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;
ret = 1;
device->fs_devices = fs_devices;
} else if (!device->name || strcmp(device->name->str, path)) {
+ /*
+ * When FS is already mounted.
+ * 1. If you are here and if the device->name is NULL that
+ * means this device was missing at time of FS mount.
+ * 2. If you are here and if the device->name is different
+ * from 'path' that means either
+ * a. The same device disappeared and reappeared with
+ * different name. or
+ * b. The missing-disk-which-was-replaced, has
+ * reappeared now.
+ *
+ * We must allow 1 and 2a above. But 2b would be a spurious
+ * and unintentional.
+ *
+ * Further in case of 1 and 2a above, the disk at 'path'
+ * would have missed some transaction when it was away and
+ * in case of 2a the stale bdev has to be updated as well.
+ * 2b must not be allowed at all time.
+ */
+
+ /*
+ * As of now don't allow update to btrfs_fs_device through
+ * the btrfs dev scan cli, after FS has been mounted.
+ */
+ if (fs_devices->opened) {
+ return -EBUSY;
+ } else {
+ /*
+ * That is if the FS is _not_ mounted and if you
+ * are here, that means there is more than one
+ * disk with same uuid and devid.We keep the one
+ * with larger generation number or the last-in if
+ * generation are equal.
+ */
+ if (found_transid < device->generation)
+ return -EEXIST;
+ }
+
name = rcu_string_strdup(path, GFP_NOFS);
if (!name)
return -ENOMEM;
}
}
- if (found_transid > fs_devices->latest_trans) {
- fs_devices->latest_devid = devid;
- fs_devices->latest_trans = found_transid;
- }
+ /*
+ * Unmount does not free the btrfs_device struct but would zero
+ * generation along with most of the other members. So just update
+ * it back. We need it to pick the disk with largest generation
+ * (as above).
+ */
+ if (!fs_devices->opened)
+ device->generation = 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;
fs_devices->total_devices = orig->total_devices;
/* We have held the volume lock, it is safe to get the devices. */
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) {
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->total_bytes);
+ 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_group(leaf, dev_item, 0);
btrfs_set_device_seek_speed(leaf, dev_item, 0);
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);
device->fs_devices->total_devices--;
if (device->missing)
- root->fs_info->fs_devices->missing_devices--;
+ device->fs_devices->missing_devices--;
next_device = list_entry(root->fs_info->fs_devices->devices.next,
struct btrfs_device, dev_list);
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--;
+ fs_devices->num_devices--;
if (srcdev->missing) {
- fs_info->fs_devices->missing_devices--;
- fs_info->fs_devices->rw_devices++;
+ fs_devices->missing_devices--;
+ if (!fs_devices->seeding)
+ 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->open_devices--;
- /* zero out the old super */
- btrfs_scratch_superblock(srcdev);
+ /*
+ * zero out the old super if it is not writable
+ * (e.g. seed device)
+ */
+ if (srcdev->writeable)
+ btrfs_scratch_superblock(srcdev);
}
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,
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);
fs_devices->seeding = 0;
fs_devices->num_devices = 0;
fs_devices->open_devices = 0;
+ fs_devices->missing_devices = 0;
+ fs_devices->rotating = 0;
fs_devices->seed = seed_devices;
generate_random_uuid(fs_devices->fsid);
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;
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;
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);
}
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) < srcdev->total_bytes) {
+ 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 = srcdev->total_bytes;
+ device->disk_total_bytes = srcdev->disk_total_bytes;
+ ASSERT(list_empty(&srcdev->resized_list));
+ device->commit_total_bytes = srcdev->commit_total_bytes;
+ device->bytes_used = srcdev->bytes_used;
+ 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;
{
struct btrfs_super_block *super_copy =
device->dev_root->fs_info->super_copy;
+ struct btrfs_fs_devices *fs_devices;
u64 old_total = btrfs_super_total_bytes(super_copy);
u64 diff = new_size - device->total_bytes;
device->is_tgtdev_for_dev_replace)
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_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);
return btrfs_update_device(trans, device);
}
found_key.offset);
if (ret == -ENOSPC)
failed++;
- else if (ret)
- BUG();
+ else
+ BUG_ON(ret);
}
if (found_key.offset == 0)
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) {
}
lock_chunks(root);
-
device->disk_total_bytes = new_size;
+ if (list_empty(&device->resized_list))
+ list_add_tail(&device->resized_list,
+ &root->fs_info->fs_devices->resized_devices);
+
/* Now btrfs_update_device() will change the on-disk size. */
ret = btrfs_update_device(trans, device);
if (ret) {
if (ret)
goto error_del_extent;
+ for (i = 0; i < map->num_stripes; i++)
+ map->stripes[i].dev->bytes_used += stripe_size;
+
+ 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;
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;
+ }
+
+ return max_errors;
+}
+
int btrfs_chunk_readonly(struct btrfs_root *root, u64 chunk_offset)
{
struct extent_map *em;
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;
}
}
}
- 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) {
else
generate_random_uuid(dev->uuid);
- btrfs_init_work(&dev->work, pending_bios_fn, NULL, NULL);
+ btrfs_init_work(&dev->work, btrfs_submit_helper,
+ pending_bios_fn, NULL, NULL);
return dev;
}
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);
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);
+}