static struct dentry *btrfs_get_dentry(struct super_block *sb, u64 objectid,
u64 root_objectid, u32 generation)
{
struct btrfs_root *root;
struct inode *inode;
struct btrfs_key key;
key.objectid = root_objectid;
btrfs_set_key_type(&key, BTRFS_ROOT_ITEM_KEY);
key.offset = (u64)-1;
root = btrfs_read_fs_root_no_name(btrfs_sb(sb)->fs_info, &key);
if (IS_ERR(root))
return ERR_CAST(root);
key.objectid = objectid;
btrfs_set_key_type(&key, BTRFS_INODE_ITEM_KEY);
key.offset = 0;
inode = btrfs_iget(sb, &key, root, NULL);
if (IS_ERR(inode))
return (void *)inode;
if (generation != inode->i_generation) {
iput(inode);
return ERR_PTR(-ESTALE);
}
return d_obtain_alias(inode);
}
/*
* resolve an indirect backref in the form (root_id, key, level)
* to a logical address
*/
static int __resolve_indirect_ref(struct btrfs_fs_info *fs_info,
struct btrfs_path *path, u64 time_seq,
struct __prelim_ref *ref,
struct ulist *parents,
const u64 *extent_item_pos)
{
struct btrfs_root *root;
struct btrfs_key root_key;
struct extent_buffer *eb;
int ret = 0;
int root_level;
int level = ref->level;
root_key.objectid = ref->root_id;
root_key.type = BTRFS_ROOT_ITEM_KEY;
root_key.offset = (u64)-1;
root = btrfs_read_fs_root_no_name(fs_info, &root_key);
if (IS_ERR(root)) {
ret = PTR_ERR(root);
goto out;
}
root_level = btrfs_old_root_level(root, time_seq);
if (root_level + 1 == level)
goto out;
path->lowest_level = level;
ret = btrfs_search_old_slot(root, &ref->key_for_search, path, time_seq);
pr_debug("search slot in root %llu (level %d, ref count %d) returned "
"%d for key (%llu %u %llu)\n",
(unsigned long long)ref->root_id, level, ref->count, ret,
(unsigned long long)ref->key_for_search.objectid,
ref->key_for_search.type,
(unsigned long long)ref->key_for_search.offset);
if (ret < 0)
goto out;
eb = path->nodes[level];
while (!eb) {
if (!level) {
WARN_ON(1);
ret = 1;
goto out;
}
level--;
eb = path->nodes[level];
}
ret = add_all_parents(root, path, parents, level, &ref->key_for_search,
time_seq, ref->wanted_disk_byte,
extent_item_pos);
out:
path->lowest_level = 0;
btrfs_release_path(path);
return ret;
}
static struct dentry *btrfs_get_dentry(struct super_block *sb, u64 objectid,
u64 root_objectid, u32 generation,
int check_generation)
{
struct btrfs_fs_info *fs_info = btrfs_sb(sb);
struct btrfs_root *root;
struct inode *inode;
struct btrfs_key key;
int index;
int err = 0;
if (objectid < BTRFS_FIRST_FREE_OBJECTID)
return ERR_PTR(-ESTALE);
key.objectid = root_objectid;
btrfs_set_key_type(&key, BTRFS_ROOT_ITEM_KEY);
key.offset = (u64)-1;
index = srcu_read_lock(&fs_info->subvol_srcu);
root = btrfs_read_fs_root_no_name(fs_info, &key);
if (IS_ERR(root)) {
err = PTR_ERR(root);
goto fail;
}
if (btrfs_root_refs(&root->root_item) == 0) {
err = -ENOENT;
goto fail;
}
key.objectid = objectid;
btrfs_set_key_type(&key, BTRFS_INODE_ITEM_KEY);
key.offset = 0;
inode = btrfs_iget(sb, &key, root, NULL);
if (IS_ERR(inode)) {
err = PTR_ERR(inode);
goto fail;
}
srcu_read_unlock(&fs_info->subvol_srcu, index);
if (check_generation && generation != inode->i_generation) {
iput(inode);
return ERR_PTR(-ESTALE);
}
return d_obtain_alias(inode);
fail:
srcu_read_unlock(&fs_info->subvol_srcu, index);
return ERR_PTR(err);
}
int btrfs_find_orphan_roots(struct btrfs_root *tree_root)
{
struct extent_buffer *leaf;
struct btrfs_path *path;
struct btrfs_key key;
struct btrfs_key root_key;
struct btrfs_root *root;
int err = 0;
int ret;
path = btrfs_alloc_path();
if (!path)
return -ENOMEM;
key.objectid = BTRFS_ORPHAN_OBJECTID;
key.type = BTRFS_ORPHAN_ITEM_KEY;
key.offset = 0;
root_key.type = BTRFS_ROOT_ITEM_KEY;
