static void btrfs_dev_stat_print_on_error(struct btrfs_device *dev);
static void btrfs_dev_stat_print_on_load(struct btrfs_device *device);
-static DEFINE_MUTEX(uuid_mutex);
+DEFINE_MUTEX(uuid_mutex);
static LIST_HEAD(fs_uuids);
static void lock_chunks(struct btrfs_root *root)
mutex_init(&fs_devs->device_list_mutex);
INIT_LIST_HEAD(&fs_devs->devices);
+ INIT_LIST_HEAD(&fs_devs->resized_devices);
INIT_LIST_HEAD(&fs_devs->alloc_list);
INIT_LIST_HEAD(&fs_devs->list);
INIT_LIST_HEAD(&dev->dev_list);
INIT_LIST_HEAD(&dev->dev_alloc_list);
+ INIT_LIST_HEAD(&dev->resized_list);
spin_lock_init(&dev->io_lock);
spin_lock_init(&dev->reada_lock);
atomic_set(&dev->reada_in_flight, 0);
+ atomic_set(&dev->dev_stats_ccnt, 0);
INIT_RADIX_TREE(&dev->reada_zones, GFP_NOFS & ~__GFP_WAIT);
INIT_RADIX_TREE(&dev->reada_extents, GFP_NOFS & ~__GFP_WAIT);
return PTR_ERR(fs_devices);
list_add(&fs_devices->list, &fs_uuids);
- fs_devices->latest_devid = devid;
- fs_devices->latest_trans = found_transid;
device = NULL;
} else {
device = __find_device(&fs_devices->devices, devid,
disk_super->dev_item.uuid);
}
+
if (!device) {
if (fs_devices->opened)
return -EBUSY;
if (!fs_devices->opened)
device->generation = found_transid;
- if (found_transid > fs_devices->latest_trans) {
- fs_devices->latest_devid = devid;
- fs_devices->latest_trans = found_transid;
- }
*fs_devices_ret = fs_devices;
return ret;
if (IS_ERR(fs_devices))
return fs_devices;
- fs_devices->latest_devid = orig->latest_devid;
- fs_devices->latest_trans = orig->latest_trans;
+ mutex_lock(&orig->device_list_mutex);
fs_devices->total_devices = orig->total_devices;
/* We have held the volume lock, it is safe to get the devices. */
device->fs_devices = fs_devices;
fs_devices->num_devices++;
}
+ mutex_unlock(&orig->device_list_mutex);
return fs_devices;
error:
+ mutex_unlock(&orig->device_list_mutex);
free_fs_devices(fs_devices);
return ERR_PTR(-ENOMEM);
}
struct btrfs_fs_devices *fs_devices, int step)
{
struct btrfs_device *device, *next;
-
- struct block_device *latest_bdev = NULL;
- u64 latest_devid = 0;
- u64 latest_transid = 0;
+ struct btrfs_device *latest_dev = NULL;
mutex_lock(&uuid_mutex);
again:
list_for_each_entry_safe(device, next, &fs_devices->devices, dev_list) {
if (device->in_fs_metadata) {
if (!device->is_tgtdev_for_dev_replace &&
- (!latest_transid ||
- device->generation > latest_transid)) {
- latest_devid = device->devid;
- latest_transid = device->generation;
- latest_bdev = device->bdev;
+ (!latest_dev ||
+ device->generation > latest_dev->generation)) {
+ latest_dev = device;
}
continue;
}
goto again;
}
- fs_devices->latest_bdev = latest_bdev;
- fs_devices->latest_devid = latest_devid;
- fs_devices->latest_trans = latest_transid;
+ fs_devices->latest_bdev = latest_dev->bdev;
mutex_unlock(&uuid_mutex);
}
fs_devices->rw_devices--;
}
- if (device->can_discard)
- fs_devices->num_can_discard--;
if (device->missing)
fs_devices->missing_devices--;
struct block_device *bdev;
struct list_head *head = &fs_devices->devices;
struct btrfs_device *device;
- struct block_device *latest_bdev = NULL;
+ struct btrfs_device *latest_dev = NULL;
struct buffer_head *bh;
struct btrfs_super_block *disk_super;
- u64 latest_devid = 0;
- u64 latest_transid = 0;
u64 devid;
int seeding = 1;
int ret = 0;
goto error_brelse;
device->generation = btrfs_super_generation(disk_super);
- if (!latest_transid || device->generation > latest_transid) {
- latest_devid = devid;
- latest_transid = device->generation;
- latest_bdev = bdev;
- }
+ if (!latest_dev ||
+ device->generation > latest_dev->generation)
+ latest_dev = device;
if (btrfs_super_flags(disk_super) & BTRFS_SUPER_FLAG_SEEDING) {
device->writeable = 0;
}
q = bdev_get_queue(bdev);
- if (blk_queue_discard(q)) {
+ if (blk_queue_discard(q))
device->can_discard = 1;
- fs_devices->num_can_discard++;
- }
device->bdev = bdev;
device->in_fs_metadata = 0;
}
fs_devices->seeding = seeding;
fs_devices->opened = 1;
- fs_devices->latest_bdev = latest_bdev;
- fs_devices->latest_devid = latest_devid;
- fs_devices->latest_trans = latest_transid;
+ fs_devices->latest_bdev = latest_dev->bdev;
fs_devices->total_rw_bytes = 0;
out:
return ret;
if (key.objectid > device->devid)
break;
- if (btrfs_key_type(&key) != BTRFS_DEV_EXTENT_KEY)
+ if (key.type != BTRFS_DEV_EXTENT_KEY)
goto next;
dev_extent = btrfs_item_ptr(l, slot, struct btrfs_dev_extent);
if (key.objectid > device->devid)
break;
- if (btrfs_key_type(&key) != BTRFS_DEV_EXTENT_KEY)
+ if (key.type != BTRFS_DEV_EXTENT_KEY)
goto next;
if (key.offset > search_start) {
static int btrfs_free_dev_extent(struct btrfs_trans_handle *trans,
