2007-06-12 07:07:21 -06:00
|
|
|
/*
|
|
|
|
* Copyright (C) 2007 Oracle. All rights reserved.
|
|
|
|
*
|
|
|
|
* This program is free software; you can redistribute it and/or
|
|
|
|
* modify it under the terms of the GNU General Public
|
|
|
|
* License v2 as published by the Free Software Foundation.
|
|
|
|
*
|
|
|
|
* This program is distributed in the hope that it will be useful,
|
|
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
|
|
|
* General Public License for more details.
|
|
|
|
*
|
|
|
|
* You should have received a copy of the GNU General Public
|
|
|
|
* License along with this program; if not, write to the
|
|
|
|
* Free Software Foundation, Inc., 59 Temple Place - Suite 330,
|
|
|
|
* Boston, MA 021110-1307, USA.
|
|
|
|
*/
|
|
|
|
|
2014-02-16 20:43:57 -07:00
|
|
|
#include <linux/err.h>
|
2012-07-25 09:35:53 -06:00
|
|
|
#include <linux/uuid.h>
|
2007-03-13 14:47:54 -06:00
|
|
|
#include "ctree.h"
|
2007-06-22 12:16:25 -06:00
|
|
|
#include "transaction.h"
|
2007-03-13 14:47:54 -06:00
|
|
|
#include "disk-io.h"
|
|
|
|
#include "print-tree.h"
|
|
|
|
|
2012-07-25 09:35:53 -06:00
|
|
|
/*
|
|
|
|
* Read a root item from the tree. In case we detect a root item smaller then
|
|
|
|
* sizeof(root_item), we know it's an old version of the root structure and
|
|
|
|
* initialize all new fields to zero. The same happens if we detect mismatching
|
|
|
|
* generation numbers as then we know the root was once mounted with an older
|
|
|
|
* kernel that was not aware of the root item structure change.
|
|
|
|
*/
|
2013-08-14 14:27:46 -06:00
|
|
|
static void btrfs_read_root_item(struct extent_buffer *eb, int slot,
|
|
|
|
struct btrfs_root_item *item)
|
2012-07-25 09:35:53 -06:00
|
|
|
{
|
|
|
|
uuid_le uuid;
|
|
|
|
int len;
|
|
|
|
int need_reset = 0;
|
|
|
|
|
|
|
|
len = btrfs_item_size_nr(eb, slot);
|
|
|
|
read_extent_buffer(eb, item, btrfs_item_ptr_offset(eb, slot),
|
|
|
|
min_t(int, len, (int)sizeof(*item)));
|
|
|
|
if (len < sizeof(*item))
|
|
|
|
need_reset = 1;
|
|
|
|
if (!need_reset && btrfs_root_generation(item)
|
|
|
|
!= btrfs_root_generation_v2(item)) {
|
|
|
|
if (btrfs_root_generation_v2(item) != 0) {
|
2015-10-08 03:37:06 -06:00
|
|
|
btrfs_warn(eb->fs_info,
|
|
|
|
"mismatching "
|
2012-07-25 09:35:53 -06:00
|
|
|
"generation and generation_v2 "
|
|
|
|
"found in root item. This root "
|
|
|
|
"was probably mounted with an "
|
|
|
|
"older kernel. Resetting all "
|
2015-10-08 03:37:06 -06:00
|
|
|
"new fields.");
|
2012-07-25 09:35:53 -06:00
|
|
|
}
|
|
|
|
need_reset = 1;
|
|
|
|
}
|
|
|
|
if (need_reset) {
|
|
|
|
memset(&item->generation_v2, 0,
|
|
|
|
sizeof(*item) - offsetof(struct btrfs_root_item,
|
|
|
|
generation_v2));
|
|
|
|
|
|
|
|
uuid_le_gen(&uuid);
|
|
|
|
memcpy(item->uuid, uuid.b, BTRFS_UUID_SIZE);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2008-09-29 13:18:18 -06:00
|
|
|
/*
|
2013-05-15 01:48:19 -06:00
|
|
|
* btrfs_find_root - lookup the root by the key.
|
|
|
|
* root: the root of the root tree
|
|
|
|
* search_key: the key to search
|
|
|
|
* path: the path we search
|
|
|
|
* root_item: the root item of the tree we look for
|
2016-05-19 19:18:45 -06:00
|
|
|
* root_key: the root key of the tree we look for
|
2013-05-15 01:48:19 -06:00
|
|
|
*
|
2016-05-19 19:18:45 -06:00
|
|
|
* If ->offset of 'search_key' is -1ULL, it means we are not sure the offset
|
2013-05-15 01:48:19 -06:00
|
|
|
* of the search key, just lookup the root with the highest offset for a
|
|
|
|
* given objectid.
|
|
|
|
*
|
|
|
|
* If we find something return 0, otherwise > 0, < 0 on error.