root_key.offset = (u64)-1;
while (1) {
ret = btrfs_search_slot(NULL, tree_root, &key, path, 0, 0);
if (ret < 0) {
err = ret;
break;
}
leaf = path->nodes[0];
if (path->slots[0] >= btrfs_header_nritems(leaf)) {
ret = btrfs_next_leaf(tree_root, path);
if (ret < 0)
err = ret;
if (ret != 0)
break;
leaf = path->nodes[0];
}
btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
btrfs_release_path(tree_root, path);
if (key.objectid != BTRFS_ORPHAN_OBJECTID ||
key.type != BTRFS_ORPHAN_ITEM_KEY)
break;
root_key.objectid = key.offset;
key.offset++;
root = btrfs_read_fs_root_no_name(tree_root->fs_info,
&root_key);
if (!IS_ERR(root))
continue;
ret = PTR_ERR(root);
if (ret != -ENOENT) {
err = ret;
break;
}
ret = btrfs_find_dead_roots(tree_root, root_key.objectid);
if (ret) {
err = ret;
break;
}
}
btrfs_free_path(path);
return err;
}
static noinline int create_subvol(struct btrfs_root *root,
struct dentry *dentry,
char *name, int namelen)
{
struct btrfs_trans_handle *trans;
struct btrfs_key key;
struct btrfs_root_item root_item;
struct btrfs_inode_item *inode_item;
struct extent_buffer *leaf;
struct btrfs_root *new_root;
struct inode *dir = dentry->d_parent->d_inode;
int ret;
int err;
u64 objectid;
u64 new_dirid = BTRFS_FIRST_FREE_OBJECTID;
u64 index = 0;
ret = btrfs_find_free_objectid(NULL, root->fs_info->tree_root,
0, &objectid);
if (ret)
return ret;
/*
* 1 - inode item
* 2 - refs
* 1 - root item
* 2 - dir items
*/
trans = btrfs_start_transaction(root, 6);
if (IS_ERR(trans))
return PTR_ERR(trans);
leaf = btrfs_alloc_free_block(trans, root, root->leafsize,
0, objectid, NULL, 0, 0, 0);
if (IS_ERR(leaf)) {
ret = PTR_ERR(leaf);
goto fail;
}
memset_extent_buffer(leaf, 0, 0, sizeof(struct btrfs_header));
btrfs_set_header_bytenr(leaf, leaf->start);
btrfs_set_header_generation(leaf, trans->transid);
btrfs_set_header_backref_rev(leaf, BTRFS_MIXED_BACKREF_REV);
btrfs_set_header_owner(leaf, objectid);
write_extent_buffer(leaf, root->fs_info->fsid,
(unsigned long)btrfs_header_fsid(leaf),
BTRFS_FSID_SIZE);
write_extent_buffer(leaf, root->fs_info->chunk_tree_uuid,
(unsigned long)btrfs_header_chunk_tree_uuid(leaf),
BTRFS_UUID_SIZE);
btrfs_mark_buffer_dirty(leaf);
inode_item = &root_item.inode;
memset(inode_item, 0, sizeof(*inode_item));
inode_item->generation = cpu_to_le64(1);
inode_item->size = cpu_to_le64(3);
inode_item->nlink = cpu_to_le32(1);
inode_item->nbytes = cpu_to_le64(root->leafsize);
inode_item->mode = cpu_to_le32(S_IFDIR | 0755);
root_item.flags = 0;
root_item.byte_limit = 0;
inode_item->flags = cpu_to_le64(BTRFS_INODE_ROOT_ITEM_INIT);
btrfs_set_root_bytenr(&root_item, leaf->start);
btrfs_set_root_generation(&root_item, trans->transid);
btrfs_set_root_level(&root_item, 0);
btrfs_set_root_refs(&root_item, 1);
btrfs_set_root_used(&root_item, leaf->len);
btrfs_set_root_last_snapshot(&root_item, 0);
memset(&root_item.drop_progress, 0, sizeof(root_item.drop_progress));
root_item.drop_level = 0;
btrfs_tree_unlock(leaf);
free_extent_buffer(leaf);
leaf = NULL;
btrfs_set_root_dirid(&root_item, new_dirid);
key.objectid = objectid;
key.offset = 0;
btrfs_set_key_type(&key, BTRFS_ROOT_ITEM_KEY);
ret = btrfs_insert_root(trans, root->fs_info->tree_root, &key,
&root_item);
if (ret)
goto fail;
key.offset = (u64)-1;
new_root = btrfs_read_fs_root_no_name(root->fs_info, &key);
BUG_ON(IS_ERR(new_root));
btrfs_record_root_in_trans(trans, new_root);
ret = btrfs_create_subvol_root(trans, new_root, new_dirid,
BTRFS_I(dir)->block_group);
/*
* insert the directory item
*/
ret = btrfs_set_inode_index(dir, &index);
BUG_ON(ret);
ret = btrfs_insert_dir_item(trans, root,
name, namelen, dir->i_ino, &key,
