid, u64 generation,
+ u64 flags, struct btrfs_disk_key *key,
+ int level, struct btrfs_key *ins)
+{
+ int ret;
+ struct btrfs_fs_info *fs_info = root->fs_info;
+ struct btrfs_extent_item *extent_item;
+ struct btrfs_tree_block_info *block_info;
+ struct btrfs_extent_inline_ref *iref;
+ struct btrfs_path *path;
+ struct extent_buffer *leaf;
+ u32 size = sizeof(*extent_item) + sizeof(*iref);
+ int skinny_metadata = btrfs_fs_incompat(fs_info, SKINNY_METADATA);
+
+ if (!skinny_metadata)
+ size += sizeof(*block_info);
+
+ path = btrfs_alloc_path();
+ if (!path)
+ return -ENOMEM;
+
+ ret = btrfs_insert_empty_item(trans, fs_info->extent_root, path,
+ ins, size);
+ BUG_ON(ret);
+
+ leaf = path->nodes[0];
+ extent_item = btrfs_item_ptr(leaf, path->slots[0],
+ struct btrfs_extent_item);
+ btrfs_set_extent_refs(leaf, extent_item, 1);
+ btrfs_set_extent_generation(leaf, extent_item, generation);
+ btrfs_set_extent_flags(leaf, extent_item,
+ flags | BTRFS_EXTENT_FLAG_TREE_BLOCK);
+
+ if (skinny_metadata) {
+ iref = (struct btrfs_extent_inline_ref *)(extent_item + 1);
+ } else {
+ block_info = (struct btrfs_tree_block_info *)(extent_item + 1);
+ btrfs_set_tree_block_key(leaf, block_info, key);
+ btrfs_set_tree_block_level(leaf, block_info, level);
+ iref = (struct btrfs_extent_inline_ref *)(block_info + 1);
+ }
+
+ btrfs_set_extent_inline_ref_type(leaf, iref, BTRFS_TREE_BLOCK_REF_KEY);
+ btrfs_set_extent_inline_ref_offset(leaf, iref, root_objectid);
+
+ btrfs_mark_buffer_dirty(leaf);
+ btrfs_free_path(path);
+
+ ret = update_block_group(root, ins->objectid, fs_info->nodesize,
+ 1, 0);
+ return ret;
+}
+
+static int alloc_tree_block(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root, u64 num_bytes,
+ u64 root_objectid, u64 generation,
+ u64 flags, struct btrfs_disk_key *key,
+ int level, u64 empty_size, u64 hint_byte,
+ u64 search_end, struct btrfs_key *ins)
+{
+ int ret;
+ ret = btrfs_reserve_extent(trans, root, num_bytes, empty_size,
+ hint_byte, search_end, ins, 0);
+ BUG_ON(ret);
+
+ if (root_objectid == BTRFS_EXTENT_TREE_OBJECTID) {
+ struct pending_extent_op *extent_op;
+
+ extent_op = kmalloc(sizeof(*extent_op), GFP_NOFS);
+ BUG_ON(!extent_op);
+
+ extent_op->type = PENDING_EXTENT_INSERT;
+ extent_op->bytenr = ins->objectid;
+ extent_op->num_bytes = ins->offset;
+ extent_op->level = level;
+ extent_op->flags = flags;
+ memcpy(&extent_op->key, key, sizeof(*key));
+
+ set_extent_bits(&root->fs_info->extent_ins, ins->objectid,
+ ins->objectid + ins->offset - 1,
+ EXTENT_LOCKED);
+ set_state_private(&root->fs_info->extent_ins,
+ ins->objectid, (unsigned long)extent_op);
+ } else {
+ if (btrfs_fs_incompat(root->fs_info, SKINNY_METADATA)) {
+ ins->offset = level;
+ ins->type = BTRFS_METADATA_ITEM_KEY;
+ }
+ ret = alloc_reserved_tree_block(trans, root, root_objectid,
+ generation, flags,
+ key, level, ins);
+ finish_current_insert(trans, root->fs_info->extent_root);
+ del_pending_extents(trans, root->fs_info->extent_root);
+ }
+ return ret;
+}
+
+/*
+ * helper function to allocate a block for a given tree
+ * returns the tree buffer or NULL.
+ */
+struct extent_buffer *btrfs_alloc_free_block(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ u32 blocksize, u64 root_objectid,
+ struct btrfs_disk_key *key, int level,
+ u64 hint, u64 empty_size)
+{
+ struct btrfs_key ins;
+ int ret;
+ struct extent_buffer *buf;
+
+ ret = alloc_tree_block(trans, root, blocksize, root_objectid,
+ trans->transid, 0, key, level,
+ empty_size, hint, (u64)-1, &ins);
+ if (ret) {
+ BUG_ON(ret > 0);
+ return ERR_PTR(ret);
+ }
+
+ buf = btrfs_find_create_tree_block(root->fs_info, ins.objectid);
+ if (!buf) {
+ btrfs_free_extent(trans, root, ins.objectid, ins.offset,
+ 0, root->root_key.objectid, level, 0);
+ BUG_ON(1);
+ return ERR_PTR(-ENOMEM);
+ }
+ btrfs_set_buffer_uptodate(buf);
+ trans->blocks_used++;
+
+ return buf;
+}
+
+#if 0
+
+static int noinline drop_leaf_ref(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ struct extent_buffer *leaf)
+{
+ u64 leaf_owner;
+ u64 leaf_generation;
+ struct btrfs_key key;
+ struct btrfs_file_extent_item *fi;
+ int i;
+ int nritems;
+ int ret;
+
+ BUG_ON(!btrfs_is_leaf(leaf));
+ nritems = btrfs_header_nritems(leaf);
+ leaf_owner = btrfs_header_owner(leaf);
+ leaf_generation = btrfs_header_generation(leaf);
+
+ for (i = 0; i < nritems; i++) {
+ u64 disk_bytenr;
+
+ btrfs_item_key_to_cpu(leaf, &key, i);
+ if (btrfs_key_type(&key) != BTRFS_EXTENT_DATA_KEY)
+ continue;
+ fi = btrfs_item_ptr(leaf, i, struct btrfs_file_extent_item);
+ if (btrfs_file_extent_type(leaf, fi) ==
+ BTRFS_FILE_EXTENT_INLINE)
+ continue;
+ /*
+ * FIXME make sure to insert a trans record that
+ * repeats the snapshot del on crash
+ */
+ disk_bytenr = btrfs_file_extent_disk_bytenr(leaf, fi);
+ if (disk_bytenr == 0)
+ continue;
+ ret = btrfs_free_extent(trans, root, disk_bytenr,
+ btrfs_file_extent_disk_num_bytes(leaf, fi),
+ leaf->start, leaf_owner, leaf_generation,
+ key.objectid, 0);
+ BUG_ON(ret);
+ }
+ return 0;
+}
+
+static void noinline reada_walk_down(struct btrfs_root *root,
+ struct extent_buffer *node,
+ int slot)
+{
+ u64 bytenr;
+ u64 last = 0;
+ u32 nritems;
+ u32 refs;
+ u32 blocksize;
+ int ret;
+ int i;
+ int level;
+ int skipped = 0;
+
+ nritems = btrfs_header_nritems(node);
+ level = btrfs_header_level(node);
+ if (level)
+ return;
+
+ for (i = slot; i < nritems && skipped < 32; i++) {
+ bytenr = btrfs_node_blockptr(node, i);
+ if (last && ((bytenr > last && bytenr - last > SZ_32K) ||
+ (last > bytenr && last - bytenr > SZ_32K))) {
+ skipped++;
+ continue;
+ }
+ blocksize = btrfs_level_size(root, level - 1);
+ if (i != slot) {
+ ret = btrfs_lookup_extent_ref(NULL, root, bytenr,
+ blocksize, &refs);
+ BUG_ON(ret);
+ if (refs != 1) {
+ skipped++;
+ continue;
+ }
+ }
+ mutex_unlock(&root->fs_info->fs_mutex);
+ ret = readahead_tree_block(root, bytenr, blocksize,
+ btrfs_node_ptr_generation(node, i));
+ last = bytenr + blocksize;
+ cond_resched();
+ mutex_lock(&root->fs_info->fs_mutex);
+ if (ret)
+ break;
+ }
+}
+
+/*
+ * helper function for drop_snapshot, this walks down the tree dropping ref
+ * counts as it goes.
