// 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 "disk-io.h"#include "transaction.h"#include "volumes.h"#include "async-thread.h"#include "dev-replace.h"#include "sysfs.h"#include "zoned.h"#include "block-group.h"#include "fs.h"#include "accessors.h"#include "scrub.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 contains 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 reusing 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 int btrfs_dev_replace_kthread(void *data); int btrfs_init_dev_replace(struct btrfs_fs_info *fs_info){ struct btrfs_dev_lookup_args args = { .devid = BTRFS_DEV_REPLACE_DEVID }; 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; if (!dev_root) return 0; 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: /* * We don't have a replace item or it's corrupted. If there is * a replace target, fail the mount. */ if (btrfs_find_device(fs_info->fs_devices, &args)) { btrfs_err(fs_info, "found replace target device without a valid replace item"); ret = -EUCLEAN; goto out; } 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(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: /* * We don't have an active replace item but if there is a * replace target, fail the mount. */ if (btrfs_find_device(fs_info->fs_devices, &args)) { btrfs_err(fs_info,"replace without active item, run 'device scan --forget' on the target device"); ret = -EUCLEAN; } else { 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->tgtdev = btrfs_find_device(fs_info->fs_devices, &args); args.devid = src_devid; dev_replace->srcdev = btrfs_find_device(fs_info->fs_devices, &args); /* * 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;} /* * Initialize a new device for device replace target from a given source dev * and path. * * Return 0 and new device in @device_out, otherwise return < 0 */static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info, const char *device_path, struct btrfs_device *srcdev, struct btrfs_device **device_out){ struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; struct btrfs_device *device; struct file *bdev_file; struct block_device *bdev; u64 devid = BTRFS_DEV_REPLACE_DEVID; int ret = 0; *device_out = NULL; if (srcdev->fs_devices->seeding) { btrfs_err(fs_info, "the filesystem is a seed filesystem!"); return -EINVAL; } bdev_file = bdev_file_open_by_path(device_path, BLK_OPEN_WRITE, fs_info->bdev_holder, NULL); if (IS_ERR(bdev_file)) { btrfs_err(fs_info, "target device %s is invalid!", device_path); return PTR_ERR(bdev_file); } bdev = file_bdev(bdev_file); if (!btrfs_check_device_zone_type(fs_info, bdev)) { btrfs_err(fs_info, "dev-replace: zoned type of target device mismatch with filesystem"); ret = -EINVAL; goto error; } sync_blockdev(bdev); list_for_each_entry(device, &fs_devices->devices, dev_list) { if (device->bdev == bdev) { btrfs_err(fs_info, "target device is in the filesystem!"); ret = -EEXIST; goto error; } } if (bdev_nr_bytes(bdev) < 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, device_path); if (IS_ERR(device)) { ret = PTR_ERR(device); goto error; } ret = lookup_bdev(device_path, &device->devt); if (ret) goto error; set_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state); device->generation = 0; device->io_width = fs_info->sectorsize; device->io_align = fs_info->sectorsize; device->sector_size = fs_info->sectorsize; 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); device->commit_total_bytes = srcdev->commit_total_bytes; device->commit_bytes_used = device->bytes_used; device->fs_info = fs_info; device->bdev = bdev; device->bdev_file = bdev_file; set_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state); set_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state); device->dev_stats_valid = 1; set_blocksize(bdev_file, BTRFS_BDEV_BLOCKSIZE); device->fs_devices = fs_devices; ret = btrfs_get_dev_zone_info(device, false); if (ret) goto error; mutex_lock(&fs_devices->device_list_mutex); list_add(&device->dev_list, &fs_devices->devices); fs_devices->num_devices++; fs_devices->open_devices++; mutex_unlock(&fs_devices->device_list_mutex); *device_out = device; return 0; error: fput(bdev_file); 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 = trans->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(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(trans, eb); out: btrfs_free_path(path); return ret;} static int mark_block_group_to_copy(struct btrfs_fs_info *fs_info, struct btrfs_device *src_dev){ struct btrfs_path *path; struct btrfs_key key; struct btrfs_key found_key; struct btrfs_root *root = fs_info->dev_root; struct btrfs_dev_extent *dev_extent = NULL; struct btrfs_block_group *cache; struct btrfs_trans_handle *trans; int iter_ret = 0; int ret = 0; u64 chunk_offset; /* Do not use "to_copy" on non zoned filesystem for now */ if (!btrfs_is_zoned(fs_info)) return 0; mutex_lock(&fs_info->chunk_mutex); /* Ensure we don't have pending new block group */ spin_lock(&fs_info->trans_lock); while (fs_info->running_transaction && !list_empty(&fs_info->running_transaction->dev_update_list)) { spin_unlock(&fs_info->trans_lock); mutex_unlock(&fs_info->chunk_mutex); trans = btrfs_attach_transaction(root); if (IS_ERR(trans)) { ret = PTR_ERR(trans); mutex_lock(&fs_info->chunk_mutex); if (ret == -ENOENT) { spin_lock(&fs_info->trans_lock); continue; } else { goto unlock; } } ret = btrfs_commit_transaction(trans); mutex_lock(&fs_info->chunk_mutex); if (ret) goto unlock; spin_lock(&fs_info->trans_lock); } spin_unlock(&fs_info->trans_lock); path = btrfs_alloc_path(); if (!path) {Lines 1–500 of 1326. Load more