struct btrfs_device *device,
- u64 start)
+ u64 start, u64 *dev_extent_len)
{
int ret;
struct btrfs_path *path;
goto out;
}
- if (device->bytes_used > 0) {
- u64 len = btrfs_dev_extent_length(leaf, extent);
- device->bytes_used -= len;
- spin_lock(&root->fs_info->free_chunk_lock);
- root->fs_info->free_chunk_space += len;
- spin_unlock(&root->fs_info->free_chunk_lock);
- }
+ *dev_extent_len = btrfs_dev_extent_length(leaf, extent);
+
ret = btrfs_del_item(trans, root, path);
if (ret) {
btrfs_error(root->fs_info, ret,
btrfs_set_device_io_align(leaf, dev_item, device->io_align);
btrfs_set_device_io_width(leaf, dev_item, device->io_width);
btrfs_set_device_sector_size(leaf, dev_item, device->sector_size);
- btrfs_set_device_total_bytes(leaf, dev_item, device->disk_total_bytes);
- btrfs_set_device_bytes_used(leaf, dev_item, device->bytes_used);
+ btrfs_set_device_total_bytes(leaf, dev_item,
+ btrfs_device_get_disk_total_bytes(device));
+ btrfs_set_device_bytes_used(leaf, dev_item,
+ btrfs_device_get_bytes_used(device));
btrfs_set_device_group(leaf, dev_item, 0);
btrfs_set_device_seek_speed(leaf, dev_item, 0);
btrfs_set_device_bandwidth(leaf, dev_item, 0);
key.objectid = BTRFS_DEV_ITEMS_OBJECTID;
key.type = BTRFS_DEV_ITEM_KEY;
key.offset = device->devid;
- lock_chunks(root);
ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
if (ret < 0)
goto out;
out:
btrfs_free_path(path);
- unlock_chunks(root);
btrfs_commit_transaction(trans, root);
return ret;
}
if (device->writeable) {
lock_chunks(root);
list_del_init(&device->dev_alloc_list);
+ device->fs_devices->rw_devices--;
unlock_chunks(root);
- root->fs_info->fs_devices->rw_devices--;
clear_super = true;
}
if (ret)
goto error_undo;
- spin_lock(&root->fs_info->free_chunk_lock);
- root->fs_info->free_chunk_space = device->total_bytes -
- device->bytes_used;
- spin_unlock(&root->fs_info->free_chunk_lock);
-
device->in_fs_metadata = 0;
btrfs_scrub_cancel_dev(root->fs_info, device);
fs_devices = fs_devices->seed;
}
cur_devices->seed = NULL;
- lock_chunks(root);
__btrfs_close_devices(cur_devices);
- unlock_chunks(root);
free_fs_devices(cur_devices);
}
lock_chunks(root);
list_add(&device->dev_alloc_list,
&root->fs_info->fs_devices->alloc_list);
+ device->fs_devices->rw_devices++;
unlock_chunks(root);
- root->fs_info->fs_devices->rw_devices++;
}
goto error_brelse;
}
void btrfs_rm_dev_replace_srcdev(struct btrfs_fs_info *fs_info,
struct btrfs_device *srcdev)
{
+ struct btrfs_fs_devices *fs_devices;
+
WARN_ON(!mutex_is_locked(&fs_info->fs_devices->device_list_mutex));
+ /*
+ * in case of fs with no seed, srcdev->fs_devices will point
+ * to fs_devices of fs_info. However when the dev being replaced is
+ * a seed dev it will point to the seed's local fs_devices. In short
+ * srcdev will have its correct fs_devices in both the cases.
+ */
+ fs_devices = srcdev->fs_devices;
+
list_del_rcu(&srcdev->dev_list);
list_del_rcu(&srcdev->dev_alloc_list);
- fs_info->fs_devices->num_devices--;
- if (srcdev->missing) {
- fs_info->fs_devices->missing_devices--;
- fs_info->fs_devices->rw_devices++;
- }
- if (srcdev->can_discard)
- fs_info->fs_devices->num_can_discard--;
- if (srcdev->bdev) {
- fs_info->fs_devices->open_devices--;
+ fs_devices->num_devices--;
+ if (srcdev->missing)
+ fs_devices->missing_devices--;
- /*
- * zero out the old super if it is not writable
- * (e.g. seed device)
- */
- if (srcdev->writeable)
- btrfs_scratch_superblock(srcdev);
+ if (srcdev->writeable) {
+ fs_devices->rw_devices--;
+ /* zero out the old super if it is writable */
+ btrfs_scratch_superblock(srcdev);
}
+ if (srcdev->bdev)
+ fs_devices->open_devices--;
+
call_rcu(&srcdev->rcu, free_device);
+
+ /*
+ * unless fs_devices is seed fs, num_devices shouldn't go
+ * zero
+ */
+ BUG_ON(!fs_devices->num_devices && !fs_devices->seeding);
+
+ /* if this is no devs we rather delete the fs_devices */
+ if (!fs_devices->num_devices) {
+ struct btrfs_fs_devices *tmp_fs_devices;
+
+ tmp_fs_devices = fs_info->fs_devices;
+ while (tmp_fs_devices) {
+ if (tmp_fs_devices->seed == fs_devices) {
+ tmp_fs_devices->seed = fs_devices->seed;
+ break;
+ }
+ tmp_fs_devices = tmp_fs_devices->seed;
+ }
+ fs_devices->seed = NULL;
+ __btrfs_close_devices(fs_devices);
+ free_fs_devices(fs_devices);
+ }
}
void btrfs_destroy_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
{
struct btrfs_device *next_device;
+ mutex_lock(&uuid_mutex);
WARN_ON(!tgtdev);
mutex_lock(&fs_info->fs_devices->device_list_mutex);
if (tgtdev->bdev) {
fs_info->fs_devices->open_devices--;
}
fs_info->fs_devices->num_devices--;
- if (tgtdev->can_discard)