+ */
+static int noinline walk_down_tree(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ struct btrfs_path *path, int *level)
+{
+ u64 root_owner;
+ u64 root_gen;
+ u64 bytenr;
+ u64 ptr_gen;
+ struct extent_buffer *next;
+ struct extent_buffer *cur;
+ struct extent_buffer *parent;
+ u32 blocksize;
+ int ret;
+ u32 refs;
+
+ WARN_ON(*level < 0);
+ WARN_ON(*level >= BTRFS_MAX_LEVEL);
+ ret = btrfs_lookup_extent_ref(trans, root,
+ path->nodes[*level]->start,
+ path->nodes[*level]->len, &refs);
+ BUG_ON(ret);
+ if (refs > 1)
+ goto out;
+
+ /*
+ * walk down to the last node level and free all the leaves
+ */
+ while(*level >= 0) {
+ WARN_ON(*level < 0);
+ WARN_ON(*level >= BTRFS_MAX_LEVEL);
+ cur = path->nodes[*level];
+
+ if (btrfs_header_level(cur) != *level)
+ WARN_ON(1);
+
+ if (path->slots[*level] >=
+ btrfs_header_nritems(cur))
+ break;
+ if (*level == 0) {
+ ret = drop_leaf_ref(trans, root, cur);
+ BUG_ON(ret);
+ break;
+ }
+ bytenr = btrfs_node_blockptr(cur, path->slots[*level]);
+ ptr_gen = btrfs_node_ptr_generation(cur, path->slots[*level]);
+ blocksize = btrfs_level_size(root, *level - 1);
+ ret = btrfs_lookup_extent_ref(trans, root, bytenr, blocksize,
+ &refs);
+ BUG_ON(ret);
+ if (refs != 1) {
+ parent = path->nodes[*level];
+ root_owner = btrfs_header_owner(parent);
+ root_gen = btrfs_header_generation(parent);
+ path->slots[*level]++;
+ ret = btrfs_free_extent(trans, root, bytenr, blocksize,
+ parent->start, root_owner,
+ root_gen, *level - 1, 1);
+ BUG_ON(ret);
+ continue;
+ }
+ next = btrfs_find_tree_block(root, bytenr, blocksize);
+ if (!next || !btrfs_buffer_uptodate(next, ptr_gen)) {
+ free_extent_buffer(next);
+ reada_walk_down(root, cur, path->slots[*level]);
+ mutex_unlock(&root->fs_info->fs_mutex);
+ next = read_tree_block(root, bytenr, blocksize,
+ ptr_gen);
+ mutex_lock(&root->fs_info->fs_mutex);
+ if (!extent_buffer_uptodate(next)) {
+ if (IS_ERR(next))
+ ret = PTR_ERR(next);
+ else
+ ret = -EIO;
+ break;
+ }
+ }
+ WARN_ON(*level <= 0);
+ if (path->nodes[*level-1])
+ free_extent_buffer(path->nodes[*level-1]);
+ path->nodes[*level-1] = next;
+ *level = btrfs_header_level(next);
+ path->slots[*level] = 0;
+ }
+out:
+ WARN_ON(*level < 0);
+ WARN_ON(*level >= BTRFS_MAX_LEVEL);
+
+ if (path->nodes[*level] == root->node) {
+ root_owner = root->root_key.objectid;
+ parent = path->nodes[*level];
+ } else {
+ parent = path->nodes[*level + 1];
+ root_owner = btrfs_header_owner(parent);
+ }
+
+ root_gen = btrfs_header_generation(parent);
+ ret = btrfs_free_extent(trans, root, path->nodes[*level]->start,
+ path->nodes[*level]->len, parent->start,
+ root_owner, root_gen, *level, 1);
+ free_extent_buffer(path->nodes[*level]);
+ path->nodes[*level] = NULL;
+ *level += 1;
+ BUG_ON(ret);
+ return 0;
+}
+
+/*
+ * helper for dropping snapshots. This walks back up the tree in the path
+ * to find the first node higher up where we haven't yet gone through
+ * all the slots
+ */
+static int noinline walk_up_tree(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ struct btrfs_path *path, int *level)
+{
+ u64 root_owner;
+ u64 root_gen;
+ struct btrfs_root_item *root_item = &root->root_item;
+ int i;
+ int slot;
+ int ret;
+
+ for(i = *level; i < BTRFS_MAX_LEVEL - 1 && path->nodes[i]; i++) {
+ slot = path->slots[i];
+ if (slot < btrfs_header_nritems(path->nodes[i]) - 1) {
+ struct extent_buffer *node;
+ struct btrfs_disk_key disk_key;
+ node = path->nodes[i];
+ path->slots[i]++;
+ *level = i;
+ WARN_ON(*level == 0);
+ btrfs_node_key(node, &disk_key, path->slots[i]);
+ memcpy(&root_item->drop_progress,
+ &disk_key, sizeof(disk_key));
+ root_item->drop_level = i;
+ return 0;
+ } else {
+ struct extent_buffer *parent;
+ if (path->nodes[*level] == root->node)
+ parent = path->nodes[*level];
+ else
+ parent = path->nodes[*level + 1];
+
+ root_owner = btrfs_header_owner(parent);
+ root_gen = btrfs_header_generation(parent);
+ ret = btrfs_free_extent(trans, root,
+ path->nodes[*level]->start,
+ path->nodes[*level]->len,
+ parent->start, root_owner,
+ root_gen, *level, 1);
+ BUG_ON(ret);
+ free_extent_buffer(path->nodes[*level]);
+ path->nodes[*level] = NULL;
+ *level = i + 1;
+ }
+ }
+ return 1;
