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.
|
|
|
|
*/
|
|
|
|
|
2007-03-15 17:03:33 -06:00
|
|
|
#include "ctree.h"
|
|
|
|
#include "disk-io.h"
|
2012-08-08 12:32:27 -06:00
|
|
|
#include "hash.h"
|
2007-03-16 14:20:31 -06:00
|
|
|
#include "transaction.h"
|
2010-08-06 11:21:20 -06:00
|
|
|
#include "print-tree.h"
|
2007-03-15 17:03:33 -06:00
|
|
|
|
2008-12-02 07:54:17 -07:00
|
|
|
static int find_name_in_backref(struct btrfs_path *path, const char *name,
|
2007-12-12 12:38:19 -07:00
|
|
|
int name_len, struct btrfs_inode_ref **ref_ret)
|
|
|
|
{
|
|
|
|
struct extent_buffer *leaf;
|
|
|
|
struct btrfs_inode_ref *ref;
|
|
|
|
unsigned long ptr;
|
|
|
|
unsigned long name_ptr;
|
|
|
|
u32 item_size;
|
|
|
|
u32 cur_offset = 0;
|
|
|
|
int len;
|
|
|
|
|
|
|
|
leaf = path->nodes[0];
|
|
|
|
item_size = btrfs_item_size_nr(leaf, path->slots[0]);
|
|
|
|
ptr = btrfs_item_ptr_offset(leaf, path->slots[0]);
|
|
|
|
while (cur_offset < item_size) {
|
|
|
|
ref = (struct btrfs_inode_ref *)(ptr + cur_offset);
|
|
|
|
len = btrfs_inode_ref_name_len(leaf, ref);
|
|
|
|
name_ptr = (unsigned long)(ref + 1);
|
|
|
|
cur_offset += len + sizeof(*ref);
|
|
|
|
if (len != name_len)
|
|
|
|
continue;
|
|
|
|
if (memcmp_extent_buffer(leaf, name, name_ptr, name_len) == 0) {
|
|
|
|
*ref_ret = ref;
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2012-08-08 12:32:27 -06:00
|
|
|
int btrfs_find_name_in_ext_backref(struct btrfs_path *path, u64 ref_objectid,
|
|
|
|
const char *name, int name_len,
|
|
|
|
struct btrfs_inode_extref **extref_ret)
|
|
|
|
{
|
|
|
|
struct extent_buffer *leaf;
|
|
|
|
struct btrfs_inode_extref *extref;
|
|
|
|
unsigned long ptr;
|
|
|
|
unsigned long name_ptr;
|
|
|
|
u32 item_size;
|
|
|
|
u32 cur_offset = 0;
|
|
|
|
int ref_name_len;
|
|
|
|
|
|
|
|
leaf = path->nodes[0];
|
|
|
|
item_size = btrfs_item_size_nr(leaf, path->slots[0]);
|
|
|
|
ptr = btrfs_item_ptr_offset(leaf, path->slots[0]);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Search all extended backrefs in this item. We're only
|
|
|
|
* looking through any collisions so most of the time this is
|
|
|
|
* just going to compare against one buffer. If all is well,
|
|
|
|
* we'll return success and the inode ref object.
