예제 #1
0
static int btrfs_dev_replace_kthread(void *data)
{
	struct btrfs_fs_info *fs_info = data;
	struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;
	struct btrfs_ioctl_dev_replace_args *status_args;
	u64 progress;

	status_args = kzalloc(sizeof(*status_args), GFP_NOFS);
	if (status_args) {
		btrfs_dev_replace_status(fs_info, status_args);
		progress = status_args->status.progress_1000;
		kfree(status_args);
		do_div(progress, 10);
		printk_in_rcu(KERN_INFO
			      "btrfs: continuing dev_replace from %s (devid %llu) to %s @%u%%\n",
			      dev_replace->srcdev->missing ? "<missing disk>" :
				rcu_str_deref(dev_replace->srcdev->name),
			      dev_replace->srcdev->devid,
			      dev_replace->tgtdev ?
				rcu_str_deref(dev_replace->tgtdev->name) :
				"<missing target disk>",
			      (unsigned int)progress);
	}
	btrfs_dev_replace_continue_on_mount(fs_info);
	atomic_set(&fs_info->mutually_exclusive_operation_running, 0);

	return 0;
}
예제 #2
0
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)) {
		pr_warn("btrfs: dev_replace cannot yet handle RAID5/RAID6\n");
		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) {
		pr_err("btrfs: target device %s is invalid!\n",
		       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) {
		pr_err("btrfs: target device is smaller than source device!\n");
		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 = btrfs_get_seconds_since_1970();
	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_all_ordered_extents(root->fs_info, 0);

	/* 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;
}
예제 #3
0
static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
				       int scrub_ret)
{
	struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;
	struct btrfs_device *tgt_device;
	struct btrfs_device *src_device;
	struct btrfs_root *root = fs_info->tree_root;
	u8 uuid_tmp[BTRFS_UUID_SIZE];
	struct btrfs_trans_handle *trans;
	int ret = 0;

	/* don't allow cancel or unmount to disturb the finishing procedure */
	mutex_lock(&dev_replace->lock_finishing_cancel_unmount);

	btrfs_dev_replace_lock(dev_replace);
	/* was the operation canceled, or is it finished? */
	if (dev_replace->replace_state !=
	    BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED) {
		btrfs_dev_replace_unlock(dev_replace);
		mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
		return 0;
	}

	tgt_device = dev_replace->tgtdev;
	src_device = dev_replace->srcdev;
	btrfs_dev_replace_unlock(dev_replace);

	/* replace old device with new one in mapping tree */
	if (!scrub_ret)
		btrfs_dev_replace_update_device_in_mapping_tree(fs_info,
								src_device,
								tgt_device);

	/*
	 * flush all outstanding I/O and inode extent mappings before the
	 * copy operation is declared as being finished
	 */
	ret = btrfs_start_all_delalloc_inodes(root->fs_info, 0);
	if (ret) {
		mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
		return ret;
	}
	btrfs_wait_all_ordered_extents(root->fs_info, 0);

	trans = btrfs_start_transaction(root, 0);
	if (IS_ERR(trans)) {
		mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
		return PTR_ERR(trans);
	}
	ret = btrfs_commit_transaction(trans, root);
	WARN_ON(ret);

	/* keep away write_all_supers() during the finishing procedure */
	mutex_lock(&root->fs_info->fs_devices->device_list_mutex);
	btrfs_dev_replace_lock(dev_replace);
	dev_replace->replace_state =
		scrub_ret ? BTRFS_IOCTL_DEV_REPLACE_STATE_CANCELED
			  : BTRFS_IOCTL_DEV_REPLACE_STATE_FINISHED;
	dev_replace->tgtdev = NULL;
	dev_replace->srcdev = NULL;
	dev_replace->time_stopped = btrfs_get_seconds_since_1970();
	dev_replace->item_needs_writeback = 1;

	if (scrub_ret) {
		printk_in_rcu(KERN_ERR
			      "btrfs: btrfs_scrub_dev(%s, %llu, %s) failed %d\n",
			      src_device->missing ? "<missing disk>" :
			        rcu_str_deref(src_device->name),
			      src_device->devid,
			      rcu_str_deref(tgt_device->name), scrub_ret);
		btrfs_dev_replace_unlock(dev_replace);
		mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
		if (tgt_device)
			btrfs_destroy_dev_replace_tgtdev(fs_info, tgt_device);
		mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);