|
2008-09-29 13:18:18 -06:00
|
|
|
*/
|
2013-05-15 01:48:19 -06:00
|
|
|
int btrfs_find_root(struct btrfs_root *root, struct btrfs_key *search_key,
|
|
|
|
struct btrfs_path *path, struct btrfs_root_item *root_item,
|
|
|
|
struct btrfs_key *root_key)
|
2007-03-13 14:47:54 -06:00
|
|
|
{
|
2007-10-15 14:14:19 -06:00
|
|
|
struct btrfs_key found_key;
|
|
|
|
struct extent_buffer *l;
|
2007-03-13 14:47:54 -06:00
|
|
|
int ret;
|
|
|
|
int slot;
|
|
|
|
|
2013-05-15 01:48:19 -06:00
|
|
|
ret = btrfs_search_slot(NULL, root, search_key, path, 0, 0);
|
2007-03-13 14:47:54 -06:00
|
|
|
if (ret < 0)
|
2013-05-15 01:48:19 -06:00
|
|
|
return ret;
|
2007-10-15 14:14:19 -06:00
|
|
|
|
2013-05-15 01:48:19 -06:00
|
|
|
if (search_key->offset != -1ULL) { /* the search key is exact */
|
|
|
|
if (ret > 0)
|
|
|
|
goto out;
|
|
|
|
} else {
|
|
|
|
BUG_ON(ret == 0); /* Logical error */
|
|
|
|
if (path->slots[0] == 0)
|
|
|
|
goto out;
|
|
|
|
path->slots[0]--;
|
|
|
|
ret = 0;
|
2009-09-21 14:00:26 -06:00
|
|
|
}
|
2013-05-15 01:48:19 -06:00
|
|
|
|
2007-10-15 14:14:19 -06:00
|
|
|
l = path->nodes[0];
|
2013-05-15 01:48:19 -06:00
|
|
|
slot = path->slots[0];
|
|
|
|
|
2007-10-15 14:14:19 -06:00
|
|
|
btrfs_item_key_to_cpu(l, &found_key, slot);
|
2013-05-15 01:48:19 -06:00
|
|
|
if (found_key.objectid != search_key->objectid ||
|
2009-09-21 14:00:26 -06:00
|
|
|
found_key.type != BTRFS_ROOT_ITEM_KEY) {
|
2007-03-13 14:47:54 -06:00
|
|
|
ret = 1;
|
|
|
|
goto out;
|
|
|
|
}
|
2012-07-25 09:35:53 -06:00
|
|
|
|
2013-05-15 01:48:19 -06:00
|
|
|
if (root_item)
|
|
|
|
btrfs_read_root_item(l, slot, root_item);
|
|
|
|
if (root_key)
|
|
|
|
memcpy(root_key, &found_key, sizeof(found_key));
|
2007-03-13 14:47:54 -06:00
|
|
|
out:
|
2013-05-15 01:48:19 -06:00
|
|
|
btrfs_release_path(path);
|
2007-03-13 14:47:54 -06:00
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2011-07-14 15:23:06 -06:00
|
|
|
void btrfs_set_root_node(struct btrfs_root_item *item,
|
|
|
|
struct extent_buffer *node)
|
Btrfs: Mixed back reference (FORWARD ROLLING FORMAT CHANGE)
This commit introduces a new kind of back reference for btrfs metadata.
Once a filesystem has been mounted with this commit, IT WILL NO LONGER
BE MOUNTABLE BY OLDER KERNELS.
When a tree block in subvolume tree is cow'd, the reference counts of all
extents it points to are increased by one. At transaction commit time,
the old root of the subvolume is recorded in a "dead root" data structure,
and the btree it points to is later walked, dropping reference counts
and freeing any blocks where the reference count goes to 0.
The increments done during cow and decrements done after commit cancel out,
and the walk is a very expensive way to go about freeing the blocks that
are no longer referenced by the new btree root. This commit reduces the
transaction overhead by avoiding the need for dead root records.
When a non-shared tree block is cow'd, we free the old block at once, and the
new block inherits old block's references. When a tree block with reference
count > 1 is cow'd, we increase the reference counts of all extents
the new block points to by one, and decrease the old block's reference count by
one.
This dead tree avoidance code removes the need to modify the reference
counts of lower level extents when a non-shared tree block is cow'd.
But we still need to update back ref for all pointers in the block.
This is because the location of the block is recorded in the back ref
item.
We can solve this by introducing a new type of back ref. The new
back ref provides information about pointer's key, level and in which
tree the pointer lives. This information allow us to find the pointer
by searching the tree. The shortcoming of the new back ref is that it
only works for pointers in tree blocks referenced by their owner trees.
This is mostly a problem for snapshots, where resolving one of these
fuzzy back references would be O(number_of_snapshots) and quite slow.
The solution used here is to use the fuzzy back references in the common
case where a given tree block is only referenced by one root,
and use the full back references when multiple roots have a reference
on a given block.
This commit adds per subvolume red-black tree to keep trace of cached
inodes. The red-black tree helps the balancing code to find cached
inodes whose inode numbers within a given range.
This commit improves the balancing code by introducing several data
structures to keep the state of balancing. The most important one
is the back ref cache. It caches how the upper level tree blocks are
referenced. This greatly reduce the overhead of checking back ref.
The improved balancing code scales significantly better with a large
number of snapshots.