+}
+
+#endif
+
+int btrfs_free_block_groups(struct btrfs_fs_info *info)
+{
+ struct btrfs_space_info *sinfo;
+ struct btrfs_block_group_cache *cache;
+ u64 start;
+ u64 end;
+ u64 ptr;
+ int ret;
+
+ while(1) {
+ ret = find_first_extent_bit(&info->block_group_cache, 0,
+ &start, &end, (unsigned int)-1);
+ if (ret)
+ break;
+ ret = get_state_private(&info->block_group_cache, start, &ptr);
+ if (!ret) {
+ cache = u64_to_ptr(ptr);
+ if (cache->free_space_ctl) {
+ btrfs_remove_free_space_cache(cache);
+ kfree(cache->free_space_ctl);
+ }
+ kfree(cache);
+ }
+ clear_extent_bits(&info->block_group_cache, start,
+ end, (unsigned int)-1);
+ }
+ while(1) {
+ ret = find_first_extent_bit(&info->free_space_cache, 0,
+ &start, &end, EXTENT_DIRTY);
+ if (ret)
+ break;
+ clear_extent_dirty(&info->free_space_cache, start, end);
+ }
+
+ while (!list_empty(&info->space_info)) {
+ sinfo = list_entry(info->space_info.next,
+ struct btrfs_space_info, list);
+ list_del_init(&sinfo->list);
+ kfree(sinfo);
+ }
+ return 0;
+}
+
+static int find_first_block_group(struct btrfs_root *root,
+ struct btrfs_path *path, struct btrfs_key *key)
+{
+ int ret;
+ struct btrfs_key found_key;
+ struct extent_buffer *leaf;
+ int slot;
+
+ ret = btrfs_search_slot(NULL, root, key, path, 0, 0);
+ if (ret < 0)
+ return ret;
+ while(1) {
+ slot = path->slots[0];
+ leaf = path->nodes[0];
+ if (slot >= btrfs_header_nritems(leaf)) {
+ ret = btrfs_next_leaf(root, path);
+ if (ret == 0)
+ continue;
+ if (ret < 0)
+ goto error;
+ break;
+ }
+ btrfs_item_key_to_cpu(leaf, &found_key, slot);
+
+ if (found_key.objectid >= key->objectid &&
+ found_key.type == BTRFS_BLOCK_GROUP_ITEM_KEY)
+ return 0;
+ path->slots[0]++;
+ }
+ ret = -ENOENT;
+error:
+ return ret;
+}
+
+static void account_super_bytes(struct btrfs_fs_info *fs_info,
+ struct btrfs_block_group_cache *cache)
+{
+ u64 bytenr;
+ u64 *logical;
+ int stripe_len;
+ int i, nr, ret;
+
+ if (cache->key.objectid < BTRFS_SUPER_INFO_OFFSET) {
+ stripe_len = BTRFS_SUPER_INFO_OFFSET - cache->key.objectid;
+ cache->bytes_super += stripe_len;
+ }
+
+ for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) {
+ bytenr = btrfs_sb_offset(i);
+ ret = btrfs_rmap_block(fs_info,
+ cache->key.objectid, bytenr,
+ 0, &logical, &nr, &stripe_len);
+ if (ret)
+ return;
+
+ while (nr--) {
+ u64 start, len;
+
+ if (logical[nr] > cache->key.objectid +
+ cache->key.offset)
+ continue;
+
+ if (logical[nr] + stripe_len <= cache->key.objectid)
+ continue;
+
+ start = logical[nr];
+ if (start < cache->key.objectid) {
+ start = cache->key.objectid;
+ len = (logical[nr] + stripe_len) - start;
+ } else {
+ len = min_t(u64, stripe_len,
+ cache->key.objectid +
+ cache->key.offset - start);
+ }
+
+ cache->bytes_super += len;
+ }
+
+ kfree(logical);
+ }
+}
+
+int btrfs_read_block_groups(struct btrfs_root *root)
+{
+ struct btrfs_path *path;
+ int ret;
+ int bit;
+ struct btrfs_block_group_cache *cache;
+ struct btrfs_fs_info *info = root->fs_info;
+ struct btrfs_space_info *space_info;
+ struct extent_io_tree *block_group_cache;
+ struct btrfs_key key;
+ struct btrfs_key found_key;
+ struct extent_buffer *leaf;
+
+ block_group_cache = &info->block_group_cache;
+
+ root = info->extent_root;
+ key.objectid = 0;
+ key.offset = 0;
+ key.type = BTRFS_BLOCK_GROUP_ITEM_KEY;
+ path = btrfs_alloc_path();
+ if (!path)
+ return -ENOMEM;
+
+ while(1) {
+ ret = find_first_block_group(root, path, &key);
+ if (ret > 0) {
+ ret = 0;
+ goto error;
+ }
+ if (ret != 0) {
+ goto error;
+ }
+ leaf = path->nodes[0];
+ btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
+
+ cache = kzalloc(sizeof(*cache), GFP_NOFS);
+ if (!cache) {
+ ret = -ENOMEM;
+ goto error;
+ }
+
+ read_extent_buffer(leaf, &cache->item,
+ btrfs_item_ptr_offset(leaf, path->slots[0]),
+ sizeof(cache->item));
+ memcpy(&cache->key, &found_key, sizeof(found_key));
+ cache->cached = 0;
+ cache->pinned = 0;
+ key.objectid = found_key.objectid + found_key.offset;
+ if (found_key.offset == 0)
+ key.objectid++;
+ btrfs_release_path(path);
+
+ /*
+ * Skip 0 sized block group, don't insert them into block
+ * group cache tree, as its length is 0, it won't get
+ * freed at close_ctree() time.