BTRFS_FT_DIR, index);
if (ret)
goto fail;
btrfs_i_size_write(dir, dir->i_size + namelen * 2);
ret = btrfs_update_inode(trans, root, dir);
BUG_ON(ret);
ret = btrfs_add_root_ref(trans, root->fs_info->tree_root,
objectid, root->root_key.objectid,
dir->i_ino, index, name, namelen);
BUG_ON(ret);
d_instantiate(dentry, btrfs_lookup_dentry(dir, dentry));
fail:
err = btrfs_commit_transaction(trans, root);
if (err && !ret)
ret = err;
return ret;
}
static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info,
struct btrfs_pending_snapshot *pending)
{
struct btrfs_key key;
struct btrfs_root_item *new_root_item;
struct btrfs_root *tree_root = fs_info->tree_root;
struct btrfs_root *root = pending->root;
struct btrfs_root *parent_root;
struct inode *parent_inode;
struct dentry *dentry;
struct extent_buffer *tmp;
struct extent_buffer *old;
int ret;
int retries = 0;
u64 to_reserve = 0;
u64 index = 0;
u64 objectid;
new_root_item = kmalloc(sizeof(*new_root_item), GFP_NOFS);
if (!new_root_item) {
pending->error = -ENOMEM;
goto fail;
}
ret = btrfs_find_free_objectid(trans, tree_root, 0, &objectid);
if (ret) {
pending->error = ret;
goto fail;
}
btrfs_reloc_pre_snapshot(trans, pending, &to_reserve);
btrfs_orphan_pre_snapshot(trans, pending, &to_reserve);
if (to_reserve > 0) {
ret = btrfs_block_rsv_add(trans, root, &pending->block_rsv,
to_reserve, &retries);
if (ret) {
pending->error = ret;
goto fail;
}
}
key.objectid = objectid;
key.offset = (u64)-1;
key.type = BTRFS_ROOT_ITEM_KEY;
trans->block_rsv = &pending->block_rsv;
dentry = pending->dentry;
parent_inode = dentry->d_parent->d_inode;
parent_root = BTRFS_I(parent_inode)->root;
record_root_in_trans(trans, parent_root);
/*
* insert the directory item
*/
ret = btrfs_set_inode_index(parent_inode, &index);
BUG_ON(ret);
ret = btrfs_insert_dir_item(trans, parent_root,
dentry->d_name.name, dentry->d_name.len,
parent_inode->i_ino, &key,
BTRFS_FT_DIR, index);
BUG_ON(ret);
btrfs_i_size_write(parent_inode, parent_inode->i_size +
dentry->d_name.len * 2);
ret = btrfs_update_inode(trans, parent_root, parent_inode);
BUG_ON(ret);
record_root_in_trans(trans, root);
btrfs_set_root_last_snapshot(&root->root_item, trans->transid);
memcpy(new_root_item, &root->root_item, sizeof(*new_root_item));
old = btrfs_lock_root_node(root);
btrfs_cow_block(trans, root, old, NULL, 0, &old);
btrfs_set_lock_blocking(old);
btrfs_copy_root(trans, root, old, &tmp, objectid);
btrfs_tree_unlock(old);
free_extent_buffer(old);
btrfs_set_root_node(new_root_item, tmp);
/* record when the snapshot was created in key.offset */
key.offset = trans->transid;
ret = btrfs_insert_root(trans, tree_root, &key, new_root_item);
btrfs_tree_unlock(tmp);
free_extent_buffer(tmp);
BUG_ON(ret);
/*
* insert root back/forward references
*/
ret = btrfs_add_root_ref(trans, tree_root, objectid,
parent_root->root_key.objectid,
parent_inode->i_ino, index,
dentry->d_name.name, dentry->d_name.len);
BUG_ON(ret);
key.offset = (u64)-1;
pending->snap = btrfs_read_fs_root_no_name(root->fs_info, &key);
BUG_ON(IS_ERR(pending->snap));
btrfs_reloc_post_snapshot(trans, pending);
btrfs_orphan_post_snapshot(trans, pending);
fail:
kfree(new_root_item);
btrfs_block_rsv_release(root, &pending->block_rsv, (u64)-1);
return 0;
}
/*
* resolve an indirect backref in the form (root_id, key, level)
* to a logical address
*/
static int __resolve_indirect_ref(struct btrfs_fs_info *fs_info,
struct btrfs_path *path, u64 time_seq,
struct __prelim_ref *ref,
struct ulist *parents,
const u64 *extent_item_pos, u64 total_refs)
{
struct btrfs_root *root;
struct btrfs_key root_key;
