struct btrfs_free_space_info *
search_free_space_info(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info,
struct btrfs_block_group_cache *block_group,
struct btrfs_path *path, int cow)
{
struct btrfs_root *root = fs_info->free_space_root;
struct btrfs_key key;
int ret;
key.objectid = block_group->key.objectid;
key.type = BTRFS_FREE_SPACE_INFO_KEY;
key.offset = block_group->key.offset;
ret = btrfs_search_slot(trans, root, &key, path, 0, cow);
if (ret < 0)
return ERR_PTR(ret);
if (ret != 0) {
btrfs_warn(fs_info, "missing free space info for %llu\n",
block_group->key.objectid);
ASSERT(0);
return ERR_PTR(-ENOENT);
}
return btrfs_item_ptr(path->nodes[0], path->slots[0],
struct btrfs_free_space_info);
}
/* 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, u8 *uuid, u8 type,
u64 subid_cpu)
{
struct btrfs_fs_info *fs_info = trans->fs_info;
struct btrfs_root *uuid_root = fs_info->uuid_root;
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(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 {
btrfs_warn(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_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, BTRFS_OLDEST_GENERATION);
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);
return ret;
}
int btrfs_uuid_tree_remove(struct btrfs_trans_handle *trans, u8 *uuid, u8 type,
u64 subid)
{
struct btrfs_fs_info *fs_info = trans->fs_info;
struct btrfs_root *uuid_root = fs_info->uuid_root;
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(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(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(path, item_size - sizeof(subid), 1);
out:
btrfs_free_path(path);
return ret;
}
int btrfs_init_dev_replace(struct btrfs_fs_info *fs_info)
{
struct btrfs_key key;
struct btrfs_root *dev_root = fs_info->dev_root;
struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;
struct extent_buffer *eb;
int slot;
int ret = 0;
struct btrfs_path *path = NULL;
int item_size;
struct btrfs_dev_replace_item *ptr;
u64 src_devid;
path = btrfs_alloc_path();
if (!path) {
ret = -ENOMEM;
goto out;
}
key.objectid = 0;
key.type = BTRFS_DEV_REPLACE_KEY;
key.offset = 0;
ret = btrfs_search_slot(NULL, dev_root, &key, path, 0, 0);
if (ret) {
no_valid_dev_replace_entry_found:
ret = 0;
dev_replace->replace_state =
BTRFS_DEV_REPLACE_ITEM_STATE_NEVER_STARTED;
dev_replace->cont_reading_from_srcdev_mode =
BTRFS_DEV_REPLACE_ITEM_CONT_READING_FROM_SRCDEV_MODE_ALWAYS;
dev_replace->time_started = 0;
dev_replace->time_stopped = 0;
atomic64_set(&dev_replace->num_write_errors, 0);
atomic64_set(&dev_replace->num_uncorrectable_read_errors, 0);
dev_replace->cursor_left = 0;
dev_replace->committed_cursor_left = 0;
dev_replace->cursor_left_last_write_of_item = 0;
dev_replace->cursor_right = 0;
dev_replace->srcdev = NULL;
dev_replace->tgtdev = NULL;
dev_replace->is_valid = 0;
dev_replace->item_needs_writeback = 0;
goto out;
}
slot = path->slots[0];
eb = path->nodes[0];
item_size = btrfs_item_size_nr(eb, slot);
ptr = btrfs_item_ptr(eb, slot, struct btrfs_dev_replace_item);
if (item_size != sizeof(struct btrfs_dev_replace_item)) {
btrfs_warn(fs_info,
