linux/fs/btrfs/uuid-tree.c
Filipe Manana f98de9b9c0 Btrfs: make btrfs_search_forward return with nodes unlocked
None of the uses of btrfs_search_forward() need to have the path
nodes (level >= 1) read locked, only the leaf needs to be locked
while the caller processes it. Therefore make it return a path
with all nodes unlocked, except for the leaf.

This change is motivated by the observation that during a file
fsync we repeatdly call btrfs_search_forward() and process the
returned leaf while upper nodes of the returned path (level >= 1)
are read locked, which unnecessarily blocks other tasks that want
to write to the same fs/subvol btree.
Therefore instead of modifying the fsync code to unlock all nodes
with level >= 1 immediately after calling btrfs_search_forward(),
change btrfs_search_forward() to do it, so that it benefits all
callers.

Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Chris Mason <clm@fb.com>
2014-09-17 13:38:02 -07:00

355 lines
8.0 KiB
C

/*
* Copyright (C) STRATO AG 2013. 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.
*/
#include <linux/uuid.h>
#include <asm/unaligned.h>
#include "ctree.h"
#include "transaction.h"
#include "disk-io.h"
#include "print-tree.h"
static void btrfs_uuid_to_key(u8 *uuid, u8 type, struct btrfs_key *key)
{
key->type = type;
key->objectid = get_unaligned_le64(uuid);
key->offset = get_unaligned_le64(uuid + sizeof(u64));
}
/* return -ENOENT for !found, < 0 for errors, or 0 if an item was found */
static int btrfs_uuid_tree_lookup(struct btrfs_root *uuid_root, u8 *uuid,
u8 type, u64 subid)
{
int ret;
struct btrfs_path *path = NULL;
struct extent_buffer *eb;
int slot;
u32 item_size;
unsigned long offset;
struct btrfs_key key;
if (WARN_ON_ONCE(!uuid_root)) {
ret = -ENOENT;
goto out;
}
path = btrfs_alloc_path();
if (!path) {
ret = -ENOMEM;
goto out;
}
btrfs_uuid_to_key(uuid, type, &key);
ret = btrfs_search_slot(NULL, uuid_root, &key, path, 0, 0);
if (ret < 0) {
goto out;
} else if (ret > 0) {
ret = -ENOENT;
goto out;
}
eb = path->nodes[0];
slot = path->slots[0];
item_size = btrfs_item_size_nr(eb, slot);
offset = btrfs_item_ptr_offset(eb, slot);
ret = -ENOENT;
if (!IS_ALIGNED(item_size, sizeof(u64))) {
btrfs_warn(uuid_root->fs_info, "uuid item with illegal size %lu!",
(unsigned long)item_size);
goto out;
}
while (item_size) {
__le64 data;
read_extent_buffer(eb, &data, offset, sizeof(data));
if (le64_to_cpu(data) == subid) {
ret = 0;
break;
}
offset += sizeof(data);
item_size -= sizeof(data);
}
out:
btrfs_free_path(path);
return ret;
}
int btrfs_uuid_tree_add(struct btrfs_trans_handle *trans,
struct btrfs_root *uuid_root, u8 *uuid, u8 type,
u64 subid_cpu)
{
int ret;
struct btrfs_path *path = NULL;
struct btrfs_key key;
struct extent_buffer *eb;
int slot;
unsigned long offset;
__le64 subid_le;
ret = btrfs_uuid_tree_lookup(uuid_root, uuid, type, subid_cpu);
if (ret != -ENOENT)
return ret;
if (WARN_ON_ONCE(!uuid_root)) {
ret = -EINVAL;
goto out;
}
btrfs_uuid_to_key(uuid, type, &key);
path = btrfs_alloc_path();
if (!path) {
ret = -ENOMEM;
goto out;
}
ret = btrfs_insert_empty_item(trans, uuid_root, path, &key,
sizeof(subid_le));
if (ret >= 0) {
/* Add an item for the type for the first time */
eb = path->nodes[0];
slot = path->slots[0];
offset = btrfs_item_ptr_offset(eb, slot);
} else if (ret == -EEXIST) {
/*
* An item with that type already exists.
* Extend the item and store the new subid at the end.
*/
btrfs_extend_item(uuid_root, path, sizeof(subid_le));
eb = path->nodes[0];
slot = path->slots[0];
offset = btrfs_item_ptr_offset(eb, slot);
offset += btrfs_item_size_nr(eb, slot) - sizeof(subid_le);
} else if (ret < 0) {
btrfs_warn(uuid_root->fs_info, "insert uuid item failed %d "
"(0x%016llx, 0x%016llx) type %u!",
ret, (unsigned long long)key.objectid,
(unsigned long long)key.offset, type);
goto out;
}
ret = 0;
subid_le = cpu_to_le64(subid_cpu);
write_extent_buffer(eb, &subid_le, offset, sizeof(subid_le));
btrfs_mark_buffer_dirty(eb);
out:
btrfs_free_path(path);
return ret;
}