+ */
+ if (found_key.offset == 0) {
+ free(cache);
+ continue;
+ }
+
+ cache->flags = btrfs_block_group_flags(&cache->item);
+ bit = 0;
+ if (cache->flags & BTRFS_BLOCK_GROUP_DATA) {
+ bit = BLOCK_GROUP_DATA;
+ } else if (cache->flags & BTRFS_BLOCK_GROUP_SYSTEM) {
+ bit = BLOCK_GROUP_SYSTEM;
+ } else if (cache->flags & BTRFS_BLOCK_GROUP_METADATA) {
+ bit = BLOCK_GROUP_METADATA;
+ }
+ set_avail_alloc_bits(info, cache->flags);
+ if (btrfs_chunk_readonly(info, cache->key.objectid))
+ cache->ro = 1;
+
+ account_super_bytes(info, cache);
+
+ ret = update_space_info(info, cache->flags, found_key.offset,
+ btrfs_block_group_used(&cache->item),
+ &space_info);
+ BUG_ON(ret);
+ cache->space_info = space_info;
+
+ /* use EXTENT_LOCKED to prevent merging */
+ set_extent_bits(block_group_cache, found_key.objectid,
+ found_key.objectid + found_key.offset - 1,
+ bit | EXTENT_LOCKED);
+ set_state_private(block_group_cache, found_key.objectid,
+ (unsigned long)cache);
+ }
+ ret = 0;
+error:
+ btrfs_free_path(path);
+ return ret;
+}
+
+struct btrfs_block_group_cache *
+btrfs_add_block_group(struct btrfs_fs_info *fs_info, u64 bytes_used, u64 type,
+ u64 chunk_offset, u64 size)
+{
+ int ret;
+ int bit = 0;
+ struct btrfs_block_group_cache *cache;
+ struct extent_io_tree *block_group_cache;
+
+ block_group_cache = &fs_info->block_group_cache;
+
+ cache = kzalloc(sizeof(*cache), GFP_NOFS);
+ BUG_ON(!cache);
+ cache->key.objectid = chunk_offset;
+ cache->key.offset = size;
+
+ cache->key.type = BTRFS_BLOCK_GROUP_ITEM_KEY;
+ btrfs_set_block_group_used(&cache->item, bytes_used);
+ btrfs_set_block_group_chunk_objectid(&cache->item,
+ BTRFS_FIRST_CHUNK_TREE_OBJECTID);
+ cache->flags = type;
+ btrfs_set_block_group_flags(&cache->item, type);
+
+ account_super_bytes(fs_info, cache);
+ ret = update_space_info(fs_info, cache->flags, size, bytes_used,
+ &cache->space_info);
+ BUG_ON(ret);
+
+ bit = block_group_state_bits(type);
+ ret = set_extent_bits(block_group_cache, chunk_offset,
+ chunk_offset + size - 1,
+ bit | EXTENT_LOCKED);
+ BUG_ON(ret);
+
+ ret = set_state_private(block_group_cache, chunk_offset,
+ (unsigned long)cache);
+ BUG_ON(ret);
+ set_avail_alloc_bits(fs_info, type);
+
+ return cache;
+}
+
+int btrfs_make_block_group(struct btrfs_trans_handle *trans,
+ struct btrfs_fs_info *fs_info, u64 bytes_used,
+ u64 type, u64 chunk_offset, u64 size)
+{
+ int ret;
+ struct btrfs_root *extent_root = fs_info->extent_root;
+ struct btrfs_block_group_cache *cache;
+
+ cache = btrfs_add_block_group(fs_info, bytes_used, type, chunk_offset,
+ size);
+ ret = btrfs_insert_item(trans, extent_root, &cache->key, &cache->item,
+ sizeof(cache->item));
+ BUG_ON(ret);
+
+ ret = finish_current_insert(trans, extent_root);
+ BUG_ON(ret);
+ ret = del_pending_extents(trans, extent_root);
+ BUG_ON(ret);
+
+ return 0;
+}
+
+/*
+ * This is for converter use only.
+ *
+ * In that case, we don't know where are free blocks located.
+ * Therefore all block group cache entries must be setup properly
+ * before doing any block allocation.
+ */
+int btrfs_make_block_groups(struct btrfs_trans_handle *trans,
+ struct btrfs_fs_info *fs_info)
+{
+ u64 total_bytes;
+ u64 cur_start;
+ u64 group_type;
+ u64 group_size;
+ u64 group_align;
+ u64 total_data = 0;
+ u64 total_metadata = 0;
+ u64 chunk_objectid;
+ int ret;
+ int bit;
+ struct btrfs_root *extent_root = fs_info->extent_root;
+ struct btrfs_block_group_cache *cache;
+ struct extent_io_tree *block_group_cache;
+
+ block_group_cache = &fs_info->block_group_cache;
+ chunk_objectid = BTRFS_FIRST_CHUNK_TREE_OBJECTID;
+ total_bytes = btrfs_super_total_bytes(fs_info->super_copy);
+ group_align = 64 * fs_info->sectorsize;
+
+ cur_start = 0;
+ while (cur_start < total_bytes) {
+ group_size = total_bytes / 12;
+ group_size = min_t(u64, group_size, total_bytes - cur_start);
+ if (cur_start == 0) {
+ bit = BLOCK_GROUP_SYSTEM;
+ group_type = BTRFS_BLOCK_GROUP_SYSTEM;
+ group_size /= 4;
+ group_size &= ~(group_align - 1);
+ group_size = max_t(u64, group_size, SZ_8M);
+ group_size = min_t(u64, group_size, SZ_32M);
+ } else {
+ group_size &= ~(group_align - 1);
+ if (total_data >= total_metadata * 2) {
+ group_type = BTRFS_BLOCK_GROUP_METADATA;
+ group_size = min_t(u64, group_size, SZ_1G);
+ total_metadata += group_size;
+ } else {
+ group_type = BTRFS_BLOCK_GROUP_DATA;
+ group_size = min_t(u64, group_size,
+ 5ULL * SZ_1G);
+ total_data += group_size;
+ }
+ if ((total_bytes - cur_start) * 4 < group_size * 5)
+ group_size = total_bytes - cur_start;
+ }
+
+ cache = kzalloc(sizeof(*cache), GFP_NOFS);
+ BUG_ON(!cache);
+
+ cache->key.objectid = cur_start;
+ cache->key.offset = group_size;
+ cache->key.type = BTRFS_BLOCK_GROUP_ITEM_KEY;
+
+ btrfs_set_block_group_used(&cache->item, 0);
+ btrfs_set_block_group_chunk_objectid(&cache->item,
+ chunk_objectid);
+ btrfs_set_block_group_flags(&cache->item, group_type);
+
+ cache->flags = group_type;
+
+ ret = update_space_info(fs_info, group_type, group_size,
+ 0, &cache->space_info);
+ BUG_ON(ret);
+ set_avail_alloc_bits(fs_info, group_type);
+
+ set_extent_bits(block_group_cache, cur_start,
+ cur_start + group_size - 1,
+ bit | EXTENT_LOCKED);
+ set_state_private(block_group_cache, cur_start,
+ (unsigned long)cache);
+ cur_start += group_size;
+ }
+ /* then insert all the items */
+ cur_start = 0;
+ while(cur_start < total_bytes) {
+ cache = btrfs_lookup_block_group(fs_info, cur_start);
+ BUG_ON(!cache);
+
+ ret = btrfs_insert_item(trans, extent_root, &cache->key, &cache->item,
+ sizeof(cache->item));
+ BUG_ON(ret);
+
+ finish_current_insert(trans, extent_root);
+ ret = del_pending_extents(trans, extent_root);
+ BUG_ON(ret);
+
+ cur_start = cache->key.objectid + cache->key.offset;
+ }
+ return 0;
+}
+
+int btrfs_update_block_group(struct btrfs_root *root,
+ u64 bytenr, u64 num_bytes, int alloc,
+ int mark_free)
+{
+ return update_block_group(root, bytenr, num_bytes,
+ alloc, mark_free);
+}
+
+/*
+ * Just remove a block group item in extent tree
+ * Caller should ensure the block group is empty and all space is pinned.