"dev_replace entry found has unexpected size, ignore entry");
goto no_valid_dev_replace_entry_found;
}
src_devid = btrfs_dev_replace_src_devid(eb, ptr);
dev_replace->cont_reading_from_srcdev_mode =
btrfs_dev_replace_cont_reading_from_srcdev_mode(eb, ptr);
dev_replace->replace_state = btrfs_dev_replace_replace_state(eb, ptr);
dev_replace->time_started = btrfs_dev_replace_time_started(eb, ptr);
dev_replace->time_stopped =
btrfs_dev_replace_time_stopped(eb, ptr);
atomic64_set(&dev_replace->num_write_errors,
btrfs_dev_replace_num_write_errors(eb, ptr));
atomic64_set(&dev_replace->num_uncorrectable_read_errors,
btrfs_dev_replace_num_uncorrectable_read_errors(eb, ptr));
dev_replace->cursor_left = btrfs_dev_replace_cursor_left(eb, ptr);
dev_replace->committed_cursor_left = dev_replace->cursor_left;
dev_replace->cursor_left_last_write_of_item = dev_replace->cursor_left;
dev_replace->cursor_right = btrfs_dev_replace_cursor_right(eb, ptr);
dev_replace->is_valid = 1;
dev_replace->item_needs_writeback = 0;
switch (dev_replace->replace_state) {
case BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED:
case BTRFS_IOCTL_DEV_REPLACE_STATE_FINISHED:
case BTRFS_IOCTL_DEV_REPLACE_STATE_CANCELED:
dev_replace->srcdev = NULL;
dev_replace->tgtdev = NULL;
break;
case BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED:
case BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED:
dev_replace->srcdev = btrfs_find_device(fs_info->fs_devices,
src_devid, NULL, NULL, true);
dev_replace->tgtdev = btrfs_find_device(fs_info->fs_devices,
BTRFS_DEV_REPLACE_DEVID,
NULL, NULL, true);
/*
* allow 'btrfs dev replace_cancel' if src/tgt device is
* missing
*/
if (!dev_replace->srcdev &&
!btrfs_test_opt(fs_info, DEGRADED)) {
ret = -EIO;
btrfs_warn(fs_info,
"cannot mount because device replace operation is ongoing and");
btrfs_warn(fs_info,
"srcdev (devid %llu) is missing, need to run 'btrfs dev scan'?",
src_devid);
}
if (!dev_replace->tgtdev &&
!btrfs_test_opt(fs_info, DEGRADED)) {
ret = -EIO;
btrfs_warn(fs_info,
"cannot mount because device replace operation is ongoing and");
btrfs_warn(fs_info,
"tgtdev (devid %llu) is missing, need to run 'btrfs dev scan'?",
BTRFS_DEV_REPLACE_DEVID);
}
if (dev_replace->tgtdev) {
if (dev_replace->srcdev) {
dev_replace->tgtdev->total_bytes =
dev_replace->srcdev->total_bytes;
dev_replace->tgtdev->disk_total_bytes =
dev_replace->srcdev->disk_total_bytes;
dev_replace->tgtdev->commit_total_bytes =
dev_replace->srcdev->commit_total_bytes;
dev_replace->tgtdev->bytes_used =
dev_replace->srcdev->bytes_used;
dev_replace->tgtdev->commit_bytes_used =
dev_replace->srcdev->commit_bytes_used;
}
set_bit(BTRFS_DEV_STATE_REPLACE_TGT,
&dev_replace->tgtdev->dev_state);
WARN_ON(fs_info->fs_devices->rw_devices == 0);
dev_replace->tgtdev->io_width = fs_info->sectorsize;
dev_replace->tgtdev->io_align = fs_info->sectorsize;
dev_replace->tgtdev->sector_size = fs_info->sectorsize;
dev_replace->tgtdev->fs_info = fs_info;
set_bit(BTRFS_DEV_STATE_IN_FS_METADATA,
&dev_replace->tgtdev->dev_state);
}
break;
}
out:
btrfs_free_path(path);
return ret;
}
/*
* called from commit_transaction. Writes changed device replace state to
* disk.