// 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 "disk-io.h" #include "transaction.h" #include "volumes.h" #include "async-thread.h" #include "dev-replace.h" #include "sysfs.h" #include "zoned.h" #include "block-group.h" #include "fs.h" #include "accessors.h" #include "scrub.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 contains 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 reusing 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 int btrfs_dev_replace_kthread(void *data); int btrfs_init_dev_replace(struct btrfs_fs_info *fs_info) { struct btrfs_dev_lookup_args args = { .devid = BTRFS_DEV_REPLACE_DEVID }; 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; if (!dev_root) return 0; 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: /* * We don't have a replace item or it's corrupted. If there is * a replace target, fail the mount. */ if (btrfs_find_device(fs_info->fs_devices, &args)) { btrfs_err(fs_info, "found replace target device without a valid replace item"); ret = -EUCLEAN; goto out; } 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(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: /* * We don't have an active replace item but if there is a * replace target, fail the mount. */ if (btrfs_find_device(fs_info->fs_devices, &args)) { btrfs_err(fs_info, "replace without active item, run 'device scan --forget' on the target device"); ret = -EUCLEAN; } else { 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->tgtdev = btrfs_find_device(fs_info->fs_devices, &args); args.devid = src_devid; dev_replace->srcdev = btrfs_find_device(fs_info->fs_devices, &args); /* * 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; } /* * Initialize a new device for device replace target from a given source dev * and path. * * Return 0 and new device in @device_out, otherwise return < 0 */ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info, const char *device_path, struct btrfs_device *srcdev, struct btrfs_device **device_out) { struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; struct btrfs_device *device; struct file *bdev_file; struct block_device *bdev; u64 devid = BTRFS_DEV_REPLACE_DEVID; int ret = 0; *device_out = NULL; if (srcdev->fs_devices->seeding) { btrfs_err(fs_info, "the filesystem is a seed filesystem!"); return -EINVAL; } bdev_file = bdev_file_open_by_path(device_path, BLK_OPEN_WRITE, fs_info->bdev_holder, NULL); if (IS_ERR(bdev_file)) { btrfs_err(fs_info, "target device %s is invalid!", device_path); return PTR_ERR(bdev_file); } bdev = file_bdev(bdev_file); if (!btrfs_check_device_zone_type(fs_info, bdev)) { btrfs_err(fs_info, "dev-replace: zoned type of target device mismatch with filesystem"); ret = -EINVAL; goto error; } sync_blockdev(bdev); list_for_each_entry(device, &fs_devices->devices, dev_list) { if (device->bdev == bdev) { btrfs_err(fs_info, "target device is in the filesystem!"); ret = -EEXIST; goto error; } } if (bdev_nr_bytes(bdev) < 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, device_path); if (IS_ERR(device)) { ret = PTR_ERR(device); goto error; } ret = lookup_bdev(device_path, &device->devt); if (ret) goto error; set_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state); device->generation = 0; device->io_width = fs_info->sectorsize; device->io_align = fs_info->sectorsize; device->sector_size = fs_info->sectorsize; 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); device->commit_total_bytes = srcdev->commit_total_bytes; device->commit_bytes_used = device->bytes_used; device->fs_info = fs_info; device->bdev = bdev; device->bdev_file = bdev_file; set_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state); set_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state); device->dev_stats_valid = 1; set_blocksize(bdev_file, BTRFS_BDEV_BLOCKSIZE); device->fs_devices = fs_devices; ret = btrfs_get_dev_zone_info(device, false); if (ret) goto error; mutex_lock(&fs_devices->device_list_mutex); list_add(&device->dev_list, &fs_devices->devices); fs_devices->num_devices++; fs_devices->open_devices++; mutex_unlock(&fs_devices->device_list_mutex); *device_out = device; return 0; error: fput(bdev_file); 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 = trans->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(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(trans, eb); out: btrfs_free_path(path); return ret; } static int mark_block_group_to_copy(struct btrfs_fs_info *fs_info, struct btrfs_device *src_dev) { struct btrfs_path *path; struct btrfs_key key; struct btrfs_key found_key; struct btrfs_root *root = fs_info->dev_root; struct btrfs_dev_extent *dev_extent = NULL; struct btrfs_block_group *cache; struct btrfs_trans_handle *trans; int iter_ret = 0; int ret = 0; u64 chunk_offset; /* Do not use "to_copy" on non zoned filesystem for now */ if (!btrfs_is_zoned(fs_info)) return 0; mutex_lock(&fs_info->chunk_mutex); /* Ensure we don't have pending new block group */ spin_lock(&fs_info->trans_lock); while (fs_info->running_transaction && !list_empty(&fs_info->running_transaction->dev_update_list)) { spin_unlock(&fs_info->trans_lock); mutex_unlock(&fs_info->chunk_mutex); trans = btrfs_attach_transaction(root); if (IS_ERR(trans)) { ret = PTR_ERR(trans); mutex_lock(&fs_info->chunk_mutex); if (ret == -ENOENT) { spin_lock(&fs_info->trans_lock); continue; } else { goto unlock; } } ret = btrfs_commit_transaction(trans); mutex_lock(&fs_info->chunk_mutex); if (ret) goto unlock; spin_lock(&fs_info->trans_lock); } spin_unlock(&fs_info->trans_lock); path = btrfs_alloc_path(); if (!path) {