path: root/fs/btrfs/dev-replace.c

// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (C) STRATO AG 2012.  All rights reserved.
 */

#include <linux/sched.h>
#include <linux/bio.h>
#include <linux/slab.h>
#include <linux/blkdev.h>
#include <linux/kthread.h>
#include <linux/math64.h>
#include "misc.h"
#include "ctree.h"
#include "extent_map.h"
#include "disk-io.h"
#include "transaction.h"
#include "print-tree.h"
#include "volumes.h"
#include "async-thread.h"
#include "check-integrity.h"
#include "rcu-string.h"
#include "dev-replace.h"
#include "sysfs.h"

/*
 * Device replace overview
 *
 * [Objective]
 * To copy all extents (both new and on-disk) from source device to target
 * device, while still keeping the filesystem read-write.
 *
 * [Method]
 * There are two main methods involved:
 *
 * - Write duplication
 *
 *   All new writes will be written to both target and source devices, so even
 *   if replace gets canceled, sources device still contans up-to-date data.
 *
 *   Location:		handle_ops_on_dev_replace() from __btrfs_map_block()
 *   Start:		btrfs_dev_replace_start()
 *   End:		btrfs_dev_replace_finishing()
 *   Content:		Latest data/metadata
 *
 * - Copy existing extents
 *
 *   This happens by re-using scrub facility, as scrub also iterates through
 *   existing extents from commit root.
 *
 *   Location:		scrub_write_block_to_dev_replace() from
 *   			scrub_block_complete()
 *   Content:		Data/meta from commit root.
 *
 * Due to the content difference, we need to avoid nocow write when dev-replace
 * is happening.  This is done by marking the block group read-only and waiting
 * for NOCOW writes.
 *
 * After replace is done, the finishing part is done by swapping the target and
 * source devices.
 *
 *   Location:		btrfs_dev_replace_update_device_in_mapping_tree() from
 *   			btrfs_dev_replace_finishing()
 */

static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
				       int scrub_ret);
static void btrfs_dev_replace_update_device_in_mapping_tree(
						struct btrfs_fs_info *fs_info,
						struct btrfs_device *srcdev,
						struct btrfs_device *tgtdev);
static int btrfs_dev_replace_kthread(void *data);

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_IOCTL_DEV_REPLACE_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 (!</