		return 0;
	}

	printk_in_rcu(KERN_INFO
		      "btrfs: dev_replace from %s (devid %llu) to %s) finished\n",
		      src_device->missing ? "<missing disk>" :
		        rcu_str_deref(src_device->name),
		      src_device->devid,
		      rcu_str_deref(tgt_device->name));
	tgt_device->is_tgtdev_for_dev_replace = 0;
	tgt_device->devid = src_device->devid;
	src_device->devid = BTRFS_DEV_REPLACE_DEVID;
	tgt_device->bytes_used = src_device->bytes_used;
	memcpy(uuid_tmp, tgt_device->uuid, sizeof(uuid_tmp));
	memcpy(tgt_device->uuid, src_device->uuid, sizeof(tgt_device->uuid));
	memcpy(src_device->uuid, uuid_tmp, sizeof(src_device->uuid));
	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;
	if (fs_info->sb->s_bdev == src_device->bdev)
		fs_info->sb->s_bdev = tgt_device->bdev;
	if (fs_info->fs_devices->latest_bdev == src_device->bdev)
		fs_info->fs_devices->latest_bdev = tgt_device->bdev;
	list_add(&tgt_device->dev_alloc_list, &fs_info->fs_devices->alloc_list);

	btrfs_rm_dev_replace_srcdev(fs_info, src_device);
	if (src_device->bdev) {
		/* zero out the old super */
		btrfs_scratch_superblock(src_device);
	}
	/*
	 * this is again a consistent state where no dev_replace procedure
	 * is running, the target device is part of the filesystem, the
	 * source device is not part of the filesystem anymore and its 1st
	 * superblock is scratched out so that it is no longer marked to
	 * belong to this filesystem.
	 */
	btrfs_dev_replace_unlock(dev_replace);
	mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);

	/* write back the superblocks */
	trans = btrfs_start_transaction(root, 0);
	if (!IS_ERR(trans))
		btrfs_commit_transaction(trans, root);

	mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);

	return 0;
}
예제 #4
0
파일: dev-replace.c 프로젝트: Abioy/kasan
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;

	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;

	/*
	 * Here we commit the transaction to make sure commit_total_bytes
	 * of all the devices are updated.
	 */
	trans = btrfs_attach_transaction(root);
	if (!IS_ERR(trans)) {
		ret = btrfs_commit_transaction(trans, root);
		if (ret)
			return ret;
	} else if (PTR_ERR(trans) != -ENOENT) {
		return PTR_ERR(trans);
	}

	/* the disk copy procedure reuses the scrub code */
	mutex_lock(&fs_info->volume_mutex);
	ret = btrfs_dev_replace_find_srcdev(root, args->start.srcdevid,
					    args->start.srcdev_name,
					    &src_device);
	if (ret) {
		mutex_unlock(&fs_info->volume_mutex);
		return ret;
	}

	ret = btrfs_init_dev_replace_tgtdev(root, args->start.tgtdev_name,
					    src_device, &tgt_device);
	mutex_unlock(&fs_info->volume_mutex);
	if (ret)
		return ret;

	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));

	/*
	 * 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,
			      btrfs_device_get_total_bytes(src_device),
			      &dev_replace->scrub_progress, 0, 1);

	ret = btrfs_dev_replace_finishing(root->fs_info, ret);
	/* don't warn if EINPROGRESS, someone else might be running scrub */
	if (ret == -EINPROGRESS) {
		args->result = BTRFS_IOCTL_DEV_REPLACE_RESULT_SCRUB_INPROGRESS;
		ret = 0;
	} else {
		WARN_ON(ret);
	}

	return ret;

leave:
	dev_replace->srcdev = NULL;
	dev_replace->tgtdev = NULL;
	btrfs_dev_replace_unlock(dev_replace);
	btrfs_destroy_dev_replace_tgtdev(fs_info, tgt_device);
	return ret;
}