|
|
|
|
*/
|
|
|
|
while (cur_offset < item_size) {
|
|
|
|
extref = (struct btrfs_inode_extref *) (ptr + cur_offset);
|
|
|
|
name_ptr = (unsigned long)(&extref->name);
|
|
|
|
ref_name_len = btrfs_inode_extref_name_len(leaf, extref);
|
|
|
|
|
|
|
|
if (ref_name_len == name_len &&
|
|
|
|
btrfs_inode_extref_parent(leaf, extref) == ref_objectid &&
|
|
|
|
(memcmp_extent_buffer(leaf, name, name_ptr, name_len) == 0)) {
|
|
|
|
if (extref_ret)
|
|
|
|
*extref_ret = extref;
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
cur_offset += ref_name_len + sizeof(*extref);
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Returns NULL if no extref found */
|
|
|
|
struct btrfs_inode_extref *
|
|
|
|
btrfs_lookup_inode_extref(struct btrfs_trans_handle *trans,
|
|
|
|
struct btrfs_root *root,
|
|
|
|
struct btrfs_path *path,
|
|
|
|
const char *name, int name_len,
|
|
|
|
u64 inode_objectid, u64 ref_objectid, int ins_len,
|
|
|
|
int cow)
|
|
|
|
{
|
|
|
|
int ret;
|
|
|
|
struct btrfs_key key;
|
|
|
|
struct btrfs_inode_extref *extref;
|
|
|
|
|
|
|
|
key.objectid = inode_objectid;
|
|
|
|
key.type = BTRFS_INODE_EXTREF_KEY;
|
|
|
|
key.offset = btrfs_extref_hash(ref_objectid, name, name_len);
|
|
|
|
|
|
|
|
ret = btrfs_search_slot(trans, root, &key, path, ins_len, cow);
|
|
|
|
if (ret < 0)
|
|
|
|
return ERR_PTR(ret);
|
|
|
|
if (ret > 0)
|
|
|
|
return NULL;
|
|
|
|
if (!btrfs_find_name_in_ext_backref(path, ref_objectid, name, name_len, &extref))
|
|
|
|
return NULL;
|
|
|
|
return extref;
|
|
|
|
}
|
|
|
|
|
2013-04-25 14:41:01 -06:00
|
|
|
static int btrfs_del_inode_extref(struct btrfs_trans_handle *trans,
|
|
|
|
struct btrfs_root *root,
|
|
|
|
const char *name, int name_len,
|
|
|
|
u64 inode_objectid, u64 ref_objectid,
|
|
|
|
u64 *index)
|
2012-08-08 12:32:27 -06:00
|
|
|
{
|
|
|
|
struct btrfs_path *path;
|
|
|
|
struct btrfs_key key;
|
|
|
|
struct btrfs_inode_extref *extref;
|
|
|
|
struct extent_buffer *leaf;
|
|
|
|
int ret;
|
|
|
|
int del_len = name_len + sizeof(*extref);
|
|
|
|
unsigned long ptr;
|
|
|
|
unsigned long item_start;
|
|
|
|
u32 item_size;
|
|
|
|
|
|
|
|
key.objectid = inode_objectid;
|
2014-06-04 10:41:45 -06:00
|
|
|
key.type = BTRFS_INODE_EXTREF_KEY;
|
2012-08-08 12:32:27 -06:00
|
|
|
key.offset = btrfs_extref_hash(ref_objectid, name, name_len);
|
|
|
|
|
|
|
|
path = btrfs_alloc_path();
|
|
|
|
if (!path)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
|
|
|
path->leave_spinning = 1;
|
|
|
|
|
|
|
|
ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
|
|
|
|
if (ret > 0)
|
|
|
|
ret = -ENOENT;
|
|
|
|
if (ret < 0)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Sanity check - did we find the right item for this name?
|
|
|
|
* This should always succeed so error here will make the FS
|
|
|
|
* readonly.
|
|
|
|
*/
|
|
|
|
if (!btrfs_find_name_in_ext_backref(path, ref_objectid,
|
|
|
|
name, name_len, &extref)) {
|
2016-03-16 02:43:06 -06:00
|
|
|
btrfs_handle_fs_error(root->fs_info, -ENOENT, NULL);
|
2012-08-08 12:32:27 -06:00
|
|
|
ret = -EROFS;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
leaf = path->nodes[0];
|
|
|
|
item_size = btrfs_item_size_nr(leaf, path->slots[0]);
|
|
|
|
if (index)
|
|
|
|
*index = btrfs_inode_extref_index(leaf, extref);
|
|
|
|
|
|
|
|
if (del_len == item_size) {
|
|
|
|
/*
|
|
|
|
* Common case only one ref in the item, remove the
|
|
|
|
* whole item.