- fs_info->fs_devices->num_can_discard++;
next_device = list_entry(fs_info->fs_devices->devices.next,
struct btrfs_device, dev_list);
call_rcu(&tgtdev->rcu, free_device);
mutex_unlock(&fs_info->fs_devices->device_list_mutex);
+ mutex_unlock(&uuid_mutex);
}
static int btrfs_find_device_by_path(struct btrfs_root *root, char *device_path,
mutex_lock(&root->fs_info->fs_devices->device_list_mutex);
list_splice_init_rcu(&fs_devices->devices, &seed_devices->devices,
synchronize_rcu);
+ list_for_each_entry(device, &seed_devices->devices, dev_list)
+ device->fs_devices = seed_devices;
+ lock_chunks(root);
list_splice_init(&fs_devices->alloc_list, &seed_devices->alloc_list);
- list_for_each_entry(device, &seed_devices->devices, dev_list) {
- device->fs_devices = seed_devices;
- }
+ unlock_chunks(root);
fs_devices->seeding = 0;
fs_devices->num_devices = 0;
fs_devices->open_devices = 0;
fs_devices->missing_devices = 0;
- fs_devices->num_can_discard = 0;
fs_devices->rotating = 0;
fs_devices->seed = seed_devices;
struct list_head *devices;
struct super_block *sb = root->fs_info->sb;
struct rcu_string *name;
- u64 total_bytes;
+ u64 tmp;
int seeding_dev = 0;
int ret = 0;
goto error;
}
- lock_chunks(root);
-
q = bdev_get_queue(bdev);
if (blk_queue_discard(q))
device->can_discard = 1;
device->sector_size = root->sectorsize;
device->total_bytes = i_size_read(bdev->bd_inode);
device->disk_total_bytes = device->total_bytes;
+ device->commit_total_bytes = device->total_bytes;
device->dev_root = root->fs_info->dev_root;
device->bdev = bdev;
device->in_fs_metadata = 1;
device->fs_devices = root->fs_info->fs_devices;
mutex_lock(&root->fs_info->fs_devices->device_list_mutex);
+ lock_chunks(root);
list_add_rcu(&device->dev_list, &root->fs_info->fs_devices->devices);
list_add(&device->dev_alloc_list,
&root->fs_info->fs_devices->alloc_list);
root->fs_info->fs_devices->open_devices++;
root->fs_info->fs_devices->rw_devices++;
root->fs_info->fs_devices->total_devices++;
- if (device->can_discard)
- root->fs_info->fs_devices->num_can_discard++;
root->fs_info->fs_devices->total_rw_bytes += device->total_bytes;
spin_lock(&root->fs_info->free_chunk_lock);
if (!blk_queue_nonrot(bdev_get_queue(bdev)))
root->fs_info->fs_devices->rotating = 1;
- total_bytes = btrfs_super_total_bytes(root->fs_info->super_copy);
+ tmp = btrfs_super_total_bytes(root->fs_info->super_copy);
btrfs_set_super_total_bytes(root->fs_info->super_copy,
- total_bytes + device->total_bytes);
+ tmp + device->total_bytes);
- total_bytes = btrfs_super_num_devices(root->fs_info->super_copy);
+ tmp = btrfs_super_num_devices(root->fs_info->super_copy);
btrfs_set_super_num_devices(root->fs_info->super_copy,
- total_bytes + 1);
+ tmp + 1);
/* add sysfs device entry */
btrfs_kobj_add_device(root->fs_info, device);
+ /*
+ * we've got more storage, clear any full flags on the space
+ * infos
+ */
+ btrfs_clear_space_info_full(root->fs_info);
+
+ unlock_chunks(root);
mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
if (seeding_dev) {
- char fsid_buf[BTRFS_UUID_UNPARSED_SIZE];
+ lock_chunks(root);
ret = init_first_rw_device(trans, root, device);
+ unlock_chunks(root);
if (ret) {
btrfs_abort_transaction(trans, root, ret);
goto error_trans;
}
+ }
+
+ ret = btrfs_add_device(trans, root, device);
+ if (ret) {
+ btrfs_abort_transaction(trans, root, ret);
+ goto error_trans;
+ }
+
+ if (seeding_dev) {
+ char fsid_buf[BTRFS_UUID_UNPARSED_SIZE];
+
ret = btrfs_finish_sprout(trans, root);
if (ret) {
btrfs_abort_transaction(trans, root, ret);
root->fs_info->fsid);
if (kobject_rename(&root->fs_info->super_kobj, fsid_buf))
goto error_trans;
- } else {
- ret = btrfs_add_device(trans, root, device);
- if (ret) {
- btrfs_abort_transaction(trans, root, ret);
- goto error_trans;
- }
}
- /*
- * we've got more storage, clear any full flags on the space
- * infos
- */
- btrfs_clear_space_info_full(root->fs_info);
-
- unlock_chunks(root);
root->fs_info->num_tolerated_disk_barrier_failures =
btrfs_calc_num_tolerated_disk_barrier_failures(root->fs_info);
ret = btrfs_commit_transaction(trans, root);
return ret;
error_trans:
- unlock_chunks(root);
btrfs_end_transaction(trans, root);
rcu_string_free(device->name);
btrfs_kobj_rm_device(root->fs_info, device);
}
int btrfs_init_dev_replace_tgtdev(struct btrfs_root *root, char *device_path,
+ struct btrfs_device *srcdev,
struct btrfs_device **device_out)
{
struct request_queue *q;
int ret = 0;
*device_out = NULL;
- if (fs_info->fs_devices->seeding)
+ if (fs_info->fs_devices->seeding) {
+ btrfs_err(fs_info, "the filesystem is a seed filesystem!");
return -EINVAL;
+ }