+ * Or new tree block/data may be allocated into it.
+ */
+static int free_block_group_item(struct btrfs_trans_handle *trans,
+ struct btrfs_fs_info *fs_info,
+ u64 bytenr, u64 len)
+{
+ struct btrfs_path *path;
+ struct btrfs_key key;
+ struct btrfs_root *root = fs_info->extent_root;
+ int ret = 0;
+
+ key.objectid = bytenr;
+ key.offset = len;
+ key.type = BTRFS_BLOCK_GROUP_ITEM_KEY;
+
+ path = btrfs_alloc_path();
+ if (!path)
+ return -ENOMEM;
+
+ ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
+ if (ret > 0) {
+ ret = -ENOENT;
+ goto out;
+ }
+ if (ret < 0)
+ goto out;
+
+ ret = btrfs_del_item(trans, root, path);
+out:
+ btrfs_free_path(path);
+ return ret;
+}
+
+static int free_dev_extent_item(struct btrfs_trans_handle *trans,
+ struct btrfs_fs_info *fs_info,
+ u64 devid, u64 dev_offset)
+{
+ struct btrfs_root *root = fs_info->dev_root;
+ struct btrfs_path *path;
+ struct btrfs_key key;
+ int ret;
+
+ path = btrfs_alloc_path();
+ if (!path)
+ return -ENOMEM;
+
+ key.objectid = devid;
+ key.type = BTRFS_DEV_EXTENT_KEY;
+ key.offset = dev_offset;
+
+ ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
+ if (ret < 0)
+ goto out;
+ if (ret > 0) {
+ ret = -ENOENT;
+ goto out;
+ }
+
+ ret = btrfs_del_item(trans, root, path);
+out:
+ btrfs_free_path(path);
+ return ret;
+}
+
+static int free_chunk_dev_extent_items(struct btrfs_trans_handle *trans,
+ struct btrfs_fs_info *fs_info,
+ u64 chunk_offset)
+{
+ struct btrfs_chunk *chunk = NULL;
+ struct btrfs_root *root= fs_info->chunk_root;
+ struct btrfs_path *path;
+ struct btrfs_key key;
+ u16 num_stripes;
+ int i;
+ int ret;
+
+ path = btrfs_alloc_path();
+ if (!path)
+ return -ENOMEM;
+
+ key.objectid = BTRFS_FIRST_CHUNK_TREE_OBJECTID;
+ key.type = BTRFS_CHUNK_ITEM_KEY;
+ key.offset = chunk_offset;
+
+ ret = btrfs_search_slot(trans, root, &key, path, 0, 0);
+ if (ret < 0)
+ goto out;
+ if (ret > 0) {
+ ret = -ENOENT;
+ goto out;
+ }
+ chunk = btrfs_item_ptr(path->nodes[0], path->slots[0],
+ struct btrfs_chunk);
+ num_stripes = btrfs_chunk_num_stripes(path->nodes[0], chunk);
+ for (i = 0; i < num_stripes; i++) {
+ ret = free_dev_extent_item(trans, fs_info,
+ btrfs_stripe_devid_nr(path->nodes[0], chunk, i),
+ btrfs_stripe_offset_nr(path->nodes[0], chunk, i));
+ if (ret < 0)
+ goto out;
+ }
+out:
+ btrfs_free_path(path);
+ return ret;
+}
+
+static int free_system_chunk_item(struct btrfs_super_block *super,
+ struct btrfs_key *key)
+{
+ struct btrfs_disk_key *disk_key;
+ struct btrfs_key cpu_key;
+ u32 array_size = btrfs_super_sys_array_size(super);
+ char *ptr = (char *)super->sys_chunk_array;
+ int cur = 0;
+ int ret = -ENOENT;
+
+ while (cur < btrfs_super_sys_array_size(super)) {
+ struct btrfs_chunk *chunk;
+ u32 num_stripes;
+ u32 chunk_len;
+
+ disk_key = (struct btrfs_disk_key *)(ptr + cur);
+ btrfs_disk_key_to_cpu(&cpu_key, disk_key);
+ if (cpu_key.type != BTRFS_CHUNK_ITEM_KEY) {
+ /* just in case */
+ ret = -EIO;
+ goto out;
+ }
+
+ chunk = (struct btrfs_chunk *)(ptr + cur + sizeof(*disk_key));
+ num_stripes = btrfs_stack_chunk_num_stripes(chunk);
+ chunk_len = btrfs_chunk_item_size(num_stripes) +
+ sizeof(*disk_key);
+
+ if (key->objectid == cpu_key.objectid &&
+ key->offset == cpu_key.offset &&
+ key->type == cpu_key.type) {
+ memmove(ptr + cur, ptr + cur + chunk_len,
+ array_size - cur - chunk_len);
+ array_size -= chunk_len;
+ btrfs_set_super_sys_array_size(super, array_size);
+ ret = 0;
+ goto out;
+ }
+
+ cur += chunk_len;
+ }
+out:
+ return ret;
+}
+
+static int free_chunk_item(struct btrfs_trans_handle *trans,
+ struct btrfs_fs_info *fs_info,
+ u64 bytenr)
+{
+ struct btrfs_path *path;
+ struct btrfs_key key;
+ struct btrfs_root *root = fs_info->chunk_root;
+ struct btrfs_chunk *chunk;
+ u64 chunk_type;
+ int ret;
+
+ key.objectid = BTRFS_FIRST_CHUNK_TREE_OBJECTID;
+ key.offset = bytenr;
+ key.type = BTRFS_CHUNK_ITEM_KEY;
+
+ path = btrfs_alloc_path();
+ if (!path)
+ return -ENOMEM;
+
+ ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
+ if (ret > 0) {
+ ret = -ENOENT;
+ goto out;
+ }
+ if (ret < 0)
+ goto out;
+ chunk = btrfs_item_ptr(path->nodes[0], path->slots[0],
+ struct btrfs_chunk);
+ chunk_type = btrfs_chunk_type(path->nodes[0], chunk);
+
+ ret = btrfs_del_item(trans, root, path);
+ if (ret < 0)
+ goto out;
+