|
|
|
|
*/
|
|
|
|
ret = btrfs_del_item(trans, root, path);
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
ptr = (unsigned long)extref;
|
|
|
|
item_start = btrfs_item_ptr_offset(leaf, path->slots[0]);
|
|
|
|
|
|
|
|
memmove_extent_buffer(leaf, ptr, ptr + del_len,
|
|
|
|
item_size - (ptr + del_len - item_start));
|
|
|
|
|
2013-04-15 23:18:22 -06:00
|
|
|
btrfs_truncate_item(root, path, item_size - del_len, 1);
|
2012-08-08 12:32:27 -06:00
|
|
|
|
|
|
|
out:
|
|
|
|
btrfs_free_path(path);
|
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
int btrfs_del_inode_ref(struct btrfs_trans_handle *trans,
|
|
|
|
struct btrfs_root *root,
|
|
|
|
const char *name, int name_len,
|
|
|
|
u64 inode_objectid, u64 ref_objectid, u64 *index)
|
2007-12-12 12:38:19 -07:00
|
|
|
{
|
|
|
|
struct btrfs_path *path;
|
|
|
|
struct btrfs_key key;
|
|
|
|
struct btrfs_inode_ref *ref;
|
|
|
|
struct extent_buffer *leaf;
|
|
|
|
unsigned long ptr;
|
|
|
|
unsigned long item_start;
|
|
|
|
u32 item_size;
|
|
|
|
u32 sub_item_len;
|
|
|
|
int ret;
|
2012-08-08 12:32:27 -06:00
|
|
|
int search_ext_refs = 0;
|
2007-12-12 12:38:19 -07:00
|
|
|
int del_len = name_len + sizeof(*ref);
|
|
|
|
|
|
|
|
key.objectid = inode_objectid;
|
|
|
|
key.offset = ref_objectid;
|
2014-06-04 10:41:45 -06:00
|
|
|
key.type = BTRFS_INODE_REF_KEY;
|
2007-12-12 12:38:19 -07:00
|
|
|
|
|
|
|
path = btrfs_alloc_path();
|
|
|
|
if (!path)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
2009-03-13 09:00:37 -06:00
|
|
|
path->leave_spinning = 1;
|
|
|
|
|
2007-12-12 12:38:19 -07:00
|
|
|
ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
|
|
|
|
if (ret > 0) {
|
|
|
|
ret = -ENOENT;
|
2012-08-08 12:32:27 -06:00
|
|
|
search_ext_refs = 1;
|
2007-12-12 12:38:19 -07:00
|
|
|
goto out;
|
|
|
|
} else if (ret < 0) {
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
if (!find_name_in_backref(path, name, name_len, &ref)) {
|
|
|
|
ret = -ENOENT;
|
2012-08-08 12:32:27 -06:00
|
|
|
search_ext_refs = 1;
|
2007-12-12 12:38:19 -07:00
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
leaf = path->nodes[0];
|
|
|
|
item_size = btrfs_item_size_nr(leaf, path->slots[0]);
|
2008-07-24 10:12:38 -06:00
|
|
|
|
|
|
|
if (index)
|
|
|
|
*index = btrfs_inode_ref_index(leaf, ref);
|
|
|
|
|
2007-12-12 12:38:19 -07:00
|
|
|
if (del_len == item_size) {
|
|
|
|
ret = btrfs_del_item(trans, root, path);
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
ptr = (unsigned long)ref;
|
|
|
|
sub_item_len = name_len + sizeof(*ref);
|
|
|
|
item_start = btrfs_item_ptr_offset(leaf, path->slots[0]);
|
|
|
|
memmove_extent_buffer(leaf, ptr, ptr + sub_item_len,
|
|
|
|
item_size - (ptr + sub_item_len - item_start));
|
2013-04-15 23:18:22 -06:00
|
|
|
btrfs_truncate_item(root, path, item_size - sub_item_len, 1);
|
2012-08-08 12:32:27 -06:00
|
|
|
out:
|
|
|
|
btrfs_free_path(path);
|
|
|
|
|
|
|
|
if (search_ext_refs) {
|
|
|
|
/*
|
|
|
|
* No refs were found, or we could not find the
|
|
|
|
* name in our ref array. Find and remove the extended
|
|
|
|
* inode ref then.
|
|
|
|
*/
|
|
|
|
return btrfs_del_inode_extref(trans, root, name, name_len,
|
|
|
|
inode_objectid, ref_objectid, index);
|
|
|
|
}
|
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* btrfs_insert_inode_extref() - Inserts an extended inode ref into a tree.
|
|
|
|
*
|
|
|
|
* The caller must have checked against BTRFS_LINK_MAX already.