This is a very large commit and was written in a number of
pieces. But, they depend heavily on the disk format change and were
squashed together to make sure git bisect didn't end up in a
bad state wrt space balancing or the format change.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2009-06-10 08:45:14 -06:00
|
|
|
{
|
|
|
|
btrfs_set_root_bytenr(item, node->start);
|
|
|
|
btrfs_set_root_level(item, btrfs_header_level(node));
|
|
|
|
btrfs_set_root_generation(item, btrfs_header_generation(node));
|
|
|
|
}
|
|
|
|
|
2008-09-29 13:18:18 -06:00
|
|
|
/*
|
|
|
|
* copy the data in 'item' into the btree
|
|
|
|
*/
|
2007-03-16 14:20:31 -06:00
|
|
|
int btrfs_update_root(struct btrfs_trans_handle *trans, struct btrfs_root
|
|
|
|
*root, struct btrfs_key *key, struct btrfs_root_item
|
|
|
|
*item)
|
2007-03-13 14:47:54 -06:00
|
|
|
{
|
2007-04-02 09:20:42 -06:00
|
|
|
struct btrfs_path *path;
|
2007-10-15 14:14:19 -06:00
|
|
|
struct extent_buffer *l;
|
2007-03-13 14:47:54 -06:00
|
|
|
int ret;
|
|
|
|
int slot;
|
2007-10-15 14:14:19 -06:00
|
|
|
unsigned long ptr;
|
2015-08-24 15:56:28 -06:00
|
|
|
u32 old_len;
|
2007-03-13 14:47:54 -06:00
|
|
|
|
2007-04-02 09:20:42 -06:00
|
|
|
path = btrfs_alloc_path();
|
2011-10-03 21:22:44 -06:00
|
|
|
if (!path)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
2007-04-02 09:20:42 -06:00
|
|
|
ret = btrfs_search_slot(trans, root, key, path, 0, 1);
|
2012-09-18 07:52:32 -06:00
|
|
|
if (ret < 0) {
|
|
|
|
btrfs_abort_transaction(trans, root, ret);
|
|
|
|
goto out;
|
|
|
|
}
|
2008-01-03 12:51:00 -07:00
|
|
|
|
|
|
|
if (ret != 0) {
|
|
|
|
btrfs_print_leaf(root, path->nodes[0]);
|
2013-12-20 09:37:06 -07:00
|
|
|
btrfs_crit(root->fs_info, "unable to update root key %llu %u %llu",
|
2013-08-20 05:20:07 -06:00
|
|
|
key->objectid, key->type, key->offset);
|
2008-01-03 12:51:00 -07:00
|
|
|
BUG_ON(1);
|
|
|
|
}
|
|
|
|
|
2007-10-15 14:14:19 -06:00
|
|
|
l = path->nodes[0];
|
2007-04-02 09:20:42 -06:00
|
|
|
slot = path->slots[0];
|
2007-10-15 14:14:19 -06:00
|
|
|
ptr = btrfs_item_ptr_offset(l, slot);
|
2012-07-25 09:35:53 -06:00
|
|
|
old_len = btrfs_item_size_nr(l, slot);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* If this is the first time we update the root item which originated
|
|
|
|
* from an older kernel, we need to enlarge the item size to make room
|
|
|
|
* for the added fields.
|
|
|
|
*/
|
|
|
|
if (old_len < sizeof(*item)) {
|
|
|
|
btrfs_release_path(path);
|
|
|
|
ret = btrfs_search_slot(trans, root, key, path,
|
|
|
|
-1, 1);
|
2012-09-18 07:52:32 -06:00
|
|
|
if (ret < 0) {
|
|
|
|
btrfs_abort_transaction(trans, root, ret);
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
2012-07-25 09:35:53 -06:00
|
|
|
ret = btrfs_del_item(trans, root, path);
|
2012-09-18 07:52:32 -06:00
|
|
|
if (ret < 0) {
|
|
|
|
btrfs_abort_transaction(trans, root, ret);
|
|
|
|
goto out;
|
|
|
|
}
|
2012-07-25 09:35:53 -06:00
|
|
|
btrfs_release_path(path);
|
|
|
|
ret = btrfs_insert_empty_item(trans, root, path,
|
|
|
|
key, sizeof(*item));
|
2012-09-18 07:52:32 -06:00
|
|
|
if (ret < 0) {
|
|
|
|
btrfs_abort_transaction(trans, root, ret);
|
|
|
|
goto out;
|
|
|
|
}
|
2012-07-25 09:35:53 -06:00
|
|
|
l = path->nodes[0];
|
|
|
|
slot = path->slots[0];
|
|
|
|
ptr = btrfs_item_ptr_offset(l, slot);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Update generation_v2 so at the next mount we know the new root
|
|
|
|
* fields are valid.
|
|
|
|
*/
|
|
|
|
btrfs_set_root_generation_v2(item, btrfs_root_generation(item));
|
|
|
|
|
2007-10-15 14:14:19 -06:00
|
|
|
write_extent_buffer(l, item, ptr, sizeof(*item));
|
2007-04-02 09:20:42 -06:00
|
|
|
btrfs_mark_buffer_dirty(path->nodes[0]);
|
2007-03-13 14:47:54 -06:00
|
|
|
out:
|
2007-04-02 09:20:42 -06:00
|
|
|
btrfs_free_path(path);
|
2007-03-13 14:47:54 -06:00
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2011-10-03 21:22:34 -06:00
|
|
|
int btrfs_insert_root(struct btrfs_trans_handle *trans, struct btrfs_root *root,
|
|
|
|
struct btrfs_key *key, struct btrfs_root_item *item)
|
2007-03-13 14:47:54 -06:00
|
|
|
{
|
2012-07-25 09:35:53 -06:00
|
|
|
/*
|
|
|
|
* Make sure generation v1 and v2 match. See update_root for details.