+ if (chunk_type & BTRFS_BLOCK_GROUP_SYSTEM)
+ ret = free_system_chunk_item(fs_info->super_copy, &key);
+out:
+ btrfs_free_path(path);
+ return ret;
+}
+
+static u64 get_dev_extent_len(struct map_lookup *map)
+{
+ int div;
+
+ switch (map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK) {
+ case 0: /* Single */
+ case BTRFS_BLOCK_GROUP_DUP:
+ case BTRFS_BLOCK_GROUP_RAID1:
+ div = 1;
+ break;
+ case BTRFS_BLOCK_GROUP_RAID5:
+ div = (map->num_stripes - 1);
+ break;
+ case BTRFS_BLOCK_GROUP_RAID6:
+ div = (map->num_stripes - 2);
+ break;
+ case BTRFS_BLOCK_GROUP_RAID10:
+ div = (map->num_stripes / map->sub_stripes);
+ break;
+ default:
+ /* normally, read chunk security hook should handled it */
+ BUG_ON(1);
+ }
+ return map->ce.size / div;
+}
+
+/* free block group/chunk related caches */
+static int free_block_group_cache(struct btrfs_trans_handle *trans,
+ struct btrfs_fs_info *fs_info,
+ u64 bytenr, u64 len)
+{
+ struct btrfs_block_group_cache *cache;
+ struct cache_extent *ce;
+ struct map_lookup *map;
+ int ret;
+ int i;
+ u64 flags;
+
+ /* Free block group cache first */
+ cache = btrfs_lookup_block_group(fs_info, bytenr);
+ if (!cache)
+ return -ENOENT;
+ flags = cache->flags;
+ if (cache->free_space_ctl) {
+ btrfs_remove_free_space_cache(cache);
+ kfree(cache->free_space_ctl);
+ }
+ clear_extent_bits(&fs_info->block_group_cache, bytenr, bytenr + len - 1,
+ (unsigned int)-1);
+ ret = free_space_info(fs_info, flags, len, 0, NULL);
+ if (ret < 0)
+ goto out;
+ kfree(cache);
+
+ /* Then free mapping info and dev usage info */
+ ce = search_cache_extent(&fs_info->mapping_tree.cache_tree, bytenr);
+ if (!ce || ce->start != bytenr) {
+ ret = -ENOENT;
+ goto out;
+ }
+ map = container_of(ce, struct map_lookup, ce);
+ for (i = 0; i < map->num_stripes; i++) {
+ struct btrfs_device *device;
+
+ device = map->stripes[i].dev;
+ device->bytes_used -= get_dev_extent_len(map);
+ ret = btrfs_update_device(trans, device);
+ if (ret < 0)
+ goto out;
+ }
+ remove_cache_extent(&fs_info->mapping_tree.cache_tree, ce);
+ free(map);
+out:
+ return ret;
+}
+
+int btrfs_free_block_group(struct btrfs_trans_handle *trans,
+ struct btrfs_fs_info *fs_info, u64 bytenr, u64 len)
+{
+ struct btrfs_root *extent_root = fs_info->extent_root;
+ struct btrfs_path *path;
+ struct btrfs_block_group_item *bgi;
+ struct btrfs_key key;
+ int ret = 0;
+
+ path = btrfs_alloc_path();
+ if (!path)
+ return -ENOMEM;
+
+ key.objectid = bytenr;
+ key.type = BTRFS_BLOCK_GROUP_ITEM_KEY;
+ key.offset = len;
+
+ /* Double check the block group to ensure it's empty */
+ ret = btrfs_search_slot(trans, extent_root, &key, path, 0, 0);
+ if (ret > 0) {
+ ret = -ENONET;
+ goto out;
+ }
+ if (ret < 0)
+ goto out;
+
+ bgi = btrfs_item_ptr(path->nodes[0], path->slots[0],
+ struct btrfs_block_group_item);
+ if (btrfs_disk_block_group_used(path->nodes[0], bgi)) {
+ fprintf(stderr,
+ "WARNING: block group [%llu,%llu) is not empty\n",
+ bytenr, bytenr + len);
+ ret = -EINVAL;
+ goto out;
+ }
+ btrfs_release_path(path);
+
+ /*
+ * Now pin all space in the block group, to prevent further transaction
+ * allocate space from it.
+ * Every operation needs a transaction must be in the range.
+ */
+ btrfs_pin_extent(fs_info, bytenr, len);
+
+ /* delete block group item and chunk item */
+ ret = free_block_group_item(trans, fs_info, bytenr, len);
+ if (ret < 0) {
+ fprintf(stderr,
+ "failed to free block group item for [%llu,%llu)\n",
+ bytenr, bytenr + len);
+ btrfs_unpin_extent(fs_info, bytenr, len);
+ goto out;
+ }
+
+ ret = free_chunk_dev_extent_items(trans, fs_info, bytenr);
+ if (ret < 0) {
+ fprintf(stderr,
+ "failed to dev extents belongs to [%llu,%llu)\n",
+ bytenr, bytenr + len);
+ btrfs_unpin_extent(fs_info, bytenr, len);
+ goto out;
+ }
+ ret = free_chunk_item(trans, fs_info, bytenr);
+ if (ret < 0) {
+ fprintf(stderr,
+ "failed to free chunk for [%llu,%llu)\n",
+ bytenr, bytenr + len);
+ btrfs_unpin_extent(fs_info, bytenr, len);
+ goto out;
+ }
+
+ /* Now release the block_group_cache */
+ ret = free_block_group_cache(trans, fs_info, bytenr, len);
+ btrfs_unpin_extent(fs_info, bytenr, len);
+
+out:
+ btrfs_free_path(path);
+ return ret;
+}
+
+/*
+ * Fixup block accounting. The initial block accounting created by
+ * make_block_groups isn't accuracy in this case.