bdev = blkdev_get_by_path(device_path, FMODE_WRITE | FMODE_EXCL,
fs_info->bdev_holder);
- if (IS_ERR(bdev))
+ if (IS_ERR(bdev)) {
+ btrfs_err(fs_info, "target device %s is invalid!", device_path);
return PTR_ERR(bdev);
+ }
filemap_write_and_wait(bdev->bd_inode->i_mapping);
devices = &fs_info->fs_devices->devices;
list_for_each_entry(device, devices, dev_list) {
if (device->bdev == bdev) {
+ btrfs_err(fs_info, "target device is in the filesystem!");
ret = -EEXIST;
goto error;
}
}
+
+ if (i_size_read(bdev->bd_inode) <
+ btrfs_device_get_total_bytes(srcdev)) {
+ btrfs_err(fs_info, "target device is smaller than source device!");
+ ret = -EINVAL;
+ goto error;
+ }
+
+
device = btrfs_alloc_device(NULL, &devid, NULL);
if (IS_ERR(device)) {
ret = PTR_ERR(device);
device->io_width = root->sectorsize;
device->io_align = root->sectorsize;
device->sector_size = root->sectorsize;
- device->total_bytes = i_size_read(bdev->bd_inode);
- device->disk_total_bytes = device->total_bytes;
+ device->total_bytes = btrfs_device_get_total_bytes(srcdev);
+ device->disk_total_bytes = btrfs_device_get_disk_total_bytes(srcdev);
+ device->bytes_used = btrfs_device_get_bytes_used(srcdev);
+ ASSERT(list_empty(&srcdev->resized_list));
+ device->commit_total_bytes = srcdev->commit_total_bytes;
+ device->commit_bytes_used = device->bytes_used;
device->dev_root = fs_info->dev_root;
device->bdev = bdev;
device->in_fs_metadata = 1;
list_add(&device->dev_list, &fs_info->fs_devices->devices);
fs_info->fs_devices->num_devices++;
fs_info->fs_devices->open_devices++;
- if (device->can_discard)
- fs_info->fs_devices->num_can_discard++;
mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
*device_out = device;
btrfs_set_device_io_align(leaf, dev_item, device->io_align);
btrfs_set_device_io_width(leaf, dev_item, device->io_width);
btrfs_set_device_sector_size(leaf, dev_item, device->sector_size);
- btrfs_set_device_total_bytes(leaf, dev_item, device->disk_total_bytes);
- btrfs_set_device_bytes_used(leaf, dev_item, device->bytes_used);
+ btrfs_set_device_total_bytes(leaf, dev_item,
+ btrfs_device_get_disk_total_bytes(device));
+ btrfs_set_device_bytes_used(leaf, dev_item,
+ btrfs_device_get_bytes_used(device));
btrfs_mark_buffer_dirty(leaf);
out:
return ret;
}
-static int __btrfs_grow_device(struct btrfs_trans_handle *trans,
+int btrfs_grow_device(struct btrfs_trans_handle *trans,
struct btrfs_device *device, u64 new_size)
{
struct btrfs_super_block *super_copy =
device->dev_root->fs_info->super_copy;
- u64 old_total = btrfs_super_total_bytes(super_copy);
- u64 diff = new_size - device->total_bytes;
+ struct btrfs_fs_devices *fs_devices;
+ u64 old_total;
+ u64 diff;
if (!device->writeable)
return -EACCES;
+
+ lock_chunks(device->dev_root);
+ old_total = btrfs_super_total_bytes(super_copy);
+ diff = new_size - device->total_bytes;
+
if (new_size <= device->total_bytes ||
- device->is_tgtdev_for_dev_replace)
+ device->is_tgtdev_for_dev_replace) {
+ unlock_chunks(device->dev_root);
return -EINVAL;
+ }
+
+ fs_devices = device->dev_root->fs_info->fs_devices;
btrfs_set_super_total_bytes(super_copy, old_total + diff);
device->fs_devices->total_rw_bytes += diff;
- device->total_bytes = new_size;
- device->disk_total_bytes = new_size;
+ btrfs_device_set_total_bytes(device, new_size);
+ btrfs_device_set_disk_total_bytes(device, new_size);
btrfs_clear_space_info_full(device->dev_root->fs_info);
+ if (list_empty(&device->resized_list))
+ list_add_tail(&device->resized_list,
+ &fs_devices->resized_devices);
+ unlock_chunks(device->dev_root);
return btrfs_update_device(trans, device);
}
-int btrfs_grow_device(struct btrfs_trans_handle *trans,
- struct btrfs_device *device, u64 new_size)
-{
- int ret;
- lock_chunks(device->dev_root);
- ret = __btrfs_grow_device(trans, device, new_size);
- unlock_chunks(device->dev_root);
- return ret;
-}
-
static int btrfs_free_chunk(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
u64 chunk_tree, u64 chunk_objectid,
u32 cur;
struct btrfs_key key;
+ lock_chunks(root);
array_size = btrfs_super_sys_array_size(super_copy);
ptr = super_copy->sys_chunk_array;
cur += len;
}
}
+ unlock_chunks(root);
return ret;
}
-static int btrfs_relocate_chunk(struct btrfs_root *root,
- u64 chunk_tree, u64 chunk_objectid,
- u64 chunk_offset)
+int btrfs_remove_chunk(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root, u64 chunk_offset)
{
struct extent_map_tree *em_tree;
- struct btrfs_root *extent_root;
- struct btrfs_trans_handle *trans;
struct extent_map *em;
+ struct btrfs_root *extent_root = root->fs_info->extent_root;
struct map_lookup *map;
- int ret;
- int i;
+ u64 dev_extent_len = 0;