|
|
|
|
*/
|
|
|
|
btrfs_set_root_generation_v2(item, btrfs_root_generation(item));
|
2011-10-03 21:22:34 -06:00
|
|
|
return btrfs_insert_item(trans, root, key, item, sizeof(*item));
|
2007-03-13 14:47:54 -06:00
|
|
|
}
|
|
|
|
|
2009-09-21 14:00:26 -06:00
|
|
|
int btrfs_find_orphan_roots(struct btrfs_root *tree_root)
|
|
|
|
{
|
|
|
|
struct extent_buffer *leaf;
|
|
|
|
struct btrfs_path *path;
|
|
|
|
struct btrfs_key key;
|
2010-05-16 08:49:58 -06:00
|
|
|
struct btrfs_key root_key;
|
|
|
|
struct btrfs_root *root;
|
2009-09-21 14:00:26 -06:00
|
|
|
int err = 0;
|
|
|
|
int ret;
|
2013-06-27 09:32:16 -06:00
|
|
|
bool can_recover = true;
|
|
|
|
|
|
|
|
if (tree_root->fs_info->sb->s_flags & MS_RDONLY)
|
|
|
|
can_recover = false;
|
2009-09-21 14:00:26 -06:00
|
|
|
|
|
|
|
path = btrfs_alloc_path();
|
|
|
|
if (!path)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
|
|
|
key.objectid = BTRFS_ORPHAN_OBJECTID;
|
|
|
|
key.type = BTRFS_ORPHAN_ITEM_KEY;
|
|
|
|
key.offset = 0;
|
|
|
|
|
2010-05-16 08:49:58 -06:00
|
|
|
root_key.type = BTRFS_ROOT_ITEM_KEY;
|
|
|
|
root_key.offset = (u64)-1;
|
|
|
|
|
2009-09-21 14:00:26 -06:00
|
|
|
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]);
|
2011-04-20 17:20:15 -06:00
|
|
|
btrfs_release_path(path);
|
2009-09-21 14:00:26 -06:00
|
|
|
|
|
|
|
if (key.objectid != BTRFS_ORPHAN_OBJECTID ||
|
|
|
|
key.type != BTRFS_ORPHAN_ITEM_KEY)
|
|
|
|
break;
|
|
|
|
|
2010-05-16 08:49:58 -06:00
|
|
|
root_key.objectid = key.offset;
|
|
|
|
key.offset++;
|
|
|
|
|
2013-05-15 01:48:19 -06:00
|
|
|
root = btrfs_read_fs_root(tree_root, &root_key);
|
2014-02-16 20:43:57 -07:00
|
|
|
err = PTR_ERR_OR_ZERO(root);
|
2013-06-27 09:32:16 -06:00
|
|
|
if (err && err != -ENOENT) {
|
2013-05-15 01:48:19 -06:00
|
|
|
break;
|
2013-06-27 09:32:16 -06:00
|
|
|
} else if (err == -ENOENT) {
|
|
|
|
struct btrfs_trans_handle *trans;
|
|
|
|
|
|
|
|
btrfs_release_path(path);
|
|
|
|
|
|
|
|
trans = btrfs_join_transaction(tree_root);
|
|
|
|
if (IS_ERR(trans)) {
|
|
|
|
err = PTR_ERR(trans);
|
2016-03-16 02:43:06 -06:00
|
|
|
btrfs_handle_fs_error(tree_root->fs_info, err,
|
2013-06-27 09:32:16 -06:00
|
|
|
"Failed to start trans to delete "
|
|
|
|
"orphan item");
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
err = btrfs_del_orphan_item(trans, tree_root,
|
|
|
|
root_key.objectid);
|
|
|
|
btrfs_end_transaction(trans, tree_root);
|
|
|
|
if (err) {
|
2016-03-16 02:43:06 -06:00
|
|
|
btrfs_handle_fs_error(tree_root->fs_info, err,
|
2013-06-27 09:32:16 -06:00
|
|
|
"Failed to delete root orphan "
|
|
|
|
"item");
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
continue;
|
2013-05-15 01:48:19 -06:00
|
|
|
}
|
|
|
|
|
|
|
|
err = btrfs_init_fs_root(root);
|
|
|
|
if (err) {
|
|
|
|
btrfs_free_fs_root(root);
|
2009-09-21 14:00:26 -06:00
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
2014-04-02 05:51:05 -06:00
|
|
|
set_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &root->state);
|
2013-05-15 01:48:19 -06:00
|
|
|
|
|
|
|
err = btrfs_insert_fs_root(root->fs_info, root);
|
Btrfs: fix loading of orphan roots leading to BUG_ON
When looking for orphan roots during mount we can end up hitting a
BUG_ON() (at root-item.c:btrfs_find_orphan_roots()) if a log tree is
replayed and qgroups are enabled. This is because after a log tree is
replayed, a transaction commit is made, which triggers qgroup extent
accounting which in turn does backref walking which ends up reading and
inserting all roots in the radix tree fs_info->fs_root_radix, including
orphan roots (deleted snapshots). So after the log tree is replayed, when
finding orphan roots we hit the BUG_ON with the following trace:
[118209.182438] ------------[ cut here ]------------
[118209.183279] kernel BUG at fs/btrfs/root-tree.c:314!