|
|
|
|
*/
|
|
|
|
static int btrfs_insert_inode_extref(struct btrfs_trans_handle *trans,
|
|
|
|
struct btrfs_root *root,
|
|
|
|
const char *name, int name_len,
|
|
|
|
u64 inode_objectid, u64 ref_objectid, u64 index)
|
|
|
|
{
|
|
|
|
struct btrfs_inode_extref *extref;
|
|
|
|
int ret;
|
|
|
|
int ins_len = name_len + sizeof(*extref);
|
|
|
|
unsigned long ptr;
|
|
|
|
struct btrfs_path *path;
|
|
|
|
struct btrfs_key key;
|
|
|
|
struct extent_buffer *leaf;
|
|
|
|
struct btrfs_item *item;
|
|
|
|
|
|
|
|
key.objectid = inode_objectid;
|
|
|
|
key.type = BTRFS_INODE_EXTREF_KEY;
|
|
|
|
key.offset = btrfs_extref_hash(ref_objectid, name, name_len);
|
|
|
|
|
|
|
|
path = btrfs_alloc_path();
|
|
|
|
if (!path)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
|
|
|
path->leave_spinning = 1;
|
|
|
|
ret = btrfs_insert_empty_item(trans, root, path, &key,
|
|
|
|
ins_len);
|
|
|
|
if (ret == -EEXIST) {
|
|
|
|
if (btrfs_find_name_in_ext_backref(path, ref_objectid,
|
|
|
|
name, name_len, NULL))
|
|
|
|
goto out;
|
|
|
|
|
2013-04-15 23:18:49 -06:00
|
|
|
btrfs_extend_item(root, path, ins_len);
|
2012-08-08 12:32:27 -06:00
|
|
|
ret = 0;
|
|
|
|
}
|
|
|
|
if (ret < 0)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
leaf = path->nodes[0];
|
2013-09-16 08:58:09 -06:00
|
|
|
item = btrfs_item_nr(path->slots[0]);
|
2012-08-08 12:32:27 -06:00
|
|
|
ptr = (unsigned long)btrfs_item_ptr(leaf, path->slots[0], char);
|
|
|
|
ptr += btrfs_item_size(leaf, item) - ins_len;
|
|
|
|
extref = (struct btrfs_inode_extref *)ptr;
|
|
|
|
|
|
|
|
btrfs_set_inode_extref_name_len(path->nodes[0], extref, name_len);
|
|
|
|
btrfs_set_inode_extref_index(path->nodes[0], extref, index);
|
|
|
|
btrfs_set_inode_extref_parent(path->nodes[0], extref, ref_objectid);
|
|
|
|
|
|
|
|
ptr = (unsigned long)&extref->name;
|
|
|
|
write_extent_buffer(path->nodes[0], name, ptr, name_len);
|
|
|
|
btrfs_mark_buffer_dirty(path->nodes[0]);
|
|
|
|
|
2007-12-12 12:38:19 -07:00
|
|
|
out:
|
|
|
|
btrfs_free_path(path);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2012-03-12 09:03:00 -06:00
|
|
|
/* Will return 0, -ENOMEM, -EMLINK, or -EEXIST or anything from the CoW path */
|
2007-12-12 12:38:19 -07:00
|
|
|
int btrfs_insert_inode_ref(struct btrfs_trans_handle *trans,
|
|
|
|
struct btrfs_root *root,
|
|
|
|
const char *name, int name_len,
|
2008-07-24 10:12:38 -06:00
|
|
|
u64 inode_objectid, u64 ref_objectid, u64 index)
|
2007-12-12 12:38:19 -07:00
|
|
|
{
|
|
|
|
struct btrfs_path *path;
|
|
|
|
struct btrfs_key key;
|
|
|
|
struct btrfs_inode_ref *ref;
|
|
|
|
unsigned long ptr;
|
|
|
|
int ret;
|
|
|
|
int ins_len = name_len + sizeof(*ref);
|
|
|
|
|
|
|
|
key.objectid = inode_objectid;
|
|
|
|
key.offset = ref_objectid;
|
2014-06-04 10:41:45 -06:00
|
|
|
key.type = BTRFS_INODE_REF_KEY;
|
2007-12-12 12:38:19 -07:00
|
|
|
|
|
|
|
path = btrfs_alloc_path();
|
|
|
|
if (!path)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
2009-03-13 09:00:37 -06:00
|
|
|
path->leave_spinning = 1;
|
Btrfs: fix fsync log replay for inodes with a mix of regular refs and extrefs
If we have an inode with a large number of hard links, some of which may
be extrefs, turn a regular ref into an extref, fsync the inode and then
replay the fsync log (after a crash/reboot), we can endup with an fsync
log that makes the replay code always fail with -EOVERFLOW when processing
the inode's references.