+ u64 chunk_objectid = BTRFS_FIRST_CHUNK_TREE_OBJECTID;
+ u64 chunk_tree = root->fs_info->chunk_root->objectid;
+ int i, ret = 0;
+ /* Just in case */
root = root->fs_info->chunk_root;
- extent_root = root->fs_info->extent_root;
em_tree = &root->fs_info->mapping_tree.map_tree;
- ret = btrfs_can_relocate(extent_root, chunk_offset);
- if (ret)
- return -ENOSPC;
-
- /* step one, relocate all the extents inside this chunk */
- ret = btrfs_relocate_block_group(extent_root, chunk_offset);
- if (ret)
- return ret;
-
- trans = btrfs_start_transaction(root, 0);
- if (IS_ERR(trans)) {
- ret = PTR_ERR(trans);
- btrfs_std_error(root->fs_info, ret);
- return ret;
- }
-
- lock_chunks(root);
-
- /*
- * step two, delete the device extents and the
- * chunk tree entries
- */
read_lock(&em_tree->lock);
em = lookup_extent_mapping(em_tree, chunk_offset, 1);
read_unlock(&em_tree->lock);
- BUG_ON(!em || em->start > chunk_offset ||
- em->start + em->len < chunk_offset);
+ if (!em || em->start > chunk_offset ||
+ em->start + em->len < chunk_offset) {
+ /*
+ * This is a logic error, but we don't want to just rely on the
+ * user having built with ASSERT enabled, so if ASSERT doens't
+ * do anything we still error out.
+ */
+ ASSERT(0);
+ if (em)
+ free_extent_map(em);
+ return -EINVAL;
+ }
map = (struct map_lookup *)em->bdev;
for (i = 0; i < map->num_stripes; i++) {
- ret = btrfs_free_dev_extent(trans, map->stripes[i].dev,
- map->stripes[i].physical);
- BUG_ON(ret);
+ struct btrfs_device *device = map->stripes[i].dev;
+ ret = btrfs_free_dev_extent(trans, device,
+ map->stripes[i].physical,
+ &dev_extent_len);
+ if (ret) {
+ btrfs_abort_transaction(trans, root, ret);
+ goto out;
+ }
+
+ if (device->bytes_used > 0) {
+ lock_chunks(root);
+ btrfs_device_set_bytes_used(device,
+ device->bytes_used - dev_extent_len);
+ spin_lock(&root->fs_info->free_chunk_lock);
+ root->fs_info->free_chunk_space += dev_extent_len;
+ spin_unlock(&root->fs_info->free_chunk_lock);
+ btrfs_clear_space_info_full(root->fs_info);
+ unlock_chunks(root);
+ }
if (map->stripes[i].dev) {
ret = btrfs_update_device(trans, map->stripes[i].dev);
- BUG_ON(ret);
+ if (ret) {
+ btrfs_abort_transaction(trans, root, ret);
+ goto out;
+ }
}
}
ret = btrfs_free_chunk(trans, root, chunk_tree, chunk_objectid,
chunk_offset);
-
- BUG_ON(ret);
+ if (ret) {
+ btrfs_abort_transaction(trans, root, ret);
+ goto out;
+ }
trace_btrfs_chunk_free(root, map, chunk_offset, em->len);
if (map->type & BTRFS_BLOCK_GROUP_SYSTEM) {
ret = btrfs_del_sys_chunk(root, chunk_objectid, chunk_offset);
- BUG_ON(ret);
+ if (ret) {
+ btrfs_abort_transaction(trans, root, ret);
+ goto out;
+ }
}
ret = btrfs_remove_block_group(trans, extent_root, chunk_offset);
- BUG_ON(ret);
+ if (ret) {
+ btrfs_abort_transaction(trans, extent_root, ret);
+ goto out;
+ }
write_lock(&em_tree->lock);
remove_extent_mapping(em_tree, em);
/* once for the tree */
free_extent_map(em);
+out:
/* once for us */
free_extent_map(em);
+ return ret;
+}
- unlock_chunks(root);
+static int btrfs_relocate_chunk(struct btrfs_root *root,
+ u64 chunk_tree, u64 chunk_objectid,
+ u64 chunk_offset)
+{
+ struct btrfs_root *extent_root;
+ struct btrfs_trans_handle *trans;
+ int ret;
+
+ root = root->fs_info->chunk_root;
+ extent_root = root->fs_info->extent_root;
+
+ ret = btrfs_can_relocate(extent_root, chunk_offset);
+ if (ret)
+ return -ENOSPC;
+
+ /* step one, relocate all the extents inside this chunk */
+ ret = btrfs_relocate_block_group(extent_root, chunk_offset);
+ if (ret)
+ return ret;
+
+ trans = btrfs_start_transaction(root, 0);
+ if (IS_ERR(trans)) {
+ ret = PTR_ERR(trans);
+ btrfs_std_error(root->fs_info, ret);
+ return ret;
+ }
+
+ /*
+ * step two, delete the device extents and the
+ * chunk tree entries
+ */
+ ret = btrfs_remove_chunk(trans, root, chunk_offset);
btrfs_end_transaction(trans, root);
- return 0;
+ return ret;
}
static int btrfs_relocate_sys_chunks(struct btrfs_root *root)
found_key.offset);
if (ret == -ENOSPC)
failed++;
- else if (ret)
- BUG();
+ else
+ BUG_ON(ret);
}
if (found_key.offset == 0)
/* step one make some room on all the devices */
devices = &fs_info->fs_devices->devices;
list_for_each_entry(device, devices, dev_list) {
- old_size = device->total_bytes;
+ old_size = btrfs_device_get_total_bytes(device);
size_to_free = div_factor(old_size, 1);
size_to_free = min(size_to_free, (u64)1 * 1024 * 1024);
if (!device->writeable ||
- device->total_bytes - device->bytes_used > size_to_free ||
+ btrfs_device_get_total_bytes(device) -
+ btrfs_device_get_bytes_used(device) > size_to_free ||
device->is_tgtdev_for_dev_replace)
continue;