[118209.184074] invalid opcode: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC
[118209.185123] Modules linked in: btrfs dm_flakey dm_mod crc32c_generic ppdev xor raid6_pq evdev sg parport_pc parport acpi_cpufreq tpm_tis tpm psmouse
processor i2c_piix4 serio_raw pcspkr i2c_core button loop autofs4 ext4 crc16 mbcache jbd2 sd_mod sr_mod cdrom ata_generic virtio_scsi ata_piix libata
virtio_pci virtio_ring virtio scsi_mod e1000 floppy [last unloaded: btrfs]
[118209.186318] CPU: 14 PID: 28428 Comm: mount Tainted: G W 4.5.0-rc5-btrfs-next-24+ #1
[118209.186318] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS by qemu-project.org 04/01/2014
[118209.186318] task: ffff8801ec131040 ti: ffff8800af34c000 task.ti: ffff8800af34c000
[118209.186318] RIP: 0010:[<ffffffffa04237d7>] [<ffffffffa04237d7>] btrfs_find_orphan_roots+0x1fc/0x244 [btrfs]
[118209.186318] RSP: 0018:ffff8800af34faa8 EFLAGS: 00010246
[118209.186318] RAX: 00000000ffffffef RBX: 00000000ffffffef RCX: 0000000000000001
[118209.186318] RDX: 0000000080000000 RSI: 0000000000000001 RDI: 00000000ffffffff
[118209.186318] RBP: ffff8800af34fb08 R08: 0000000000000001 R09: 0000000000000000
[118209.186318] R10: ffff8800af34f9f0 R11: 6db6db6db6db6db7 R12: ffff880171b97000
[118209.186318] R13: ffff8801ca9d65e0 R14: ffff8800afa2e000 R15: 0000160000000000
[118209.186318] FS: 00007f5bcb914840(0000) GS:ffff88023edc0000(0000) knlGS:0000000000000000
[118209.186318] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b
[118209.186318] CR2: 00007f5bcaceb5d9 CR3: 00000000b49b5000 CR4: 00000000000006e0
[118209.186318] Stack:
[118209.186318] fffffbffffffffff 010230ffffffffff 0101000000000000 ff84000000000000
[118209.186318] fbffffffffffffff 30ffffffffffffff 0000000000000101 ffff880082348000
[118209.186318] 0000000000000000 ffff8800afa2e000 ffff8800afa2e000 0000000000000000
[118209.186318] Call Trace:
[118209.186318] [<ffffffffa042e2db>] open_ctree+0x1e37/0x21b9 [btrfs]
[118209.186318] [<ffffffffa040a753>] btrfs_mount+0x97e/0xaed [btrfs]
[118209.186318] [<ffffffff8108e1c0>] ? trace_hardirqs_on+0xd/0xf
[118209.186318] [<ffffffff8117b87e>] mount_fs+0x67/0x131
[118209.186318] [<ffffffff81192d2b>] vfs_kern_mount+0x6c/0xde
[118209.186318] [<ffffffffa0409f81>] btrfs_mount+0x1ac/0xaed [btrfs]
[118209.186318] [<ffffffff8108e1c0>] ? trace_hardirqs_on+0xd/0xf
[118209.186318] [<ffffffff8108c26b>] ? lockdep_init_map+0xb9/0x1b3
[118209.186318] [<ffffffff8117b87e>] mount_fs+0x67/0x131
[118209.186318] [<ffffffff81192d2b>] vfs_kern_mount+0x6c/0xde
[118209.186318] [<ffffffff81195637>] do_mount+0x8a6/0x9e8
[118209.186318] [<ffffffff8119598d>] SyS_mount+0x77/0x9f
[118209.186318] [<ffffffff81493017>] entry_SYSCALL_64_fastpath+0x12/0x6b
[118209.186318] Code: 64 00 00 85 c0 89 c3 75 24 f0 41 80 4c 24 20 20 49 8b bc 24 f0 01 00 00 4c 89 e6 e8 e8 65 00 00 85 c0 89 c3 74 11 83 f8 ef 75 02 <0f> 0b
4c 89 e7 e8 da 72 00 00 eb 1c 41 83 bc 24 00 01 00 00 00
[118209.186318] RIP [<ffffffffa04237d7>] btrfs_find_orphan_roots+0x1fc/0x244 [btrfs]
[118209.186318] RSP <ffff8800af34faa8>
[118209.230735] ---[ end trace 83938f987d85d477 ]---
So fix this by not treating the error -EEXIST, returned when attempting
to insert a root already inserted by the backref walking code, as an error.
The following test case for xfstests reproduces the bug:
seq=`basename $0`
seqres=$RESULT_DIR/$seq
echo "QA output created by $seq"
tmp=/tmp/$$
status=1 # failure is the default!