+ */
+int btrfs_fix_block_accounting(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root)
+{
+ int ret = 0;
+ int slot;
+ u64 start = 0;
+ u64 bytes_used = 0;
+ struct btrfs_path path;
+ struct btrfs_key key;
+ struct extent_buffer *leaf;
+ struct btrfs_block_group_cache *cache;
+ struct btrfs_fs_info *fs_info = root->fs_info;
+
+ root = root->fs_info->extent_root;
+
+ while(extent_root_pending_ops(fs_info)) {
+ ret = finish_current_insert(trans, root);
+ if (ret)
+ return ret;
+ ret = del_pending_extents(trans, root);
+ if (ret)
+ return ret;
+ }
+
+ while(1) {
+ cache = btrfs_lookup_first_block_group(fs_info, start);
+ if (!cache)
+ break;
+ start = cache->key.objectid + cache->key.offset;
+ btrfs_set_block_group_used(&cache->item, 0);
+ cache->space_info->bytes_used = 0;
+ set_extent_bits(&root->fs_info->block_group_cache,
+ cache->key.objectid,
+ cache->key.objectid + cache->key.offset -1,
+ BLOCK_GROUP_DIRTY);
+ }
+
+ btrfs_init_path(&path);
+ key.offset = 0;
+ key.objectid = 0;
+ key.type = BTRFS_EXTENT_ITEM_KEY;
+ ret = btrfs_search_slot(trans, root->fs_info->extent_root,
+ &key, &path, 0, 0);
+ if (ret < 0)
+ return ret;
+ while(1) {
+ leaf = path.nodes[0];
+ slot = path.slots[0];
+ if (slot >= btrfs_header_nritems(leaf)) {
+ ret = btrfs_next_leaf(root, &path);
+ if (ret < 0)
+ return ret;
+ if (ret > 0)
+ break;
+ leaf = path.nodes[0];
+ slot = path.slots[0];
+ }
+ btrfs_item_key_to_cpu(leaf, &key, slot);
+ if (key.type == BTRFS_EXTENT_ITEM_KEY) {
+ bytes_used += key.offset;
+ ret = btrfs_update_block_group(root,
+ key.objectid, key.offset, 1, 0);
+ BUG_ON(ret);
+ } else if (key.type == BTRFS_METADATA_ITEM_KEY) {
+ bytes_used += fs_info->nodesize;
+ ret = btrfs_update_block_group(root,
+ key.objectid, fs_info->nodesize, 1, 0);
+ if (ret)
+ goto out;
+ }
+ path.slots[0]++;
+ }
+ btrfs_set_super_bytes_used(root->fs_info->super_copy, bytes_used);
+ ret = 0;
+out:
+ btrfs_release_path(&path);
+ return ret;
+}
+
+static void __get_extent_size(struct btrfs_root *root, struct btrfs_path *path,
+ u64 *start, u64 *len)
+{
+ struct btrfs_key key;
+
+ btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
+ BUG_ON(!(key.type == BTRFS_EXTENT_ITEM_KEY ||
+ key.type == BTRFS_METADATA_ITEM_KEY));
+ *start = key.objectid;
+ if (key.type == BTRFS_EXTENT_ITEM_KEY)
+ *len = key.offset;
+ else
+ *len = root->fs_info->nodesize;
+}
+
+/*
+ * Find first overlap extent for range [bytenr, bytenr + len)
+ * Return 0 for found and point path to it.
+ * Return >0 for not found.
+ * Return <0 for err
+ */
+int btrfs_search_overlap_extent(struct btrfs_root *root,
+ struct btrfs_path *path, u64 bytenr, u64 len)
+{
+ struct btrfs_key key;
+ u64 cur_start;
+ u64 cur_len;
+ int ret;
+
+ key.objectid = bytenr;
+ key.type = BTRFS_EXTENT_DATA_KEY;
+ key.offset = (u64)-1;
+
+ ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+ if (ret < 0)
+ return ret;
+ BUG_ON(ret == 0);
+
+ ret = btrfs_previous_extent_item(root, path, 0);
+ if (ret < 0)
+ return ret;
+ /* no previous, check next extent */
+ if (ret > 0)
+ goto next;
+ __get_extent_size(root, path, &cur_start, &cur_len);
+ /* Tail overlap */
+ if (cur_start + cur_len > bytenr)
+ return 1;
+
+next:
+ ret = btrfs_next_extent_item(root, path, bytenr + len);
+ if (ret < 0)
+ return ret;
+ /* No next, prev already checked, no overlap */
+ if (ret > 0)
+ return 0;
+ __get_extent_size(root, path, &cur_start, &cur_len);
+ /* head overlap*/
+ if (cur_start < bytenr + len)
+ return 1;
+ return 0;
+}
+
+static int __btrfs_record_file_extent(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root, u64 objectid,
+ struct btrfs_inode_item *inode,
+ u64 file_pos, u64 disk_bytenr,
+ u64 *ret_num_bytes)
+{
+ int ret;
+ struct btrfs_fs_info *info = root->fs_info;
+ struct btrfs_root *extent_root = info->extent_root;
+ struct extent_buffer *leaf;
+ struct btrfs_file_extent_item *fi;
+ struct btrfs_key ins_key;
+ struct btrfs_path *path;
+ struct btrfs_extent_item *ei;
+ u64 nbytes;
+ u64 extent_num_bytes;
+ u64 extent_bytenr;
+ u64 extent_offset;
+ u64 num_bytes = *ret_num_bytes;
+
+ /*
+ * All supported file system should not use its 0 extent.
+ * As it's for hole
+ *
+ * And hole extent has no size limit, no need to loop.
+ */
+ if (disk_bytenr == 0) {
+ ret = btrfs_insert_file_extent(trans, root, objectid,
+ file_pos, disk_bytenr,
+ num_bytes, num_bytes);
+ return ret;
+ }
+ num_bytes = min_t(u64, num_bytes, BTRFS_MAX_EXTENT_SIZE);
+
+ path = btrfs_alloc_path();
+ if (!path)
+ return -ENOMEM;
+
+ /* First to check extent overlap */
+ ret = btrfs_search_overlap_extent(extent_root, path, disk_bytenr,
+ num_bytes);
+ if (ret < 0)
+ goto fail;
+ if (ret > 0) {
+ /* Found overlap */
+ u64 cur_start;
+ u64 cur_len;
+
+ __get_extent_size(extent_root, path, &cur_start, &cur_len);
+ /*
+ * For convert case, this extent should be a subset of
+ * existing one.