This is easy to reproduce with the test case I made for xfstests. Its steps
are the following:
_scratch_mkfs "-O extref" >> $seqres.full 2>&1
_init_flakey
_mount_flakey
# Create a test file with 3001 hard links. This number is large enough to
# make btrfs start using extrefs at some point even if the fs has the maximum
# possible leaf/node size (64Kb).
echo "hello world" > $SCRATCH_MNT/foo
for i in `seq 1 3000`; do
ln $SCRATCH_MNT/foo $SCRATCH_MNT/foo_link_`printf "%04d" $i`
done
# Make sure all metadata and data are durably persisted.
sync
# Now remove one link, add a new one with a new name, add another new one with
# the same name as the one we just removed and fsync the inode.
rm -f $SCRATCH_MNT/foo_link_0001
ln $SCRATCH_MNT/foo $SCRATCH_MNT/foo_link_3001
ln $SCRATCH_MNT/foo $SCRATCH_MNT/foo_link_0001
rm -f $SCRATCH_MNT/foo_link_0002
ln $SCRATCH_MNT/foo $SCRATCH_MNT/foo_link_3002
ln $SCRATCH_MNT/foo $SCRATCH_MNT/foo_link_3003
$XFS_IO_PROG -c "fsync" $SCRATCH_MNT/foo
# Simulate a crash/power loss. This makes sure the next mount
# will see an fsync log and will replay that log.
_load_flakey_table $FLAKEY_DROP_WRITES
_unmount_flakey
_load_flakey_table $FLAKEY_ALLOW_WRITES
_mount_flakey
# Check that the number of hard links is correct, we are able to remove all
# the hard links and read the file's data. This is just to verify we don't
# get stale file handle errors (due to dangling directory index entries that
# point to inodes that no longer exist).
echo "Link count: $(stat --format=%h $SCRATCH_MNT/foo)"
[ -f $SCRATCH_MNT/foo ] || echo "Link foo is missing"
for ((i = 1; i <= 3003; i++)); do
name=foo_link_`printf "%04d" $i`
if [ $i -eq 2 ]; then
[ -f $SCRATCH_MNT/$name ] && echo "Link $name found"
else
[ -f $SCRATCH_MNT/$name ] || echo "Link $name is missing"
fi
done
rm -f $SCRATCH_MNT/foo_link_*
cat $SCRATCH_MNT/foo
rm -f $SCRATCH_MNT/foo
status=0
exit
The fix is simply to correct the overflow condition when overwriting a
reference item because it was wrong, trying to increase the item in the
fs/subvol tree by an impossible amount. Also ensure that we don't insert
one normal ref and one ext ref for the same dentry - this happened because
processing a dir index entry from the parent in the log happened when
the normal ref item was full, which made the logic insert an extref and
later when the normal ref had enough room, it would be inserted again
when processing the ref item from the child inode in the log.
This issue has been present since the introduction of the extrefs feature
(2012).
A test case for xfstests follows soon. This test only passes if the previous
patch titled "Btrfs: fix fsync when extend references are added to an inode"
is applied too.
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Chris Mason <clm@fb.com>
2015-01-13 18:52:25 -07:00
|
|
|
path->skip_release_on_error = 1;
|
2007-12-12 12:38:19 -07:00
|
|
|
ret = btrfs_insert_empty_item(trans, root, path, &key,
|
|
|
|
ins_len);
|
|
|
|
if (ret == -EEXIST) {
|
|
|
|
u32 old_size;
|
|
|
|
|
|
|
|
if (find_name_in_backref(path, name, name_len, &ref))
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
old_size = btrfs_item_size_nr(path->nodes[0], path->slots[0]);
|
2013-04-15 23:18:49 -06:00
|
|
|
btrfs_extend_item(root, path, ins_len);
|
2007-12-12 12:38:19 -07:00
|
|
|
ref = btrfs_item_ptr(path->nodes[0], path->slots[0],
|
|
|
|
struct btrfs_inode_ref);
|
|
|
|
ref = (struct btrfs_inode_ref *)((unsigned long)ref + old_size);
|
|
|
|
btrfs_set_inode_ref_name_len(path->nodes[0], ref, name_len);
|
2008-07-24 10:12:38 -06:00
|
|
|
btrfs_set_inode_ref_index(path->nodes[0], ref, index);
|
2007-12-12 12:38:19 -07:00
|
|
|
ptr = (unsigned long)(ref + 1);
|
|
|
|
ret = 0;
|
|
|
|
} else if (ret < 0) {
|
Btrfs: fix fsync log replay for inodes with a mix of regular refs and extrefs
If we have an inode with a large number of hard links, some of which may
be extrefs, turn a regular ref into an extref, fsync the inode and then
replay the fsync log (after a crash/reboot), we can endup with an fsync
log that makes the replay code always fail with -EOVERFLOW when processing
the inode's references.