trap "_cleanup; exit \$status" 0 1 2 3 15
_cleanup()
{
_cleanup_flakey
cd /
rm -f $tmp.*
}
# get standard environment, filters and checks
. ./common/rc
. ./common/filter
. ./common/dmflakey
# real QA test starts here
_supported_fs btrfs
_supported_os Linux
_require_scratch
_require_dm_target flakey
_require_metadata_journaling $SCRATCH_DEV
rm -f $seqres.full
_scratch_mkfs >>$seqres.full 2>&1
_init_flakey
_mount_flakey
_run_btrfs_util_prog quota enable $SCRATCH_MNT
# Create 2 directories with one file in one of them.
# We use these just to trigger a transaction commit later, moving the file from
# directory a to directory b and doing an fsync against directory a.
mkdir $SCRATCH_MNT/a
mkdir $SCRATCH_MNT/b
touch $SCRATCH_MNT/a/f
sync
# Create our test file with 2 4K extents.
$XFS_IO_PROG -f -s -c "pwrite -S 0xaa 0 8K" $SCRATCH_MNT/foobar | _filter_xfs_io
# Create a snapshot and delete it. This doesn't really delete the snapshot
# immediately, just makes it inaccessible and invisible to user space, the
# snapshot is deleted later by a dedicated kernel thread (cleaner kthread)
# which is woke up at the next transaction commit.
# A root orphan item is inserted into the tree of tree roots, so that if a
# power failure happens before the dedicated kernel thread does the snapshot
# deletion, the next time the filesystem is mounted it resumes the snapshot
# deletion.
_run_btrfs_util_prog subvolume snapshot $SCRATCH_MNT $SCRATCH_MNT/snap
_run_btrfs_util_prog subvolume delete $SCRATCH_MNT/snap
# Now overwrite half of the extents we wrote before. Because we made a snapshpot
# before, which isn't really deleted yet (since no transaction commit happened
# after we did the snapshot delete request), the non overwritten extents get
# referenced twice, once by the default subvolume and once by the snapshot.
$XFS_IO_PROG -c "pwrite -S 0xbb 4K 8K" $SCRATCH_MNT/foobar | _filter_xfs_io
# Now move file f from directory a to directory b and fsync directory a.
# The fsync on the directory a triggers a transaction commit (because a file
# was moved from it to another directory) and the file fsync leaves a log tree
# with file extent items to replay.
mv $SCRATCH_MNT/a/f $SCRATCH_MNT/a/b
$XFS_IO_PROG -c "fsync" $SCRATCH_MNT/a
$XFS_IO_PROG -c "fsync" $SCRATCH_MNT/foobar
echo "File digest before power failure:"
md5sum $SCRATCH_MNT/foobar | _filter_scratch
# Now simulate a power failure and mount the filesystem to replay the log tree.
# After the log tree was replayed, we used to hit a BUG_ON() when processing
# the root orphan item for the deleted snapshot. This is because when processing
# an orphan root the code expected to be the first code inserting the root into
# the fs_info->fs_root_radix radix tree, while in reallity it was the second
# caller attempting to do it - the first caller was the transaction commit that
# took place after replaying the log tree, when updating the qgroup counters.
_flakey_drop_and_remount
echo "File digest before after failure:"
# Must match what he got before the power failure.
md5sum $SCRATCH_MNT/foobar | _filter_scratch
_unmount_flakey
status=0
exit
Fixes: 2d9e97761087 ("Btrfs: use btrfs_get_fs_root in resolve_indirect_ref")
Cc: stable@vger.kernel.org # 4.4+
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: Qu Wenruo <quwenruo@cn.fujitsu.com>
Signed-off-by: Chris Mason <clm@fb.com>
2016-03-02 08:49:38 -07:00
|
|
|
/*
|
|
|
|
* The root might have been inserted already, as before we look
|
|
|
|
* for orphan roots, log replay might have happened, which
|
|
|
|
* triggers a transaction commit and qgroup accounting, which
|
|
|
|
* in turn reads and inserts fs roots while doing backref
|
|
|
|
* walking.
|
|
|
|
*/
|
|
|
|
if (err == -EEXIST)
|
|
|
|
err = 0;
|
2013-05-15 01:48:19 -06:00
|
|
|
if (err) {
|
|
|
|
btrfs_free_fs_root(root);
|
2010-05-16 08:49:58 -06:00
|
|
|
break;
|
|
|
|
}
|
2013-09-25 07:47:43 -06:00
|
|
|
|
|
|
|
if (btrfs_root_refs(&root->root_item) == 0)
|
|
|
|
btrfs_add_dead_root(root);