struct extent_buffer *eb;
int ret = 0;
int root_level;
int level = ref->level;
int index;
root_key.objectid = ref->root_id;
root_key.type = BTRFS_ROOT_ITEM_KEY;
root_key.offset = (u64)-1;
index = srcu_read_lock(&fs_info->subvol_srcu);
root = btrfs_read_fs_root_no_name(fs_info, &root_key);
if (IS_ERR(root)) {
srcu_read_unlock(&fs_info->subvol_srcu, index);
ret = PTR_ERR(root);
goto out;
}
root_level = btrfs_old_root_level(root, time_seq);
if (root_level + 1 == level) {
srcu_read_unlock(&fs_info->subvol_srcu, index);
goto out;
}
path->lowest_level = level;
ret = btrfs_search_old_slot(root, &ref->key_for_search, path, time_seq);
/* root node has been locked, we can release @subvol_srcu safely here */
srcu_read_unlock(&fs_info->subvol_srcu, index);
pr_debug("search slot in root %llu (level %d, ref count %d) returned "
"%d for key (%llu %u %llu)\n",
ref->root_id, level, ref->count, ret,
ref->key_for_search.objectid, ref->key_for_search.type,
ref->key_for_search.offset);
if (ret < 0)
goto out;
eb = path->nodes[level];
while (!eb) {
if (WARN_ON(!level)) {
ret = 1;
goto out;
}
level--;
eb = path->nodes[level];
}
ret = add_all_parents(root, path, parents, ref, level, time_seq,
extent_item_pos, total_refs);
out:
path->lowest_level = 0;
btrfs_release_path(path);
return ret;
}
/*
* run through the list of inodes in the FS that need
* defragging
*/
int btrfs_run_defrag_inodes(struct btrfs_fs_info *fs_info)
{
struct inode_defrag *defrag;
struct btrfs_root *inode_root;
struct inode *inode;
struct rb_node *n;
struct btrfs_key key;
struct btrfs_ioctl_defrag_range_args range;
u64 first_ino = 0;
u64 root_objectid = 0;
int num_defrag;
int defrag_batch = 1024;
memset(&range, 0, sizeof(range));
range.len = (u64)-1;
atomic_inc(&fs_info->defrag_running);
spin_lock(&fs_info->defrag_inodes_lock);
while(1) {
n = NULL;
/* find an inode to defrag */
defrag = btrfs_find_defrag_inode(fs_info, root_objectid,
first_ino, &n);
if (!defrag) {
if (n) {
defrag = rb_entry(n, struct inode_defrag,
rb_node);
} else if (root_objectid || first_ino) {
root_objectid = 0;
first_ino = 0;
continue;
} else {
break;
}
}
/* remove it from the rbtree */
first_ino = defrag->ino + 1;
root_objectid = defrag->root;
rb_erase(&defrag->rb_node, &fs_info->defrag_inodes);
if (btrfs_fs_closing(fs_info))
goto next_free;
spin_unlock(&fs_info->defrag_inodes_lock);
/* get the inode */
key.objectid = defrag->root;
btrfs_set_key_type(&key, BTRFS_ROOT_ITEM_KEY);
key.offset = (u64)-1;
inode_root = btrfs_read_fs_root_no_name(fs_info, &key);
if (IS_ERR(inode_root))
goto next;
key.objectid = defrag->ino;
btrfs_set_key_type(&key, BTRFS_INODE_ITEM_KEY);
key.offset = 0;
inode = btrfs_iget(fs_info->sb, &key, inode_root, NULL);
if (IS_ERR(inode))
goto next;
/* do a chunk of defrag */
clear_bit(BTRFS_INODE_IN_DEFRAG, &BTRFS_I(inode)->runtime_flags);
range.start = defrag->last_offset;
num_defrag = btrfs_defrag_file(inode, NULL, &range, defrag->transid,
defrag_batch);
/*
* if we filled the whole defrag batch, there
* must be more work to do. Queue this defrag
* again
*/
if (num_defrag == defrag_batch) {
defrag->last_offset = range.start;
__btrfs_add_inode_defrag(inode, defrag);
/*
* we don't want to kfree defrag, we added it back to
* the rbtree
*/
defrag = NULL;
} else if (defrag->last_offset && !defrag->cycled) {
/*
* we didn't fill our defrag batch, but
* we didn't start at zero. Make sure we loop
* around to the start of the file.
*/
defrag->last_offset = 0;
defrag->cycled = 1;
__btrfs_add_inode_defrag(inode, defrag);
defrag = NULL;
}
iput(inode);
next:
spin_lock(&fs_info->defrag_inodes_lock);
next_free:
kfree(defrag);
}