This is easy to reproduce with the test case I made for xfstests. Its steps
are the following:
_scratch_mkfs "-O extref" >> $seqres.full 2>&1
_init_flakey
_mount_flakey
# Create a test file with 3001 hard links. This number is large enough to
# make btrfs start using extrefs at some point even if the fs has the maximum
# possible leaf/node size (64Kb).
echo "hello world" > $SCRATCH_MNT/foo
for i in `seq 1 3000`; do
ln $SCRATCH_MNT/foo $SCRATCH_MNT/foo_link_`printf "%04d" $i`
done
# Make sure all metadata and data are durably persisted.
sync
# Now remove one link, add a new one with a new name, add another new one with
# the same name as the one we just removed and fsync the inode.
rm -f $SCRATCH_MNT/foo_link_0001
ln $SCRATCH_MNT/foo $SCRATCH_MNT/foo_link_3001
ln $SCRATCH_MNT/foo $SCRATCH_MNT/foo_link_0001
rm -f $SCRATCH_MNT/foo_link_0002
ln $SCRATCH_MNT/foo $SCRATCH_MNT/foo_link_3002
ln $SCRATCH_MNT/foo $SCRATCH_MNT/foo_link_3003
$XFS_IO_PROG -c "fsync" $SCRATCH_MNT/foo
# Simulate a crash/power loss. This makes sure the next mount
# will see an fsync log and will replay that log.
_load_flakey_table $FLAKEY_DROP_WRITES
_unmount_flakey
_load_flakey_table $FLAKEY_ALLOW_WRITES
_mount_flakey
# Check that the number of hard links is correct, we are able to remove all
# the hard links and read the file's data. This is just to verify we don't
# get stale file handle errors (due to dangling directory index entries that
# point to inodes that no longer exist).
echo "Link count: $(stat --format=%h $SCRATCH_MNT/foo)"
[ -f $SCRATCH_MNT/foo ] || echo "Link foo is missing"
for ((i = 1; i <= 3003; i++)); do
name=foo_link_`printf "%04d" $i`
if [ $i -eq 2 ]; then
[ -f $SCRATCH_MNT/$name ] && echo "Link $name found"
else
[ -f $SCRATCH_MNT/$name ] || echo "Link $name is missing"
fi
done
rm -f $SCRATCH_MNT/foo_link_*
cat $SCRATCH_MNT/foo
rm -f $SCRATCH_MNT/foo
status=0
exit
The fix is simply to correct the overflow condition when overwriting a
reference item because it was wrong, trying to increase the item in the
fs/subvol tree by an impossible amount. Also ensure that we don't insert
one normal ref and one ext ref for the same dentry - this happened because
processing a dir index entry from the parent in the log happened when
the normal ref item was full, which made the logic insert an extref and
later when the normal ref had enough room, it would be inserted again
when processing the ref item from the child inode in the log.
This issue has been present since the introduction of the extrefs feature
(2012).
A test case for xfstests follows soon. This test only passes if the previous
patch titled "Btrfs: fix fsync when extend references are added to an inode"
is applied too.