max_key.type = BTRFS_ROOT_ITEM_KEY;
max_key.offset = (u64)-1;
- path->keep_locks = 1;
-
while (1) {
ret = btrfs_search_forward(root, &key, path, 0);
if (ret) {
struct btrfs_key key;
struct btrfs_super_block *super_copy = root->fs_info->super_copy;
u64 old_total = btrfs_super_total_bytes(super_copy);
- u64 old_size = device->total_bytes;
- u64 diff = device->total_bytes - new_size;
+ u64 old_size = btrfs_device_get_total_bytes(device);
+ u64 diff = old_size - new_size;
if (device->is_tgtdev_for_dev_replace)
return -EINVAL;
lock_chunks(root);
- device->total_bytes = new_size;
+ btrfs_device_set_total_bytes(device, new_size);
if (device->writeable) {
device->fs_devices->total_rw_bytes -= diff;
spin_lock(&root->fs_info->free_chunk_lock);
ret = -ENOSPC;
lock_chunks(root);
- device->total_bytes = old_size;
+ btrfs_device_set_total_bytes(device, old_size);
if (device->writeable)
device->fs_devices->total_rw_bytes += diff;
spin_lock(&root->fs_info->free_chunk_lock);
}
lock_chunks(root);
+ btrfs_device_set_disk_total_bytes(device, new_size);
+ if (list_empty(&device->resized_list))
+ list_add_tail(&device->resized_list,
+ &root->fs_info->fs_devices->resized_devices);
- device->disk_total_bytes = new_size;
- /* Now btrfs_update_device() will change the on-disk size. */
- ret = btrfs_update_device(trans, device);
- if (ret) {
- unlock_chunks(root);
- btrfs_end_transaction(trans, root);
- goto done;
- }
WARN_ON(diff > old_total);
btrfs_set_super_total_bytes(super_copy, old_total - diff);
unlock_chunks(root);
+
+ /* Now btrfs_update_device() will change the on-disk size. */
+ ret = btrfs_update_device(trans, device);
btrfs_end_transaction(trans, root);
done:
btrfs_free_path(path);
u32 array_size;
u8 *ptr;
+ lock_chunks(root);
array_size = btrfs_super_sys_array_size(super_copy);
if (array_size + item_size + sizeof(disk_key)
- > BTRFS_SYSTEM_CHUNK_ARRAY_SIZE)
+ > BTRFS_SYSTEM_CHUNK_ARRAY_SIZE) {
+ unlock_chunks(root);
return -EFBIG;
+ }
ptr = super_copy->sys_chunk_array + array_size;
btrfs_cpu_key_to_disk(&disk_key, key);
memcpy(ptr, chunk, item_size);
item_size += sizeof(disk_key);
btrfs_set_super_sys_array_size(super_copy, array_size + item_size);
+ unlock_chunks(root);
+
return 0;
}
if (ret)
goto error_del_extent;
+ for (i = 0; i < map->num_stripes; i++) {
+ num_bytes = map->stripes[i].dev->bytes_used + stripe_size;
+ btrfs_device_set_bytes_used(map->stripes[i].dev, num_bytes);
+ }
+
+ spin_lock(&extent_root->fs_info->free_chunk_lock);
+ extent_root->fs_info->free_chunk_space -= (stripe_size *
+ map->num_stripes);
+ spin_unlock(&extent_root->fs_info->free_chunk_lock);
+
free_extent_map(em);
check_raid56_incompat_flag(extent_root->fs_info, type);
device = map->stripes[i].dev;
dev_offset = map->stripes[i].physical;
- device->bytes_used += stripe_size;
ret = btrfs_update_device(trans, device);
if (ret)
goto out;
goto out;
}
- spin_lock(&extent_root->fs_info->free_chunk_lock);
- extent_root->fs_info->free_chunk_space -= (stripe_size *
- map->num_stripes);
- spin_unlock(&extent_root->fs_info->free_chunk_lock);
-
stripe = &chunk->stripe;
for (i = 0; i < map->num_stripes; i++) {
device = map->stripes[i].dev;
alloc_profile = btrfs_get_alloc_profile(fs_info->chunk_root, 0);
ret = __btrfs_alloc_chunk(trans, extent_root, sys_chunk_offset,
alloc_profile);
- if (ret) {
- btrfs_abort_transaction(trans, root, ret);
- goto out;
+ return ret;
+}
+
+static inline int btrfs_chunk_max_errors(struct map_lookup *map)
+{
+ int max_errors;
+
+ if (map->type & (BTRFS_BLOCK_GROUP_RAID1 |
+ BTRFS_BLOCK_GROUP_RAID10 |
+ BTRFS_BLOCK_GROUP_RAID5 |
+ BTRFS_BLOCK_GROUP_DUP)) {
+ max_errors = 1;
+ } else if (map->type & BTRFS_BLOCK_GROUP_RAID6) {
+ max_errors = 2;
+ } else {
+ max_errors = 0;
}
- ret = btrfs_add_device(trans, fs_info->chunk_root, device);
- if (ret)
- btrfs_abort_transaction(trans, root, ret);
-out:
- return ret;
+ return max_errors;
}
int btrfs_chunk_readonly(struct btrfs_root *root, u64 chunk_offset)
struct map_lookup *map;
struct btrfs_mapping_tree *map_tree = &root->fs_info->mapping_tree;
int readonly = 0;
+ int miss_ndevs = 0;
int i;
read_lock(&map_tree->map_tree.lock);
if (!em)
return 1;
- if (btrfs_test_opt(root, DEGRADED)) {
- free_extent_map(em);
- return 0;
- }
-
map = (struct map_lookup *)em->bdev;
for (i = 0; i < map->num_stripes; i++) {
+ if (map->stripes[i].dev->missing) {
+ miss_ndevs++;
+ continue;
+ }
+
if (!map->stripes[i].dev->writeable) {
readonly = 1;
- break;
+ goto end;
}
}
+
+ /*
+ * If the number of missing devices is larger than max errors,
+ * we can not write the data into that chunk successfully, so
+ * set it readonly.