*/
int btrfs_run_dev_replace(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info)
{
int ret;
struct btrfs_root *dev_root = fs_info->dev_root;
struct btrfs_path *path;
struct btrfs_key key;
struct extent_buffer *eb;
struct btrfs_dev_replace_item *ptr;
struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;
down_read(&dev_replace->rwsem);
if (!dev_replace->is_valid ||
!dev_replace->item_needs_writeback) {
up_read(&dev_replace->rwsem);
return 0;
}
up_read(&dev_replace->rwsem);
key.objectid = 0;
key.type = BTRFS_DEV_REPLACE_KEY;
key.offset = 0;
path = btrfs_alloc_path();
if (!path) {
ret = -ENOMEM;
goto out;
}
ret = btrfs_search_slot(trans, dev_root, &key, path, -1, 1);
if (ret < 0) {
btrfs_warn(fs_info,
"error %d while searching for dev_replace item!",
ret);
goto out;
}
if (ret == 0 &&
btrfs_item_size_nr(path->nodes[0], path->slots[0]) < sizeof(*ptr)) {
/*
* need to delete old one and insert a new one.
* Since no attempt is made to recover any old state, if the
* dev_replace state is 'running', the data on the target
* drive is lost.
* It would be possible to recover the state: just make sure
* that the beginning of the item is never changed and always
* contains all the essential information. Then read this
* minimal set of information and use it as a base for the
* new state.
*/
ret = btrfs_del_item(trans, dev_root, path);
if (ret != 0) {
btrfs_warn(fs_info,
"delete too small dev_replace item failed %d!",
ret);
goto out;
}
ret = 1;
}
if (ret == 1) {
/* need to insert a new item */
btrfs_release_path(path);
ret = btrfs_insert_empty_item(trans, dev_root, path,
&key, sizeof(*ptr));
if (ret < 0) {
btrfs_warn(fs_info,
"insert dev_replace item failed %d!", ret);
goto out;
}
}
eb = path->nodes[0];
ptr = btrfs_item_ptr(eb, path->slots[0],
struct btrfs_dev_replace_item);
down_write(&dev_replace->rwsem);
if (dev_replace->srcdev)
btrfs_set_dev_replace_src_devid(eb, ptr,
dev_replace->srcdev->devid);
else
btrfs_set_dev_replace_src_devid(eb, ptr, (u64)-1);
btrfs_set_dev_replace_cont_reading_from_srcdev_mode(eb, ptr,
dev_replace->cont_reading_from_srcdev_mode);
btrfs_set_dev_replace_replace_state(eb, ptr,
dev_replace->replace_state);
btrfs_set_dev_replace_time_started(eb, ptr, dev_replace->time_started);
btrfs_set_dev_replace_time_stopped(eb, ptr, dev_replace->time_stopped);
btrfs_set_dev_replace_num_write_errors(eb, ptr,
atomic64_read(&dev_replace->num_write_errors));
btrfs_set_dev_replace_num_uncorrectable_read_errors(eb, ptr,
atomic64_read(&dev_replace->num_uncorrectable_read_errors));
dev_replace->cursor_left_last_write_of_item =
dev_replace->cursor_left;
btrfs_set_dev_replace_cursor_left(eb, ptr,
dev_replace->cursor_left_last_write_of_item);
btrfs_set_dev_replace_cursor_right(eb, ptr,
dev_replace->cursor_right);
dev_replace->item_needs_writeback = 0;
up_write(&dev_replace->rwsem);
btrfs_mark_buffer_dirty(eb);
out:
btrfs_free_path(path);
return ret;
}
int btrfs_dev_replace_start(struct btrfs_root *root,
struct btrfs_ioctl_dev_replace_args *args)
{
struct btrfs_trans_handle *trans;
struct btrfs_fs_info *fs_info = root->fs_info;
struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;
int ret;
struct btrfs_device *tgt_device = NULL;
struct btrfs_device *src_device = NULL;
if (btrfs_fs_incompat(fs_info, RAID56)) {
btrfs_warn(fs_info, "dev_replace cannot yet handle RAID5/RAID6");