|
2009-09-21 14:00:26 -06:00
|
|
|
}
|
|
|
|
|
|
|
|
btrfs_free_path(path);
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
2008-09-29 13:18:18 -06:00
|
|
|
/* drop the root item for 'key' from 'root' */
|
2007-03-16 14:20:31 -06:00
|
|
|
int btrfs_del_root(struct btrfs_trans_handle *trans, struct btrfs_root *root,
|
|
|
|
struct btrfs_key *key)
|
2007-03-13 14:47:54 -06:00
|
|
|
{
|
2007-04-02 09:20:42 -06:00
|
|
|
struct btrfs_path *path;
|
2007-03-13 14:47:54 -06:00
|
|
|
int ret;
|
|
|
|
|
2007-04-02 09:20:42 -06:00
|
|
|
path = btrfs_alloc_path();
|
2011-03-23 02:14:16 -06:00
|
|
|
if (!path)
|
|
|
|
return -ENOMEM;
|
2007-04-02 09:20:42 -06:00
|
|
|
ret = btrfs_search_slot(trans, root, key, path, -1, 1);
|
2007-03-13 14:47:54 -06:00
|
|
|
if (ret < 0)
|
|
|
|
goto out;
|
2007-12-21 14:27:24 -07:00
|
|
|
|
2007-03-13 14:47:54 -06:00
|
|
|
BUG_ON(ret != 0);
|
2007-04-10 07:27:04 -06:00
|
|
|
|
2007-06-22 12:16:25 -06:00
|
|
|
ret = btrfs_del_item(trans, root, path);
|
2007-03-13 14:47:54 -06:00
|
|
|
out:
|
2007-04-02 09:20:42 -06:00
|
|
|
btrfs_free_path(path);
|
2007-03-13 14:47:54 -06:00
|
|
|
return ret;
|
|
|
|
}
|
2008-11-17 18:37:39 -07:00
|
|
|
|
|
|
|
int btrfs_del_root_ref(struct btrfs_trans_handle *trans,
|
|
|
|
struct btrfs_root *tree_root,
|
2009-09-21 13:56:00 -06:00
|
|
|
u64 root_id, u64 ref_id, u64 dirid, u64 *sequence,
|
|
|
|
const char *name, int name_len)
|
|
|
|
|
2008-11-17 18:37:39 -07:00
|
|
|
{
|
2009-09-21 13:56:00 -06:00
|
|
|
struct btrfs_path *path;
|
|
|
|
struct btrfs_root_ref *ref;
|
|
|
|
struct extent_buffer *leaf;
|
2008-11-17 18:37:39 -07:00
|
|
|
struct btrfs_key key;
|
2009-09-21 13:56:00 -06:00
|
|
|
unsigned long ptr;
|
|
|
|
int err = 0;
|
2008-11-17 18:37:39 -07:00
|
|
|
int ret;
|
|
|
|
|
|
|
|
path = btrfs_alloc_path();
|
2009-09-21 13:56:00 -06:00
|
|
|
if (!path)
|
|
|
|
return -ENOMEM;
|
2008-11-17 18:37:39 -07:00
|
|
|
|
|
|
|
key.objectid = root_id;
|
2009-09-21 13:56:00 -06:00
|
|
|
key.type = BTRFS_ROOT_BACKREF_KEY;
|
2008-11-17 18:37:39 -07:00
|
|
|
key.offset = ref_id;
|
2009-09-21 13:56:00 -06:00
|
|
|
again:
|
2008-11-17 18:37:39 -07:00
|
|
|
ret = btrfs_search_slot(trans, tree_root, &key, path, -1, 1);
|
2009-09-21 13:56:00 -06:00
|
|
|
BUG_ON(ret < 0);
|
|
|
|
if (ret == 0) {
|
|
|
|
leaf = path->nodes[0];
|
|
|
|
ref = btrfs_item_ptr(leaf, path->slots[0],
|
|
|
|
struct btrfs_root_ref);
|
|
|
|
|
|
|
|
WARN_ON(btrfs_root_ref_dirid(leaf, ref) != dirid);
|
|
|
|
WARN_ON(btrfs_root_ref_name_len(leaf, ref) != name_len);
|
|
|
|
ptr = (unsigned long)(ref + 1);
|
|
|
|
WARN_ON(memcmp_extent_buffer(leaf, name, ptr, name_len));
|
|
|
|
*sequence = btrfs_root_ref_sequence(leaf, ref);
|
|
|
|
|
|
|
|
ret = btrfs_del_item(trans, tree_root, path);
|
2011-05-18 22:37:44 -06:00
|
|
|
if (ret) {
|
|
|
|
err = ret;
|
|
|
|
goto out;
|
|
|
|
}
|
2009-09-21 13:56:00 -06:00
|
|
|
} else
|
|
|
|
err = -ENOENT;
|
|
|
|
|
|
|
|
if (key.type == BTRFS_ROOT_BACKREF_KEY) {
|
2011-04-20 17:20:15 -06:00
|
|
|
btrfs_release_path(path);
|
2009-09-21 13:56:00 -06:00
|
|
|
key.objectid = ref_id;
|
|
|
|
key.type = BTRFS_ROOT_REF_KEY;
|
|
|
|
key.offset = root_id;
|
|
|
|
goto again;
|
|
|
|
}
|
2008-11-17 18:37:39 -07:00
|
|
|
|
2011-05-18 22:37:44 -06:00
|
|
|
out:
|
2008-11-17 18:37:39 -07:00
|
|
|
btrfs_free_path(path);
|
2009-09-21 13:56:00 -06:00
|
|
|
return err;
|
2008-11-17 18:37:39 -07:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* add a btrfs_root_ref item. type is either BTRFS_ROOT_REF_KEY
|
|
|
|
* or BTRFS_ROOT_BACKREF_KEY.
|
|
|
|
*
|
|
|
|
* The dirid, sequence, name and name_len refer to the directory entry
|
|
|
|
* that is referencing the root.
|
|
|
|
*
|
|
|
|
* For a forward ref, the root_id is the id of the tree referencing
|
|
|
|
* the root and ref_id is the id of the subvol or snapshot.
|
|
|
|
*
|
|
|
|
* For a back ref the root_id is the id of the subvol or snapshot and
|
|
|
|
* ref_id is the id of the tree referencing it.