+ */
+ if (miss_ndevs > btrfs_chunk_max_errors(map))
+ readonly = 1;
+end:
free_extent_map(em);
return readonly;
}
num_stripes = min_t(u64, map->num_stripes,
stripe_nr_end - stripe_nr_orig);
stripe_index = do_div(stripe_nr, map->num_stripes);
+ if (!(rw & (REQ_WRITE | REQ_DISCARD | REQ_GET_READ_MIRRORS)))
+ mirror_num = 1;
} else if (map->type & BTRFS_BLOCK_GROUP_RAID1) {
if (rw & (REQ_WRITE | REQ_DISCARD | REQ_GET_READ_MIRRORS))
num_stripes = map->num_stripes;
/* We distribute the parity blocks across stripes */
tmp = stripe_nr + stripe_index;
stripe_index = do_div(tmp, map->num_stripes);
+ if (!(rw & (REQ_WRITE | REQ_DISCARD |
+ REQ_GET_READ_MIRRORS)) && mirror_num <= 1)
+ mirror_num = 1;
}
} else {
/*
}
}
- if (rw & (REQ_WRITE | REQ_GET_READ_MIRRORS)) {
- if (map->type & (BTRFS_BLOCK_GROUP_RAID1 |
- BTRFS_BLOCK_GROUP_RAID10 |
- BTRFS_BLOCK_GROUP_RAID5 |
- BTRFS_BLOCK_GROUP_DUP)) {
- max_errors = 1;
- } else if (map->type & BTRFS_BLOCK_GROUP_RAID6) {
- max_errors = 2;
- }
- }
+ if (rw & (REQ_WRITE | REQ_GET_READ_MIRRORS))
+ max_errors = btrfs_chunk_max_errors(map);
if (dev_replace_is_ongoing && (rw & (REQ_WRITE | REQ_DISCARD)) &&
dev_replace->tgtdev != NULL) {
name = rcu_dereference(dev->name);
pr_debug("btrfs_map_bio: rw %d, sector=%llu, dev=%lu "
"(%s id %llu), size=%u\n", rw,
- (u64)bio->bi_sector, (u_long)dev->bdev->bd_dev,
- name->str, dev->devid, bio->bi_size);
+ (u64)bio->bi_iter.bi_sector, (u_long)dev->bdev->bd_dev,
+ name->str, dev->devid, bio->bi_iter.bi_size);
rcu_read_unlock();
}
#endif
}
static struct btrfs_device *add_missing_dev(struct btrfs_root *root,
+ struct btrfs_fs_devices *fs_devices,
u64 devid, u8 *dev_uuid)
{
struct btrfs_device *device;
- struct btrfs_fs_devices *fs_devices = root->fs_info->fs_devices;
device = btrfs_alloc_device(NULL, &devid, dev_uuid);
if (IS_ERR(device))
}
if (!map->stripes[i].dev) {
map->stripes[i].dev =
- add_missing_dev(root, devid, uuid);
+ add_missing_dev(root, root->fs_info->fs_devices,
+ devid, uuid);
if (!map->stripes[i].dev) {
free_extent_map(em);
return -EIO;
device->devid = btrfs_device_id(leaf, dev_item);
device->disk_total_bytes = btrfs_device_total_bytes(leaf, dev_item);
device->total_bytes = device->disk_total_bytes;
+ device->commit_total_bytes = device->disk_total_bytes;
device->bytes_used = btrfs_device_bytes_used(leaf, dev_item);
+ device->commit_bytes_used = device->bytes_used;
device->type = btrfs_device_type(leaf, dev_item);
device->io_align = btrfs_device_io_align(leaf, dev_item);
device->io_width = btrfs_device_io_width(leaf, dev_item);
read_extent_buffer(leaf, device->uuid, ptr, BTRFS_UUID_SIZE);
}
-static int open_seed_devices(struct btrfs_root *root, u8 *fsid)
+static struct btrfs_fs_devices *open_seed_devices(struct btrfs_root *root,
+ u8 *fsid)
{
struct btrfs_fs_devices *fs_devices;
int ret;
fs_devices = root->fs_info->fs_devices->seed;
while (fs_devices) {
- if (!memcmp(fs_devices->fsid, fsid, BTRFS_UUID_SIZE)) {
- ret = 0;
- goto out;
- }
+ if (!memcmp(fs_devices->fsid, fsid, BTRFS_UUID_SIZE))
+ return fs_devices;
+
fs_devices = fs_devices->seed;
}
fs_devices = find_fsid(fsid);
if (!fs_devices) {
- ret = -ENOENT;
- goto out;
+ if (!btrfs_test_opt(root, DEGRADED))
+ return ERR_PTR(-ENOENT);
+
+ fs_devices = alloc_fs_devices(fsid);
+ if (IS_ERR(fs_devices))
+ return fs_devices;
+
+ fs_devices->seeding = 1;
+ fs_devices->opened = 1;
+ return fs_devices;
}
fs_devices = clone_fs_devices(fs_devices);
- if (IS_ERR(fs_devices)) {
- ret = PTR_ERR(fs_devices);
- goto out;
- }
+ if (IS_ERR(fs_devices))
+ return fs_devices;
ret = __btrfs_open_devices(fs_devices, FMODE_READ,
root->fs_info->bdev_holder);
if (ret) {
free_fs_devices(fs_devices);
+ fs_devices = ERR_PTR(ret);
goto out;
}
if (!fs_devices->seeding) {
__btrfs_close_devices(fs_devices);
free_fs_devices(fs_devices);
- ret = -EINVAL;
+ fs_devices = ERR_PTR(-EINVAL);
goto out;
}
fs_devices->seed = root->fs_info->fs_devices->seed;
root->fs_info->fs_devices->seed = fs_devices;