return -EINVAL;
}
switch (args->start.cont_reading_from_srcdev_mode) {
case BTRFS_IOCTL_DEV_REPLACE_CONT_READING_FROM_SRCDEV_MODE_ALWAYS:
case BTRFS_IOCTL_DEV_REPLACE_CONT_READING_FROM_SRCDEV_MODE_AVOID:
break;
default:
return -EINVAL;
}
if ((args->start.srcdevid == 0 && args->start.srcdev_name[0] == '\0') ||
args->start.tgtdev_name[0] == '\0')
return -EINVAL;
mutex_lock(&fs_info->volume_mutex);
ret = btrfs_init_dev_replace_tgtdev(root, args->start.tgtdev_name,
&tgt_device);
if (ret) {
btrfs_err(fs_info, "target device %s is invalid!",
args->start.tgtdev_name);
mutex_unlock(&fs_info->volume_mutex);
return -EINVAL;
}
ret = btrfs_dev_replace_find_srcdev(root, args->start.srcdevid,
args->start.srcdev_name,
&src_device);
mutex_unlock(&fs_info->volume_mutex);
if (ret) {
ret = -EINVAL;
goto leave_no_lock;
}
if (tgt_device->total_bytes < src_device->total_bytes) {
btrfs_err(fs_info, "target device is smaller than source device!");
ret = -EINVAL;
goto leave_no_lock;
}
btrfs_dev_replace_lock(dev_replace);
switch (dev_replace->replace_state) {
case BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED:
case BTRFS_IOCTL_DEV_REPLACE_STATE_FINISHED:
case BTRFS_IOCTL_DEV_REPLACE_STATE_CANCELED:
break;
case BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED:
case BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED:
args->result = BTRFS_IOCTL_DEV_REPLACE_RESULT_ALREADY_STARTED;
goto leave;
}
dev_replace->cont_reading_from_srcdev_mode =
args->start.cont_reading_from_srcdev_mode;
WARN_ON(!src_device);
dev_replace->srcdev = src_device;
WARN_ON(!tgt_device);
dev_replace->tgtdev = tgt_device;
printk_in_rcu(KERN_INFO
"BTRFS: dev_replace from %s (devid %llu) to %s started\n",
src_device->missing ? "<missing disk>" :
rcu_str_deref(src_device->name),
src_device->devid,
rcu_str_deref(tgt_device->name));
tgt_device->total_bytes = src_device->total_bytes;
tgt_device->disk_total_bytes = src_device->disk_total_bytes;
tgt_device->bytes_used = src_device->bytes_used;
/*
* from now on, the writes to the srcdev are all duplicated to
* go to the tgtdev as well (refer to btrfs_map_block()).
*/
dev_replace->replace_state = BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED;
dev_replace->time_started = get_seconds();
dev_replace->cursor_left = 0;
dev_replace->committed_cursor_left = 0;
dev_replace->cursor_left_last_write_of_item = 0;
dev_replace->cursor_right = 0;
dev_replace->is_valid = 1;
dev_replace->item_needs_writeback = 1;
args->result = BTRFS_IOCTL_DEV_REPLACE_RESULT_NO_ERROR;
btrfs_dev_replace_unlock(dev_replace);
btrfs_wait_ordered_roots(root->fs_info, -1);
/* force writing the updated state information to disk */
trans = btrfs_start_transaction(root, 0);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
btrfs_dev_replace_lock(dev_replace);
goto leave;
}
ret = btrfs_commit_transaction(trans, root);
WARN_ON(ret);
/* the disk copy procedure reuses the scrub code */
ret = btrfs_scrub_dev(fs_info, src_device->devid, 0,
src_device->total_bytes,
&dev_replace->scrub_progress, 0, 1);
ret = btrfs_dev_replace_finishing(root->fs_info, ret);
WARN_ON(ret);
return 0;
leave:
dev_replace->srcdev = NULL;
dev_replace->tgtdev = NULL;
btrfs_dev_replace_unlock(dev_replace);
leave_no_lock:
if (tgt_device)
btrfs_destroy_dev_replace_tgtdev(fs_info, tgt_device);
return ret;
}