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Chris Mason <clm@fb.com>
2015-01-13 18:52:25 -07:00
|
|
|
if (ret == -EOVERFLOW) {
|
|
|
|
if (find_name_in_backref(path, name, name_len, &ref))
|
|
|
|
ret = -EEXIST;
|
|
|
|
else
|
|
|
|
ret = -EMLINK;
|
|
|
|
}
|
2007-12-12 12:38:19 -07:00
|
|
|
goto out;
|
|
|
|
} else {
|
|
|
|
ref = btrfs_item_ptr(path->nodes[0], path->slots[0],
|
|
|
|
struct btrfs_inode_ref);
|
|
|
|
btrfs_set_inode_ref_name_len(path->nodes[0], ref, name_len);
|
2008-07-24 10:12:38 -06:00
|
|
|
btrfs_set_inode_ref_index(path->nodes[0], ref, index);
|
2007-12-12 12:38:19 -07:00
|
|
|
ptr = (unsigned long)(ref + 1);
|
|
|
|
}
|
|
|
|
write_extent_buffer(path->nodes[0], name, ptr, name_len);
|
|
|
|
btrfs_mark_buffer_dirty(path->nodes[0]);
|
|
|
|
|
|
|
|
out:
|
|
|
|
btrfs_free_path(path);
|
2012-08-08 12:32:27 -06:00
|
|
|
|
|
|
|
if (ret == -EMLINK) {
|
|
|
|
struct btrfs_super_block *disk_super = root->fs_info->super_copy;
|
|
|
|
/* We ran out of space in the ref array. Need to
|
|
|
|
* add an extended ref. */
|
|
|
|
if (btrfs_super_incompat_flags(disk_super)
|
|
|
|
& BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF)
|
|
|
|
ret = btrfs_insert_inode_extref(trans, root, name,
|
|
|
|
name_len,
|
|
|
|
inode_objectid,
|
|
|
|
ref_objectid, index);
|
|
|
|
}
|
|
|
|
|
2007-12-12 12:38:19 -07:00
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2007-10-15 14:14:19 -06:00
|
|
|
int btrfs_insert_empty_inode(struct btrfs_trans_handle *trans,
|
|
|
|
struct btrfs_root *root,
|
|
|
|
struct btrfs_path *path, u64 objectid)
|
2007-03-15 17:03:33 -06:00
|
|
|
{
|
|
|
|
struct btrfs_key key;
|
|
|
|
int ret;
|
|
|
|
key.objectid = objectid;
|
2014-06-04 10:41:45 -06:00
|
|
|
key.type = BTRFS_INODE_ITEM_KEY;
|
2007-03-15 17:03:33 -06:00
|
|
|
key.offset = 0;
|
|
|
|
|
2007-10-15 14:14:19 -06:00
|
|
|
ret = btrfs_insert_empty_item(trans, root, path, &key,
|
|
|
|
sizeof(struct btrfs_inode_item));
|
2007-03-15 17:03:33 -06:00
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2007-03-16 14:20:31 -06:00
|
|
|
int btrfs_lookup_inode(struct btrfs_trans_handle *trans, struct btrfs_root
|
2007-04-06 13:37:36 -06:00
|
|
|
*root, struct btrfs_path *path,
|
|
|
|
struct btrfs_key *location, int mod)
|
2007-03-15 17:03:33 -06:00
|
|
|
{
|
|
|
|
int ins_len = mod < 0 ? -1 : 0;
|
|
|
|
int cow = mod != 0;
|
2007-04-06 13:37:36 -06:00
|
|
|
int ret;
|
|
|
|
int slot;
|
2007-10-15 14:14:19 -06:00
|
|
|
struct extent_buffer *leaf;
|
2007-04-06 13:37:36 -06:00
|
|
|
struct btrfs_key found_key;
|
2007-03-15 17:03:33 -06:00
|
|
|
|
2007-04-06 13:37:36 -06:00
|
|
|
ret = btrfs_search_slot(trans, root, location, path, ins_len, cow);
|
2014-06-04 10:41:45 -06:00
|
|
|
if (ret > 0 && location->type == BTRFS_ROOT_ITEM_KEY &&
|
2007-04-06 13:37:36 -06:00
|
|
|
location->offset == (u64)-1 && path->slots[0] != 0) {
|
|
|
|
slot = path->slots[0] - 1;
|
2007-10-15 14:14:19 -06:00
|
|
|
leaf = path->nodes[0];
|
|
|
|
btrfs_item_key_to_cpu(leaf, &found_key, slot);
|
2007-04-06 13:37:36 -06:00
|
|
|
if (found_key.objectid == location->objectid &&
|
2014-06-04 10:41:45 -06:00
|
|
|
found_key.type == location->type) {
|
2007-04-06 13:37:36 -06:00
|
|
|
path->slots[0]--;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return ret;
|
2007-03-15 17:03:33 -06:00
|
|
|
}
|