int btrfs_uuid_tree_rem(struct btrfs_trans_handle *trans,
struct btrfs_root *uuid_root, u8 *uuid, u8 type,
u64 subid)
{
int ret;
struct btrfs_path *path = NULL;
struct btrfs_key key;
struct extent_buffer *eb;
int slot;
unsigned long offset;
u32 item_size;
unsigned long move_dst;
unsigned long move_src;
unsigned long move_len;
if (WARN_ON_ONCE(!uuid_root)) {
ret = -EINVAL;
goto out;
}
btrfs_uuid_to_key(uuid, type, &key);
path = btrfs_alloc_path();
if (!path) {
ret = -ENOMEM;
goto out;
}
ret = btrfs_search_slot(trans, uuid_root, &key, path, -1, 1);
if (ret < 0) {
btrfs_warn(uuid_root->fs_info, "error %d while searching for uuid item!",
ret);
goto out;
}
if (ret > 0) {
ret = -ENOENT;
goto out;
}
eb = path->nodes[0];
slot = path->slots[0];
offset = btrfs_item_ptr_offset(eb, slot);
item_size = btrfs_item_size_nr(eb, slot);
if (!IS_ALIGNED(item_size, sizeof(u64))) {
btrfs_warn(uuid_root->fs_info, "uuid item with illegal size %lu!",
(unsigned long)item_size);
ret = -ENOENT;
goto out;
}
while (item_size) {
__le64 read_subid;
read_extent_buffer(eb, &read_subid, offset, sizeof(read_subid));
if (le64_to_cpu(read_subid) == subid)
break;
offset += sizeof(read_subid);
item_size -= sizeof(read_subid);
}
if (!item_size) {
ret = -ENOENT;
goto out;
}
item_size = btrfs_item_size_nr(eb, slot);
if (item_size == sizeof(subid)) {
ret = btrfs_del_item(trans, uuid_root, path);
goto out;
}
move_dst = offset;
move_src = offset + sizeof(subid);
move_len = item_size - (move_src - btrfs_item_ptr_offset(eb, slot));
memmove_extent_buffer(eb, move_dst, move_src, move_len);
btrfs_truncate_item(uuid_root, path, item_size - sizeof(subid), 1);
out:
btrfs_free_path(path);
return ret;
}
static int btrfs_uuid_iter_rem(struct btrfs_root *uuid_root, u8 *uuid, u8 type,
u64 subid)
{
struct btrfs_trans_handle *trans;
int ret;
/* 1 - for the uuid item */
trans = btrfs_start_transaction(uuid_root, 1);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
goto out;
}
ret = btrfs_uuid_tree_rem(trans, uuid_root, uuid, type, subid);
btrfs_end_transaction(trans, uuid_root);
out:
return ret;
}
int btrfs_uuid_tree_iterate(struct btrfs_fs_info *fs_info,
int (*check_func)(struct btrfs_fs_info *, u8 *, u8,
u64))
{
struct btrfs_root *root = fs_info->uuid_root;
struct btrfs_key key;
struct btrfs_path *path;
int ret = 0;
struct extent_buffer *leaf;
int slot;
u32 item_size;
unsigned long offset;
path = btrfs_alloc_path();
if (!path) {
ret = -ENOMEM;
goto out;
}
key.objectid = 0;
key.type = 0;
key.offset = 0;
again_search_slot:
ret = btrfs_search_forward(root, &key, path, 0);
if (ret) {
if (ret > 0)
ret = 0;
goto out;
}
while (1) {
cond_resched();
leaf = path->nodes[0];
slot = path->slots[0];
btrfs_item_key_to_cpu(leaf, &key, slot);
if (key.type != BTRFS_UUID_KEY_SUBVOL &&
key.type != BTRFS_UUID_KEY_RECEIVED_SUBVOL)
goto skip;
offset = btrfs_item_ptr_offset(leaf, slot);
item_size = btrfs_item_size_nr(leaf, slot);
if (!IS_ALIGNED(item_size, sizeof(u64))) {
btrfs_warn(fs_info, "uuid item with illegal size %lu!",
(unsigned long)item_size);
goto skip;
}
while (item_size) {
u8 uuid[BTRFS_UUID_SIZE];
__le64 subid_le;
u64 subid_cpu;
put_unaligned_le64(key.objectid, uuid);
put_unaligned_le64(key.offset, uuid + sizeof(u64));
read_extent_buffer(leaf, &subid_le, offset,
sizeof(subid_le));
subid_cpu = le64_to_cpu(subid_le);
ret = check_func(fs_info, uuid, key.type, subid_cpu);
if (ret < 0)
goto out;
if (ret > 0) {
btrfs_release_path(path);
ret = btrfs_uuid_iter_rem(root, uuid, key.type,
subid_cpu);
if (ret == 0) {
/*
* this might look inefficient, but the
* justification is that it is an
* exception that check_func returns 1,
* and that in the regular case only one
* entry per UUID exists.
*/
goto again_search_slot;
}
if (ret < 0 && ret != -ENOENT)
goto out;
}
item_size -= sizeof(subid_le);
offset += sizeof(subid_le);
}
skip:
ret = btrfs_next_item(root, path);
if (ret == 0)
continue;
else if (ret > 0)
ret = 0;
break;
}
out:
btrfs_free_path(path);
if (ret)
btrfs_warn(fs_info, "btrfs_uuid_tree_iterate failed %d", ret);
return 0;
}