+ */
+ BUG_ON(disk_bytenr < cur_start);
+
+ extent_bytenr = cur_start;
+ extent_num_bytes = cur_len;
+ extent_offset = disk_bytenr - extent_bytenr;
+ } else {
+ /* No overlap, create new extent */
+ btrfs_release_path(path);
+ ins_key.objectid = disk_bytenr;
+ ins_key.offset = num_bytes;
+ ins_key.type = BTRFS_EXTENT_ITEM_KEY;
+
+ ret = btrfs_insert_empty_item(trans, extent_root, path,
+ &ins_key, sizeof(*ei));
+ if (ret == 0) {
+ leaf = path->nodes[0];
+ ei = btrfs_item_ptr(leaf, path->slots[0],
+ struct btrfs_extent_item);
+
+ btrfs_set_extent_refs(leaf, ei, 0);
+ btrfs_set_extent_generation(leaf, ei, 0);
+ btrfs_set_extent_flags(leaf, ei,
+ BTRFS_EXTENT_FLAG_DATA);
+ btrfs_mark_buffer_dirty(leaf);
+
+ ret = btrfs_update_block_group(root, disk_bytenr,
+ num_bytes, 1, 0);
+ if (ret)
+ goto fail;
+ } else if (ret != -EEXIST) {
+ goto fail;
+ }
+ btrfs_extent_post_op(trans, extent_root);
+ extent_bytenr = disk_bytenr;
+ extent_num_bytes = num_bytes;
+ extent_offset = 0;
+ }
+ btrfs_release_path(path);
+ ins_key.objectid = objectid;
+ ins_key.offset = file_pos;
+ ins_key.type = BTRFS_EXTENT_DATA_KEY;
+ ret = btrfs_insert_empty_item(trans, root, path, &ins_key,
+ sizeof(*fi));
+ if (ret)
+ goto fail;
+ leaf = path->nodes[0];
+ fi = btrfs_item_ptr(leaf, path->slots[0],
+ struct btrfs_file_extent_item);
+ btrfs_set_file_extent_generation(leaf, fi, trans->transid);
+ btrfs_set_file_extent_type(leaf, fi, BTRFS_FILE_EXTENT_REG);
+ btrfs_set_file_extent_disk_bytenr(leaf, fi, extent_bytenr);
+ btrfs_set_file_extent_disk_num_bytes(leaf, fi, extent_num_bytes);
+ btrfs_set_file_extent_offset(leaf, fi, extent_offset);
+ btrfs_set_file_extent_num_bytes(leaf, fi, num_bytes);
+ btrfs_set_file_extent_ram_bytes(leaf, fi, extent_num_bytes);
+ btrfs_set_file_extent_compression(leaf, fi, 0);
+ btrfs_set_file_extent_encryption(leaf, fi, 0);
+ btrfs_set_file_extent_other_encoding(leaf, fi, 0);
+ btrfs_mark_buffer_dirty(leaf);
+
+ nbytes = btrfs_stack_inode_nbytes(inode) + num_bytes;
+ btrfs_set_stack_inode_nbytes(inode, nbytes);
+ btrfs_release_path(path);
+
+ ret = btrfs_inc_extent_ref(trans, root, extent_bytenr, extent_num_bytes,
+ 0, root->root_key.objectid, objectid,
+ file_pos - extent_offset);
+ if (ret)
+ goto fail;
+ ret = 0;
+ *ret_num_bytes = min(extent_num_bytes - extent_offset, num_bytes);
+fail:
+ btrfs_free_path(path);
+ return ret;
+}
+
+/*
+ * Record a file extent. Do all the required works, such as inserting
+ * file extent item, inserting extent item and backref item into extent
+ * tree and updating block accounting.
+ */
+int btrfs_record_file_extent(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root, u64 objectid,
+ struct btrfs_inode_item *inode,
+ u64 file_pos, u64 disk_bytenr,
+ u64 num_bytes)
+{
+ u64 cur_disk_bytenr = disk_bytenr;
+ u64 cur_file_pos = file_pos;
+ u64 cur_num_bytes = num_bytes;
+ int ret = 0;
+
+ while (num_bytes > 0) {
+ ret = __btrfs_record_file_extent(trans, root, objectid,
+ inode, cur_file_pos,
+ cur_disk_bytenr,
+ &cur_num_bytes);
+ if (ret < 0)
+ break;
+ cur_disk_bytenr += cur_num_bytes;
+ cur_file_pos += cur_num_bytes;
+ num_bytes -= cur_num_bytes;
+ }
+ return ret;
+}
+
+
+static int add_excluded_extent(struct btrfs_root *root,
+ u64 start, u64 num_bytes)
+{
+ u64 end = start + num_bytes - 1;
+ set_extent_bits(&root->fs_info->pinned_extents,
+ start, end, EXTENT_UPTODATE);
+ return 0;
+}
+
+void free_excluded_extents(struct btrfs_root *root,
+ struct btrfs_block_group_cache *cache)
+{
+ u64 start, end;
+
+ start = cache->key.objectid;
+ end = start + cache->key.offset - 1;
+
+ clear_extent_bits(&root->fs_info->pinned_extents,
+ start, end, EXTENT_UPTODATE);
+}
+
+int exclude_super_stripes(struct btrfs_root *root,
+ struct btrfs_block_group_cache *cache)
+{
+ u64 bytenr;
+ u64 *logical;
+ int stripe_len;
+ int i, nr, ret;
+
+ if (cache->key.objectid < BTRFS_SUPER_INFO_OFFSET) {
+ stripe_len = BTRFS_SUPER_INFO_OFFSET - cache->key.objectid;
+ cache->bytes_super += stripe_len;
+ ret = add_excluded_extent(root, cache->key.objectid,
+ stripe_len);
+ if (ret)
+ return ret;
+ }
+
+ for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) {
+ bytenr = btrfs_sb_offset(i);
+ ret = btrfs_rmap_block(root->fs_info,
+ cache->key.objectid, bytenr,
+ 0, &logical, &nr, &stripe_len);
+ if (ret)
+ return ret;
+
+ while (nr--) {
+ u64 start, len;
+
+ if (logical[nr] > cache->key.objectid +
+ cache->key.offset)
+ continue;
+
+ if (logical[nr] + stripe_len <= cache->key.objectid)
+ continue;
+
+ start = logical[nr];
+ if (start < cache->key.objectid) {
+ start = cache->key.objectid;
+ len = (logical[nr] + stripe_len) - start;
+ } else {
+ len = min_t(u64, stripe_len,
+ cache->key.objectid +
+ cache->key.offset - start);
+ }
+
+ cache->bytes_super += len;
+ ret = add_excluded_extent(root, start, len);
+ if (ret) {
+ kfree(logical);
+ return ret;
+ }
+ }
+
+ kfree(logical);
+ }
+ return 0;
+}
+
+u64 add_new_free_space(struct btrfs_block_group_cache *block_group,
+ struct btrfs_fs_info *info, u64 start, u64 end)
+{
+ u64 extent_start, extent_end, size, total_added = 0;
+ int ret;
+
+ while (start < end) {
+ ret = find_first_extent_bit(&info->pinned_extents, start,
+ &extent_start, &extent_end,
+ EXTENT_DIRTY | EXTENT_UPTODATE);
+ if (ret)
+ break;
+
+ if (extent_start <= start) {
+ start = extent_end + 1;
+ } else if (extent_start > start && extent_start < end) {
+ size = extent_start - start;
+ total_added += size;
+ ret = btrfs_add_free_space(block_group->free_space_ctl,
+ start, size);
+ BUG_ON(ret); /* -ENOMEM or logic error */
+ start = extent_end + 1;
+ } else {
+ break;
+ }
+ }
+
+ if (start < end) {
+ size = end - start;
+ total_added += size;
+ ret = btrfs_add_free_space(block_group->free_space_ctl, start,
+ size);
+ BUG_ON(ret); /* -ENOMEM or logic error */
+ }
+
+ return total_added;
+}