|
2012-03-12 09:03:00 -06:00
|
|
|
*
|
|
|
|
* Will return 0, -ENOMEM, or anything from the CoW path
|
2008-11-17 18:37:39 -07:00
|
|
|
*/
|
|
|
|
int btrfs_add_root_ref(struct btrfs_trans_handle *trans,
|
|
|
|
struct btrfs_root *tree_root,
|
2009-09-21 13:56:00 -06:00
|
|
|
u64 root_id, u64 ref_id, u64 dirid, u64 sequence,
|
2008-11-17 18:37:39 -07:00
|
|
|
const char *name, int name_len)
|
|
|
|
{
|
|
|
|
struct btrfs_key key;
|
|
|
|
int ret;
|
|
|
|
struct btrfs_path *path;
|
|
|
|
struct btrfs_root_ref *ref;
|
|
|
|
struct extent_buffer *leaf;
|
|
|
|
unsigned long ptr;
|
|
|
|
|
|
|
|
path = btrfs_alloc_path();
|
2009-09-21 13:56:00 -06:00
|
|
|
if (!path)
|
|
|
|
return -ENOMEM;
|
2008-11-17 18:37:39 -07:00
|
|
|
|
|
|
|
key.objectid = root_id;
|
2009-09-21 13:56:00 -06:00
|
|
|
key.type = BTRFS_ROOT_BACKREF_KEY;
|
2008-11-17 18:37:39 -07:00
|
|
|
key.offset = ref_id;
|
2009-09-21 13:56:00 -06:00
|
|
|
again:
|
2008-11-17 18:37:39 -07:00
|
|
|
ret = btrfs_insert_empty_item(trans, tree_root, path, &key,
|
|
|
|
sizeof(*ref) + name_len);
|
2012-03-12 09:03:00 -06:00
|
|
|
if (ret) {
|
|
|
|
btrfs_abort_transaction(trans, tree_root, ret);
|
|
|
|
btrfs_free_path(path);
|
|
|
|
return ret;
|
|
|
|
}
|
2008-11-17 18:37:39 -07:00
|
|
|
|
|
|
|
leaf = path->nodes[0];
|
|
|
|
ref = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_root_ref);
|
|
|
|
btrfs_set_root_ref_dirid(leaf, ref, dirid);
|
|
|
|
btrfs_set_root_ref_sequence(leaf, ref, sequence);
|
|
|
|
btrfs_set_root_ref_name_len(leaf, ref, name_len);
|
|
|
|
ptr = (unsigned long)(ref + 1);
|
|
|
|
write_extent_buffer(leaf, name, ptr, name_len);
|
|
|
|
btrfs_mark_buffer_dirty(leaf);
|
|
|
|
|
2009-09-21 13:56:00 -06:00
|
|
|
if (key.type == BTRFS_ROOT_BACKREF_KEY) {
|
2011-04-20 17:20:15 -06:00
|
|
|
btrfs_release_path(path);
|
2009-09-21 13:56:00 -06:00
|
|
|
key.objectid = ref_id;
|
|
|
|
key.type = BTRFS_ROOT_REF_KEY;
|
|
|
|
key.offset = root_id;
|
|
|
|
goto again;
|
|
|
|
}
|
|
|
|
|
2008-11-17 18:37:39 -07:00
|
|
|
btrfs_free_path(path);
|
2009-09-21 13:56:00 -06:00
|
|
|
return 0;
|
2008-11-17 18:37:39 -07:00
|
|
|
}
|
2011-03-27 20:01:25 -06:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Old btrfs forgets to init root_item->flags and root_item->byte_limit
|
|
|
|
* for subvolumes. To work around this problem, we steal a bit from
|
|
|
|
* root_item->inode_item->flags, and use it to indicate if those fields
|
|
|
|
* have been properly initialized.
|
|
|
|
*/
|
|
|
|
void btrfs_check_and_init_root_item(struct btrfs_root_item *root_item)
|
|
|
|
{
|
2013-07-15 21:19:18 -06:00
|
|
|
u64 inode_flags = btrfs_stack_inode_flags(&root_item->inode);
|
2011-03-27 20:01:25 -06:00
|
|
|
|
|
|
|
if (!(inode_flags & BTRFS_INODE_ROOT_ITEM_INIT)) {
|
|
|
|
inode_flags |= BTRFS_INODE_ROOT_ITEM_INIT;
|
2013-07-15 21:19:18 -06:00
|
|
|
btrfs_set_stack_inode_flags(&root_item->inode, inode_flags);
|
|
|
|
btrfs_set_root_flags(root_item, 0);
|
|
|
|
btrfs_set_root_limit(root_item, 0);
|
2011-03-27 20:01:25 -06:00
|
|
|
}
|
|
|
|
}
|
2012-07-25 09:35:53 -06:00
|
|
|
|
|
|
|
void btrfs_update_root_times(struct btrfs_trans_handle *trans,
|
|
|
|
struct btrfs_root *root)
|
|
|
|
{
|
|
|
|
struct btrfs_root_item *item = &root->root_item;
|
2016-02-07 00:57:21 -07:00
|
|
|
struct timespec ct = current_fs_time(root->fs_info->sb);
|
2012-07-25 09:35:53 -06:00
|
|
|
|
2012-12-07 02:28:54 -07:00
|
|
|
spin_lock(&root->root_item_lock);
|
2013-07-15 21:19:18 -06:00
|
|
|
btrfs_set_root_ctransid(item, trans->transid);
|
|
|
|
btrfs_set_stack_timespec_sec(&item->ctime, ct.tv_sec);
|
|
|
|
btrfs_set_stack_timespec_nsec(&item->ctime, ct.tv_nsec);
|
2012-12-07 02:28:54 -07:00
|
|
|
spin_unlock(&root->root_item_lock);
|
2012-07-25 09:35:53 -06:00
|
|
|
}
|