out:
- return ret;
+ return fs_devices;
}
static int read_one_dev(struct btrfs_root *root,
struct extent_buffer *leaf,
struct btrfs_dev_item *dev_item)
{
+ struct btrfs_fs_devices *fs_devices = root->fs_info->fs_devices;
struct btrfs_device *device;
u64 devid;
int ret;
BTRFS_UUID_SIZE);
if (memcmp(fs_uuid, root->fs_info->fsid, BTRFS_UUID_SIZE)) {
- ret = open_seed_devices(root, fs_uuid);
- if (ret && !btrfs_test_opt(root, DEGRADED))
- return ret;
+ fs_devices = open_seed_devices(root, fs_uuid);
+ if (IS_ERR(fs_devices))
+ return PTR_ERR(fs_devices);
}
device = btrfs_find_device(root->fs_info, devid, dev_uuid, fs_uuid);
- if (!device || !device->bdev) {
+ if (!device) {
if (!btrfs_test_opt(root, DEGRADED))
return -EIO;
- if (!device) {
- btrfs_warn(root->fs_info, "devid %llu missing", devid);
- device = add_missing_dev(root, devid, dev_uuid);
- if (!device)
- return -ENOMEM;
- } else if (!device->missing) {
+ btrfs_warn(root->fs_info, "devid %llu missing", devid);
+ device = add_missing_dev(root, fs_devices, devid, dev_uuid);
+ if (!device)
+ return -ENOMEM;
+ } else {
+ if (!device->bdev && !btrfs_test_opt(root, DEGRADED))
+ return -EIO;
+
+ if(!device->bdev && !device->missing) {
/*
* this happens when a device that was properly setup
* in the device info lists suddenly goes bad.
* device->bdev is NULL, and so we have to set
* device->missing to one here
*/
- root->fs_info->fs_devices->missing_devices++;
+ device->fs_devices->missing_devices++;
device->missing = 1;
}
+
+ /* Move the device to its own fs_devices */
+ if (device->fs_devices != fs_devices) {
+ ASSERT(device->missing);
+
+ list_move(&device->dev_list, &fs_devices->devices);
+ device->fs_devices->num_devices--;
+ fs_devices->num_devices++;
+
+ device->fs_devices->missing_devices--;
+ fs_devices->missing_devices++;
+
+ device->fs_devices = fs_devices;
+ }
}
if (device->fs_devices != root->fs_info->fs_devices) {
struct btrfs_root *dev_root = fs_info->dev_root;
struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
struct btrfs_device *device;
+ int stats_cnt;
int ret = 0;
mutex_lock(&fs_devices->device_list_mutex);
list_for_each_entry(device, &fs_devices->devices, dev_list) {
- if (!device->dev_stats_valid || !device->dev_stats_dirty)
+ if (!device->dev_stats_valid || !btrfs_dev_stats_dirty(device))
continue;
+ stats_cnt = atomic_read(&device->dev_stats_ccnt);
ret = update_dev_stat_item(trans, dev_root, device);
if (!ret)
- device->dev_stats_dirty = 0;
+ atomic_sub(stats_cnt, &device->dev_stats_ccnt);
}
mutex_unlock(&fs_devices->device_list_mutex);
return 0;
}
+
+/*
+ * Update the size of all devices, which is used for writing out the
+ * super blocks.
+ */
+void btrfs_update_commit_device_size(struct btrfs_fs_info *fs_info)
+{
+ struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
+ struct btrfs_device *curr, *next;
+
+ if (list_empty(&fs_devices->resized_devices))
+ return;
+
+ mutex_lock(&fs_devices->device_list_mutex);
+ lock_chunks(fs_info->dev_root);
+ list_for_each_entry_safe(curr, next, &fs_devices->resized_devices,
+ resized_list) {
+ list_del_init(&curr->resized_list);
+ curr->commit_total_bytes = curr->disk_total_bytes;
+ }
+ unlock_chunks(fs_info->dev_root);
+ mutex_unlock(&fs_devices->device_list_mutex);
+}
+
+/* Must be invoked during the transaction commit */
+void btrfs_update_commit_device_bytes_used(struct btrfs_root *root,
+ struct btrfs_transaction *transaction)
+{
+ struct extent_map *em;
+ struct map_lookup *map;
+ struct btrfs_device *dev;
+ int i;
+
+ if (list_empty(&transaction->pending_chunks))
+ return;
+
+ /* In order to kick the device replace finish process */
+ lock_chunks(root);
+ list_for_each_entry(em, &transaction->pending_chunks, list) {
+ map = (struct map_lookup *)em->bdev;
+
+ for (i = 0; i < map->num_stripes; i++) {
+ dev = map->stripes[i].dev;
+ dev->commit_bytes_used = dev->bytes_used;
+ }
+ }
+ unlock_chunks(root);
+}
projects / karo-tx-linux.git / blobdiff